mirror of
https://github.com/ceph/ceph-csi.git
synced 2025-05-22 07:16:41 +00:00
rebase: bump the github-dependencies group with 3 updates
Bumps the github-dependencies group with 3 updates: [github.com/Azure/azure-sdk-for-go/sdk/azidentity](https://github.com/Azure/azure-sdk-for-go), [github.com/aws/aws-sdk-go-v2/service/sts](https://github.com/aws/aws-sdk-go-v2) and [github.com/prometheus/client_golang](https://github.com/prometheus/client_golang). Updates `github.com/Azure/azure-sdk-for-go/sdk/azidentity` from 1.8.2 to 1.9.0 - [Release notes](https://github.com/Azure/azure-sdk-for-go/releases) - [Changelog](https://github.com/Azure/azure-sdk-for-go/blob/main/documentation/release.md) - [Commits](https://github.com/Azure/azure-sdk-for-go/compare/sdk/azidentity/v1.8.2...sdk/azcore/v1.9.0) Updates `github.com/aws/aws-sdk-go-v2/service/sts` from 1.33.18 to 1.33.19 - [Release notes](https://github.com/aws/aws-sdk-go-v2/releases) - [Changelog](https://github.com/aws/aws-sdk-go-v2/blob/main/changelog-template.json) - [Commits](https://github.com/aws/aws-sdk-go-v2/compare/service/sns/v1.33.18...service/sns/v1.33.19) Updates `github.com/prometheus/client_golang` from 1.21.1 to 1.22.0 - [Release notes](https://github.com/prometheus/client_golang/releases) - [Changelog](https://github.com/prometheus/client_golang/blob/main/CHANGELOG.md) - [Commits](https://github.com/prometheus/client_golang/compare/v1.21.1...v1.22.0) --- updated-dependencies: - dependency-name: github.com/Azure/azure-sdk-for-go/sdk/azidentity dependency-version: 1.9.0 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: github-dependencies - dependency-name: github.com/aws/aws-sdk-go-v2/service/sts dependency-version: 1.33.19 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: github-dependencies - dependency-name: github.com/prometheus/client_golang dependency-version: 1.22.0 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: github-dependencies ... Signed-off-by: dependabot[bot] <support@github.com>
This commit is contained in:
dependabot[bot]
mergify[bot]
parent
0b811ff8b1
commit
72c19ab743
15
go.mod
15
go.mod
@ -8,11 +8,11 @@ toolchain go1.23.4
|
||||
replace github.com/ceph/ceph-csi/api => ./api
|
||||
|
||||
require (
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.8.2
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.9.0
|
||||
github.com/Azure/azure-sdk-for-go/sdk/security/keyvault/azsecrets v1.3.1
|
||||
github.com/IBM/keyprotect-go-client v0.15.1
|
||||
github.com/aws/aws-sdk-go v1.55.6
|
||||
github.com/aws/aws-sdk-go-v2/service/sts v1.33.18
|
||||
github.com/aws/aws-sdk-go-v2/service/sts v1.33.19
|
||||
github.com/ceph/ceph-csi/api v0.0.0-00010101000000-000000000000
|
||||
github.com/ceph/go-ceph v0.32.1-0.20250307053135-38b9676b1d4e
|
||||
github.com/container-storage-interface/spec v1.11.0
|
||||
@ -27,7 +27,7 @@ require (
|
||||
github.com/kubernetes-csi/csi-lib-utils v0.21.0
|
||||
github.com/libopenstorage/secrets v0.0.0-20231011182615-5f4b25ceede1
|
||||
github.com/pkg/xattr v0.4.10
|
||||
github.com/prometheus/client_golang v1.21.1
|
||||
github.com/prometheus/client_golang v1.22.0
|
||||
github.com/stretchr/testify v1.10.0
|
||||
golang.org/x/crypto v0.37.0
|
||||
golang.org/x/net v0.39.0
|
||||
@ -63,10 +63,10 @@ exclude (
|
||||
)
|
||||
|
||||
require (
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0 // indirect
|
||||
github.com/Azure/azure-sdk-for-go/sdk/internal v1.10.0 // indirect
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azcore v1.18.0 // indirect
|
||||
github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.1 // indirect
|
||||
github.com/Azure/azure-sdk-for-go/sdk/security/keyvault/internal v1.1.1 // indirect
|
||||
github.com/AzureAD/microsoft-authentication-library-for-go v1.3.3 // indirect
|
||||
github.com/AzureAD/microsoft-authentication-library-for-go v1.4.2 // indirect
|
||||
github.com/ansel1/merry v1.6.2 // indirect
|
||||
github.com/ansel1/merry/v2 v2.0.1 // indirect
|
||||
github.com/aws/aws-sdk-go-v2 v1.36.3 // indirect
|
||||
@ -96,7 +96,7 @@ require (
|
||||
github.com/golang-jwt/jwt/v5 v5.2.2 // indirect
|
||||
github.com/google/btree v1.1.3 // indirect
|
||||
github.com/google/gnostic-models v0.6.9 // indirect
|
||||
github.com/google/go-cmp v0.6.0 // indirect
|
||||
github.com/google/go-cmp v0.7.0 // indirect
|
||||
github.com/google/gofuzz v1.2.0 // indirect
|
||||
github.com/hashicorp/errwrap v1.1.0 // indirect
|
||||
github.com/hashicorp/go-cleanhttp v0.5.2 // indirect
|
||||
@ -113,7 +113,6 @@ require (
|
||||
github.com/jmespath/go-jmespath v0.4.0 // indirect
|
||||
github.com/josharian/intern v1.0.0 // indirect
|
||||
github.com/json-iterator/go v1.1.12 // indirect
|
||||
github.com/klauspost/compress v1.17.11 // indirect
|
||||
github.com/kylelemons/godebug v1.1.0 // indirect
|
||||
github.com/mailru/easyjson v0.9.0 // indirect
|
||||
github.com/mattn/go-colorable v0.1.13 // indirect
|
||||
|
||||
39
go.sum
39
go.sum
@ -53,14 +53,14 @@ cloud.google.com/go/storage v1.10.0/go.mod h1:FLPqc6j+Ki4BU591ie1oL6qBQGu2Bl/tZ9
|
||||
dmitri.shuralyov.com/gpu/mtl v0.0.0-20190408044501-666a987793e9/go.mod h1:H6x//7gZCb22OMCxBHrMx7a5I7Hp++hsVxbQ4BYO7hU=
|
||||
github.com/Azure/azure-sdk-for-go v62.0.0+incompatible h1:8N2k27SYtc12qj5nTsuFMFJPZn5CGmgMWqTy4y9I7Jw=
|
||||
github.com/Azure/azure-sdk-for-go v62.0.0+incompatible/go.mod h1:9XXNKU+eRnpl9moKnB4QOLf1HestfXbmab5FXxiDBjc=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0 h1:g0EZJwz7xkXQiZAI5xi9f3WWFYBlX1CPTrR+NDToRkQ=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0/go.mod h1:XCW7KnZet0Opnr7HccfUw1PLc4CjHqpcaxW8DHklNkQ=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.8.2 h1:F0gBpfdPLGsw+nsgk6aqqkZS1jiixa5WwFe3fk/T3Ys=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.8.2/go.mod h1:SqINnQ9lVVdRlyC8cd1lCI0SdX4n2paeABd2K8ggfnE=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azcore v1.18.0 h1:Gt0j3wceWMwPmiazCa8MzMA0MfhmPIz0Qp0FJ6qcM0U=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azcore v1.18.0/go.mod h1:Ot/6aikWnKWi4l9QB7qVSwa8iMphQNqkWALMoNT3rzM=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.9.0 h1:OVoM452qUFBrX+URdH3VpR299ma4kfom0yB0URYky9g=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.9.0/go.mod h1:kUjrAo8bgEwLeZ/CmHqNl3Z/kPm7y6FKfxxK0izYUg4=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azidentity/cache v0.3.2 h1:yz1bePFlP5Vws5+8ez6T3HWXPmwOK7Yvq8QxDBD3SKY=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/azidentity/cache v0.3.2/go.mod h1:Pa9ZNPuoNu/GztvBSKk9J1cDJW6vk/n0zLtV4mgd8N8=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/internal v1.10.0 h1:ywEEhmNahHBihViHepv3xPBn1663uRv2t2q/ESv9seY=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/internal v1.10.0/go.mod h1:iZDifYGJTIgIIkYRNWPENUnqx6bJ2xnSDFI2tjwZNuY=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.1 h1:FPKJS1T+clwv+OLGt13a8UjqeRuh0O4SJ3lUriThc+4=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.1/go.mod h1:j2chePtV91HrC22tGoRX3sGY42uF13WzmmV80/OdVAA=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/security/keyvault/azsecrets v1.3.1 h1:mrkDCdkMsD4l9wjFGhofFHFrV43Y3c53RSLKOCJ5+Ow=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/security/keyvault/azsecrets v1.3.1/go.mod h1:hPv41DbqMmnxcGralanA/kVlfdH5jv3T4LxGku2E1BY=
|
||||
github.com/Azure/azure-sdk-for-go/sdk/security/keyvault/internal v1.1.1 h1:bFWuoEKg+gImo7pvkiQEFAc8ocibADgXeiLAxWhWmkI=
|
||||
@ -78,8 +78,8 @@ github.com/Azure/go-autorest/logger v0.2.1/go.mod h1:T9E3cAhj2VqvPOtCYAvby9aBXkZ
|
||||
github.com/Azure/go-autorest/tracing v0.6.0/go.mod h1:+vhtPC754Xsa23ID7GlGsrdKBpUA79WCAKPPZVC2DeU=
|
||||
github.com/AzureAD/microsoft-authentication-extensions-for-go/cache v0.1.1 h1:WJTmL004Abzc5wDB5VtZG2PJk5ndYDgVacGqfirKxjM=
|
||||
github.com/AzureAD/microsoft-authentication-extensions-for-go/cache v0.1.1/go.mod h1:tCcJZ0uHAmvjsVYzEFivsRTN00oz5BEsRgQHu5JZ9WE=
|
||||
github.com/AzureAD/microsoft-authentication-library-for-go v1.3.3 h1:H5xDQaE3XowWfhZRUpnfC+rGZMEVoSiji+b+/HFAPU4=
|
||||
github.com/AzureAD/microsoft-authentication-library-for-go v1.3.3/go.mod h1:wP83P5OoQ5p6ip3ScPr0BAq0BvuPAvacpEuSzyouqAI=
|
||||
github.com/AzureAD/microsoft-authentication-library-for-go v1.4.2 h1:oygO0locgZJe7PpYPXT5A29ZkwJaPqcva7BVeemZOZs=
|
||||
github.com/AzureAD/microsoft-authentication-library-for-go v1.4.2/go.mod h1:wP83P5OoQ5p6ip3ScPr0BAq0BvuPAvacpEuSzyouqAI=
|
||||
github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
|
||||
github.com/BurntSushi/xgb v0.0.0-20160522181843-27f122750802/go.mod h1:IVnqGOEym/WlBOVXweHU+Q+/VP0lqqI8lqeDx9IjBqo=
|
||||
github.com/IBM/keyprotect-go-client v0.5.1/go.mod h1:5TwDM/4FRJq1ZOlwQL1xFahLWQ3TveR88VmL1u3njyI=
|
||||
@ -118,8 +118,8 @@ github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.12.3 h1:eAh2A4b
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.12.3/go.mod h1:0yKJC/kb8sAnmlYa6Zs3QVYqaC8ug2AbnNChv5Ox3uA=
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.12.15 h1:dM9/92u2F1JbDaGooxTq18wmmFzbJRfXfVfy96/1CXM=
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.12.15/go.mod h1:SwFBy2vjtA0vZbjjaFtfN045boopadnoVPhu4Fv66vY=
|
||||
github.com/aws/aws-sdk-go-v2/service/sts v1.33.18 h1:xz7WvTMfSStb9Y8NpCT82FXLNC3QasqBfuAFHY4Pk5g=
|
||||
github.com/aws/aws-sdk-go-v2/service/sts v1.33.18/go.mod h1:cQnB8CUnxbMU82JvlqjKR2HBOm3fe9pWorWBza6MBJ4=
|
||||
github.com/aws/aws-sdk-go-v2/service/sts v1.33.19 h1:1XuUZ8mYJw9B6lzAkXhqHlJd/XvaX32evhproijJEZY=
|
||||
github.com/aws/aws-sdk-go-v2/service/sts v1.33.19/go.mod h1:cQnB8CUnxbMU82JvlqjKR2HBOm3fe9pWorWBza6MBJ4=
|
||||
github.com/aws/smithy-go v1.22.3 h1:Z//5NuZCSW6R4PhQ93hShNbyBbn8BWCmCVCt+Q8Io5k=
|
||||
github.com/aws/smithy-go v1.22.3/go.mod h1:t1ufH5HMublsJYulve2RKmHDC15xu1f26kHCp/HgceI=
|
||||
github.com/benbjohnson/clock v1.1.0/go.mod h1:J11/hYXuz8f4ySSvYwY0FKfm+ezbsZBKZxNJlLklBHA=
|
||||
@ -333,8 +333,9 @@ github.com/google/go-cmp v0.5.6/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/
|
||||
github.com/google/go-cmp v0.5.7/go.mod h1:n+brtR0CgQNWTVd5ZUFpTBC8YFBDLK/h/bpaJ8/DtOE=
|
||||
github.com/google/go-cmp v0.5.8/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
|
||||
github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
|
||||
github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
|
||||
github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
|
||||
github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
|
||||
github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
|
||||
github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
|
||||
github.com/google/gofuzz v1.1.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
|
||||
github.com/google/gofuzz v1.2.0 h1:xRy4A+RhZaiKjJ1bPfwQ8sedCA+YS2YcCHW6ec7JMi0=
|
||||
@ -444,12 +445,12 @@ github.com/jstemmer/go-junit-report v0.0.0-20190106144839-af01ea7f8024/go.mod h1
|
||||
github.com/jstemmer/go-junit-report v0.9.1/go.mod h1:Brl9GWCQeLvo8nXZwPNNblvFj/XSXhF0NWZEnDohbsk=
|
||||
github.com/k0kubun/colorstring v0.0.0-20150214042306-9440f1994b88/go.mod h1:3w7q1U84EfirKl04SVQ/s7nPm1ZPhiXd34z40TNz36k=
|
||||
github.com/k0kubun/pp v2.3.0+incompatible/go.mod h1:GWse8YhT0p8pT4ir3ZgBbfZild3tgzSScAn6HmfYukg=
|
||||
github.com/keybase/go-keychain v0.0.0-20231219164618-57a3676c3af6 h1:IsMZxCuZqKuao2vNdfD82fjjgPLfyHLpR41Z88viRWs=
|
||||
github.com/keybase/go-keychain v0.0.0-20231219164618-57a3676c3af6/go.mod h1:3VeWNIJaW+O5xpRQbPp0Ybqu1vJd/pm7s2F473HRrkw=
|
||||
github.com/keybase/go-keychain v0.0.1 h1:way+bWYa6lDppZoZcgMbYsvC7GxljxrskdNInRtuthU=
|
||||
github.com/keybase/go-keychain v0.0.1/go.mod h1:PdEILRW3i9D8JcdM+FmY6RwkHGnhHxXwkPPMeUgOK1k=
|
||||
github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
|
||||
github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
|
||||
github.com/klauspost/compress v1.17.11 h1:In6xLpyWOi1+C7tXUUWv2ot1QvBjxevKAaI6IXrJmUc=
|
||||
github.com/klauspost/compress v1.17.11/go.mod h1:pMDklpSncoRMuLFrf1W9Ss9KT+0rH90U12bZKk7uwG0=
|
||||
github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo=
|
||||
github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYWRCY2AiWywWQ=
|
||||
github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
|
||||
github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
|
||||
github.com/kr/pretty v0.2.0/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
|
||||
@ -596,8 +597,8 @@ github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH
|
||||
github.com/portworx/dcos-secrets v0.0.0-20180616013705-8e8ec3f66611/go.mod h1:4hklRW/4DQpLqkcXcjtNprbH2tz/sJaNtqinfPWl/LA=
|
||||
github.com/portworx/kvdb v0.0.0-20200929023115-b312c7519467/go.mod h1:Q8YyrNDvPp3DVF96BDcQuaC7fAYUCuUX+l58S7OnD2M=
|
||||
github.com/posener/complete v1.1.1/go.mod h1:em0nMJCgc9GFtwrmVmEMR/ZL6WyhyjMBndrE9hABlRI=
|
||||
github.com/prometheus/client_golang v1.21.1 h1:DOvXXTqVzvkIewV/CDPFdejpMCGeMcbGCQ8YOmu+Ibk=
|
||||
github.com/prometheus/client_golang v1.21.1/go.mod h1:U9NM32ykUErtVBxdvD3zfi+EuFkkaBvMb09mIfe0Zgg=
|
||||
github.com/prometheus/client_golang v1.22.0 h1:rb93p9lokFEsctTys46VnV1kLCDpVZ0a/Y92Vm0Zc6Q=
|
||||
github.com/prometheus/client_golang v1.22.0/go.mod h1:R7ljNsLXhuQXYZYtw6GAE9AZg8Y7vEW5scdCXrWRXC0=
|
||||
github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
|
||||
github.com/prometheus/client_model v0.6.1 h1:ZKSh/rekM+n3CeS952MLRAdFwIKqeY8b62p8ais2e9E=
|
||||
github.com/prometheus/client_model v0.6.1/go.mod h1:OrxVMOVHjw3lKMa8+x6HeMGkHMQyHDk9E3jmP2AmGiY=
|
||||
@ -605,8 +606,8 @@ github.com/prometheus/common v0.62.0 h1:xasJaQlnWAeyHdUBeGjXmutelfJHWMRr+Fg4QszZ
|
||||
github.com/prometheus/common v0.62.0/go.mod h1:vyBcEuLSvWos9B1+CyL7JZ2up+uFzXhkqml0W5zIY1I=
|
||||
github.com/prometheus/procfs v0.15.1 h1:YagwOFzUgYfKKHX6Dr+sHT7km/hxC76UB0learggepc=
|
||||
github.com/prometheus/procfs v0.15.1/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoGhij/e3PBqk=
|
||||
github.com/redis/go-redis/v9 v9.7.0 h1:HhLSs+B6O021gwzl+locl0zEDnyNkxMtf/Z3NNBMa9E=
|
||||
github.com/redis/go-redis/v9 v9.7.0/go.mod h1:f6zhXITC7JUJIlPEiBOTXxJgPLdZcA93GewI7inzyWw=
|
||||
github.com/redis/go-redis/v9 v9.7.3 h1:YpPyAayJV+XErNsatSElgRZZVCwXX9QzkKYNvO7x0wM=
|
||||
github.com/redis/go-redis/v9 v9.7.3/go.mod h1:bGUrSggJ9X9GUmZpZNEOQKaANxSGgOEBRltRTZHSvrA=
|
||||
github.com/rogpeppe/fastuuid v1.2.0/go.mod h1:jVj6XXZzXRy/MSR5jhDC/2q6DgLz+nrA6LYCDYWNEvQ=
|
||||
github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
|
||||
github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=
|
||||
|
||||
14
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/CHANGELOG.md
generated
vendored
14
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/CHANGELOG.md
generated
vendored
@ -1,5 +1,19 @@
|
||||
# Release History
|
||||
|
||||
## 1.18.0 (2025-04-03)
|
||||
|
||||
### Features Added
|
||||
|
||||
* Added `AccessToken.RefreshOn` and updated `BearerTokenPolicy` to consider nonzero values of it when deciding whether to request a new token
|
||||
|
||||
|
||||
## 1.17.1 (2025-03-20)
|
||||
|
||||
### Other Changes
|
||||
|
||||
* Upgraded to Go 1.23
|
||||
* Upgraded dependencies
|
||||
|
||||
## 1.17.0 (2025-01-07)
|
||||
|
||||
### Features Added
|
||||
|
||||
5
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/exported/exported.go
generated
vendored
5
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/exported/exported.go
generated
vendored
@ -47,8 +47,13 @@ func HasStatusCode(resp *http.Response, statusCodes ...int) bool {
|
||||
// AccessToken represents an Azure service bearer access token with expiry information.
|
||||
// Exported as azcore.AccessToken.
|
||||
type AccessToken struct {
|
||||
// Token is the access token
|
||||
Token string
|
||||
// ExpiresOn indicates when the token expires
|
||||
ExpiresOn time.Time
|
||||
// RefreshOn is a suggested time to refresh the token.
|
||||
// Clients should ignore this value when it's zero.
|
||||
RefreshOn time.Time
|
||||
}
|
||||
|
||||
// TokenRequestOptions contain specific parameter that may be used by credentials types when attempting to get a token.
|
||||
|
||||
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/shared/constants.go
generated
vendored
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/internal/shared/constants.go
generated
vendored
@ -40,5 +40,5 @@ const (
|
||||
Module = "azcore"
|
||||
|
||||
// Version is the semantic version (see http://semver.org) of this module.
|
||||
Version = "v1.17.0"
|
||||
Version = "v1.18.0"
|
||||
)
|
||||
|
||||
14
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_bearer_token.go
generated
vendored
14
vendor/github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime/policy_bearer_token.go
generated
vendored
@ -51,6 +51,15 @@ func acquire(state acquiringResourceState) (newResource exported.AccessToken, ne
|
||||
return tk, tk.ExpiresOn, nil
|
||||
}
|
||||
|
||||
// shouldRefresh determines whether the token should be refreshed. It's a variable so tests can replace it.
|
||||
var shouldRefresh = func(tk exported.AccessToken, _ acquiringResourceState) bool {
|
||||
if tk.RefreshOn.IsZero() {
|
||||
return tk.ExpiresOn.Add(-5 * time.Minute).Before(time.Now())
|
||||
}
|
||||
// no offset in this case because the authority suggested a refresh window--between RefreshOn and ExpiresOn
|
||||
return tk.RefreshOn.Before(time.Now())
|
||||
}
|
||||
|
||||
// NewBearerTokenPolicy creates a policy object that authorizes requests with bearer tokens.
|
||||
// cred: an azcore.TokenCredential implementation such as a credential object from azidentity
|
||||
// scopes: the list of permission scopes required for the token.
|
||||
@ -69,11 +78,14 @@ func NewBearerTokenPolicy(cred exported.TokenCredential, scopes []string, opts *
|
||||
return authNZ(policy.TokenRequestOptions{Scopes: scopes})
|
||||
}
|
||||
}
|
||||
mr := temporal.NewResourceWithOptions(acquire, temporal.ResourceOptions[exported.AccessToken, acquiringResourceState]{
|
||||
ShouldRefresh: shouldRefresh,
|
||||
})
|
||||
return &BearerTokenPolicy{
|
||||
authzHandler: ah,
|
||||
cred: cred,
|
||||
scopes: scopes,
|
||||
mainResource: temporal.NewResource(acquire),
|
||||
mainResource: mr,
|
||||
allowHTTP: opts.InsecureAllowCredentialWithHTTP,
|
||||
}
|
||||
}
|
||||
|
||||
12
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/CHANGELOG.md
generated
vendored
12
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/CHANGELOG.md
generated
vendored
@ -1,5 +1,17 @@
|
||||
# Release History
|
||||
|
||||
## 1.9.0 (2025-04-08)
|
||||
|
||||
### Features Added
|
||||
* `GetToken()` sets `AccessToken.RefreshOn` when the token provider specifies a value
|
||||
|
||||
### Other Changes
|
||||
* `NewManagedIdentityCredential` logs the configured user-assigned identity, if any
|
||||
* Deprecated `UsernamePasswordCredential` because it can't support multifactor
|
||||
authentication (MFA), which Microsoft Entra ID requires for most tenants. See
|
||||
https://aka.ms/azsdk/identity/mfa for migration guidance.
|
||||
* Updated dependencies
|
||||
|
||||
## 1.8.2 (2025-02-12)
|
||||
|
||||
### Other Changes
|
||||
|
||||
18
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/README.md
generated
vendored
18
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/README.md
generated
vendored
@ -21,7 +21,7 @@ go get -u github.com/Azure/azure-sdk-for-go/sdk/azidentity
|
||||
## Prerequisites
|
||||
|
||||
- an [Azure subscription](https://azure.microsoft.com/free/)
|
||||
- Go 1.18
|
||||
- [Supported](https://aka.ms/azsdk/go/supported-versions) version of Go
|
||||
|
||||
### Authenticating during local development
|
||||
|
||||
@ -146,7 +146,6 @@ client := armresources.NewResourceGroupsClient("subscription ID", chain, nil)
|
||||
|-|-
|
||||
|[InteractiveBrowserCredential](https://pkg.go.dev/github.com/Azure/azure-sdk-for-go/sdk/azidentity#InteractiveBrowserCredential)|Interactively authenticate a user with the default web browser
|
||||
|[DeviceCodeCredential](https://pkg.go.dev/github.com/Azure/azure-sdk-for-go/sdk/azidentity#DeviceCodeCredential)|Interactively authenticate a user on a device with limited UI
|
||||
|[UsernamePasswordCredential](https://pkg.go.dev/github.com/Azure/azure-sdk-for-go/sdk/azidentity#UsernamePasswordCredential)|Authenticate a user with a username and password
|
||||
|
||||
### Authenticating via Development Tools
|
||||
|
||||
@ -159,7 +158,7 @@ client := armresources.NewResourceGroupsClient("subscription ID", chain, nil)
|
||||
|
||||
`DefaultAzureCredential` and `EnvironmentCredential` can be configured with environment variables. Each type of authentication requires values for specific variables:
|
||||
|
||||
#### Service principal with secret
|
||||
### Service principal with secret
|
||||
|
||||
|variable name|value
|
||||
|-|-
|
||||
@ -167,7 +166,7 @@ client := armresources.NewResourceGroupsClient("subscription ID", chain, nil)
|
||||
|`AZURE_TENANT_ID`|ID of the application's Microsoft Entra tenant
|
||||
|`AZURE_CLIENT_SECRET`|one of the application's client secrets
|
||||
|
||||
#### Service principal with certificate
|
||||
### Service principal with certificate
|
||||
|
||||
|variable name|value
|
||||
|-|-
|
||||
@ -176,16 +175,7 @@ client := armresources.NewResourceGroupsClient("subscription ID", chain, nil)
|
||||
|`AZURE_CLIENT_CERTIFICATE_PATH`|path to a certificate file including private key
|
||||
|`AZURE_CLIENT_CERTIFICATE_PASSWORD`|password of the certificate file, if any
|
||||
|
||||
#### Username and password
|
||||
|
||||
|variable name|value
|
||||
|-|-
|
||||
|`AZURE_CLIENT_ID`|ID of a Microsoft Entra application
|
||||
|`AZURE_USERNAME`|a username (usually an email address)
|
||||
|`AZURE_PASSWORD`|that user's password
|
||||
|
||||
Configuration is attempted in the above order. For example, if values for a
|
||||
client secret and certificate are both present, the client secret will be used.
|
||||
Configuration is attempted in the above order. For example, if values for a client secret and certificate are both present, the client secret will be used.
|
||||
|
||||
## Token caching
|
||||
|
||||
|
||||
11
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/TOKEN_CACHING.MD
generated
vendored
11
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/TOKEN_CACHING.MD
generated
vendored
@ -22,12 +22,11 @@ Some credential types support opt-in persistent token caching (see [the below ta
|
||||
|
||||
Persistent caches are encrypted at rest using a mechanism that depends on the operating system:
|
||||
|
||||
| Operating system | Encryption facility |
|
||||
| ---------------- | ---------------------------------------------- |
|
||||
| Linux | kernel key retention service (keyctl) |
|
||||
| macOS | Keychain (requires cgo and native build tools) |
|
||||
| Windows | Data Protection API (DPAPI) |
|
||||
|
||||
| Operating system | Encryption facility | Limitations |
|
||||
| ---------------- | ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| Linux | kernel key retention service (keyctl) | Cache data is lost on system shutdown because kernel keys are stored in memory. Depending on kernel compile options, data may also be lost on logout, or storage may be impossible because the key retention service isn't available. |
|
||||
| macOS | Keychain | Building requires cgo and native build tools. Keychain access requires a graphical session, so persistent caching isn't possible in a headless environment such as an SSH session (macOS as host). |
|
||||
| Windows | Data Protection API (DPAPI) | No specific limitations. |
|
||||
Persistent caching requires encryption. When the required encryption facility is unuseable, or the application is running on an unsupported OS, the persistent cache constructor returns an error. This doesn't mean that authentication is impossible, only that credentials can't persist authentication data and the application will need to reauthenticate the next time it runs. See the package documentation for examples showing how to configure persistent caching and access cached data for [users][user_example] and [service principals][sp_example].
|
||||
|
||||
### Credentials supporting token caching
|
||||
|
||||
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/assets.json
generated
vendored
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/assets.json
generated
vendored
@ -2,5 +2,5 @@
|
||||
"AssetsRepo": "Azure/azure-sdk-assets",
|
||||
"AssetsRepoPrefixPath": "go",
|
||||
"TagPrefix": "go/azidentity",
|
||||
"Tag": "go/azidentity_c55452bbf6"
|
||||
"Tag": "go/azidentity_191110b0dd"
|
||||
}
|
||||
|
||||
5
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/azidentity.go
generated
vendored
5
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/azidentity.go
generated
vendored
@ -22,6 +22,7 @@ import (
|
||||
"github.com/Azure/azure-sdk-for-go/sdk/azcore/streaming"
|
||||
"github.com/Azure/azure-sdk-for-go/sdk/azidentity/internal"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/confidential"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/managedidentity"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/public"
|
||||
)
|
||||
|
||||
@ -208,6 +209,10 @@ type msalConfidentialClient interface {
|
||||
AcquireTokenOnBehalfOf(ctx context.Context, userAssertion string, scopes []string, options ...confidential.AcquireOnBehalfOfOption) (confidential.AuthResult, error)
|
||||
}
|
||||
|
||||
type msalManagedIdentityClient interface {
|
||||
AcquireToken(context.Context, string, ...managedidentity.AcquireTokenOption) (managedidentity.AuthResult, error)
|
||||
}
|
||||
|
||||
// enables fakes for test scenarios
|
||||
type msalPublicClient interface {
|
||||
AcquireTokenSilent(ctx context.Context, scopes []string, options ...public.AcquireSilentOption) (public.AuthResult, error)
|
||||
|
||||
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/confidential_client.go
generated
vendored
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/confidential_client.go
generated
vendored
@ -118,7 +118,7 @@ func (c *confidentialClient) GetToken(ctx context.Context, tro policy.TokenReque
|
||||
msg := fmt.Sprintf(scopeLogFmt, c.name, strings.Join(ar.GrantedScopes, ", "))
|
||||
log.Write(EventAuthentication, msg)
|
||||
}
|
||||
return azcore.AccessToken{Token: ar.AccessToken, ExpiresOn: ar.ExpiresOn.UTC()}, err
|
||||
return azcore.AccessToken{Token: ar.AccessToken, ExpiresOn: ar.ExpiresOn.UTC(), RefreshOn: ar.Metadata.RefreshOn.UTC()}, err
|
||||
}
|
||||
|
||||
func (c *confidentialClient) client(tro policy.TokenRequestOptions) (msalConfidentialClient, *sync.Mutex, error) {
|
||||
|
||||
7
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/environment_credential.go
generated
vendored
7
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/environment_credential.go
generated
vendored
@ -60,7 +60,10 @@ type EnvironmentCredentialOptions struct {
|
||||
// Note that this credential uses [ParseCertificates] to load the certificate and key from the file. If this
|
||||
// function isn't able to parse your certificate, use [ClientCertificateCredential] instead.
|
||||
//
|
||||
// # User with username and password
|
||||
// # Deprecated: User with username and password
|
||||
//
|
||||
// User password authentication is deprecated because it can't support multifactor authentication. See
|
||||
// [Entra ID documentation] for migration guidance.
|
||||
//
|
||||
// AZURE_TENANT_ID: (optional) tenant to authenticate in. Defaults to "organizations".
|
||||
//
|
||||
@ -75,6 +78,8 @@ type EnvironmentCredentialOptions struct {
|
||||
// To enable multitenant authentication, set AZURE_ADDITIONALLY_ALLOWED_TENANTS with a semicolon delimited list of tenants
|
||||
// the credential may request tokens from in addition to the tenant specified by AZURE_TENANT_ID. Set
|
||||
// AZURE_ADDITIONALLY_ALLOWED_TENANTS to "*" to enable the credential to request a token from any tenant.
|
||||
//
|
||||
// [Entra ID documentation]: https://aka.ms/azsdk/identity/mfa
|
||||
type EnvironmentCredential struct {
|
||||
cred azcore.TokenCredential
|
||||
}
|
||||
|
||||
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/go.work
generated
vendored
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/go.work
generated
vendored
@ -1,4 +1,4 @@
|
||||
go 1.18
|
||||
go 1.23.0
|
||||
|
||||
use (
|
||||
.
|
||||
|
||||
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/managed-identity-matrix.json
generated
vendored
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/managed-identity-matrix.json
generated
vendored
@ -9,7 +9,7 @@
|
||||
}
|
||||
},
|
||||
"GoVersion": [
|
||||
"1.22.1"
|
||||
"env:GO_VERSION_PREVIOUS"
|
||||
],
|
||||
"IDENTITY_IMDS_AVAILABLE": "1"
|
||||
}
|
||||
|
||||
419
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/managed_identity_client.go
generated
vendored
419
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/managed_identity_client.go
generated
vendored
@ -8,24 +8,18 @@ package azidentity
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/Azure/azure-sdk-for-go/sdk/azcore"
|
||||
"github.com/Azure/azure-sdk-for-go/sdk/azcore/policy"
|
||||
azruntime "github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime"
|
||||
"github.com/Azure/azure-sdk-for-go/sdk/azcore/streaming"
|
||||
"github.com/Azure/azure-sdk-for-go/sdk/internal/log"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/confidential"
|
||||
msalerrors "github.com/AzureAD/microsoft-authentication-library-for-go/apps/errors"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/managedidentity"
|
||||
)
|
||||
|
||||
const (
|
||||
@ -41,59 +35,20 @@ const (
|
||||
msiResID = "msi_res_id"
|
||||
msiSecret = "MSI_SECRET"
|
||||
imdsAPIVersion = "2018-02-01"
|
||||
azureArcAPIVersion = "2019-08-15"
|
||||
azureArcAPIVersion = "2020-06-01"
|
||||
qpClientID = "client_id"
|
||||
serviceFabricAPIVersion = "2019-07-01-preview"
|
||||
)
|
||||
|
||||
var imdsProbeTimeout = time.Second
|
||||
|
||||
type msiType int
|
||||
|
||||
const (
|
||||
msiTypeAppService msiType = iota
|
||||
msiTypeAzureArc
|
||||
msiTypeAzureML
|
||||
msiTypeCloudShell
|
||||
msiTypeIMDS
|
||||
msiTypeServiceFabric
|
||||
)
|
||||
|
||||
type managedIdentityClient struct {
|
||||
azClient *azcore.Client
|
||||
endpoint string
|
||||
id ManagedIDKind
|
||||
msiType msiType
|
||||
probeIMDS bool
|
||||
imds, probeIMDS, userAssigned bool
|
||||
// chained indicates whether the client is part of a credential chain. If true, the client will return
|
||||
// a credentialUnavailableError instead of an AuthenticationFailedError for an unexpected IMDS response.
|
||||
chained bool
|
||||
}
|
||||
|
||||
// arcKeyDirectory returns the directory expected to contain Azure Arc keys
|
||||
var arcKeyDirectory = func() (string, error) {
|
||||
switch runtime.GOOS {
|
||||
case "linux":
|
||||
return "/var/opt/azcmagent/tokens", nil
|
||||
case "windows":
|
||||
pd := os.Getenv("ProgramData")
|
||||
if pd == "" {
|
||||
return "", errors.New("environment variable ProgramData has no value")
|
||||
}
|
||||
return filepath.Join(pd, "AzureConnectedMachineAgent", "Tokens"), nil
|
||||
default:
|
||||
return "", fmt.Errorf("unsupported OS %q", runtime.GOOS)
|
||||
}
|
||||
}
|
||||
|
||||
type wrappedNumber json.Number
|
||||
|
||||
func (n *wrappedNumber) UnmarshalJSON(b []byte) error {
|
||||
c := string(b)
|
||||
if c == "\"\"" {
|
||||
return nil
|
||||
}
|
||||
return json.Unmarshal(b, (*json.Number)(n))
|
||||
msalClient msalManagedIdentityClient
|
||||
}
|
||||
|
||||
// setIMDSRetryOptionDefaults sets zero-valued fields to default values appropriate for IMDS
|
||||
@ -141,51 +96,20 @@ func newManagedIdentityClient(options *ManagedIdentityCredentialOptions) (*manag
|
||||
options = &ManagedIdentityCredentialOptions{}
|
||||
}
|
||||
cp := options.ClientOptions
|
||||
c := managedIdentityClient{id: options.ID, endpoint: imdsEndpoint, msiType: msiTypeIMDS}
|
||||
env := "IMDS"
|
||||
if endpoint, ok := os.LookupEnv(identityEndpoint); ok {
|
||||
if _, ok := os.LookupEnv(identityHeader); ok {
|
||||
if _, ok := os.LookupEnv(identityServerThumbprint); ok {
|
||||
if options.ID != nil {
|
||||
return nil, errors.New("the Service Fabric API doesn't support specifying a user-assigned identity at runtime. The identity is determined by cluster resource configuration. See https://aka.ms/servicefabricmi")
|
||||
c := managedIdentityClient{}
|
||||
source, err := managedidentity.GetSource()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
env = "Service Fabric"
|
||||
c.endpoint = endpoint
|
||||
c.msiType = msiTypeServiceFabric
|
||||
} else {
|
||||
env = "App Service"
|
||||
c.endpoint = endpoint
|
||||
c.msiType = msiTypeAppService
|
||||
}
|
||||
} else if _, ok := os.LookupEnv(arcIMDSEndpoint); ok {
|
||||
if options.ID != nil {
|
||||
return nil, errors.New("the Azure Arc API doesn't support specifying a user-assigned managed identity at runtime")
|
||||
}
|
||||
env = "Azure Arc"
|
||||
c.endpoint = endpoint
|
||||
c.msiType = msiTypeAzureArc
|
||||
}
|
||||
} else if endpoint, ok := os.LookupEnv(msiEndpoint); ok {
|
||||
c.endpoint = endpoint
|
||||
if _, ok := os.LookupEnv(msiSecret); ok {
|
||||
if options.ID != nil && options.ID.idKind() != miClientID {
|
||||
return nil, errors.New("the Azure ML API supports specifying a user-assigned managed identity by client ID only")
|
||||
}
|
||||
env = "Azure ML"
|
||||
c.msiType = msiTypeAzureML
|
||||
} else {
|
||||
if options.ID != nil {
|
||||
return nil, errors.New("the Cloud Shell API doesn't support user-assigned managed identities")
|
||||
}
|
||||
env = "Cloud Shell"
|
||||
c.msiType = msiTypeCloudShell
|
||||
}
|
||||
} else {
|
||||
env := string(source)
|
||||
if source == managedidentity.DefaultToIMDS {
|
||||
env = "IMDS"
|
||||
c.imds = true
|
||||
c.probeIMDS = options.dac
|
||||
setIMDSRetryOptionDefaults(&cp.Retry)
|
||||
}
|
||||
|
||||
client, err := azcore.NewClient(module, version, azruntime.PipelineOptions{
|
||||
c.azClient, err = azcore.NewClient(module, version, azruntime.PipelineOptions{
|
||||
Tracing: azruntime.TracingOptions{
|
||||
Namespace: traceNamespace,
|
||||
},
|
||||
@ -193,28 +117,53 @@ func newManagedIdentityClient(options *ManagedIdentityCredentialOptions) (*manag
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
c.azClient = client
|
||||
|
||||
id := managedidentity.SystemAssigned()
|
||||
if options.ID != nil {
|
||||
c.userAssigned = true
|
||||
switch s := options.ID.String(); options.ID.idKind() {
|
||||
case miClientID:
|
||||
id = managedidentity.UserAssignedClientID(s)
|
||||
case miObjectID:
|
||||
id = managedidentity.UserAssignedObjectID(s)
|
||||
case miResourceID:
|
||||
id = managedidentity.UserAssignedResourceID(s)
|
||||
}
|
||||
}
|
||||
msalClient, err := managedidentity.New(id, managedidentity.WithHTTPClient(&c), managedidentity.WithRetryPolicyDisabled())
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
c.msalClient = &msalClient
|
||||
|
||||
if log.Should(EventAuthentication) {
|
||||
log.Writef(EventAuthentication, "Managed Identity Credential will use %s managed identity", env)
|
||||
msg := fmt.Sprintf("%s will use %s managed identity", credNameManagedIdentity, env)
|
||||
if options.ID != nil {
|
||||
kind := "client"
|
||||
switch options.ID.(type) {
|
||||
case ObjectID:
|
||||
kind = "object"
|
||||
case ResourceID:
|
||||
kind = "resource"
|
||||
}
|
||||
msg += fmt.Sprintf(" with %s ID %q", kind, options.ID.String())
|
||||
}
|
||||
log.Write(EventAuthentication, msg)
|
||||
}
|
||||
|
||||
return &c, nil
|
||||
}
|
||||
|
||||
// provideToken acquires a token for MSAL's confidential.Client, which caches the token
|
||||
func (c *managedIdentityClient) provideToken(ctx context.Context, params confidential.TokenProviderParameters) (confidential.TokenProviderResult, error) {
|
||||
result := confidential.TokenProviderResult{}
|
||||
tk, err := c.authenticate(ctx, c.id, params.Scopes)
|
||||
if err == nil {
|
||||
result.AccessToken = tk.Token
|
||||
result.ExpiresInSeconds = int(time.Until(tk.ExpiresOn).Seconds())
|
||||
func (*managedIdentityClient) CloseIdleConnections() {
|
||||
// do nothing
|
||||
}
|
||||
return result, err
|
||||
|
||||
func (c *managedIdentityClient) Do(r *http.Request) (*http.Response, error) {
|
||||
return doForClient(c.azClient, r)
|
||||
}
|
||||
|
||||
// authenticate acquires an access token
|
||||
func (c *managedIdentityClient) authenticate(ctx context.Context, id ManagedIDKind, scopes []string) (azcore.AccessToken, error) {
|
||||
func (c *managedIdentityClient) GetToken(ctx context.Context, tro policy.TokenRequestOptions) (azcore.AccessToken, error) {
|
||||
// no need to synchronize around this value because it's true only when DefaultAzureCredential constructed the client,
|
||||
// and in that case ChainedTokenCredential.GetToken synchronizes goroutines that would execute this block
|
||||
if c.probeIMDS {
|
||||
@ -222,7 +171,7 @@ func (c *managedIdentityClient) authenticate(ctx context.Context, id ManagedIDKi
|
||||
cx, cancel := context.WithTimeout(ctx, imdsProbeTimeout)
|
||||
defer cancel()
|
||||
cx = policy.WithRetryOptions(cx, policy.RetryOptions{MaxRetries: -1})
|
||||
req, err := azruntime.NewRequest(cx, http.MethodGet, c.endpoint)
|
||||
req, err := azruntime.NewRequest(cx, http.MethodGet, imdsEndpoint)
|
||||
if err != nil {
|
||||
return azcore.AccessToken{}, fmt.Errorf("failed to create IMDS probe request: %s", err)
|
||||
}
|
||||
@ -237,32 +186,26 @@ func (c *managedIdentityClient) authenticate(ctx context.Context, id ManagedIDKi
|
||||
c.probeIMDS = false
|
||||
}
|
||||
|
||||
msg, err := c.createAuthRequest(ctx, id, scopes)
|
||||
if err != nil {
|
||||
return azcore.AccessToken{}, err
|
||||
ar, err := c.msalClient.AcquireToken(ctx, tro.Scopes[0], managedidentity.WithClaims(tro.Claims))
|
||||
if err == nil {
|
||||
msg := fmt.Sprintf(scopeLogFmt, credNameManagedIdentity, strings.Join(ar.GrantedScopes, ", "))
|
||||
log.Write(EventAuthentication, msg)
|
||||
return azcore.AccessToken{Token: ar.AccessToken, ExpiresOn: ar.ExpiresOn.UTC(), RefreshOn: ar.Metadata.RefreshOn.UTC()}, err
|
||||
}
|
||||
|
||||
resp, err := c.azClient.Pipeline().Do(msg)
|
||||
if err != nil {
|
||||
return azcore.AccessToken{}, newAuthenticationFailedError(credNameManagedIdentity, err.Error(), nil)
|
||||
}
|
||||
|
||||
if azruntime.HasStatusCode(resp, http.StatusOK, http.StatusCreated) {
|
||||
tk, err := c.createAccessToken(resp)
|
||||
if err != nil && c.chained && c.msiType == msiTypeIMDS {
|
||||
// failure to unmarshal a 2xx implies the response is from something other than IMDS such as a proxy listening at
|
||||
if c.imds {
|
||||
var ije msalerrors.InvalidJsonErr
|
||||
if c.chained && errors.As(err, &ije) {
|
||||
// an unmarshaling error implies the response is from something other than IMDS such as a proxy listening at
|
||||
// the same address. Return a credentialUnavailableError so credential chains continue to their next credential
|
||||
err = newCredentialUnavailableError(credNameManagedIdentity, err.Error())
|
||||
return azcore.AccessToken{}, newCredentialUnavailableError(credNameManagedIdentity, err.Error())
|
||||
}
|
||||
return tk, err
|
||||
resp := getResponseFromError(err)
|
||||
if resp == nil {
|
||||
return azcore.AccessToken{}, newAuthenticationFailedErrorFromMSAL(credNameManagedIdentity, err)
|
||||
}
|
||||
|
||||
if c.msiType == msiTypeIMDS {
|
||||
switch resp.StatusCode {
|
||||
case http.StatusBadRequest:
|
||||
if id != nil {
|
||||
// return authenticationFailedError, halting any encompassing credential chain,
|
||||
// because the explicit user-assigned identity implies the developer expected this to work
|
||||
if c.userAssigned {
|
||||
return azcore.AccessToken{}, newAuthenticationFailedError(credNameManagedIdentity, "the requested identity isn't assigned to this resource", resp)
|
||||
}
|
||||
msg := "failed to authenticate a system assigned identity"
|
||||
@ -278,237 +221,7 @@ func (c *managedIdentityClient) authenticate(ctx context.Context, id ManagedIDKi
|
||||
return azcore.AccessToken{}, newCredentialUnavailableError(credNameManagedIdentity, fmt.Sprintf("unexpected response %q", string(body)))
|
||||
}
|
||||
}
|
||||
if c.chained {
|
||||
// the response may be from something other than IMDS, for example a proxy returning
|
||||
// 404. Return credentialUnavailableError so credential chains continue to their
|
||||
// next credential, include the response in the error message to help debugging
|
||||
err = newAuthenticationFailedError(credNameManagedIdentity, "", resp)
|
||||
return azcore.AccessToken{}, newCredentialUnavailableError(credNameManagedIdentity, err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
return azcore.AccessToken{}, newAuthenticationFailedError(credNameManagedIdentity, "", resp)
|
||||
}
|
||||
|
||||
func (c *managedIdentityClient) createAccessToken(res *http.Response) (azcore.AccessToken, error) {
|
||||
value := struct {
|
||||
// these are the only fields that we use
|
||||
Token string `json:"access_token,omitempty"`
|
||||
RefreshToken string `json:"refresh_token,omitempty"`
|
||||
ExpiresIn wrappedNumber `json:"expires_in,omitempty"` // this field should always return the number of seconds for which a token is valid
|
||||
ExpiresOn interface{} `json:"expires_on,omitempty"` // the value returned in this field varies between a number and a date string
|
||||
}{}
|
||||
if err := azruntime.UnmarshalAsJSON(res, &value); err != nil {
|
||||
return azcore.AccessToken{}, newAuthenticationFailedError(credNameManagedIdentity, "Unexpected response content", res)
|
||||
}
|
||||
if value.ExpiresIn != "" {
|
||||
expiresIn, err := json.Number(value.ExpiresIn).Int64()
|
||||
if err != nil {
|
||||
err = newAuthenticationFailedErrorFromMSAL(credNameManagedIdentity, err)
|
||||
return azcore.AccessToken{}, err
|
||||
}
|
||||
return azcore.AccessToken{Token: value.Token, ExpiresOn: time.Now().Add(time.Second * time.Duration(expiresIn)).UTC()}, nil
|
||||
}
|
||||
switch v := value.ExpiresOn.(type) {
|
||||
case float64:
|
||||
return azcore.AccessToken{Token: value.Token, ExpiresOn: time.Unix(int64(v), 0).UTC()}, nil
|
||||
case string:
|
||||
if expiresOn, err := strconv.Atoi(v); err == nil {
|
||||
return azcore.AccessToken{Token: value.Token, ExpiresOn: time.Unix(int64(expiresOn), 0).UTC()}, nil
|
||||
}
|
||||
return azcore.AccessToken{}, newAuthenticationFailedError(credNameManagedIdentity, "unexpected expires_on value: "+v, res)
|
||||
default:
|
||||
msg := fmt.Sprintf("unsupported type received in expires_on: %T, %v", v, v)
|
||||
return azcore.AccessToken{}, newAuthenticationFailedError(credNameManagedIdentity, msg, res)
|
||||
}
|
||||
}
|
||||
|
||||
func (c *managedIdentityClient) createAuthRequest(ctx context.Context, id ManagedIDKind, scopes []string) (*policy.Request, error) {
|
||||
switch c.msiType {
|
||||
case msiTypeIMDS:
|
||||
return c.createIMDSAuthRequest(ctx, id, scopes)
|
||||
case msiTypeAppService:
|
||||
return c.createAppServiceAuthRequest(ctx, id, scopes)
|
||||
case msiTypeAzureArc:
|
||||
// need to perform preliminary request to retreive the secret key challenge provided by the HIMDS service
|
||||
key, err := c.getAzureArcSecretKey(ctx, scopes)
|
||||
if err != nil {
|
||||
msg := fmt.Sprintf("failed to retreive secret key from the identity endpoint: %v", err)
|
||||
return nil, newAuthenticationFailedError(credNameManagedIdentity, msg, nil)
|
||||
}
|
||||
return c.createAzureArcAuthRequest(ctx, scopes, key)
|
||||
case msiTypeAzureML:
|
||||
return c.createAzureMLAuthRequest(ctx, id, scopes)
|
||||
case msiTypeServiceFabric:
|
||||
return c.createServiceFabricAuthRequest(ctx, scopes)
|
||||
case msiTypeCloudShell:
|
||||
return c.createCloudShellAuthRequest(ctx, scopes)
|
||||
default:
|
||||
return nil, newCredentialUnavailableError(credNameManagedIdentity, "managed identity isn't supported in this environment")
|
||||
}
|
||||
}
|
||||
|
||||
func (c *managedIdentityClient) createIMDSAuthRequest(ctx context.Context, id ManagedIDKind, scopes []string) (*policy.Request, error) {
|
||||
request, err := azruntime.NewRequest(ctx, http.MethodGet, c.endpoint)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
request.Raw().Header.Set(headerMetadata, "true")
|
||||
q := request.Raw().URL.Query()
|
||||
q.Set("api-version", imdsAPIVersion)
|
||||
q.Set("resource", strings.Join(scopes, " "))
|
||||
if id != nil {
|
||||
switch id.idKind() {
|
||||
case miClientID:
|
||||
q.Set(qpClientID, id.String())
|
||||
case miObjectID:
|
||||
q.Set("object_id", id.String())
|
||||
case miResourceID:
|
||||
q.Set(msiResID, id.String())
|
||||
}
|
||||
}
|
||||
request.Raw().URL.RawQuery = q.Encode()
|
||||
return request, nil
|
||||
}
|
||||
|
||||
func (c *managedIdentityClient) createAppServiceAuthRequest(ctx context.Context, id ManagedIDKind, scopes []string) (*policy.Request, error) {
|
||||
request, err := azruntime.NewRequest(ctx, http.MethodGet, c.endpoint)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
request.Raw().Header.Set("X-IDENTITY-HEADER", os.Getenv(identityHeader))
|
||||
q := request.Raw().URL.Query()
|
||||
q.Set("api-version", "2019-08-01")
|
||||
q.Set("resource", scopes[0])
|
||||
if id != nil {
|
||||
switch id.idKind() {
|
||||
case miClientID:
|
||||
q.Set(qpClientID, id.String())
|
||||
case miObjectID:
|
||||
q.Set("principal_id", id.String())
|
||||
case miResourceID:
|
||||
q.Set(miResID, id.String())
|
||||
}
|
||||
}
|
||||
request.Raw().URL.RawQuery = q.Encode()
|
||||
return request, nil
|
||||
}
|
||||
|
||||
func (c *managedIdentityClient) createAzureMLAuthRequest(ctx context.Context, id ManagedIDKind, scopes []string) (*policy.Request, error) {
|
||||
request, err := azruntime.NewRequest(ctx, http.MethodGet, c.endpoint)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
request.Raw().Header.Set("secret", os.Getenv(msiSecret))
|
||||
q := request.Raw().URL.Query()
|
||||
q.Set("api-version", "2017-09-01")
|
||||
q.Set("resource", strings.Join(scopes, " "))
|
||||
q.Set("clientid", os.Getenv(defaultIdentityClientID))
|
||||
if id != nil {
|
||||
switch id.idKind() {
|
||||
case miClientID:
|
||||
q.Set("clientid", id.String())
|
||||
case miObjectID:
|
||||
return nil, newAuthenticationFailedError(credNameManagedIdentity, "Azure ML doesn't support specifying a managed identity by object ID", nil)
|
||||
case miResourceID:
|
||||
return nil, newAuthenticationFailedError(credNameManagedIdentity, "Azure ML doesn't support specifying a managed identity by resource ID", nil)
|
||||
}
|
||||
}
|
||||
request.Raw().URL.RawQuery = q.Encode()
|
||||
return request, nil
|
||||
}
|
||||
|
||||
func (c *managedIdentityClient) createServiceFabricAuthRequest(ctx context.Context, scopes []string) (*policy.Request, error) {
|
||||
request, err := azruntime.NewRequest(ctx, http.MethodGet, c.endpoint)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
q := request.Raw().URL.Query()
|
||||
request.Raw().Header.Set("Accept", "application/json")
|
||||
request.Raw().Header.Set("Secret", os.Getenv(identityHeader))
|
||||
q.Set("api-version", serviceFabricAPIVersion)
|
||||
q.Set("resource", strings.Join(scopes, " "))
|
||||
request.Raw().URL.RawQuery = q.Encode()
|
||||
return request, nil
|
||||
}
|
||||
|
||||
func (c *managedIdentityClient) getAzureArcSecretKey(ctx context.Context, resources []string) (string, error) {
|
||||
// create the request to retreive the secret key challenge provided by the HIMDS service
|
||||
request, err := azruntime.NewRequest(ctx, http.MethodGet, c.endpoint)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
request.Raw().Header.Set(headerMetadata, "true")
|
||||
q := request.Raw().URL.Query()
|
||||
q.Set("api-version", azureArcAPIVersion)
|
||||
q.Set("resource", strings.Join(resources, " "))
|
||||
request.Raw().URL.RawQuery = q.Encode()
|
||||
// send the initial request to get the short-lived secret key
|
||||
response, err := c.azClient.Pipeline().Do(request)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
// the endpoint is expected to return a 401 with the WWW-Authenticate header set to the location
|
||||
// of the secret key file. Any other status code indicates an error in the request.
|
||||
if response.StatusCode != 401 {
|
||||
msg := fmt.Sprintf("expected a 401 response, received %d", response.StatusCode)
|
||||
return "", newAuthenticationFailedError(credNameManagedIdentity, msg, response)
|
||||
}
|
||||
header := response.Header.Get("WWW-Authenticate")
|
||||
if len(header) == 0 {
|
||||
return "", newAuthenticationFailedError(credNameManagedIdentity, "HIMDS response has no WWW-Authenticate header", nil)
|
||||
}
|
||||
// the WWW-Authenticate header is expected in the following format: Basic realm=/some/file/path.key
|
||||
_, p, found := strings.Cut(header, "=")
|
||||
if !found {
|
||||
return "", newAuthenticationFailedError(credNameManagedIdentity, "unexpected WWW-Authenticate header from HIMDS: "+header, nil)
|
||||
}
|
||||
expected, err := arcKeyDirectory()
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
if filepath.Dir(p) != expected || !strings.HasSuffix(p, ".key") {
|
||||
return "", newAuthenticationFailedError(credNameManagedIdentity, "unexpected file path from HIMDS service: "+p, nil)
|
||||
}
|
||||
f, err := os.Stat(p)
|
||||
if err != nil {
|
||||
return "", newAuthenticationFailedError(credNameManagedIdentity, fmt.Sprintf("could not stat %q: %v", p, err), nil)
|
||||
}
|
||||
if s := f.Size(); s > 4096 {
|
||||
return "", newAuthenticationFailedError(credNameManagedIdentity, fmt.Sprintf("key is too large (%d bytes)", s), nil)
|
||||
}
|
||||
key, err := os.ReadFile(p)
|
||||
if err != nil {
|
||||
return "", newAuthenticationFailedError(credNameManagedIdentity, fmt.Sprintf("could not read %q: %v", p, err), nil)
|
||||
}
|
||||
return string(key), nil
|
||||
}
|
||||
|
||||
func (c *managedIdentityClient) createAzureArcAuthRequest(ctx context.Context, resources []string, key string) (*policy.Request, error) {
|
||||
request, err := azruntime.NewRequest(ctx, http.MethodGet, c.endpoint)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
request.Raw().Header.Set(headerMetadata, "true")
|
||||
request.Raw().Header.Set("Authorization", fmt.Sprintf("Basic %s", key))
|
||||
q := request.Raw().URL.Query()
|
||||
q.Set("api-version", azureArcAPIVersion)
|
||||
q.Set("resource", strings.Join(resources, " "))
|
||||
request.Raw().URL.RawQuery = q.Encode()
|
||||
return request, nil
|
||||
}
|
||||
|
||||
func (c *managedIdentityClient) createCloudShellAuthRequest(ctx context.Context, scopes []string) (*policy.Request, error) {
|
||||
request, err := azruntime.NewRequest(ctx, http.MethodPost, c.endpoint)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
request.Raw().Header.Set(headerMetadata, "true")
|
||||
data := url.Values{}
|
||||
data.Set("resource", strings.Join(scopes, " "))
|
||||
dataEncoded := data.Encode()
|
||||
body := streaming.NopCloser(strings.NewReader(dataEncoded))
|
||||
if err := request.SetBody(body, "application/x-www-form-urlencoded"); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return request, nil
|
||||
}
|
||||
|
||||
26
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/managed_identity_credential.go
generated
vendored
26
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/managed_identity_credential.go
generated
vendored
@ -14,7 +14,6 @@ import (
|
||||
"github.com/Azure/azure-sdk-for-go/sdk/azcore"
|
||||
"github.com/Azure/azure-sdk-for-go/sdk/azcore/policy"
|
||||
"github.com/Azure/azure-sdk-for-go/sdk/azcore/runtime"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/confidential"
|
||||
)
|
||||
|
||||
const credNameManagedIdentity = "ManagedIdentityCredential"
|
||||
@ -110,7 +109,6 @@ type ManagedIdentityCredentialOptions struct {
|
||||
//
|
||||
// [Azure managed identity]: https://learn.microsoft.com/entra/identity/managed-identities-azure-resources/overview
|
||||
type ManagedIdentityCredential struct {
|
||||
client *confidentialClient
|
||||
mic *managedIdentityClient
|
||||
}
|
||||
|
||||
@ -123,38 +121,22 @@ func NewManagedIdentityCredential(options *ManagedIdentityCredentialOptions) (*M
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
cred := confidential.NewCredFromTokenProvider(mic.provideToken)
|
||||
|
||||
// It's okay to give MSAL an invalid client ID because MSAL will use it only as part of a cache key.
|
||||
// ManagedIdentityClient handles all the details of authentication and won't receive this value from MSAL.
|
||||
clientID := "SYSTEM-ASSIGNED-MANAGED-IDENTITY"
|
||||
if options.ID != nil {
|
||||
clientID = options.ID.String()
|
||||
}
|
||||
// similarly, it's okay to give MSAL an incorrect tenant because MSAL won't use the value
|
||||
c, err := newConfidentialClient("common", clientID, credNameManagedIdentity, cred, confidentialClientOptions{
|
||||
ClientOptions: options.ClientOptions,
|
||||
})
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &ManagedIdentityCredential{client: c, mic: mic}, nil
|
||||
return &ManagedIdentityCredential{mic: mic}, nil
|
||||
}
|
||||
|
||||
// GetToken requests an access token from the hosting environment. This method is called automatically by Azure SDK clients.
|
||||
func (c *ManagedIdentityCredential) GetToken(ctx context.Context, opts policy.TokenRequestOptions) (azcore.AccessToken, error) {
|
||||
var err error
|
||||
ctx, endSpan := runtime.StartSpan(ctx, credNameManagedIdentity+"."+traceOpGetToken, c.client.azClient.Tracer(), nil)
|
||||
ctx, endSpan := runtime.StartSpan(ctx, credNameManagedIdentity+"."+traceOpGetToken, c.mic.azClient.Tracer(), nil)
|
||||
defer func() { endSpan(err) }()
|
||||
|
||||
if len(opts.Scopes) != 1 {
|
||||
err = fmt.Errorf("%s.GetToken() requires exactly one scope", credNameManagedIdentity)
|
||||
return azcore.AccessToken{}, err
|
||||
}
|
||||
// managed identity endpoints require a Microsoft Entra ID v1 resource (i.e. token audience), not a v2 scope, so we remove "/.default" here
|
||||
// managed identity endpoints require a v1 resource (i.e. token audience), not a v2 scope, so we remove "/.default" here
|
||||
opts.Scopes = []string{strings.TrimSuffix(opts.Scopes[0], defaultSuffix)}
|
||||
tk, err := c.client.GetToken(ctx, opts)
|
||||
return tk, err
|
||||
return c.mic.GetToken(ctx, opts)
|
||||
}
|
||||
|
||||
var _ azcore.TokenCredential = (*ManagedIdentityCredential)(nil)
|
||||
|
||||
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/public_client.go
generated
vendored
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/public_client.go
generated
vendored
@ -243,7 +243,7 @@ func (p *publicClient) token(ar public.AuthResult, err error) (azcore.AccessToke
|
||||
} else {
|
||||
err = newAuthenticationFailedErrorFromMSAL(p.name, err)
|
||||
}
|
||||
return azcore.AccessToken{Token: ar.AccessToken, ExpiresOn: ar.ExpiresOn.UTC()}, err
|
||||
return azcore.AccessToken{Token: ar.AccessToken, ExpiresOn: ar.ExpiresOn.UTC(), RefreshOn: ar.Metadata.RefreshOn.UTC()}, err
|
||||
}
|
||||
|
||||
// resolveTenant returns the correct WithTenantID() argument for a token request given the client's
|
||||
|
||||
4
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/test-resources-post.ps1
generated
vendored
4
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/test-resources-post.ps1
generated
vendored
@ -72,6 +72,7 @@ az container create -g $rg -n $aciName --image $image `
|
||||
--acr-identity $($DeploymentOutputs['AZIDENTITY_USER_ASSIGNED_IDENTITY']) `
|
||||
--assign-identity [system] $($DeploymentOutputs['AZIDENTITY_USER_ASSIGNED_IDENTITY']) `
|
||||
--cpu 1 `
|
||||
--ip-address Public `
|
||||
--memory 1.0 `
|
||||
--os-type Linux `
|
||||
--role "Storage Blob Data Reader" `
|
||||
@ -82,7 +83,8 @@ az container create -g $rg -n $aciName --image $image `
|
||||
AZIDENTITY_USER_ASSIGNED_IDENTITY_CLIENT_ID=$($DeploymentOutputs['AZIDENTITY_USER_ASSIGNED_IDENTITY_CLIENT_ID']) `
|
||||
AZIDENTITY_USER_ASSIGNED_IDENTITY_OBJECT_ID=$($DeploymentOutputs['AZIDENTITY_USER_ASSIGNED_IDENTITY_OBJECT_ID']) `
|
||||
FUNCTIONS_CUSTOMHANDLER_PORT=80
|
||||
Write-Host "##vso[task.setvariable variable=AZIDENTITY_ACI_NAME;]$aciName"
|
||||
$aciIP = az container show -g $rg -n $aciName --query ipAddress.ip --output tsv
|
||||
Write-Host "##vso[task.setvariable variable=AZIDENTITY_ACI_IP;]$aciIP"
|
||||
|
||||
# Azure Functions deployment: copy the Windows binary from the Docker image, deploy it in a zip
|
||||
Write-Host "Deploying to Azure Functions"
|
||||
|
||||
12
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/username_password_credential.go
generated
vendored
12
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/username_password_credential.go
generated
vendored
@ -17,6 +17,11 @@ import (
|
||||
const credNameUserPassword = "UsernamePasswordCredential"
|
||||
|
||||
// UsernamePasswordCredentialOptions contains optional parameters for UsernamePasswordCredential.
|
||||
//
|
||||
// Deprecated: UsernamePasswordCredential is deprecated because it can't support multifactor
|
||||
// authentication. See [Entra ID documentation] for migration guidance.
|
||||
//
|
||||
// [Entra ID documentation]: https://aka.ms/azsdk/identity/mfa
|
||||
type UsernamePasswordCredentialOptions struct {
|
||||
azcore.ClientOptions
|
||||
|
||||
@ -43,8 +48,13 @@ type UsernamePasswordCredentialOptions struct {
|
||||
|
||||
// UsernamePasswordCredential authenticates a user with a password. Microsoft doesn't recommend this kind of authentication,
|
||||
// because it's less secure than other authentication flows. This credential is not interactive, so it isn't compatible
|
||||
// with any form of multi-factor authentication, and the application must already have user or admin consent.
|
||||
// with any form of multifactor authentication, and the application must already have user or admin consent.
|
||||
// This credential can only authenticate work and school accounts; it can't authenticate Microsoft accounts.
|
||||
//
|
||||
// Deprecated: this credential is deprecated because it can't support multifactor authentication. See [Entra ID documentation]
|
||||
// for migration guidance.
|
||||
//
|
||||
// [Entra ID documentation]: https://aka.ms/azsdk/identity/mfa
|
||||
type UsernamePasswordCredential struct {
|
||||
client *publicClient
|
||||
}
|
||||
|
||||
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/version.go
generated
vendored
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/azidentity/version.go
generated
vendored
@ -14,5 +14,5 @@ const (
|
||||
module = "github.com/Azure/azure-sdk-for-go/sdk/" + component
|
||||
|
||||
// Version is the semantic version (see http://semver.org) of this module.
|
||||
version = "v1.8.2"
|
||||
version = "v1.9.0"
|
||||
)
|
||||
|
||||
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/log/log.go
generated
vendored
2
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/log/log.go
generated
vendored
@ -44,7 +44,7 @@ func Should(cls Event) bool {
|
||||
if log.lst == nil {
|
||||
return false
|
||||
}
|
||||
if log.cls == nil || len(log.cls) == 0 {
|
||||
if len(log.cls) == 0 {
|
||||
return true
|
||||
}
|
||||
for _, c := range log.cls {
|
||||
|
||||
51
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/temporal/resource.go
generated
vendored
51
vendor/github.com/Azure/azure-sdk-for-go/sdk/internal/temporal/resource.go
generated
vendored
@ -11,9 +11,17 @@ import (
|
||||
"time"
|
||||
)
|
||||
|
||||
// backoff sets a minimum wait time between eager update attempts. It's a variable so tests can manipulate it.
|
||||
var backoff = func(now, lastAttempt time.Time) bool {
|
||||
return lastAttempt.Add(30 * time.Second).After(now)
|
||||
}
|
||||
|
||||
// AcquireResource abstracts a method for refreshing a temporal resource.
|
||||
type AcquireResource[TResource, TState any] func(state TState) (newResource TResource, newExpiration time.Time, err error)
|
||||
|
||||
// ShouldRefresh abstracts a method for indicating whether a resource should be refreshed before expiration.
|
||||
type ShouldRefresh[TResource, TState any] func(TResource, TState) bool
|
||||
|
||||
// Resource is a temporal resource (usually a credential) that requires periodic refreshing.
|
||||
type Resource[TResource, TState any] struct {
|
||||
// cond is used to synchronize access to the shared resource embodied by the remaining fields
|
||||
@ -31,24 +39,43 @@ type Resource[TResource, TState any] struct {
|
||||
// lastAttempt indicates when a thread/goroutine last attempted to acquire/update the resource
|
||||
lastAttempt time.Time
|
||||
|
||||
// shouldRefresh indicates whether the resource should be refreshed before expiration
|
||||
shouldRefresh ShouldRefresh[TResource, TState]
|
||||
|
||||
// acquireResource is the callback function that actually acquires the resource
|
||||
acquireResource AcquireResource[TResource, TState]
|
||||
}
|
||||
|
||||
// NewResource creates a new Resource that uses the specified AcquireResource for refreshing.
|
||||
func NewResource[TResource, TState any](ar AcquireResource[TResource, TState]) *Resource[TResource, TState] {
|
||||
return &Resource[TResource, TState]{cond: sync.NewCond(&sync.Mutex{}), acquireResource: ar}
|
||||
r := &Resource[TResource, TState]{acquireResource: ar, cond: sync.NewCond(&sync.Mutex{})}
|
||||
r.shouldRefresh = r.expiringSoon
|
||||
return r
|
||||
}
|
||||
|
||||
// ResourceOptions contains optional configuration for Resource
|
||||
type ResourceOptions[TResource, TState any] struct {
|
||||
// ShouldRefresh indicates whether [Resource.Get] should acquire an updated resource despite
|
||||
// the currently held resource not having expired. [Resource.Get] ignores all errors from
|
||||
// refresh attempts triggered by ShouldRefresh returning true, and doesn't call ShouldRefresh
|
||||
// when the resource has expired (it unconditionally updates expired resources). When
|
||||
// ShouldRefresh is nil, [Resource.Get] refreshes the resource if it will expire within 5
|
||||
// minutes.
|
||||
ShouldRefresh ShouldRefresh[TResource, TState]
|
||||
}
|
||||
|
||||
// NewResourceWithOptions creates a new Resource that uses the specified AcquireResource for refreshing.
|
||||
func NewResourceWithOptions[TResource, TState any](ar AcquireResource[TResource, TState], opts ResourceOptions[TResource, TState]) *Resource[TResource, TState] {
|
||||
r := NewResource(ar)
|
||||
if opts.ShouldRefresh != nil {
|
||||
r.shouldRefresh = opts.ShouldRefresh
|
||||
}
|
||||
return r
|
||||
}
|
||||
|
||||
// Get returns the underlying resource.
|
||||
// If the resource is fresh, no refresh is performed.
|
||||
func (er *Resource[TResource, TState]) Get(state TState) (TResource, error) {
|
||||
// If the resource is expiring within this time window, update it eagerly.
|
||||
// This allows other threads/goroutines to keep running by using the not-yet-expired
|
||||
// resource value while one thread/goroutine updates the resource.
|
||||
const window = 5 * time.Minute // This example updates the resource 5 minutes prior to expiration
|
||||
const backoff = 30 * time.Second // Minimum wait time between eager update attempts
|
||||
|
||||
now, acquire, expired := time.Now(), false, false
|
||||
|
||||
// acquire exclusive lock
|
||||
@ -65,9 +92,8 @@ func (er *Resource[TResource, TState]) Get(state TState) (TResource, error) {
|
||||
break
|
||||
}
|
||||
// Getting here means that this thread/goroutine will wait for the updated resource
|
||||
} else if er.expiration.Add(-window).Before(now) {
|
||||
// The resource is valid but is expiring within the time window
|
||||
if !er.acquiring && er.lastAttempt.Add(backoff).Before(now) {
|
||||
} else if er.shouldRefresh(resource, state) {
|
||||
if !(er.acquiring || backoff(now, er.lastAttempt)) {
|
||||
// If another thread/goroutine is not acquiring/renewing the resource, and none has attempted
|
||||
// to do so within the last 30 seconds, this thread/goroutine will do it
|
||||
er.acquiring, acquire = true, true
|
||||
@ -121,3 +147,8 @@ func (er *Resource[TResource, TState]) Expire() {
|
||||
// Reset the expiration as if we never got this resource to begin with
|
||||
er.expiration = time.Time{}
|
||||
}
|
||||
|
||||
func (er *Resource[TResource, TState]) expiringSoon(TResource, TState) bool {
|
||||
// call time.Now() instead of using Get's value so ShouldRefresh doesn't need a time.Time parameter
|
||||
return er.expiration.Add(-5 * time.Minute).Before(time.Now())
|
||||
}
|
||||
|
||||
@ -65,6 +65,13 @@ type AuthenticationScheme = authority.AuthenticationScheme
|
||||
|
||||
type Account = shared.Account
|
||||
|
||||
type TokenSource = base.TokenSource
|
||||
|
||||
const (
|
||||
TokenSourceIdentityProvider = base.TokenSourceIdentityProvider
|
||||
TokenSourceCache = base.TokenSourceCache
|
||||
)
|
||||
|
||||
// CertFromPEM converts a PEM file (.pem or .key) for use with [NewCredFromCert]. The file
|
||||
// must contain the public certificate and the private key. If a PEM block is encrypted and
|
||||
// password is not an empty string, it attempts to decrypt the PEM blocks using the password.
|
||||
@ -639,7 +646,7 @@ func (cca Client) AcquireTokenByUsernamePassword(ctx context.Context, scopes []s
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
return cca.base.AuthResultFromToken(ctx, authParams, token, true)
|
||||
return cca.base.AuthResultFromToken(ctx, authParams, token)
|
||||
}
|
||||
|
||||
// acquireTokenByAuthCodeOptions contains the optional parameters used to acquire an access token using the authorization code flow.
|
||||
@ -733,7 +740,7 @@ func (cca Client) AcquireTokenByCredential(ctx context.Context, scopes []string,
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
return cca.base.AuthResultFromToken(ctx, authParams, token, true)
|
||||
return cca.base.AuthResultFromToken(ctx, authParams, token)
|
||||
}
|
||||
|
||||
// acquireTokenOnBehalfOfOptions contains optional configuration for AcquireTokenOnBehalfOf
|
||||
|
||||
@ -64,11 +64,20 @@ type CallErr struct {
|
||||
Err error
|
||||
}
|
||||
|
||||
type InvalidJsonErr struct {
|
||||
Err error
|
||||
}
|
||||
|
||||
// Errors implements error.Error().
|
||||
func (e CallErr) Error() string {
|
||||
return e.Err.Error()
|
||||
}
|
||||
|
||||
// Errors implements error.Error().
|
||||
func (e InvalidJsonErr) Error() string {
|
||||
return e.Err.Error()
|
||||
}
|
||||
|
||||
// Verbose prints a versbose error message with the request or response.
|
||||
func (e CallErr) Verbose() string {
|
||||
e.Resp.Request = nil // This brings in a bunch of TLS crap we don't need
|
||||
|
||||
@ -5,16 +5,17 @@ package base
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"net/url"
|
||||
"reflect"
|
||||
"strings"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/cache"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/internal/base/internal/storage"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/errors"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/internal/base/storage"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/internal/oauth"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/internal/oauth/ops/accesstokens"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/internal/oauth/ops/authority"
|
||||
@ -94,6 +95,7 @@ type AuthResult struct {
|
||||
|
||||
// AuthResultMetadata which contains meta data for the AuthResult
|
||||
type AuthResultMetadata struct {
|
||||
RefreshOn time.Time
|
||||
TokenSource TokenSource
|
||||
}
|
||||
|
||||
@ -101,9 +103,8 @@ type TokenSource int
|
||||
|
||||
// These are all the types of token flows.
|
||||
const (
|
||||
SourceUnknown TokenSource = 0
|
||||
IdentityProvider TokenSource = 1
|
||||
Cache TokenSource = 2
|
||||
TokenSourceIdentityProvider TokenSource = 0
|
||||
TokenSourceCache TokenSource = 1
|
||||
)
|
||||
|
||||
// AuthResultFromStorage creates an AuthResult from a storage token response (which is generated from the cache).
|
||||
@ -111,7 +112,6 @@ func AuthResultFromStorage(storageTokenResponse storage.TokenResponse) (AuthResu
|
||||
if err := storageTokenResponse.AccessToken.Validate(); err != nil {
|
||||
return AuthResult{}, fmt.Errorf("problem with access token in StorageTokenResponse: %w", err)
|
||||
}
|
||||
|
||||
account := storageTokenResponse.Account
|
||||
accessToken := storageTokenResponse.AccessToken.Secret
|
||||
grantedScopes := strings.Split(storageTokenResponse.AccessToken.Scopes, scopeSeparator)
|
||||
@ -132,7 +132,8 @@ func AuthResultFromStorage(storageTokenResponse storage.TokenResponse) (AuthResu
|
||||
GrantedScopes: grantedScopes,
|
||||
DeclinedScopes: nil,
|
||||
Metadata: AuthResultMetadata{
|
||||
TokenSource: Cache,
|
||||
TokenSource: TokenSourceCache,
|
||||
RefreshOn: storageTokenResponse.AccessToken.RefreshOn.T,
|
||||
},
|
||||
}, nil
|
||||
}
|
||||
@ -146,10 +147,11 @@ func NewAuthResult(tokenResponse accesstokens.TokenResponse, account shared.Acco
|
||||
Account: account,
|
||||
IDToken: tokenResponse.IDToken,
|
||||
AccessToken: tokenResponse.AccessToken,
|
||||
ExpiresOn: tokenResponse.ExpiresOn.T,
|
||||
ExpiresOn: tokenResponse.ExpiresOn,
|
||||
GrantedScopes: tokenResponse.GrantedScopes.Slice,
|
||||
Metadata: AuthResultMetadata{
|
||||
TokenSource: IdentityProvider,
|
||||
TokenSource: TokenSourceIdentityProvider,
|
||||
RefreshOn: tokenResponse.RefreshOn.T,
|
||||
},
|
||||
}, nil
|
||||
}
|
||||
@ -165,6 +167,8 @@ type Client struct {
|
||||
AuthParams authority.AuthParams // DO NOT EVER MAKE THIS A POINTER! See "Note" in New().
|
||||
cacheAccessor cache.ExportReplace
|
||||
cacheAccessorMu *sync.RWMutex
|
||||
canRefresh map[string]*atomic.Value
|
||||
canRefreshMu *sync.Mutex
|
||||
}
|
||||
|
||||
// Option is an optional argument to the New constructor.
|
||||
@ -241,6 +245,8 @@ func New(clientID string, authorityURI string, token *oauth.Client, options ...O
|
||||
cacheAccessorMu: &sync.RWMutex{},
|
||||
manager: storage.New(token),
|
||||
pmanager: storage.NewPartitionedManager(token),
|
||||
canRefresh: make(map[string]*atomic.Value),
|
||||
canRefreshMu: &sync.Mutex{},
|
||||
}
|
||||
for _, o := range options {
|
||||
if err = o(&client); err != nil {
|
||||
@ -345,6 +351,28 @@ func (b Client) AcquireTokenSilent(ctx context.Context, silent AcquireTokenSilen
|
||||
if silent.Claims == "" {
|
||||
ar, err = AuthResultFromStorage(storageTokenResponse)
|
||||
if err == nil {
|
||||
if rt := storageTokenResponse.AccessToken.RefreshOn.T; !rt.IsZero() && Now().After(rt) {
|
||||
b.canRefreshMu.Lock()
|
||||
refreshValue, ok := b.canRefresh[tenant]
|
||||
if !ok {
|
||||
refreshValue = &atomic.Value{}
|
||||
refreshValue.Store(false)
|
||||
b.canRefresh[tenant] = refreshValue
|
||||
}
|
||||
b.canRefreshMu.Unlock()
|
||||
if refreshValue.CompareAndSwap(false, true) {
|
||||
defer refreshValue.Store(false)
|
||||
// Added a check to see if the token is still same because there is a chance
|
||||
// that the token is already refreshed by another thread.
|
||||
// If the token is not same, we don't need to refresh it.
|
||||
// Which means it refreshed.
|
||||
if str, err := m.Read(ctx, authParams); err == nil && str.AccessToken.Secret == ar.AccessToken {
|
||||
if tr, er := b.Token.Credential(ctx, authParams, silent.Credential); er == nil {
|
||||
return b.AuthResultFromToken(ctx, authParams, tr)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
ar.AccessToken, err = authParams.AuthnScheme.FormatAccessToken(ar.AccessToken)
|
||||
return ar, err
|
||||
}
|
||||
@ -362,7 +390,7 @@ func (b Client) AcquireTokenSilent(ctx context.Context, silent AcquireTokenSilen
|
||||
if err != nil {
|
||||
return ar, err
|
||||
}
|
||||
return b.AuthResultFromToken(ctx, authParams, token, true)
|
||||
return b.AuthResultFromToken(ctx, authParams, token)
|
||||
}
|
||||
|
||||
func (b Client) AcquireTokenByAuthCode(ctx context.Context, authCodeParams AcquireTokenAuthCodeParameters) (AuthResult, error) {
|
||||
@ -391,7 +419,7 @@ func (b Client) AcquireTokenByAuthCode(ctx context.Context, authCodeParams Acqui
|
||||
return AuthResult{}, err
|
||||
}
|
||||
|
||||
return b.AuthResultFromToken(ctx, authParams, token, true)
|
||||
return b.AuthResultFromToken(ctx, authParams, token)
|
||||
}
|
||||
|
||||
// AcquireTokenOnBehalfOf acquires a security token for an app using middle tier apps access token.
|
||||
@ -420,15 +448,12 @@ func (b Client) AcquireTokenOnBehalfOf(ctx context.Context, onBehalfOfParams Acq
|
||||
authParams.UserAssertion = onBehalfOfParams.UserAssertion
|
||||
token, err := b.Token.OnBehalfOf(ctx, authParams, onBehalfOfParams.Credential)
|
||||
if err == nil {
|
||||
ar, err = b.AuthResultFromToken(ctx, authParams, token, true)
|
||||
ar, err = b.AuthResultFromToken(ctx, authParams, token)
|
||||
}
|
||||
return ar, err
|
||||
}
|
||||
|
||||
func (b Client) AuthResultFromToken(ctx context.Context, authParams authority.AuthParams, token accesstokens.TokenResponse, cacheWrite bool) (AuthResult, error) {
|
||||
if !cacheWrite {
|
||||
return NewAuthResult(token, shared.Account{})
|
||||
}
|
||||
func (b Client) AuthResultFromToken(ctx context.Context, authParams authority.AuthParams, token accesstokens.TokenResponse) (AuthResult, error) {
|
||||
var m manager = b.manager
|
||||
if authParams.AuthorizationType == authority.ATOnBehalfOf {
|
||||
m = b.pmanager
|
||||
@ -458,6 +483,10 @@ func (b Client) AuthResultFromToken(ctx context.Context, authParams authority.Au
|
||||
return ar, err
|
||||
}
|
||||
|
||||
// This function wraps time.Now() and is used for refreshing the application
|
||||
// was created to test the function against refreshin
|
||||
var Now = time.Now
|
||||
|
||||
func (b Client) AllAccounts(ctx context.Context) ([]shared.Account, error) {
|
||||
if b.cacheAccessor != nil {
|
||||
b.cacheAccessorMu.RLock()
|
||||
|
||||
@ -72,6 +72,7 @@ type AccessToken struct {
|
||||
ClientID string `json:"client_id,omitempty"`
|
||||
Secret string `json:"secret,omitempty"`
|
||||
Scopes string `json:"target,omitempty"`
|
||||
RefreshOn internalTime.Unix `json:"refresh_on,omitempty"`
|
||||
ExpiresOn internalTime.Unix `json:"expires_on,omitempty"`
|
||||
ExtendedExpiresOn internalTime.Unix `json:"extended_expires_on,omitempty"`
|
||||
CachedAt internalTime.Unix `json:"cached_at,omitempty"`
|
||||
@ -83,7 +84,7 @@ type AccessToken struct {
|
||||
}
|
||||
|
||||
// NewAccessToken is the constructor for AccessToken.
|
||||
func NewAccessToken(homeID, env, realm, clientID string, cachedAt, expiresOn, extendedExpiresOn time.Time, scopes, token, tokenType, authnSchemeKeyID string) AccessToken {
|
||||
func NewAccessToken(homeID, env, realm, clientID string, cachedAt, refreshOn, expiresOn, extendedExpiresOn time.Time, scopes, token, tokenType, authnSchemeKeyID string) AccessToken {
|
||||
return AccessToken{
|
||||
HomeAccountID: homeID,
|
||||
Environment: env,
|
||||
@ -93,6 +94,7 @@ func NewAccessToken(homeID, env, realm, clientID string, cachedAt, expiresOn, ex
|
||||
Secret: token,
|
||||
Scopes: scopes,
|
||||
CachedAt: internalTime.Unix{T: cachedAt.UTC()},
|
||||
RefreshOn: internalTime.Unix{T: refreshOn.UTC()},
|
||||
ExpiresOn: internalTime.Unix{T: expiresOn.UTC()},
|
||||
ExtendedExpiresOn: internalTime.Unix{T: extendedExpiresOn.UTC()},
|
||||
TokenType: tokenType,
|
||||
@ -102,8 +104,9 @@ func NewAccessToken(homeID, env, realm, clientID string, cachedAt, expiresOn, ex
|
||||
|
||||
// Key outputs the key that can be used to uniquely look up this entry in a map.
|
||||
func (a AccessToken) Key() string {
|
||||
ks := []string{a.HomeAccountID, a.Environment, a.CredentialType, a.ClientID, a.Realm, a.Scopes}
|
||||
key := strings.Join(
|
||||
[]string{a.HomeAccountID, a.Environment, a.CredentialType, a.ClientID, a.Realm, a.Scopes},
|
||||
ks,
|
||||
shared.CacheKeySeparator,
|
||||
)
|
||||
// add token type to key for new access tokens types. skip for bearer token type to
|
||||
@ -114,7 +114,8 @@ func (m *PartitionedManager) Write(authParameters authority.AuthParams, tokenRes
|
||||
realm,
|
||||
clientID,
|
||||
cachedAt,
|
||||
tokenResponse.ExpiresOn.T,
|
||||
tokenResponse.RefreshOn.T,
|
||||
tokenResponse.ExpiresOn,
|
||||
tokenResponse.ExtExpiresOn.T,
|
||||
target,
|
||||
tokenResponse.AccessToken,
|
||||
@ -173,6 +173,7 @@ func (m *Manager) Write(authParameters authority.AuthParams, tokenResponse acces
|
||||
environment := authParameters.AuthorityInfo.Host
|
||||
realm := authParameters.AuthorityInfo.Tenant
|
||||
clientID := authParameters.ClientID
|
||||
|
||||
target := strings.Join(tokenResponse.GrantedScopes.Slice, scopeSeparator)
|
||||
cachedAt := time.Now()
|
||||
authnSchemeKeyID := authParameters.AuthnScheme.KeyID()
|
||||
@ -193,7 +194,8 @@ func (m *Manager) Write(authParameters authority.AuthParams, tokenResponse acces
|
||||
realm,
|
||||
clientID,
|
||||
cachedAt,
|
||||
tokenResponse.ExpiresOn.T,
|
||||
tokenResponse.RefreshOn.T,
|
||||
tokenResponse.ExpiresOn,
|
||||
tokenResponse.ExtExpiresOn.T,
|
||||
target,
|
||||
tokenResponse.AccessToken,
|
||||
@ -265,6 +267,9 @@ func (m *Manager) aadMetadataFromCache(ctx context.Context, authorityInfo author
|
||||
}
|
||||
|
||||
func (m *Manager) aadMetadata(ctx context.Context, authorityInfo authority.Info) (authority.InstanceDiscoveryMetadata, error) {
|
||||
if m.requests == nil {
|
||||
return authority.InstanceDiscoveryMetadata{}, fmt.Errorf("httpclient in oauth instance for fetching metadata is nil")
|
||||
}
|
||||
m.aadCacheMu.Lock()
|
||||
defer m.aadCacheMu.Unlock()
|
||||
discoveryResponse, err := m.requests.AADInstanceDiscovery(ctx, authorityInfo)
|
||||
@ -459,6 +464,7 @@ func (m *Manager) readAccount(homeAccountID string, envAliases []string, realm s
|
||||
|
||||
func (m *Manager) writeAccount(account shared.Account) error {
|
||||
key := account.Key()
|
||||
|
||||
m.contractMu.Lock()
|
||||
defer m.contractMu.Unlock()
|
||||
m.contract.Accounts[key] = account
|
||||
@ -31,4 +31,6 @@ type TokenProviderResult struct {
|
||||
AccessToken string
|
||||
// ExpiresInSeconds is the lifetime of the token in seconds
|
||||
ExpiresInSeconds int
|
||||
// RefreshInSeconds indicates the suggested time to refresh the token, if any
|
||||
RefreshInSeconds int
|
||||
}
|
||||
|
||||
@ -146,7 +146,8 @@ func (s *Server) handler(w http.ResponseWriter, r *http.Request) {
|
||||
// Note: It is a little weird we handle some errors by not going to the failPage. If they all should,
|
||||
// change this to s.error() and make s.error() write the failPage instead of an error code.
|
||||
_, _ = w.Write([]byte(fmt.Sprintf(failPage, headerErr, desc)))
|
||||
s.putResult(Result{Err: fmt.Errorf(desc)})
|
||||
s.putResult(Result{Err: fmt.Errorf("%s", desc)})
|
||||
|
||||
return
|
||||
}
|
||||
|
||||
|
||||
@ -111,7 +111,7 @@ func (t *Client) Credential(ctx context.Context, authParams authority.AuthParams
|
||||
Scopes: scopes,
|
||||
TenantID: authParams.AuthorityInfo.Tenant,
|
||||
}
|
||||
tr, err := cred.TokenProvider(ctx, params)
|
||||
pr, err := cred.TokenProvider(ctx, params)
|
||||
if err != nil {
|
||||
if len(scopes) == 0 {
|
||||
err = fmt.Errorf("token request had an empty authority.AuthParams.Scopes, which may cause the following error: %w", err)
|
||||
@ -119,14 +119,18 @@ func (t *Client) Credential(ctx context.Context, authParams authority.AuthParams
|
||||
}
|
||||
return accesstokens.TokenResponse{}, err
|
||||
}
|
||||
return accesstokens.TokenResponse{
|
||||
tr := accesstokens.TokenResponse{
|
||||
TokenType: authParams.AuthnScheme.AccessTokenType(),
|
||||
AccessToken: tr.AccessToken,
|
||||
ExpiresOn: internalTime.DurationTime{
|
||||
T: now.Add(time.Duration(tr.ExpiresInSeconds) * time.Second),
|
||||
},
|
||||
AccessToken: pr.AccessToken,
|
||||
ExpiresOn: now.Add(time.Duration(pr.ExpiresInSeconds) * time.Second),
|
||||
GrantedScopes: accesstokens.Scopes{Slice: authParams.Scopes},
|
||||
}, nil
|
||||
}
|
||||
if pr.RefreshInSeconds > 0 {
|
||||
tr.RefreshOn = internalTime.DurationTime{
|
||||
T: now.Add(time.Duration(pr.RefreshInSeconds) * time.Second),
|
||||
}
|
||||
}
|
||||
return tr, nil
|
||||
}
|
||||
|
||||
if err := t.resolveEndpoint(ctx, &authParams, ""); err != nil {
|
||||
|
||||
@ -17,6 +17,7 @@ import (
|
||||
|
||||
/* #nosec */
|
||||
"crypto/sha1"
|
||||
"crypto/sha256"
|
||||
"crypto/x509"
|
||||
"encoding/base64"
|
||||
"encoding/json"
|
||||
@ -68,7 +69,7 @@ type DeviceCodeResponse struct {
|
||||
|
||||
UserCode string `json:"user_code"`
|
||||
DeviceCode string `json:"device_code"`
|
||||
VerificationURL string `json:"verification_url"`
|
||||
VerificationURL string `json:"verification_uri"`
|
||||
ExpiresIn int `json:"expires_in"`
|
||||
Interval int `json:"interval"`
|
||||
Message string `json:"message"`
|
||||
@ -112,19 +113,31 @@ func (c *Credential) JWT(ctx context.Context, authParams authority.AuthParams) (
|
||||
}
|
||||
return c.AssertionCallback(ctx, options)
|
||||
}
|
||||
|
||||
token := jwt.NewWithClaims(jwt.SigningMethodRS256, jwt.MapClaims{
|
||||
claims := jwt.MapClaims{
|
||||
"aud": authParams.Endpoints.TokenEndpoint,
|
||||
"exp": json.Number(strconv.FormatInt(time.Now().Add(10*time.Minute).Unix(), 10)),
|
||||
"iss": authParams.ClientID,
|
||||
"jti": uuid.New().String(),
|
||||
"nbf": json.Number(strconv.FormatInt(time.Now().Unix(), 10)),
|
||||
"sub": authParams.ClientID,
|
||||
})
|
||||
}
|
||||
|
||||
isADFSorDSTS := authParams.AuthorityInfo.AuthorityType == authority.ADFS ||
|
||||
authParams.AuthorityInfo.AuthorityType == authority.DSTS
|
||||
|
||||
var signingMethod jwt.SigningMethod = jwt.SigningMethodPS256
|
||||
thumbprintKey := "x5t#S256"
|
||||
|
||||
if isADFSorDSTS {
|
||||
signingMethod = jwt.SigningMethodRS256
|
||||
thumbprintKey = "x5t"
|
||||
}
|
||||
|
||||
token := jwt.NewWithClaims(signingMethod, claims)
|
||||
token.Header = map[string]interface{}{
|
||||
"alg": "RS256",
|
||||
"alg": signingMethod.Alg(),
|
||||
"typ": "JWT",
|
||||
"x5t": base64.StdEncoding.EncodeToString(thumbprint(c.Cert)),
|
||||
thumbprintKey: base64.StdEncoding.EncodeToString(thumbprint(c.Cert, signingMethod.Alg())),
|
||||
}
|
||||
|
||||
if authParams.SendX5C {
|
||||
@ -133,17 +146,23 @@ func (c *Credential) JWT(ctx context.Context, authParams authority.AuthParams) (
|
||||
|
||||
assertion, err := token.SignedString(c.Key)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("unable to sign a JWT token using private key: %w", err)
|
||||
return "", fmt.Errorf("unable to sign JWT token: %w", err)
|
||||
}
|
||||
|
||||
return assertion, nil
|
||||
}
|
||||
|
||||
// thumbprint runs the asn1.Der bytes through sha1 for use in the x5t parameter of JWT.
|
||||
// https://tools.ietf.org/html/rfc7517#section-4.8
|
||||
func thumbprint(cert *x509.Certificate) []byte {
|
||||
/* #nosec */
|
||||
a := sha1.Sum(cert.Raw)
|
||||
return a[:]
|
||||
func thumbprint(cert *x509.Certificate, alg string) []byte {
|
||||
switch alg {
|
||||
case jwt.SigningMethodRS256.Name: // identity providers like ADFS don't support SHA256 assertions, so need to support this
|
||||
hash := sha1.Sum(cert.Raw) /* #nosec */
|
||||
return hash[:]
|
||||
default:
|
||||
hash := sha256.Sum256(cert.Raw)
|
||||
return hash[:]
|
||||
}
|
||||
}
|
||||
|
||||
// Client represents the REST calls to get tokens from token generator backends.
|
||||
@ -262,11 +281,7 @@ func (c Client) FromClientSecret(ctx context.Context, authParameters authority.A
|
||||
qv.Set(clientID, authParameters.ClientID)
|
||||
addScopeQueryParam(qv, authParameters)
|
||||
|
||||
token, err := c.doTokenResp(ctx, authParameters, qv)
|
||||
if err != nil {
|
||||
return token, fmt.Errorf("FromClientSecret(): %w", err)
|
||||
}
|
||||
return token, nil
|
||||
return c.doTokenResp(ctx, authParameters, qv)
|
||||
}
|
||||
|
||||
func (c Client) FromAssertion(ctx context.Context, authParameters authority.AuthParams, assertion string) (TokenResponse, error) {
|
||||
@ -281,11 +296,7 @@ func (c Client) FromAssertion(ctx context.Context, authParameters authority.Auth
|
||||
qv.Set(clientInfo, clientInfoVal)
|
||||
addScopeQueryParam(qv, authParameters)
|
||||
|
||||
token, err := c.doTokenResp(ctx, authParameters, qv)
|
||||
if err != nil {
|
||||
return token, fmt.Errorf("FromAssertion(): %w", err)
|
||||
}
|
||||
return token, nil
|
||||
return c.doTokenResp(ctx, authParameters, qv)
|
||||
}
|
||||
|
||||
func (c Client) FromUserAssertionClientSecret(ctx context.Context, authParameters authority.AuthParams, userAssertion string, clientSecret string) (TokenResponse, error) {
|
||||
|
||||
@ -10,6 +10,7 @@ import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"reflect"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
@ -173,16 +174,77 @@ type TokenResponse struct {
|
||||
FamilyID string `json:"foci"`
|
||||
IDToken IDToken `json:"id_token"`
|
||||
ClientInfo ClientInfo `json:"client_info"`
|
||||
ExpiresOn internalTime.DurationTime `json:"expires_in"`
|
||||
RefreshOn internalTime.DurationTime `json:"refresh_in,omitempty"`
|
||||
ExpiresOn time.Time `json:"-"`
|
||||
ExtExpiresOn internalTime.DurationTime `json:"ext_expires_in"`
|
||||
GrantedScopes Scopes `json:"scope"`
|
||||
DeclinedScopes []string // This is derived
|
||||
|
||||
AdditionalFields map[string]interface{}
|
||||
|
||||
scopesComputed bool
|
||||
}
|
||||
|
||||
func (tr *TokenResponse) UnmarshalJSON(data []byte) error {
|
||||
type Alias TokenResponse
|
||||
aux := &struct {
|
||||
ExpiresIn internalTime.DurationTime `json:"expires_in,omitempty"`
|
||||
ExpiresOn any `json:"expires_on,omitempty"`
|
||||
*Alias
|
||||
}{
|
||||
Alias: (*Alias)(tr),
|
||||
}
|
||||
|
||||
// Unmarshal the JSON data into the aux struct
|
||||
if err := json.Unmarshal(data, &aux); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
// Function to parse different date formats
|
||||
// This is a workaround for the issue described here:
|
||||
// https://github.com/AzureAD/microsoft-authentication-library-for-dotnet/issues/4963
|
||||
parseExpiresOn := func(expiresOn string) (time.Time, error) {
|
||||
var formats = []string{
|
||||
"01/02/2006 15:04:05", // MM/dd/yyyy HH:mm:ss
|
||||
"2006-01-02 15:04:05", // yyyy-MM-dd HH:mm:ss
|
||||
time.RFC3339Nano, // ISO 8601 (with nanosecond precision)
|
||||
}
|
||||
|
||||
for _, format := range formats {
|
||||
if t, err := time.Parse(format, expiresOn); err == nil {
|
||||
return t, nil
|
||||
}
|
||||
}
|
||||
return time.Time{}, fmt.Errorf("invalid ExpiresOn format: %s", expiresOn)
|
||||
}
|
||||
|
||||
if expiresOnStr, ok := aux.ExpiresOn.(string); ok {
|
||||
if ts, err := strconv.ParseInt(expiresOnStr, 10, 64); err == nil {
|
||||
tr.ExpiresOn = time.Unix(ts, 0)
|
||||
return nil
|
||||
}
|
||||
if expiresOnStr != "" {
|
||||
if t, err := parseExpiresOn(expiresOnStr); err != nil {
|
||||
return err
|
||||
} else {
|
||||
tr.ExpiresOn = t
|
||||
return nil
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Check if ExpiresOn is a number (Unix timestamp or ISO 8601)
|
||||
if expiresOnNum, ok := aux.ExpiresOn.(float64); ok {
|
||||
tr.ExpiresOn = time.Unix(int64(expiresOnNum), 0)
|
||||
return nil
|
||||
}
|
||||
|
||||
if !aux.ExpiresIn.T.IsZero() {
|
||||
tr.ExpiresOn = aux.ExpiresIn.T
|
||||
return nil
|
||||
}
|
||||
return errors.New("expires_in and expires_on are both missing or invalid")
|
||||
}
|
||||
|
||||
// ComputeScope computes the final scopes based on what was granted by the server and
|
||||
// what our AuthParams were from the authority server. Per OAuth spec, if no scopes are returned, the response should be treated as if all scopes were granted
|
||||
// This behavior can be observed in client assertion flows, but can happen at any time, this check ensures we treat
|
||||
|
||||
@ -98,7 +98,7 @@ func (c *Client) JSONCall(ctx context.Context, endpoint string, headers http.Hea
|
||||
|
||||
if resp != nil {
|
||||
if err := unmarshal(data, resp); err != nil {
|
||||
return fmt.Errorf("json decode error: %w\njson message bytes were: %s", err, string(data))
|
||||
return errors.InvalidJsonErr{Err: fmt.Errorf("json decode error: %w\njson message bytes were: %s", err, string(data))}
|
||||
}
|
||||
}
|
||||
return nil
|
||||
@ -221,7 +221,7 @@ func (c *Client) URLFormCall(ctx context.Context, endpoint string, qv url.Values
|
||||
}
|
||||
if resp != nil {
|
||||
if err := unmarshal(data, resp); err != nil {
|
||||
return fmt.Errorf("json decode error: %w\nraw message was: %s", err, string(data))
|
||||
return errors.InvalidJsonErr{Err: fmt.Errorf("json decode error: %w\nraw message was: %s", err, string(data))}
|
||||
}
|
||||
}
|
||||
return nil
|
||||
|
||||
@ -5,4 +5,4 @@
|
||||
package version
|
||||
|
||||
// Version is the version of this client package that is communicated to the server.
|
||||
const Version = "1.2.0"
|
||||
const Version = "1.4.2"
|
||||
|
||||
28
vendor/github.com/AzureAD/microsoft-authentication-library-for-go/apps/managedidentity/azure_ml.go
generated
vendored
Normal file
28
vendor/github.com/AzureAD/microsoft-authentication-library-for-go/apps/managedidentity/azure_ml.go
generated
vendored
Normal file
@ -0,0 +1,28 @@
|
||||
// Copyright (c) Microsoft Corporation.
|
||||
// Licensed under the MIT license.
|
||||
|
||||
package managedidentity
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"os"
|
||||
)
|
||||
|
||||
func createAzureMLAuthRequest(ctx context.Context, id ID, resource string) (*http.Request, error) {
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodGet, os.Getenv(msiEndpointEnvVar), nil)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
req.Header.Set("secret", os.Getenv(msiSecretEnvVar))
|
||||
q := req.URL.Query()
|
||||
q.Set(apiVersionQueryParameterName, azureMLAPIVersion)
|
||||
q.Set(resourceQueryParameterName, resource)
|
||||
q.Set("clientid", os.Getenv("DEFAULT_IDENTITY_CLIENT_ID"))
|
||||
if cid, ok := id.(UserAssignedClientID); ok {
|
||||
q.Set("clientid", string(cid))
|
||||
}
|
||||
req.URL.RawQuery = q.Encode()
|
||||
return req, nil
|
||||
}
|
||||
37
vendor/github.com/AzureAD/microsoft-authentication-library-for-go/apps/managedidentity/cloud_shell.go
generated
vendored
Normal file
37
vendor/github.com/AzureAD/microsoft-authentication-library-for-go/apps/managedidentity/cloud_shell.go
generated
vendored
Normal file
@ -0,0 +1,37 @@
|
||||
// Copyright (c) Microsoft Corporation.
|
||||
// Licensed under the MIT license.
|
||||
|
||||
package managedidentity
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"io"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"os"
|
||||
"strings"
|
||||
)
|
||||
|
||||
func createCloudShellAuthRequest(ctx context.Context, resource string) (*http.Request, error) {
|
||||
msiEndpoint := os.Getenv(msiEndpointEnvVar)
|
||||
msiEndpointParsed, err := url.Parse(msiEndpoint)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("couldn't parse %q: %s", msiEndpoint, err)
|
||||
}
|
||||
|
||||
data := url.Values{}
|
||||
data.Set(resourceQueryParameterName, resource)
|
||||
msiDataEncoded := data.Encode()
|
||||
body := io.NopCloser(strings.NewReader(msiDataEncoded))
|
||||
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodPost, msiEndpointParsed.String(), body)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("error creating http request %s", err)
|
||||
}
|
||||
|
||||
req.Header.Set(metaHTTPHeaderName, "true")
|
||||
req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
|
||||
|
||||
return req, nil
|
||||
}
|
||||
717
vendor/github.com/AzureAD/microsoft-authentication-library-for-go/apps/managedidentity/managedidentity.go
generated
vendored
Normal file
717
vendor/github.com/AzureAD/microsoft-authentication-library-for-go/apps/managedidentity/managedidentity.go
generated
vendored
Normal file
@ -0,0 +1,717 @@
|
||||
// Copyright (c) Microsoft Corporation.
|
||||
// Licensed under the MIT license.
|
||||
|
||||
/*
|
||||
Package managedidentity provides a client for retrieval of Managed Identity applications.
|
||||
The Managed Identity Client is used to acquire a token for managed identity assigned to
|
||||
an azure resource such as Azure function, app service, virtual machine, etc. to acquire a token
|
||||
without using credentials.
|
||||
*/
|
||||
package managedidentity
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"io"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"strings"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/errors"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/internal/base"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/internal/base/storage"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/internal/oauth/ops"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/internal/oauth/ops/accesstokens"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/internal/oauth/ops/authority"
|
||||
"github.com/AzureAD/microsoft-authentication-library-for-go/apps/internal/shared"
|
||||
)
|
||||
|
||||
// AuthResult contains the results of one token acquisition operation.
|
||||
// For details see https://aka.ms/msal-net-authenticationresult
|
||||
type AuthResult = base.AuthResult
|
||||
|
||||
type TokenSource = base.TokenSource
|
||||
|
||||
const (
|
||||
TokenSourceIdentityProvider = base.TokenSourceIdentityProvider
|
||||
TokenSourceCache = base.TokenSourceCache
|
||||
)
|
||||
|
||||
const (
|
||||
// DefaultToIMDS indicates that the source is defaulted to IMDS when no environment variables are set.
|
||||
DefaultToIMDS Source = "DefaultToIMDS"
|
||||
AzureArc Source = "AzureArc"
|
||||
ServiceFabric Source = "ServiceFabric"
|
||||
CloudShell Source = "CloudShell"
|
||||
AzureML Source = "AzureML"
|
||||
AppService Source = "AppService"
|
||||
|
||||
// General request query parameter names
|
||||
metaHTTPHeaderName = "Metadata"
|
||||
apiVersionQueryParameterName = "api-version"
|
||||
resourceQueryParameterName = "resource"
|
||||
wwwAuthenticateHeaderName = "www-authenticate"
|
||||
|
||||
// UAMI query parameter name
|
||||
miQueryParameterClientId = "client_id"
|
||||
miQueryParameterObjectId = "object_id"
|
||||
miQueryParameterPrincipalId = "principal_id"
|
||||
miQueryParameterResourceIdIMDS = "msi_res_id"
|
||||
miQueryParameterResourceId = "mi_res_id"
|
||||
|
||||
// IMDS
|
||||
imdsDefaultEndpoint = "http://169.254.169.254/metadata/identity/oauth2/token"
|
||||
imdsAPIVersion = "2018-02-01"
|
||||
systemAssignedManagedIdentity = "system_assigned_managed_identity"
|
||||
|
||||
// Azure Arc
|
||||
azureArcEndpoint = "http://127.0.0.1:40342/metadata/identity/oauth2/token"
|
||||
azureArcAPIVersion = "2020-06-01"
|
||||
azureArcFileExtension = ".key"
|
||||
azureArcMaxFileSizeBytes int64 = 4096
|
||||
linuxTokenPath = "/var/opt/azcmagent/tokens" // #nosec G101
|
||||
linuxHimdsPath = "/opt/azcmagent/bin/himds"
|
||||
azureConnectedMachine = "AzureConnectedMachineAgent"
|
||||
himdsExecutableName = "himds.exe"
|
||||
tokenName = "Tokens"
|
||||
|
||||
// App Service
|
||||
appServiceAPIVersion = "2019-08-01"
|
||||
|
||||
// AzureML
|
||||
azureMLAPIVersion = "2017-09-01"
|
||||
// Service Fabric
|
||||
serviceFabricAPIVersion = "2019-07-01-preview"
|
||||
|
||||
// Environment Variables
|
||||
identityEndpointEnvVar = "IDENTITY_ENDPOINT"
|
||||
identityHeaderEnvVar = "IDENTITY_HEADER"
|
||||
azurePodIdentityAuthorityHostEnvVar = "AZURE_POD_IDENTITY_AUTHORITY_HOST"
|
||||
imdsEndVar = "IMDS_ENDPOINT"
|
||||
msiEndpointEnvVar = "MSI_ENDPOINT"
|
||||
msiSecretEnvVar = "MSI_SECRET"
|
||||
identityServerThumbprintEnvVar = "IDENTITY_SERVER_THUMBPRINT"
|
||||
|
||||
defaultRetryCount = 3
|
||||
)
|
||||
|
||||
var retryCodesForIMDS = []int{
|
||||
http.StatusNotFound, // 404
|
||||
http.StatusGone, // 410
|
||||
http.StatusTooManyRequests, // 429
|
||||
http.StatusInternalServerError, // 500
|
||||
http.StatusNotImplemented, // 501
|
||||
http.StatusBadGateway, // 502
|
||||
http.StatusServiceUnavailable, // 503
|
||||
http.StatusGatewayTimeout, // 504
|
||||
http.StatusHTTPVersionNotSupported, // 505
|
||||
http.StatusVariantAlsoNegotiates, // 506
|
||||
http.StatusInsufficientStorage, // 507
|
||||
http.StatusLoopDetected, // 508
|
||||
http.StatusNotExtended, // 510
|
||||
http.StatusNetworkAuthenticationRequired, // 511
|
||||
}
|
||||
|
||||
var retryStatusCodes = []int{
|
||||
http.StatusRequestTimeout, // 408
|
||||
http.StatusTooManyRequests, // 429
|
||||
http.StatusInternalServerError, // 500
|
||||
http.StatusBadGateway, // 502
|
||||
http.StatusServiceUnavailable, // 503
|
||||
http.StatusGatewayTimeout, // 504
|
||||
}
|
||||
|
||||
var getAzureArcPlatformPath = func(platform string) string {
|
||||
switch platform {
|
||||
case "windows":
|
||||
return filepath.Join(os.Getenv("ProgramData"), azureConnectedMachine, tokenName)
|
||||
case "linux":
|
||||
return linuxTokenPath
|
||||
default:
|
||||
return ""
|
||||
}
|
||||
}
|
||||
|
||||
var getAzureArcHimdsFilePath = func(platform string) string {
|
||||
switch platform {
|
||||
case "windows":
|
||||
return filepath.Join(os.Getenv("ProgramData"), azureConnectedMachine, himdsExecutableName)
|
||||
case "linux":
|
||||
return linuxHimdsPath
|
||||
default:
|
||||
return ""
|
||||
}
|
||||
}
|
||||
|
||||
type Source string
|
||||
|
||||
type ID interface {
|
||||
value() string
|
||||
}
|
||||
|
||||
type systemAssignedValue string // its private for a reason to make the input consistent.
|
||||
type UserAssignedClientID string
|
||||
type UserAssignedObjectID string
|
||||
type UserAssignedResourceID string
|
||||
|
||||
func (s systemAssignedValue) value() string { return string(s) }
|
||||
func (c UserAssignedClientID) value() string { return string(c) }
|
||||
func (o UserAssignedObjectID) value() string { return string(o) }
|
||||
func (r UserAssignedResourceID) value() string { return string(r) }
|
||||
func SystemAssigned() ID {
|
||||
return systemAssignedValue(systemAssignedManagedIdentity)
|
||||
}
|
||||
|
||||
// cache never uses the client because instance discovery is always disabled.
|
||||
var cacheManager *storage.Manager = storage.New(nil)
|
||||
|
||||
type Client struct {
|
||||
httpClient ops.HTTPClient
|
||||
miType ID
|
||||
source Source
|
||||
authParams authority.AuthParams
|
||||
retryPolicyEnabled bool
|
||||
canRefresh *atomic.Value
|
||||
}
|
||||
|
||||
type AcquireTokenOptions struct {
|
||||
claims string
|
||||
}
|
||||
|
||||
type ClientOption func(*Client)
|
||||
|
||||
type AcquireTokenOption func(o *AcquireTokenOptions)
|
||||
|
||||
// WithClaims sets additional claims to request for the token, such as those required by token revocation or conditional access policies.
|
||||
// Use this option when Azure AD returned a claims challenge for a prior request. The argument must be decoded.
|
||||
func WithClaims(claims string) AcquireTokenOption {
|
||||
return func(o *AcquireTokenOptions) {
|
||||
o.claims = claims
|
||||
}
|
||||
}
|
||||
|
||||
// WithHTTPClient allows for a custom HTTP client to be set.
|
||||
func WithHTTPClient(httpClient ops.HTTPClient) ClientOption {
|
||||
return func(c *Client) {
|
||||
c.httpClient = httpClient
|
||||
}
|
||||
}
|
||||
|
||||
func WithRetryPolicyDisabled() ClientOption {
|
||||
return func(c *Client) {
|
||||
c.retryPolicyEnabled = false
|
||||
}
|
||||
}
|
||||
|
||||
// Client to be used to acquire tokens for managed identity.
|
||||
// ID: [SystemAssigned], [UserAssignedClientID], [UserAssignedResourceID], [UserAssignedObjectID]
|
||||
//
|
||||
// Options: [WithHTTPClient]
|
||||
func New(id ID, options ...ClientOption) (Client, error) {
|
||||
source, err := GetSource()
|
||||
if err != nil {
|
||||
return Client{}, err
|
||||
}
|
||||
|
||||
// Check for user-assigned restrictions based on the source
|
||||
switch source {
|
||||
case AzureArc:
|
||||
switch id.(type) {
|
||||
case UserAssignedClientID, UserAssignedResourceID, UserAssignedObjectID:
|
||||
return Client{}, errors.New("Azure Arc doesn't support user-assigned managed identities")
|
||||
}
|
||||
case AzureML:
|
||||
switch id.(type) {
|
||||
case UserAssignedObjectID, UserAssignedResourceID:
|
||||
return Client{}, errors.New("Azure ML supports specifying a user-assigned managed identity by client ID only")
|
||||
}
|
||||
case CloudShell:
|
||||
switch id.(type) {
|
||||
case UserAssignedClientID, UserAssignedResourceID, UserAssignedObjectID:
|
||||
return Client{}, errors.New("Cloud Shell doesn't support user-assigned managed identities")
|
||||
}
|
||||
case ServiceFabric:
|
||||
switch id.(type) {
|
||||
case UserAssignedClientID, UserAssignedResourceID, UserAssignedObjectID:
|
||||
return Client{}, errors.New("Service Fabric API doesn't support specifying a user-assigned identity. The identity is determined by cluster resource configuration. See https://aka.ms/servicefabricmi")
|
||||
}
|
||||
}
|
||||
|
||||
switch t := id.(type) {
|
||||
case UserAssignedClientID:
|
||||
if len(string(t)) == 0 {
|
||||
return Client{}, fmt.Errorf("empty %T", t)
|
||||
}
|
||||
case UserAssignedResourceID:
|
||||
if len(string(t)) == 0 {
|
||||
return Client{}, fmt.Errorf("empty %T", t)
|
||||
}
|
||||
case UserAssignedObjectID:
|
||||
if len(string(t)) == 0 {
|
||||
return Client{}, fmt.Errorf("empty %T", t)
|
||||
}
|
||||
case systemAssignedValue:
|
||||
default:
|
||||
return Client{}, fmt.Errorf("unsupported type %T", id)
|
||||
}
|
||||
zero := atomic.Value{}
|
||||
zero.Store(false)
|
||||
client := Client{
|
||||
miType: id,
|
||||
httpClient: shared.DefaultClient,
|
||||
retryPolicyEnabled: true,
|
||||
source: source,
|
||||
canRefresh: &zero,
|
||||
}
|
||||
for _, option := range options {
|
||||
option(&client)
|
||||
}
|
||||
fakeAuthInfo, err := authority.NewInfoFromAuthorityURI("https://login.microsoftonline.com/managed_identity", false, true)
|
||||
if err != nil {
|
||||
return Client{}, err
|
||||
}
|
||||
client.authParams = authority.NewAuthParams(client.miType.value(), fakeAuthInfo)
|
||||
return client, nil
|
||||
}
|
||||
|
||||
// GetSource detects and returns the managed identity source available on the environment.
|
||||
func GetSource() (Source, error) {
|
||||
identityEndpoint := os.Getenv(identityEndpointEnvVar)
|
||||
identityHeader := os.Getenv(identityHeaderEnvVar)
|
||||
identityServerThumbprint := os.Getenv(identityServerThumbprintEnvVar)
|
||||
msiEndpoint := os.Getenv(msiEndpointEnvVar)
|
||||
msiSecret := os.Getenv(msiSecretEnvVar)
|
||||
imdsEndpoint := os.Getenv(imdsEndVar)
|
||||
|
||||
if identityEndpoint != "" && identityHeader != "" {
|
||||
if identityServerThumbprint != "" {
|
||||
return ServiceFabric, nil
|
||||
}
|
||||
return AppService, nil
|
||||
} else if msiEndpoint != "" {
|
||||
if msiSecret != "" {
|
||||
return AzureML, nil
|
||||
} else {
|
||||
return CloudShell, nil
|
||||
}
|
||||
} else if isAzureArcEnvironment(identityEndpoint, imdsEndpoint) {
|
||||
return AzureArc, nil
|
||||
}
|
||||
|
||||
return DefaultToIMDS, nil
|
||||
}
|
||||
|
||||
// This function wraps time.Now() and is used for refreshing the application
|
||||
// was created to test the function against refreshin
|
||||
var now = time.Now
|
||||
|
||||
// Acquires tokens from the configured managed identity on an azure resource.
|
||||
//
|
||||
// Resource: scopes application is requesting access to
|
||||
// Options: [WithClaims]
|
||||
func (c Client) AcquireToken(ctx context.Context, resource string, options ...AcquireTokenOption) (AuthResult, error) {
|
||||
resource = strings.TrimSuffix(resource, "/.default")
|
||||
o := AcquireTokenOptions{}
|
||||
for _, option := range options {
|
||||
option(&o)
|
||||
}
|
||||
c.authParams.Scopes = []string{resource}
|
||||
|
||||
// ignore cached access tokens when given claims
|
||||
if o.claims == "" {
|
||||
stResp, err := cacheManager.Read(ctx, c.authParams)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
ar, err := base.AuthResultFromStorage(stResp)
|
||||
if err == nil {
|
||||
if !stResp.AccessToken.RefreshOn.T.IsZero() && !stResp.AccessToken.RefreshOn.T.After(now()) && c.canRefresh.CompareAndSwap(false, true) {
|
||||
defer c.canRefresh.Store(false)
|
||||
if tr, er := c.getToken(ctx, resource); er == nil {
|
||||
return tr, nil
|
||||
}
|
||||
}
|
||||
ar.AccessToken, err = c.authParams.AuthnScheme.FormatAccessToken(ar.AccessToken)
|
||||
return ar, err
|
||||
}
|
||||
}
|
||||
return c.getToken(ctx, resource)
|
||||
}
|
||||
|
||||
func (c Client) getToken(ctx context.Context, resource string) (AuthResult, error) {
|
||||
switch c.source {
|
||||
case AzureArc:
|
||||
return c.acquireTokenForAzureArc(ctx, resource)
|
||||
case AzureML:
|
||||
return c.acquireTokenForAzureML(ctx, resource)
|
||||
case CloudShell:
|
||||
return c.acquireTokenForCloudShell(ctx, resource)
|
||||
case DefaultToIMDS:
|
||||
return c.acquireTokenForIMDS(ctx, resource)
|
||||
case AppService:
|
||||
return c.acquireTokenForAppService(ctx, resource)
|
||||
case ServiceFabric:
|
||||
return c.acquireTokenForServiceFabric(ctx, resource)
|
||||
default:
|
||||
return AuthResult{}, fmt.Errorf("unsupported source %q", c.source)
|
||||
}
|
||||
}
|
||||
|
||||
func (c Client) acquireTokenForAppService(ctx context.Context, resource string) (AuthResult, error) {
|
||||
req, err := createAppServiceAuthRequest(ctx, c.miType, resource)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
tokenResponse, err := c.getTokenForRequest(req, resource)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
return authResultFromToken(c.authParams, tokenResponse)
|
||||
}
|
||||
|
||||
func (c Client) acquireTokenForIMDS(ctx context.Context, resource string) (AuthResult, error) {
|
||||
req, err := createIMDSAuthRequest(ctx, c.miType, resource)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
tokenResponse, err := c.getTokenForRequest(req, resource)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
return authResultFromToken(c.authParams, tokenResponse)
|
||||
}
|
||||
|
||||
func (c Client) acquireTokenForCloudShell(ctx context.Context, resource string) (AuthResult, error) {
|
||||
req, err := createCloudShellAuthRequest(ctx, resource)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
tokenResponse, err := c.getTokenForRequest(req, resource)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
return authResultFromToken(c.authParams, tokenResponse)
|
||||
}
|
||||
|
||||
func (c Client) acquireTokenForAzureML(ctx context.Context, resource string) (AuthResult, error) {
|
||||
req, err := createAzureMLAuthRequest(ctx, c.miType, resource)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
tokenResponse, err := c.getTokenForRequest(req, resource)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
return authResultFromToken(c.authParams, tokenResponse)
|
||||
}
|
||||
|
||||
func (c Client) acquireTokenForServiceFabric(ctx context.Context, resource string) (AuthResult, error) {
|
||||
req, err := createServiceFabricAuthRequest(ctx, resource)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
tokenResponse, err := c.getTokenForRequest(req, resource)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
return authResultFromToken(c.authParams, tokenResponse)
|
||||
}
|
||||
|
||||
func (c Client) acquireTokenForAzureArc(ctx context.Context, resource string) (AuthResult, error) {
|
||||
req, err := createAzureArcAuthRequest(ctx, resource, "")
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
|
||||
response, err := c.httpClient.Do(req)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
defer response.Body.Close()
|
||||
|
||||
if response.StatusCode != http.StatusUnauthorized {
|
||||
return AuthResult{}, fmt.Errorf("expected a 401 response, received %d", response.StatusCode)
|
||||
}
|
||||
|
||||
secret, err := c.getAzureArcSecretKey(response, runtime.GOOS)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
|
||||
secondRequest, err := createAzureArcAuthRequest(ctx, resource, string(secret))
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
|
||||
tokenResponse, err := c.getTokenForRequest(secondRequest, resource)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
return authResultFromToken(c.authParams, tokenResponse)
|
||||
}
|
||||
|
||||
func authResultFromToken(authParams authority.AuthParams, token accesstokens.TokenResponse) (AuthResult, error) {
|
||||
if cacheManager == nil {
|
||||
return AuthResult{}, errors.New("cache instance is nil")
|
||||
}
|
||||
account, err := cacheManager.Write(authParams, token)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
// if refreshOn is not set, set it to half of the time until expiry if expiry is more than 2 hours away
|
||||
if token.RefreshOn.T.IsZero() {
|
||||
if lifetime := time.Until(token.ExpiresOn); lifetime > 2*time.Hour {
|
||||
token.RefreshOn.T = time.Now().Add(lifetime / 2)
|
||||
}
|
||||
}
|
||||
ar, err := base.NewAuthResult(token, account)
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
ar.AccessToken, err = authParams.AuthnScheme.FormatAccessToken(ar.AccessToken)
|
||||
return ar, err
|
||||
}
|
||||
|
||||
// contains checks if the element is present in the list.
|
||||
func contains[T comparable](list []T, element T) bool {
|
||||
for _, v := range list {
|
||||
if v == element {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// retry performs an HTTP request with retries based on the provided options.
|
||||
func (c Client) retry(maxRetries int, req *http.Request) (*http.Response, error) {
|
||||
var resp *http.Response
|
||||
var err error
|
||||
for attempt := 0; attempt < maxRetries; attempt++ {
|
||||
tryCtx, tryCancel := context.WithTimeout(req.Context(), time.Minute)
|
||||
defer tryCancel()
|
||||
if resp != nil && resp.Body != nil {
|
||||
_, _ = io.Copy(io.Discard, resp.Body)
|
||||
resp.Body.Close()
|
||||
}
|
||||
cloneReq := req.Clone(tryCtx)
|
||||
resp, err = c.httpClient.Do(cloneReq)
|
||||
retrylist := retryStatusCodes
|
||||
if c.source == DefaultToIMDS {
|
||||
retrylist = retryCodesForIMDS
|
||||
}
|
||||
if err == nil && !contains(retrylist, resp.StatusCode) {
|
||||
return resp, nil
|
||||
}
|
||||
select {
|
||||
case <-time.After(time.Second):
|
||||
case <-req.Context().Done():
|
||||
err = req.Context().Err()
|
||||
return resp, err
|
||||
}
|
||||
}
|
||||
return resp, err
|
||||
}
|
||||
|
||||
func (c Client) getTokenForRequest(req *http.Request, resource string) (accesstokens.TokenResponse, error) {
|
||||
r := accesstokens.TokenResponse{}
|
||||
var resp *http.Response
|
||||
var err error
|
||||
|
||||
if c.retryPolicyEnabled {
|
||||
resp, err = c.retry(defaultRetryCount, req)
|
||||
} else {
|
||||
resp, err = c.httpClient.Do(req)
|
||||
}
|
||||
if err != nil {
|
||||
return r, err
|
||||
}
|
||||
responseBytes, err := io.ReadAll(resp.Body)
|
||||
defer resp.Body.Close()
|
||||
if err != nil {
|
||||
return r, err
|
||||
}
|
||||
switch resp.StatusCode {
|
||||
case http.StatusOK, http.StatusAccepted:
|
||||
default:
|
||||
sd := strings.TrimSpace(string(responseBytes))
|
||||
if sd != "" {
|
||||
return r, errors.CallErr{
|
||||
Req: req,
|
||||
Resp: resp,
|
||||
Err: fmt.Errorf("http call(%s)(%s) error: reply status code was %d:\n%s",
|
||||
req.URL.String(),
|
||||
req.Method,
|
||||
resp.StatusCode,
|
||||
sd),
|
||||
}
|
||||
}
|
||||
return r, errors.CallErr{
|
||||
Req: req,
|
||||
Resp: resp,
|
||||
Err: fmt.Errorf("http call(%s)(%s) error: reply status code was %d", req.URL.String(), req.Method, resp.StatusCode),
|
||||
}
|
||||
}
|
||||
|
||||
err = json.Unmarshal(responseBytes, &r)
|
||||
if err != nil {
|
||||
return r, errors.InvalidJsonErr{
|
||||
Err: fmt.Errorf("error parsing the json error: %s", err),
|
||||
}
|
||||
}
|
||||
r.GrantedScopes.Slice = append(r.GrantedScopes.Slice, resource)
|
||||
|
||||
return r, err
|
||||
}
|
||||
|
||||
func createAppServiceAuthRequest(ctx context.Context, id ID, resource string) (*http.Request, error) {
|
||||
identityEndpoint := os.Getenv(identityEndpointEnvVar)
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodGet, identityEndpoint, nil)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
req.Header.Set("X-IDENTITY-HEADER", os.Getenv(identityHeaderEnvVar))
|
||||
q := req.URL.Query()
|
||||
q.Set("api-version", appServiceAPIVersion)
|
||||
q.Set("resource", resource)
|
||||
switch t := id.(type) {
|
||||
case UserAssignedClientID:
|
||||
q.Set(miQueryParameterClientId, string(t))
|
||||
case UserAssignedResourceID:
|
||||
q.Set(miQueryParameterResourceId, string(t))
|
||||
case UserAssignedObjectID:
|
||||
q.Set(miQueryParameterObjectId, string(t))
|
||||
case systemAssignedValue:
|
||||
default:
|
||||
return nil, fmt.Errorf("unsupported type %T", id)
|
||||
}
|
||||
req.URL.RawQuery = q.Encode()
|
||||
return req, nil
|
||||
}
|
||||
|
||||
func createIMDSAuthRequest(ctx context.Context, id ID, resource string) (*http.Request, error) {
|
||||
msiEndpoint, err := url.Parse(imdsDefaultEndpoint)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("couldn't parse %q: %s", imdsDefaultEndpoint, err)
|
||||
}
|
||||
msiParameters := msiEndpoint.Query()
|
||||
msiParameters.Set(apiVersionQueryParameterName, imdsAPIVersion)
|
||||
msiParameters.Set(resourceQueryParameterName, resource)
|
||||
|
||||
switch t := id.(type) {
|
||||
case UserAssignedClientID:
|
||||
msiParameters.Set(miQueryParameterClientId, string(t))
|
||||
case UserAssignedResourceID:
|
||||
msiParameters.Set(miQueryParameterResourceIdIMDS, string(t))
|
||||
case UserAssignedObjectID:
|
||||
msiParameters.Set(miQueryParameterObjectId, string(t))
|
||||
case systemAssignedValue: // not adding anything
|
||||
default:
|
||||
return nil, fmt.Errorf("unsupported type %T", id)
|
||||
}
|
||||
|
||||
msiEndpoint.RawQuery = msiParameters.Encode()
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodGet, msiEndpoint.String(), nil)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("error creating http request %s", err)
|
||||
}
|
||||
req.Header.Set(metaHTTPHeaderName, "true")
|
||||
return req, nil
|
||||
}
|
||||
|
||||
func createAzureArcAuthRequest(ctx context.Context, resource string, key string) (*http.Request, error) {
|
||||
identityEndpoint := os.Getenv(identityEndpointEnvVar)
|
||||
if identityEndpoint == "" {
|
||||
identityEndpoint = azureArcEndpoint
|
||||
}
|
||||
msiEndpoint, parseErr := url.Parse(identityEndpoint)
|
||||
|
||||
if parseErr != nil {
|
||||
return nil, fmt.Errorf("couldn't parse %q: %s", identityEndpoint, parseErr)
|
||||
}
|
||||
|
||||
msiParameters := msiEndpoint.Query()
|
||||
msiParameters.Set(apiVersionQueryParameterName, azureArcAPIVersion)
|
||||
msiParameters.Set(resourceQueryParameterName, resource)
|
||||
|
||||
msiEndpoint.RawQuery = msiParameters.Encode()
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodGet, msiEndpoint.String(), nil)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("error creating http request %s", err)
|
||||
}
|
||||
req.Header.Set(metaHTTPHeaderName, "true")
|
||||
|
||||
if key != "" {
|
||||
req.Header.Set("Authorization", fmt.Sprintf("Basic %s", key))
|
||||
}
|
||||
|
||||
return req, nil
|
||||
}
|
||||
|
||||
func isAzureArcEnvironment(identityEndpoint, imdsEndpoint string) bool {
|
||||
if identityEndpoint != "" && imdsEndpoint != "" {
|
||||
return true
|
||||
}
|
||||
himdsFilePath := getAzureArcHimdsFilePath(runtime.GOOS)
|
||||
if himdsFilePath != "" {
|
||||
if _, err := os.Stat(himdsFilePath); err == nil {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
func (c *Client) getAzureArcSecretKey(response *http.Response, platform string) (string, error) {
|
||||
wwwAuthenticateHeader := response.Header.Get(wwwAuthenticateHeaderName)
|
||||
|
||||
if len(wwwAuthenticateHeader) == 0 {
|
||||
return "", errors.New("response has no www-authenticate header")
|
||||
}
|
||||
|
||||
// check if the platform is supported
|
||||
expectedSecretFilePath := getAzureArcPlatformPath(platform)
|
||||
if expectedSecretFilePath == "" {
|
||||
return "", errors.New("platform not supported, expected linux or windows")
|
||||
}
|
||||
|
||||
parts := strings.Split(wwwAuthenticateHeader, "Basic realm=")
|
||||
if len(parts) < 2 {
|
||||
return "", fmt.Errorf("basic realm= not found in the string, instead found: %s", wwwAuthenticateHeader)
|
||||
}
|
||||
|
||||
secretFilePath := parts
|
||||
|
||||
// check that the file in the file path is a .key file
|
||||
fileName := filepath.Base(secretFilePath[1])
|
||||
if !strings.HasSuffix(fileName, azureArcFileExtension) {
|
||||
return "", fmt.Errorf("invalid file extension, expected %s, got %s", azureArcFileExtension, filepath.Ext(fileName))
|
||||
}
|
||||
|
||||
// check that file path from header matches the expected file path for the platform
|
||||
if expectedSecretFilePath != filepath.Dir(secretFilePath[1]) {
|
||||
return "", fmt.Errorf("invalid file path, expected %s, got %s", expectedSecretFilePath, filepath.Dir(secretFilePath[1]))
|
||||
}
|
||||
|
||||
fileInfo, err := os.Stat(secretFilePath[1])
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("failed to get metadata for %s due to error: %s", secretFilePath[1], err)
|
||||
}
|
||||
|
||||
// Throw an error if the secret file's size is greater than 4096 bytes
|
||||
if s := fileInfo.Size(); s > azureArcMaxFileSizeBytes {
|
||||
return "", fmt.Errorf("invalid secret file size, expected %d, file size was %d", azureArcMaxFileSizeBytes, s)
|
||||
}
|
||||
|
||||
// Attempt to read the contents of the secret file
|
||||
secret, err := os.ReadFile(secretFilePath[1])
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("failed to read %q due to error: %s", secretFilePath[1], err)
|
||||
}
|
||||
|
||||
return string(secret), nil
|
||||
}
|
||||
25
vendor/github.com/AzureAD/microsoft-authentication-library-for-go/apps/managedidentity/servicefabric.go
generated
vendored
Normal file
25
vendor/github.com/AzureAD/microsoft-authentication-library-for-go/apps/managedidentity/servicefabric.go
generated
vendored
Normal file
@ -0,0 +1,25 @@
|
||||
// Copyright (c) Microsoft Corporation.
|
||||
// Licensed under the MIT license.
|
||||
|
||||
package managedidentity
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"os"
|
||||
)
|
||||
|
||||
func createServiceFabricAuthRequest(ctx context.Context, resource string) (*http.Request, error) {
|
||||
identityEndpoint := os.Getenv(identityEndpointEnvVar)
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodGet, identityEndpoint, nil)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
req.Header.Set("Accept", "application/json")
|
||||
req.Header.Set("Secret", os.Getenv(identityHeaderEnvVar))
|
||||
q := req.URL.Query()
|
||||
q.Set("api-version", serviceFabricAPIVersion)
|
||||
q.Set("resource", resource)
|
||||
req.URL.RawQuery = q.Encode()
|
||||
return req, nil
|
||||
}
|
||||
13
vendor/github.com/AzureAD/microsoft-authentication-library-for-go/apps/public/public.go
generated
vendored
13
vendor/github.com/AzureAD/microsoft-authentication-library-for-go/apps/public/public.go
generated
vendored
@ -51,6 +51,13 @@ type AuthenticationScheme = authority.AuthenticationScheme
|
||||
|
||||
type Account = shared.Account
|
||||
|
||||
type TokenSource = base.TokenSource
|
||||
|
||||
const (
|
||||
TokenSourceIdentityProvider = base.TokenSourceIdentityProvider
|
||||
TokenSourceCache = base.TokenSourceCache
|
||||
)
|
||||
|
||||
var errNoAccount = errors.New("no account was specified with public.WithSilentAccount(), or the specified account is invalid")
|
||||
|
||||
// clientOptions configures the Client's behavior.
|
||||
@ -387,7 +394,7 @@ func (pca Client) AcquireTokenByUsernamePassword(ctx context.Context, scopes []s
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
return pca.base.AuthResultFromToken(ctx, authParams, token, true)
|
||||
return pca.base.AuthResultFromToken(ctx, authParams, token)
|
||||
}
|
||||
|
||||
type DeviceCodeResult = accesstokens.DeviceCodeResult
|
||||
@ -412,7 +419,7 @@ func (d DeviceCode) AuthenticationResult(ctx context.Context) (AuthResult, error
|
||||
if err != nil {
|
||||
return AuthResult{}, err
|
||||
}
|
||||
return d.client.base.AuthResultFromToken(ctx, d.authParams, token, true)
|
||||
return d.client.base.AuthResultFromToken(ctx, d.authParams, token)
|
||||
}
|
||||
|
||||
// acquireTokenByDeviceCodeOptions contains optional configuration for AcquireTokenByDeviceCode
|
||||
@ -687,7 +694,7 @@ func (pca Client) AcquireTokenInteractive(ctx context.Context, scopes []string,
|
||||
return AuthResult{}, err
|
||||
}
|
||||
|
||||
return pca.base.AuthResultFromToken(ctx, authParams, token, true)
|
||||
return pca.base.AuthResultFromToken(ctx, authParams, token)
|
||||
}
|
||||
|
||||
type interactiveAuthResult struct {
|
||||
|
||||
4
vendor/github.com/aws/aws-sdk-go-v2/service/sts/CHANGELOG.md
generated
vendored
4
vendor/github.com/aws/aws-sdk-go-v2/service/sts/CHANGELOG.md
generated
vendored
@ -1,3 +1,7 @@
|
||||
# v1.33.19 (2025-04-10)
|
||||
|
||||
* No change notes available for this release.
|
||||
|
||||
# v1.33.18 (2025-04-03)
|
||||
|
||||
* No change notes available for this release.
|
||||
|
||||
2
vendor/github.com/aws/aws-sdk-go-v2/service/sts/go_module_metadata.go
generated
vendored
2
vendor/github.com/aws/aws-sdk-go-v2/service/sts/go_module_metadata.go
generated
vendored
@ -3,4 +3,4 @@
|
||||
package sts
|
||||
|
||||
// goModuleVersion is the tagged release for this module
|
||||
const goModuleVersion = "1.33.18"
|
||||
const goModuleVersion = "1.33.19"
|
||||
|
||||
5
vendor/github.com/aws/aws-sdk-go-v2/service/sts/internal/endpoints/endpoints.go
generated
vendored
5
vendor/github.com/aws/aws-sdk-go-v2/service/sts/internal/endpoints/endpoints.go
generated
vendored
@ -446,6 +446,11 @@ var defaultPartitions = endpoints.Partitions{
|
||||
},
|
||||
RegionRegex: partitionRegexp.AwsIsoE,
|
||||
IsRegionalized: true,
|
||||
Endpoints: endpoints.Endpoints{
|
||||
endpoints.EndpointKey{
|
||||
Region: "eu-isoe-west-1",
|
||||
}: endpoints.Endpoint{},
|
||||
},
|
||||
},
|
||||
{
|
||||
ID: "aws-iso-f",
|
||||
|
||||
7
vendor/github.com/google/go-cmp/cmp/internal/function/func.go
generated
vendored
7
vendor/github.com/google/go-cmp/cmp/internal/function/func.go
generated
vendored
@ -19,6 +19,7 @@ const (
|
||||
|
||||
tbFunc // func(T) bool
|
||||
ttbFunc // func(T, T) bool
|
||||
ttiFunc // func(T, T) int
|
||||
trbFunc // func(T, R) bool
|
||||
tibFunc // func(T, I) bool
|
||||
trFunc // func(T) R
|
||||
@ -28,11 +29,13 @@ const (
|
||||
Transformer = trFunc // func(T) R
|
||||
ValueFilter = ttbFunc // func(T, T) bool
|
||||
Less = ttbFunc // func(T, T) bool
|
||||
Compare = ttiFunc // func(T, T) int
|
||||
ValuePredicate = tbFunc // func(T) bool
|
||||
KeyValuePredicate = trbFunc // func(T, R) bool
|
||||
)
|
||||
|
||||
var boolType = reflect.TypeOf(true)
|
||||
var intType = reflect.TypeOf(0)
|
||||
|
||||
// IsType reports whether the reflect.Type is of the specified function type.
|
||||
func IsType(t reflect.Type, ft funcType) bool {
|
||||
@ -49,6 +52,10 @@ func IsType(t reflect.Type, ft funcType) bool {
|
||||
if ni == 2 && no == 1 && t.In(0) == t.In(1) && t.Out(0) == boolType {
|
||||
return true
|
||||
}
|
||||
case ttiFunc: // func(T, T) int
|
||||
if ni == 2 && no == 1 && t.In(0) == t.In(1) && t.Out(0) == intType {
|
||||
return true
|
||||
}
|
||||
case trbFunc: // func(T, R) bool
|
||||
if ni == 2 && no == 1 && t.Out(0) == boolType {
|
||||
return true
|
||||
|
||||
10
vendor/github.com/google/go-cmp/cmp/options.go
generated
vendored
10
vendor/github.com/google/go-cmp/cmp/options.go
generated
vendored
@ -232,7 +232,15 @@ func (validator) apply(s *state, vx, vy reflect.Value) {
|
||||
if t := s.curPath.Index(-2).Type(); t.Name() != "" {
|
||||
// Named type with unexported fields.
|
||||
name = fmt.Sprintf("%q.%v", t.PkgPath(), t.Name()) // e.g., "path/to/package".MyType
|
||||
if _, ok := reflect.New(t).Interface().(error); ok {
|
||||
isProtoMessage := func(t reflect.Type) bool {
|
||||
m, ok := reflect.PointerTo(t).MethodByName("ProtoReflect")
|
||||
return ok && m.Type.NumIn() == 1 && m.Type.NumOut() == 1 &&
|
||||
m.Type.Out(0).PkgPath() == "google.golang.org/protobuf/reflect/protoreflect" &&
|
||||
m.Type.Out(0).Name() == "Message"
|
||||
}
|
||||
if isProtoMessage(t) {
|
||||
help = `consider using "google.golang.org/protobuf/testing/protocmp".Transform to compare proto.Message types`
|
||||
} else if _, ok := reflect.New(t).Interface().(error); ok {
|
||||
help = "consider using cmpopts.EquateErrors to compare error values"
|
||||
} else if t.Comparable() {
|
||||
help = "consider using cmpopts.EquateComparable to compare comparable Go types"
|
||||
|
||||
2
vendor/github.com/klauspost/compress/.gitattributes
generated
vendored
2
vendor/github.com/klauspost/compress/.gitattributes
generated
vendored
@ -1,2 +0,0 @@
|
||||
* -text
|
||||
*.bin -text -diff
|
||||
32
vendor/github.com/klauspost/compress/.gitignore
generated
vendored
32
vendor/github.com/klauspost/compress/.gitignore
generated
vendored
@ -1,32 +0,0 @@
|
||||
# Compiled Object files, Static and Dynamic libs (Shared Objects)
|
||||
*.o
|
||||
*.a
|
||||
*.so
|
||||
|
||||
# Folders
|
||||
_obj
|
||||
_test
|
||||
|
||||
# Architecture specific extensions/prefixes
|
||||
*.[568vq]
|
||||
[568vq].out
|
||||
|
||||
*.cgo1.go
|
||||
*.cgo2.c
|
||||
_cgo_defun.c
|
||||
_cgo_gotypes.go
|
||||
_cgo_export.*
|
||||
|
||||
_testmain.go
|
||||
|
||||
*.exe
|
||||
*.test
|
||||
*.prof
|
||||
/s2/cmd/_s2sx/sfx-exe
|
||||
|
||||
# Linux perf files
|
||||
perf.data
|
||||
perf.data.old
|
||||
|
||||
# gdb history
|
||||
.gdb_history
|
||||
123
vendor/github.com/klauspost/compress/.goreleaser.yml
generated
vendored
123
vendor/github.com/klauspost/compress/.goreleaser.yml
generated
vendored
@ -1,123 +0,0 @@
|
||||
version: 2
|
||||
|
||||
before:
|
||||
hooks:
|
||||
- ./gen.sh
|
||||
|
||||
builds:
|
||||
-
|
||||
id: "s2c"
|
||||
binary: s2c
|
||||
main: ./s2/cmd/s2c/main.go
|
||||
flags:
|
||||
- -trimpath
|
||||
env:
|
||||
- CGO_ENABLED=0
|
||||
goos:
|
||||
- aix
|
||||
- linux
|
||||
- freebsd
|
||||
- netbsd
|
||||
- windows
|
||||
- darwin
|
||||
goarch:
|
||||
- 386
|
||||
- amd64
|
||||
- arm
|
||||
- arm64
|
||||
- ppc64
|
||||
- ppc64le
|
||||
- mips64
|
||||
- mips64le
|
||||
goarm:
|
||||
- 7
|
||||
-
|
||||
id: "s2d"
|
||||
binary: s2d
|
||||
main: ./s2/cmd/s2d/main.go
|
||||
flags:
|
||||
- -trimpath
|
||||
env:
|
||||
- CGO_ENABLED=0
|
||||
goos:
|
||||
- aix
|
||||
- linux
|
||||
- freebsd
|
||||
- netbsd
|
||||
- windows
|
||||
- darwin
|
||||
goarch:
|
||||
- 386
|
||||
- amd64
|
||||
- arm
|
||||
- arm64
|
||||
- ppc64
|
||||
- ppc64le
|
||||
- mips64
|
||||
- mips64le
|
||||
goarm:
|
||||
- 7
|
||||
-
|
||||
id: "s2sx"
|
||||
binary: s2sx
|
||||
main: ./s2/cmd/_s2sx/main.go
|
||||
flags:
|
||||
- -modfile=s2sx.mod
|
||||
- -trimpath
|
||||
env:
|
||||
- CGO_ENABLED=0
|
||||
goos:
|
||||
- aix
|
||||
- linux
|
||||
- freebsd
|
||||
- netbsd
|
||||
- windows
|
||||
- darwin
|
||||
goarch:
|
||||
- 386
|
||||
- amd64
|
||||
- arm
|
||||
- arm64
|
||||
- ppc64
|
||||
- ppc64le
|
||||
- mips64
|
||||
- mips64le
|
||||
goarm:
|
||||
- 7
|
||||
|
||||
archives:
|
||||
-
|
||||
id: s2-binaries
|
||||
name_template: "s2-{{ .Os }}_{{ .Arch }}{{ if .Arm }}v{{ .Arm }}{{ end }}"
|
||||
format_overrides:
|
||||
- goos: windows
|
||||
format: zip
|
||||
files:
|
||||
- unpack/*
|
||||
- s2/LICENSE
|
||||
- s2/README.md
|
||||
checksum:
|
||||
name_template: 'checksums.txt'
|
||||
snapshot:
|
||||
version_template: "{{ .Tag }}-next"
|
||||
changelog:
|
||||
sort: asc
|
||||
filters:
|
||||
exclude:
|
||||
- '^doc:'
|
||||
- '^docs:'
|
||||
- '^test:'
|
||||
- '^tests:'
|
||||
- '^Update\sREADME.md'
|
||||
|
||||
nfpms:
|
||||
-
|
||||
file_name_template: "s2_package__{{ .Os }}_{{ .Arch }}{{ if .Arm }}v{{ .Arm }}{{ end }}"
|
||||
vendor: Klaus Post
|
||||
homepage: https://github.com/klauspost/compress
|
||||
maintainer: Klaus Post <klauspost@gmail.com>
|
||||
description: S2 Compression Tool
|
||||
license: BSD 3-Clause
|
||||
formats:
|
||||
- deb
|
||||
- rpm
|
||||
304
vendor/github.com/klauspost/compress/LICENSE
generated
vendored
304
vendor/github.com/klauspost/compress/LICENSE
generated
vendored
@ -1,304 +0,0 @@
|
||||
Copyright (c) 2012 The Go Authors. All rights reserved.
|
||||
Copyright (c) 2019 Klaus Post. All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
* Neither the name of Google Inc. nor the names of its
|
||||
contributors may be used to endorse or promote products derived from
|
||||
this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
------------------
|
||||
|
||||
Files: gzhttp/*
|
||||
|
||||
Apache License
|
||||
Version 2.0, January 2004
|
||||
http://www.apache.org/licenses/
|
||||
|
||||
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||
|
||||
1. Definitions.
|
||||
|
||||
"License" shall mean the terms and conditions for use, reproduction,
|
||||
and distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
"Licensor" shall mean the copyright owner or entity authorized by
|
||||
the copyright owner that is granting the License.
|
||||
|
||||
"Legal Entity" shall mean the union of the acting entity and all
|
||||
other entities that control, are controlled by, or are under common
|
||||
control with that entity. For the purposes of this definition,
|
||||
"control" means (i) the power, direct or indirect, to cause the
|
||||
direction or management of such entity, whether by contract or
|
||||
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||
|
||||
"You" (or "Your") shall mean an individual or Legal Entity
|
||||
exercising permissions granted by this License.
|
||||
|
||||
"Source" form shall mean the preferred form for making modifications,
|
||||
including but not limited to software source code, documentation
|
||||
source, and configuration files.
|
||||
|
||||
"Object" form shall mean any form resulting from mechanical
|
||||
transformation or translation of a Source form, including but
|
||||
not limited to compiled object code, generated documentation,
|
||||
and conversions to other media types.
|
||||
|
||||
"Work" shall mean the work of authorship, whether in Source or
|
||||
Object form, made available under the License, as indicated by a
|
||||
copyright notice that is included in or attached to the work
|
||||
(an example is provided in the Appendix below).
|
||||
|
||||
"Derivative Works" shall mean any work, whether in Source or Object
|
||||
form, that is based on (or derived from) the Work and for which the
|
||||
editorial revisions, annotations, elaborations, or other modifications
|
||||
represent, as a whole, an original work of authorship. For the purposes
|
||||
of this License, Derivative Works shall not include works that remain
|
||||
separable from, or merely link (or bind by name) to the interfaces of,
|
||||
the Work and Derivative Works thereof.
|
||||
|
||||
"Contribution" shall mean any work of authorship, including
|
||||
the original version of the Work and any modifications or additions
|
||||
to that Work or Derivative Works thereof, that is intentionally
|
||||
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||
or by an individual or Legal Entity authorized to submit on behalf of
|
||||
the copyright owner. For the purposes of this definition, "submitted"
|
||||
means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems,
|
||||
and issue tracking systems that are managed by, or on behalf of, the
|
||||
Licensor for the purpose of discussing and improving the Work, but
|
||||
excluding communication that is conspicuously marked or otherwise
|
||||
designated in writing by the copyright owner as "Not a Contribution."
|
||||
|
||||
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||
on behalf of whom a Contribution has been received by Licensor and
|
||||
subsequently incorporated within the Work.
|
||||
|
||||
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the
|
||||
Work and such Derivative Works in Source or Object form.
|
||||
|
||||
3. Grant of Patent License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
(except as stated in this section) patent license to make, have made,
|
||||
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||
where such license applies only to those patent claims licensable
|
||||
by such Contributor that are necessarily infringed by their
|
||||
Contribution(s) alone or by combination of their Contribution(s)
|
||||
with the Work to which such Contribution(s) was submitted. If You
|
||||
institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||
or a Contribution incorporated within the Work constitutes direct
|
||||
or contributory patent infringement, then any patent licenses
|
||||
granted to You under this License for that Work shall terminate
|
||||
as of the date such litigation is filed.
|
||||
|
||||
4. Redistribution. You may reproduce and distribute copies of the
|
||||
Work or Derivative Works thereof in any medium, with or without
|
||||
modifications, and in Source or Object form, provided that You
|
||||
meet the following conditions:
|
||||
|
||||
(a) You must give any other recipients of the Work or
|
||||
Derivative Works a copy of this License; and
|
||||
|
||||
(b) You must cause any modified files to carry prominent notices
|
||||
stating that You changed the files; and
|
||||
|
||||
(c) You must retain, in the Source form of any Derivative Works
|
||||
that You distribute, all copyright, patent, trademark, and
|
||||
attribution notices from the Source form of the Work,
|
||||
excluding those notices that do not pertain to any part of
|
||||
the Derivative Works; and
|
||||
|
||||
(d) If the Work includes a "NOTICE" text file as part of its
|
||||
distribution, then any Derivative Works that You distribute must
|
||||
include a readable copy of the attribution notices contained
|
||||
within such NOTICE file, excluding those notices that do not
|
||||
pertain to any part of the Derivative Works, in at least one
|
||||
of the following places: within a NOTICE text file distributed
|
||||
as part of the Derivative Works; within the Source form or
|
||||
documentation, if provided along with the Derivative Works; or,
|
||||
within a display generated by the Derivative Works, if and
|
||||
wherever such third-party notices normally appear. The contents
|
||||
of the NOTICE file are for informational purposes only and
|
||||
do not modify the License. You may add Your own attribution
|
||||
notices within Derivative Works that You distribute, alongside
|
||||
or as an addendum to the NOTICE text from the Work, provided
|
||||
that such additional attribution notices cannot be construed
|
||||
as modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and
|
||||
may provide additional or different license terms and conditions
|
||||
for use, reproduction, or distribution of Your modifications, or
|
||||
for any such Derivative Works as a whole, provided Your use,
|
||||
reproduction, and distribution of the Work otherwise complies with
|
||||
the conditions stated in this License.
|
||||
|
||||
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||
any Contribution intentionally submitted for inclusion in the Work
|
||||
by You to the Licensor shall be under the terms and conditions of
|
||||
this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify
|
||||
the terms of any separate license agreement you may have executed
|
||||
with Licensor regarding such Contributions.
|
||||
|
||||
6. Trademarks. This License does not grant permission to use the trade
|
||||
names, trademarks, service marks, or product names of the Licensor,
|
||||
except as required for reasonable and customary use in describing the
|
||||
origin of the Work and reproducing the content of the NOTICE file.
|
||||
|
||||
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||
agreed to in writing, Licensor provides the Work (and each
|
||||
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
implied, including, without limitation, any warranties or conditions
|
||||
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||
appropriateness of using or redistributing the Work and assume any
|
||||
risks associated with Your exercise of permissions under this License.
|
||||
|
||||
8. Limitation of Liability. In no event and under no legal theory,
|
||||
whether in tort (including negligence), contract, or otherwise,
|
||||
unless required by applicable law (such as deliberate and grossly
|
||||
negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special,
|
||||
incidental, or consequential damages of any character arising as a
|
||||
result of this License or out of the use or inability to use the
|
||||
Work (including but not limited to damages for loss of goodwill,
|
||||
work stoppage, computer failure or malfunction, or any and all
|
||||
other commercial damages or losses), even if such Contributor
|
||||
has been advised of the possibility of such damages.
|
||||
|
||||
9. Accepting Warranty or Additional Liability. While redistributing
|
||||
the Work or Derivative Works thereof, You may choose to offer,
|
||||
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||
or other liability obligations and/or rights consistent with this
|
||||
License. However, in accepting such obligations, You may act only
|
||||
on Your own behalf and on Your sole responsibility, not on behalf
|
||||
of any other Contributor, and only if You agree to indemnify,
|
||||
defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason
|
||||
of your accepting any such warranty or additional liability.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
APPENDIX: How to apply the Apache License to your work.
|
||||
|
||||
To apply the Apache License to your work, attach the following
|
||||
boilerplate notice, with the fields enclosed by brackets "[]"
|
||||
replaced with your own identifying information. (Don't include
|
||||
the brackets!) The text should be enclosed in the appropriate
|
||||
comment syntax for the file format. We also recommend that a
|
||||
file or class name and description of purpose be included on the
|
||||
same "printed page" as the copyright notice for easier
|
||||
identification within third-party archives.
|
||||
|
||||
Copyright 2016-2017 The New York Times Company
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
|
||||
------------------
|
||||
|
||||
Files: s2/cmd/internal/readahead/*
|
||||
|
||||
The MIT License (MIT)
|
||||
|
||||
Copyright (c) 2015 Klaus Post
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
|
||||
---------------------
|
||||
Files: snappy/*
|
||||
Files: internal/snapref/*
|
||||
|
||||
Copyright (c) 2011 The Snappy-Go Authors. All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
* Neither the name of Google Inc. nor the names of its
|
||||
contributors may be used to endorse or promote products derived from
|
||||
this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
-----------------
|
||||
|
||||
Files: s2/cmd/internal/filepathx/*
|
||||
|
||||
Copyright 2016 The filepathx Authors
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||
721
vendor/github.com/klauspost/compress/README.md
generated
vendored
721
vendor/github.com/klauspost/compress/README.md
generated
vendored
@ -1,721 +0,0 @@
|
||||
# compress
|
||||
|
||||
This package provides various compression algorithms.
|
||||
|
||||
* [zstandard](https://github.com/klauspost/compress/tree/master/zstd#zstd) compression and decompression in pure Go.
|
||||
* [S2](https://github.com/klauspost/compress/tree/master/s2#s2-compression) is a high performance replacement for Snappy.
|
||||
* Optimized [deflate](https://godoc.org/github.com/klauspost/compress/flate) packages which can be used as a dropin replacement for [gzip](https://godoc.org/github.com/klauspost/compress/gzip), [zip](https://godoc.org/github.com/klauspost/compress/zip) and [zlib](https://godoc.org/github.com/klauspost/compress/zlib).
|
||||
* [snappy](https://github.com/klauspost/compress/tree/master/snappy) is a drop-in replacement for `github.com/golang/snappy` offering better compression and concurrent streams.
|
||||
* [huff0](https://github.com/klauspost/compress/tree/master/huff0) and [FSE](https://github.com/klauspost/compress/tree/master/fse) implementations for raw entropy encoding.
|
||||
* [gzhttp](https://github.com/klauspost/compress/tree/master/gzhttp) Provides client and server wrappers for handling gzipped requests efficiently.
|
||||
* [pgzip](https://github.com/klauspost/pgzip) is a separate package that provides a very fast parallel gzip implementation.
|
||||
|
||||
[](https://pkg.go.dev/github.com/klauspost/compress?tab=subdirectories)
|
||||
[](https://github.com/klauspost/compress/actions/workflows/go.yml)
|
||||
[](https://sourcegraph.com/github.com/klauspost/compress?badge)
|
||||
|
||||
# changelog
|
||||
|
||||
* Sep 23rd, 2024 - [1.17.10](https://github.com/klauspost/compress/releases/tag/v1.17.10)
|
||||
* gzhttp: Add TransportAlwaysDecompress option. https://github.com/klauspost/compress/pull/978
|
||||
* gzhttp: Add supported decompress request body by @mirecl in https://github.com/klauspost/compress/pull/1002
|
||||
* s2: Add EncodeBuffer buffer recycling callback https://github.com/klauspost/compress/pull/982
|
||||
* zstd: Improve memory usage on small streaming encodes https://github.com/klauspost/compress/pull/1007
|
||||
* flate: read data written with partial flush by @vajexal in https://github.com/klauspost/compress/pull/996
|
||||
|
||||
* Jun 12th, 2024 - [1.17.9](https://github.com/klauspost/compress/releases/tag/v1.17.9)
|
||||
* s2: Reduce ReadFrom temporary allocations https://github.com/klauspost/compress/pull/949
|
||||
* flate, zstd: Shave some bytes off amd64 matchLen by @greatroar in https://github.com/klauspost/compress/pull/963
|
||||
* Upgrade zip/zlib to 1.22.4 upstream https://github.com/klauspost/compress/pull/970 https://github.com/klauspost/compress/pull/971
|
||||
* zstd: BuildDict fails with RLE table https://github.com/klauspost/compress/pull/951
|
||||
|
||||
* Apr 9th, 2024 - [1.17.8](https://github.com/klauspost/compress/releases/tag/v1.17.8)
|
||||
* zstd: Reject blocks where reserved values are not 0 https://github.com/klauspost/compress/pull/885
|
||||
* zstd: Add RLE detection+encoding https://github.com/klauspost/compress/pull/938
|
||||
|
||||
* Feb 21st, 2024 - [1.17.7](https://github.com/klauspost/compress/releases/tag/v1.17.7)
|
||||
* s2: Add AsyncFlush method: Complete the block without flushing by @Jille in https://github.com/klauspost/compress/pull/927
|
||||
* s2: Fix literal+repeat exceeds dst crash https://github.com/klauspost/compress/pull/930
|
||||
|
||||
* Feb 5th, 2024 - [1.17.6](https://github.com/klauspost/compress/releases/tag/v1.17.6)
|
||||
* zstd: Fix incorrect repeat coding in best mode https://github.com/klauspost/compress/pull/923
|
||||
* s2: Fix DecodeConcurrent deadlock on errors https://github.com/klauspost/compress/pull/925
|
||||
|
||||
* Jan 26th, 2024 - [v1.17.5](https://github.com/klauspost/compress/releases/tag/v1.17.5)
|
||||
* flate: Fix reset with dictionary on custom window encodes https://github.com/klauspost/compress/pull/912
|
||||
* zstd: Add Frame header encoding and stripping https://github.com/klauspost/compress/pull/908
|
||||
* zstd: Limit better/best default window to 8MB https://github.com/klauspost/compress/pull/913
|
||||
* zstd: Speed improvements by @greatroar in https://github.com/klauspost/compress/pull/896 https://github.com/klauspost/compress/pull/910
|
||||
* s2: Fix callbacks for skippable blocks and disallow 0xfe (Padding) by @Jille in https://github.com/klauspost/compress/pull/916 https://github.com/klauspost/compress/pull/917
|
||||
https://github.com/klauspost/compress/pull/919 https://github.com/klauspost/compress/pull/918
|
||||
|
||||
* Dec 1st, 2023 - [v1.17.4](https://github.com/klauspost/compress/releases/tag/v1.17.4)
|
||||
* huff0: Speed up symbol counting by @greatroar in https://github.com/klauspost/compress/pull/887
|
||||
* huff0: Remove byteReader by @greatroar in https://github.com/klauspost/compress/pull/886
|
||||
* gzhttp: Allow overriding decompression on transport https://github.com/klauspost/compress/pull/892
|
||||
* gzhttp: Clamp compression level https://github.com/klauspost/compress/pull/890
|
||||
* gzip: Error out if reserved bits are set https://github.com/klauspost/compress/pull/891
|
||||
|
||||
* Nov 15th, 2023 - [v1.17.3](https://github.com/klauspost/compress/releases/tag/v1.17.3)
|
||||
* fse: Fix max header size https://github.com/klauspost/compress/pull/881
|
||||
* zstd: Improve better/best compression https://github.com/klauspost/compress/pull/877
|
||||
* gzhttp: Fix missing content type on Close https://github.com/klauspost/compress/pull/883
|
||||
|
||||
* Oct 22nd, 2023 - [v1.17.2](https://github.com/klauspost/compress/releases/tag/v1.17.2)
|
||||
* zstd: Fix rare *CORRUPTION* output in "best" mode. See https://github.com/klauspost/compress/pull/876
|
||||
|
||||
* Oct 14th, 2023 - [v1.17.1](https://github.com/klauspost/compress/releases/tag/v1.17.1)
|
||||
* s2: Fix S2 "best" dictionary wrong encoding by @klauspost in https://github.com/klauspost/compress/pull/871
|
||||
* flate: Reduce allocations in decompressor and minor code improvements by @fakefloordiv in https://github.com/klauspost/compress/pull/869
|
||||
* s2: Fix EstimateBlockSize on 6&7 length input by @klauspost in https://github.com/klauspost/compress/pull/867
|
||||
|
||||
* Sept 19th, 2023 - [v1.17.0](https://github.com/klauspost/compress/releases/tag/v1.17.0)
|
||||
* Add experimental dictionary builder https://github.com/klauspost/compress/pull/853
|
||||
* Add xerial snappy read/writer https://github.com/klauspost/compress/pull/838
|
||||
* flate: Add limited window compression https://github.com/klauspost/compress/pull/843
|
||||
* s2: Do 2 overlapping match checks https://github.com/klauspost/compress/pull/839
|
||||
* flate: Add amd64 assembly matchlen https://github.com/klauspost/compress/pull/837
|
||||
* gzip: Copy bufio.Reader on Reset by @thatguystone in https://github.com/klauspost/compress/pull/860
|
||||
|
||||
<details>
|
||||
<summary>See changes to v1.16.x</summary>
|
||||
|
||||
|
||||
* July 1st, 2023 - [v1.16.7](https://github.com/klauspost/compress/releases/tag/v1.16.7)
|
||||
* zstd: Fix default level first dictionary encode https://github.com/klauspost/compress/pull/829
|
||||
* s2: add GetBufferCapacity() method by @GiedriusS in https://github.com/klauspost/compress/pull/832
|
||||
|
||||
* June 13, 2023 - [v1.16.6](https://github.com/klauspost/compress/releases/tag/v1.16.6)
|
||||
* zstd: correctly ignore WithEncoderPadding(1) by @ianlancetaylor in https://github.com/klauspost/compress/pull/806
|
||||
* zstd: Add amd64 match length assembly https://github.com/klauspost/compress/pull/824
|
||||
* gzhttp: Handle informational headers by @rtribotte in https://github.com/klauspost/compress/pull/815
|
||||
* s2: Improve Better compression slightly https://github.com/klauspost/compress/pull/663
|
||||
|
||||
* Apr 16, 2023 - [v1.16.5](https://github.com/klauspost/compress/releases/tag/v1.16.5)
|
||||
* zstd: readByte needs to use io.ReadFull by @jnoxon in https://github.com/klauspost/compress/pull/802
|
||||
* gzip: Fix WriterTo after initial read https://github.com/klauspost/compress/pull/804
|
||||
|
||||
* Apr 5, 2023 - [v1.16.4](https://github.com/klauspost/compress/releases/tag/v1.16.4)
|
||||
* zstd: Improve zstd best efficiency by @greatroar and @klauspost in https://github.com/klauspost/compress/pull/784
|
||||
* zstd: Respect WithAllLitEntropyCompression https://github.com/klauspost/compress/pull/792
|
||||
* zstd: Fix amd64 not always detecting corrupt data https://github.com/klauspost/compress/pull/785
|
||||
* zstd: Various minor improvements by @greatroar in https://github.com/klauspost/compress/pull/788 https://github.com/klauspost/compress/pull/794 https://github.com/klauspost/compress/pull/795
|
||||
* s2: Fix huge block overflow https://github.com/klauspost/compress/pull/779
|
||||
* s2: Allow CustomEncoder fallback https://github.com/klauspost/compress/pull/780
|
||||
* gzhttp: Support ResponseWriter Unwrap() in gzhttp handler by @jgimenez in https://github.com/klauspost/compress/pull/799
|
||||
|
||||
* Mar 13, 2023 - [v1.16.1](https://github.com/klauspost/compress/releases/tag/v1.16.1)
|
||||
* zstd: Speed up + improve best encoder by @greatroar in https://github.com/klauspost/compress/pull/776
|
||||
* gzhttp: Add optional [BREACH mitigation](https://github.com/klauspost/compress/tree/master/gzhttp#breach-mitigation). https://github.com/klauspost/compress/pull/762 https://github.com/klauspost/compress/pull/768 https://github.com/klauspost/compress/pull/769 https://github.com/klauspost/compress/pull/770 https://github.com/klauspost/compress/pull/767
|
||||
* s2: Add Intel LZ4s converter https://github.com/klauspost/compress/pull/766
|
||||
* zstd: Minor bug fixes https://github.com/klauspost/compress/pull/771 https://github.com/klauspost/compress/pull/772 https://github.com/klauspost/compress/pull/773
|
||||
* huff0: Speed up compress1xDo by @greatroar in https://github.com/klauspost/compress/pull/774
|
||||
|
||||
* Feb 26, 2023 - [v1.16.0](https://github.com/klauspost/compress/releases/tag/v1.16.0)
|
||||
* s2: Add [Dictionary](https://github.com/klauspost/compress/tree/master/s2#dictionaries) support. https://github.com/klauspost/compress/pull/685
|
||||
* s2: Add Compression Size Estimate. https://github.com/klauspost/compress/pull/752
|
||||
* s2: Add support for custom stream encoder. https://github.com/klauspost/compress/pull/755
|
||||
* s2: Add LZ4 block converter. https://github.com/klauspost/compress/pull/748
|
||||
* s2: Support io.ReaderAt in ReadSeeker. https://github.com/klauspost/compress/pull/747
|
||||
* s2c/s2sx: Use concurrent decoding. https://github.com/klauspost/compress/pull/746
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>See changes to v1.15.x</summary>
|
||||
|
||||
* Jan 21st, 2023 (v1.15.15)
|
||||
* deflate: Improve level 7-9 by @klauspost in https://github.com/klauspost/compress/pull/739
|
||||
* zstd: Add delta encoding support by @greatroar in https://github.com/klauspost/compress/pull/728
|
||||
* zstd: Various speed improvements by @greatroar https://github.com/klauspost/compress/pull/741 https://github.com/klauspost/compress/pull/734 https://github.com/klauspost/compress/pull/736 https://github.com/klauspost/compress/pull/744 https://github.com/klauspost/compress/pull/743 https://github.com/klauspost/compress/pull/745
|
||||
* gzhttp: Add SuffixETag() and DropETag() options to prevent ETag collisions on compressed responses by @willbicks in https://github.com/klauspost/compress/pull/740
|
||||
|
||||
* Jan 3rd, 2023 (v1.15.14)
|
||||
|
||||
* flate: Improve speed in big stateless blocks https://github.com/klauspost/compress/pull/718
|
||||
* zstd: Minor speed tweaks by @greatroar in https://github.com/klauspost/compress/pull/716 https://github.com/klauspost/compress/pull/720
|
||||
* export NoGzipResponseWriter for custom ResponseWriter wrappers by @harshavardhana in https://github.com/klauspost/compress/pull/722
|
||||
* s2: Add example for indexing and existing stream https://github.com/klauspost/compress/pull/723
|
||||
|
||||
* Dec 11, 2022 (v1.15.13)
|
||||
* zstd: Add [MaxEncodedSize](https://pkg.go.dev/github.com/klauspost/compress@v1.15.13/zstd#Encoder.MaxEncodedSize) to encoder https://github.com/klauspost/compress/pull/691
|
||||
* zstd: Various tweaks and improvements https://github.com/klauspost/compress/pull/693 https://github.com/klauspost/compress/pull/695 https://github.com/klauspost/compress/pull/696 https://github.com/klauspost/compress/pull/701 https://github.com/klauspost/compress/pull/702 https://github.com/klauspost/compress/pull/703 https://github.com/klauspost/compress/pull/704 https://github.com/klauspost/compress/pull/705 https://github.com/klauspost/compress/pull/706 https://github.com/klauspost/compress/pull/707 https://github.com/klauspost/compress/pull/708
|
||||
|
||||
* Oct 26, 2022 (v1.15.12)
|
||||
|
||||
* zstd: Tweak decoder allocs. https://github.com/klauspost/compress/pull/680
|
||||
* gzhttp: Always delete `HeaderNoCompression` https://github.com/klauspost/compress/pull/683
|
||||
|
||||
* Sept 26, 2022 (v1.15.11)
|
||||
|
||||
* flate: Improve level 1-3 compression https://github.com/klauspost/compress/pull/678
|
||||
* zstd: Improve "best" compression by @nightwolfz in https://github.com/klauspost/compress/pull/677
|
||||
* zstd: Fix+reduce decompression allocations https://github.com/klauspost/compress/pull/668
|
||||
* zstd: Fix non-effective noescape tag https://github.com/klauspost/compress/pull/667
|
||||
|
||||
* Sept 16, 2022 (v1.15.10)
|
||||
|
||||
* zstd: Add [WithDecodeAllCapLimit](https://pkg.go.dev/github.com/klauspost/compress@v1.15.10/zstd#WithDecodeAllCapLimit) https://github.com/klauspost/compress/pull/649
|
||||
* Add Go 1.19 - deprecate Go 1.16 https://github.com/klauspost/compress/pull/651
|
||||
* flate: Improve level 5+6 compression https://github.com/klauspost/compress/pull/656
|
||||
* zstd: Improve "better" compression https://github.com/klauspost/compress/pull/657
|
||||
* s2: Improve "best" compression https://github.com/klauspost/compress/pull/658
|
||||
* s2: Improve "better" compression. https://github.com/klauspost/compress/pull/635
|
||||
* s2: Slightly faster non-assembly decompression https://github.com/klauspost/compress/pull/646
|
||||
* Use arrays for constant size copies https://github.com/klauspost/compress/pull/659
|
||||
|
||||
* July 21, 2022 (v1.15.9)
|
||||
|
||||
* zstd: Fix decoder crash on amd64 (no BMI) on invalid input https://github.com/klauspost/compress/pull/645
|
||||
* zstd: Disable decoder extended memory copies (amd64) due to possible crashes https://github.com/klauspost/compress/pull/644
|
||||
* zstd: Allow single segments up to "max decoded size" by @klauspost in https://github.com/klauspost/compress/pull/643
|
||||
|
||||
* July 13, 2022 (v1.15.8)
|
||||
|
||||
* gzip: fix stack exhaustion bug in Reader.Read https://github.com/klauspost/compress/pull/641
|
||||
* s2: Add Index header trim/restore https://github.com/klauspost/compress/pull/638
|
||||
* zstd: Optimize seqdeq amd64 asm by @greatroar in https://github.com/klauspost/compress/pull/636
|
||||
* zstd: Improve decoder memcopy https://github.com/klauspost/compress/pull/637
|
||||
* huff0: Pass a single bitReader pointer to asm by @greatroar in https://github.com/klauspost/compress/pull/634
|
||||
* zstd: Branchless getBits for amd64 w/o BMI2 by @greatroar in https://github.com/klauspost/compress/pull/640
|
||||
* gzhttp: Remove header before writing https://github.com/klauspost/compress/pull/639
|
||||
|
||||
* June 29, 2022 (v1.15.7)
|
||||
|
||||
* s2: Fix absolute forward seeks https://github.com/klauspost/compress/pull/633
|
||||
* zip: Merge upstream https://github.com/klauspost/compress/pull/631
|
||||
* zip: Re-add zip64 fix https://github.com/klauspost/compress/pull/624
|
||||
* zstd: translate fseDecoder.buildDtable into asm by @WojciechMula in https://github.com/klauspost/compress/pull/598
|
||||
* flate: Faster histograms https://github.com/klauspost/compress/pull/620
|
||||
* deflate: Use compound hcode https://github.com/klauspost/compress/pull/622
|
||||
|
||||
* June 3, 2022 (v1.15.6)
|
||||
* s2: Improve coding for long, close matches https://github.com/klauspost/compress/pull/613
|
||||
* s2c: Add Snappy/S2 stream recompression https://github.com/klauspost/compress/pull/611
|
||||
* zstd: Always use configured block size https://github.com/klauspost/compress/pull/605
|
||||
* zstd: Fix incorrect hash table placement for dict encoding in default https://github.com/klauspost/compress/pull/606
|
||||
* zstd: Apply default config to ZipDecompressor without options https://github.com/klauspost/compress/pull/608
|
||||
* gzhttp: Exclude more common archive formats https://github.com/klauspost/compress/pull/612
|
||||
* s2: Add ReaderIgnoreCRC https://github.com/klauspost/compress/pull/609
|
||||
* s2: Remove sanity load on index creation https://github.com/klauspost/compress/pull/607
|
||||
* snappy: Use dedicated function for scoring https://github.com/klauspost/compress/pull/614
|
||||
* s2c+s2d: Use official snappy framed extension https://github.com/klauspost/compress/pull/610
|
||||
|
||||
* May 25, 2022 (v1.15.5)
|
||||
* s2: Add concurrent stream decompression https://github.com/klauspost/compress/pull/602
|
||||
* s2: Fix final emit oob read crash on amd64 https://github.com/klauspost/compress/pull/601
|
||||
* huff0: asm implementation of Decompress1X by @WojciechMula https://github.com/klauspost/compress/pull/596
|
||||
* zstd: Use 1 less goroutine for stream decoding https://github.com/klauspost/compress/pull/588
|
||||
* zstd: Copy literal in 16 byte blocks when possible https://github.com/klauspost/compress/pull/592
|
||||
* zstd: Speed up when WithDecoderLowmem(false) https://github.com/klauspost/compress/pull/599
|
||||
* zstd: faster next state update in BMI2 version of decode by @WojciechMula in https://github.com/klauspost/compress/pull/593
|
||||
* huff0: Do not check max size when reading table. https://github.com/klauspost/compress/pull/586
|
||||
* flate: Inplace hashing for level 7-9 by @klauspost in https://github.com/klauspost/compress/pull/590
|
||||
|
||||
|
||||
* May 11, 2022 (v1.15.4)
|
||||
* huff0: decompress directly into output by @WojciechMula in [#577](https://github.com/klauspost/compress/pull/577)
|
||||
* inflate: Keep dict on stack [#581](https://github.com/klauspost/compress/pull/581)
|
||||
* zstd: Faster decoding memcopy in asm [#583](https://github.com/klauspost/compress/pull/583)
|
||||
* zstd: Fix ignored crc [#580](https://github.com/klauspost/compress/pull/580)
|
||||
|
||||
* May 5, 2022 (v1.15.3)
|
||||
* zstd: Allow to ignore checksum checking by @WojciechMula [#572](https://github.com/klauspost/compress/pull/572)
|
||||
* s2: Fix incorrect seek for io.SeekEnd in [#575](https://github.com/klauspost/compress/pull/575)
|
||||
|
||||
* Apr 26, 2022 (v1.15.2)
|
||||
* zstd: Add x86-64 assembly for decompression on streams and blocks. Contributed by [@WojciechMula](https://github.com/WojciechMula). Typically 2x faster. [#528](https://github.com/klauspost/compress/pull/528) [#531](https://github.com/klauspost/compress/pull/531) [#545](https://github.com/klauspost/compress/pull/545) [#537](https://github.com/klauspost/compress/pull/537)
|
||||
* zstd: Add options to ZipDecompressor and fixes [#539](https://github.com/klauspost/compress/pull/539)
|
||||
* s2: Use sorted search for index [#555](https://github.com/klauspost/compress/pull/555)
|
||||
* Minimum version is Go 1.16, added CI test on 1.18.
|
||||
|
||||
* Mar 11, 2022 (v1.15.1)
|
||||
* huff0: Add x86 assembly of Decode4X by @WojciechMula in [#512](https://github.com/klauspost/compress/pull/512)
|
||||
* zstd: Reuse zip decoders in [#514](https://github.com/klauspost/compress/pull/514)
|
||||
* zstd: Detect extra block data and report as corrupted in [#520](https://github.com/klauspost/compress/pull/520)
|
||||
* zstd: Handle zero sized frame content size stricter in [#521](https://github.com/klauspost/compress/pull/521)
|
||||
* zstd: Add stricter block size checks in [#523](https://github.com/klauspost/compress/pull/523)
|
||||
|
||||
* Mar 3, 2022 (v1.15.0)
|
||||
* zstd: Refactor decoder by @klauspost in [#498](https://github.com/klauspost/compress/pull/498)
|
||||
* zstd: Add stream encoding without goroutines by @klauspost in [#505](https://github.com/klauspost/compress/pull/505)
|
||||
* huff0: Prevent single blocks exceeding 16 bits by @klauspost in[#507](https://github.com/klauspost/compress/pull/507)
|
||||
* flate: Inline literal emission by @klauspost in [#509](https://github.com/klauspost/compress/pull/509)
|
||||
* gzhttp: Add zstd to transport by @klauspost in [#400](https://github.com/klauspost/compress/pull/400)
|
||||
* gzhttp: Make content-type optional by @klauspost in [#510](https://github.com/klauspost/compress/pull/510)
|
||||
|
||||
Both compression and decompression now supports "synchronous" stream operations. This means that whenever "concurrency" is set to 1, they will operate without spawning goroutines.
|
||||
|
||||
Stream decompression is now faster on asynchronous, since the goroutine allocation much more effectively splits the workload. On typical streams this will typically use 2 cores fully for decompression. When a stream has finished decoding no goroutines will be left over, so decoders can now safely be pooled and still be garbage collected.
|
||||
|
||||
While the release has been extensively tested, it is recommended to testing when upgrading.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>See changes to v1.14.x</summary>
|
||||
|
||||
* Feb 22, 2022 (v1.14.4)
|
||||
* flate: Fix rare huffman only (-2) corruption. [#503](https://github.com/klauspost/compress/pull/503)
|
||||
* zip: Update deprecated CreateHeaderRaw to correctly call CreateRaw by @saracen in [#502](https://github.com/klauspost/compress/pull/502)
|
||||
* zip: don't read data descriptor early by @saracen in [#501](https://github.com/klauspost/compress/pull/501) #501
|
||||
* huff0: Use static decompression buffer up to 30% faster by @klauspost in [#499](https://github.com/klauspost/compress/pull/499) [#500](https://github.com/klauspost/compress/pull/500)
|
||||
|
||||
* Feb 17, 2022 (v1.14.3)
|
||||
* flate: Improve fastest levels compression speed ~10% more throughput. [#482](https://github.com/klauspost/compress/pull/482) [#489](https://github.com/klauspost/compress/pull/489) [#490](https://github.com/klauspost/compress/pull/490) [#491](https://github.com/klauspost/compress/pull/491) [#494](https://github.com/klauspost/compress/pull/494) [#478](https://github.com/klauspost/compress/pull/478)
|
||||
* flate: Faster decompression speed, ~5-10%. [#483](https://github.com/klauspost/compress/pull/483)
|
||||
* s2: Faster compression with Go v1.18 and amd64 microarch level 3+. [#484](https://github.com/klauspost/compress/pull/484) [#486](https://github.com/klauspost/compress/pull/486)
|
||||
|
||||
* Jan 25, 2022 (v1.14.2)
|
||||
* zstd: improve header decoder by @dsnet [#476](https://github.com/klauspost/compress/pull/476)
|
||||
* zstd: Add bigger default blocks [#469](https://github.com/klauspost/compress/pull/469)
|
||||
* zstd: Remove unused decompression buffer [#470](https://github.com/klauspost/compress/pull/470)
|
||||
* zstd: Fix logically dead code by @ningmingxiao [#472](https://github.com/klauspost/compress/pull/472)
|
||||
* flate: Improve level 7-9 [#471](https://github.com/klauspost/compress/pull/471) [#473](https://github.com/klauspost/compress/pull/473)
|
||||
* zstd: Add noasm tag for xxhash [#475](https://github.com/klauspost/compress/pull/475)
|
||||
|
||||
* Jan 11, 2022 (v1.14.1)
|
||||
* s2: Add stream index in [#462](https://github.com/klauspost/compress/pull/462)
|
||||
* flate: Speed and efficiency improvements in [#439](https://github.com/klauspost/compress/pull/439) [#461](https://github.com/klauspost/compress/pull/461) [#455](https://github.com/klauspost/compress/pull/455) [#452](https://github.com/klauspost/compress/pull/452) [#458](https://github.com/klauspost/compress/pull/458)
|
||||
* zstd: Performance improvement in [#420]( https://github.com/klauspost/compress/pull/420) [#456](https://github.com/klauspost/compress/pull/456) [#437](https://github.com/klauspost/compress/pull/437) [#467](https://github.com/klauspost/compress/pull/467) [#468](https://github.com/klauspost/compress/pull/468)
|
||||
* zstd: add arm64 xxhash assembly in [#464](https://github.com/klauspost/compress/pull/464)
|
||||
* Add garbled for binaries for s2 in [#445](https://github.com/klauspost/compress/pull/445)
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>See changes to v1.13.x</summary>
|
||||
|
||||
* Aug 30, 2021 (v1.13.5)
|
||||
* gz/zlib/flate: Alias stdlib errors [#425](https://github.com/klauspost/compress/pull/425)
|
||||
* s2: Add block support to commandline tools [#413](https://github.com/klauspost/compress/pull/413)
|
||||
* zstd: pooledZipWriter should return Writers to the same pool [#426](https://github.com/klauspost/compress/pull/426)
|
||||
* Removed golang/snappy as external dependency for tests [#421](https://github.com/klauspost/compress/pull/421)
|
||||
|
||||
* Aug 12, 2021 (v1.13.4)
|
||||
* Add [snappy replacement package](https://github.com/klauspost/compress/tree/master/snappy).
|
||||
* zstd: Fix incorrect encoding in "best" mode [#415](https://github.com/klauspost/compress/pull/415)
|
||||
|
||||
* Aug 3, 2021 (v1.13.3)
|
||||
* zstd: Improve Best compression [#404](https://github.com/klauspost/compress/pull/404)
|
||||
* zstd: Fix WriteTo error forwarding [#411](https://github.com/klauspost/compress/pull/411)
|
||||
* gzhttp: Return http.HandlerFunc instead of http.Handler. Unlikely breaking change. [#406](https://github.com/klauspost/compress/pull/406)
|
||||
* s2sx: Fix max size error [#399](https://github.com/klauspost/compress/pull/399)
|
||||
* zstd: Add optional stream content size on reset [#401](https://github.com/klauspost/compress/pull/401)
|
||||
* zstd: use SpeedBestCompression for level >= 10 [#410](https://github.com/klauspost/compress/pull/410)
|
||||
|
||||
* Jun 14, 2021 (v1.13.1)
|
||||
* s2: Add full Snappy output support [#396](https://github.com/klauspost/compress/pull/396)
|
||||
* zstd: Add configurable [Decoder window](https://pkg.go.dev/github.com/klauspost/compress/zstd#WithDecoderMaxWindow) size [#394](https://github.com/klauspost/compress/pull/394)
|
||||
* gzhttp: Add header to skip compression [#389](https://github.com/klauspost/compress/pull/389)
|
||||
* s2: Improve speed with bigger output margin [#395](https://github.com/klauspost/compress/pull/395)
|
||||
|
||||
* Jun 3, 2021 (v1.13.0)
|
||||
* Added [gzhttp](https://github.com/klauspost/compress/tree/master/gzhttp#gzip-handler) which allows wrapping HTTP servers and clients with GZIP compressors.
|
||||
* zstd: Detect short invalid signatures [#382](https://github.com/klauspost/compress/pull/382)
|
||||
* zstd: Spawn decoder goroutine only if needed. [#380](https://github.com/klauspost/compress/pull/380)
|
||||
</details>
|
||||
|
||||
|
||||
<details>
|
||||
<summary>See changes to v1.12.x</summary>
|
||||
|
||||
* May 25, 2021 (v1.12.3)
|
||||
* deflate: Better/faster Huffman encoding [#374](https://github.com/klauspost/compress/pull/374)
|
||||
* deflate: Allocate less for history. [#375](https://github.com/klauspost/compress/pull/375)
|
||||
* zstd: Forward read errors [#373](https://github.com/klauspost/compress/pull/373)
|
||||
|
||||
* Apr 27, 2021 (v1.12.2)
|
||||
* zstd: Improve better/best compression [#360](https://github.com/klauspost/compress/pull/360) [#364](https://github.com/klauspost/compress/pull/364) [#365](https://github.com/klauspost/compress/pull/365)
|
||||
* zstd: Add helpers to compress/decompress zstd inside zip files [#363](https://github.com/klauspost/compress/pull/363)
|
||||
* deflate: Improve level 5+6 compression [#367](https://github.com/klauspost/compress/pull/367)
|
||||
* s2: Improve better/best compression [#358](https://github.com/klauspost/compress/pull/358) [#359](https://github.com/klauspost/compress/pull/358)
|
||||
* s2: Load after checking src limit on amd64. [#362](https://github.com/klauspost/compress/pull/362)
|
||||
* s2sx: Limit max executable size [#368](https://github.com/klauspost/compress/pull/368)
|
||||
|
||||
* Apr 14, 2021 (v1.12.1)
|
||||
* snappy package removed. Upstream added as dependency.
|
||||
* s2: Better compression in "best" mode [#353](https://github.com/klauspost/compress/pull/353)
|
||||
* s2sx: Add stdin input and detect pre-compressed from signature [#352](https://github.com/klauspost/compress/pull/352)
|
||||
* s2c/s2d: Add http as possible input [#348](https://github.com/klauspost/compress/pull/348)
|
||||
* s2c/s2d/s2sx: Always truncate when writing files [#352](https://github.com/klauspost/compress/pull/352)
|
||||
* zstd: Reduce memory usage further when using [WithLowerEncoderMem](https://pkg.go.dev/github.com/klauspost/compress/zstd#WithLowerEncoderMem) [#346](https://github.com/klauspost/compress/pull/346)
|
||||
* s2: Fix potential problem with amd64 assembly and profilers [#349](https://github.com/klauspost/compress/pull/349)
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>See changes to v1.11.x</summary>
|
||||
|
||||
* Mar 26, 2021 (v1.11.13)
|
||||
* zstd: Big speedup on small dictionary encodes [#344](https://github.com/klauspost/compress/pull/344) [#345](https://github.com/klauspost/compress/pull/345)
|
||||
* zstd: Add [WithLowerEncoderMem](https://pkg.go.dev/github.com/klauspost/compress/zstd#WithLowerEncoderMem) encoder option [#336](https://github.com/klauspost/compress/pull/336)
|
||||
* deflate: Improve entropy compression [#338](https://github.com/klauspost/compress/pull/338)
|
||||
* s2: Clean up and minor performance improvement in best [#341](https://github.com/klauspost/compress/pull/341)
|
||||
|
||||
* Mar 5, 2021 (v1.11.12)
|
||||
* s2: Add `s2sx` binary that creates [self extracting archives](https://github.com/klauspost/compress/tree/master/s2#s2sx-self-extracting-archives).
|
||||
* s2: Speed up decompression on non-assembly platforms [#328](https://github.com/klauspost/compress/pull/328)
|
||||
|
||||
* Mar 1, 2021 (v1.11.9)
|
||||
* s2: Add ARM64 decompression assembly. Around 2x output speed. [#324](https://github.com/klauspost/compress/pull/324)
|
||||
* s2: Improve "better" speed and efficiency. [#325](https://github.com/klauspost/compress/pull/325)
|
||||
* s2: Fix binaries.
|
||||
|
||||
* Feb 25, 2021 (v1.11.8)
|
||||
* s2: Fixed occasional out-of-bounds write on amd64. Upgrade recommended.
|
||||
* s2: Add AMD64 assembly for better mode. 25-50% faster. [#315](https://github.com/klauspost/compress/pull/315)
|
||||
* s2: Less upfront decoder allocation. [#322](https://github.com/klauspost/compress/pull/322)
|
||||
* zstd: Faster "compression" of incompressible data. [#314](https://github.com/klauspost/compress/pull/314)
|
||||
* zip: Fix zip64 headers. [#313](https://github.com/klauspost/compress/pull/313)
|
||||
|
||||
* Jan 14, 2021 (v1.11.7)
|
||||
* Use Bytes() interface to get bytes across packages. [#309](https://github.com/klauspost/compress/pull/309)
|
||||
* s2: Add 'best' compression option. [#310](https://github.com/klauspost/compress/pull/310)
|
||||
* s2: Add ReaderMaxBlockSize, changes `s2.NewReader` signature to include varargs. [#311](https://github.com/klauspost/compress/pull/311)
|
||||
* s2: Fix crash on small better buffers. [#308](https://github.com/klauspost/compress/pull/308)
|
||||
* s2: Clean up decoder. [#312](https://github.com/klauspost/compress/pull/312)
|
||||
|
||||
* Jan 7, 2021 (v1.11.6)
|
||||
* zstd: Make decoder allocations smaller [#306](https://github.com/klauspost/compress/pull/306)
|
||||
* zstd: Free Decoder resources when Reset is called with a nil io.Reader [#305](https://github.com/klauspost/compress/pull/305)
|
||||
|
||||
* Dec 20, 2020 (v1.11.4)
|
||||
* zstd: Add Best compression mode [#304](https://github.com/klauspost/compress/pull/304)
|
||||
* Add header decoder [#299](https://github.com/klauspost/compress/pull/299)
|
||||
* s2: Add uncompressed stream option [#297](https://github.com/klauspost/compress/pull/297)
|
||||
* Simplify/speed up small blocks with known max size. [#300](https://github.com/klauspost/compress/pull/300)
|
||||
* zstd: Always reset literal dict encoder [#303](https://github.com/klauspost/compress/pull/303)
|
||||
|
||||
* Nov 15, 2020 (v1.11.3)
|
||||
* inflate: 10-15% faster decompression [#293](https://github.com/klauspost/compress/pull/293)
|
||||
* zstd: Tweak DecodeAll default allocation [#295](https://github.com/klauspost/compress/pull/295)
|
||||
|
||||
* Oct 11, 2020 (v1.11.2)
|
||||
* s2: Fix out of bounds read in "better" block compression [#291](https://github.com/klauspost/compress/pull/291)
|
||||
|
||||
* Oct 1, 2020 (v1.11.1)
|
||||
* zstd: Set allLitEntropy true in default configuration [#286](https://github.com/klauspost/compress/pull/286)
|
||||
|
||||
* Sept 8, 2020 (v1.11.0)
|
||||
* zstd: Add experimental compression [dictionaries](https://github.com/klauspost/compress/tree/master/zstd#dictionaries) [#281](https://github.com/klauspost/compress/pull/281)
|
||||
* zstd: Fix mixed Write and ReadFrom calls [#282](https://github.com/klauspost/compress/pull/282)
|
||||
* inflate/gz: Limit variable shifts, ~5% faster decompression [#274](https://github.com/klauspost/compress/pull/274)
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>See changes to v1.10.x</summary>
|
||||
|
||||
* July 8, 2020 (v1.10.11)
|
||||
* zstd: Fix extra block when compressing with ReadFrom. [#278](https://github.com/klauspost/compress/pull/278)
|
||||
* huff0: Also populate compression table when reading decoding table. [#275](https://github.com/klauspost/compress/pull/275)
|
||||
|
||||
* June 23, 2020 (v1.10.10)
|
||||
* zstd: Skip entropy compression in fastest mode when no matches. [#270](https://github.com/klauspost/compress/pull/270)
|
||||
|
||||
* June 16, 2020 (v1.10.9):
|
||||
* zstd: API change for specifying dictionaries. See [#268](https://github.com/klauspost/compress/pull/268)
|
||||
* zip: update CreateHeaderRaw to handle zip64 fields. [#266](https://github.com/klauspost/compress/pull/266)
|
||||
* Fuzzit tests removed. The service has been purchased and is no longer available.
|
||||
|
||||
* June 5, 2020 (v1.10.8):
|
||||
* 1.15x faster zstd block decompression. [#265](https://github.com/klauspost/compress/pull/265)
|
||||
|
||||
* June 1, 2020 (v1.10.7):
|
||||
* Added zstd decompression [dictionary support](https://github.com/klauspost/compress/tree/master/zstd#dictionaries)
|
||||
* Increase zstd decompression speed up to 1.19x. [#259](https://github.com/klauspost/compress/pull/259)
|
||||
* Remove internal reset call in zstd compression and reduce allocations. [#263](https://github.com/klauspost/compress/pull/263)
|
||||
|
||||
* May 21, 2020: (v1.10.6)
|
||||
* zstd: Reduce allocations while decoding. [#258](https://github.com/klauspost/compress/pull/258), [#252](https://github.com/klauspost/compress/pull/252)
|
||||
* zstd: Stricter decompression checks.
|
||||
|
||||
* April 12, 2020: (v1.10.5)
|
||||
* s2-commands: Flush output when receiving SIGINT. [#239](https://github.com/klauspost/compress/pull/239)
|
||||
|
||||
* Apr 8, 2020: (v1.10.4)
|
||||
* zstd: Minor/special case optimizations. [#251](https://github.com/klauspost/compress/pull/251), [#250](https://github.com/klauspost/compress/pull/250), [#249](https://github.com/klauspost/compress/pull/249), [#247](https://github.com/klauspost/compress/pull/247)
|
||||
* Mar 11, 2020: (v1.10.3)
|
||||
* s2: Use S2 encoder in pure Go mode for Snappy output as well. [#245](https://github.com/klauspost/compress/pull/245)
|
||||
* s2: Fix pure Go block encoder. [#244](https://github.com/klauspost/compress/pull/244)
|
||||
* zstd: Added "better compression" mode. [#240](https://github.com/klauspost/compress/pull/240)
|
||||
* zstd: Improve speed of fastest compression mode by 5-10% [#241](https://github.com/klauspost/compress/pull/241)
|
||||
* zstd: Skip creating encoders when not needed. [#238](https://github.com/klauspost/compress/pull/238)
|
||||
|
||||
* Feb 27, 2020: (v1.10.2)
|
||||
* Close to 50% speedup in inflate (gzip/zip decompression). [#236](https://github.com/klauspost/compress/pull/236) [#234](https://github.com/klauspost/compress/pull/234) [#232](https://github.com/klauspost/compress/pull/232)
|
||||
* Reduce deflate level 1-6 memory usage up to 59%. [#227](https://github.com/klauspost/compress/pull/227)
|
||||
|
||||
* Feb 18, 2020: (v1.10.1)
|
||||
* Fix zstd crash when resetting multiple times without sending data. [#226](https://github.com/klauspost/compress/pull/226)
|
||||
* deflate: Fix dictionary use on level 1-6. [#224](https://github.com/klauspost/compress/pull/224)
|
||||
* Remove deflate writer reference when closing. [#224](https://github.com/klauspost/compress/pull/224)
|
||||
|
||||
* Feb 4, 2020: (v1.10.0)
|
||||
* Add optional dictionary to [stateless deflate](https://pkg.go.dev/github.com/klauspost/compress/flate?tab=doc#StatelessDeflate). Breaking change, send `nil` for previous behaviour. [#216](https://github.com/klauspost/compress/pull/216)
|
||||
* Fix buffer overflow on repeated small block deflate. [#218](https://github.com/klauspost/compress/pull/218)
|
||||
* Allow copying content from an existing ZIP file without decompressing+compressing. [#214](https://github.com/klauspost/compress/pull/214)
|
||||
* Added [S2](https://github.com/klauspost/compress/tree/master/s2#s2-compression) AMD64 assembler and various optimizations. Stream speed >10GB/s. [#186](https://github.com/klauspost/compress/pull/186)
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>See changes prior to v1.10.0</summary>
|
||||
|
||||
* Jan 20,2020 (v1.9.8) Optimize gzip/deflate with better size estimates and faster table generation. [#207](https://github.com/klauspost/compress/pull/207) by [luyu6056](https://github.com/luyu6056), [#206](https://github.com/klauspost/compress/pull/206).
|
||||
* Jan 11, 2020: S2 Encode/Decode will use provided buffer if capacity is big enough. [#204](https://github.com/klauspost/compress/pull/204)
|
||||
* Jan 5, 2020: (v1.9.7) Fix another zstd regression in v1.9.5 - v1.9.6 removed.
|
||||
* Jan 4, 2020: (v1.9.6) Regression in v1.9.5 fixed causing corrupt zstd encodes in rare cases.
|
||||
* Jan 4, 2020: Faster IO in [s2c + s2d commandline tools](https://github.com/klauspost/compress/tree/master/s2#commandline-tools) compression/decompression. [#192](https://github.com/klauspost/compress/pull/192)
|
||||
* Dec 29, 2019: Removed v1.9.5 since fuzz tests showed a compatibility problem with the reference zstandard decoder.
|
||||
* Dec 29, 2019: (v1.9.5) zstd: 10-20% faster block compression. [#199](https://github.com/klauspost/compress/pull/199)
|
||||
* Dec 29, 2019: [zip](https://godoc.org/github.com/klauspost/compress/zip) package updated with latest Go features
|
||||
* Dec 29, 2019: zstd: Single segment flag condintions tweaked. [#197](https://github.com/klauspost/compress/pull/197)
|
||||
* Dec 18, 2019: s2: Faster compression when ReadFrom is used. [#198](https://github.com/klauspost/compress/pull/198)
|
||||
* Dec 10, 2019: s2: Fix repeat length output when just above at 16MB limit.
|
||||
* Dec 10, 2019: zstd: Add function to get decoder as io.ReadCloser. [#191](https://github.com/klauspost/compress/pull/191)
|
||||
* Dec 3, 2019: (v1.9.4) S2: limit max repeat length. [#188](https://github.com/klauspost/compress/pull/188)
|
||||
* Dec 3, 2019: Add [WithNoEntropyCompression](https://godoc.org/github.com/klauspost/compress/zstd#WithNoEntropyCompression) to zstd [#187](https://github.com/klauspost/compress/pull/187)
|
||||
* Dec 3, 2019: Reduce memory use for tests. Check for leaked goroutines.
|
||||
* Nov 28, 2019 (v1.9.3) Less allocations in stateless deflate.
|
||||
* Nov 28, 2019: 5-20% Faster huff0 decode. Impacts zstd as well. [#184](https://github.com/klauspost/compress/pull/184)
|
||||
* Nov 12, 2019 (v1.9.2) Added [Stateless Compression](#stateless-compression) for gzip/deflate.
|
||||
* Nov 12, 2019: Fixed zstd decompression of large single blocks. [#180](https://github.com/klauspost/compress/pull/180)
|
||||
* Nov 11, 2019: Set default [s2c](https://github.com/klauspost/compress/tree/master/s2#commandline-tools) block size to 4MB.
|
||||
* Nov 11, 2019: Reduce inflate memory use by 1KB.
|
||||
* Nov 10, 2019: Less allocations in deflate bit writer.
|
||||
* Nov 10, 2019: Fix inconsistent error returned by zstd decoder.
|
||||
* Oct 28, 2019 (v1.9.1) ztsd: Fix crash when compressing blocks. [#174](https://github.com/klauspost/compress/pull/174)
|
||||
* Oct 24, 2019 (v1.9.0) zstd: Fix rare data corruption [#173](https://github.com/klauspost/compress/pull/173)
|
||||
* Oct 24, 2019 zstd: Fix huff0 out of buffer write [#171](https://github.com/klauspost/compress/pull/171) and always return errors [#172](https://github.com/klauspost/compress/pull/172)
|
||||
* Oct 10, 2019: Big deflate rewrite, 30-40% faster with better compression [#105](https://github.com/klauspost/compress/pull/105)
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>See changes prior to v1.9.0</summary>
|
||||
|
||||
* Oct 10, 2019: (v1.8.6) zstd: Allow partial reads to get flushed data. [#169](https://github.com/klauspost/compress/pull/169)
|
||||
* Oct 3, 2019: Fix inconsistent results on broken zstd streams.
|
||||
* Sep 25, 2019: Added `-rm` (remove source files) and `-q` (no output except errors) to `s2c` and `s2d` [commands](https://github.com/klauspost/compress/tree/master/s2#commandline-tools)
|
||||
* Sep 16, 2019: (v1.8.4) Add `s2c` and `s2d` [commandline tools](https://github.com/klauspost/compress/tree/master/s2#commandline-tools).
|
||||
* Sep 10, 2019: (v1.8.3) Fix s2 decoder [Skip](https://godoc.org/github.com/klauspost/compress/s2#Reader.Skip).
|
||||
* Sep 7, 2019: zstd: Added [WithWindowSize](https://godoc.org/github.com/klauspost/compress/zstd#WithWindowSize), contributed by [ianwilkes](https://github.com/ianwilkes).
|
||||
* Sep 5, 2019: (v1.8.2) Add [WithZeroFrames](https://godoc.org/github.com/klauspost/compress/zstd#WithZeroFrames) which adds full zero payload block encoding option.
|
||||
* Sep 5, 2019: Lazy initialization of zstandard predefined en/decoder tables.
|
||||
* Aug 26, 2019: (v1.8.1) S2: 1-2% compression increase in "better" compression mode.
|
||||
* Aug 26, 2019: zstd: Check maximum size of Huffman 1X compressed literals while decoding.
|
||||
* Aug 24, 2019: (v1.8.0) Added [S2 compression](https://github.com/klauspost/compress/tree/master/s2#s2-compression), a high performance replacement for Snappy.
|
||||
* Aug 21, 2019: (v1.7.6) Fixed minor issues found by fuzzer. One could lead to zstd not decompressing.
|
||||
* Aug 18, 2019: Add [fuzzit](https://fuzzit.dev/) continuous fuzzing.
|
||||
* Aug 14, 2019: zstd: Skip incompressible data 2x faster. [#147](https://github.com/klauspost/compress/pull/147)
|
||||
* Aug 4, 2019 (v1.7.5): Better literal compression. [#146](https://github.com/klauspost/compress/pull/146)
|
||||
* Aug 4, 2019: Faster zstd compression. [#143](https://github.com/klauspost/compress/pull/143) [#144](https://github.com/klauspost/compress/pull/144)
|
||||
* Aug 4, 2019: Faster zstd decompression. [#145](https://github.com/klauspost/compress/pull/145) [#143](https://github.com/klauspost/compress/pull/143) [#142](https://github.com/klauspost/compress/pull/142)
|
||||
* July 15, 2019 (v1.7.4): Fix double EOF block in rare cases on zstd encoder.
|
||||
* July 15, 2019 (v1.7.3): Minor speedup/compression increase in default zstd encoder.
|
||||
* July 14, 2019: zstd decoder: Fix decompression error on multiple uses with mixed content.
|
||||
* July 7, 2019 (v1.7.2): Snappy update, zstd decoder potential race fix.
|
||||
* June 17, 2019: zstd decompression bugfix.
|
||||
* June 17, 2019: fix 32 bit builds.
|
||||
* June 17, 2019: Easier use in modules (less dependencies).
|
||||
* June 9, 2019: New stronger "default" [zstd](https://github.com/klauspost/compress/tree/master/zstd#zstd) compression mode. Matches zstd default compression ratio.
|
||||
* June 5, 2019: 20-40% throughput in [zstandard](https://github.com/klauspost/compress/tree/master/zstd#zstd) compression and better compression.
|
||||
* June 5, 2019: deflate/gzip compression: Reduce memory usage of lower compression levels.
|
||||
* June 2, 2019: Added [zstandard](https://github.com/klauspost/compress/tree/master/zstd#zstd) compression!
|
||||
* May 25, 2019: deflate/gzip: 10% faster bit writer, mostly visible in lower levels.
|
||||
* Apr 22, 2019: [zstd](https://github.com/klauspost/compress/tree/master/zstd#zstd) decompression added.
|
||||
* Aug 1, 2018: Added [huff0 README](https://github.com/klauspost/compress/tree/master/huff0#huff0-entropy-compression).
|
||||
* Jul 8, 2018: Added [Performance Update 2018](#performance-update-2018) below.
|
||||
* Jun 23, 2018: Merged [Go 1.11 inflate optimizations](https://go-review.googlesource.com/c/go/+/102235). Go 1.9 is now required. Backwards compatible version tagged with [v1.3.0](https://github.com/klauspost/compress/releases/tag/v1.3.0).
|
||||
* Apr 2, 2018: Added [huff0](https://godoc.org/github.com/klauspost/compress/huff0) en/decoder. Experimental for now, API may change.
|
||||
* Mar 4, 2018: Added [FSE Entropy](https://godoc.org/github.com/klauspost/compress/fse) en/decoder. Experimental for now, API may change.
|
||||
* Nov 3, 2017: Add compression [Estimate](https://godoc.org/github.com/klauspost/compress#Estimate) function.
|
||||
* May 28, 2017: Reduce allocations when resetting decoder.
|
||||
* Apr 02, 2017: Change back to official crc32, since changes were merged in Go 1.7.
|
||||
* Jan 14, 2017: Reduce stack pressure due to array copies. See [Issue #18625](https://github.com/golang/go/issues/18625).
|
||||
* Oct 25, 2016: Level 2-4 have been rewritten and now offers significantly better performance than before.
|
||||
* Oct 20, 2016: Port zlib changes from Go 1.7 to fix zlib writer issue. Please update.
|
||||
* Oct 16, 2016: Go 1.7 changes merged. Apples to apples this package is a few percent faster, but has a significantly better balance between speed and compression per level.
|
||||
* Mar 24, 2016: Always attempt Huffman encoding on level 4-7. This improves base 64 encoded data compression.
|
||||
* Mar 24, 2016: Small speedup for level 1-3.
|
||||
* Feb 19, 2016: Faster bit writer, level -2 is 15% faster, level 1 is 4% faster.
|
||||
* Feb 19, 2016: Handle small payloads faster in level 1-3.
|
||||
* Feb 19, 2016: Added faster level 2 + 3 compression modes.
|
||||
* Feb 19, 2016: [Rebalanced compression levels](https://blog.klauspost.com/rebalancing-deflate-compression-levels/), so there is a more even progression in terms of compression. New default level is 5.
|
||||
* Feb 14, 2016: Snappy: Merge upstream changes.
|
||||
* Feb 14, 2016: Snappy: Fix aggressive skipping.
|
||||
* Feb 14, 2016: Snappy: Update benchmark.
|
||||
* Feb 13, 2016: Deflate: Fixed assembler problem that could lead to sub-optimal compression.
|
||||
* Feb 12, 2016: Snappy: Added AMD64 SSE 4.2 optimizations to matching, which makes easy to compress material run faster. Typical speedup is around 25%.
|
||||
* Feb 9, 2016: Added Snappy package fork. This version is 5-7% faster, much more on hard to compress content.
|
||||
* Jan 30, 2016: Optimize level 1 to 3 by not considering static dictionary or storing uncompressed. ~4-5% speedup.
|
||||
* Jan 16, 2016: Optimization on deflate level 1,2,3 compression.
|
||||
* Jan 8 2016: Merge [CL 18317](https://go-review.googlesource.com/#/c/18317): fix reading, writing of zip64 archives.
|
||||
* Dec 8 2015: Make level 1 and -2 deterministic even if write size differs.
|
||||
* Dec 8 2015: Split encoding functions, so hashing and matching can potentially be inlined. 1-3% faster on AMD64. 5% faster on other platforms.
|
||||
* Dec 8 2015: Fixed rare [one byte out-of bounds read](https://github.com/klauspost/compress/issues/20). Please update!
|
||||
* Nov 23 2015: Optimization on token writer. ~2-4% faster. Contributed by [@dsnet](https://github.com/dsnet).
|
||||
* Nov 20 2015: Small optimization to bit writer on 64 bit systems.
|
||||
* Nov 17 2015: Fixed out-of-bound errors if the underlying Writer returned an error. See [#15](https://github.com/klauspost/compress/issues/15).
|
||||
* Nov 12 2015: Added [io.WriterTo](https://golang.org/pkg/io/#WriterTo) support to gzip/inflate.
|
||||
* Nov 11 2015: Merged [CL 16669](https://go-review.googlesource.com/#/c/16669/4): archive/zip: enable overriding (de)compressors per file
|
||||
* Oct 15 2015: Added skipping on uncompressible data. Random data speed up >5x.
|
||||
|
||||
</details>
|
||||
|
||||
# deflate usage
|
||||
|
||||
The packages are drop-in replacements for standard libraries. Simply replace the import path to use them:
|
||||
|
||||
| old import | new import | Documentation
|
||||
|--------------------|-----------------------------------------|--------------------|
|
||||
| `compress/gzip` | `github.com/klauspost/compress/gzip` | [gzip](https://pkg.go.dev/github.com/klauspost/compress/gzip?tab=doc)
|
||||
| `compress/zlib` | `github.com/klauspost/compress/zlib` | [zlib](https://pkg.go.dev/github.com/klauspost/compress/zlib?tab=doc)
|
||||
| `archive/zip` | `github.com/klauspost/compress/zip` | [zip](https://pkg.go.dev/github.com/klauspost/compress/zip?tab=doc)
|
||||
| `compress/flate` | `github.com/klauspost/compress/flate` | [flate](https://pkg.go.dev/github.com/klauspost/compress/flate?tab=doc)
|
||||
|
||||
* Optimized [deflate](https://godoc.org/github.com/klauspost/compress/flate) packages which can be used as a dropin replacement for [gzip](https://godoc.org/github.com/klauspost/compress/gzip), [zip](https://godoc.org/github.com/klauspost/compress/zip) and [zlib](https://godoc.org/github.com/klauspost/compress/zlib).
|
||||
|
||||
You may also be interested in [pgzip](https://github.com/klauspost/pgzip), which is a drop in replacement for gzip, which support multithreaded compression on big files and the optimized [crc32](https://github.com/klauspost/crc32) package used by these packages.
|
||||
|
||||
The packages contains the same as the standard library, so you can use the godoc for that: [gzip](http://golang.org/pkg/compress/gzip/), [zip](http://golang.org/pkg/archive/zip/), [zlib](http://golang.org/pkg/compress/zlib/), [flate](http://golang.org/pkg/compress/flate/).
|
||||
|
||||
Currently there is only minor speedup on decompression (mostly CRC32 calculation).
|
||||
|
||||
Memory usage is typically 1MB for a Writer. stdlib is in the same range.
|
||||
If you expect to have a lot of concurrently allocated Writers consider using
|
||||
the stateless compress described below.
|
||||
|
||||
For compression performance, see: [this spreadsheet](https://docs.google.com/spreadsheets/d/1nuNE2nPfuINCZJRMt6wFWhKpToF95I47XjSsc-1rbPQ/edit?usp=sharing).
|
||||
|
||||
To disable all assembly add `-tags=noasm`. This works across all packages.
|
||||
|
||||
# Stateless compression
|
||||
|
||||
This package offers stateless compression as a special option for gzip/deflate.
|
||||
It will do compression but without maintaining any state between Write calls.
|
||||
|
||||
This means there will be no memory kept between Write calls, but compression and speed will be suboptimal.
|
||||
|
||||
This is only relevant in cases where you expect to run many thousands of compressors concurrently,
|
||||
but with very little activity. This is *not* intended for regular web servers serving individual requests.
|
||||
|
||||
Because of this, the size of actual Write calls will affect output size.
|
||||
|
||||
In gzip, specify level `-3` / `gzip.StatelessCompression` to enable.
|
||||
|
||||
For direct deflate use, NewStatelessWriter and StatelessDeflate are available. See [documentation](https://godoc.org/github.com/klauspost/compress/flate#NewStatelessWriter)
|
||||
|
||||
A `bufio.Writer` can of course be used to control write sizes. For example, to use a 4KB buffer:
|
||||
|
||||
```go
|
||||
// replace 'ioutil.Discard' with your output.
|
||||
gzw, err := gzip.NewWriterLevel(ioutil.Discard, gzip.StatelessCompression)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer gzw.Close()
|
||||
|
||||
w := bufio.NewWriterSize(gzw, 4096)
|
||||
defer w.Flush()
|
||||
|
||||
// Write to 'w'
|
||||
```
|
||||
|
||||
This will only use up to 4KB in memory when the writer is idle.
|
||||
|
||||
Compression is almost always worse than the fastest compression level
|
||||
and each write will allocate (a little) memory.
|
||||
|
||||
# Performance Update 2018
|
||||
|
||||
It has been a while since we have been looking at the speed of this package compared to the standard library, so I thought I would re-do my tests and give some overall recommendations based on the current state. All benchmarks have been performed with Go 1.10 on my Desktop Intel(R) Core(TM) i7-2600 CPU @3.40GHz. Since I last ran the tests, I have gotten more RAM, which means tests with big files are no longer limited by my SSD.
|
||||
|
||||
The raw results are in my [updated spreadsheet](https://docs.google.com/spreadsheets/d/1nuNE2nPfuINCZJRMt6wFWhKpToF95I47XjSsc-1rbPQ/edit?usp=sharing). Due to cgo changes and upstream updates i could not get the cgo version of gzip to compile. Instead I included the [zstd](https://github.com/datadog/zstd) cgo implementation. If I get cgo gzip to work again, I might replace the results in the sheet.
|
||||
|
||||
The columns to take note of are: *MB/s* - the throughput. *Reduction* - the data size reduction in percent of the original. *Rel Speed* relative speed compared to the standard library at the same level. *Smaller* - how many percent smaller is the compressed output compared to stdlib. Negative means the output was bigger. *Loss* means the loss (or gain) in compression as a percentage difference of the input.
|
||||
|
||||
The `gzstd` (standard library gzip) and `gzkp` (this package gzip) only uses one CPU core. [`pgzip`](https://github.com/klauspost/pgzip), [`bgzf`](https://github.com/biogo/hts/tree/master/bgzf) uses all 4 cores. [`zstd`](https://github.com/DataDog/zstd) uses one core, and is a beast (but not Go, yet).
|
||||
|
||||
|
||||
## Overall differences.
|
||||
|
||||
There appears to be a roughly 5-10% speed advantage over the standard library when comparing at similar compression levels.
|
||||
|
||||
The biggest difference you will see is the result of [re-balancing](https://blog.klauspost.com/rebalancing-deflate-compression-levels/) the compression levels. I wanted by library to give a smoother transition between the compression levels than the standard library.
|
||||
|
||||
This package attempts to provide a more smooth transition, where "1" is taking a lot of shortcuts, "5" is the reasonable trade-off and "9" is the "give me the best compression", and the values in between gives something reasonable in between. The standard library has big differences in levels 1-4, but levels 5-9 having no significant gains - often spending a lot more time than can be justified by the achieved compression.
|
||||
|
||||
There are links to all the test data in the [spreadsheet](https://docs.google.com/spreadsheets/d/1nuNE2nPfuINCZJRMt6wFWhKpToF95I47XjSsc-1rbPQ/edit?usp=sharing) in the top left field on each tab.
|
||||
|
||||
## Web Content
|
||||
|
||||
This test set aims to emulate typical use in a web server. The test-set is 4GB data in 53k files, and is a mixture of (mostly) HTML, JS, CSS.
|
||||
|
||||
Since level 1 and 9 are close to being the same code, they are quite close. But looking at the levels in-between the differences are quite big.
|
||||
|
||||
Looking at level 6, this package is 88% faster, but will output about 6% more data. For a web server, this means you can serve 88% more data, but have to pay for 6% more bandwidth. You can draw your own conclusions on what would be the most expensive for your case.
|
||||
|
||||
## Object files
|
||||
|
||||
This test is for typical data files stored on a server. In this case it is a collection of Go precompiled objects. They are very compressible.
|
||||
|
||||
The picture is similar to the web content, but with small differences since this is very compressible. Levels 2-3 offer good speed, but is sacrificing quite a bit of compression.
|
||||
|
||||
The standard library seems suboptimal on level 3 and 4 - offering both worse compression and speed than level 6 & 7 of this package respectively.
|
||||
|
||||
## Highly Compressible File
|
||||
|
||||
This is a JSON file with very high redundancy. The reduction starts at 95% on level 1, so in real life terms we are dealing with something like a highly redundant stream of data, etc.
|
||||
|
||||
It is definitely visible that we are dealing with specialized content here, so the results are very scattered. This package does not do very well at levels 1-4, but picks up significantly at level 5 and levels 7 and 8 offering great speed for the achieved compression.
|
||||
|
||||
So if you know you content is extremely compressible you might want to go slightly higher than the defaults. The standard library has a huge gap between levels 3 and 4 in terms of speed (2.75x slowdown), so it offers little "middle ground".
|
||||
|
||||
## Medium-High Compressible
|
||||
|
||||
This is a pretty common test corpus: [enwik9](http://mattmahoney.net/dc/textdata.html). It contains the first 10^9 bytes of the English Wikipedia dump on Mar. 3, 2006. This is a very good test of typical text based compression and more data heavy streams.
|
||||
|
||||
We see a similar picture here as in "Web Content". On equal levels some compression is sacrificed for more speed. Level 5 seems to be the best trade-off between speed and size, beating stdlib level 3 in both.
|
||||
|
||||
## Medium Compressible
|
||||
|
||||
I will combine two test sets, one [10GB file set](http://mattmahoney.net/dc/10gb.html) and a VM disk image (~8GB). Both contain different data types and represent a typical backup scenario.
|
||||
|
||||
The most notable thing is how quickly the standard library drops to very low compression speeds around level 5-6 without any big gains in compression. Since this type of data is fairly common, this does not seem like good behavior.
|
||||
|
||||
|
||||
## Un-compressible Content
|
||||
|
||||
This is mainly a test of how good the algorithms are at detecting un-compressible input. The standard library only offers this feature with very conservative settings at level 1. Obviously there is no reason for the algorithms to try to compress input that cannot be compressed. The only downside is that it might skip some compressible data on false detections.
|
||||
|
||||
|
||||
## Huffman only compression
|
||||
|
||||
This compression library adds a special compression level, named `HuffmanOnly`, which allows near linear time compression. This is done by completely disabling matching of previous data, and only reduce the number of bits to represent each character.
|
||||
|
||||
This means that often used characters, like 'e' and ' ' (space) in text use the fewest bits to represent, and rare characters like '¤' takes more bits to represent. For more information see [wikipedia](https://en.wikipedia.org/wiki/Huffman_coding) or this nice [video](https://youtu.be/ZdooBTdW5bM).
|
||||
|
||||
Since this type of compression has much less variance, the compression speed is mostly unaffected by the input data, and is usually more than *180MB/s* for a single core.
|
||||
|
||||
The downside is that the compression ratio is usually considerably worse than even the fastest conventional compression. The compression ratio can never be better than 8:1 (12.5%).
|
||||
|
||||
The linear time compression can be used as a "better than nothing" mode, where you cannot risk the encoder to slow down on some content. For comparison, the size of the "Twain" text is *233460 bytes* (+29% vs. level 1) and encode speed is 144MB/s (4.5x level 1). So in this case you trade a 30% size increase for a 4 times speedup.
|
||||
|
||||
For more information see my blog post on [Fast Linear Time Compression](http://blog.klauspost.com/constant-time-gzipzip-compression/).
|
||||
|
||||
This is implemented on Go 1.7 as "Huffman Only" mode, though not exposed for gzip.
|
||||
|
||||
# Other packages
|
||||
|
||||
Here are other packages of good quality and pure Go (no cgo wrappers or autoconverted code):
|
||||
|
||||
* [github.com/pierrec/lz4](https://github.com/pierrec/lz4) - strong multithreaded LZ4 compression.
|
||||
* [github.com/cosnicolaou/pbzip2](https://github.com/cosnicolaou/pbzip2) - multithreaded bzip2 decompression.
|
||||
* [github.com/dsnet/compress](https://github.com/dsnet/compress) - brotli decompression, bzip2 writer.
|
||||
* [github.com/ronanh/intcomp](https://github.com/ronanh/intcomp) - Integer compression.
|
||||
* [github.com/spenczar/fpc](https://github.com/spenczar/fpc) - Float compression.
|
||||
* [github.com/minio/zipindex](https://github.com/minio/zipindex) - External ZIP directory index.
|
||||
* [github.com/ybirader/pzip](https://github.com/ybirader/pzip) - Fast concurrent zip archiver and extractor.
|
||||
|
||||
# license
|
||||
|
||||
This code is licensed under the same conditions as the original Go code. See LICENSE file.
|
||||
25
vendor/github.com/klauspost/compress/SECURITY.md
generated
vendored
25
vendor/github.com/klauspost/compress/SECURITY.md
generated
vendored
@ -1,25 +0,0 @@
|
||||
# Security Policy
|
||||
|
||||
## Supported Versions
|
||||
|
||||
Security updates are applied only to the latest release.
|
||||
|
||||
## Vulnerability Definition
|
||||
|
||||
A security vulnerability is a bug that with certain input triggers a crash or an infinite loop. Most calls will have varying execution time and only in rare cases will slow operation be considered a security vulnerability.
|
||||
|
||||
Corrupted output generally is not considered a security vulnerability, unless independent operations are able to affect each other. Note that not all functionality is re-entrant and safe to use concurrently.
|
||||
|
||||
Out-of-memory crashes only applies if the en/decoder uses an abnormal amount of memory, with appropriate options applied, to limit maximum window size, concurrency, etc. However, if you are in doubt you are welcome to file a security issue.
|
||||
|
||||
It is assumed that all callers are trusted, meaning internal data exposed through reflection or inspection of returned data structures is not considered a vulnerability.
|
||||
|
||||
Vulnerabilities resulting from compiler/assembler errors should be reported upstream. Depending on the severity this package may or may not implement a workaround.
|
||||
|
||||
## Reporting a Vulnerability
|
||||
|
||||
If you have discovered a security vulnerability in this project, please report it privately. **Do not disclose it as a public issue.** This gives us time to work with you to fix the issue before public exposure, reducing the chance that the exploit will be used before a patch is released.
|
||||
|
||||
Please disclose it at [security advisory](https://github.com/klauspost/compress/security/advisories/new). If possible please provide a minimal reproducer. If the issue only applies to a single platform, it would be helpful to provide access to that.
|
||||
|
||||
This project is maintained by a team of volunteers on a reasonable-effort basis. As such, vulnerabilities will be disclosed in a best effort base.
|
||||
85
vendor/github.com/klauspost/compress/compressible.go
generated
vendored
85
vendor/github.com/klauspost/compress/compressible.go
generated
vendored
@ -1,85 +0,0 @@
|
||||
package compress
|
||||
|
||||
import "math"
|
||||
|
||||
// Estimate returns a normalized compressibility estimate of block b.
|
||||
// Values close to zero are likely uncompressible.
|
||||
// Values above 0.1 are likely to be compressible.
|
||||
// Values above 0.5 are very compressible.
|
||||
// Very small lengths will return 0.
|
||||
func Estimate(b []byte) float64 {
|
||||
if len(b) < 16 {
|
||||
return 0
|
||||
}
|
||||
|
||||
// Correctly predicted order 1
|
||||
hits := 0
|
||||
lastMatch := false
|
||||
var o1 [256]byte
|
||||
var hist [256]int
|
||||
c1 := byte(0)
|
||||
for _, c := range b {
|
||||
if c == o1[c1] {
|
||||
// We only count a hit if there was two correct predictions in a row.
|
||||
if lastMatch {
|
||||
hits++
|
||||
}
|
||||
lastMatch = true
|
||||
} else {
|
||||
lastMatch = false
|
||||
}
|
||||
o1[c1] = c
|
||||
c1 = c
|
||||
hist[c]++
|
||||
}
|
||||
|
||||
// Use x^0.6 to give better spread
|
||||
prediction := math.Pow(float64(hits)/float64(len(b)), 0.6)
|
||||
|
||||
// Calculate histogram distribution
|
||||
variance := float64(0)
|
||||
avg := float64(len(b)) / 256
|
||||
|
||||
for _, v := range hist {
|
||||
Δ := float64(v) - avg
|
||||
variance += Δ * Δ
|
||||
}
|
||||
|
||||
stddev := math.Sqrt(float64(variance)) / float64(len(b))
|
||||
exp := math.Sqrt(1 / float64(len(b)))
|
||||
|
||||
// Subtract expected stddev
|
||||
stddev -= exp
|
||||
if stddev < 0 {
|
||||
stddev = 0
|
||||
}
|
||||
stddev *= 1 + exp
|
||||
|
||||
// Use x^0.4 to give better spread
|
||||
entropy := math.Pow(stddev, 0.4)
|
||||
|
||||
// 50/50 weight between prediction and histogram distribution
|
||||
return math.Pow((prediction+entropy)/2, 0.9)
|
||||
}
|
||||
|
||||
// ShannonEntropyBits returns the number of bits minimum required to represent
|
||||
// an entropy encoding of the input bytes.
|
||||
// https://en.wiktionary.org/wiki/Shannon_entropy
|
||||
func ShannonEntropyBits(b []byte) int {
|
||||
if len(b) == 0 {
|
||||
return 0
|
||||
}
|
||||
var hist [256]int
|
||||
for _, c := range b {
|
||||
hist[c]++
|
||||
}
|
||||
shannon := float64(0)
|
||||
invTotal := 1.0 / float64(len(b))
|
||||
for _, v := range hist[:] {
|
||||
if v > 0 {
|
||||
n := float64(v)
|
||||
shannon += math.Ceil(-math.Log2(n*invTotal) * n)
|
||||
}
|
||||
}
|
||||
return int(math.Ceil(shannon))
|
||||
}
|
||||
79
vendor/github.com/klauspost/compress/fse/README.md
generated
vendored
79
vendor/github.com/klauspost/compress/fse/README.md
generated
vendored
@ -1,79 +0,0 @@
|
||||
# Finite State Entropy
|
||||
|
||||
This package provides Finite State Entropy encoding and decoding.
|
||||
|
||||
Finite State Entropy (also referenced as [tANS](https://en.wikipedia.org/wiki/Asymmetric_numeral_systems#tANS))
|
||||
encoding provides a fast near-optimal symbol encoding/decoding
|
||||
for byte blocks as implemented in [zstandard](https://github.com/facebook/zstd).
|
||||
|
||||
This can be used for compressing input with a lot of similar input values to the smallest number of bytes.
|
||||
This does not perform any multi-byte [dictionary coding](https://en.wikipedia.org/wiki/Dictionary_coder) as LZ coders,
|
||||
but it can be used as a secondary step to compressors (like Snappy) that does not do entropy encoding.
|
||||
|
||||
* [Godoc documentation](https://godoc.org/github.com/klauspost/compress/fse)
|
||||
|
||||
## News
|
||||
|
||||
* Feb 2018: First implementation released. Consider this beta software for now.
|
||||
|
||||
# Usage
|
||||
|
||||
This package provides a low level interface that allows to compress single independent blocks.
|
||||
|
||||
Each block is separate, and there is no built in integrity checks.
|
||||
This means that the caller should keep track of block sizes and also do checksums if needed.
|
||||
|
||||
Compressing a block is done via the [`Compress`](https://godoc.org/github.com/klauspost/compress/fse#Compress) function.
|
||||
You must provide input and will receive the output and maybe an error.
|
||||
|
||||
These error values can be returned:
|
||||
|
||||
| Error | Description |
|
||||
|---------------------|-----------------------------------------------------------------------------|
|
||||
| `<nil>` | Everything ok, output is returned |
|
||||
| `ErrIncompressible` | Returned when input is judged to be too hard to compress |
|
||||
| `ErrUseRLE` | Returned from the compressor when the input is a single byte value repeated |
|
||||
| `(error)` | An internal error occurred. |
|
||||
|
||||
As can be seen above there are errors that will be returned even under normal operation so it is important to handle these.
|
||||
|
||||
To reduce allocations you can provide a [`Scratch`](https://godoc.org/github.com/klauspost/compress/fse#Scratch) object
|
||||
that can be re-used for successive calls. Both compression and decompression accepts a `Scratch` object, and the same
|
||||
object can be used for both.
|
||||
|
||||
Be aware, that when re-using a `Scratch` object that the *output* buffer is also re-used, so if you are still using this
|
||||
you must set the `Out` field in the scratch to nil. The same buffer is used for compression and decompression output.
|
||||
|
||||
Decompressing is done by calling the [`Decompress`](https://godoc.org/github.com/klauspost/compress/fse#Decompress) function.
|
||||
You must provide the output from the compression stage, at exactly the size you got back. If you receive an error back
|
||||
your input was likely corrupted.
|
||||
|
||||
It is important to note that a successful decoding does *not* mean your output matches your original input.
|
||||
There are no integrity checks, so relying on errors from the decompressor does not assure your data is valid.
|
||||
|
||||
For more detailed usage, see examples in the [godoc documentation](https://godoc.org/github.com/klauspost/compress/fse#pkg-examples).
|
||||
|
||||
# Performance
|
||||
|
||||
A lot of factors are affecting speed. Block sizes and compressibility of the material are primary factors.
|
||||
All compression functions are currently only running on the calling goroutine so only one core will be used per block.
|
||||
|
||||
The compressor is significantly faster if symbols are kept as small as possible. The highest byte value of the input
|
||||
is used to reduce some of the processing, so if all your input is above byte value 64 for instance, it may be
|
||||
beneficial to transpose all your input values down by 64.
|
||||
|
||||
With moderate block sizes around 64k speed are typically 200MB/s per core for compression and
|
||||
around 300MB/s decompression speed.
|
||||
|
||||
The same hardware typically does Huffman (deflate) encoding at 125MB/s and decompression at 100MB/s.
|
||||
|
||||
# Plans
|
||||
|
||||
At one point, more internals will be exposed to facilitate more "expert" usage of the components.
|
||||
|
||||
A streaming interface is also likely to be implemented. Likely compatible with [FSE stream format](https://github.com/Cyan4973/FiniteStateEntropy/blob/dev/programs/fileio.c#L261).
|
||||
|
||||
# Contributing
|
||||
|
||||
Contributions are always welcome. Be aware that adding public functions will require good justification and breaking
|
||||
changes will likely not be accepted. If in doubt open an issue before writing the PR.
|
||||
122
vendor/github.com/klauspost/compress/fse/bitreader.go
generated
vendored
122
vendor/github.com/klauspost/compress/fse/bitreader.go
generated
vendored
@ -1,122 +0,0 @@
|
||||
// Copyright 2018 Klaus Post. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
// Based on work Copyright (c) 2013, Yann Collet, released under BSD License.
|
||||
|
||||
package fse
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
"io"
|
||||
)
|
||||
|
||||
// bitReader reads a bitstream in reverse.
|
||||
// The last set bit indicates the start of the stream and is used
|
||||
// for aligning the input.
|
||||
type bitReader struct {
|
||||
in []byte
|
||||
off uint // next byte to read is at in[off - 1]
|
||||
value uint64
|
||||
bitsRead uint8
|
||||
}
|
||||
|
||||
// init initializes and resets the bit reader.
|
||||
func (b *bitReader) init(in []byte) error {
|
||||
if len(in) < 1 {
|
||||
return errors.New("corrupt stream: too short")
|
||||
}
|
||||
b.in = in
|
||||
b.off = uint(len(in))
|
||||
// The highest bit of the last byte indicates where to start
|
||||
v := in[len(in)-1]
|
||||
if v == 0 {
|
||||
return errors.New("corrupt stream, did not find end of stream")
|
||||
}
|
||||
b.bitsRead = 64
|
||||
b.value = 0
|
||||
if len(in) >= 8 {
|
||||
b.fillFastStart()
|
||||
} else {
|
||||
b.fill()
|
||||
b.fill()
|
||||
}
|
||||
b.bitsRead += 8 - uint8(highBits(uint32(v)))
|
||||
return nil
|
||||
}
|
||||
|
||||
// getBits will return n bits. n can be 0.
|
||||
func (b *bitReader) getBits(n uint8) uint16 {
|
||||
if n == 0 || b.bitsRead >= 64 {
|
||||
return 0
|
||||
}
|
||||
return b.getBitsFast(n)
|
||||
}
|
||||
|
||||
// getBitsFast requires that at least one bit is requested every time.
|
||||
// There are no checks if the buffer is filled.
|
||||
func (b *bitReader) getBitsFast(n uint8) uint16 {
|
||||
const regMask = 64 - 1
|
||||
v := uint16((b.value << (b.bitsRead & regMask)) >> ((regMask + 1 - n) & regMask))
|
||||
b.bitsRead += n
|
||||
return v
|
||||
}
|
||||
|
||||
// fillFast() will make sure at least 32 bits are available.
|
||||
// There must be at least 4 bytes available.
|
||||
func (b *bitReader) fillFast() {
|
||||
if b.bitsRead < 32 {
|
||||
return
|
||||
}
|
||||
// 2 bounds checks.
|
||||
v := b.in[b.off-4:]
|
||||
v = v[:4]
|
||||
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
|
||||
b.value = (b.value << 32) | uint64(low)
|
||||
b.bitsRead -= 32
|
||||
b.off -= 4
|
||||
}
|
||||
|
||||
// fill() will make sure at least 32 bits are available.
|
||||
func (b *bitReader) fill() {
|
||||
if b.bitsRead < 32 {
|
||||
return
|
||||
}
|
||||
if b.off > 4 {
|
||||
v := b.in[b.off-4:]
|
||||
v = v[:4]
|
||||
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
|
||||
b.value = (b.value << 32) | uint64(low)
|
||||
b.bitsRead -= 32
|
||||
b.off -= 4
|
||||
return
|
||||
}
|
||||
for b.off > 0 {
|
||||
b.value = (b.value << 8) | uint64(b.in[b.off-1])
|
||||
b.bitsRead -= 8
|
||||
b.off--
|
||||
}
|
||||
}
|
||||
|
||||
// fillFastStart() assumes the bitreader is empty and there is at least 8 bytes to read.
|
||||
func (b *bitReader) fillFastStart() {
|
||||
// Do single re-slice to avoid bounds checks.
|
||||
b.value = binary.LittleEndian.Uint64(b.in[b.off-8:])
|
||||
b.bitsRead = 0
|
||||
b.off -= 8
|
||||
}
|
||||
|
||||
// finished returns true if all bits have been read from the bit stream.
|
||||
func (b *bitReader) finished() bool {
|
||||
return b.bitsRead >= 64 && b.off == 0
|
||||
}
|
||||
|
||||
// close the bitstream and returns an error if out-of-buffer reads occurred.
|
||||
func (b *bitReader) close() error {
|
||||
// Release reference.
|
||||
b.in = nil
|
||||
if b.bitsRead > 64 {
|
||||
return io.ErrUnexpectedEOF
|
||||
}
|
||||
return nil
|
||||
}
|
||||
167
vendor/github.com/klauspost/compress/fse/bitwriter.go
generated
vendored
167
vendor/github.com/klauspost/compress/fse/bitwriter.go
generated
vendored
@ -1,167 +0,0 @@
|
||||
// Copyright 2018 Klaus Post. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
// Based on work Copyright (c) 2013, Yann Collet, released under BSD License.
|
||||
|
||||
package fse
|
||||
|
||||
import "fmt"
|
||||
|
||||
// bitWriter will write bits.
|
||||
// First bit will be LSB of the first byte of output.
|
||||
type bitWriter struct {
|
||||
bitContainer uint64
|
||||
nBits uint8
|
||||
out []byte
|
||||
}
|
||||
|
||||
// bitMask16 is bitmasks. Has extra to avoid bounds check.
|
||||
var bitMask16 = [32]uint16{
|
||||
0, 1, 3, 7, 0xF, 0x1F,
|
||||
0x3F, 0x7F, 0xFF, 0x1FF, 0x3FF, 0x7FF,
|
||||
0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF, 0xFFFF,
|
||||
0xFFFF, 0xFFFF, 0xFFFF, 0xFFFF, 0xFFFF, 0xFFFF,
|
||||
0xFFFF, 0xFFFF} /* up to 16 bits */
|
||||
|
||||
// addBits16NC will add up to 16 bits.
|
||||
// It will not check if there is space for them,
|
||||
// so the caller must ensure that it has flushed recently.
|
||||
func (b *bitWriter) addBits16NC(value uint16, bits uint8) {
|
||||
b.bitContainer |= uint64(value&bitMask16[bits&31]) << (b.nBits & 63)
|
||||
b.nBits += bits
|
||||
}
|
||||
|
||||
// addBits16Clean will add up to 16 bits. value may not contain more set bits than indicated.
|
||||
// It will not check if there is space for them, so the caller must ensure that it has flushed recently.
|
||||
func (b *bitWriter) addBits16Clean(value uint16, bits uint8) {
|
||||
b.bitContainer |= uint64(value) << (b.nBits & 63)
|
||||
b.nBits += bits
|
||||
}
|
||||
|
||||
// addBits16ZeroNC will add up to 16 bits.
|
||||
// It will not check if there is space for them,
|
||||
// so the caller must ensure that it has flushed recently.
|
||||
// This is fastest if bits can be zero.
|
||||
func (b *bitWriter) addBits16ZeroNC(value uint16, bits uint8) {
|
||||
if bits == 0 {
|
||||
return
|
||||
}
|
||||
value <<= (16 - bits) & 15
|
||||
value >>= (16 - bits) & 15
|
||||
b.bitContainer |= uint64(value) << (b.nBits & 63)
|
||||
b.nBits += bits
|
||||
}
|
||||
|
||||
// flush will flush all pending full bytes.
|
||||
// There will be at least 56 bits available for writing when this has been called.
|
||||
// Using flush32 is faster, but leaves less space for writing.
|
||||
func (b *bitWriter) flush() {
|
||||
v := b.nBits >> 3
|
||||
switch v {
|
||||
case 0:
|
||||
case 1:
|
||||
b.out = append(b.out,
|
||||
byte(b.bitContainer),
|
||||
)
|
||||
case 2:
|
||||
b.out = append(b.out,
|
||||
byte(b.bitContainer),
|
||||
byte(b.bitContainer>>8),
|
||||
)
|
||||
case 3:
|
||||
b.out = append(b.out,
|
||||
byte(b.bitContainer),
|
||||
byte(b.bitContainer>>8),
|
||||
byte(b.bitContainer>>16),
|
||||
)
|
||||
case 4:
|
||||
b.out = append(b.out,
|
||||
byte(b.bitContainer),
|
||||
byte(b.bitContainer>>8),
|
||||
byte(b.bitContainer>>16),
|
||||
byte(b.bitContainer>>24),
|
||||
)
|
||||
case 5:
|
||||
b.out = append(b.out,
|
||||
byte(b.bitContainer),
|
||||
byte(b.bitContainer>>8),
|
||||
byte(b.bitContainer>>16),
|
||||
byte(b.bitContainer>>24),
|
||||
byte(b.bitContainer>>32),
|
||||
)
|
||||
case 6:
|
||||
b.out = append(b.out,
|
||||
byte(b.bitContainer),
|
||||
byte(b.bitContainer>>8),
|
||||
byte(b.bitContainer>>16),
|
||||
byte(b.bitContainer>>24),
|
||||
byte(b.bitContainer>>32),
|
||||
byte(b.bitContainer>>40),
|
||||
)
|
||||
case 7:
|
||||
b.out = append(b.out,
|
||||
byte(b.bitContainer),
|
||||
byte(b.bitContainer>>8),
|
||||
byte(b.bitContainer>>16),
|
||||
byte(b.bitContainer>>24),
|
||||
byte(b.bitContainer>>32),
|
||||
byte(b.bitContainer>>40),
|
||||
byte(b.bitContainer>>48),
|
||||
)
|
||||
case 8:
|
||||
b.out = append(b.out,
|
||||
byte(b.bitContainer),
|
||||
byte(b.bitContainer>>8),
|
||||
byte(b.bitContainer>>16),
|
||||
byte(b.bitContainer>>24),
|
||||
byte(b.bitContainer>>32),
|
||||
byte(b.bitContainer>>40),
|
||||
byte(b.bitContainer>>48),
|
||||
byte(b.bitContainer>>56),
|
||||
)
|
||||
default:
|
||||
panic(fmt.Errorf("bits (%d) > 64", b.nBits))
|
||||
}
|
||||
b.bitContainer >>= v << 3
|
||||
b.nBits &= 7
|
||||
}
|
||||
|
||||
// flush32 will flush out, so there are at least 32 bits available for writing.
|
||||
func (b *bitWriter) flush32() {
|
||||
if b.nBits < 32 {
|
||||
return
|
||||
}
|
||||
b.out = append(b.out,
|
||||
byte(b.bitContainer),
|
||||
byte(b.bitContainer>>8),
|
||||
byte(b.bitContainer>>16),
|
||||
byte(b.bitContainer>>24))
|
||||
b.nBits -= 32
|
||||
b.bitContainer >>= 32
|
||||
}
|
||||
|
||||
// flushAlign will flush remaining full bytes and align to next byte boundary.
|
||||
func (b *bitWriter) flushAlign() {
|
||||
nbBytes := (b.nBits + 7) >> 3
|
||||
for i := uint8(0); i < nbBytes; i++ {
|
||||
b.out = append(b.out, byte(b.bitContainer>>(i*8)))
|
||||
}
|
||||
b.nBits = 0
|
||||
b.bitContainer = 0
|
||||
}
|
||||
|
||||
// close will write the alignment bit and write the final byte(s)
|
||||
// to the output.
|
||||
func (b *bitWriter) close() {
|
||||
// End mark
|
||||
b.addBits16Clean(1, 1)
|
||||
// flush until next byte.
|
||||
b.flushAlign()
|
||||
}
|
||||
|
||||
// reset and continue writing by appending to out.
|
||||
func (b *bitWriter) reset(out []byte) {
|
||||
b.bitContainer = 0
|
||||
b.nBits = 0
|
||||
b.out = out
|
||||
}
|
||||
47
vendor/github.com/klauspost/compress/fse/bytereader.go
generated
vendored
47
vendor/github.com/klauspost/compress/fse/bytereader.go
generated
vendored
@ -1,47 +0,0 @@
|
||||
// Copyright 2018 Klaus Post. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
// Based on work Copyright (c) 2013, Yann Collet, released under BSD License.
|
||||
|
||||
package fse
|
||||
|
||||
// byteReader provides a byte reader that reads
|
||||
// little endian values from a byte stream.
|
||||
// The input stream is manually advanced.
|
||||
// The reader performs no bounds checks.
|
||||
type byteReader struct {
|
||||
b []byte
|
||||
off int
|
||||
}
|
||||
|
||||
// init will initialize the reader and set the input.
|
||||
func (b *byteReader) init(in []byte) {
|
||||
b.b = in
|
||||
b.off = 0
|
||||
}
|
||||
|
||||
// advance the stream b n bytes.
|
||||
func (b *byteReader) advance(n uint) {
|
||||
b.off += int(n)
|
||||
}
|
||||
|
||||
// Uint32 returns a little endian uint32 starting at current offset.
|
||||
func (b byteReader) Uint32() uint32 {
|
||||
b2 := b.b[b.off:]
|
||||
b2 = b2[:4]
|
||||
v3 := uint32(b2[3])
|
||||
v2 := uint32(b2[2])
|
||||
v1 := uint32(b2[1])
|
||||
v0 := uint32(b2[0])
|
||||
return v0 | (v1 << 8) | (v2 << 16) | (v3 << 24)
|
||||
}
|
||||
|
||||
// unread returns the unread portion of the input.
|
||||
func (b byteReader) unread() []byte {
|
||||
return b.b[b.off:]
|
||||
}
|
||||
|
||||
// remain will return the number of bytes remaining.
|
||||
func (b byteReader) remain() int {
|
||||
return len(b.b) - b.off
|
||||
}
|
||||
683
vendor/github.com/klauspost/compress/fse/compress.go
generated
vendored
683
vendor/github.com/klauspost/compress/fse/compress.go
generated
vendored
@ -1,683 +0,0 @@
|
||||
// Copyright 2018 Klaus Post. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
// Based on work Copyright (c) 2013, Yann Collet, released under BSD License.
|
||||
|
||||
package fse
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
)
|
||||
|
||||
// Compress the input bytes. Input must be < 2GB.
|
||||
// Provide a Scratch buffer to avoid memory allocations.
|
||||
// Note that the output is also kept in the scratch buffer.
|
||||
// If input is too hard to compress, ErrIncompressible is returned.
|
||||
// If input is a single byte value repeated ErrUseRLE is returned.
|
||||
func Compress(in []byte, s *Scratch) ([]byte, error) {
|
||||
if len(in) <= 1 {
|
||||
return nil, ErrIncompressible
|
||||
}
|
||||
if len(in) > (2<<30)-1 {
|
||||
return nil, errors.New("input too big, must be < 2GB")
|
||||
}
|
||||
s, err := s.prepare(in)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
// Create histogram, if none was provided.
|
||||
maxCount := s.maxCount
|
||||
if maxCount == 0 {
|
||||
maxCount = s.countSimple(in)
|
||||
}
|
||||
// Reset for next run.
|
||||
s.clearCount = true
|
||||
s.maxCount = 0
|
||||
if maxCount == len(in) {
|
||||
// One symbol, use RLE
|
||||
return nil, ErrUseRLE
|
||||
}
|
||||
if maxCount == 1 || maxCount < (len(in)>>7) {
|
||||
// Each symbol present maximum once or too well distributed.
|
||||
return nil, ErrIncompressible
|
||||
}
|
||||
s.optimalTableLog()
|
||||
err = s.normalizeCount()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
err = s.writeCount()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
if false {
|
||||
err = s.validateNorm()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
|
||||
err = s.buildCTable()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
err = s.compress(in)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
s.Out = s.bw.out
|
||||
// Check if we compressed.
|
||||
if len(s.Out) >= len(in) {
|
||||
return nil, ErrIncompressible
|
||||
}
|
||||
return s.Out, nil
|
||||
}
|
||||
|
||||
// cState contains the compression state of a stream.
|
||||
type cState struct {
|
||||
bw *bitWriter
|
||||
stateTable []uint16
|
||||
state uint16
|
||||
}
|
||||
|
||||
// init will initialize the compression state to the first symbol of the stream.
|
||||
func (c *cState) init(bw *bitWriter, ct *cTable, tableLog uint8, first symbolTransform) {
|
||||
c.bw = bw
|
||||
c.stateTable = ct.stateTable
|
||||
|
||||
nbBitsOut := (first.deltaNbBits + (1 << 15)) >> 16
|
||||
im := int32((nbBitsOut << 16) - first.deltaNbBits)
|
||||
lu := (im >> nbBitsOut) + first.deltaFindState
|
||||
c.state = c.stateTable[lu]
|
||||
}
|
||||
|
||||
// encode the output symbol provided and write it to the bitstream.
|
||||
func (c *cState) encode(symbolTT symbolTransform) {
|
||||
nbBitsOut := (uint32(c.state) + symbolTT.deltaNbBits) >> 16
|
||||
dstState := int32(c.state>>(nbBitsOut&15)) + symbolTT.deltaFindState
|
||||
c.bw.addBits16NC(c.state, uint8(nbBitsOut))
|
||||
c.state = c.stateTable[dstState]
|
||||
}
|
||||
|
||||
// encode the output symbol provided and write it to the bitstream.
|
||||
func (c *cState) encodeZero(symbolTT symbolTransform) {
|
||||
nbBitsOut := (uint32(c.state) + symbolTT.deltaNbBits) >> 16
|
||||
dstState := int32(c.state>>(nbBitsOut&15)) + symbolTT.deltaFindState
|
||||
c.bw.addBits16ZeroNC(c.state, uint8(nbBitsOut))
|
||||
c.state = c.stateTable[dstState]
|
||||
}
|
||||
|
||||
// flush will write the tablelog to the output and flush the remaining full bytes.
|
||||
func (c *cState) flush(tableLog uint8) {
|
||||
c.bw.flush32()
|
||||
c.bw.addBits16NC(c.state, tableLog)
|
||||
c.bw.flush()
|
||||
}
|
||||
|
||||
// compress is the main compression loop that will encode the input from the last byte to the first.
|
||||
func (s *Scratch) compress(src []byte) error {
|
||||
if len(src) <= 2 {
|
||||
return errors.New("compress: src too small")
|
||||
}
|
||||
tt := s.ct.symbolTT[:256]
|
||||
s.bw.reset(s.Out)
|
||||
|
||||
// Our two states each encodes every second byte.
|
||||
// Last byte encoded (first byte decoded) will always be encoded by c1.
|
||||
var c1, c2 cState
|
||||
|
||||
// Encode so remaining size is divisible by 4.
|
||||
ip := len(src)
|
||||
if ip&1 == 1 {
|
||||
c1.init(&s.bw, &s.ct, s.actualTableLog, tt[src[ip-1]])
|
||||
c2.init(&s.bw, &s.ct, s.actualTableLog, tt[src[ip-2]])
|
||||
c1.encodeZero(tt[src[ip-3]])
|
||||
ip -= 3
|
||||
} else {
|
||||
c2.init(&s.bw, &s.ct, s.actualTableLog, tt[src[ip-1]])
|
||||
c1.init(&s.bw, &s.ct, s.actualTableLog, tt[src[ip-2]])
|
||||
ip -= 2
|
||||
}
|
||||
if ip&2 != 0 {
|
||||
c2.encodeZero(tt[src[ip-1]])
|
||||
c1.encodeZero(tt[src[ip-2]])
|
||||
ip -= 2
|
||||
}
|
||||
src = src[:ip]
|
||||
|
||||
// Main compression loop.
|
||||
switch {
|
||||
case !s.zeroBits && s.actualTableLog <= 8:
|
||||
// We can encode 4 symbols without requiring a flush.
|
||||
// We do not need to check if any output is 0 bits.
|
||||
for ; len(src) >= 4; src = src[:len(src)-4] {
|
||||
s.bw.flush32()
|
||||
v3, v2, v1, v0 := src[len(src)-4], src[len(src)-3], src[len(src)-2], src[len(src)-1]
|
||||
c2.encode(tt[v0])
|
||||
c1.encode(tt[v1])
|
||||
c2.encode(tt[v2])
|
||||
c1.encode(tt[v3])
|
||||
}
|
||||
case !s.zeroBits:
|
||||
// We do not need to check if any output is 0 bits.
|
||||
for ; len(src) >= 4; src = src[:len(src)-4] {
|
||||
s.bw.flush32()
|
||||
v3, v2, v1, v0 := src[len(src)-4], src[len(src)-3], src[len(src)-2], src[len(src)-1]
|
||||
c2.encode(tt[v0])
|
||||
c1.encode(tt[v1])
|
||||
s.bw.flush32()
|
||||
c2.encode(tt[v2])
|
||||
c1.encode(tt[v3])
|
||||
}
|
||||
case s.actualTableLog <= 8:
|
||||
// We can encode 4 symbols without requiring a flush
|
||||
for ; len(src) >= 4; src = src[:len(src)-4] {
|
||||
s.bw.flush32()
|
||||
v3, v2, v1, v0 := src[len(src)-4], src[len(src)-3], src[len(src)-2], src[len(src)-1]
|
||||
c2.encodeZero(tt[v0])
|
||||
c1.encodeZero(tt[v1])
|
||||
c2.encodeZero(tt[v2])
|
||||
c1.encodeZero(tt[v3])
|
||||
}
|
||||
default:
|
||||
for ; len(src) >= 4; src = src[:len(src)-4] {
|
||||
s.bw.flush32()
|
||||
v3, v2, v1, v0 := src[len(src)-4], src[len(src)-3], src[len(src)-2], src[len(src)-1]
|
||||
c2.encodeZero(tt[v0])
|
||||
c1.encodeZero(tt[v1])
|
||||
s.bw.flush32()
|
||||
c2.encodeZero(tt[v2])
|
||||
c1.encodeZero(tt[v3])
|
||||
}
|
||||
}
|
||||
|
||||
// Flush final state.
|
||||
// Used to initialize state when decoding.
|
||||
c2.flush(s.actualTableLog)
|
||||
c1.flush(s.actualTableLog)
|
||||
|
||||
s.bw.close()
|
||||
return nil
|
||||
}
|
||||
|
||||
// writeCount will write the normalized histogram count to header.
|
||||
// This is read back by readNCount.
|
||||
func (s *Scratch) writeCount() error {
|
||||
var (
|
||||
tableLog = s.actualTableLog
|
||||
tableSize = 1 << tableLog
|
||||
previous0 bool
|
||||
charnum uint16
|
||||
|
||||
maxHeaderSize = ((int(s.symbolLen)*int(tableLog) + 4 + 2) >> 3) + 3
|
||||
|
||||
// Write Table Size
|
||||
bitStream = uint32(tableLog - minTablelog)
|
||||
bitCount = uint(4)
|
||||
remaining = int16(tableSize + 1) /* +1 for extra accuracy */
|
||||
threshold = int16(tableSize)
|
||||
nbBits = uint(tableLog + 1)
|
||||
)
|
||||
if cap(s.Out) < maxHeaderSize {
|
||||
s.Out = make([]byte, 0, s.br.remain()+maxHeaderSize)
|
||||
}
|
||||
outP := uint(0)
|
||||
out := s.Out[:maxHeaderSize]
|
||||
|
||||
// stops at 1
|
||||
for remaining > 1 {
|
||||
if previous0 {
|
||||
start := charnum
|
||||
for s.norm[charnum] == 0 {
|
||||
charnum++
|
||||
}
|
||||
for charnum >= start+24 {
|
||||
start += 24
|
||||
bitStream += uint32(0xFFFF) << bitCount
|
||||
out[outP] = byte(bitStream)
|
||||
out[outP+1] = byte(bitStream >> 8)
|
||||
outP += 2
|
||||
bitStream >>= 16
|
||||
}
|
||||
for charnum >= start+3 {
|
||||
start += 3
|
||||
bitStream += 3 << bitCount
|
||||
bitCount += 2
|
||||
}
|
||||
bitStream += uint32(charnum-start) << bitCount
|
||||
bitCount += 2
|
||||
if bitCount > 16 {
|
||||
out[outP] = byte(bitStream)
|
||||
out[outP+1] = byte(bitStream >> 8)
|
||||
outP += 2
|
||||
bitStream >>= 16
|
||||
bitCount -= 16
|
||||
}
|
||||
}
|
||||
|
||||
count := s.norm[charnum]
|
||||
charnum++
|
||||
max := (2*threshold - 1) - remaining
|
||||
if count < 0 {
|
||||
remaining += count
|
||||
} else {
|
||||
remaining -= count
|
||||
}
|
||||
count++ // +1 for extra accuracy
|
||||
if count >= threshold {
|
||||
count += max // [0..max[ [max..threshold[ (...) [threshold+max 2*threshold[
|
||||
}
|
||||
bitStream += uint32(count) << bitCount
|
||||
bitCount += nbBits
|
||||
if count < max {
|
||||
bitCount--
|
||||
}
|
||||
|
||||
previous0 = count == 1
|
||||
if remaining < 1 {
|
||||
return errors.New("internal error: remaining<1")
|
||||
}
|
||||
for remaining < threshold {
|
||||
nbBits--
|
||||
threshold >>= 1
|
||||
}
|
||||
|
||||
if bitCount > 16 {
|
||||
out[outP] = byte(bitStream)
|
||||
out[outP+1] = byte(bitStream >> 8)
|
||||
outP += 2
|
||||
bitStream >>= 16
|
||||
bitCount -= 16
|
||||
}
|
||||
}
|
||||
|
||||
out[outP] = byte(bitStream)
|
||||
out[outP+1] = byte(bitStream >> 8)
|
||||
outP += (bitCount + 7) / 8
|
||||
|
||||
if charnum > s.symbolLen {
|
||||
return errors.New("internal error: charnum > s.symbolLen")
|
||||
}
|
||||
s.Out = out[:outP]
|
||||
return nil
|
||||
}
|
||||
|
||||
// symbolTransform contains the state transform for a symbol.
|
||||
type symbolTransform struct {
|
||||
deltaFindState int32
|
||||
deltaNbBits uint32
|
||||
}
|
||||
|
||||
// String prints values as a human readable string.
|
||||
func (s symbolTransform) String() string {
|
||||
return fmt.Sprintf("dnbits: %08x, fs:%d", s.deltaNbBits, s.deltaFindState)
|
||||
}
|
||||
|
||||
// cTable contains tables used for compression.
|
||||
type cTable struct {
|
||||
tableSymbol []byte
|
||||
stateTable []uint16
|
||||
symbolTT []symbolTransform
|
||||
}
|
||||
|
||||
// allocCtable will allocate tables needed for compression.
|
||||
// If existing tables a re big enough, they are simply re-used.
|
||||
func (s *Scratch) allocCtable() {
|
||||
tableSize := 1 << s.actualTableLog
|
||||
// get tableSymbol that is big enough.
|
||||
if cap(s.ct.tableSymbol) < tableSize {
|
||||
s.ct.tableSymbol = make([]byte, tableSize)
|
||||
}
|
||||
s.ct.tableSymbol = s.ct.tableSymbol[:tableSize]
|
||||
|
||||
ctSize := tableSize
|
||||
if cap(s.ct.stateTable) < ctSize {
|
||||
s.ct.stateTable = make([]uint16, ctSize)
|
||||
}
|
||||
s.ct.stateTable = s.ct.stateTable[:ctSize]
|
||||
|
||||
if cap(s.ct.symbolTT) < 256 {
|
||||
s.ct.symbolTT = make([]symbolTransform, 256)
|
||||
}
|
||||
s.ct.symbolTT = s.ct.symbolTT[:256]
|
||||
}
|
||||
|
||||
// buildCTable will populate the compression table so it is ready to be used.
|
||||
func (s *Scratch) buildCTable() error {
|
||||
tableSize := uint32(1 << s.actualTableLog)
|
||||
highThreshold := tableSize - 1
|
||||
var cumul [maxSymbolValue + 2]int16
|
||||
|
||||
s.allocCtable()
|
||||
tableSymbol := s.ct.tableSymbol[:tableSize]
|
||||
// symbol start positions
|
||||
{
|
||||
cumul[0] = 0
|
||||
for ui, v := range s.norm[:s.symbolLen-1] {
|
||||
u := byte(ui) // one less than reference
|
||||
if v == -1 {
|
||||
// Low proba symbol
|
||||
cumul[u+1] = cumul[u] + 1
|
||||
tableSymbol[highThreshold] = u
|
||||
highThreshold--
|
||||
} else {
|
||||
cumul[u+1] = cumul[u] + v
|
||||
}
|
||||
}
|
||||
// Encode last symbol separately to avoid overflowing u
|
||||
u := int(s.symbolLen - 1)
|
||||
v := s.norm[s.symbolLen-1]
|
||||
if v == -1 {
|
||||
// Low proba symbol
|
||||
cumul[u+1] = cumul[u] + 1
|
||||
tableSymbol[highThreshold] = byte(u)
|
||||
highThreshold--
|
||||
} else {
|
||||
cumul[u+1] = cumul[u] + v
|
||||
}
|
||||
if uint32(cumul[s.symbolLen]) != tableSize {
|
||||
return fmt.Errorf("internal error: expected cumul[s.symbolLen] (%d) == tableSize (%d)", cumul[s.symbolLen], tableSize)
|
||||
}
|
||||
cumul[s.symbolLen] = int16(tableSize) + 1
|
||||
}
|
||||
// Spread symbols
|
||||
s.zeroBits = false
|
||||
{
|
||||
step := tableStep(tableSize)
|
||||
tableMask := tableSize - 1
|
||||
var position uint32
|
||||
// if any symbol > largeLimit, we may have 0 bits output.
|
||||
largeLimit := int16(1 << (s.actualTableLog - 1))
|
||||
for ui, v := range s.norm[:s.symbolLen] {
|
||||
symbol := byte(ui)
|
||||
if v > largeLimit {
|
||||
s.zeroBits = true
|
||||
}
|
||||
for nbOccurrences := int16(0); nbOccurrences < v; nbOccurrences++ {
|
||||
tableSymbol[position] = symbol
|
||||
position = (position + step) & tableMask
|
||||
for position > highThreshold {
|
||||
position = (position + step) & tableMask
|
||||
} /* Low proba area */
|
||||
}
|
||||
}
|
||||
|
||||
// Check if we have gone through all positions
|
||||
if position != 0 {
|
||||
return errors.New("position!=0")
|
||||
}
|
||||
}
|
||||
|
||||
// Build table
|
||||
table := s.ct.stateTable
|
||||
{
|
||||
tsi := int(tableSize)
|
||||
for u, v := range tableSymbol {
|
||||
// TableU16 : sorted by symbol order; gives next state value
|
||||
table[cumul[v]] = uint16(tsi + u)
|
||||
cumul[v]++
|
||||
}
|
||||
}
|
||||
|
||||
// Build Symbol Transformation Table
|
||||
{
|
||||
total := int16(0)
|
||||
symbolTT := s.ct.symbolTT[:s.symbolLen]
|
||||
tableLog := s.actualTableLog
|
||||
tl := (uint32(tableLog) << 16) - (1 << tableLog)
|
||||
for i, v := range s.norm[:s.symbolLen] {
|
||||
switch v {
|
||||
case 0:
|
||||
case -1, 1:
|
||||
symbolTT[i].deltaNbBits = tl
|
||||
symbolTT[i].deltaFindState = int32(total - 1)
|
||||
total++
|
||||
default:
|
||||
maxBitsOut := uint32(tableLog) - highBits(uint32(v-1))
|
||||
minStatePlus := uint32(v) << maxBitsOut
|
||||
symbolTT[i].deltaNbBits = (maxBitsOut << 16) - minStatePlus
|
||||
symbolTT[i].deltaFindState = int32(total - v)
|
||||
total += v
|
||||
}
|
||||
}
|
||||
if total != int16(tableSize) {
|
||||
return fmt.Errorf("total mismatch %d (got) != %d (want)", total, tableSize)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// countSimple will create a simple histogram in s.count.
|
||||
// Returns the biggest count.
|
||||
// Does not update s.clearCount.
|
||||
func (s *Scratch) countSimple(in []byte) (max int) {
|
||||
for _, v := range in {
|
||||
s.count[v]++
|
||||
}
|
||||
m, symlen := uint32(0), s.symbolLen
|
||||
for i, v := range s.count[:] {
|
||||
if v == 0 {
|
||||
continue
|
||||
}
|
||||
if v > m {
|
||||
m = v
|
||||
}
|
||||
symlen = uint16(i) + 1
|
||||
}
|
||||
s.symbolLen = symlen
|
||||
return int(m)
|
||||
}
|
||||
|
||||
// minTableLog provides the minimum logSize to safely represent a distribution.
|
||||
func (s *Scratch) minTableLog() uint8 {
|
||||
minBitsSrc := highBits(uint32(s.br.remain()-1)) + 1
|
||||
minBitsSymbols := highBits(uint32(s.symbolLen-1)) + 2
|
||||
if minBitsSrc < minBitsSymbols {
|
||||
return uint8(minBitsSrc)
|
||||
}
|
||||
return uint8(minBitsSymbols)
|
||||
}
|
||||
|
||||
// optimalTableLog calculates and sets the optimal tableLog in s.actualTableLog
|
||||
func (s *Scratch) optimalTableLog() {
|
||||
tableLog := s.TableLog
|
||||
minBits := s.minTableLog()
|
||||
maxBitsSrc := uint8(highBits(uint32(s.br.remain()-1))) - 2
|
||||
if maxBitsSrc < tableLog {
|
||||
// Accuracy can be reduced
|
||||
tableLog = maxBitsSrc
|
||||
}
|
||||
if minBits > tableLog {
|
||||
tableLog = minBits
|
||||
}
|
||||
// Need a minimum to safely represent all symbol values
|
||||
if tableLog < minTablelog {
|
||||
tableLog = minTablelog
|
||||
}
|
||||
if tableLog > maxTableLog {
|
||||
tableLog = maxTableLog
|
||||
}
|
||||
s.actualTableLog = tableLog
|
||||
}
|
||||
|
||||
var rtbTable = [...]uint32{0, 473195, 504333, 520860, 550000, 700000, 750000, 830000}
|
||||
|
||||
// normalizeCount will normalize the count of the symbols so
|
||||
// the total is equal to the table size.
|
||||
func (s *Scratch) normalizeCount() error {
|
||||
var (
|
||||
tableLog = s.actualTableLog
|
||||
scale = 62 - uint64(tableLog)
|
||||
step = (1 << 62) / uint64(s.br.remain())
|
||||
vStep = uint64(1) << (scale - 20)
|
||||
stillToDistribute = int16(1 << tableLog)
|
||||
largest int
|
||||
largestP int16
|
||||
lowThreshold = (uint32)(s.br.remain() >> tableLog)
|
||||
)
|
||||
|
||||
for i, cnt := range s.count[:s.symbolLen] {
|
||||
// already handled
|
||||
// if (count[s] == s.length) return 0; /* rle special case */
|
||||
|
||||
if cnt == 0 {
|
||||
s.norm[i] = 0
|
||||
continue
|
||||
}
|
||||
if cnt <= lowThreshold {
|
||||
s.norm[i] = -1
|
||||
stillToDistribute--
|
||||
} else {
|
||||
proba := (int16)((uint64(cnt) * step) >> scale)
|
||||
if proba < 8 {
|
||||
restToBeat := vStep * uint64(rtbTable[proba])
|
||||
v := uint64(cnt)*step - (uint64(proba) << scale)
|
||||
if v > restToBeat {
|
||||
proba++
|
||||
}
|
||||
}
|
||||
if proba > largestP {
|
||||
largestP = proba
|
||||
largest = i
|
||||
}
|
||||
s.norm[i] = proba
|
||||
stillToDistribute -= proba
|
||||
}
|
||||
}
|
||||
|
||||
if -stillToDistribute >= (s.norm[largest] >> 1) {
|
||||
// corner case, need another normalization method
|
||||
return s.normalizeCount2()
|
||||
}
|
||||
s.norm[largest] += stillToDistribute
|
||||
return nil
|
||||
}
|
||||
|
||||
// Secondary normalization method.
|
||||
// To be used when primary method fails.
|
||||
func (s *Scratch) normalizeCount2() error {
|
||||
const notYetAssigned = -2
|
||||
var (
|
||||
distributed uint32
|
||||
total = uint32(s.br.remain())
|
||||
tableLog = s.actualTableLog
|
||||
lowThreshold = total >> tableLog
|
||||
lowOne = (total * 3) >> (tableLog + 1)
|
||||
)
|
||||
for i, cnt := range s.count[:s.symbolLen] {
|
||||
if cnt == 0 {
|
||||
s.norm[i] = 0
|
||||
continue
|
||||
}
|
||||
if cnt <= lowThreshold {
|
||||
s.norm[i] = -1
|
||||
distributed++
|
||||
total -= cnt
|
||||
continue
|
||||
}
|
||||
if cnt <= lowOne {
|
||||
s.norm[i] = 1
|
||||
distributed++
|
||||
total -= cnt
|
||||
continue
|
||||
}
|
||||
s.norm[i] = notYetAssigned
|
||||
}
|
||||
toDistribute := (1 << tableLog) - distributed
|
||||
|
||||
if (total / toDistribute) > lowOne {
|
||||
// risk of rounding to zero
|
||||
lowOne = (total * 3) / (toDistribute * 2)
|
||||
for i, cnt := range s.count[:s.symbolLen] {
|
||||
if (s.norm[i] == notYetAssigned) && (cnt <= lowOne) {
|
||||
s.norm[i] = 1
|
||||
distributed++
|
||||
total -= cnt
|
||||
continue
|
||||
}
|
||||
}
|
||||
toDistribute = (1 << tableLog) - distributed
|
||||
}
|
||||
if distributed == uint32(s.symbolLen)+1 {
|
||||
// all values are pretty poor;
|
||||
// probably incompressible data (should have already been detected);
|
||||
// find max, then give all remaining points to max
|
||||
var maxV int
|
||||
var maxC uint32
|
||||
for i, cnt := range s.count[:s.symbolLen] {
|
||||
if cnt > maxC {
|
||||
maxV = i
|
||||
maxC = cnt
|
||||
}
|
||||
}
|
||||
s.norm[maxV] += int16(toDistribute)
|
||||
return nil
|
||||
}
|
||||
|
||||
if total == 0 {
|
||||
// all of the symbols were low enough for the lowOne or lowThreshold
|
||||
for i := uint32(0); toDistribute > 0; i = (i + 1) % (uint32(s.symbolLen)) {
|
||||
if s.norm[i] > 0 {
|
||||
toDistribute--
|
||||
s.norm[i]++
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
var (
|
||||
vStepLog = 62 - uint64(tableLog)
|
||||
mid = uint64((1 << (vStepLog - 1)) - 1)
|
||||
rStep = (((1 << vStepLog) * uint64(toDistribute)) + mid) / uint64(total) // scale on remaining
|
||||
tmpTotal = mid
|
||||
)
|
||||
for i, cnt := range s.count[:s.symbolLen] {
|
||||
if s.norm[i] == notYetAssigned {
|
||||
var (
|
||||
end = tmpTotal + uint64(cnt)*rStep
|
||||
sStart = uint32(tmpTotal >> vStepLog)
|
||||
sEnd = uint32(end >> vStepLog)
|
||||
weight = sEnd - sStart
|
||||
)
|
||||
if weight < 1 {
|
||||
return errors.New("weight < 1")
|
||||
}
|
||||
s.norm[i] = int16(weight)
|
||||
tmpTotal = end
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// validateNorm validates the normalized histogram table.
|
||||
func (s *Scratch) validateNorm() (err error) {
|
||||
var total int
|
||||
for _, v := range s.norm[:s.symbolLen] {
|
||||
if v >= 0 {
|
||||
total += int(v)
|
||||
} else {
|
||||
total -= int(v)
|
||||
}
|
||||
}
|
||||
defer func() {
|
||||
if err == nil {
|
||||
return
|
||||
}
|
||||
fmt.Printf("selected TableLog: %d, Symbol length: %d\n", s.actualTableLog, s.symbolLen)
|
||||
for i, v := range s.norm[:s.symbolLen] {
|
||||
fmt.Printf("%3d: %5d -> %4d \n", i, s.count[i], v)
|
||||
}
|
||||
}()
|
||||
if total != (1 << s.actualTableLog) {
|
||||
return fmt.Errorf("warning: Total == %d != %d", total, 1<<s.actualTableLog)
|
||||
}
|
||||
for i, v := range s.count[s.symbolLen:] {
|
||||
if v != 0 {
|
||||
return fmt.Errorf("warning: Found symbol out of range, %d after cut", i)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
376
vendor/github.com/klauspost/compress/fse/decompress.go
generated
vendored
376
vendor/github.com/klauspost/compress/fse/decompress.go
generated
vendored
@ -1,376 +0,0 @@
|
||||
package fse
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
)
|
||||
|
||||
const (
|
||||
tablelogAbsoluteMax = 15
|
||||
)
|
||||
|
||||
// Decompress a block of data.
|
||||
// You can provide a scratch buffer to avoid allocations.
|
||||
// If nil is provided a temporary one will be allocated.
|
||||
// It is possible, but by no way guaranteed that corrupt data will
|
||||
// return an error.
|
||||
// It is up to the caller to verify integrity of the returned data.
|
||||
// Use a predefined Scratch to set maximum acceptable output size.
|
||||
func Decompress(b []byte, s *Scratch) ([]byte, error) {
|
||||
s, err := s.prepare(b)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
s.Out = s.Out[:0]
|
||||
err = s.readNCount()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
err = s.buildDtable()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
err = s.decompress()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
return s.Out, nil
|
||||
}
|
||||
|
||||
// readNCount will read the symbol distribution so decoding tables can be constructed.
|
||||
func (s *Scratch) readNCount() error {
|
||||
var (
|
||||
charnum uint16
|
||||
previous0 bool
|
||||
b = &s.br
|
||||
)
|
||||
iend := b.remain()
|
||||
if iend < 4 {
|
||||
return errors.New("input too small")
|
||||
}
|
||||
bitStream := b.Uint32()
|
||||
nbBits := uint((bitStream & 0xF) + minTablelog) // extract tableLog
|
||||
if nbBits > tablelogAbsoluteMax {
|
||||
return errors.New("tableLog too large")
|
||||
}
|
||||
bitStream >>= 4
|
||||
bitCount := uint(4)
|
||||
|
||||
s.actualTableLog = uint8(nbBits)
|
||||
remaining := int32((1 << nbBits) + 1)
|
||||
threshold := int32(1 << nbBits)
|
||||
gotTotal := int32(0)
|
||||
nbBits++
|
||||
|
||||
for remaining > 1 {
|
||||
if previous0 {
|
||||
n0 := charnum
|
||||
for (bitStream & 0xFFFF) == 0xFFFF {
|
||||
n0 += 24
|
||||
if b.off < iend-5 {
|
||||
b.advance(2)
|
||||
bitStream = b.Uint32() >> bitCount
|
||||
} else {
|
||||
bitStream >>= 16
|
||||
bitCount += 16
|
||||
}
|
||||
}
|
||||
for (bitStream & 3) == 3 {
|
||||
n0 += 3
|
||||
bitStream >>= 2
|
||||
bitCount += 2
|
||||
}
|
||||
n0 += uint16(bitStream & 3)
|
||||
bitCount += 2
|
||||
if n0 > maxSymbolValue {
|
||||
return errors.New("maxSymbolValue too small")
|
||||
}
|
||||
for charnum < n0 {
|
||||
s.norm[charnum&0xff] = 0
|
||||
charnum++
|
||||
}
|
||||
|
||||
if b.off <= iend-7 || b.off+int(bitCount>>3) <= iend-4 {
|
||||
b.advance(bitCount >> 3)
|
||||
bitCount &= 7
|
||||
bitStream = b.Uint32() >> bitCount
|
||||
} else {
|
||||
bitStream >>= 2
|
||||
}
|
||||
}
|
||||
|
||||
max := (2*(threshold) - 1) - (remaining)
|
||||
var count int32
|
||||
|
||||
if (int32(bitStream) & (threshold - 1)) < max {
|
||||
count = int32(bitStream) & (threshold - 1)
|
||||
bitCount += nbBits - 1
|
||||
} else {
|
||||
count = int32(bitStream) & (2*threshold - 1)
|
||||
if count >= threshold {
|
||||
count -= max
|
||||
}
|
||||
bitCount += nbBits
|
||||
}
|
||||
|
||||
count-- // extra accuracy
|
||||
if count < 0 {
|
||||
// -1 means +1
|
||||
remaining += count
|
||||
gotTotal -= count
|
||||
} else {
|
||||
remaining -= count
|
||||
gotTotal += count
|
||||
}
|
||||
s.norm[charnum&0xff] = int16(count)
|
||||
charnum++
|
||||
previous0 = count == 0
|
||||
for remaining < threshold {
|
||||
nbBits--
|
||||
threshold >>= 1
|
||||
}
|
||||
if b.off <= iend-7 || b.off+int(bitCount>>3) <= iend-4 {
|
||||
b.advance(bitCount >> 3)
|
||||
bitCount &= 7
|
||||
} else {
|
||||
bitCount -= (uint)(8 * (len(b.b) - 4 - b.off))
|
||||
b.off = len(b.b) - 4
|
||||
}
|
||||
bitStream = b.Uint32() >> (bitCount & 31)
|
||||
}
|
||||
s.symbolLen = charnum
|
||||
|
||||
if s.symbolLen <= 1 {
|
||||
return fmt.Errorf("symbolLen (%d) too small", s.symbolLen)
|
||||
}
|
||||
if s.symbolLen > maxSymbolValue+1 {
|
||||
return fmt.Errorf("symbolLen (%d) too big", s.symbolLen)
|
||||
}
|
||||
if remaining != 1 {
|
||||
return fmt.Errorf("corruption detected (remaining %d != 1)", remaining)
|
||||
}
|
||||
if bitCount > 32 {
|
||||
return fmt.Errorf("corruption detected (bitCount %d > 32)", bitCount)
|
||||
}
|
||||
if gotTotal != 1<<s.actualTableLog {
|
||||
return fmt.Errorf("corruption detected (total %d != %d)", gotTotal, 1<<s.actualTableLog)
|
||||
}
|
||||
b.advance((bitCount + 7) >> 3)
|
||||
return nil
|
||||
}
|
||||
|
||||
// decSymbol contains information about a state entry,
|
||||
// Including the state offset base, the output symbol and
|
||||
// the number of bits to read for the low part of the destination state.
|
||||
type decSymbol struct {
|
||||
newState uint16
|
||||
symbol uint8
|
||||
nbBits uint8
|
||||
}
|
||||
|
||||
// allocDtable will allocate decoding tables if they are not big enough.
|
||||
func (s *Scratch) allocDtable() {
|
||||
tableSize := 1 << s.actualTableLog
|
||||
if cap(s.decTable) < tableSize {
|
||||
s.decTable = make([]decSymbol, tableSize)
|
||||
}
|
||||
s.decTable = s.decTable[:tableSize]
|
||||
|
||||
if cap(s.ct.tableSymbol) < 256 {
|
||||
s.ct.tableSymbol = make([]byte, 256)
|
||||
}
|
||||
s.ct.tableSymbol = s.ct.tableSymbol[:256]
|
||||
|
||||
if cap(s.ct.stateTable) < 256 {
|
||||
s.ct.stateTable = make([]uint16, 256)
|
||||
}
|
||||
s.ct.stateTable = s.ct.stateTable[:256]
|
||||
}
|
||||
|
||||
// buildDtable will build the decoding table.
|
||||
func (s *Scratch) buildDtable() error {
|
||||
tableSize := uint32(1 << s.actualTableLog)
|
||||
highThreshold := tableSize - 1
|
||||
s.allocDtable()
|
||||
symbolNext := s.ct.stateTable[:256]
|
||||
|
||||
// Init, lay down lowprob symbols
|
||||
s.zeroBits = false
|
||||
{
|
||||
largeLimit := int16(1 << (s.actualTableLog - 1))
|
||||
for i, v := range s.norm[:s.symbolLen] {
|
||||
if v == -1 {
|
||||
s.decTable[highThreshold].symbol = uint8(i)
|
||||
highThreshold--
|
||||
symbolNext[i] = 1
|
||||
} else {
|
||||
if v >= largeLimit {
|
||||
s.zeroBits = true
|
||||
}
|
||||
symbolNext[i] = uint16(v)
|
||||
}
|
||||
}
|
||||
}
|
||||
// Spread symbols
|
||||
{
|
||||
tableMask := tableSize - 1
|
||||
step := tableStep(tableSize)
|
||||
position := uint32(0)
|
||||
for ss, v := range s.norm[:s.symbolLen] {
|
||||
for i := 0; i < int(v); i++ {
|
||||
s.decTable[position].symbol = uint8(ss)
|
||||
position = (position + step) & tableMask
|
||||
for position > highThreshold {
|
||||
// lowprob area
|
||||
position = (position + step) & tableMask
|
||||
}
|
||||
}
|
||||
}
|
||||
if position != 0 {
|
||||
// position must reach all cells once, otherwise normalizedCounter is incorrect
|
||||
return errors.New("corrupted input (position != 0)")
|
||||
}
|
||||
}
|
||||
|
||||
// Build Decoding table
|
||||
{
|
||||
tableSize := uint16(1 << s.actualTableLog)
|
||||
for u, v := range s.decTable {
|
||||
symbol := v.symbol
|
||||
nextState := symbolNext[symbol]
|
||||
symbolNext[symbol] = nextState + 1
|
||||
nBits := s.actualTableLog - byte(highBits(uint32(nextState)))
|
||||
s.decTable[u].nbBits = nBits
|
||||
newState := (nextState << nBits) - tableSize
|
||||
if newState >= tableSize {
|
||||
return fmt.Errorf("newState (%d) outside table size (%d)", newState, tableSize)
|
||||
}
|
||||
if newState == uint16(u) && nBits == 0 {
|
||||
// Seems weird that this is possible with nbits > 0.
|
||||
return fmt.Errorf("newState (%d) == oldState (%d) and no bits", newState, u)
|
||||
}
|
||||
s.decTable[u].newState = newState
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// decompress will decompress the bitstream.
|
||||
// If the buffer is over-read an error is returned.
|
||||
func (s *Scratch) decompress() error {
|
||||
br := &s.bits
|
||||
if err := br.init(s.br.unread()); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
var s1, s2 decoder
|
||||
// Initialize and decode first state and symbol.
|
||||
s1.init(br, s.decTable, s.actualTableLog)
|
||||
s2.init(br, s.decTable, s.actualTableLog)
|
||||
|
||||
// Use temp table to avoid bound checks/append penalty.
|
||||
var tmp = s.ct.tableSymbol[:256]
|
||||
var off uint8
|
||||
|
||||
// Main part
|
||||
if !s.zeroBits {
|
||||
for br.off >= 8 {
|
||||
br.fillFast()
|
||||
tmp[off+0] = s1.nextFast()
|
||||
tmp[off+1] = s2.nextFast()
|
||||
br.fillFast()
|
||||
tmp[off+2] = s1.nextFast()
|
||||
tmp[off+3] = s2.nextFast()
|
||||
off += 4
|
||||
// When off is 0, we have overflowed and should write.
|
||||
if off == 0 {
|
||||
s.Out = append(s.Out, tmp...)
|
||||
if len(s.Out) >= s.DecompressLimit {
|
||||
return fmt.Errorf("output size (%d) > DecompressLimit (%d)", len(s.Out), s.DecompressLimit)
|
||||
}
|
||||
}
|
||||
}
|
||||
} else {
|
||||
for br.off >= 8 {
|
||||
br.fillFast()
|
||||
tmp[off+0] = s1.next()
|
||||
tmp[off+1] = s2.next()
|
||||
br.fillFast()
|
||||
tmp[off+2] = s1.next()
|
||||
tmp[off+3] = s2.next()
|
||||
off += 4
|
||||
if off == 0 {
|
||||
s.Out = append(s.Out, tmp...)
|
||||
// When off is 0, we have overflowed and should write.
|
||||
if len(s.Out) >= s.DecompressLimit {
|
||||
return fmt.Errorf("output size (%d) > DecompressLimit (%d)", len(s.Out), s.DecompressLimit)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
s.Out = append(s.Out, tmp[:off]...)
|
||||
|
||||
// Final bits, a bit more expensive check
|
||||
for {
|
||||
if s1.finished() {
|
||||
s.Out = append(s.Out, s1.final(), s2.final())
|
||||
break
|
||||
}
|
||||
br.fill()
|
||||
s.Out = append(s.Out, s1.next())
|
||||
if s2.finished() {
|
||||
s.Out = append(s.Out, s2.final(), s1.final())
|
||||
break
|
||||
}
|
||||
s.Out = append(s.Out, s2.next())
|
||||
if len(s.Out) >= s.DecompressLimit {
|
||||
return fmt.Errorf("output size (%d) > DecompressLimit (%d)", len(s.Out), s.DecompressLimit)
|
||||
}
|
||||
}
|
||||
return br.close()
|
||||
}
|
||||
|
||||
// decoder keeps track of the current state and updates it from the bitstream.
|
||||
type decoder struct {
|
||||
state uint16
|
||||
br *bitReader
|
||||
dt []decSymbol
|
||||
}
|
||||
|
||||
// init will initialize the decoder and read the first state from the stream.
|
||||
func (d *decoder) init(in *bitReader, dt []decSymbol, tableLog uint8) {
|
||||
d.dt = dt
|
||||
d.br = in
|
||||
d.state = in.getBits(tableLog)
|
||||
}
|
||||
|
||||
// next returns the next symbol and sets the next state.
|
||||
// At least tablelog bits must be available in the bit reader.
|
||||
func (d *decoder) next() uint8 {
|
||||
n := &d.dt[d.state]
|
||||
lowBits := d.br.getBits(n.nbBits)
|
||||
d.state = n.newState + lowBits
|
||||
return n.symbol
|
||||
}
|
||||
|
||||
// finished returns true if all bits have been read from the bitstream
|
||||
// and the next state would require reading bits from the input.
|
||||
func (d *decoder) finished() bool {
|
||||
return d.br.finished() && d.dt[d.state].nbBits > 0
|
||||
}
|
||||
|
||||
// final returns the current state symbol without decoding the next.
|
||||
func (d *decoder) final() uint8 {
|
||||
return d.dt[d.state].symbol
|
||||
}
|
||||
|
||||
// nextFast returns the next symbol and sets the next state.
|
||||
// This can only be used if no symbols are 0 bits.
|
||||
// At least tablelog bits must be available in the bit reader.
|
||||
func (d *decoder) nextFast() uint8 {
|
||||
n := d.dt[d.state]
|
||||
lowBits := d.br.getBitsFast(n.nbBits)
|
||||
d.state = n.newState + lowBits
|
||||
return n.symbol
|
||||
}
|
||||
144
vendor/github.com/klauspost/compress/fse/fse.go
generated
vendored
144
vendor/github.com/klauspost/compress/fse/fse.go
generated
vendored
@ -1,144 +0,0 @@
|
||||
// Copyright 2018 Klaus Post. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
// Based on work Copyright (c) 2013, Yann Collet, released under BSD License.
|
||||
|
||||
// Package fse provides Finite State Entropy encoding and decoding.
|
||||
//
|
||||
// Finite State Entropy encoding provides a fast near-optimal symbol encoding/decoding
|
||||
// for byte blocks as implemented in zstd.
|
||||
//
|
||||
// See https://github.com/klauspost/compress/tree/master/fse for more information.
|
||||
package fse
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"math/bits"
|
||||
)
|
||||
|
||||
const (
|
||||
/*!MEMORY_USAGE :
|
||||
* Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
|
||||
* Increasing memory usage improves compression ratio
|
||||
* Reduced memory usage can improve speed, due to cache effect
|
||||
* Recommended max value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */
|
||||
maxMemoryUsage = 14
|
||||
defaultMemoryUsage = 13
|
||||
|
||||
maxTableLog = maxMemoryUsage - 2
|
||||
maxTablesize = 1 << maxTableLog
|
||||
defaultTablelog = defaultMemoryUsage - 2
|
||||
minTablelog = 5
|
||||
maxSymbolValue = 255
|
||||
)
|
||||
|
||||
var (
|
||||
// ErrIncompressible is returned when input is judged to be too hard to compress.
|
||||
ErrIncompressible = errors.New("input is not compressible")
|
||||
|
||||
// ErrUseRLE is returned from the compressor when the input is a single byte value repeated.
|
||||
ErrUseRLE = errors.New("input is single value repeated")
|
||||
)
|
||||
|
||||
// Scratch provides temporary storage for compression and decompression.
|
||||
type Scratch struct {
|
||||
// Private
|
||||
count [maxSymbolValue + 1]uint32
|
||||
norm [maxSymbolValue + 1]int16
|
||||
br byteReader
|
||||
bits bitReader
|
||||
bw bitWriter
|
||||
ct cTable // Compression tables.
|
||||
decTable []decSymbol // Decompression table.
|
||||
maxCount int // count of the most probable symbol
|
||||
|
||||
// Per block parameters.
|
||||
// These can be used to override compression parameters of the block.
|
||||
// Do not touch, unless you know what you are doing.
|
||||
|
||||
// Out is output buffer.
|
||||
// If the scratch is re-used before the caller is done processing the output,
|
||||
// set this field to nil.
|
||||
// Otherwise the output buffer will be re-used for next Compression/Decompression step
|
||||
// and allocation will be avoided.
|
||||
Out []byte
|
||||
|
||||
// DecompressLimit limits the maximum decoded size acceptable.
|
||||
// If > 0 decompression will stop when approximately this many bytes
|
||||
// has been decoded.
|
||||
// If 0, maximum size will be 2GB.
|
||||
DecompressLimit int
|
||||
|
||||
symbolLen uint16 // Length of active part of the symbol table.
|
||||
actualTableLog uint8 // Selected tablelog.
|
||||
zeroBits bool // no bits has prob > 50%.
|
||||
clearCount bool // clear count
|
||||
|
||||
// MaxSymbolValue will override the maximum symbol value of the next block.
|
||||
MaxSymbolValue uint8
|
||||
|
||||
// TableLog will attempt to override the tablelog for the next block.
|
||||
TableLog uint8
|
||||
}
|
||||
|
||||
// Histogram allows to populate the histogram and skip that step in the compression,
|
||||
// It otherwise allows to inspect the histogram when compression is done.
|
||||
// To indicate that you have populated the histogram call HistogramFinished
|
||||
// with the value of the highest populated symbol, as well as the number of entries
|
||||
// in the most populated entry. These are accepted at face value.
|
||||
// The returned slice will always be length 256.
|
||||
func (s *Scratch) Histogram() []uint32 {
|
||||
return s.count[:]
|
||||
}
|
||||
|
||||
// HistogramFinished can be called to indicate that the histogram has been populated.
|
||||
// maxSymbol is the index of the highest set symbol of the next data segment.
|
||||
// maxCount is the number of entries in the most populated entry.
|
||||
// These are accepted at face value.
|
||||
func (s *Scratch) HistogramFinished(maxSymbol uint8, maxCount int) {
|
||||
s.maxCount = maxCount
|
||||
s.symbolLen = uint16(maxSymbol) + 1
|
||||
s.clearCount = maxCount != 0
|
||||
}
|
||||
|
||||
// prepare will prepare and allocate scratch tables used for both compression and decompression.
|
||||
func (s *Scratch) prepare(in []byte) (*Scratch, error) {
|
||||
if s == nil {
|
||||
s = &Scratch{}
|
||||
}
|
||||
if s.MaxSymbolValue == 0 {
|
||||
s.MaxSymbolValue = 255
|
||||
}
|
||||
if s.TableLog == 0 {
|
||||
s.TableLog = defaultTablelog
|
||||
}
|
||||
if s.TableLog > maxTableLog {
|
||||
return nil, fmt.Errorf("tableLog (%d) > maxTableLog (%d)", s.TableLog, maxTableLog)
|
||||
}
|
||||
if cap(s.Out) == 0 {
|
||||
s.Out = make([]byte, 0, len(in))
|
||||
}
|
||||
if s.clearCount && s.maxCount == 0 {
|
||||
for i := range s.count {
|
||||
s.count[i] = 0
|
||||
}
|
||||
s.clearCount = false
|
||||
}
|
||||
s.br.init(in)
|
||||
if s.DecompressLimit == 0 {
|
||||
// Max size 2GB.
|
||||
s.DecompressLimit = (2 << 30) - 1
|
||||
}
|
||||
|
||||
return s, nil
|
||||
}
|
||||
|
||||
// tableStep returns the next table index.
|
||||
func tableStep(tableSize uint32) uint32 {
|
||||
return (tableSize >> 1) + (tableSize >> 3) + 3
|
||||
}
|
||||
|
||||
func highBits(val uint32) (n uint32) {
|
||||
return uint32(bits.Len32(val) - 1)
|
||||
}
|
||||
4
vendor/github.com/klauspost/compress/gen.sh
generated
vendored
4
vendor/github.com/klauspost/compress/gen.sh
generated
vendored
@ -1,4 +0,0 @@
|
||||
#!/bin/sh
|
||||
|
||||
cd s2/cmd/_s2sx/ || exit 1
|
||||
go generate .
|
||||
1
vendor/github.com/klauspost/compress/huff0/.gitignore
generated
vendored
1
vendor/github.com/klauspost/compress/huff0/.gitignore
generated
vendored
@ -1 +0,0 @@
|
||||
/huff0-fuzz.zip
|
||||
89
vendor/github.com/klauspost/compress/huff0/README.md
generated
vendored
89
vendor/github.com/klauspost/compress/huff0/README.md
generated
vendored
@ -1,89 +0,0 @@
|
||||
# Huff0 entropy compression
|
||||
|
||||
This package provides Huff0 encoding and decoding as used in zstd.
|
||||
|
||||
[Huff0](https://github.com/Cyan4973/FiniteStateEntropy#new-generation-entropy-coders),
|
||||
a Huffman codec designed for modern CPU, featuring OoO (Out of Order) operations on multiple ALU
|
||||
(Arithmetic Logic Unit), achieving extremely fast compression and decompression speeds.
|
||||
|
||||
This can be used for compressing input with a lot of similar input values to the smallest number of bytes.
|
||||
This does not perform any multi-byte [dictionary coding](https://en.wikipedia.org/wiki/Dictionary_coder) as LZ coders,
|
||||
but it can be used as a secondary step to compressors (like Snappy) that does not do entropy encoding.
|
||||
|
||||
* [Godoc documentation](https://godoc.org/github.com/klauspost/compress/huff0)
|
||||
|
||||
## News
|
||||
|
||||
This is used as part of the [zstandard](https://github.com/klauspost/compress/tree/master/zstd#zstd) compression and decompression package.
|
||||
|
||||
This ensures that most functionality is well tested.
|
||||
|
||||
# Usage
|
||||
|
||||
This package provides a low level interface that allows to compress single independent blocks.
|
||||
|
||||
Each block is separate, and there is no built in integrity checks.
|
||||
This means that the caller should keep track of block sizes and also do checksums if needed.
|
||||
|
||||
Compressing a block is done via the [`Compress1X`](https://godoc.org/github.com/klauspost/compress/huff0#Compress1X) and
|
||||
[`Compress4X`](https://godoc.org/github.com/klauspost/compress/huff0#Compress4X) functions.
|
||||
You must provide input and will receive the output and maybe an error.
|
||||
|
||||
These error values can be returned:
|
||||
|
||||
| Error | Description |
|
||||
|---------------------|-----------------------------------------------------------------------------|
|
||||
| `<nil>` | Everything ok, output is returned |
|
||||
| `ErrIncompressible` | Returned when input is judged to be too hard to compress |
|
||||
| `ErrUseRLE` | Returned from the compressor when the input is a single byte value repeated |
|
||||
| `ErrTooBig` | Returned if the input block exceeds the maximum allowed size (128 Kib) |
|
||||
| `(error)` | An internal error occurred. |
|
||||
|
||||
|
||||
As can be seen above some of there are errors that will be returned even under normal operation so it is important to handle these.
|
||||
|
||||
To reduce allocations you can provide a [`Scratch`](https://godoc.org/github.com/klauspost/compress/huff0#Scratch) object
|
||||
that can be re-used for successive calls. Both compression and decompression accepts a `Scratch` object, and the same
|
||||
object can be used for both.
|
||||
|
||||
Be aware, that when re-using a `Scratch` object that the *output* buffer is also re-used, so if you are still using this
|
||||
you must set the `Out` field in the scratch to nil. The same buffer is used for compression and decompression output.
|
||||
|
||||
The `Scratch` object will retain state that allows to re-use previous tables for encoding and decoding.
|
||||
|
||||
## Tables and re-use
|
||||
|
||||
Huff0 allows for reusing tables from the previous block to save space if that is expected to give better/faster results.
|
||||
|
||||
The Scratch object allows you to set a [`ReusePolicy`](https://godoc.org/github.com/klauspost/compress/huff0#ReusePolicy)
|
||||
that controls this behaviour. See the documentation for details. This can be altered between each block.
|
||||
|
||||
Do however note that this information is *not* stored in the output block and it is up to the users of the package to
|
||||
record whether [`ReadTable`](https://godoc.org/github.com/klauspost/compress/huff0#ReadTable) should be called,
|
||||
based on the boolean reported back from the CompressXX call.
|
||||
|
||||
If you want to store the table separate from the data, you can access them as `OutData` and `OutTable` on the
|
||||
[`Scratch`](https://godoc.org/github.com/klauspost/compress/huff0#Scratch) object.
|
||||
|
||||
## Decompressing
|
||||
|
||||
The first part of decoding is to initialize the decoding table through [`ReadTable`](https://godoc.org/github.com/klauspost/compress/huff0#ReadTable).
|
||||
This will initialize the decoding tables.
|
||||
You can supply the complete block to `ReadTable` and it will return the data part of the block
|
||||
which can be given to the decompressor.
|
||||
|
||||
Decompressing is done by calling the [`Decompress1X`](https://godoc.org/github.com/klauspost/compress/huff0#Scratch.Decompress1X)
|
||||
or [`Decompress4X`](https://godoc.org/github.com/klauspost/compress/huff0#Scratch.Decompress4X) function.
|
||||
|
||||
For concurrently decompressing content with a fixed table a stateless [`Decoder`](https://godoc.org/github.com/klauspost/compress/huff0#Decoder) can be requested which will remain correct as long as the scratch is unchanged. The capacity of the provided slice indicates the expected output size.
|
||||
|
||||
You must provide the output from the compression stage, at exactly the size you got back. If you receive an error back
|
||||
your input was likely corrupted.
|
||||
|
||||
It is important to note that a successful decoding does *not* mean your output matches your original input.
|
||||
There are no integrity checks, so relying on errors from the decompressor does not assure your data is valid.
|
||||
|
||||
# Contributing
|
||||
|
||||
Contributions are always welcome. Be aware that adding public functions will require good justification and breaking
|
||||
changes will likely not be accepted. If in doubt open an issue before writing the PR.
|
||||
229
vendor/github.com/klauspost/compress/huff0/bitreader.go
generated
vendored
229
vendor/github.com/klauspost/compress/huff0/bitreader.go
generated
vendored
@ -1,229 +0,0 @@
|
||||
// Copyright 2018 Klaus Post. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
// Based on work Copyright (c) 2013, Yann Collet, released under BSD License.
|
||||
|
||||
package huff0
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
)
|
||||
|
||||
// bitReader reads a bitstream in reverse.
|
||||
// The last set bit indicates the start of the stream and is used
|
||||
// for aligning the input.
|
||||
type bitReaderBytes struct {
|
||||
in []byte
|
||||
off uint // next byte to read is at in[off - 1]
|
||||
value uint64
|
||||
bitsRead uint8
|
||||
}
|
||||
|
||||
// init initializes and resets the bit reader.
|
||||
func (b *bitReaderBytes) init(in []byte) error {
|
||||
if len(in) < 1 {
|
||||
return errors.New("corrupt stream: too short")
|
||||
}
|
||||
b.in = in
|
||||
b.off = uint(len(in))
|
||||
// The highest bit of the last byte indicates where to start
|
||||
v := in[len(in)-1]
|
||||
if v == 0 {
|
||||
return errors.New("corrupt stream, did not find end of stream")
|
||||
}
|
||||
b.bitsRead = 64
|
||||
b.value = 0
|
||||
if len(in) >= 8 {
|
||||
b.fillFastStart()
|
||||
} else {
|
||||
b.fill()
|
||||
b.fill()
|
||||
}
|
||||
b.advance(8 - uint8(highBit32(uint32(v))))
|
||||
return nil
|
||||
}
|
||||
|
||||
// peekBitsFast requires that at least one bit is requested every time.
|
||||
// There are no checks if the buffer is filled.
|
||||
func (b *bitReaderBytes) peekByteFast() uint8 {
|
||||
got := uint8(b.value >> 56)
|
||||
return got
|
||||
}
|
||||
|
||||
func (b *bitReaderBytes) advance(n uint8) {
|
||||
b.bitsRead += n
|
||||
b.value <<= n & 63
|
||||
}
|
||||
|
||||
// fillFast() will make sure at least 32 bits are available.
|
||||
// There must be at least 4 bytes available.
|
||||
func (b *bitReaderBytes) fillFast() {
|
||||
if b.bitsRead < 32 {
|
||||
return
|
||||
}
|
||||
|
||||
// 2 bounds checks.
|
||||
v := b.in[b.off-4 : b.off]
|
||||
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
|
||||
b.value |= uint64(low) << (b.bitsRead - 32)
|
||||
b.bitsRead -= 32
|
||||
b.off -= 4
|
||||
}
|
||||
|
||||
// fillFastStart() assumes the bitReaderBytes is empty and there is at least 8 bytes to read.
|
||||
func (b *bitReaderBytes) fillFastStart() {
|
||||
// Do single re-slice to avoid bounds checks.
|
||||
b.value = binary.LittleEndian.Uint64(b.in[b.off-8:])
|
||||
b.bitsRead = 0
|
||||
b.off -= 8
|
||||
}
|
||||
|
||||
// fill() will make sure at least 32 bits are available.
|
||||
func (b *bitReaderBytes) fill() {
|
||||
if b.bitsRead < 32 {
|
||||
return
|
||||
}
|
||||
if b.off > 4 {
|
||||
v := b.in[b.off-4 : b.off]
|
||||
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
|
||||
b.value |= uint64(low) << (b.bitsRead - 32)
|
||||
b.bitsRead -= 32
|
||||
b.off -= 4
|
||||
return
|
||||
}
|
||||
for b.off > 0 {
|
||||
b.value |= uint64(b.in[b.off-1]) << (b.bitsRead - 8)
|
||||
b.bitsRead -= 8
|
||||
b.off--
|
||||
}
|
||||
}
|
||||
|
||||
// finished returns true if all bits have been read from the bit stream.
|
||||
func (b *bitReaderBytes) finished() bool {
|
||||
return b.off == 0 && b.bitsRead >= 64
|
||||
}
|
||||
|
||||
func (b *bitReaderBytes) remaining() uint {
|
||||
return b.off*8 + uint(64-b.bitsRead)
|
||||
}
|
||||
|
||||
// close the bitstream and returns an error if out-of-buffer reads occurred.
|
||||
func (b *bitReaderBytes) close() error {
|
||||
// Release reference.
|
||||
b.in = nil
|
||||
if b.remaining() > 0 {
|
||||
return fmt.Errorf("corrupt input: %d bits remain on stream", b.remaining())
|
||||
}
|
||||
if b.bitsRead > 64 {
|
||||
return io.ErrUnexpectedEOF
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// bitReaderShifted reads a bitstream in reverse.
|
||||
// The last set bit indicates the start of the stream and is used
|
||||
// for aligning the input.
|
||||
type bitReaderShifted struct {
|
||||
in []byte
|
||||
off uint // next byte to read is at in[off - 1]
|
||||
value uint64
|
||||
bitsRead uint8
|
||||
}
|
||||
|
||||
// init initializes and resets the bit reader.
|
||||
func (b *bitReaderShifted) init(in []byte) error {
|
||||
if len(in) < 1 {
|
||||
return errors.New("corrupt stream: too short")
|
||||
}
|
||||
b.in = in
|
||||
b.off = uint(len(in))
|
||||
// The highest bit of the last byte indicates where to start
|
||||
v := in[len(in)-1]
|
||||
if v == 0 {
|
||||
return errors.New("corrupt stream, did not find end of stream")
|
||||
}
|
||||
b.bitsRead = 64
|
||||
b.value = 0
|
||||
if len(in) >= 8 {
|
||||
b.fillFastStart()
|
||||
} else {
|
||||
b.fill()
|
||||
b.fill()
|
||||
}
|
||||
b.advance(8 - uint8(highBit32(uint32(v))))
|
||||
return nil
|
||||
}
|
||||
|
||||
// peekBitsFast requires that at least one bit is requested every time.
|
||||
// There are no checks if the buffer is filled.
|
||||
func (b *bitReaderShifted) peekBitsFast(n uint8) uint16 {
|
||||
return uint16(b.value >> ((64 - n) & 63))
|
||||
}
|
||||
|
||||
func (b *bitReaderShifted) advance(n uint8) {
|
||||
b.bitsRead += n
|
||||
b.value <<= n & 63
|
||||
}
|
||||
|
||||
// fillFast() will make sure at least 32 bits are available.
|
||||
// There must be at least 4 bytes available.
|
||||
func (b *bitReaderShifted) fillFast() {
|
||||
if b.bitsRead < 32 {
|
||||
return
|
||||
}
|
||||
|
||||
// 2 bounds checks.
|
||||
v := b.in[b.off-4 : b.off]
|
||||
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
|
||||
b.value |= uint64(low) << ((b.bitsRead - 32) & 63)
|
||||
b.bitsRead -= 32
|
||||
b.off -= 4
|
||||
}
|
||||
|
||||
// fillFastStart() assumes the bitReaderShifted is empty and there is at least 8 bytes to read.
|
||||
func (b *bitReaderShifted) fillFastStart() {
|
||||
// Do single re-slice to avoid bounds checks.
|
||||
b.value = binary.LittleEndian.Uint64(b.in[b.off-8:])
|
||||
b.bitsRead = 0
|
||||
b.off -= 8
|
||||
}
|
||||
|
||||
// fill() will make sure at least 32 bits are available.
|
||||
func (b *bitReaderShifted) fill() {
|
||||
if b.bitsRead < 32 {
|
||||
return
|
||||
}
|
||||
if b.off > 4 {
|
||||
v := b.in[b.off-4 : b.off]
|
||||
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
|
||||
b.value |= uint64(low) << ((b.bitsRead - 32) & 63)
|
||||
b.bitsRead -= 32
|
||||
b.off -= 4
|
||||
return
|
||||
}
|
||||
for b.off > 0 {
|
||||
b.value |= uint64(b.in[b.off-1]) << ((b.bitsRead - 8) & 63)
|
||||
b.bitsRead -= 8
|
||||
b.off--
|
||||
}
|
||||
}
|
||||
|
||||
func (b *bitReaderShifted) remaining() uint {
|
||||
return b.off*8 + uint(64-b.bitsRead)
|
||||
}
|
||||
|
||||
// close the bitstream and returns an error if out-of-buffer reads occurred.
|
||||
func (b *bitReaderShifted) close() error {
|
||||
// Release reference.
|
||||
b.in = nil
|
||||
if b.remaining() > 0 {
|
||||
return fmt.Errorf("corrupt input: %d bits remain on stream", b.remaining())
|
||||
}
|
||||
if b.bitsRead > 64 {
|
||||
return io.ErrUnexpectedEOF
|
||||
}
|
||||
return nil
|
||||
}
|
||||
102
vendor/github.com/klauspost/compress/huff0/bitwriter.go
generated
vendored
102
vendor/github.com/klauspost/compress/huff0/bitwriter.go
generated
vendored
@ -1,102 +0,0 @@
|
||||
// Copyright 2018 Klaus Post. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
// Based on work Copyright (c) 2013, Yann Collet, released under BSD License.
|
||||
|
||||
package huff0
|
||||
|
||||
// bitWriter will write bits.
|
||||
// First bit will be LSB of the first byte of output.
|
||||
type bitWriter struct {
|
||||
bitContainer uint64
|
||||
nBits uint8
|
||||
out []byte
|
||||
}
|
||||
|
||||
// addBits16Clean will add up to 16 bits. value may not contain more set bits than indicated.
|
||||
// It will not check if there is space for them, so the caller must ensure that it has flushed recently.
|
||||
func (b *bitWriter) addBits16Clean(value uint16, bits uint8) {
|
||||
b.bitContainer |= uint64(value) << (b.nBits & 63)
|
||||
b.nBits += bits
|
||||
}
|
||||
|
||||
// encSymbol will add up to 16 bits. value may not contain more set bits than indicated.
|
||||
// It will not check if there is space for them, so the caller must ensure that it has flushed recently.
|
||||
func (b *bitWriter) encSymbol(ct cTable, symbol byte) {
|
||||
enc := ct[symbol]
|
||||
b.bitContainer |= uint64(enc.val) << (b.nBits & 63)
|
||||
if false {
|
||||
if enc.nBits == 0 {
|
||||
panic("nbits 0")
|
||||
}
|
||||
}
|
||||
b.nBits += enc.nBits
|
||||
}
|
||||
|
||||
// encTwoSymbols will add up to 32 bits. value may not contain more set bits than indicated.
|
||||
// It will not check if there is space for them, so the caller must ensure that it has flushed recently.
|
||||
func (b *bitWriter) encTwoSymbols(ct cTable, av, bv byte) {
|
||||
encA := ct[av]
|
||||
encB := ct[bv]
|
||||
sh := b.nBits & 63
|
||||
combined := uint64(encA.val) | (uint64(encB.val) << (encA.nBits & 63))
|
||||
b.bitContainer |= combined << sh
|
||||
if false {
|
||||
if encA.nBits == 0 {
|
||||
panic("nbitsA 0")
|
||||
}
|
||||
if encB.nBits == 0 {
|
||||
panic("nbitsB 0")
|
||||
}
|
||||
}
|
||||
b.nBits += encA.nBits + encB.nBits
|
||||
}
|
||||
|
||||
// encFourSymbols adds up to 32 bits from four symbols.
|
||||
// It will not check if there is space for them,
|
||||
// so the caller must ensure that b has been flushed recently.
|
||||
func (b *bitWriter) encFourSymbols(encA, encB, encC, encD cTableEntry) {
|
||||
bitsA := encA.nBits
|
||||
bitsB := bitsA + encB.nBits
|
||||
bitsC := bitsB + encC.nBits
|
||||
bitsD := bitsC + encD.nBits
|
||||
combined := uint64(encA.val) |
|
||||
(uint64(encB.val) << (bitsA & 63)) |
|
||||
(uint64(encC.val) << (bitsB & 63)) |
|
||||
(uint64(encD.val) << (bitsC & 63))
|
||||
b.bitContainer |= combined << (b.nBits & 63)
|
||||
b.nBits += bitsD
|
||||
}
|
||||
|
||||
// flush32 will flush out, so there are at least 32 bits available for writing.
|
||||
func (b *bitWriter) flush32() {
|
||||
if b.nBits < 32 {
|
||||
return
|
||||
}
|
||||
b.out = append(b.out,
|
||||
byte(b.bitContainer),
|
||||
byte(b.bitContainer>>8),
|
||||
byte(b.bitContainer>>16),
|
||||
byte(b.bitContainer>>24))
|
||||
b.nBits -= 32
|
||||
b.bitContainer >>= 32
|
||||
}
|
||||
|
||||
// flushAlign will flush remaining full bytes and align to next byte boundary.
|
||||
func (b *bitWriter) flushAlign() {
|
||||
nbBytes := (b.nBits + 7) >> 3
|
||||
for i := uint8(0); i < nbBytes; i++ {
|
||||
b.out = append(b.out, byte(b.bitContainer>>(i*8)))
|
||||
}
|
||||
b.nBits = 0
|
||||
b.bitContainer = 0
|
||||
}
|
||||
|
||||
// close will write the alignment bit and write the final byte(s)
|
||||
// to the output.
|
||||
func (b *bitWriter) close() {
|
||||
// End mark
|
||||
b.addBits16Clean(1, 1)
|
||||
// flush until next byte.
|
||||
b.flushAlign()
|
||||
}
|
||||
742
vendor/github.com/klauspost/compress/huff0/compress.go
generated
vendored
742
vendor/github.com/klauspost/compress/huff0/compress.go
generated
vendored
@ -1,742 +0,0 @@
|
||||
package huff0
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"math"
|
||||
"runtime"
|
||||
"sync"
|
||||
)
|
||||
|
||||
// Compress1X will compress the input.
|
||||
// The output can be decoded using Decompress1X.
|
||||
// Supply a Scratch object. The scratch object contains state about re-use,
|
||||
// So when sharing across independent encodes, be sure to set the re-use policy.
|
||||
func Compress1X(in []byte, s *Scratch) (out []byte, reUsed bool, err error) {
|
||||
s, err = s.prepare(in)
|
||||
if err != nil {
|
||||
return nil, false, err
|
||||
}
|
||||
return compress(in, s, s.compress1X)
|
||||
}
|
||||
|
||||
// Compress4X will compress the input. The input is split into 4 independent blocks
|
||||
// and compressed similar to Compress1X.
|
||||
// The output can be decoded using Decompress4X.
|
||||
// Supply a Scratch object. The scratch object contains state about re-use,
|
||||
// So when sharing across independent encodes, be sure to set the re-use policy.
|
||||
func Compress4X(in []byte, s *Scratch) (out []byte, reUsed bool, err error) {
|
||||
s, err = s.prepare(in)
|
||||
if err != nil {
|
||||
return nil, false, err
|
||||
}
|
||||
if false {
|
||||
// TODO: compress4Xp only slightly faster.
|
||||
const parallelThreshold = 8 << 10
|
||||
if len(in) < parallelThreshold || runtime.GOMAXPROCS(0) == 1 {
|
||||
return compress(in, s, s.compress4X)
|
||||
}
|
||||
return compress(in, s, s.compress4Xp)
|
||||
}
|
||||
return compress(in, s, s.compress4X)
|
||||
}
|
||||
|
||||
func compress(in []byte, s *Scratch, compressor func(src []byte) ([]byte, error)) (out []byte, reUsed bool, err error) {
|
||||
// Nuke previous table if we cannot reuse anyway.
|
||||
if s.Reuse == ReusePolicyNone {
|
||||
s.prevTable = s.prevTable[:0]
|
||||
}
|
||||
|
||||
// Create histogram, if none was provided.
|
||||
maxCount := s.maxCount
|
||||
var canReuse = false
|
||||
if maxCount == 0 {
|
||||
maxCount, canReuse = s.countSimple(in)
|
||||
} else {
|
||||
canReuse = s.canUseTable(s.prevTable)
|
||||
}
|
||||
|
||||
// We want the output size to be less than this:
|
||||
wantSize := len(in)
|
||||
if s.WantLogLess > 0 {
|
||||
wantSize -= wantSize >> s.WantLogLess
|
||||
}
|
||||
|
||||
// Reset for next run.
|
||||
s.clearCount = true
|
||||
s.maxCount = 0
|
||||
if maxCount >= len(in) {
|
||||
if maxCount > len(in) {
|
||||
return nil, false, fmt.Errorf("maxCount (%d) > length (%d)", maxCount, len(in))
|
||||
}
|
||||
if len(in) == 1 {
|
||||
return nil, false, ErrIncompressible
|
||||
}
|
||||
// One symbol, use RLE
|
||||
return nil, false, ErrUseRLE
|
||||
}
|
||||
if maxCount == 1 || maxCount < (len(in)>>7) {
|
||||
// Each symbol present maximum once or too well distributed.
|
||||
return nil, false, ErrIncompressible
|
||||
}
|
||||
if s.Reuse == ReusePolicyMust && !canReuse {
|
||||
// We must reuse, but we can't.
|
||||
return nil, false, ErrIncompressible
|
||||
}
|
||||
if (s.Reuse == ReusePolicyPrefer || s.Reuse == ReusePolicyMust) && canReuse {
|
||||
keepTable := s.cTable
|
||||
keepTL := s.actualTableLog
|
||||
s.cTable = s.prevTable
|
||||
s.actualTableLog = s.prevTableLog
|
||||
s.Out, err = compressor(in)
|
||||
s.cTable = keepTable
|
||||
s.actualTableLog = keepTL
|
||||
if err == nil && len(s.Out) < wantSize {
|
||||
s.OutData = s.Out
|
||||
return s.Out, true, nil
|
||||
}
|
||||
if s.Reuse == ReusePolicyMust {
|
||||
return nil, false, ErrIncompressible
|
||||
}
|
||||
// Do not attempt to re-use later.
|
||||
s.prevTable = s.prevTable[:0]
|
||||
}
|
||||
|
||||
// Calculate new table.
|
||||
err = s.buildCTable()
|
||||
if err != nil {
|
||||
return nil, false, err
|
||||
}
|
||||
|
||||
if false && !s.canUseTable(s.cTable) {
|
||||
panic("invalid table generated")
|
||||
}
|
||||
|
||||
if s.Reuse == ReusePolicyAllow && canReuse {
|
||||
hSize := len(s.Out)
|
||||
oldSize := s.prevTable.estimateSize(s.count[:s.symbolLen])
|
||||
newSize := s.cTable.estimateSize(s.count[:s.symbolLen])
|
||||
if oldSize <= hSize+newSize || hSize+12 >= wantSize {
|
||||
// Retain cTable even if we re-use.
|
||||
keepTable := s.cTable
|
||||
keepTL := s.actualTableLog
|
||||
|
||||
s.cTable = s.prevTable
|
||||
s.actualTableLog = s.prevTableLog
|
||||
s.Out, err = compressor(in)
|
||||
|
||||
// Restore ctable.
|
||||
s.cTable = keepTable
|
||||
s.actualTableLog = keepTL
|
||||
if err != nil {
|
||||
return nil, false, err
|
||||
}
|
||||
if len(s.Out) >= wantSize {
|
||||
return nil, false, ErrIncompressible
|
||||
}
|
||||
s.OutData = s.Out
|
||||
return s.Out, true, nil
|
||||
}
|
||||
}
|
||||
|
||||
// Use new table
|
||||
err = s.cTable.write(s)
|
||||
if err != nil {
|
||||
s.OutTable = nil
|
||||
return nil, false, err
|
||||
}
|
||||
s.OutTable = s.Out
|
||||
|
||||
// Compress using new table
|
||||
s.Out, err = compressor(in)
|
||||
if err != nil {
|
||||
s.OutTable = nil
|
||||
return nil, false, err
|
||||
}
|
||||
if len(s.Out) >= wantSize {
|
||||
s.OutTable = nil
|
||||
return nil, false, ErrIncompressible
|
||||
}
|
||||
// Move current table into previous.
|
||||
s.prevTable, s.prevTableLog, s.cTable = s.cTable, s.actualTableLog, s.prevTable[:0]
|
||||
s.OutData = s.Out[len(s.OutTable):]
|
||||
return s.Out, false, nil
|
||||
}
|
||||
|
||||
// EstimateSizes will estimate the data sizes
|
||||
func EstimateSizes(in []byte, s *Scratch) (tableSz, dataSz, reuseSz int, err error) {
|
||||
s, err = s.prepare(in)
|
||||
if err != nil {
|
||||
return 0, 0, 0, err
|
||||
}
|
||||
|
||||
// Create histogram, if none was provided.
|
||||
tableSz, dataSz, reuseSz = -1, -1, -1
|
||||
maxCount := s.maxCount
|
||||
var canReuse = false
|
||||
if maxCount == 0 {
|
||||
maxCount, canReuse = s.countSimple(in)
|
||||
} else {
|
||||
canReuse = s.canUseTable(s.prevTable)
|
||||
}
|
||||
|
||||
// We want the output size to be less than this:
|
||||
wantSize := len(in)
|
||||
if s.WantLogLess > 0 {
|
||||
wantSize -= wantSize >> s.WantLogLess
|
||||
}
|
||||
|
||||
// Reset for next run.
|
||||
s.clearCount = true
|
||||
s.maxCount = 0
|
||||
if maxCount >= len(in) {
|
||||
if maxCount > len(in) {
|
||||
return 0, 0, 0, fmt.Errorf("maxCount (%d) > length (%d)", maxCount, len(in))
|
||||
}
|
||||
if len(in) == 1 {
|
||||
return 0, 0, 0, ErrIncompressible
|
||||
}
|
||||
// One symbol, use RLE
|
||||
return 0, 0, 0, ErrUseRLE
|
||||
}
|
||||
if maxCount == 1 || maxCount < (len(in)>>7) {
|
||||
// Each symbol present maximum once or too well distributed.
|
||||
return 0, 0, 0, ErrIncompressible
|
||||
}
|
||||
|
||||
// Calculate new table.
|
||||
err = s.buildCTable()
|
||||
if err != nil {
|
||||
return 0, 0, 0, err
|
||||
}
|
||||
|
||||
if false && !s.canUseTable(s.cTable) {
|
||||
panic("invalid table generated")
|
||||
}
|
||||
|
||||
tableSz, err = s.cTable.estTableSize(s)
|
||||
if err != nil {
|
||||
return 0, 0, 0, err
|
||||
}
|
||||
if canReuse {
|
||||
reuseSz = s.prevTable.estimateSize(s.count[:s.symbolLen])
|
||||
}
|
||||
dataSz = s.cTable.estimateSize(s.count[:s.symbolLen])
|
||||
|
||||
// Restore
|
||||
return tableSz, dataSz, reuseSz, nil
|
||||
}
|
||||
|
||||
func (s *Scratch) compress1X(src []byte) ([]byte, error) {
|
||||
return s.compress1xDo(s.Out, src), nil
|
||||
}
|
||||
|
||||
func (s *Scratch) compress1xDo(dst, src []byte) []byte {
|
||||
var bw = bitWriter{out: dst}
|
||||
|
||||
// N is length divisible by 4.
|
||||
n := len(src)
|
||||
n -= n & 3
|
||||
cTable := s.cTable[:256]
|
||||
|
||||
// Encode last bytes.
|
||||
for i := len(src) & 3; i > 0; i-- {
|
||||
bw.encSymbol(cTable, src[n+i-1])
|
||||
}
|
||||
n -= 4
|
||||
if s.actualTableLog <= 8 {
|
||||
for ; n >= 0; n -= 4 {
|
||||
tmp := src[n : n+4]
|
||||
// tmp should be len 4
|
||||
bw.flush32()
|
||||
bw.encFourSymbols(cTable[tmp[3]], cTable[tmp[2]], cTable[tmp[1]], cTable[tmp[0]])
|
||||
}
|
||||
} else {
|
||||
for ; n >= 0; n -= 4 {
|
||||
tmp := src[n : n+4]
|
||||
// tmp should be len 4
|
||||
bw.flush32()
|
||||
bw.encTwoSymbols(cTable, tmp[3], tmp[2])
|
||||
bw.flush32()
|
||||
bw.encTwoSymbols(cTable, tmp[1], tmp[0])
|
||||
}
|
||||
}
|
||||
bw.close()
|
||||
return bw.out
|
||||
}
|
||||
|
||||
var sixZeros [6]byte
|
||||
|
||||
func (s *Scratch) compress4X(src []byte) ([]byte, error) {
|
||||
if len(src) < 12 {
|
||||
return nil, ErrIncompressible
|
||||
}
|
||||
segmentSize := (len(src) + 3) / 4
|
||||
|
||||
// Add placeholder for output length
|
||||
offsetIdx := len(s.Out)
|
||||
s.Out = append(s.Out, sixZeros[:]...)
|
||||
|
||||
for i := 0; i < 4; i++ {
|
||||
toDo := src
|
||||
if len(toDo) > segmentSize {
|
||||
toDo = toDo[:segmentSize]
|
||||
}
|
||||
src = src[len(toDo):]
|
||||
|
||||
idx := len(s.Out)
|
||||
s.Out = s.compress1xDo(s.Out, toDo)
|
||||
if len(s.Out)-idx > math.MaxUint16 {
|
||||
// We cannot store the size in the jump table
|
||||
return nil, ErrIncompressible
|
||||
}
|
||||
// Write compressed length as little endian before block.
|
||||
if i < 3 {
|
||||
// Last length is not written.
|
||||
length := len(s.Out) - idx
|
||||
s.Out[i*2+offsetIdx] = byte(length)
|
||||
s.Out[i*2+offsetIdx+1] = byte(length >> 8)
|
||||
}
|
||||
}
|
||||
|
||||
return s.Out, nil
|
||||
}
|
||||
|
||||
// compress4Xp will compress 4 streams using separate goroutines.
|
||||
func (s *Scratch) compress4Xp(src []byte) ([]byte, error) {
|
||||
if len(src) < 12 {
|
||||
return nil, ErrIncompressible
|
||||
}
|
||||
// Add placeholder for output length
|
||||
s.Out = s.Out[:6]
|
||||
|
||||
segmentSize := (len(src) + 3) / 4
|
||||
var wg sync.WaitGroup
|
||||
wg.Add(4)
|
||||
for i := 0; i < 4; i++ {
|
||||
toDo := src
|
||||
if len(toDo) > segmentSize {
|
||||
toDo = toDo[:segmentSize]
|
||||
}
|
||||
src = src[len(toDo):]
|
||||
|
||||
// Separate goroutine for each block.
|
||||
go func(i int) {
|
||||
s.tmpOut[i] = s.compress1xDo(s.tmpOut[i][:0], toDo)
|
||||
wg.Done()
|
||||
}(i)
|
||||
}
|
||||
wg.Wait()
|
||||
for i := 0; i < 4; i++ {
|
||||
o := s.tmpOut[i]
|
||||
if len(o) > math.MaxUint16 {
|
||||
// We cannot store the size in the jump table
|
||||
return nil, ErrIncompressible
|
||||
}
|
||||
// Write compressed length as little endian before block.
|
||||
if i < 3 {
|
||||
// Last length is not written.
|
||||
s.Out[i*2] = byte(len(o))
|
||||
s.Out[i*2+1] = byte(len(o) >> 8)
|
||||
}
|
||||
|
||||
// Write output.
|
||||
s.Out = append(s.Out, o...)
|
||||
}
|
||||
return s.Out, nil
|
||||
}
|
||||
|
||||
// countSimple will create a simple histogram in s.count.
|
||||
// Returns the biggest count.
|
||||
// Does not update s.clearCount.
|
||||
func (s *Scratch) countSimple(in []byte) (max int, reuse bool) {
|
||||
reuse = true
|
||||
_ = s.count // Assert that s != nil to speed up the following loop.
|
||||
for _, v := range in {
|
||||
s.count[v]++
|
||||
}
|
||||
m := uint32(0)
|
||||
if len(s.prevTable) > 0 {
|
||||
for i, v := range s.count[:] {
|
||||
if v == 0 {
|
||||
continue
|
||||
}
|
||||
if v > m {
|
||||
m = v
|
||||
}
|
||||
s.symbolLen = uint16(i) + 1
|
||||
if i >= len(s.prevTable) {
|
||||
reuse = false
|
||||
} else if s.prevTable[i].nBits == 0 {
|
||||
reuse = false
|
||||
}
|
||||
}
|
||||
return int(m), reuse
|
||||
}
|
||||
for i, v := range s.count[:] {
|
||||
if v == 0 {
|
||||
continue
|
||||
}
|
||||
if v > m {
|
||||
m = v
|
||||
}
|
||||
s.symbolLen = uint16(i) + 1
|
||||
}
|
||||
return int(m), false
|
||||
}
|
||||
|
||||
func (s *Scratch) canUseTable(c cTable) bool {
|
||||
if len(c) < int(s.symbolLen) {
|
||||
return false
|
||||
}
|
||||
for i, v := range s.count[:s.symbolLen] {
|
||||
if v != 0 && c[i].nBits == 0 {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
//lint:ignore U1000 used for debugging
|
||||
func (s *Scratch) validateTable(c cTable) bool {
|
||||
if len(c) < int(s.symbolLen) {
|
||||
return false
|
||||
}
|
||||
for i, v := range s.count[:s.symbolLen] {
|
||||
if v != 0 {
|
||||
if c[i].nBits == 0 {
|
||||
return false
|
||||
}
|
||||
if c[i].nBits > s.actualTableLog {
|
||||
return false
|
||||
}
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// minTableLog provides the minimum logSize to safely represent a distribution.
|
||||
func (s *Scratch) minTableLog() uint8 {
|
||||
minBitsSrc := highBit32(uint32(s.srcLen)) + 1
|
||||
minBitsSymbols := highBit32(uint32(s.symbolLen-1)) + 2
|
||||
if minBitsSrc < minBitsSymbols {
|
||||
return uint8(minBitsSrc)
|
||||
}
|
||||
return uint8(minBitsSymbols)
|
||||
}
|
||||
|
||||
// optimalTableLog calculates and sets the optimal tableLog in s.actualTableLog
|
||||
func (s *Scratch) optimalTableLog() {
|
||||
tableLog := s.TableLog
|
||||
minBits := s.minTableLog()
|
||||
maxBitsSrc := uint8(highBit32(uint32(s.srcLen-1))) - 1
|
||||
if maxBitsSrc < tableLog {
|
||||
// Accuracy can be reduced
|
||||
tableLog = maxBitsSrc
|
||||
}
|
||||
if minBits > tableLog {
|
||||
tableLog = minBits
|
||||
}
|
||||
// Need a minimum to safely represent all symbol values
|
||||
if tableLog < minTablelog {
|
||||
tableLog = minTablelog
|
||||
}
|
||||
if tableLog > tableLogMax {
|
||||
tableLog = tableLogMax
|
||||
}
|
||||
s.actualTableLog = tableLog
|
||||
}
|
||||
|
||||
type cTableEntry struct {
|
||||
val uint16
|
||||
nBits uint8
|
||||
// We have 8 bits extra
|
||||
}
|
||||
|
||||
const huffNodesMask = huffNodesLen - 1
|
||||
|
||||
func (s *Scratch) buildCTable() error {
|
||||
s.optimalTableLog()
|
||||
s.huffSort()
|
||||
if cap(s.cTable) < maxSymbolValue+1 {
|
||||
s.cTable = make([]cTableEntry, s.symbolLen, maxSymbolValue+1)
|
||||
} else {
|
||||
s.cTable = s.cTable[:s.symbolLen]
|
||||
for i := range s.cTable {
|
||||
s.cTable[i] = cTableEntry{}
|
||||
}
|
||||
}
|
||||
|
||||
var startNode = int16(s.symbolLen)
|
||||
nonNullRank := s.symbolLen - 1
|
||||
|
||||
nodeNb := startNode
|
||||
huffNode := s.nodes[1 : huffNodesLen+1]
|
||||
|
||||
// This overlays the slice above, but allows "-1" index lookups.
|
||||
// Different from reference implementation.
|
||||
huffNode0 := s.nodes[0 : huffNodesLen+1]
|
||||
|
||||
for huffNode[nonNullRank].count() == 0 {
|
||||
nonNullRank--
|
||||
}
|
||||
|
||||
lowS := int16(nonNullRank)
|
||||
nodeRoot := nodeNb + lowS - 1
|
||||
lowN := nodeNb
|
||||
huffNode[nodeNb].setCount(huffNode[lowS].count() + huffNode[lowS-1].count())
|
||||
huffNode[lowS].setParent(nodeNb)
|
||||
huffNode[lowS-1].setParent(nodeNb)
|
||||
nodeNb++
|
||||
lowS -= 2
|
||||
for n := nodeNb; n <= nodeRoot; n++ {
|
||||
huffNode[n].setCount(1 << 30)
|
||||
}
|
||||
// fake entry, strong barrier
|
||||
huffNode0[0].setCount(1 << 31)
|
||||
|
||||
// create parents
|
||||
for nodeNb <= nodeRoot {
|
||||
var n1, n2 int16
|
||||
if huffNode0[lowS+1].count() < huffNode0[lowN+1].count() {
|
||||
n1 = lowS
|
||||
lowS--
|
||||
} else {
|
||||
n1 = lowN
|
||||
lowN++
|
||||
}
|
||||
if huffNode0[lowS+1].count() < huffNode0[lowN+1].count() {
|
||||
n2 = lowS
|
||||
lowS--
|
||||
} else {
|
||||
n2 = lowN
|
||||
lowN++
|
||||
}
|
||||
|
||||
huffNode[nodeNb].setCount(huffNode0[n1+1].count() + huffNode0[n2+1].count())
|
||||
huffNode0[n1+1].setParent(nodeNb)
|
||||
huffNode0[n2+1].setParent(nodeNb)
|
||||
nodeNb++
|
||||
}
|
||||
|
||||
// distribute weights (unlimited tree height)
|
||||
huffNode[nodeRoot].setNbBits(0)
|
||||
for n := nodeRoot - 1; n >= startNode; n-- {
|
||||
huffNode[n].setNbBits(huffNode[huffNode[n].parent()].nbBits() + 1)
|
||||
}
|
||||
for n := uint16(0); n <= nonNullRank; n++ {
|
||||
huffNode[n].setNbBits(huffNode[huffNode[n].parent()].nbBits() + 1)
|
||||
}
|
||||
s.actualTableLog = s.setMaxHeight(int(nonNullRank))
|
||||
maxNbBits := s.actualTableLog
|
||||
|
||||
// fill result into tree (val, nbBits)
|
||||
if maxNbBits > tableLogMax {
|
||||
return fmt.Errorf("internal error: maxNbBits (%d) > tableLogMax (%d)", maxNbBits, tableLogMax)
|
||||
}
|
||||
var nbPerRank [tableLogMax + 1]uint16
|
||||
var valPerRank [16]uint16
|
||||
for _, v := range huffNode[:nonNullRank+1] {
|
||||
nbPerRank[v.nbBits()]++
|
||||
}
|
||||
// determine stating value per rank
|
||||
{
|
||||
min := uint16(0)
|
||||
for n := maxNbBits; n > 0; n-- {
|
||||
// get starting value within each rank
|
||||
valPerRank[n] = min
|
||||
min += nbPerRank[n]
|
||||
min >>= 1
|
||||
}
|
||||
}
|
||||
|
||||
// push nbBits per symbol, symbol order
|
||||
for _, v := range huffNode[:nonNullRank+1] {
|
||||
s.cTable[v.symbol()].nBits = v.nbBits()
|
||||
}
|
||||
|
||||
// assign value within rank, symbol order
|
||||
t := s.cTable[:s.symbolLen]
|
||||
for n, val := range t {
|
||||
nbits := val.nBits & 15
|
||||
v := valPerRank[nbits]
|
||||
t[n].val = v
|
||||
valPerRank[nbits] = v + 1
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// huffSort will sort symbols, decreasing order.
|
||||
func (s *Scratch) huffSort() {
|
||||
type rankPos struct {
|
||||
base uint32
|
||||
current uint32
|
||||
}
|
||||
|
||||
// Clear nodes
|
||||
nodes := s.nodes[:huffNodesLen+1]
|
||||
s.nodes = nodes
|
||||
nodes = nodes[1 : huffNodesLen+1]
|
||||
|
||||
// Sort into buckets based on length of symbol count.
|
||||
var rank [32]rankPos
|
||||
for _, v := range s.count[:s.symbolLen] {
|
||||
r := highBit32(v+1) & 31
|
||||
rank[r].base++
|
||||
}
|
||||
// maxBitLength is log2(BlockSizeMax) + 1
|
||||
const maxBitLength = 18 + 1
|
||||
for n := maxBitLength; n > 0; n-- {
|
||||
rank[n-1].base += rank[n].base
|
||||
}
|
||||
for n := range rank[:maxBitLength] {
|
||||
rank[n].current = rank[n].base
|
||||
}
|
||||
for n, c := range s.count[:s.symbolLen] {
|
||||
r := (highBit32(c+1) + 1) & 31
|
||||
pos := rank[r].current
|
||||
rank[r].current++
|
||||
prev := nodes[(pos-1)&huffNodesMask]
|
||||
for pos > rank[r].base && c > prev.count() {
|
||||
nodes[pos&huffNodesMask] = prev
|
||||
pos--
|
||||
prev = nodes[(pos-1)&huffNodesMask]
|
||||
}
|
||||
nodes[pos&huffNodesMask] = makeNodeElt(c, byte(n))
|
||||
}
|
||||
}
|
||||
|
||||
func (s *Scratch) setMaxHeight(lastNonNull int) uint8 {
|
||||
maxNbBits := s.actualTableLog
|
||||
huffNode := s.nodes[1 : huffNodesLen+1]
|
||||
//huffNode = huffNode[: huffNodesLen]
|
||||
|
||||
largestBits := huffNode[lastNonNull].nbBits()
|
||||
|
||||
// early exit : no elt > maxNbBits
|
||||
if largestBits <= maxNbBits {
|
||||
return largestBits
|
||||
}
|
||||
totalCost := int(0)
|
||||
baseCost := int(1) << (largestBits - maxNbBits)
|
||||
n := uint32(lastNonNull)
|
||||
|
||||
for huffNode[n].nbBits() > maxNbBits {
|
||||
totalCost += baseCost - (1 << (largestBits - huffNode[n].nbBits()))
|
||||
huffNode[n].setNbBits(maxNbBits)
|
||||
n--
|
||||
}
|
||||
// n stops at huffNode[n].nbBits <= maxNbBits
|
||||
|
||||
for huffNode[n].nbBits() == maxNbBits {
|
||||
n--
|
||||
}
|
||||
// n end at index of smallest symbol using < maxNbBits
|
||||
|
||||
// renorm totalCost
|
||||
totalCost >>= largestBits - maxNbBits /* note : totalCost is necessarily a multiple of baseCost */
|
||||
|
||||
// repay normalized cost
|
||||
{
|
||||
const noSymbol = 0xF0F0F0F0
|
||||
var rankLast [tableLogMax + 2]uint32
|
||||
|
||||
for i := range rankLast[:] {
|
||||
rankLast[i] = noSymbol
|
||||
}
|
||||
|
||||
// Get pos of last (smallest) symbol per rank
|
||||
{
|
||||
currentNbBits := maxNbBits
|
||||
for pos := int(n); pos >= 0; pos-- {
|
||||
if huffNode[pos].nbBits() >= currentNbBits {
|
||||
continue
|
||||
}
|
||||
currentNbBits = huffNode[pos].nbBits() // < maxNbBits
|
||||
rankLast[maxNbBits-currentNbBits] = uint32(pos)
|
||||
}
|
||||
}
|
||||
|
||||
for totalCost > 0 {
|
||||
nBitsToDecrease := uint8(highBit32(uint32(totalCost))) + 1
|
||||
|
||||
for ; nBitsToDecrease > 1; nBitsToDecrease-- {
|
||||
highPos := rankLast[nBitsToDecrease]
|
||||
lowPos := rankLast[nBitsToDecrease-1]
|
||||
if highPos == noSymbol {
|
||||
continue
|
||||
}
|
||||
if lowPos == noSymbol {
|
||||
break
|
||||
}
|
||||
highTotal := huffNode[highPos].count()
|
||||
lowTotal := 2 * huffNode[lowPos].count()
|
||||
if highTotal <= lowTotal {
|
||||
break
|
||||
}
|
||||
}
|
||||
// only triggered when no more rank 1 symbol left => find closest one (note : there is necessarily at least one !)
|
||||
// HUF_MAX_TABLELOG test just to please gcc 5+; but it should not be necessary
|
||||
// FIXME: try to remove
|
||||
for (nBitsToDecrease <= tableLogMax) && (rankLast[nBitsToDecrease] == noSymbol) {
|
||||
nBitsToDecrease++
|
||||
}
|
||||
totalCost -= 1 << (nBitsToDecrease - 1)
|
||||
if rankLast[nBitsToDecrease-1] == noSymbol {
|
||||
// this rank is no longer empty
|
||||
rankLast[nBitsToDecrease-1] = rankLast[nBitsToDecrease]
|
||||
}
|
||||
huffNode[rankLast[nBitsToDecrease]].setNbBits(1 +
|
||||
huffNode[rankLast[nBitsToDecrease]].nbBits())
|
||||
if rankLast[nBitsToDecrease] == 0 {
|
||||
/* special case, reached largest symbol */
|
||||
rankLast[nBitsToDecrease] = noSymbol
|
||||
} else {
|
||||
rankLast[nBitsToDecrease]--
|
||||
if huffNode[rankLast[nBitsToDecrease]].nbBits() != maxNbBits-nBitsToDecrease {
|
||||
rankLast[nBitsToDecrease] = noSymbol /* this rank is now empty */
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
for totalCost < 0 { /* Sometimes, cost correction overshoot */
|
||||
if rankLast[1] == noSymbol { /* special case : no rank 1 symbol (using maxNbBits-1); let's create one from largest rank 0 (using maxNbBits) */
|
||||
for huffNode[n].nbBits() == maxNbBits {
|
||||
n--
|
||||
}
|
||||
huffNode[n+1].setNbBits(huffNode[n+1].nbBits() - 1)
|
||||
rankLast[1] = n + 1
|
||||
totalCost++
|
||||
continue
|
||||
}
|
||||
huffNode[rankLast[1]+1].setNbBits(huffNode[rankLast[1]+1].nbBits() - 1)
|
||||
rankLast[1]++
|
||||
totalCost++
|
||||
}
|
||||
}
|
||||
return maxNbBits
|
||||
}
|
||||
|
||||
// A nodeElt is the fields
|
||||
//
|
||||
// count uint32
|
||||
// parent uint16
|
||||
// symbol byte
|
||||
// nbBits uint8
|
||||
//
|
||||
// in some order, all squashed into an integer so that the compiler
|
||||
// always loads and stores entire nodeElts instead of separate fields.
|
||||
type nodeElt uint64
|
||||
|
||||
func makeNodeElt(count uint32, symbol byte) nodeElt {
|
||||
return nodeElt(count) | nodeElt(symbol)<<48
|
||||
}
|
||||
|
||||
func (e *nodeElt) count() uint32 { return uint32(*e) }
|
||||
func (e *nodeElt) parent() uint16 { return uint16(*e >> 32) }
|
||||
func (e *nodeElt) symbol() byte { return byte(*e >> 48) }
|
||||
func (e *nodeElt) nbBits() uint8 { return uint8(*e >> 56) }
|
||||
|
||||
func (e *nodeElt) setCount(c uint32) { *e = (*e)&0xffffffff00000000 | nodeElt(c) }
|
||||
func (e *nodeElt) setParent(p int16) { *e = (*e)&0xffff0000ffffffff | nodeElt(uint16(p))<<32 }
|
||||
func (e *nodeElt) setNbBits(n uint8) { *e = (*e)&0x00ffffffffffffff | nodeElt(n)<<56 }
|
||||
1167
vendor/github.com/klauspost/compress/huff0/decompress.go
generated
vendored
1167
vendor/github.com/klauspost/compress/huff0/decompress.go
generated
vendored
File diff suppressed because it is too large
Load Diff
226
vendor/github.com/klauspost/compress/huff0/decompress_amd64.go
generated
vendored
226
vendor/github.com/klauspost/compress/huff0/decompress_amd64.go
generated
vendored
@ -1,226 +0,0 @@
|
||||
//go:build amd64 && !appengine && !noasm && gc
|
||||
// +build amd64,!appengine,!noasm,gc
|
||||
|
||||
// This file contains the specialisation of Decoder.Decompress4X
|
||||
// and Decoder.Decompress1X that use an asm implementation of thir main loops.
|
||||
package huff0
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
|
||||
"github.com/klauspost/compress/internal/cpuinfo"
|
||||
)
|
||||
|
||||
// decompress4x_main_loop_x86 is an x86 assembler implementation
|
||||
// of Decompress4X when tablelog > 8.
|
||||
//
|
||||
//go:noescape
|
||||
func decompress4x_main_loop_amd64(ctx *decompress4xContext)
|
||||
|
||||
// decompress4x_8b_loop_x86 is an x86 assembler implementation
|
||||
// of Decompress4X when tablelog <= 8 which decodes 4 entries
|
||||
// per loop.
|
||||
//
|
||||
//go:noescape
|
||||
func decompress4x_8b_main_loop_amd64(ctx *decompress4xContext)
|
||||
|
||||
// fallback8BitSize is the size where using Go version is faster.
|
||||
const fallback8BitSize = 800
|
||||
|
||||
type decompress4xContext struct {
|
||||
pbr *[4]bitReaderShifted
|
||||
peekBits uint8
|
||||
out *byte
|
||||
dstEvery int
|
||||
tbl *dEntrySingle
|
||||
decoded int
|
||||
limit *byte
|
||||
}
|
||||
|
||||
// Decompress4X will decompress a 4X encoded stream.
|
||||
// The length of the supplied input must match the end of a block exactly.
|
||||
// The *capacity* of the dst slice must match the destination size of
|
||||
// the uncompressed data exactly.
|
||||
func (d *Decoder) Decompress4X(dst, src []byte) ([]byte, error) {
|
||||
if len(d.dt.single) == 0 {
|
||||
return nil, errors.New("no table loaded")
|
||||
}
|
||||
if len(src) < 6+(4*1) {
|
||||
return nil, errors.New("input too small")
|
||||
}
|
||||
|
||||
use8BitTables := d.actualTableLog <= 8
|
||||
if cap(dst) < fallback8BitSize && use8BitTables {
|
||||
return d.decompress4X8bit(dst, src)
|
||||
}
|
||||
|
||||
var br [4]bitReaderShifted
|
||||
// Decode "jump table"
|
||||
start := 6
|
||||
for i := 0; i < 3; i++ {
|
||||
length := int(src[i*2]) | (int(src[i*2+1]) << 8)
|
||||
if start+length >= len(src) {
|
||||
return nil, errors.New("truncated input (or invalid offset)")
|
||||
}
|
||||
err := br[i].init(src[start : start+length])
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
start += length
|
||||
}
|
||||
err := br[3].init(src[start:])
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
// destination, offset to match first output
|
||||
dstSize := cap(dst)
|
||||
dst = dst[:dstSize]
|
||||
out := dst
|
||||
dstEvery := (dstSize + 3) / 4
|
||||
|
||||
const tlSize = 1 << tableLogMax
|
||||
const tlMask = tlSize - 1
|
||||
single := d.dt.single[:tlSize]
|
||||
|
||||
var decoded int
|
||||
|
||||
if len(out) > 4*4 && !(br[0].off < 4 || br[1].off < 4 || br[2].off < 4 || br[3].off < 4) {
|
||||
ctx := decompress4xContext{
|
||||
pbr: &br,
|
||||
peekBits: uint8((64 - d.actualTableLog) & 63), // see: bitReaderShifted.peekBitsFast()
|
||||
out: &out[0],
|
||||
dstEvery: dstEvery,
|
||||
tbl: &single[0],
|
||||
limit: &out[dstEvery-4], // Always stop decoding when first buffer gets here to avoid writing OOB on last.
|
||||
}
|
||||
if use8BitTables {
|
||||
decompress4x_8b_main_loop_amd64(&ctx)
|
||||
} else {
|
||||
decompress4x_main_loop_amd64(&ctx)
|
||||
}
|
||||
|
||||
decoded = ctx.decoded
|
||||
out = out[decoded/4:]
|
||||
}
|
||||
|
||||
// Decode remaining.
|
||||
remainBytes := dstEvery - (decoded / 4)
|
||||
for i := range br {
|
||||
offset := dstEvery * i
|
||||
endsAt := offset + remainBytes
|
||||
if endsAt > len(out) {
|
||||
endsAt = len(out)
|
||||
}
|
||||
br := &br[i]
|
||||
bitsLeft := br.remaining()
|
||||
for bitsLeft > 0 {
|
||||
br.fill()
|
||||
if offset >= endsAt {
|
||||
return nil, errors.New("corruption detected: stream overrun 4")
|
||||
}
|
||||
|
||||
// Read value and increment offset.
|
||||
val := br.peekBitsFast(d.actualTableLog)
|
||||
v := single[val&tlMask].entry
|
||||
nBits := uint8(v)
|
||||
br.advance(nBits)
|
||||
bitsLeft -= uint(nBits)
|
||||
out[offset] = uint8(v >> 8)
|
||||
offset++
|
||||
}
|
||||
if offset != endsAt {
|
||||
return nil, fmt.Errorf("corruption detected: short output block %d, end %d != %d", i, offset, endsAt)
|
||||
}
|
||||
decoded += offset - dstEvery*i
|
||||
err = br.close()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
if dstSize != decoded {
|
||||
return nil, errors.New("corruption detected: short output block")
|
||||
}
|
||||
return dst, nil
|
||||
}
|
||||
|
||||
// decompress4x_main_loop_x86 is an x86 assembler implementation
|
||||
// of Decompress1X when tablelog > 8.
|
||||
//
|
||||
//go:noescape
|
||||
func decompress1x_main_loop_amd64(ctx *decompress1xContext)
|
||||
|
||||
// decompress4x_main_loop_x86 is an x86 with BMI2 assembler implementation
|
||||
// of Decompress1X when tablelog > 8.
|
||||
//
|
||||
//go:noescape
|
||||
func decompress1x_main_loop_bmi2(ctx *decompress1xContext)
|
||||
|
||||
type decompress1xContext struct {
|
||||
pbr *bitReaderShifted
|
||||
peekBits uint8
|
||||
out *byte
|
||||
outCap int
|
||||
tbl *dEntrySingle
|
||||
decoded int
|
||||
}
|
||||
|
||||
// Error reported by asm implementations
|
||||
const error_max_decoded_size_exeeded = -1
|
||||
|
||||
// Decompress1X will decompress a 1X encoded stream.
|
||||
// The cap of the output buffer will be the maximum decompressed size.
|
||||
// The length of the supplied input must match the end of a block exactly.
|
||||
func (d *Decoder) Decompress1X(dst, src []byte) ([]byte, error) {
|
||||
if len(d.dt.single) == 0 {
|
||||
return nil, errors.New("no table loaded")
|
||||
}
|
||||
var br bitReaderShifted
|
||||
err := br.init(src)
|
||||
if err != nil {
|
||||
return dst, err
|
||||
}
|
||||
maxDecodedSize := cap(dst)
|
||||
dst = dst[:maxDecodedSize]
|
||||
|
||||
const tlSize = 1 << tableLogMax
|
||||
const tlMask = tlSize - 1
|
||||
|
||||
if maxDecodedSize >= 4 {
|
||||
ctx := decompress1xContext{
|
||||
pbr: &br,
|
||||
out: &dst[0],
|
||||
outCap: maxDecodedSize,
|
||||
peekBits: uint8((64 - d.actualTableLog) & 63), // see: bitReaderShifted.peekBitsFast()
|
||||
tbl: &d.dt.single[0],
|
||||
}
|
||||
|
||||
if cpuinfo.HasBMI2() {
|
||||
decompress1x_main_loop_bmi2(&ctx)
|
||||
} else {
|
||||
decompress1x_main_loop_amd64(&ctx)
|
||||
}
|
||||
if ctx.decoded == error_max_decoded_size_exeeded {
|
||||
return nil, ErrMaxDecodedSizeExceeded
|
||||
}
|
||||
|
||||
dst = dst[:ctx.decoded]
|
||||
}
|
||||
|
||||
// br < 8, so uint8 is fine
|
||||
bitsLeft := uint8(br.off)*8 + 64 - br.bitsRead
|
||||
for bitsLeft > 0 {
|
||||
br.fill()
|
||||
if len(dst) >= maxDecodedSize {
|
||||
br.close()
|
||||
return nil, ErrMaxDecodedSizeExceeded
|
||||
}
|
||||
v := d.dt.single[br.peekBitsFast(d.actualTableLog)&tlMask]
|
||||
nBits := uint8(v.entry)
|
||||
br.advance(nBits)
|
||||
bitsLeft -= nBits
|
||||
dst = append(dst, uint8(v.entry>>8))
|
||||
}
|
||||
return dst, br.close()
|
||||
}
|
||||
830
vendor/github.com/klauspost/compress/huff0/decompress_amd64.s
generated
vendored
830
vendor/github.com/klauspost/compress/huff0/decompress_amd64.s
generated
vendored
@ -1,830 +0,0 @@
|
||||
// Code generated by command: go run gen.go -out ../decompress_amd64.s -pkg=huff0. DO NOT EDIT.
|
||||
|
||||
//go:build amd64 && !appengine && !noasm && gc
|
||||
|
||||
// func decompress4x_main_loop_amd64(ctx *decompress4xContext)
|
||||
TEXT ·decompress4x_main_loop_amd64(SB), $0-8
|
||||
// Preload values
|
||||
MOVQ ctx+0(FP), AX
|
||||
MOVBQZX 8(AX), DI
|
||||
MOVQ 16(AX), BX
|
||||
MOVQ 48(AX), SI
|
||||
MOVQ 24(AX), R8
|
||||
MOVQ 32(AX), R9
|
||||
MOVQ (AX), R10
|
||||
|
||||
// Main loop
|
||||
main_loop:
|
||||
XORL DX, DX
|
||||
CMPQ BX, SI
|
||||
SETGE DL
|
||||
|
||||
// br0.fillFast32()
|
||||
MOVQ 32(R10), R11
|
||||
MOVBQZX 40(R10), R12
|
||||
CMPQ R12, $0x20
|
||||
JBE skip_fill0
|
||||
MOVQ 24(R10), AX
|
||||
SUBQ $0x20, R12
|
||||
SUBQ $0x04, AX
|
||||
MOVQ (R10), R13
|
||||
|
||||
// b.value |= uint64(low) << (b.bitsRead & 63)
|
||||
MOVL (AX)(R13*1), R13
|
||||
MOVQ R12, CX
|
||||
SHLQ CL, R13
|
||||
MOVQ AX, 24(R10)
|
||||
ORQ R13, R11
|
||||
|
||||
// exhausted += (br0.off < 4)
|
||||
CMPQ AX, $0x04
|
||||
ADCB $+0, DL
|
||||
|
||||
skip_fill0:
|
||||
// val0 := br0.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v0 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br0.advance(uint8(v0.entry)
|
||||
MOVB CH, AL
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// val1 := br0.peekTopBits(peekBits)
|
||||
MOVQ DI, CX
|
||||
MOVQ R11, R13
|
||||
SHRQ CL, R13
|
||||
|
||||
// v1 := table[val1&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br0.advance(uint8(v1.entry))
|
||||
MOVB CH, AH
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// these two writes get coalesced
|
||||
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
|
||||
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
|
||||
MOVW AX, (BX)
|
||||
|
||||
// update the bitreader structure
|
||||
MOVQ R11, 32(R10)
|
||||
MOVB R12, 40(R10)
|
||||
|
||||
// br1.fillFast32()
|
||||
MOVQ 80(R10), R11
|
||||
MOVBQZX 88(R10), R12
|
||||
CMPQ R12, $0x20
|
||||
JBE skip_fill1
|
||||
MOVQ 72(R10), AX
|
||||
SUBQ $0x20, R12
|
||||
SUBQ $0x04, AX
|
||||
MOVQ 48(R10), R13
|
||||
|
||||
// b.value |= uint64(low) << (b.bitsRead & 63)
|
||||
MOVL (AX)(R13*1), R13
|
||||
MOVQ R12, CX
|
||||
SHLQ CL, R13
|
||||
MOVQ AX, 72(R10)
|
||||
ORQ R13, R11
|
||||
|
||||
// exhausted += (br1.off < 4)
|
||||
CMPQ AX, $0x04
|
||||
ADCB $+0, DL
|
||||
|
||||
skip_fill1:
|
||||
// val0 := br1.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v0 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br1.advance(uint8(v0.entry)
|
||||
MOVB CH, AL
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// val1 := br1.peekTopBits(peekBits)
|
||||
MOVQ DI, CX
|
||||
MOVQ R11, R13
|
||||
SHRQ CL, R13
|
||||
|
||||
// v1 := table[val1&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br1.advance(uint8(v1.entry))
|
||||
MOVB CH, AH
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// these two writes get coalesced
|
||||
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
|
||||
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
|
||||
MOVW AX, (BX)(R8*1)
|
||||
|
||||
// update the bitreader structure
|
||||
MOVQ R11, 80(R10)
|
||||
MOVB R12, 88(R10)
|
||||
|
||||
// br2.fillFast32()
|
||||
MOVQ 128(R10), R11
|
||||
MOVBQZX 136(R10), R12
|
||||
CMPQ R12, $0x20
|
||||
JBE skip_fill2
|
||||
MOVQ 120(R10), AX
|
||||
SUBQ $0x20, R12
|
||||
SUBQ $0x04, AX
|
||||
MOVQ 96(R10), R13
|
||||
|
||||
// b.value |= uint64(low) << (b.bitsRead & 63)
|
||||
MOVL (AX)(R13*1), R13
|
||||
MOVQ R12, CX
|
||||
SHLQ CL, R13
|
||||
MOVQ AX, 120(R10)
|
||||
ORQ R13, R11
|
||||
|
||||
// exhausted += (br2.off < 4)
|
||||
CMPQ AX, $0x04
|
||||
ADCB $+0, DL
|
||||
|
||||
skip_fill2:
|
||||
// val0 := br2.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v0 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br2.advance(uint8(v0.entry)
|
||||
MOVB CH, AL
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// val1 := br2.peekTopBits(peekBits)
|
||||
MOVQ DI, CX
|
||||
MOVQ R11, R13
|
||||
SHRQ CL, R13
|
||||
|
||||
// v1 := table[val1&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br2.advance(uint8(v1.entry))
|
||||
MOVB CH, AH
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// these two writes get coalesced
|
||||
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
|
||||
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
|
||||
MOVW AX, (BX)(R8*2)
|
||||
|
||||
// update the bitreader structure
|
||||
MOVQ R11, 128(R10)
|
||||
MOVB R12, 136(R10)
|
||||
|
||||
// br3.fillFast32()
|
||||
MOVQ 176(R10), R11
|
||||
MOVBQZX 184(R10), R12
|
||||
CMPQ R12, $0x20
|
||||
JBE skip_fill3
|
||||
MOVQ 168(R10), AX
|
||||
SUBQ $0x20, R12
|
||||
SUBQ $0x04, AX
|
||||
MOVQ 144(R10), R13
|
||||
|
||||
// b.value |= uint64(low) << (b.bitsRead & 63)
|
||||
MOVL (AX)(R13*1), R13
|
||||
MOVQ R12, CX
|
||||
SHLQ CL, R13
|
||||
MOVQ AX, 168(R10)
|
||||
ORQ R13, R11
|
||||
|
||||
// exhausted += (br3.off < 4)
|
||||
CMPQ AX, $0x04
|
||||
ADCB $+0, DL
|
||||
|
||||
skip_fill3:
|
||||
// val0 := br3.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v0 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br3.advance(uint8(v0.entry)
|
||||
MOVB CH, AL
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// val1 := br3.peekTopBits(peekBits)
|
||||
MOVQ DI, CX
|
||||
MOVQ R11, R13
|
||||
SHRQ CL, R13
|
||||
|
||||
// v1 := table[val1&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br3.advance(uint8(v1.entry))
|
||||
MOVB CH, AH
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// these two writes get coalesced
|
||||
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
|
||||
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
|
||||
LEAQ (R8)(R8*2), CX
|
||||
MOVW AX, (BX)(CX*1)
|
||||
|
||||
// update the bitreader structure
|
||||
MOVQ R11, 176(R10)
|
||||
MOVB R12, 184(R10)
|
||||
ADDQ $0x02, BX
|
||||
TESTB DL, DL
|
||||
JZ main_loop
|
||||
MOVQ ctx+0(FP), AX
|
||||
SUBQ 16(AX), BX
|
||||
SHLQ $0x02, BX
|
||||
MOVQ BX, 40(AX)
|
||||
RET
|
||||
|
||||
// func decompress4x_8b_main_loop_amd64(ctx *decompress4xContext)
|
||||
TEXT ·decompress4x_8b_main_loop_amd64(SB), $0-8
|
||||
// Preload values
|
||||
MOVQ ctx+0(FP), CX
|
||||
MOVBQZX 8(CX), DI
|
||||
MOVQ 16(CX), BX
|
||||
MOVQ 48(CX), SI
|
||||
MOVQ 24(CX), R8
|
||||
MOVQ 32(CX), R9
|
||||
MOVQ (CX), R10
|
||||
|
||||
// Main loop
|
||||
main_loop:
|
||||
XORL DX, DX
|
||||
CMPQ BX, SI
|
||||
SETGE DL
|
||||
|
||||
// br0.fillFast32()
|
||||
MOVQ 32(R10), R11
|
||||
MOVBQZX 40(R10), R12
|
||||
CMPQ R12, $0x20
|
||||
JBE skip_fill0
|
||||
MOVQ 24(R10), R13
|
||||
SUBQ $0x20, R12
|
||||
SUBQ $0x04, R13
|
||||
MOVQ (R10), R14
|
||||
|
||||
// b.value |= uint64(low) << (b.bitsRead & 63)
|
||||
MOVL (R13)(R14*1), R14
|
||||
MOVQ R12, CX
|
||||
SHLQ CL, R14
|
||||
MOVQ R13, 24(R10)
|
||||
ORQ R14, R11
|
||||
|
||||
// exhausted += (br0.off < 4)
|
||||
CMPQ R13, $0x04
|
||||
ADCB $+0, DL
|
||||
|
||||
skip_fill0:
|
||||
// val0 := br0.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v0 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br0.advance(uint8(v0.entry)
|
||||
MOVB CH, AL
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// val1 := br0.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v1 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br0.advance(uint8(v1.entry)
|
||||
MOVB CH, AH
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
BSWAPL AX
|
||||
|
||||
// val2 := br0.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v2 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br0.advance(uint8(v2.entry)
|
||||
MOVB CH, AH
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// val3 := br0.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v3 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br0.advance(uint8(v3.entry)
|
||||
MOVB CH, AL
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
BSWAPL AX
|
||||
|
||||
// these four writes get coalesced
|
||||
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
|
||||
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
|
||||
// out[id * dstEvery + 3] = uint8(v2.entry >> 8)
|
||||
// out[id * dstEvery + 4] = uint8(v3.entry >> 8)
|
||||
MOVL AX, (BX)
|
||||
|
||||
// update the bitreader structure
|
||||
MOVQ R11, 32(R10)
|
||||
MOVB R12, 40(R10)
|
||||
|
||||
// br1.fillFast32()
|
||||
MOVQ 80(R10), R11
|
||||
MOVBQZX 88(R10), R12
|
||||
CMPQ R12, $0x20
|
||||
JBE skip_fill1
|
||||
MOVQ 72(R10), R13
|
||||
SUBQ $0x20, R12
|
||||
SUBQ $0x04, R13
|
||||
MOVQ 48(R10), R14
|
||||
|
||||
// b.value |= uint64(low) << (b.bitsRead & 63)
|
||||
MOVL (R13)(R14*1), R14
|
||||
MOVQ R12, CX
|
||||
SHLQ CL, R14
|
||||
MOVQ R13, 72(R10)
|
||||
ORQ R14, R11
|
||||
|
||||
// exhausted += (br1.off < 4)
|
||||
CMPQ R13, $0x04
|
||||
ADCB $+0, DL
|
||||
|
||||
skip_fill1:
|
||||
// val0 := br1.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v0 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br1.advance(uint8(v0.entry)
|
||||
MOVB CH, AL
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// val1 := br1.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v1 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br1.advance(uint8(v1.entry)
|
||||
MOVB CH, AH
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
BSWAPL AX
|
||||
|
||||
// val2 := br1.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v2 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br1.advance(uint8(v2.entry)
|
||||
MOVB CH, AH
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// val3 := br1.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v3 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br1.advance(uint8(v3.entry)
|
||||
MOVB CH, AL
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
BSWAPL AX
|
||||
|
||||
// these four writes get coalesced
|
||||
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
|
||||
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
|
||||
// out[id * dstEvery + 3] = uint8(v2.entry >> 8)
|
||||
// out[id * dstEvery + 4] = uint8(v3.entry >> 8)
|
||||
MOVL AX, (BX)(R8*1)
|
||||
|
||||
// update the bitreader structure
|
||||
MOVQ R11, 80(R10)
|
||||
MOVB R12, 88(R10)
|
||||
|
||||
// br2.fillFast32()
|
||||
MOVQ 128(R10), R11
|
||||
MOVBQZX 136(R10), R12
|
||||
CMPQ R12, $0x20
|
||||
JBE skip_fill2
|
||||
MOVQ 120(R10), R13
|
||||
SUBQ $0x20, R12
|
||||
SUBQ $0x04, R13
|
||||
MOVQ 96(R10), R14
|
||||
|
||||
// b.value |= uint64(low) << (b.bitsRead & 63)
|
||||
MOVL (R13)(R14*1), R14
|
||||
MOVQ R12, CX
|
||||
SHLQ CL, R14
|
||||
MOVQ R13, 120(R10)
|
||||
ORQ R14, R11
|
||||
|
||||
// exhausted += (br2.off < 4)
|
||||
CMPQ R13, $0x04
|
||||
ADCB $+0, DL
|
||||
|
||||
skip_fill2:
|
||||
// val0 := br2.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v0 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br2.advance(uint8(v0.entry)
|
||||
MOVB CH, AL
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// val1 := br2.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v1 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br2.advance(uint8(v1.entry)
|
||||
MOVB CH, AH
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
BSWAPL AX
|
||||
|
||||
// val2 := br2.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v2 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br2.advance(uint8(v2.entry)
|
||||
MOVB CH, AH
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// val3 := br2.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v3 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br2.advance(uint8(v3.entry)
|
||||
MOVB CH, AL
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
BSWAPL AX
|
||||
|
||||
// these four writes get coalesced
|
||||
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
|
||||
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
|
||||
// out[id * dstEvery + 3] = uint8(v2.entry >> 8)
|
||||
// out[id * dstEvery + 4] = uint8(v3.entry >> 8)
|
||||
MOVL AX, (BX)(R8*2)
|
||||
|
||||
// update the bitreader structure
|
||||
MOVQ R11, 128(R10)
|
||||
MOVB R12, 136(R10)
|
||||
|
||||
// br3.fillFast32()
|
||||
MOVQ 176(R10), R11
|
||||
MOVBQZX 184(R10), R12
|
||||
CMPQ R12, $0x20
|
||||
JBE skip_fill3
|
||||
MOVQ 168(R10), R13
|
||||
SUBQ $0x20, R12
|
||||
SUBQ $0x04, R13
|
||||
MOVQ 144(R10), R14
|
||||
|
||||
// b.value |= uint64(low) << (b.bitsRead & 63)
|
||||
MOVL (R13)(R14*1), R14
|
||||
MOVQ R12, CX
|
||||
SHLQ CL, R14
|
||||
MOVQ R13, 168(R10)
|
||||
ORQ R14, R11
|
||||
|
||||
// exhausted += (br3.off < 4)
|
||||
CMPQ R13, $0x04
|
||||
ADCB $+0, DL
|
||||
|
||||
skip_fill3:
|
||||
// val0 := br3.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v0 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br3.advance(uint8(v0.entry)
|
||||
MOVB CH, AL
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// val1 := br3.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v1 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br3.advance(uint8(v1.entry)
|
||||
MOVB CH, AH
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
BSWAPL AX
|
||||
|
||||
// val2 := br3.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v2 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br3.advance(uint8(v2.entry)
|
||||
MOVB CH, AH
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
|
||||
// val3 := br3.peekTopBits(peekBits)
|
||||
MOVQ R11, R13
|
||||
MOVQ DI, CX
|
||||
SHRQ CL, R13
|
||||
|
||||
// v3 := table[val0&mask]
|
||||
MOVW (R9)(R13*2), CX
|
||||
|
||||
// br3.advance(uint8(v3.entry)
|
||||
MOVB CH, AL
|
||||
SHLQ CL, R11
|
||||
ADDB CL, R12
|
||||
BSWAPL AX
|
||||
|
||||
// these four writes get coalesced
|
||||
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
|
||||
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
|
||||
// out[id * dstEvery + 3] = uint8(v2.entry >> 8)
|
||||
// out[id * dstEvery + 4] = uint8(v3.entry >> 8)
|
||||
LEAQ (R8)(R8*2), CX
|
||||
MOVL AX, (BX)(CX*1)
|
||||
|
||||
// update the bitreader structure
|
||||
MOVQ R11, 176(R10)
|
||||
MOVB R12, 184(R10)
|
||||
ADDQ $0x04, BX
|
||||
TESTB DL, DL
|
||||
JZ main_loop
|
||||
MOVQ ctx+0(FP), AX
|
||||
SUBQ 16(AX), BX
|
||||
SHLQ $0x02, BX
|
||||
MOVQ BX, 40(AX)
|
||||
RET
|
||||
|
||||
// func decompress1x_main_loop_amd64(ctx *decompress1xContext)
|
||||
TEXT ·decompress1x_main_loop_amd64(SB), $0-8
|
||||
MOVQ ctx+0(FP), CX
|
||||
MOVQ 16(CX), DX
|
||||
MOVQ 24(CX), BX
|
||||
CMPQ BX, $0x04
|
||||
JB error_max_decoded_size_exceeded
|
||||
LEAQ (DX)(BX*1), BX
|
||||
MOVQ (CX), SI
|
||||
MOVQ (SI), R8
|
||||
MOVQ 24(SI), R9
|
||||
MOVQ 32(SI), R10
|
||||
MOVBQZX 40(SI), R11
|
||||
MOVQ 32(CX), SI
|
||||
MOVBQZX 8(CX), DI
|
||||
JMP loop_condition
|
||||
|
||||
main_loop:
|
||||
// Check if we have room for 4 bytes in the output buffer
|
||||
LEAQ 4(DX), CX
|
||||
CMPQ CX, BX
|
||||
JGE error_max_decoded_size_exceeded
|
||||
|
||||
// Decode 4 values
|
||||
CMPQ R11, $0x20
|
||||
JL bitReader_fillFast_1_end
|
||||
SUBQ $0x20, R11
|
||||
SUBQ $0x04, R9
|
||||
MOVL (R8)(R9*1), R12
|
||||
MOVQ R11, CX
|
||||
SHLQ CL, R12
|
||||
ORQ R12, R10
|
||||
|
||||
bitReader_fillFast_1_end:
|
||||
MOVQ DI, CX
|
||||
MOVQ R10, R12
|
||||
SHRQ CL, R12
|
||||
MOVW (SI)(R12*2), CX
|
||||
MOVB CH, AL
|
||||
MOVBQZX CL, CX
|
||||
ADDQ CX, R11
|
||||
SHLQ CL, R10
|
||||
MOVQ DI, CX
|
||||
MOVQ R10, R12
|
||||
SHRQ CL, R12
|
||||
MOVW (SI)(R12*2), CX
|
||||
MOVB CH, AH
|
||||
MOVBQZX CL, CX
|
||||
ADDQ CX, R11
|
||||
SHLQ CL, R10
|
||||
BSWAPL AX
|
||||
CMPQ R11, $0x20
|
||||
JL bitReader_fillFast_2_end
|
||||
SUBQ $0x20, R11
|
||||
SUBQ $0x04, R9
|
||||
MOVL (R8)(R9*1), R12
|
||||
MOVQ R11, CX
|
||||
SHLQ CL, R12
|
||||
ORQ R12, R10
|
||||
|
||||
bitReader_fillFast_2_end:
|
||||
MOVQ DI, CX
|
||||
MOVQ R10, R12
|
||||
SHRQ CL, R12
|
||||
MOVW (SI)(R12*2), CX
|
||||
MOVB CH, AH
|
||||
MOVBQZX CL, CX
|
||||
ADDQ CX, R11
|
||||
SHLQ CL, R10
|
||||
MOVQ DI, CX
|
||||
MOVQ R10, R12
|
||||
SHRQ CL, R12
|
||||
MOVW (SI)(R12*2), CX
|
||||
MOVB CH, AL
|
||||
MOVBQZX CL, CX
|
||||
ADDQ CX, R11
|
||||
SHLQ CL, R10
|
||||
BSWAPL AX
|
||||
|
||||
// Store the decoded values
|
||||
MOVL AX, (DX)
|
||||
ADDQ $0x04, DX
|
||||
|
||||
loop_condition:
|
||||
CMPQ R9, $0x08
|
||||
JGE main_loop
|
||||
|
||||
// Update ctx structure
|
||||
MOVQ ctx+0(FP), AX
|
||||
SUBQ 16(AX), DX
|
||||
MOVQ DX, 40(AX)
|
||||
MOVQ (AX), AX
|
||||
MOVQ R9, 24(AX)
|
||||
MOVQ R10, 32(AX)
|
||||
MOVB R11, 40(AX)
|
||||
RET
|
||||
|
||||
// Report error
|
||||
error_max_decoded_size_exceeded:
|
||||
MOVQ ctx+0(FP), AX
|
||||
MOVQ $-1, CX
|
||||
MOVQ CX, 40(AX)
|
||||
RET
|
||||
|
||||
// func decompress1x_main_loop_bmi2(ctx *decompress1xContext)
|
||||
// Requires: BMI2
|
||||
TEXT ·decompress1x_main_loop_bmi2(SB), $0-8
|
||||
MOVQ ctx+0(FP), CX
|
||||
MOVQ 16(CX), DX
|
||||
MOVQ 24(CX), BX
|
||||
CMPQ BX, $0x04
|
||||
JB error_max_decoded_size_exceeded
|
||||
LEAQ (DX)(BX*1), BX
|
||||
MOVQ (CX), SI
|
||||
MOVQ (SI), R8
|
||||
MOVQ 24(SI), R9
|
||||
MOVQ 32(SI), R10
|
||||
MOVBQZX 40(SI), R11
|
||||
MOVQ 32(CX), SI
|
||||
MOVBQZX 8(CX), DI
|
||||
JMP loop_condition
|
||||
|
||||
main_loop:
|
||||
// Check if we have room for 4 bytes in the output buffer
|
||||
LEAQ 4(DX), CX
|
||||
CMPQ CX, BX
|
||||
JGE error_max_decoded_size_exceeded
|
||||
|
||||
// Decode 4 values
|
||||
CMPQ R11, $0x20
|
||||
JL bitReader_fillFast_1_end
|
||||
SUBQ $0x20, R11
|
||||
SUBQ $0x04, R9
|
||||
MOVL (R8)(R9*1), CX
|
||||
SHLXQ R11, CX, CX
|
||||
ORQ CX, R10
|
||||
|
||||
bitReader_fillFast_1_end:
|
||||
SHRXQ DI, R10, CX
|
||||
MOVW (SI)(CX*2), CX
|
||||
MOVB CH, AL
|
||||
MOVBQZX CL, CX
|
||||
ADDQ CX, R11
|
||||
SHLXQ CX, R10, R10
|
||||
SHRXQ DI, R10, CX
|
||||
MOVW (SI)(CX*2), CX
|
||||
MOVB CH, AH
|
||||
MOVBQZX CL, CX
|
||||
ADDQ CX, R11
|
||||
SHLXQ CX, R10, R10
|
||||
BSWAPL AX
|
||||
CMPQ R11, $0x20
|
||||
JL bitReader_fillFast_2_end
|
||||
SUBQ $0x20, R11
|
||||
SUBQ $0x04, R9
|
||||
MOVL (R8)(R9*1), CX
|
||||
SHLXQ R11, CX, CX
|
||||
ORQ CX, R10
|
||||
|
||||
bitReader_fillFast_2_end:
|
||||
SHRXQ DI, R10, CX
|
||||
MOVW (SI)(CX*2), CX
|
||||
MOVB CH, AH
|
||||
MOVBQZX CL, CX
|
||||
ADDQ CX, R11
|
||||
SHLXQ CX, R10, R10
|
||||
SHRXQ DI, R10, CX
|
||||
MOVW (SI)(CX*2), CX
|
||||
MOVB CH, AL
|
||||
MOVBQZX CL, CX
|
||||
ADDQ CX, R11
|
||||
SHLXQ CX, R10, R10
|
||||
BSWAPL AX
|
||||
|
||||
// Store the decoded values
|
||||
MOVL AX, (DX)
|
||||
ADDQ $0x04, DX
|
||||
|
||||
loop_condition:
|
||||
CMPQ R9, $0x08
|
||||
JGE main_loop
|
||||
|
||||
// Update ctx structure
|
||||
MOVQ ctx+0(FP), AX
|
||||
SUBQ 16(AX), DX
|
||||
MOVQ DX, 40(AX)
|
||||
MOVQ (AX), AX
|
||||
MOVQ R9, 24(AX)
|
||||
MOVQ R10, 32(AX)
|
||||
MOVB R11, 40(AX)
|
||||
RET
|
||||
|
||||
// Report error
|
||||
error_max_decoded_size_exceeded:
|
||||
MOVQ ctx+0(FP), AX
|
||||
MOVQ $-1, CX
|
||||
MOVQ CX, 40(AX)
|
||||
RET
|
||||
299
vendor/github.com/klauspost/compress/huff0/decompress_generic.go
generated
vendored
299
vendor/github.com/klauspost/compress/huff0/decompress_generic.go
generated
vendored
@ -1,299 +0,0 @@
|
||||
//go:build !amd64 || appengine || !gc || noasm
|
||||
// +build !amd64 appengine !gc noasm
|
||||
|
||||
// This file contains a generic implementation of Decoder.Decompress4X.
|
||||
package huff0
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
)
|
||||
|
||||
// Decompress4X will decompress a 4X encoded stream.
|
||||
// The length of the supplied input must match the end of a block exactly.
|
||||
// The *capacity* of the dst slice must match the destination size of
|
||||
// the uncompressed data exactly.
|
||||
func (d *Decoder) Decompress4X(dst, src []byte) ([]byte, error) {
|
||||
if len(d.dt.single) == 0 {
|
||||
return nil, errors.New("no table loaded")
|
||||
}
|
||||
if len(src) < 6+(4*1) {
|
||||
return nil, errors.New("input too small")
|
||||
}
|
||||
if use8BitTables && d.actualTableLog <= 8 {
|
||||
return d.decompress4X8bit(dst, src)
|
||||
}
|
||||
|
||||
var br [4]bitReaderShifted
|
||||
// Decode "jump table"
|
||||
start := 6
|
||||
for i := 0; i < 3; i++ {
|
||||
length := int(src[i*2]) | (int(src[i*2+1]) << 8)
|
||||
if start+length >= len(src) {
|
||||
return nil, errors.New("truncated input (or invalid offset)")
|
||||
}
|
||||
err := br[i].init(src[start : start+length])
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
start += length
|
||||
}
|
||||
err := br[3].init(src[start:])
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
// destination, offset to match first output
|
||||
dstSize := cap(dst)
|
||||
dst = dst[:dstSize]
|
||||
out := dst
|
||||
dstEvery := (dstSize + 3) / 4
|
||||
|
||||
const tlSize = 1 << tableLogMax
|
||||
const tlMask = tlSize - 1
|
||||
single := d.dt.single[:tlSize]
|
||||
|
||||
// Use temp table to avoid bound checks/append penalty.
|
||||
buf := d.buffer()
|
||||
var off uint8
|
||||
var decoded int
|
||||
|
||||
// Decode 2 values from each decoder/loop.
|
||||
const bufoff = 256
|
||||
for {
|
||||
if br[0].off < 4 || br[1].off < 4 || br[2].off < 4 || br[3].off < 4 {
|
||||
break
|
||||
}
|
||||
|
||||
{
|
||||
const stream = 0
|
||||
const stream2 = 1
|
||||
br[stream].fillFast()
|
||||
br[stream2].fillFast()
|
||||
|
||||
val := br[stream].peekBitsFast(d.actualTableLog)
|
||||
val2 := br[stream2].peekBitsFast(d.actualTableLog)
|
||||
v := single[val&tlMask]
|
||||
v2 := single[val2&tlMask]
|
||||
br[stream].advance(uint8(v.entry))
|
||||
br[stream2].advance(uint8(v2.entry))
|
||||
buf[stream][off] = uint8(v.entry >> 8)
|
||||
buf[stream2][off] = uint8(v2.entry >> 8)
|
||||
|
||||
val = br[stream].peekBitsFast(d.actualTableLog)
|
||||
val2 = br[stream2].peekBitsFast(d.actualTableLog)
|
||||
v = single[val&tlMask]
|
||||
v2 = single[val2&tlMask]
|
||||
br[stream].advance(uint8(v.entry))
|
||||
br[stream2].advance(uint8(v2.entry))
|
||||
buf[stream][off+1] = uint8(v.entry >> 8)
|
||||
buf[stream2][off+1] = uint8(v2.entry >> 8)
|
||||
}
|
||||
|
||||
{
|
||||
const stream = 2
|
||||
const stream2 = 3
|
||||
br[stream].fillFast()
|
||||
br[stream2].fillFast()
|
||||
|
||||
val := br[stream].peekBitsFast(d.actualTableLog)
|
||||
val2 := br[stream2].peekBitsFast(d.actualTableLog)
|
||||
v := single[val&tlMask]
|
||||
v2 := single[val2&tlMask]
|
||||
br[stream].advance(uint8(v.entry))
|
||||
br[stream2].advance(uint8(v2.entry))
|
||||
buf[stream][off] = uint8(v.entry >> 8)
|
||||
buf[stream2][off] = uint8(v2.entry >> 8)
|
||||
|
||||
val = br[stream].peekBitsFast(d.actualTableLog)
|
||||
val2 = br[stream2].peekBitsFast(d.actualTableLog)
|
||||
v = single[val&tlMask]
|
||||
v2 = single[val2&tlMask]
|
||||
br[stream].advance(uint8(v.entry))
|
||||
br[stream2].advance(uint8(v2.entry))
|
||||
buf[stream][off+1] = uint8(v.entry >> 8)
|
||||
buf[stream2][off+1] = uint8(v2.entry >> 8)
|
||||
}
|
||||
|
||||
off += 2
|
||||
|
||||
if off == 0 {
|
||||
if bufoff > dstEvery {
|
||||
d.bufs.Put(buf)
|
||||
return nil, errors.New("corruption detected: stream overrun 1")
|
||||
}
|
||||
// There must at least be 3 buffers left.
|
||||
if len(out)-bufoff < dstEvery*3 {
|
||||
d.bufs.Put(buf)
|
||||
return nil, errors.New("corruption detected: stream overrun 2")
|
||||
}
|
||||
//copy(out, buf[0][:])
|
||||
//copy(out[dstEvery:], buf[1][:])
|
||||
//copy(out[dstEvery*2:], buf[2][:])
|
||||
//copy(out[dstEvery*3:], buf[3][:])
|
||||
*(*[bufoff]byte)(out) = buf[0]
|
||||
*(*[bufoff]byte)(out[dstEvery:]) = buf[1]
|
||||
*(*[bufoff]byte)(out[dstEvery*2:]) = buf[2]
|
||||
*(*[bufoff]byte)(out[dstEvery*3:]) = buf[3]
|
||||
out = out[bufoff:]
|
||||
decoded += bufoff * 4
|
||||
}
|
||||
}
|
||||
if off > 0 {
|
||||
ioff := int(off)
|
||||
if len(out) < dstEvery*3+ioff {
|
||||
d.bufs.Put(buf)
|
||||
return nil, errors.New("corruption detected: stream overrun 3")
|
||||
}
|
||||
copy(out, buf[0][:off])
|
||||
copy(out[dstEvery:], buf[1][:off])
|
||||
copy(out[dstEvery*2:], buf[2][:off])
|
||||
copy(out[dstEvery*3:], buf[3][:off])
|
||||
decoded += int(off) * 4
|
||||
out = out[off:]
|
||||
}
|
||||
|
||||
// Decode remaining.
|
||||
remainBytes := dstEvery - (decoded / 4)
|
||||
for i := range br {
|
||||
offset := dstEvery * i
|
||||
endsAt := offset + remainBytes
|
||||
if endsAt > len(out) {
|
||||
endsAt = len(out)
|
||||
}
|
||||
br := &br[i]
|
||||
bitsLeft := br.remaining()
|
||||
for bitsLeft > 0 {
|
||||
br.fill()
|
||||
if offset >= endsAt {
|
||||
d.bufs.Put(buf)
|
||||
return nil, errors.New("corruption detected: stream overrun 4")
|
||||
}
|
||||
|
||||
// Read value and increment offset.
|
||||
val := br.peekBitsFast(d.actualTableLog)
|
||||
v := single[val&tlMask].entry
|
||||
nBits := uint8(v)
|
||||
br.advance(nBits)
|
||||
bitsLeft -= uint(nBits)
|
||||
out[offset] = uint8(v >> 8)
|
||||
offset++
|
||||
}
|
||||
if offset != endsAt {
|
||||
d.bufs.Put(buf)
|
||||
return nil, fmt.Errorf("corruption detected: short output block %d, end %d != %d", i, offset, endsAt)
|
||||
}
|
||||
decoded += offset - dstEvery*i
|
||||
err = br.close()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
d.bufs.Put(buf)
|
||||
if dstSize != decoded {
|
||||
return nil, errors.New("corruption detected: short output block")
|
||||
}
|
||||
return dst, nil
|
||||
}
|
||||
|
||||
// Decompress1X will decompress a 1X encoded stream.
|
||||
// The cap of the output buffer will be the maximum decompressed size.
|
||||
// The length of the supplied input must match the end of a block exactly.
|
||||
func (d *Decoder) Decompress1X(dst, src []byte) ([]byte, error) {
|
||||
if len(d.dt.single) == 0 {
|
||||
return nil, errors.New("no table loaded")
|
||||
}
|
||||
if use8BitTables && d.actualTableLog <= 8 {
|
||||
return d.decompress1X8Bit(dst, src)
|
||||
}
|
||||
var br bitReaderShifted
|
||||
err := br.init(src)
|
||||
if err != nil {
|
||||
return dst, err
|
||||
}
|
||||
maxDecodedSize := cap(dst)
|
||||
dst = dst[:0]
|
||||
|
||||
// Avoid bounds check by always having full sized table.
|
||||
const tlSize = 1 << tableLogMax
|
||||
const tlMask = tlSize - 1
|
||||
dt := d.dt.single[:tlSize]
|
||||
|
||||
// Use temp table to avoid bound checks/append penalty.
|
||||
bufs := d.buffer()
|
||||
buf := &bufs[0]
|
||||
var off uint8
|
||||
|
||||
for br.off >= 8 {
|
||||
br.fillFast()
|
||||
v := dt[br.peekBitsFast(d.actualTableLog)&tlMask]
|
||||
br.advance(uint8(v.entry))
|
||||
buf[off+0] = uint8(v.entry >> 8)
|
||||
|
||||
v = dt[br.peekBitsFast(d.actualTableLog)&tlMask]
|
||||
br.advance(uint8(v.entry))
|
||||
buf[off+1] = uint8(v.entry >> 8)
|
||||
|
||||
// Refill
|
||||
br.fillFast()
|
||||
|
||||
v = dt[br.peekBitsFast(d.actualTableLog)&tlMask]
|
||||
br.advance(uint8(v.entry))
|
||||
buf[off+2] = uint8(v.entry >> 8)
|
||||
|
||||
v = dt[br.peekBitsFast(d.actualTableLog)&tlMask]
|
||||
br.advance(uint8(v.entry))
|
||||
buf[off+3] = uint8(v.entry >> 8)
|
||||
|
||||
off += 4
|
||||
if off == 0 {
|
||||
if len(dst)+256 > maxDecodedSize {
|
||||
br.close()
|
||||
d.bufs.Put(bufs)
|
||||
return nil, ErrMaxDecodedSizeExceeded
|
||||
}
|
||||
dst = append(dst, buf[:]...)
|
||||
}
|
||||
}
|
||||
|
||||
if len(dst)+int(off) > maxDecodedSize {
|
||||
d.bufs.Put(bufs)
|
||||
br.close()
|
||||
return nil, ErrMaxDecodedSizeExceeded
|
||||
}
|
||||
dst = append(dst, buf[:off]...)
|
||||
|
||||
// br < 8, so uint8 is fine
|
||||
bitsLeft := uint8(br.off)*8 + 64 - br.bitsRead
|
||||
for bitsLeft > 0 {
|
||||
br.fill()
|
||||
if false && br.bitsRead >= 32 {
|
||||
if br.off >= 4 {
|
||||
v := br.in[br.off-4:]
|
||||
v = v[:4]
|
||||
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
|
||||
br.value = (br.value << 32) | uint64(low)
|
||||
br.bitsRead -= 32
|
||||
br.off -= 4
|
||||
} else {
|
||||
for br.off > 0 {
|
||||
br.value = (br.value << 8) | uint64(br.in[br.off-1])
|
||||
br.bitsRead -= 8
|
||||
br.off--
|
||||
}
|
||||
}
|
||||
}
|
||||
if len(dst) >= maxDecodedSize {
|
||||
d.bufs.Put(bufs)
|
||||
br.close()
|
||||
return nil, ErrMaxDecodedSizeExceeded
|
||||
}
|
||||
v := d.dt.single[br.peekBitsFast(d.actualTableLog)&tlMask]
|
||||
nBits := uint8(v.entry)
|
||||
br.advance(nBits)
|
||||
bitsLeft -= nBits
|
||||
dst = append(dst, uint8(v.entry>>8))
|
||||
}
|
||||
d.bufs.Put(bufs)
|
||||
return dst, br.close()
|
||||
}
|
||||
337
vendor/github.com/klauspost/compress/huff0/huff0.go
generated
vendored
337
vendor/github.com/klauspost/compress/huff0/huff0.go
generated
vendored
@ -1,337 +0,0 @@
|
||||
// Package huff0 provides fast huffman encoding as used in zstd.
|
||||
//
|
||||
// See README.md at https://github.com/klauspost/compress/tree/master/huff0 for details.
|
||||
package huff0
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"math"
|
||||
"math/bits"
|
||||
"sync"
|
||||
|
||||
"github.com/klauspost/compress/fse"
|
||||
)
|
||||
|
||||
const (
|
||||
maxSymbolValue = 255
|
||||
|
||||
// zstandard limits tablelog to 11, see:
|
||||
// https://github.com/facebook/zstd/blob/dev/doc/zstd_compression_format.md#huffman-tree-description
|
||||
tableLogMax = 11
|
||||
tableLogDefault = 11
|
||||
minTablelog = 5
|
||||
huffNodesLen = 512
|
||||
|
||||
// BlockSizeMax is maximum input size for a single block uncompressed.
|
||||
BlockSizeMax = 1<<18 - 1
|
||||
)
|
||||
|
||||
var (
|
||||
// ErrIncompressible is returned when input is judged to be too hard to compress.
|
||||
ErrIncompressible = errors.New("input is not compressible")
|
||||
|
||||
// ErrUseRLE is returned from the compressor when the input is a single byte value repeated.
|
||||
ErrUseRLE = errors.New("input is single value repeated")
|
||||
|
||||
// ErrTooBig is return if input is too large for a single block.
|
||||
ErrTooBig = errors.New("input too big")
|
||||
|
||||
// ErrMaxDecodedSizeExceeded is return if input is too large for a single block.
|
||||
ErrMaxDecodedSizeExceeded = errors.New("maximum output size exceeded")
|
||||
)
|
||||
|
||||
type ReusePolicy uint8
|
||||
|
||||
const (
|
||||
// ReusePolicyAllow will allow reuse if it produces smaller output.
|
||||
ReusePolicyAllow ReusePolicy = iota
|
||||
|
||||
// ReusePolicyPrefer will re-use aggressively if possible.
|
||||
// This will not check if a new table will produce smaller output,
|
||||
// except if the current table is impossible to use or
|
||||
// compressed output is bigger than input.
|
||||
ReusePolicyPrefer
|
||||
|
||||
// ReusePolicyNone will disable re-use of tables.
|
||||
// This is slightly faster than ReusePolicyAllow but may produce larger output.
|
||||
ReusePolicyNone
|
||||
|
||||
// ReusePolicyMust must allow reuse and produce smaller output.
|
||||
ReusePolicyMust
|
||||
)
|
||||
|
||||
type Scratch struct {
|
||||
count [maxSymbolValue + 1]uint32
|
||||
|
||||
// Per block parameters.
|
||||
// These can be used to override compression parameters of the block.
|
||||
// Do not touch, unless you know what you are doing.
|
||||
|
||||
// Out is output buffer.
|
||||
// If the scratch is re-used before the caller is done processing the output,
|
||||
// set this field to nil.
|
||||
// Otherwise the output buffer will be re-used for next Compression/Decompression step
|
||||
// and allocation will be avoided.
|
||||
Out []byte
|
||||
|
||||
// OutTable will contain the table data only, if a new table has been generated.
|
||||
// Slice of the returned data.
|
||||
OutTable []byte
|
||||
|
||||
// OutData will contain the compressed data.
|
||||
// Slice of the returned data.
|
||||
OutData []byte
|
||||
|
||||
// MaxDecodedSize will set the maximum allowed output size.
|
||||
// This value will automatically be set to BlockSizeMax if not set.
|
||||
// Decoders will return ErrMaxDecodedSizeExceeded is this limit is exceeded.
|
||||
MaxDecodedSize int
|
||||
|
||||
srcLen int
|
||||
|
||||
// MaxSymbolValue will override the maximum symbol value of the next block.
|
||||
MaxSymbolValue uint8
|
||||
|
||||
// TableLog will attempt to override the tablelog for the next block.
|
||||
// Must be <= 11 and >= 5.
|
||||
TableLog uint8
|
||||
|
||||
// Reuse will specify the reuse policy
|
||||
Reuse ReusePolicy
|
||||
|
||||
// WantLogLess allows to specify a log 2 reduction that should at least be achieved,
|
||||
// otherwise the block will be returned as incompressible.
|
||||
// The reduction should then at least be (input size >> WantLogLess)
|
||||
// If WantLogLess == 0 any improvement will do.
|
||||
WantLogLess uint8
|
||||
|
||||
symbolLen uint16 // Length of active part of the symbol table.
|
||||
maxCount int // count of the most probable symbol
|
||||
clearCount bool // clear count
|
||||
actualTableLog uint8 // Selected tablelog.
|
||||
prevTableLog uint8 // Tablelog for previous table
|
||||
prevTable cTable // Table used for previous compression.
|
||||
cTable cTable // compression table
|
||||
dt dTable // decompression table
|
||||
nodes []nodeElt
|
||||
tmpOut [4][]byte
|
||||
fse *fse.Scratch
|
||||
decPool sync.Pool // *[4][256]byte buffers.
|
||||
huffWeight [maxSymbolValue + 1]byte
|
||||
}
|
||||
|
||||
// TransferCTable will transfer the previously used compression table.
|
||||
func (s *Scratch) TransferCTable(src *Scratch) {
|
||||
if cap(s.prevTable) < len(src.prevTable) {
|
||||
s.prevTable = make(cTable, 0, maxSymbolValue+1)
|
||||
}
|
||||
s.prevTable = s.prevTable[:len(src.prevTable)]
|
||||
copy(s.prevTable, src.prevTable)
|
||||
s.prevTableLog = src.prevTableLog
|
||||
}
|
||||
|
||||
func (s *Scratch) prepare(in []byte) (*Scratch, error) {
|
||||
if len(in) > BlockSizeMax {
|
||||
return nil, ErrTooBig
|
||||
}
|
||||
if s == nil {
|
||||
s = &Scratch{}
|
||||
}
|
||||
if s.MaxSymbolValue == 0 {
|
||||
s.MaxSymbolValue = maxSymbolValue
|
||||
}
|
||||
if s.TableLog == 0 {
|
||||
s.TableLog = tableLogDefault
|
||||
}
|
||||
if s.TableLog > tableLogMax || s.TableLog < minTablelog {
|
||||
return nil, fmt.Errorf(" invalid tableLog %d (%d -> %d)", s.TableLog, minTablelog, tableLogMax)
|
||||
}
|
||||
if s.MaxDecodedSize <= 0 || s.MaxDecodedSize > BlockSizeMax {
|
||||
s.MaxDecodedSize = BlockSizeMax
|
||||
}
|
||||
if s.clearCount && s.maxCount == 0 {
|
||||
for i := range s.count {
|
||||
s.count[i] = 0
|
||||
}
|
||||
s.clearCount = false
|
||||
}
|
||||
if cap(s.Out) == 0 {
|
||||
s.Out = make([]byte, 0, len(in))
|
||||
}
|
||||
s.Out = s.Out[:0]
|
||||
|
||||
s.OutTable = nil
|
||||
s.OutData = nil
|
||||
if cap(s.nodes) < huffNodesLen+1 {
|
||||
s.nodes = make([]nodeElt, 0, huffNodesLen+1)
|
||||
}
|
||||
s.nodes = s.nodes[:0]
|
||||
if s.fse == nil {
|
||||
s.fse = &fse.Scratch{}
|
||||
}
|
||||
s.srcLen = len(in)
|
||||
|
||||
return s, nil
|
||||
}
|
||||
|
||||
type cTable []cTableEntry
|
||||
|
||||
func (c cTable) write(s *Scratch) error {
|
||||
var (
|
||||
// precomputed conversion table
|
||||
bitsToWeight [tableLogMax + 1]byte
|
||||
huffLog = s.actualTableLog
|
||||
// last weight is not saved.
|
||||
maxSymbolValue = uint8(s.symbolLen - 1)
|
||||
huffWeight = s.huffWeight[:256]
|
||||
)
|
||||
const (
|
||||
maxFSETableLog = 6
|
||||
)
|
||||
// convert to weight
|
||||
bitsToWeight[0] = 0
|
||||
for n := uint8(1); n < huffLog+1; n++ {
|
||||
bitsToWeight[n] = huffLog + 1 - n
|
||||
}
|
||||
|
||||
// Acquire histogram for FSE.
|
||||
hist := s.fse.Histogram()
|
||||
hist = hist[:256]
|
||||
for i := range hist[:16] {
|
||||
hist[i] = 0
|
||||
}
|
||||
for n := uint8(0); n < maxSymbolValue; n++ {
|
||||
v := bitsToWeight[c[n].nBits] & 15
|
||||
huffWeight[n] = v
|
||||
hist[v]++
|
||||
}
|
||||
|
||||
// FSE compress if feasible.
|
||||
if maxSymbolValue >= 2 {
|
||||
huffMaxCnt := uint32(0)
|
||||
huffMax := uint8(0)
|
||||
for i, v := range hist[:16] {
|
||||
if v == 0 {
|
||||
continue
|
||||
}
|
||||
huffMax = byte(i)
|
||||
if v > huffMaxCnt {
|
||||
huffMaxCnt = v
|
||||
}
|
||||
}
|
||||
s.fse.HistogramFinished(huffMax, int(huffMaxCnt))
|
||||
s.fse.TableLog = maxFSETableLog
|
||||
b, err := fse.Compress(huffWeight[:maxSymbolValue], s.fse)
|
||||
if err == nil && len(b) < int(s.symbolLen>>1) {
|
||||
s.Out = append(s.Out, uint8(len(b)))
|
||||
s.Out = append(s.Out, b...)
|
||||
return nil
|
||||
}
|
||||
// Unable to compress (RLE/uncompressible)
|
||||
}
|
||||
// write raw values as 4-bits (max : 15)
|
||||
if maxSymbolValue > (256 - 128) {
|
||||
// should not happen : likely means source cannot be compressed
|
||||
return ErrIncompressible
|
||||
}
|
||||
op := s.Out
|
||||
// special case, pack weights 4 bits/weight.
|
||||
op = append(op, 128|(maxSymbolValue-1))
|
||||
// be sure it doesn't cause msan issue in final combination
|
||||
huffWeight[maxSymbolValue] = 0
|
||||
for n := uint16(0); n < uint16(maxSymbolValue); n += 2 {
|
||||
op = append(op, (huffWeight[n]<<4)|huffWeight[n+1])
|
||||
}
|
||||
s.Out = op
|
||||
return nil
|
||||
}
|
||||
|
||||
func (c cTable) estTableSize(s *Scratch) (sz int, err error) {
|
||||
var (
|
||||
// precomputed conversion table
|
||||
bitsToWeight [tableLogMax + 1]byte
|
||||
huffLog = s.actualTableLog
|
||||
// last weight is not saved.
|
||||
maxSymbolValue = uint8(s.symbolLen - 1)
|
||||
huffWeight = s.huffWeight[:256]
|
||||
)
|
||||
const (
|
||||
maxFSETableLog = 6
|
||||
)
|
||||
// convert to weight
|
||||
bitsToWeight[0] = 0
|
||||
for n := uint8(1); n < huffLog+1; n++ {
|
||||
bitsToWeight[n] = huffLog + 1 - n
|
||||
}
|
||||
|
||||
// Acquire histogram for FSE.
|
||||
hist := s.fse.Histogram()
|
||||
hist = hist[:256]
|
||||
for i := range hist[:16] {
|
||||
hist[i] = 0
|
||||
}
|
||||
for n := uint8(0); n < maxSymbolValue; n++ {
|
||||
v := bitsToWeight[c[n].nBits] & 15
|
||||
huffWeight[n] = v
|
||||
hist[v]++
|
||||
}
|
||||
|
||||
// FSE compress if feasible.
|
||||
if maxSymbolValue >= 2 {
|
||||
huffMaxCnt := uint32(0)
|
||||
huffMax := uint8(0)
|
||||
for i, v := range hist[:16] {
|
||||
if v == 0 {
|
||||
continue
|
||||
}
|
||||
huffMax = byte(i)
|
||||
if v > huffMaxCnt {
|
||||
huffMaxCnt = v
|
||||
}
|
||||
}
|
||||
s.fse.HistogramFinished(huffMax, int(huffMaxCnt))
|
||||
s.fse.TableLog = maxFSETableLog
|
||||
b, err := fse.Compress(huffWeight[:maxSymbolValue], s.fse)
|
||||
if err == nil && len(b) < int(s.symbolLen>>1) {
|
||||
sz += 1 + len(b)
|
||||
return sz, nil
|
||||
}
|
||||
// Unable to compress (RLE/uncompressible)
|
||||
}
|
||||
// write raw values as 4-bits (max : 15)
|
||||
if maxSymbolValue > (256 - 128) {
|
||||
// should not happen : likely means source cannot be compressed
|
||||
return 0, ErrIncompressible
|
||||
}
|
||||
// special case, pack weights 4 bits/weight.
|
||||
sz += 1 + int(maxSymbolValue/2)
|
||||
return sz, nil
|
||||
}
|
||||
|
||||
// estimateSize returns the estimated size in bytes of the input represented in the
|
||||
// histogram supplied.
|
||||
func (c cTable) estimateSize(hist []uint32) int {
|
||||
nbBits := uint32(7)
|
||||
for i, v := range c[:len(hist)] {
|
||||
nbBits += uint32(v.nBits) * hist[i]
|
||||
}
|
||||
return int(nbBits >> 3)
|
||||
}
|
||||
|
||||
// minSize returns the minimum possible size considering the shannon limit.
|
||||
func (s *Scratch) minSize(total int) int {
|
||||
nbBits := float64(7)
|
||||
fTotal := float64(total)
|
||||
for _, v := range s.count[:s.symbolLen] {
|
||||
n := float64(v)
|
||||
if n > 0 {
|
||||
nbBits += math.Log2(fTotal/n) * n
|
||||
}
|
||||
}
|
||||
return int(nbBits) >> 3
|
||||
}
|
||||
|
||||
func highBit32(val uint32) (n uint32) {
|
||||
return uint32(bits.Len32(val) - 1)
|
||||
}
|
||||
34
vendor/github.com/klauspost/compress/internal/cpuinfo/cpuinfo.go
generated
vendored
34
vendor/github.com/klauspost/compress/internal/cpuinfo/cpuinfo.go
generated
vendored
@ -1,34 +0,0 @@
|
||||
// Package cpuinfo gives runtime info about the current CPU.
|
||||
//
|
||||
// This is a very limited module meant for use internally
|
||||
// in this project. For more versatile solution check
|
||||
// https://github.com/klauspost/cpuid.
|
||||
package cpuinfo
|
||||
|
||||
// HasBMI1 checks whether an x86 CPU supports the BMI1 extension.
|
||||
func HasBMI1() bool {
|
||||
return hasBMI1
|
||||
}
|
||||
|
||||
// HasBMI2 checks whether an x86 CPU supports the BMI2 extension.
|
||||
func HasBMI2() bool {
|
||||
return hasBMI2
|
||||
}
|
||||
|
||||
// DisableBMI2 will disable BMI2, for testing purposes.
|
||||
// Call returned function to restore previous state.
|
||||
func DisableBMI2() func() {
|
||||
old := hasBMI2
|
||||
hasBMI2 = false
|
||||
return func() {
|
||||
hasBMI2 = old
|
||||
}
|
||||
}
|
||||
|
||||
// HasBMI checks whether an x86 CPU supports both BMI1 and BMI2 extensions.
|
||||
func HasBMI() bool {
|
||||
return HasBMI1() && HasBMI2()
|
||||
}
|
||||
|
||||
var hasBMI1 bool
|
||||
var hasBMI2 bool
|
||||
11
vendor/github.com/klauspost/compress/internal/cpuinfo/cpuinfo_amd64.go
generated
vendored
11
vendor/github.com/klauspost/compress/internal/cpuinfo/cpuinfo_amd64.go
generated
vendored
@ -1,11 +0,0 @@
|
||||
//go:build amd64 && !appengine && !noasm && gc
|
||||
// +build amd64,!appengine,!noasm,gc
|
||||
|
||||
package cpuinfo
|
||||
|
||||
// go:noescape
|
||||
func x86extensions() (bmi1, bmi2 bool)
|
||||
|
||||
func init() {
|
||||
hasBMI1, hasBMI2 = x86extensions()
|
||||
}
|
||||
36
vendor/github.com/klauspost/compress/internal/cpuinfo/cpuinfo_amd64.s
generated
vendored
36
vendor/github.com/klauspost/compress/internal/cpuinfo/cpuinfo_amd64.s
generated
vendored
@ -1,36 +0,0 @@
|
||||
// +build !appengine
|
||||
// +build gc
|
||||
// +build !noasm
|
||||
|
||||
#include "textflag.h"
|
||||
#include "funcdata.h"
|
||||
#include "go_asm.h"
|
||||
|
||||
TEXT ·x86extensions(SB), NOSPLIT, $0
|
||||
// 1. determine max EAX value
|
||||
XORQ AX, AX
|
||||
CPUID
|
||||
|
||||
CMPQ AX, $7
|
||||
JB unsupported
|
||||
|
||||
// 2. EAX = 7, ECX = 0 --- see Table 3-8 "Information Returned by CPUID Instruction"
|
||||
MOVQ $7, AX
|
||||
MOVQ $0, CX
|
||||
CPUID
|
||||
|
||||
BTQ $3, BX // bit 3 = BMI1
|
||||
SETCS AL
|
||||
|
||||
BTQ $8, BX // bit 8 = BMI2
|
||||
SETCS AH
|
||||
|
||||
MOVB AL, bmi1+0(FP)
|
||||
MOVB AH, bmi2+1(FP)
|
||||
RET
|
||||
|
||||
unsupported:
|
||||
XORQ AX, AX
|
||||
MOVB AL, bmi1+0(FP)
|
||||
MOVB AL, bmi2+1(FP)
|
||||
RET
|
||||
27
vendor/github.com/klauspost/compress/internal/snapref/LICENSE
generated
vendored
27
vendor/github.com/klauspost/compress/internal/snapref/LICENSE
generated
vendored
@ -1,27 +0,0 @@
|
||||
Copyright (c) 2011 The Snappy-Go Authors. All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
* Neither the name of Google Inc. nor the names of its
|
||||
contributors may be used to endorse or promote products derived from
|
||||
this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
264
vendor/github.com/klauspost/compress/internal/snapref/decode.go
generated
vendored
264
vendor/github.com/klauspost/compress/internal/snapref/decode.go
generated
vendored
@ -1,264 +0,0 @@
|
||||
// Copyright 2011 The Snappy-Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
package snapref
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
"io"
|
||||
)
|
||||
|
||||
var (
|
||||
// ErrCorrupt reports that the input is invalid.
|
||||
ErrCorrupt = errors.New("snappy: corrupt input")
|
||||
// ErrTooLarge reports that the uncompressed length is too large.
|
||||
ErrTooLarge = errors.New("snappy: decoded block is too large")
|
||||
// ErrUnsupported reports that the input isn't supported.
|
||||
ErrUnsupported = errors.New("snappy: unsupported input")
|
||||
|
||||
errUnsupportedLiteralLength = errors.New("snappy: unsupported literal length")
|
||||
)
|
||||
|
||||
// DecodedLen returns the length of the decoded block.
|
||||
func DecodedLen(src []byte) (int, error) {
|
||||
v, _, err := decodedLen(src)
|
||||
return v, err
|
||||
}
|
||||
|
||||
// decodedLen returns the length of the decoded block and the number of bytes
|
||||
// that the length header occupied.
|
||||
func decodedLen(src []byte) (blockLen, headerLen int, err error) {
|
||||
v, n := binary.Uvarint(src)
|
||||
if n <= 0 || v > 0xffffffff {
|
||||
return 0, 0, ErrCorrupt
|
||||
}
|
||||
|
||||
const wordSize = 32 << (^uint(0) >> 32 & 1)
|
||||
if wordSize == 32 && v > 0x7fffffff {
|
||||
return 0, 0, ErrTooLarge
|
||||
}
|
||||
return int(v), n, nil
|
||||
}
|
||||
|
||||
const (
|
||||
decodeErrCodeCorrupt = 1
|
||||
decodeErrCodeUnsupportedLiteralLength = 2
|
||||
)
|
||||
|
||||
// Decode returns the decoded form of src. The returned slice may be a sub-
|
||||
// slice of dst if dst was large enough to hold the entire decoded block.
|
||||
// Otherwise, a newly allocated slice will be returned.
|
||||
//
|
||||
// The dst and src must not overlap. It is valid to pass a nil dst.
|
||||
//
|
||||
// Decode handles the Snappy block format, not the Snappy stream format.
|
||||
func Decode(dst, src []byte) ([]byte, error) {
|
||||
dLen, s, err := decodedLen(src)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if dLen <= len(dst) {
|
||||
dst = dst[:dLen]
|
||||
} else {
|
||||
dst = make([]byte, dLen)
|
||||
}
|
||||
switch decode(dst, src[s:]) {
|
||||
case 0:
|
||||
return dst, nil
|
||||
case decodeErrCodeUnsupportedLiteralLength:
|
||||
return nil, errUnsupportedLiteralLength
|
||||
}
|
||||
return nil, ErrCorrupt
|
||||
}
|
||||
|
||||
// NewReader returns a new Reader that decompresses from r, using the framing
|
||||
// format described at
|
||||
// https://github.com/google/snappy/blob/master/framing_format.txt
|
||||
func NewReader(r io.Reader) *Reader {
|
||||
return &Reader{
|
||||
r: r,
|
||||
decoded: make([]byte, maxBlockSize),
|
||||
buf: make([]byte, maxEncodedLenOfMaxBlockSize+checksumSize),
|
||||
}
|
||||
}
|
||||
|
||||
// Reader is an io.Reader that can read Snappy-compressed bytes.
|
||||
//
|
||||
// Reader handles the Snappy stream format, not the Snappy block format.
|
||||
type Reader struct {
|
||||
r io.Reader
|
||||
err error
|
||||
decoded []byte
|
||||
buf []byte
|
||||
// decoded[i:j] contains decoded bytes that have not yet been passed on.
|
||||
i, j int
|
||||
readHeader bool
|
||||
}
|
||||
|
||||
// Reset discards any buffered data, resets all state, and switches the Snappy
|
||||
// reader to read from r. This permits reusing a Reader rather than allocating
|
||||
// a new one.
|
||||
func (r *Reader) Reset(reader io.Reader) {
|
||||
r.r = reader
|
||||
r.err = nil
|
||||
r.i = 0
|
||||
r.j = 0
|
||||
r.readHeader = false
|
||||
}
|
||||
|
||||
func (r *Reader) readFull(p []byte, allowEOF bool) (ok bool) {
|
||||
if _, r.err = io.ReadFull(r.r, p); r.err != nil {
|
||||
if r.err == io.ErrUnexpectedEOF || (r.err == io.EOF && !allowEOF) {
|
||||
r.err = ErrCorrupt
|
||||
}
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
func (r *Reader) fill() error {
|
||||
for r.i >= r.j {
|
||||
if !r.readFull(r.buf[:4], true) {
|
||||
return r.err
|
||||
}
|
||||
chunkType := r.buf[0]
|
||||
if !r.readHeader {
|
||||
if chunkType != chunkTypeStreamIdentifier {
|
||||
r.err = ErrCorrupt
|
||||
return r.err
|
||||
}
|
||||
r.readHeader = true
|
||||
}
|
||||
chunkLen := int(r.buf[1]) | int(r.buf[2])<<8 | int(r.buf[3])<<16
|
||||
if chunkLen > len(r.buf) {
|
||||
r.err = ErrUnsupported
|
||||
return r.err
|
||||
}
|
||||
|
||||
// The chunk types are specified at
|
||||
// https://github.com/google/snappy/blob/master/framing_format.txt
|
||||
switch chunkType {
|
||||
case chunkTypeCompressedData:
|
||||
// Section 4.2. Compressed data (chunk type 0x00).
|
||||
if chunkLen < checksumSize {
|
||||
r.err = ErrCorrupt
|
||||
return r.err
|
||||
}
|
||||
buf := r.buf[:chunkLen]
|
||||
if !r.readFull(buf, false) {
|
||||
return r.err
|
||||
}
|
||||
checksum := uint32(buf[0]) | uint32(buf[1])<<8 | uint32(buf[2])<<16 | uint32(buf[3])<<24
|
||||
buf = buf[checksumSize:]
|
||||
|
||||
n, err := DecodedLen(buf)
|
||||
if err != nil {
|
||||
r.err = err
|
||||
return r.err
|
||||
}
|
||||
if n > len(r.decoded) {
|
||||
r.err = ErrCorrupt
|
||||
return r.err
|
||||
}
|
||||
if _, err := Decode(r.decoded, buf); err != nil {
|
||||
r.err = err
|
||||
return r.err
|
||||
}
|
||||
if crc(r.decoded[:n]) != checksum {
|
||||
r.err = ErrCorrupt
|
||||
return r.err
|
||||
}
|
||||
r.i, r.j = 0, n
|
||||
continue
|
||||
|
||||
case chunkTypeUncompressedData:
|
||||
// Section 4.3. Uncompressed data (chunk type 0x01).
|
||||
if chunkLen < checksumSize {
|
||||
r.err = ErrCorrupt
|
||||
return r.err
|
||||
}
|
||||
buf := r.buf[:checksumSize]
|
||||
if !r.readFull(buf, false) {
|
||||
return r.err
|
||||
}
|
||||
checksum := uint32(buf[0]) | uint32(buf[1])<<8 | uint32(buf[2])<<16 | uint32(buf[3])<<24
|
||||
// Read directly into r.decoded instead of via r.buf.
|
||||
n := chunkLen - checksumSize
|
||||
if n > len(r.decoded) {
|
||||
r.err = ErrCorrupt
|
||||
return r.err
|
||||
}
|
||||
if !r.readFull(r.decoded[:n], false) {
|
||||
return r.err
|
||||
}
|
||||
if crc(r.decoded[:n]) != checksum {
|
||||
r.err = ErrCorrupt
|
||||
return r.err
|
||||
}
|
||||
r.i, r.j = 0, n
|
||||
continue
|
||||
|
||||
case chunkTypeStreamIdentifier:
|
||||
// Section 4.1. Stream identifier (chunk type 0xff).
|
||||
if chunkLen != len(magicBody) {
|
||||
r.err = ErrCorrupt
|
||||
return r.err
|
||||
}
|
||||
if !r.readFull(r.buf[:len(magicBody)], false) {
|
||||
return r.err
|
||||
}
|
||||
for i := 0; i < len(magicBody); i++ {
|
||||
if r.buf[i] != magicBody[i] {
|
||||
r.err = ErrCorrupt
|
||||
return r.err
|
||||
}
|
||||
}
|
||||
continue
|
||||
}
|
||||
|
||||
if chunkType <= 0x7f {
|
||||
// Section 4.5. Reserved unskippable chunks (chunk types 0x02-0x7f).
|
||||
r.err = ErrUnsupported
|
||||
return r.err
|
||||
}
|
||||
// Section 4.4 Padding (chunk type 0xfe).
|
||||
// Section 4.6. Reserved skippable chunks (chunk types 0x80-0xfd).
|
||||
if !r.readFull(r.buf[:chunkLen], false) {
|
||||
return r.err
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// Read satisfies the io.Reader interface.
|
||||
func (r *Reader) Read(p []byte) (int, error) {
|
||||
if r.err != nil {
|
||||
return 0, r.err
|
||||
}
|
||||
|
||||
if err := r.fill(); err != nil {
|
||||
return 0, err
|
||||
}
|
||||
|
||||
n := copy(p, r.decoded[r.i:r.j])
|
||||
r.i += n
|
||||
return n, nil
|
||||
}
|
||||
|
||||
// ReadByte satisfies the io.ByteReader interface.
|
||||
func (r *Reader) ReadByte() (byte, error) {
|
||||
if r.err != nil {
|
||||
return 0, r.err
|
||||
}
|
||||
|
||||
if err := r.fill(); err != nil {
|
||||
return 0, err
|
||||
}
|
||||
|
||||
c := r.decoded[r.i]
|
||||
r.i++
|
||||
return c, nil
|
||||
}
|
||||
113
vendor/github.com/klauspost/compress/internal/snapref/decode_other.go
generated
vendored
113
vendor/github.com/klauspost/compress/internal/snapref/decode_other.go
generated
vendored
@ -1,113 +0,0 @@
|
||||
// Copyright 2016 The Snappy-Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
package snapref
|
||||
|
||||
// decode writes the decoding of src to dst. It assumes that the varint-encoded
|
||||
// length of the decompressed bytes has already been read, and that len(dst)
|
||||
// equals that length.
|
||||
//
|
||||
// It returns 0 on success or a decodeErrCodeXxx error code on failure.
|
||||
func decode(dst, src []byte) int {
|
||||
var d, s, offset, length int
|
||||
for s < len(src) {
|
||||
switch src[s] & 0x03 {
|
||||
case tagLiteral:
|
||||
x := uint32(src[s] >> 2)
|
||||
switch {
|
||||
case x < 60:
|
||||
s++
|
||||
case x == 60:
|
||||
s += 2
|
||||
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
|
||||
return decodeErrCodeCorrupt
|
||||
}
|
||||
x = uint32(src[s-1])
|
||||
case x == 61:
|
||||
s += 3
|
||||
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
|
||||
return decodeErrCodeCorrupt
|
||||
}
|
||||
x = uint32(src[s-2]) | uint32(src[s-1])<<8
|
||||
case x == 62:
|
||||
s += 4
|
||||
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
|
||||
return decodeErrCodeCorrupt
|
||||
}
|
||||
x = uint32(src[s-3]) | uint32(src[s-2])<<8 | uint32(src[s-1])<<16
|
||||
case x == 63:
|
||||
s += 5
|
||||
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
|
||||
return decodeErrCodeCorrupt
|
||||
}
|
||||
x = uint32(src[s-4]) | uint32(src[s-3])<<8 | uint32(src[s-2])<<16 | uint32(src[s-1])<<24
|
||||
}
|
||||
length = int(x) + 1
|
||||
if length <= 0 {
|
||||
return decodeErrCodeUnsupportedLiteralLength
|
||||
}
|
||||
if length > len(dst)-d || length > len(src)-s {
|
||||
return decodeErrCodeCorrupt
|
||||
}
|
||||
copy(dst[d:], src[s:s+length])
|
||||
d += length
|
||||
s += length
|
||||
continue
|
||||
|
||||
case tagCopy1:
|
||||
s += 2
|
||||
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
|
||||
return decodeErrCodeCorrupt
|
||||
}
|
||||
length = 4 + int(src[s-2])>>2&0x7
|
||||
offset = int(uint32(src[s-2])&0xe0<<3 | uint32(src[s-1]))
|
||||
|
||||
case tagCopy2:
|
||||
s += 3
|
||||
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
|
||||
return decodeErrCodeCorrupt
|
||||
}
|
||||
length = 1 + int(src[s-3])>>2
|
||||
offset = int(uint32(src[s-2]) | uint32(src[s-1])<<8)
|
||||
|
||||
case tagCopy4:
|
||||
s += 5
|
||||
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
|
||||
return decodeErrCodeCorrupt
|
||||
}
|
||||
length = 1 + int(src[s-5])>>2
|
||||
offset = int(uint32(src[s-4]) | uint32(src[s-3])<<8 | uint32(src[s-2])<<16 | uint32(src[s-1])<<24)
|
||||
}
|
||||
|
||||
if offset <= 0 || d < offset || length > len(dst)-d {
|
||||
return decodeErrCodeCorrupt
|
||||
}
|
||||
// Copy from an earlier sub-slice of dst to a later sub-slice.
|
||||
// If no overlap, use the built-in copy:
|
||||
if offset >= length {
|
||||
copy(dst[d:d+length], dst[d-offset:])
|
||||
d += length
|
||||
continue
|
||||
}
|
||||
|
||||
// Unlike the built-in copy function, this byte-by-byte copy always runs
|
||||
// forwards, even if the slices overlap. Conceptually, this is:
|
||||
//
|
||||
// d += forwardCopy(dst[d:d+length], dst[d-offset:])
|
||||
//
|
||||
// We align the slices into a and b and show the compiler they are the same size.
|
||||
// This allows the loop to run without bounds checks.
|
||||
a := dst[d : d+length]
|
||||
b := dst[d-offset:]
|
||||
b = b[:len(a)]
|
||||
for i := range a {
|
||||
a[i] = b[i]
|
||||
}
|
||||
d += length
|
||||
}
|
||||
if d != len(dst) {
|
||||
return decodeErrCodeCorrupt
|
||||
}
|
||||
return 0
|
||||
}
|
||||
289
vendor/github.com/klauspost/compress/internal/snapref/encode.go
generated
vendored
289
vendor/github.com/klauspost/compress/internal/snapref/encode.go
generated
vendored
@ -1,289 +0,0 @@
|
||||
// Copyright 2011 The Snappy-Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
package snapref
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
"io"
|
||||
)
|
||||
|
||||
// Encode returns the encoded form of src. The returned slice may be a sub-
|
||||
// slice of dst if dst was large enough to hold the entire encoded block.
|
||||
// Otherwise, a newly allocated slice will be returned.
|
||||
//
|
||||
// The dst and src must not overlap. It is valid to pass a nil dst.
|
||||
//
|
||||
// Encode handles the Snappy block format, not the Snappy stream format.
|
||||
func Encode(dst, src []byte) []byte {
|
||||
if n := MaxEncodedLen(len(src)); n < 0 {
|
||||
panic(ErrTooLarge)
|
||||
} else if len(dst) < n {
|
||||
dst = make([]byte, n)
|
||||
}
|
||||
|
||||
// The block starts with the varint-encoded length of the decompressed bytes.
|
||||
d := binary.PutUvarint(dst, uint64(len(src)))
|
||||
|
||||
for len(src) > 0 {
|
||||
p := src
|
||||
src = nil
|
||||
if len(p) > maxBlockSize {
|
||||
p, src = p[:maxBlockSize], p[maxBlockSize:]
|
||||
}
|
||||
if len(p) < minNonLiteralBlockSize {
|
||||
d += emitLiteral(dst[d:], p)
|
||||
} else {
|
||||
d += encodeBlock(dst[d:], p)
|
||||
}
|
||||
}
|
||||
return dst[:d]
|
||||
}
|
||||
|
||||
// inputMargin is the minimum number of extra input bytes to keep, inside
|
||||
// encodeBlock's inner loop. On some architectures, this margin lets us
|
||||
// implement a fast path for emitLiteral, where the copy of short (<= 16 byte)
|
||||
// literals can be implemented as a single load to and store from a 16-byte
|
||||
// register. That literal's actual length can be as short as 1 byte, so this
|
||||
// can copy up to 15 bytes too much, but that's OK as subsequent iterations of
|
||||
// the encoding loop will fix up the copy overrun, and this inputMargin ensures
|
||||
// that we don't overrun the dst and src buffers.
|
||||
const inputMargin = 16 - 1
|
||||
|
||||
// minNonLiteralBlockSize is the minimum size of the input to encodeBlock that
|
||||
// could be encoded with a copy tag. This is the minimum with respect to the
|
||||
// algorithm used by encodeBlock, not a minimum enforced by the file format.
|
||||
//
|
||||
// The encoded output must start with at least a 1 byte literal, as there are
|
||||
// no previous bytes to copy. A minimal (1 byte) copy after that, generated
|
||||
// from an emitCopy call in encodeBlock's main loop, would require at least
|
||||
// another inputMargin bytes, for the reason above: we want any emitLiteral
|
||||
// calls inside encodeBlock's main loop to use the fast path if possible, which
|
||||
// requires being able to overrun by inputMargin bytes. Thus,
|
||||
// minNonLiteralBlockSize equals 1 + 1 + inputMargin.
|
||||
//
|
||||
// The C++ code doesn't use this exact threshold, but it could, as discussed at
|
||||
// https://groups.google.com/d/topic/snappy-compression/oGbhsdIJSJ8/discussion
|
||||
// The difference between Go (2+inputMargin) and C++ (inputMargin) is purely an
|
||||
// optimization. It should not affect the encoded form. This is tested by
|
||||
// TestSameEncodingAsCppShortCopies.
|
||||
const minNonLiteralBlockSize = 1 + 1 + inputMargin
|
||||
|
||||
// MaxEncodedLen returns the maximum length of a snappy block, given its
|
||||
// uncompressed length.
|
||||
//
|
||||
// It will return a negative value if srcLen is too large to encode.
|
||||
func MaxEncodedLen(srcLen int) int {
|
||||
n := uint64(srcLen)
|
||||
if n > 0xffffffff {
|
||||
return -1
|
||||
}
|
||||
// Compressed data can be defined as:
|
||||
// compressed := item* literal*
|
||||
// item := literal* copy
|
||||
//
|
||||
// The trailing literal sequence has a space blowup of at most 62/60
|
||||
// since a literal of length 60 needs one tag byte + one extra byte
|
||||
// for length information.
|
||||
//
|
||||
// Item blowup is trickier to measure. Suppose the "copy" op copies
|
||||
// 4 bytes of data. Because of a special check in the encoding code,
|
||||
// we produce a 4-byte copy only if the offset is < 65536. Therefore
|
||||
// the copy op takes 3 bytes to encode, and this type of item leads
|
||||
// to at most the 62/60 blowup for representing literals.
|
||||
//
|
||||
// Suppose the "copy" op copies 5 bytes of data. If the offset is big
|
||||
// enough, it will take 5 bytes to encode the copy op. Therefore the
|
||||
// worst case here is a one-byte literal followed by a five-byte copy.
|
||||
// That is, 6 bytes of input turn into 7 bytes of "compressed" data.
|
||||
//
|
||||
// This last factor dominates the blowup, so the final estimate is:
|
||||
n = 32 + n + n/6
|
||||
if n > 0xffffffff {
|
||||
return -1
|
||||
}
|
||||
return int(n)
|
||||
}
|
||||
|
||||
var errClosed = errors.New("snappy: Writer is closed")
|
||||
|
||||
// NewWriter returns a new Writer that compresses to w.
|
||||
//
|
||||
// The Writer returned does not buffer writes. There is no need to Flush or
|
||||
// Close such a Writer.
|
||||
//
|
||||
// Deprecated: the Writer returned is not suitable for many small writes, only
|
||||
// for few large writes. Use NewBufferedWriter instead, which is efficient
|
||||
// regardless of the frequency and shape of the writes, and remember to Close
|
||||
// that Writer when done.
|
||||
func NewWriter(w io.Writer) *Writer {
|
||||
return &Writer{
|
||||
w: w,
|
||||
obuf: make([]byte, obufLen),
|
||||
}
|
||||
}
|
||||
|
||||
// NewBufferedWriter returns a new Writer that compresses to w, using the
|
||||
// framing format described at
|
||||
// https://github.com/google/snappy/blob/master/framing_format.txt
|
||||
//
|
||||
// The Writer returned buffers writes. Users must call Close to guarantee all
|
||||
// data has been forwarded to the underlying io.Writer. They may also call
|
||||
// Flush zero or more times before calling Close.
|
||||
func NewBufferedWriter(w io.Writer) *Writer {
|
||||
return &Writer{
|
||||
w: w,
|
||||
ibuf: make([]byte, 0, maxBlockSize),
|
||||
obuf: make([]byte, obufLen),
|
||||
}
|
||||
}
|
||||
|
||||
// Writer is an io.Writer that can write Snappy-compressed bytes.
|
||||
//
|
||||
// Writer handles the Snappy stream format, not the Snappy block format.
|
||||
type Writer struct {
|
||||
w io.Writer
|
||||
err error
|
||||
|
||||
// ibuf is a buffer for the incoming (uncompressed) bytes.
|
||||
//
|
||||
// Its use is optional. For backwards compatibility, Writers created by the
|
||||
// NewWriter function have ibuf == nil, do not buffer incoming bytes, and
|
||||
// therefore do not need to be Flush'ed or Close'd.
|
||||
ibuf []byte
|
||||
|
||||
// obuf is a buffer for the outgoing (compressed) bytes.
|
||||
obuf []byte
|
||||
|
||||
// wroteStreamHeader is whether we have written the stream header.
|
||||
wroteStreamHeader bool
|
||||
}
|
||||
|
||||
// Reset discards the writer's state and switches the Snappy writer to write to
|
||||
// w. This permits reusing a Writer rather than allocating a new one.
|
||||
func (w *Writer) Reset(writer io.Writer) {
|
||||
w.w = writer
|
||||
w.err = nil
|
||||
if w.ibuf != nil {
|
||||
w.ibuf = w.ibuf[:0]
|
||||
}
|
||||
w.wroteStreamHeader = false
|
||||
}
|
||||
|
||||
// Write satisfies the io.Writer interface.
|
||||
func (w *Writer) Write(p []byte) (nRet int, errRet error) {
|
||||
if w.ibuf == nil {
|
||||
// Do not buffer incoming bytes. This does not perform or compress well
|
||||
// if the caller of Writer.Write writes many small slices. This
|
||||
// behavior is therefore deprecated, but still supported for backwards
|
||||
// compatibility with code that doesn't explicitly Flush or Close.
|
||||
return w.write(p)
|
||||
}
|
||||
|
||||
// The remainder of this method is based on bufio.Writer.Write from the
|
||||
// standard library.
|
||||
|
||||
for len(p) > (cap(w.ibuf)-len(w.ibuf)) && w.err == nil {
|
||||
var n int
|
||||
if len(w.ibuf) == 0 {
|
||||
// Large write, empty buffer.
|
||||
// Write directly from p to avoid copy.
|
||||
n, _ = w.write(p)
|
||||
} else {
|
||||
n = copy(w.ibuf[len(w.ibuf):cap(w.ibuf)], p)
|
||||
w.ibuf = w.ibuf[:len(w.ibuf)+n]
|
||||
w.Flush()
|
||||
}
|
||||
nRet += n
|
||||
p = p[n:]
|
||||
}
|
||||
if w.err != nil {
|
||||
return nRet, w.err
|
||||
}
|
||||
n := copy(w.ibuf[len(w.ibuf):cap(w.ibuf)], p)
|
||||
w.ibuf = w.ibuf[:len(w.ibuf)+n]
|
||||
nRet += n
|
||||
return nRet, nil
|
||||
}
|
||||
|
||||
func (w *Writer) write(p []byte) (nRet int, errRet error) {
|
||||
if w.err != nil {
|
||||
return 0, w.err
|
||||
}
|
||||
for len(p) > 0 {
|
||||
obufStart := len(magicChunk)
|
||||
if !w.wroteStreamHeader {
|
||||
w.wroteStreamHeader = true
|
||||
copy(w.obuf, magicChunk)
|
||||
obufStart = 0
|
||||
}
|
||||
|
||||
var uncompressed []byte
|
||||
if len(p) > maxBlockSize {
|
||||
uncompressed, p = p[:maxBlockSize], p[maxBlockSize:]
|
||||
} else {
|
||||
uncompressed, p = p, nil
|
||||
}
|
||||
checksum := crc(uncompressed)
|
||||
|
||||
// Compress the buffer, discarding the result if the improvement
|
||||
// isn't at least 12.5%.
|
||||
compressed := Encode(w.obuf[obufHeaderLen:], uncompressed)
|
||||
chunkType := uint8(chunkTypeCompressedData)
|
||||
chunkLen := 4 + len(compressed)
|
||||
obufEnd := obufHeaderLen + len(compressed)
|
||||
if len(compressed) >= len(uncompressed)-len(uncompressed)/8 {
|
||||
chunkType = chunkTypeUncompressedData
|
||||
chunkLen = 4 + len(uncompressed)
|
||||
obufEnd = obufHeaderLen
|
||||
}
|
||||
|
||||
// Fill in the per-chunk header that comes before the body.
|
||||
w.obuf[len(magicChunk)+0] = chunkType
|
||||
w.obuf[len(magicChunk)+1] = uint8(chunkLen >> 0)
|
||||
w.obuf[len(magicChunk)+2] = uint8(chunkLen >> 8)
|
||||
w.obuf[len(magicChunk)+3] = uint8(chunkLen >> 16)
|
||||
w.obuf[len(magicChunk)+4] = uint8(checksum >> 0)
|
||||
w.obuf[len(magicChunk)+5] = uint8(checksum >> 8)
|
||||
w.obuf[len(magicChunk)+6] = uint8(checksum >> 16)
|
||||
w.obuf[len(magicChunk)+7] = uint8(checksum >> 24)
|
||||
|
||||
if _, err := w.w.Write(w.obuf[obufStart:obufEnd]); err != nil {
|
||||
w.err = err
|
||||
return nRet, err
|
||||
}
|
||||
if chunkType == chunkTypeUncompressedData {
|
||||
if _, err := w.w.Write(uncompressed); err != nil {
|
||||
w.err = err
|
||||
return nRet, err
|
||||
}
|
||||
}
|
||||
nRet += len(uncompressed)
|
||||
}
|
||||
return nRet, nil
|
||||
}
|
||||
|
||||
// Flush flushes the Writer to its underlying io.Writer.
|
||||
func (w *Writer) Flush() error {
|
||||
if w.err != nil {
|
||||
return w.err
|
||||
}
|
||||
if len(w.ibuf) == 0 {
|
||||
return nil
|
||||
}
|
||||
w.write(w.ibuf)
|
||||
w.ibuf = w.ibuf[:0]
|
||||
return w.err
|
||||
}
|
||||
|
||||
// Close calls Flush and then closes the Writer.
|
||||
func (w *Writer) Close() error {
|
||||
w.Flush()
|
||||
ret := w.err
|
||||
if w.err == nil {
|
||||
w.err = errClosed
|
||||
}
|
||||
return ret
|
||||
}
|
||||
250
vendor/github.com/klauspost/compress/internal/snapref/encode_other.go
generated
vendored
250
vendor/github.com/klauspost/compress/internal/snapref/encode_other.go
generated
vendored
@ -1,250 +0,0 @@
|
||||
// Copyright 2016 The Snappy-Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
package snapref
|
||||
|
||||
func load32(b []byte, i int) uint32 {
|
||||
b = b[i : i+4 : len(b)] // Help the compiler eliminate bounds checks on the next line.
|
||||
return uint32(b[0]) | uint32(b[1])<<8 | uint32(b[2])<<16 | uint32(b[3])<<24
|
||||
}
|
||||
|
||||
func load64(b []byte, i int) uint64 {
|
||||
b = b[i : i+8 : len(b)] // Help the compiler eliminate bounds checks on the next line.
|
||||
return uint64(b[0]) | uint64(b[1])<<8 | uint64(b[2])<<16 | uint64(b[3])<<24 |
|
||||
uint64(b[4])<<32 | uint64(b[5])<<40 | uint64(b[6])<<48 | uint64(b[7])<<56
|
||||
}
|
||||
|
||||
// emitLiteral writes a literal chunk and returns the number of bytes written.
|
||||
//
|
||||
// It assumes that:
|
||||
//
|
||||
// dst is long enough to hold the encoded bytes
|
||||
// 1 <= len(lit) && len(lit) <= 65536
|
||||
func emitLiteral(dst, lit []byte) int {
|
||||
i, n := 0, uint(len(lit)-1)
|
||||
switch {
|
||||
case n < 60:
|
||||
dst[0] = uint8(n)<<2 | tagLiteral
|
||||
i = 1
|
||||
case n < 1<<8:
|
||||
dst[0] = 60<<2 | tagLiteral
|
||||
dst[1] = uint8(n)
|
||||
i = 2
|
||||
default:
|
||||
dst[0] = 61<<2 | tagLiteral
|
||||
dst[1] = uint8(n)
|
||||
dst[2] = uint8(n >> 8)
|
||||
i = 3
|
||||
}
|
||||
return i + copy(dst[i:], lit)
|
||||
}
|
||||
|
||||
// emitCopy writes a copy chunk and returns the number of bytes written.
|
||||
//
|
||||
// It assumes that:
|
||||
//
|
||||
// dst is long enough to hold the encoded bytes
|
||||
// 1 <= offset && offset <= 65535
|
||||
// 4 <= length && length <= 65535
|
||||
func emitCopy(dst []byte, offset, length int) int {
|
||||
i := 0
|
||||
// The maximum length for a single tagCopy1 or tagCopy2 op is 64 bytes. The
|
||||
// threshold for this loop is a little higher (at 68 = 64 + 4), and the
|
||||
// length emitted down below is a little lower (at 60 = 64 - 4), because
|
||||
// it's shorter to encode a length 67 copy as a length 60 tagCopy2 followed
|
||||
// by a length 7 tagCopy1 (which encodes as 3+2 bytes) than to encode it as
|
||||
// a length 64 tagCopy2 followed by a length 3 tagCopy2 (which encodes as
|
||||
// 3+3 bytes). The magic 4 in the 64±4 is because the minimum length for a
|
||||
// tagCopy1 op is 4 bytes, which is why a length 3 copy has to be an
|
||||
// encodes-as-3-bytes tagCopy2 instead of an encodes-as-2-bytes tagCopy1.
|
||||
for length >= 68 {
|
||||
// Emit a length 64 copy, encoded as 3 bytes.
|
||||
dst[i+0] = 63<<2 | tagCopy2
|
||||
dst[i+1] = uint8(offset)
|
||||
dst[i+2] = uint8(offset >> 8)
|
||||
i += 3
|
||||
length -= 64
|
||||
}
|
||||
if length > 64 {
|
||||
// Emit a length 60 copy, encoded as 3 bytes.
|
||||
dst[i+0] = 59<<2 | tagCopy2
|
||||
dst[i+1] = uint8(offset)
|
||||
dst[i+2] = uint8(offset >> 8)
|
||||
i += 3
|
||||
length -= 60
|
||||
}
|
||||
if length >= 12 || offset >= 2048 {
|
||||
// Emit the remaining copy, encoded as 3 bytes.
|
||||
dst[i+0] = uint8(length-1)<<2 | tagCopy2
|
||||
dst[i+1] = uint8(offset)
|
||||
dst[i+2] = uint8(offset >> 8)
|
||||
return i + 3
|
||||
}
|
||||
// Emit the remaining copy, encoded as 2 bytes.
|
||||
dst[i+0] = uint8(offset>>8)<<5 | uint8(length-4)<<2 | tagCopy1
|
||||
dst[i+1] = uint8(offset)
|
||||
return i + 2
|
||||
}
|
||||
|
||||
func hash(u, shift uint32) uint32 {
|
||||
return (u * 0x1e35a7bd) >> shift
|
||||
}
|
||||
|
||||
// EncodeBlockInto exposes encodeBlock but checks dst size.
|
||||
func EncodeBlockInto(dst, src []byte) (d int) {
|
||||
if MaxEncodedLen(len(src)) > len(dst) {
|
||||
return 0
|
||||
}
|
||||
|
||||
// encodeBlock breaks on too big blocks, so split.
|
||||
for len(src) > 0 {
|
||||
p := src
|
||||
src = nil
|
||||
if len(p) > maxBlockSize {
|
||||
p, src = p[:maxBlockSize], p[maxBlockSize:]
|
||||
}
|
||||
if len(p) < minNonLiteralBlockSize {
|
||||
d += emitLiteral(dst[d:], p)
|
||||
} else {
|
||||
d += encodeBlock(dst[d:], p)
|
||||
}
|
||||
}
|
||||
return d
|
||||
}
|
||||
|
||||
// encodeBlock encodes a non-empty src to a guaranteed-large-enough dst. It
|
||||
// assumes that the varint-encoded length of the decompressed bytes has already
|
||||
// been written.
|
||||
//
|
||||
// It also assumes that:
|
||||
//
|
||||
// len(dst) >= MaxEncodedLen(len(src)) &&
|
||||
// minNonLiteralBlockSize <= len(src) && len(src) <= maxBlockSize
|
||||
func encodeBlock(dst, src []byte) (d int) {
|
||||
// Initialize the hash table. Its size ranges from 1<<8 to 1<<14 inclusive.
|
||||
// The table element type is uint16, as s < sLimit and sLimit < len(src)
|
||||
// and len(src) <= maxBlockSize and maxBlockSize == 65536.
|
||||
const (
|
||||
maxTableSize = 1 << 14
|
||||
// tableMask is redundant, but helps the compiler eliminate bounds
|
||||
// checks.
|
||||
tableMask = maxTableSize - 1
|
||||
)
|
||||
shift := uint32(32 - 8)
|
||||
for tableSize := 1 << 8; tableSize < maxTableSize && tableSize < len(src); tableSize *= 2 {
|
||||
shift--
|
||||
}
|
||||
// In Go, all array elements are zero-initialized, so there is no advantage
|
||||
// to a smaller tableSize per se. However, it matches the C++ algorithm,
|
||||
// and in the asm versions of this code, we can get away with zeroing only
|
||||
// the first tableSize elements.
|
||||
var table [maxTableSize]uint16
|
||||
|
||||
// sLimit is when to stop looking for offset/length copies. The inputMargin
|
||||
// lets us use a fast path for emitLiteral in the main loop, while we are
|
||||
// looking for copies.
|
||||
sLimit := len(src) - inputMargin
|
||||
|
||||
// nextEmit is where in src the next emitLiteral should start from.
|
||||
nextEmit := 0
|
||||
|
||||
// The encoded form must start with a literal, as there are no previous
|
||||
// bytes to copy, so we start looking for hash matches at s == 1.
|
||||
s := 1
|
||||
nextHash := hash(load32(src, s), shift)
|
||||
|
||||
for {
|
||||
// Copied from the C++ snappy implementation:
|
||||
//
|
||||
// Heuristic match skipping: If 32 bytes are scanned with no matches
|
||||
// found, start looking only at every other byte. If 32 more bytes are
|
||||
// scanned (or skipped), look at every third byte, etc.. When a match
|
||||
// is found, immediately go back to looking at every byte. This is a
|
||||
// small loss (~5% performance, ~0.1% density) for compressible data
|
||||
// due to more bookkeeping, but for non-compressible data (such as
|
||||
// JPEG) it's a huge win since the compressor quickly "realizes" the
|
||||
// data is incompressible and doesn't bother looking for matches
|
||||
// everywhere.
|
||||
//
|
||||
// The "skip" variable keeps track of how many bytes there are since
|
||||
// the last match; dividing it by 32 (ie. right-shifting by five) gives
|
||||
// the number of bytes to move ahead for each iteration.
|
||||
skip := 32
|
||||
|
||||
nextS := s
|
||||
candidate := 0
|
||||
for {
|
||||
s = nextS
|
||||
bytesBetweenHashLookups := skip >> 5
|
||||
nextS = s + bytesBetweenHashLookups
|
||||
skip += bytesBetweenHashLookups
|
||||
if nextS > sLimit {
|
||||
goto emitRemainder
|
||||
}
|
||||
candidate = int(table[nextHash&tableMask])
|
||||
table[nextHash&tableMask] = uint16(s)
|
||||
nextHash = hash(load32(src, nextS), shift)
|
||||
if load32(src, s) == load32(src, candidate) {
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
// A 4-byte match has been found. We'll later see if more than 4 bytes
|
||||
// match. But, prior to the match, src[nextEmit:s] are unmatched. Emit
|
||||
// them as literal bytes.
|
||||
d += emitLiteral(dst[d:], src[nextEmit:s])
|
||||
|
||||
// Call emitCopy, and then see if another emitCopy could be our next
|
||||
// move. Repeat until we find no match for the input immediately after
|
||||
// what was consumed by the last emitCopy call.
|
||||
//
|
||||
// If we exit this loop normally then we need to call emitLiteral next,
|
||||
// though we don't yet know how big the literal will be. We handle that
|
||||
// by proceeding to the next iteration of the main loop. We also can
|
||||
// exit this loop via goto if we get close to exhausting the input.
|
||||
for {
|
||||
// Invariant: we have a 4-byte match at s, and no need to emit any
|
||||
// literal bytes prior to s.
|
||||
base := s
|
||||
|
||||
// Extend the 4-byte match as long as possible.
|
||||
//
|
||||
// This is an inlined version of:
|
||||
// s = extendMatch(src, candidate+4, s+4)
|
||||
s += 4
|
||||
for i := candidate + 4; s < len(src) && src[i] == src[s]; i, s = i+1, s+1 {
|
||||
}
|
||||
|
||||
d += emitCopy(dst[d:], base-candidate, s-base)
|
||||
nextEmit = s
|
||||
if s >= sLimit {
|
||||
goto emitRemainder
|
||||
}
|
||||
|
||||
// We could immediately start working at s now, but to improve
|
||||
// compression we first update the hash table at s-1 and at s. If
|
||||
// another emitCopy is not our next move, also calculate nextHash
|
||||
// at s+1. At least on GOARCH=amd64, these three hash calculations
|
||||
// are faster as one load64 call (with some shifts) instead of
|
||||
// three load32 calls.
|
||||
x := load64(src, s-1)
|
||||
prevHash := hash(uint32(x>>0), shift)
|
||||
table[prevHash&tableMask] = uint16(s - 1)
|
||||
currHash := hash(uint32(x>>8), shift)
|
||||
candidate = int(table[currHash&tableMask])
|
||||
table[currHash&tableMask] = uint16(s)
|
||||
if uint32(x>>8) != load32(src, candidate) {
|
||||
nextHash = hash(uint32(x>>16), shift)
|
||||
s++
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
emitRemainder:
|
||||
if nextEmit < len(src) {
|
||||
d += emitLiteral(dst[d:], src[nextEmit:])
|
||||
}
|
||||
return d
|
||||
}
|
||||
98
vendor/github.com/klauspost/compress/internal/snapref/snappy.go
generated
vendored
98
vendor/github.com/klauspost/compress/internal/snapref/snappy.go
generated
vendored
@ -1,98 +0,0 @@
|
||||
// Copyright 2011 The Snappy-Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// Package snapref implements the Snappy compression format. It aims for very
|
||||
// high speeds and reasonable compression.
|
||||
//
|
||||
// There are actually two Snappy formats: block and stream. They are related,
|
||||
// but different: trying to decompress block-compressed data as a Snappy stream
|
||||
// will fail, and vice versa. The block format is the Decode and Encode
|
||||
// functions and the stream format is the Reader and Writer types.
|
||||
//
|
||||
// The block format, the more common case, is used when the complete size (the
|
||||
// number of bytes) of the original data is known upfront, at the time
|
||||
// compression starts. The stream format, also known as the framing format, is
|
||||
// for when that isn't always true.
|
||||
//
|
||||
// The canonical, C++ implementation is at https://github.com/google/snappy and
|
||||
// it only implements the block format.
|
||||
package snapref
|
||||
|
||||
import (
|
||||
"hash/crc32"
|
||||
)
|
||||
|
||||
/*
|
||||
Each encoded block begins with the varint-encoded length of the decoded data,
|
||||
followed by a sequence of chunks. Chunks begin and end on byte boundaries. The
|
||||
first byte of each chunk is broken into its 2 least and 6 most significant bits
|
||||
called l and m: l ranges in [0, 4) and m ranges in [0, 64). l is the chunk tag.
|
||||
Zero means a literal tag. All other values mean a copy tag.
|
||||
|
||||
For literal tags:
|
||||
- If m < 60, the next 1 + m bytes are literal bytes.
|
||||
- Otherwise, let n be the little-endian unsigned integer denoted by the next
|
||||
m - 59 bytes. The next 1 + n bytes after that are literal bytes.
|
||||
|
||||
For copy tags, length bytes are copied from offset bytes ago, in the style of
|
||||
Lempel-Ziv compression algorithms. In particular:
|
||||
- For l == 1, the offset ranges in [0, 1<<11) and the length in [4, 12).
|
||||
The length is 4 + the low 3 bits of m. The high 3 bits of m form bits 8-10
|
||||
of the offset. The next byte is bits 0-7 of the offset.
|
||||
- For l == 2, the offset ranges in [0, 1<<16) and the length in [1, 65).
|
||||
The length is 1 + m. The offset is the little-endian unsigned integer
|
||||
denoted by the next 2 bytes.
|
||||
- For l == 3, this tag is a legacy format that is no longer issued by most
|
||||
encoders. Nonetheless, the offset ranges in [0, 1<<32) and the length in
|
||||
[1, 65). The length is 1 + m. The offset is the little-endian unsigned
|
||||
integer denoted by the next 4 bytes.
|
||||
*/
|
||||
const (
|
||||
tagLiteral = 0x00
|
||||
tagCopy1 = 0x01
|
||||
tagCopy2 = 0x02
|
||||
tagCopy4 = 0x03
|
||||
)
|
||||
|
||||
const (
|
||||
checksumSize = 4
|
||||
chunkHeaderSize = 4
|
||||
magicChunk = "\xff\x06\x00\x00" + magicBody
|
||||
magicBody = "sNaPpY"
|
||||
|
||||
// maxBlockSize is the maximum size of the input to encodeBlock. It is not
|
||||
// part of the wire format per se, but some parts of the encoder assume
|
||||
// that an offset fits into a uint16.
|
||||
//
|
||||
// Also, for the framing format (Writer type instead of Encode function),
|
||||
// https://github.com/google/snappy/blob/master/framing_format.txt says
|
||||
// that "the uncompressed data in a chunk must be no longer than 65536
|
||||
// bytes".
|
||||
maxBlockSize = 65536
|
||||
|
||||
// maxEncodedLenOfMaxBlockSize equals MaxEncodedLen(maxBlockSize), but is
|
||||
// hard coded to be a const instead of a variable, so that obufLen can also
|
||||
// be a const. Their equivalence is confirmed by
|
||||
// TestMaxEncodedLenOfMaxBlockSize.
|
||||
maxEncodedLenOfMaxBlockSize = 76490
|
||||
|
||||
obufHeaderLen = len(magicChunk) + checksumSize + chunkHeaderSize
|
||||
obufLen = obufHeaderLen + maxEncodedLenOfMaxBlockSize
|
||||
)
|
||||
|
||||
const (
|
||||
chunkTypeCompressedData = 0x00
|
||||
chunkTypeUncompressedData = 0x01
|
||||
chunkTypePadding = 0xfe
|
||||
chunkTypeStreamIdentifier = 0xff
|
||||
)
|
||||
|
||||
var crcTable = crc32.MakeTable(crc32.Castagnoli)
|
||||
|
||||
// crc implements the checksum specified in section 3 of
|
||||
// https://github.com/google/snappy/blob/master/framing_format.txt
|
||||
func crc(b []byte) uint32 {
|
||||
c := crc32.Update(0, crcTable, b)
|
||||
return uint32(c>>15|c<<17) + 0xa282ead8
|
||||
}
|
||||
4
vendor/github.com/klauspost/compress/s2sx.mod
generated
vendored
4
vendor/github.com/klauspost/compress/s2sx.mod
generated
vendored
@ -1,4 +0,0 @@
|
||||
module github.com/klauspost/compress
|
||||
|
||||
go 1.19
|
||||
|
||||
0
vendor/github.com/klauspost/compress/s2sx.sum
generated
vendored
0
vendor/github.com/klauspost/compress/s2sx.sum
generated
vendored
441
vendor/github.com/klauspost/compress/zstd/README.md
generated
vendored
441
vendor/github.com/klauspost/compress/zstd/README.md
generated
vendored
@ -1,441 +0,0 @@
|
||||
# zstd
|
||||
|
||||
[Zstandard](https://facebook.github.io/zstd/) is a real-time compression algorithm, providing high compression ratios.
|
||||
It offers a very wide range of compression / speed trade-off, while being backed by a very fast decoder.
|
||||
A high performance compression algorithm is implemented. For now focused on speed.
|
||||
|
||||
This package provides [compression](#Compressor) to and [decompression](#Decompressor) of Zstandard content.
|
||||
|
||||
This package is pure Go and without use of "unsafe".
|
||||
|
||||
The `zstd` package is provided as open source software using a Go standard license.
|
||||
|
||||
Currently the package is heavily optimized for 64 bit processors and will be significantly slower on 32 bit processors.
|
||||
|
||||
For seekable zstd streams, see [this excellent package](https://github.com/SaveTheRbtz/zstd-seekable-format-go).
|
||||
|
||||
## Installation
|
||||
|
||||
Install using `go get -u github.com/klauspost/compress`. The package is located in `github.com/klauspost/compress/zstd`.
|
||||
|
||||
[](https://pkg.go.dev/github.com/klauspost/compress/zstd)
|
||||
|
||||
## Compressor
|
||||
|
||||
### Status:
|
||||
|
||||
STABLE - there may always be subtle bugs, a wide variety of content has been tested and the library is actively
|
||||
used by several projects. This library is being [fuzz-tested](https://github.com/klauspost/compress-fuzz) for all updates.
|
||||
|
||||
There may still be specific combinations of data types/size/settings that could lead to edge cases,
|
||||
so as always, testing is recommended.
|
||||
|
||||
For now, a high speed (fastest) and medium-fast (default) compressor has been implemented.
|
||||
|
||||
* The "Fastest" compression ratio is roughly equivalent to zstd level 1.
|
||||
* The "Default" compression ratio is roughly equivalent to zstd level 3 (default).
|
||||
* The "Better" compression ratio is roughly equivalent to zstd level 7.
|
||||
* The "Best" compression ratio is roughly equivalent to zstd level 11.
|
||||
|
||||
In terms of speed, it is typically 2x as fast as the stdlib deflate/gzip in its fastest mode.
|
||||
The compression ratio compared to stdlib is around level 3, but usually 3x as fast.
|
||||
|
||||
|
||||
### Usage
|
||||
|
||||
An Encoder can be used for either compressing a stream via the
|
||||
`io.WriteCloser` interface supported by the Encoder or as multiple independent
|
||||
tasks via the `EncodeAll` function.
|
||||
Smaller encodes are encouraged to use the EncodeAll function.
|
||||
Use `NewWriter` to create a new instance that can be used for both.
|
||||
|
||||
To create a writer with default options, do like this:
|
||||
|
||||
```Go
|
||||
// Compress input to output.
|
||||
func Compress(in io.Reader, out io.Writer) error {
|
||||
enc, err := zstd.NewWriter(out)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
_, err = io.Copy(enc, in)
|
||||
if err != nil {
|
||||
enc.Close()
|
||||
return err
|
||||
}
|
||||
return enc.Close()
|
||||
}
|
||||
```
|
||||
|
||||
Now you can encode by writing data to `enc`. The output will be finished writing when `Close()` is called.
|
||||
Even if your encode fails, you should still call `Close()` to release any resources that may be held up.
|
||||
|
||||
The above is fine for big encodes. However, whenever possible try to *reuse* the writer.
|
||||
|
||||
To reuse the encoder, you can use the `Reset(io.Writer)` function to change to another output.
|
||||
This will allow the encoder to reuse all resources and avoid wasteful allocations.
|
||||
|
||||
Currently stream encoding has 'light' concurrency, meaning up to 2 goroutines can be working on part
|
||||
of a stream. This is independent of the `WithEncoderConcurrency(n)`, but that is likely to change
|
||||
in the future. So if you want to limit concurrency for future updates, specify the concurrency
|
||||
you would like.
|
||||
|
||||
If you would like stream encoding to be done without spawning async goroutines, use `WithEncoderConcurrency(1)`
|
||||
which will compress input as each block is completed, blocking on writes until each has completed.
|
||||
|
||||
You can specify your desired compression level using `WithEncoderLevel()` option. Currently only pre-defined
|
||||
compression settings can be specified.
|
||||
|
||||
#### Future Compatibility Guarantees
|
||||
|
||||
This will be an evolving project. When using this package it is important to note that both the compression efficiency and speed may change.
|
||||
|
||||
The goal will be to keep the default efficiency at the default zstd (level 3).
|
||||
However the encoding should never be assumed to remain the same,
|
||||
and you should not use hashes of compressed output for similarity checks.
|
||||
|
||||
The Encoder can be assumed to produce the same output from the exact same code version.
|
||||
However, the may be modes in the future that break this,
|
||||
although they will not be enabled without an explicit option.
|
||||
|
||||
This encoder is not designed to (and will probably never) output the exact same bitstream as the reference encoder.
|
||||
|
||||
Also note, that the cgo decompressor currently does not [report all errors on invalid input](https://github.com/DataDog/zstd/issues/59),
|
||||
[omits error checks](https://github.com/DataDog/zstd/issues/61), [ignores checksums](https://github.com/DataDog/zstd/issues/43)
|
||||
and seems to ignore concatenated streams, even though [it is part of the spec](https://github.com/facebook/zstd/blob/dev/doc/zstd_compression_format.md#frames).
|
||||
|
||||
#### Blocks
|
||||
|
||||
For compressing small blocks, the returned encoder has a function called `EncodeAll(src, dst []byte) []byte`.
|
||||
|
||||
`EncodeAll` will encode all input in src and append it to dst.
|
||||
This function can be called concurrently.
|
||||
Each call will only run on a same goroutine as the caller.
|
||||
|
||||
Encoded blocks can be concatenated and the result will be the combined input stream.
|
||||
Data compressed with EncodeAll can be decoded with the Decoder, using either a stream or `DecodeAll`.
|
||||
|
||||
Especially when encoding blocks you should take special care to reuse the encoder.
|
||||
This will effectively make it run without allocations after a warmup period.
|
||||
To make it run completely without allocations, supply a destination buffer with space for all content.
|
||||
|
||||
```Go
|
||||
import "github.com/klauspost/compress/zstd"
|
||||
|
||||
// Create a writer that caches compressors.
|
||||
// For this operation type we supply a nil Reader.
|
||||
var encoder, _ = zstd.NewWriter(nil)
|
||||
|
||||
// Compress a buffer.
|
||||
// If you have a destination buffer, the allocation in the call can also be eliminated.
|
||||
func Compress(src []byte) []byte {
|
||||
return encoder.EncodeAll(src, make([]byte, 0, len(src)))
|
||||
}
|
||||
```
|
||||
|
||||
You can control the maximum number of concurrent encodes using the `WithEncoderConcurrency(n)`
|
||||
option when creating the writer.
|
||||
|
||||
Using the Encoder for both a stream and individual blocks concurrently is safe.
|
||||
|
||||
### Performance
|
||||
|
||||
I have collected some speed examples to compare speed and compression against other compressors.
|
||||
|
||||
* `file` is the input file.
|
||||
* `out` is the compressor used. `zskp` is this package. `zstd` is the Datadog cgo library. `gzstd/gzkp` is gzip standard and this library.
|
||||
* `level` is the compression level used. For `zskp` level 1 is "fastest", level 2 is "default"; 3 is "better", 4 is "best".
|
||||
* `insize`/`outsize` is the input/output size.
|
||||
* `millis` is the number of milliseconds used for compression.
|
||||
* `mb/s` is megabytes (2^20 bytes) per second.
|
||||
|
||||
```
|
||||
Silesia Corpus:
|
||||
http://sun.aei.polsl.pl/~sdeor/corpus/silesia.zip
|
||||
|
||||
This package:
|
||||
file out level insize outsize millis mb/s
|
||||
silesia.tar zskp 1 211947520 73821326 634 318.47
|
||||
silesia.tar zskp 2 211947520 67655404 1508 133.96
|
||||
silesia.tar zskp 3 211947520 64746933 3000 67.37
|
||||
silesia.tar zskp 4 211947520 60073508 16926 11.94
|
||||
|
||||
cgo zstd:
|
||||
silesia.tar zstd 1 211947520 73605392 543 371.56
|
||||
silesia.tar zstd 3 211947520 66793289 864 233.68
|
||||
silesia.tar zstd 6 211947520 62916450 1913 105.66
|
||||
silesia.tar zstd 9 211947520 60212393 5063 39.92
|
||||
|
||||
gzip, stdlib/this package:
|
||||
silesia.tar gzstd 1 211947520 80007735 1498 134.87
|
||||
silesia.tar gzkp 1 211947520 80088272 1009 200.31
|
||||
|
||||
GOB stream of binary data. Highly compressible.
|
||||
https://files.klauspost.com/compress/gob-stream.7z
|
||||
|
||||
file out level insize outsize millis mb/s
|
||||
gob-stream zskp 1 1911399616 233948096 3230 564.34
|
||||
gob-stream zskp 2 1911399616 203997694 4997 364.73
|
||||
gob-stream zskp 3 1911399616 173526523 13435 135.68
|
||||
gob-stream zskp 4 1911399616 162195235 47559 38.33
|
||||
|
||||
gob-stream zstd 1 1911399616 249810424 2637 691.26
|
||||
gob-stream zstd 3 1911399616 208192146 3490 522.31
|
||||
gob-stream zstd 6 1911399616 193632038 6687 272.56
|
||||
gob-stream zstd 9 1911399616 177620386 16175 112.70
|
||||
|
||||
gob-stream gzstd 1 1911399616 357382013 9046 201.49
|
||||
gob-stream gzkp 1 1911399616 359136669 4885 373.08
|
||||
|
||||
The test data for the Large Text Compression Benchmark is the first
|
||||
10^9 bytes of the English Wikipedia dump on Mar. 3, 2006.
|
||||
http://mattmahoney.net/dc/textdata.html
|
||||
|
||||
file out level insize outsize millis mb/s
|
||||
enwik9 zskp 1 1000000000 343833605 3687 258.64
|
||||
enwik9 zskp 2 1000000000 317001237 7672 124.29
|
||||
enwik9 zskp 3 1000000000 291915823 15923 59.89
|
||||
enwik9 zskp 4 1000000000 261710291 77697 12.27
|
||||
|
||||
enwik9 zstd 1 1000000000 358072021 3110 306.65
|
||||
enwik9 zstd 3 1000000000 313734672 4784 199.35
|
||||
enwik9 zstd 6 1000000000 295138875 10290 92.68
|
||||
enwik9 zstd 9 1000000000 278348700 28549 33.40
|
||||
|
||||
enwik9 gzstd 1 1000000000 382578136 8608 110.78
|
||||
enwik9 gzkp 1 1000000000 382781160 5628 169.45
|
||||
|
||||
Highly compressible JSON file.
|
||||
https://files.klauspost.com/compress/github-june-2days-2019.json.zst
|
||||
|
||||
file out level insize outsize millis mb/s
|
||||
github-june-2days-2019.json zskp 1 6273951764 697439532 9789 611.17
|
||||
github-june-2days-2019.json zskp 2 6273951764 610876538 18553 322.49
|
||||
github-june-2days-2019.json zskp 3 6273951764 517662858 44186 135.41
|
||||
github-june-2days-2019.json zskp 4 6273951764 464617114 165373 36.18
|
||||
|
||||
github-june-2days-2019.json zstd 1 6273951764 766284037 8450 708.00
|
||||
github-june-2days-2019.json zstd 3 6273951764 661889476 10927 547.57
|
||||
github-june-2days-2019.json zstd 6 6273951764 642756859 22996 260.18
|
||||
github-june-2days-2019.json zstd 9 6273951764 601974523 52413 114.16
|
||||
|
||||
github-june-2days-2019.json gzstd 1 6273951764 1164397768 26793 223.32
|
||||
github-june-2days-2019.json gzkp 1 6273951764 1120631856 17693 338.16
|
||||
|
||||
VM Image, Linux mint with a few installed applications:
|
||||
https://files.klauspost.com/compress/rawstudio-mint14.7z
|
||||
|
||||
file out level insize outsize millis mb/s
|
||||
rawstudio-mint14.tar zskp 1 8558382592 3718400221 18206 448.29
|
||||
rawstudio-mint14.tar zskp 2 8558382592 3326118337 37074 220.15
|
||||
rawstudio-mint14.tar zskp 3 8558382592 3163842361 87306 93.49
|
||||
rawstudio-mint14.tar zskp 4 8558382592 2970480650 783862 10.41
|
||||
|
||||
rawstudio-mint14.tar zstd 1 8558382592 3609250104 17136 476.27
|
||||
rawstudio-mint14.tar zstd 3 8558382592 3341679997 29262 278.92
|
||||
rawstudio-mint14.tar zstd 6 8558382592 3235846406 77904 104.77
|
||||
rawstudio-mint14.tar zstd 9 8558382592 3160778861 140946 57.91
|
||||
|
||||
rawstudio-mint14.tar gzstd 1 8558382592 3926234992 51345 158.96
|
||||
rawstudio-mint14.tar gzkp 1 8558382592 3960117298 36722 222.26
|
||||
|
||||
CSV data:
|
||||
https://files.klauspost.com/compress/nyc-taxi-data-10M.csv.zst
|
||||
|
||||
file out level insize outsize millis mb/s
|
||||
nyc-taxi-data-10M.csv zskp 1 3325605752 641319332 9462 335.17
|
||||
nyc-taxi-data-10M.csv zskp 2 3325605752 588976126 17570 180.50
|
||||
nyc-taxi-data-10M.csv zskp 3 3325605752 529329260 32432 97.79
|
||||
nyc-taxi-data-10M.csv zskp 4 3325605752 474949772 138025 22.98
|
||||
|
||||
nyc-taxi-data-10M.csv zstd 1 3325605752 687399637 8233 385.18
|
||||
nyc-taxi-data-10M.csv zstd 3 3325605752 598514411 10065 315.07
|
||||
nyc-taxi-data-10M.csv zstd 6 3325605752 570522953 20038 158.27
|
||||
nyc-taxi-data-10M.csv zstd 9 3325605752 517554797 64565 49.12
|
||||
|
||||
nyc-taxi-data-10M.csv gzstd 1 3325605752 928654908 21270 149.11
|
||||
nyc-taxi-data-10M.csv gzkp 1 3325605752 922273214 13929 227.68
|
||||
```
|
||||
|
||||
## Decompressor
|
||||
|
||||
Status: STABLE - there may still be subtle bugs, but a wide variety of content has been tested.
|
||||
|
||||
This library is being continuously [fuzz-tested](https://github.com/klauspost/compress-fuzz),
|
||||
kindly supplied by [fuzzit.dev](https://fuzzit.dev/).
|
||||
The main purpose of the fuzz testing is to ensure that it is not possible to crash the decoder,
|
||||
or run it past its limits with ANY input provided.
|
||||
|
||||
### Usage
|
||||
|
||||
The package has been designed for two main usages, big streams of data and smaller in-memory buffers.
|
||||
There are two main usages of the package for these. Both of them are accessed by creating a `Decoder`.
|
||||
|
||||
For streaming use a simple setup could look like this:
|
||||
|
||||
```Go
|
||||
import "github.com/klauspost/compress/zstd"
|
||||
|
||||
func Decompress(in io.Reader, out io.Writer) error {
|
||||
d, err := zstd.NewReader(in)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer d.Close()
|
||||
|
||||
// Copy content...
|
||||
_, err = io.Copy(out, d)
|
||||
return err
|
||||
}
|
||||
```
|
||||
|
||||
It is important to use the "Close" function when you no longer need the Reader to stop running goroutines,
|
||||
when running with default settings.
|
||||
Goroutines will exit once an error has been returned, including `io.EOF` at the end of a stream.
|
||||
|
||||
Streams are decoded concurrently in 4 asynchronous stages to give the best possible throughput.
|
||||
However, if you prefer synchronous decompression, use `WithDecoderConcurrency(1)` which will decompress data
|
||||
as it is being requested only.
|
||||
|
||||
For decoding buffers, it could look something like this:
|
||||
|
||||
```Go
|
||||
import "github.com/klauspost/compress/zstd"
|
||||
|
||||
// Create a reader that caches decompressors.
|
||||
// For this operation type we supply a nil Reader.
|
||||
var decoder, _ = zstd.NewReader(nil, zstd.WithDecoderConcurrency(0))
|
||||
|
||||
// Decompress a buffer. We don't supply a destination buffer,
|
||||
// so it will be allocated by the decoder.
|
||||
func Decompress(src []byte) ([]byte, error) {
|
||||
return decoder.DecodeAll(src, nil)
|
||||
}
|
||||
```
|
||||
|
||||
Both of these cases should provide the functionality needed.
|
||||
The decoder can be used for *concurrent* decompression of multiple buffers.
|
||||
By default 4 decompressors will be created.
|
||||
|
||||
It will only allow a certain number of concurrent operations to run.
|
||||
To tweak that yourself use the `WithDecoderConcurrency(n)` option when creating the decoder.
|
||||
It is possible to use `WithDecoderConcurrency(0)` to create GOMAXPROCS decoders.
|
||||
|
||||
### Dictionaries
|
||||
|
||||
Data compressed with [dictionaries](https://github.com/facebook/zstd#the-case-for-small-data-compression) can be decompressed.
|
||||
|
||||
Dictionaries are added individually to Decoders.
|
||||
Dictionaries are generated by the `zstd --train` command and contains an initial state for the decoder.
|
||||
To add a dictionary use the `WithDecoderDicts(dicts ...[]byte)` option with the dictionary data.
|
||||
Several dictionaries can be added at once.
|
||||
|
||||
The dictionary will be used automatically for the data that specifies them.
|
||||
A re-used Decoder will still contain the dictionaries registered.
|
||||
|
||||
When registering multiple dictionaries with the same ID, the last one will be used.
|
||||
|
||||
It is possible to use dictionaries when compressing data.
|
||||
|
||||
To enable a dictionary use `WithEncoderDict(dict []byte)`. Here only one dictionary will be used
|
||||
and it will likely be used even if it doesn't improve compression.
|
||||
|
||||
The used dictionary must be used to decompress the content.
|
||||
|
||||
For any real gains, the dictionary should be built with similar data.
|
||||
If an unsuitable dictionary is used the output may be slightly larger than using no dictionary.
|
||||
Use the [zstd commandline tool](https://github.com/facebook/zstd/releases) to build a dictionary from sample data.
|
||||
For information see [zstd dictionary information](https://github.com/facebook/zstd#the-case-for-small-data-compression).
|
||||
|
||||
For now there is a fixed startup performance penalty for compressing content with dictionaries.
|
||||
This will likely be improved over time. Just be aware to test performance when implementing.
|
||||
|
||||
### Allocation-less operation
|
||||
|
||||
The decoder has been designed to operate without allocations after a warmup.
|
||||
|
||||
This means that you should *store* the decoder for best performance.
|
||||
To re-use a stream decoder, use the `Reset(r io.Reader) error` to switch to another stream.
|
||||
A decoder can safely be re-used even if the previous stream failed.
|
||||
|
||||
To release the resources, you must call the `Close()` function on a decoder.
|
||||
After this it can *no longer be reused*, but all running goroutines will be stopped.
|
||||
So you *must* use this if you will no longer need the Reader.
|
||||
|
||||
For decompressing smaller buffers a single decoder can be used.
|
||||
When decoding buffers, you can supply a destination slice with length 0 and your expected capacity.
|
||||
In this case no unneeded allocations should be made.
|
||||
|
||||
### Concurrency
|
||||
|
||||
The buffer decoder does everything on the same goroutine and does nothing concurrently.
|
||||
It can however decode several buffers concurrently. Use `WithDecoderConcurrency(n)` to limit that.
|
||||
|
||||
The stream decoder will create goroutines that:
|
||||
|
||||
1) Reads input and splits the input into blocks.
|
||||
2) Decompression of literals.
|
||||
3) Decompression of sequences.
|
||||
4) Reconstruction of output stream.
|
||||
|
||||
So effectively this also means the decoder will "read ahead" and prepare data to always be available for output.
|
||||
|
||||
The concurrency level will, for streams, determine how many blocks ahead the compression will start.
|
||||
|
||||
Since "blocks" are quite dependent on the output of the previous block stream decoding will only have limited concurrency.
|
||||
|
||||
In practice this means that concurrency is often limited to utilizing about 3 cores effectively.
|
||||
|
||||
### Benchmarks
|
||||
|
||||
The first two are streaming decodes and the last are smaller inputs.
|
||||
|
||||
Running on AMD Ryzen 9 3950X 16-Core Processor. AMD64 assembly used.
|
||||
|
||||
```
|
||||
BenchmarkDecoderSilesia-32 5 206878840 ns/op 1024.50 MB/s 49808 B/op 43 allocs/op
|
||||
BenchmarkDecoderEnwik9-32 1 1271809000 ns/op 786.28 MB/s 72048 B/op 52 allocs/op
|
||||
|
||||
Concurrent blocks, performance:
|
||||
|
||||
BenchmarkDecoder_DecodeAllParallel/kppkn.gtb.zst-32 67356 17857 ns/op 10321.96 MB/s 22.48 pct 102 B/op 0 allocs/op
|
||||
BenchmarkDecoder_DecodeAllParallel/geo.protodata.zst-32 266656 4421 ns/op 26823.21 MB/s 11.89 pct 19 B/op 0 allocs/op
|
||||
BenchmarkDecoder_DecodeAllParallel/plrabn12.txt.zst-32 20992 56842 ns/op 8477.17 MB/s 39.90 pct 754 B/op 0 allocs/op
|
||||
BenchmarkDecoder_DecodeAllParallel/lcet10.txt.zst-32 27456 43932 ns/op 9714.01 MB/s 33.27 pct 524 B/op 0 allocs/op
|
||||
BenchmarkDecoder_DecodeAllParallel/asyoulik.txt.zst-32 78432 15047 ns/op 8319.15 MB/s 40.34 pct 66 B/op 0 allocs/op
|
||||
BenchmarkDecoder_DecodeAllParallel/alice29.txt.zst-32 65800 18436 ns/op 8249.63 MB/s 37.75 pct 88 B/op 0 allocs/op
|
||||
BenchmarkDecoder_DecodeAllParallel/html_x_4.zst-32 102993 11523 ns/op 35546.09 MB/s 3.637 pct 143 B/op 0 allocs/op
|
||||
BenchmarkDecoder_DecodeAllParallel/paper-100k.pdf.zst-32 1000000 1070 ns/op 95720.98 MB/s 80.53 pct 3 B/op 0 allocs/op
|
||||
BenchmarkDecoder_DecodeAllParallel/fireworks.jpeg.zst-32 749802 1752 ns/op 70272.35 MB/s 100.0 pct 5 B/op 0 allocs/op
|
||||
BenchmarkDecoder_DecodeAllParallel/urls.10K.zst-32 22640 52934 ns/op 13263.37 MB/s 26.25 pct 1014 B/op 0 allocs/op
|
||||
BenchmarkDecoder_DecodeAllParallel/html.zst-32 226412 5232 ns/op 19572.27 MB/s 14.49 pct 20 B/op 0 allocs/op
|
||||
BenchmarkDecoder_DecodeAllParallel/comp-data.bin.zst-32 923041 1276 ns/op 3194.71 MB/s 31.26 pct 0 B/op 0 allocs/op
|
||||
```
|
||||
|
||||
This reflects the performance around May 2022, but this may be out of date.
|
||||
|
||||
## Zstd inside ZIP files
|
||||
|
||||
It is possible to use zstandard to compress individual files inside zip archives.
|
||||
While this isn't widely supported it can be useful for internal files.
|
||||
|
||||
To support the compression and decompression of these files you must register a compressor and decompressor.
|
||||
|
||||
It is highly recommended registering the (de)compressors on individual zip Reader/Writer and NOT
|
||||
use the global registration functions. The main reason for this is that 2 registrations from
|
||||
different packages will result in a panic.
|
||||
|
||||
It is a good idea to only have a single compressor and decompressor, since they can be used for multiple zip
|
||||
files concurrently, and using a single instance will allow reusing some resources.
|
||||
|
||||
See [this example](https://pkg.go.dev/github.com/klauspost/compress/zstd#example-ZipCompressor) for
|
||||
how to compress and decompress files inside zip archives.
|
||||
|
||||
# Contributions
|
||||
|
||||
Contributions are always welcome.
|
||||
For new features/fixes, remember to add tests and for performance enhancements include benchmarks.
|
||||
|
||||
For general feedback and experience reports, feel free to open an issue or write me on [Twitter](https://twitter.com/sh0dan).
|
||||
|
||||
This package includes the excellent [`github.com/cespare/xxhash`](https://github.com/cespare/xxhash) package Copyright (c) 2016 Caleb Spare.
|
||||
136
vendor/github.com/klauspost/compress/zstd/bitreader.go
generated
vendored
136
vendor/github.com/klauspost/compress/zstd/bitreader.go
generated
vendored
@ -1,136 +0,0 @@
|
||||
// Copyright 2019+ Klaus Post. All rights reserved.
|
||||
// License information can be found in the LICENSE file.
|
||||
// Based on work by Yann Collet, released under BSD License.
|
||||
|
||||
package zstd
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"math/bits"
|
||||
)
|
||||
|
||||
// bitReader reads a bitstream in reverse.
|
||||
// The last set bit indicates the start of the stream and is used
|
||||
// for aligning the input.
|
||||
type bitReader struct {
|
||||
in []byte
|
||||
value uint64 // Maybe use [16]byte, but shifting is awkward.
|
||||
bitsRead uint8
|
||||
}
|
||||
|
||||
// init initializes and resets the bit reader.
|
||||
func (b *bitReader) init(in []byte) error {
|
||||
if len(in) < 1 {
|
||||
return errors.New("corrupt stream: too short")
|
||||
}
|
||||
b.in = in
|
||||
// The highest bit of the last byte indicates where to start
|
||||
v := in[len(in)-1]
|
||||
if v == 0 {
|
||||
return errors.New("corrupt stream, did not find end of stream")
|
||||
}
|
||||
b.bitsRead = 64
|
||||
b.value = 0
|
||||
if len(in) >= 8 {
|
||||
b.fillFastStart()
|
||||
} else {
|
||||
b.fill()
|
||||
b.fill()
|
||||
}
|
||||
b.bitsRead += 8 - uint8(highBits(uint32(v)))
|
||||
return nil
|
||||
}
|
||||
|
||||
// getBits will return n bits. n can be 0.
|
||||
func (b *bitReader) getBits(n uint8) int {
|
||||
if n == 0 /*|| b.bitsRead >= 64 */ {
|
||||
return 0
|
||||
}
|
||||
return int(b.get32BitsFast(n))
|
||||
}
|
||||
|
||||
// get32BitsFast requires that at least one bit is requested every time.
|
||||
// There are no checks if the buffer is filled.
|
||||
func (b *bitReader) get32BitsFast(n uint8) uint32 {
|
||||
const regMask = 64 - 1
|
||||
v := uint32((b.value << (b.bitsRead & regMask)) >> ((regMask + 1 - n) & regMask))
|
||||
b.bitsRead += n
|
||||
return v
|
||||
}
|
||||
|
||||
// fillFast() will make sure at least 32 bits are available.
|
||||
// There must be at least 4 bytes available.
|
||||
func (b *bitReader) fillFast() {
|
||||
if b.bitsRead < 32 {
|
||||
return
|
||||
}
|
||||
v := b.in[len(b.in)-4:]
|
||||
b.in = b.in[:len(b.in)-4]
|
||||
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
|
||||
b.value = (b.value << 32) | uint64(low)
|
||||
b.bitsRead -= 32
|
||||
}
|
||||
|
||||
// fillFastStart() assumes the bitreader is empty and there is at least 8 bytes to read.
|
||||
func (b *bitReader) fillFastStart() {
|
||||
v := b.in[len(b.in)-8:]
|
||||
b.in = b.in[:len(b.in)-8]
|
||||
b.value = binary.LittleEndian.Uint64(v)
|
||||
b.bitsRead = 0
|
||||
}
|
||||
|
||||
// fill() will make sure at least 32 bits are available.
|
||||
func (b *bitReader) fill() {
|
||||
if b.bitsRead < 32 {
|
||||
return
|
||||
}
|
||||
if len(b.in) >= 4 {
|
||||
v := b.in[len(b.in)-4:]
|
||||
b.in = b.in[:len(b.in)-4]
|
||||
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
|
||||
b.value = (b.value << 32) | uint64(low)
|
||||
b.bitsRead -= 32
|
||||
return
|
||||
}
|
||||
|
||||
b.bitsRead -= uint8(8 * len(b.in))
|
||||
for len(b.in) > 0 {
|
||||
b.value = (b.value << 8) | uint64(b.in[len(b.in)-1])
|
||||
b.in = b.in[:len(b.in)-1]
|
||||
}
|
||||
}
|
||||
|
||||
// finished returns true if all bits have been read from the bit stream.
|
||||
func (b *bitReader) finished() bool {
|
||||
return len(b.in) == 0 && b.bitsRead >= 64
|
||||
}
|
||||
|
||||
// overread returns true if more bits have been requested than is on the stream.
|
||||
func (b *bitReader) overread() bool {
|
||||
return b.bitsRead > 64
|
||||
}
|
||||
|
||||
// remain returns the number of bits remaining.
|
||||
func (b *bitReader) remain() uint {
|
||||
return 8*uint(len(b.in)) + 64 - uint(b.bitsRead)
|
||||
}
|
||||
|
||||
// close the bitstream and returns an error if out-of-buffer reads occurred.
|
||||
func (b *bitReader) close() error {
|
||||
// Release reference.
|
||||
b.in = nil
|
||||
if !b.finished() {
|
||||
return fmt.Errorf("%d extra bits on block, should be 0", b.remain())
|
||||
}
|
||||
if b.bitsRead > 64 {
|
||||
return io.ErrUnexpectedEOF
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func highBits(val uint32) (n uint32) {
|
||||
return uint32(bits.Len32(val) - 1)
|
||||
}
|
||||
112
vendor/github.com/klauspost/compress/zstd/bitwriter.go
generated
vendored
112
vendor/github.com/klauspost/compress/zstd/bitwriter.go
generated
vendored
@ -1,112 +0,0 @@
|
||||
// Copyright 2018 Klaus Post. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
// Based on work Copyright (c) 2013, Yann Collet, released under BSD License.
|
||||
|
||||
package zstd
|
||||
|
||||
// bitWriter will write bits.
|
||||
// First bit will be LSB of the first byte of output.
|
||||
type bitWriter struct {
|
||||
bitContainer uint64
|
||||
nBits uint8
|
||||
out []byte
|
||||
}
|
||||
|
||||
// bitMask16 is bitmasks. Has extra to avoid bounds check.
|
||||
var bitMask16 = [32]uint16{
|
||||
0, 1, 3, 7, 0xF, 0x1F,
|
||||
0x3F, 0x7F, 0xFF, 0x1FF, 0x3FF, 0x7FF,
|
||||
0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF, 0xFFFF,
|
||||
0xFFFF, 0xFFFF, 0xFFFF, 0xFFFF, 0xFFFF, 0xFFFF,
|
||||
0xFFFF, 0xFFFF} /* up to 16 bits */
|
||||
|
||||
var bitMask32 = [32]uint32{
|
||||
0, 1, 3, 7, 0xF, 0x1F, 0x3F, 0x7F, 0xFF,
|
||||
0x1FF, 0x3FF, 0x7FF, 0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF,
|
||||
0x1ffff, 0x3ffff, 0x7FFFF, 0xfFFFF, 0x1fFFFF, 0x3fFFFF, 0x7fFFFF, 0xffFFFF,
|
||||
0x1ffFFFF, 0x3ffFFFF, 0x7ffFFFF, 0xfffFFFF, 0x1fffFFFF, 0x3fffFFFF, 0x7fffFFFF,
|
||||
} // up to 32 bits
|
||||
|
||||
// addBits16NC will add up to 16 bits.
|
||||
// It will not check if there is space for them,
|
||||
// so the caller must ensure that it has flushed recently.
|
||||
func (b *bitWriter) addBits16NC(value uint16, bits uint8) {
|
||||
b.bitContainer |= uint64(value&bitMask16[bits&31]) << (b.nBits & 63)
|
||||
b.nBits += bits
|
||||
}
|
||||
|
||||
// addBits32NC will add up to 31 bits.
|
||||
// It will not check if there is space for them,
|
||||
// so the caller must ensure that it has flushed recently.
|
||||
func (b *bitWriter) addBits32NC(value uint32, bits uint8) {
|
||||
b.bitContainer |= uint64(value&bitMask32[bits&31]) << (b.nBits & 63)
|
||||
b.nBits += bits
|
||||
}
|
||||
|
||||
// addBits64NC will add up to 64 bits.
|
||||
// There must be space for 32 bits.
|
||||
func (b *bitWriter) addBits64NC(value uint64, bits uint8) {
|
||||
if bits <= 31 {
|
||||
b.addBits32Clean(uint32(value), bits)
|
||||
return
|
||||
}
|
||||
b.addBits32Clean(uint32(value), 32)
|
||||
b.flush32()
|
||||
b.addBits32Clean(uint32(value>>32), bits-32)
|
||||
}
|
||||
|
||||
// addBits32Clean will add up to 32 bits.
|
||||
// It will not check if there is space for them.
|
||||
// The input must not contain more bits than specified.
|
||||
func (b *bitWriter) addBits32Clean(value uint32, bits uint8) {
|
||||
b.bitContainer |= uint64(value) << (b.nBits & 63)
|
||||
b.nBits += bits
|
||||
}
|
||||
|
||||
// addBits16Clean will add up to 16 bits. value may not contain more set bits than indicated.
|
||||
// It will not check if there is space for them, so the caller must ensure that it has flushed recently.
|
||||
func (b *bitWriter) addBits16Clean(value uint16, bits uint8) {
|
||||
b.bitContainer |= uint64(value) << (b.nBits & 63)
|
||||
b.nBits += bits
|
||||
}
|
||||
|
||||
// flush32 will flush out, so there are at least 32 bits available for writing.
|
||||
func (b *bitWriter) flush32() {
|
||||
if b.nBits < 32 {
|
||||
return
|
||||
}
|
||||
b.out = append(b.out,
|
||||
byte(b.bitContainer),
|
||||
byte(b.bitContainer>>8),
|
||||
byte(b.bitContainer>>16),
|
||||
byte(b.bitContainer>>24))
|
||||
b.nBits -= 32
|
||||
b.bitContainer >>= 32
|
||||
}
|
||||
|
||||
// flushAlign will flush remaining full bytes and align to next byte boundary.
|
||||
func (b *bitWriter) flushAlign() {
|
||||
nbBytes := (b.nBits + 7) >> 3
|
||||
for i := uint8(0); i < nbBytes; i++ {
|
||||
b.out = append(b.out, byte(b.bitContainer>>(i*8)))
|
||||
}
|
||||
b.nBits = 0
|
||||
b.bitContainer = 0
|
||||
}
|
||||
|
||||
// close will write the alignment bit and write the final byte(s)
|
||||
// to the output.
|
||||
func (b *bitWriter) close() {
|
||||
// End mark
|
||||
b.addBits16Clean(1, 1)
|
||||
// flush until next byte.
|
||||
b.flushAlign()
|
||||
}
|
||||
|
||||
// reset and continue writing by appending to out.
|
||||
func (b *bitWriter) reset(out []byte) {
|
||||
b.bitContainer = 0
|
||||
b.nBits = 0
|
||||
b.out = out
|
||||
}
|
||||
731
vendor/github.com/klauspost/compress/zstd/blockdec.go
generated
vendored
731
vendor/github.com/klauspost/compress/zstd/blockdec.go
generated
vendored
@ -1,731 +0,0 @@
|
||||
// Copyright 2019+ Klaus Post. All rights reserved.
|
||||
// License information can be found in the LICENSE file.
|
||||
// Based on work by Yann Collet, released under BSD License.
|
||||
|
||||
package zstd
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
"fmt"
|
||||
"hash/crc32"
|
||||
"io"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"sync"
|
||||
|
||||
"github.com/klauspost/compress/huff0"
|
||||
"github.com/klauspost/compress/zstd/internal/xxhash"
|
||||
)
|
||||
|
||||
type blockType uint8
|
||||
|
||||
//go:generate stringer -type=blockType,literalsBlockType,seqCompMode,tableIndex
|
||||
|
||||
const (
|
||||
blockTypeRaw blockType = iota
|
||||
blockTypeRLE
|
||||
blockTypeCompressed
|
||||
blockTypeReserved
|
||||
)
|
||||
|
||||
type literalsBlockType uint8
|
||||
|
||||
const (
|
||||
literalsBlockRaw literalsBlockType = iota
|
||||
literalsBlockRLE
|
||||
literalsBlockCompressed
|
||||
literalsBlockTreeless
|
||||
)
|
||||
|
||||
const (
|
||||
// maxCompressedBlockSize is the biggest allowed compressed block size (128KB)
|
||||
maxCompressedBlockSize = 128 << 10
|
||||
|
||||
compressedBlockOverAlloc = 16
|
||||
maxCompressedBlockSizeAlloc = 128<<10 + compressedBlockOverAlloc
|
||||
|
||||
// Maximum possible block size (all Raw+Uncompressed).
|
||||
maxBlockSize = (1 << 21) - 1
|
||||
|
||||
maxMatchLen = 131074
|
||||
maxSequences = 0x7f00 + 0xffff
|
||||
|
||||
// We support slightly less than the reference decoder to be able to
|
||||
// use ints on 32 bit archs.
|
||||
maxOffsetBits = 30
|
||||
)
|
||||
|
||||
var (
|
||||
huffDecoderPool = sync.Pool{New: func() interface{} {
|
||||
return &huff0.Scratch{}
|
||||
}}
|
||||
|
||||
fseDecoderPool = sync.Pool{New: func() interface{} {
|
||||
return &fseDecoder{}
|
||||
}}
|
||||
)
|
||||
|
||||
type blockDec struct {
|
||||
// Raw source data of the block.
|
||||
data []byte
|
||||
dataStorage []byte
|
||||
|
||||
// Destination of the decoded data.
|
||||
dst []byte
|
||||
|
||||
// Buffer for literals data.
|
||||
literalBuf []byte
|
||||
|
||||
// Window size of the block.
|
||||
WindowSize uint64
|
||||
|
||||
err error
|
||||
|
||||
// Check against this crc, if hasCRC is true.
|
||||
checkCRC uint32
|
||||
hasCRC bool
|
||||
|
||||
// Frame to use for singlethreaded decoding.
|
||||
// Should not be used by the decoder itself since parent may be another frame.
|
||||
localFrame *frameDec
|
||||
|
||||
sequence []seqVals
|
||||
|
||||
async struct {
|
||||
newHist *history
|
||||
literals []byte
|
||||
seqData []byte
|
||||
seqSize int // Size of uncompressed sequences
|
||||
fcs uint64
|
||||
}
|
||||
|
||||
// Block is RLE, this is the size.
|
||||
RLESize uint32
|
||||
|
||||
Type blockType
|
||||
|
||||
// Is this the last block of a frame?
|
||||
Last bool
|
||||
|
||||
// Use less memory
|
||||
lowMem bool
|
||||
}
|
||||
|
||||
func (b *blockDec) String() string {
|
||||
if b == nil {
|
||||
return "<nil>"
|
||||
}
|
||||
return fmt.Sprintf("Steam Size: %d, Type: %v, Last: %t, Window: %d", len(b.data), b.Type, b.Last, b.WindowSize)
|
||||
}
|
||||
|
||||
func newBlockDec(lowMem bool) *blockDec {
|
||||
b := blockDec{
|
||||
lowMem: lowMem,
|
||||
}
|
||||
return &b
|
||||
}
|
||||
|
||||
// reset will reset the block.
|
||||
// Input must be a start of a block and will be at the end of the block when returned.
|
||||
func (b *blockDec) reset(br byteBuffer, windowSize uint64) error {
|
||||
b.WindowSize = windowSize
|
||||
tmp, err := br.readSmall(3)
|
||||
if err != nil {
|
||||
println("Reading block header:", err)
|
||||
return err
|
||||
}
|
||||
bh := uint32(tmp[0]) | (uint32(tmp[1]) << 8) | (uint32(tmp[2]) << 16)
|
||||
b.Last = bh&1 != 0
|
||||
b.Type = blockType((bh >> 1) & 3)
|
||||
// find size.
|
||||
cSize := int(bh >> 3)
|
||||
maxSize := maxCompressedBlockSizeAlloc
|
||||
switch b.Type {
|
||||
case blockTypeReserved:
|
||||
return ErrReservedBlockType
|
||||
case blockTypeRLE:
|
||||
if cSize > maxCompressedBlockSize || cSize > int(b.WindowSize) {
|
||||
if debugDecoder {
|
||||
printf("rle block too big: csize:%d block: %+v\n", uint64(cSize), b)
|
||||
}
|
||||
return ErrWindowSizeExceeded
|
||||
}
|
||||
b.RLESize = uint32(cSize)
|
||||
if b.lowMem {
|
||||
maxSize = cSize
|
||||
}
|
||||
cSize = 1
|
||||
case blockTypeCompressed:
|
||||
if debugDecoder {
|
||||
println("Data size on stream:", cSize)
|
||||
}
|
||||
b.RLESize = 0
|
||||
maxSize = maxCompressedBlockSizeAlloc
|
||||
if windowSize < maxCompressedBlockSize && b.lowMem {
|
||||
maxSize = int(windowSize) + compressedBlockOverAlloc
|
||||
}
|
||||
if cSize > maxCompressedBlockSize || uint64(cSize) > b.WindowSize {
|
||||
if debugDecoder {
|
||||
printf("compressed block too big: csize:%d block: %+v\n", uint64(cSize), b)
|
||||
}
|
||||
return ErrCompressedSizeTooBig
|
||||
}
|
||||
// Empty compressed blocks must at least be 2 bytes
|
||||
// for Literals_Block_Type and one for Sequences_Section_Header.
|
||||
if cSize < 2 {
|
||||
return ErrBlockTooSmall
|
||||
}
|
||||
case blockTypeRaw:
|
||||
if cSize > maxCompressedBlockSize || cSize > int(b.WindowSize) {
|
||||
if debugDecoder {
|
||||
printf("rle block too big: csize:%d block: %+v\n", uint64(cSize), b)
|
||||
}
|
||||
return ErrWindowSizeExceeded
|
||||
}
|
||||
|
||||
b.RLESize = 0
|
||||
// We do not need a destination for raw blocks.
|
||||
maxSize = -1
|
||||
default:
|
||||
panic("Invalid block type")
|
||||
}
|
||||
|
||||
// Read block data.
|
||||
if _, ok := br.(*byteBuf); !ok && cap(b.dataStorage) < cSize {
|
||||
// byteBuf doesn't need a destination buffer.
|
||||
if b.lowMem || cSize > maxCompressedBlockSize {
|
||||
b.dataStorage = make([]byte, 0, cSize+compressedBlockOverAlloc)
|
||||
} else {
|
||||
b.dataStorage = make([]byte, 0, maxCompressedBlockSizeAlloc)
|
||||
}
|
||||
}
|
||||
b.data, err = br.readBig(cSize, b.dataStorage)
|
||||
if err != nil {
|
||||
if debugDecoder {
|
||||
println("Reading block:", err, "(", cSize, ")", len(b.data))
|
||||
printf("%T", br)
|
||||
}
|
||||
return err
|
||||
}
|
||||
if cap(b.dst) <= maxSize {
|
||||
b.dst = make([]byte, 0, maxSize+1)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// sendEOF will make the decoder send EOF on this frame.
|
||||
func (b *blockDec) sendErr(err error) {
|
||||
b.Last = true
|
||||
b.Type = blockTypeReserved
|
||||
b.err = err
|
||||
}
|
||||
|
||||
// Close will release resources.
|
||||
// Closed blockDec cannot be reset.
|
||||
func (b *blockDec) Close() {
|
||||
}
|
||||
|
||||
// decodeBuf
|
||||
func (b *blockDec) decodeBuf(hist *history) error {
|
||||
switch b.Type {
|
||||
case blockTypeRLE:
|
||||
if cap(b.dst) < int(b.RLESize) {
|
||||
if b.lowMem {
|
||||
b.dst = make([]byte, b.RLESize)
|
||||
} else {
|
||||
b.dst = make([]byte, maxCompressedBlockSize)
|
||||
}
|
||||
}
|
||||
b.dst = b.dst[:b.RLESize]
|
||||
v := b.data[0]
|
||||
for i := range b.dst {
|
||||
b.dst[i] = v
|
||||
}
|
||||
hist.appendKeep(b.dst)
|
||||
return nil
|
||||
case blockTypeRaw:
|
||||
hist.appendKeep(b.data)
|
||||
return nil
|
||||
case blockTypeCompressed:
|
||||
saved := b.dst
|
||||
// Append directly to history
|
||||
if hist.ignoreBuffer == 0 {
|
||||
b.dst = hist.b
|
||||
hist.b = nil
|
||||
} else {
|
||||
b.dst = b.dst[:0]
|
||||
}
|
||||
err := b.decodeCompressed(hist)
|
||||
if debugDecoder {
|
||||
println("Decompressed to total", len(b.dst), "bytes, hash:", xxhash.Sum64(b.dst), "error:", err)
|
||||
}
|
||||
if hist.ignoreBuffer == 0 {
|
||||
hist.b = b.dst
|
||||
b.dst = saved
|
||||
} else {
|
||||
hist.appendKeep(b.dst)
|
||||
}
|
||||
return err
|
||||
case blockTypeReserved:
|
||||
// Used for returning errors.
|
||||
return b.err
|
||||
default:
|
||||
panic("Invalid block type")
|
||||
}
|
||||
}
|
||||
|
||||
func (b *blockDec) decodeLiterals(in []byte, hist *history) (remain []byte, err error) {
|
||||
// There must be at least one byte for Literals_Block_Type and one for Sequences_Section_Header
|
||||
if len(in) < 2 {
|
||||
return in, ErrBlockTooSmall
|
||||
}
|
||||
|
||||
litType := literalsBlockType(in[0] & 3)
|
||||
var litRegenSize int
|
||||
var litCompSize int
|
||||
sizeFormat := (in[0] >> 2) & 3
|
||||
var fourStreams bool
|
||||
var literals []byte
|
||||
switch litType {
|
||||
case literalsBlockRaw, literalsBlockRLE:
|
||||
switch sizeFormat {
|
||||
case 0, 2:
|
||||
// Regenerated_Size uses 5 bits (0-31). Literals_Section_Header uses 1 byte.
|
||||
litRegenSize = int(in[0] >> 3)
|
||||
in = in[1:]
|
||||
case 1:
|
||||
// Regenerated_Size uses 12 bits (0-4095). Literals_Section_Header uses 2 bytes.
|
||||
litRegenSize = int(in[0]>>4) + (int(in[1]) << 4)
|
||||
in = in[2:]
|
||||
case 3:
|
||||
// Regenerated_Size uses 20 bits (0-1048575). Literals_Section_Header uses 3 bytes.
|
||||
if len(in) < 3 {
|
||||
println("too small: litType:", litType, " sizeFormat", sizeFormat, len(in))
|
||||
return in, ErrBlockTooSmall
|
||||
}
|
||||
litRegenSize = int(in[0]>>4) + (int(in[1]) << 4) + (int(in[2]) << 12)
|
||||
in = in[3:]
|
||||
}
|
||||
case literalsBlockCompressed, literalsBlockTreeless:
|
||||
switch sizeFormat {
|
||||
case 0, 1:
|
||||
// Both Regenerated_Size and Compressed_Size use 10 bits (0-1023).
|
||||
if len(in) < 3 {
|
||||
println("too small: litType:", litType, " sizeFormat", sizeFormat, len(in))
|
||||
return in, ErrBlockTooSmall
|
||||
}
|
||||
n := uint64(in[0]>>4) + (uint64(in[1]) << 4) + (uint64(in[2]) << 12)
|
||||
litRegenSize = int(n & 1023)
|
||||
litCompSize = int(n >> 10)
|
||||
fourStreams = sizeFormat == 1
|
||||
in = in[3:]
|
||||
case 2:
|
||||
fourStreams = true
|
||||
if len(in) < 4 {
|
||||
println("too small: litType:", litType, " sizeFormat", sizeFormat, len(in))
|
||||
return in, ErrBlockTooSmall
|
||||
}
|
||||
n := uint64(in[0]>>4) + (uint64(in[1]) << 4) + (uint64(in[2]) << 12) + (uint64(in[3]) << 20)
|
||||
litRegenSize = int(n & 16383)
|
||||
litCompSize = int(n >> 14)
|
||||
in = in[4:]
|
||||
case 3:
|
||||
fourStreams = true
|
||||
if len(in) < 5 {
|
||||
println("too small: litType:", litType, " sizeFormat", sizeFormat, len(in))
|
||||
return in, ErrBlockTooSmall
|
||||
}
|
||||
n := uint64(in[0]>>4) + (uint64(in[1]) << 4) + (uint64(in[2]) << 12) + (uint64(in[3]) << 20) + (uint64(in[4]) << 28)
|
||||
litRegenSize = int(n & 262143)
|
||||
litCompSize = int(n >> 18)
|
||||
in = in[5:]
|
||||
}
|
||||
}
|
||||
if debugDecoder {
|
||||
println("literals type:", litType, "litRegenSize:", litRegenSize, "litCompSize:", litCompSize, "sizeFormat:", sizeFormat, "4X:", fourStreams)
|
||||
}
|
||||
if litRegenSize > int(b.WindowSize) || litRegenSize > maxCompressedBlockSize {
|
||||
return in, ErrWindowSizeExceeded
|
||||
}
|
||||
|
||||
switch litType {
|
||||
case literalsBlockRaw:
|
||||
if len(in) < litRegenSize {
|
||||
println("too small: litType:", litType, " sizeFormat", sizeFormat, "remain:", len(in), "want:", litRegenSize)
|
||||
return in, ErrBlockTooSmall
|
||||
}
|
||||
literals = in[:litRegenSize]
|
||||
in = in[litRegenSize:]
|
||||
//printf("Found %d uncompressed literals\n", litRegenSize)
|
||||
case literalsBlockRLE:
|
||||
if len(in) < 1 {
|
||||
println("too small: litType:", litType, " sizeFormat", sizeFormat, "remain:", len(in), "want:", 1)
|
||||
return in, ErrBlockTooSmall
|
||||
}
|
||||
if cap(b.literalBuf) < litRegenSize {
|
||||
if b.lowMem {
|
||||
b.literalBuf = make([]byte, litRegenSize, litRegenSize+compressedBlockOverAlloc)
|
||||
} else {
|
||||
b.literalBuf = make([]byte, litRegenSize, maxCompressedBlockSize+compressedBlockOverAlloc)
|
||||
}
|
||||
}
|
||||
literals = b.literalBuf[:litRegenSize]
|
||||
v := in[0]
|
||||
for i := range literals {
|
||||
literals[i] = v
|
||||
}
|
||||
in = in[1:]
|
||||
if debugDecoder {
|
||||
printf("Found %d RLE compressed literals\n", litRegenSize)
|
||||
}
|
||||
case literalsBlockTreeless:
|
||||
if len(in) < litCompSize {
|
||||
println("too small: litType:", litType, " sizeFormat", sizeFormat, "remain:", len(in), "want:", litCompSize)
|
||||
return in, ErrBlockTooSmall
|
||||
}
|
||||
// Store compressed literals, so we defer decoding until we get history.
|
||||
literals = in[:litCompSize]
|
||||
in = in[litCompSize:]
|
||||
if debugDecoder {
|
||||
printf("Found %d compressed literals\n", litCompSize)
|
||||
}
|
||||
huff := hist.huffTree
|
||||
if huff == nil {
|
||||
return in, errors.New("literal block was treeless, but no history was defined")
|
||||
}
|
||||
// Ensure we have space to store it.
|
||||
if cap(b.literalBuf) < litRegenSize {
|
||||
if b.lowMem {
|
||||
b.literalBuf = make([]byte, 0, litRegenSize+compressedBlockOverAlloc)
|
||||
} else {
|
||||
b.literalBuf = make([]byte, 0, maxCompressedBlockSize+compressedBlockOverAlloc)
|
||||
}
|
||||
}
|
||||
var err error
|
||||
// Use our out buffer.
|
||||
huff.MaxDecodedSize = litRegenSize
|
||||
if fourStreams {
|
||||
literals, err = huff.Decoder().Decompress4X(b.literalBuf[:0:litRegenSize], literals)
|
||||
} else {
|
||||
literals, err = huff.Decoder().Decompress1X(b.literalBuf[:0:litRegenSize], literals)
|
||||
}
|
||||
// Make sure we don't leak our literals buffer
|
||||
if err != nil {
|
||||
println("decompressing literals:", err)
|
||||
return in, err
|
||||
}
|
||||
if len(literals) != litRegenSize {
|
||||
return in, fmt.Errorf("literal output size mismatch want %d, got %d", litRegenSize, len(literals))
|
||||
}
|
||||
|
||||
case literalsBlockCompressed:
|
||||
if len(in) < litCompSize {
|
||||
println("too small: litType:", litType, " sizeFormat", sizeFormat, "remain:", len(in), "want:", litCompSize)
|
||||
return in, ErrBlockTooSmall
|
||||
}
|
||||
literals = in[:litCompSize]
|
||||
in = in[litCompSize:]
|
||||
// Ensure we have space to store it.
|
||||
if cap(b.literalBuf) < litRegenSize {
|
||||
if b.lowMem {
|
||||
b.literalBuf = make([]byte, 0, litRegenSize+compressedBlockOverAlloc)
|
||||
} else {
|
||||
b.literalBuf = make([]byte, 0, maxCompressedBlockSize+compressedBlockOverAlloc)
|
||||
}
|
||||
}
|
||||
huff := hist.huffTree
|
||||
if huff == nil || (hist.dict != nil && huff == hist.dict.litEnc) {
|
||||
huff = huffDecoderPool.Get().(*huff0.Scratch)
|
||||
if huff == nil {
|
||||
huff = &huff0.Scratch{}
|
||||
}
|
||||
}
|
||||
var err error
|
||||
if debugDecoder {
|
||||
println("huff table input:", len(literals), "CRC:", crc32.ChecksumIEEE(literals))
|
||||
}
|
||||
huff, literals, err = huff0.ReadTable(literals, huff)
|
||||
if err != nil {
|
||||
println("reading huffman table:", err)
|
||||
return in, err
|
||||
}
|
||||
hist.huffTree = huff
|
||||
huff.MaxDecodedSize = litRegenSize
|
||||
// Use our out buffer.
|
||||
if fourStreams {
|
||||
literals, err = huff.Decoder().Decompress4X(b.literalBuf[:0:litRegenSize], literals)
|
||||
} else {
|
||||
literals, err = huff.Decoder().Decompress1X(b.literalBuf[:0:litRegenSize], literals)
|
||||
}
|
||||
if err != nil {
|
||||
println("decoding compressed literals:", err)
|
||||
return in, err
|
||||
}
|
||||
// Make sure we don't leak our literals buffer
|
||||
if len(literals) != litRegenSize {
|
||||
return in, fmt.Errorf("literal output size mismatch want %d, got %d", litRegenSize, len(literals))
|
||||
}
|
||||
// Re-cap to get extra size.
|
||||
literals = b.literalBuf[:len(literals)]
|
||||
if debugDecoder {
|
||||
printf("Decompressed %d literals into %d bytes\n", litCompSize, litRegenSize)
|
||||
}
|
||||
}
|
||||
hist.decoders.literals = literals
|
||||
return in, nil
|
||||
}
|
||||
|
||||
// decodeCompressed will start decompressing a block.
|
||||
func (b *blockDec) decodeCompressed(hist *history) error {
|
||||
in := b.data
|
||||
in, err := b.decodeLiterals(in, hist)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
err = b.prepareSequences(in, hist)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if hist.decoders.nSeqs == 0 {
|
||||
b.dst = append(b.dst, hist.decoders.literals...)
|
||||
return nil
|
||||
}
|
||||
before := len(hist.decoders.out)
|
||||
err = hist.decoders.decodeSync(hist.b[hist.ignoreBuffer:])
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if hist.decoders.maxSyncLen > 0 {
|
||||
hist.decoders.maxSyncLen += uint64(before)
|
||||
hist.decoders.maxSyncLen -= uint64(len(hist.decoders.out))
|
||||
}
|
||||
b.dst = hist.decoders.out
|
||||
hist.recentOffsets = hist.decoders.prevOffset
|
||||
return nil
|
||||
}
|
||||
|
||||
func (b *blockDec) prepareSequences(in []byte, hist *history) (err error) {
|
||||
if debugDecoder {
|
||||
printf("prepareSequences: %d byte(s) input\n", len(in))
|
||||
}
|
||||
// Decode Sequences
|
||||
// https://github.com/facebook/zstd/blob/dev/doc/zstd_compression_format.md#sequences-section
|
||||
if len(in) < 1 {
|
||||
return ErrBlockTooSmall
|
||||
}
|
||||
var nSeqs int
|
||||
seqHeader := in[0]
|
||||
switch {
|
||||
case seqHeader < 128:
|
||||
nSeqs = int(seqHeader)
|
||||
in = in[1:]
|
||||
case seqHeader < 255:
|
||||
if len(in) < 2 {
|
||||
return ErrBlockTooSmall
|
||||
}
|
||||
nSeqs = int(seqHeader-128)<<8 | int(in[1])
|
||||
in = in[2:]
|
||||
case seqHeader == 255:
|
||||
if len(in) < 3 {
|
||||
return ErrBlockTooSmall
|
||||
}
|
||||
nSeqs = 0x7f00 + int(in[1]) + (int(in[2]) << 8)
|
||||
in = in[3:]
|
||||
}
|
||||
if nSeqs == 0 && len(in) != 0 {
|
||||
// When no sequences, there should not be any more data...
|
||||
if debugDecoder {
|
||||
printf("prepareSequences: 0 sequences, but %d byte(s) left on stream\n", len(in))
|
||||
}
|
||||
return ErrUnexpectedBlockSize
|
||||
}
|
||||
|
||||
var seqs = &hist.decoders
|
||||
seqs.nSeqs = nSeqs
|
||||
if nSeqs > 0 {
|
||||
if len(in) < 1 {
|
||||
return ErrBlockTooSmall
|
||||
}
|
||||
br := byteReader{b: in, off: 0}
|
||||
compMode := br.Uint8()
|
||||
br.advance(1)
|
||||
if debugDecoder {
|
||||
printf("Compression modes: 0b%b", compMode)
|
||||
}
|
||||
if compMode&3 != 0 {
|
||||
return errors.New("corrupt block: reserved bits not zero")
|
||||
}
|
||||
for i := uint(0); i < 3; i++ {
|
||||
mode := seqCompMode((compMode >> (6 - i*2)) & 3)
|
||||
if debugDecoder {
|
||||
println("Table", tableIndex(i), "is", mode)
|
||||
}
|
||||
var seq *sequenceDec
|
||||
switch tableIndex(i) {
|
||||
case tableLiteralLengths:
|
||||
seq = &seqs.litLengths
|
||||
case tableOffsets:
|
||||
seq = &seqs.offsets
|
||||
case tableMatchLengths:
|
||||
seq = &seqs.matchLengths
|
||||
default:
|
||||
panic("unknown table")
|
||||
}
|
||||
switch mode {
|
||||
case compModePredefined:
|
||||
if seq.fse != nil && !seq.fse.preDefined {
|
||||
fseDecoderPool.Put(seq.fse)
|
||||
}
|
||||
seq.fse = &fsePredef[i]
|
||||
case compModeRLE:
|
||||
if br.remain() < 1 {
|
||||
return ErrBlockTooSmall
|
||||
}
|
||||
v := br.Uint8()
|
||||
br.advance(1)
|
||||
if seq.fse == nil || seq.fse.preDefined {
|
||||
seq.fse = fseDecoderPool.Get().(*fseDecoder)
|
||||
}
|
||||
symb, err := decSymbolValue(v, symbolTableX[i])
|
||||
if err != nil {
|
||||
printf("RLE Transform table (%v) error: %v", tableIndex(i), err)
|
||||
return err
|
||||
}
|
||||
seq.fse.setRLE(symb)
|
||||
if debugDecoder {
|
||||
printf("RLE set to 0x%x, code: %v", symb, v)
|
||||
}
|
||||
case compModeFSE:
|
||||
if debugDecoder {
|
||||
println("Reading table for", tableIndex(i))
|
||||
}
|
||||
if seq.fse == nil || seq.fse.preDefined {
|
||||
seq.fse = fseDecoderPool.Get().(*fseDecoder)
|
||||
}
|
||||
err := seq.fse.readNCount(&br, uint16(maxTableSymbol[i]))
|
||||
if err != nil {
|
||||
println("Read table error:", err)
|
||||
return err
|
||||
}
|
||||
err = seq.fse.transform(symbolTableX[i])
|
||||
if err != nil {
|
||||
println("Transform table error:", err)
|
||||
return err
|
||||
}
|
||||
if debugDecoder {
|
||||
println("Read table ok", "symbolLen:", seq.fse.symbolLen)
|
||||
}
|
||||
case compModeRepeat:
|
||||
seq.repeat = true
|
||||
}
|
||||
if br.overread() {
|
||||
return io.ErrUnexpectedEOF
|
||||
}
|
||||
}
|
||||
in = br.unread()
|
||||
}
|
||||
if debugDecoder {
|
||||
println("Literals:", len(seqs.literals), "hash:", xxhash.Sum64(seqs.literals), "and", seqs.nSeqs, "sequences.")
|
||||
}
|
||||
|
||||
if nSeqs == 0 {
|
||||
if len(b.sequence) > 0 {
|
||||
b.sequence = b.sequence[:0]
|
||||
}
|
||||
return nil
|
||||
}
|
||||
br := seqs.br
|
||||
if br == nil {
|
||||
br = &bitReader{}
|
||||
}
|
||||
if err := br.init(in); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if err := seqs.initialize(br, hist, b.dst); err != nil {
|
||||
println("initializing sequences:", err)
|
||||
return err
|
||||
}
|
||||
// Extract blocks...
|
||||
if false && hist.dict == nil {
|
||||
fatalErr := func(err error) {
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
}
|
||||
fn := fmt.Sprintf("n-%d-lits-%d-prev-%d-%d-%d-win-%d.blk", hist.decoders.nSeqs, len(hist.decoders.literals), hist.recentOffsets[0], hist.recentOffsets[1], hist.recentOffsets[2], hist.windowSize)
|
||||
var buf bytes.Buffer
|
||||
fatalErr(binary.Write(&buf, binary.LittleEndian, hist.decoders.litLengths.fse))
|
||||
fatalErr(binary.Write(&buf, binary.LittleEndian, hist.decoders.matchLengths.fse))
|
||||
fatalErr(binary.Write(&buf, binary.LittleEndian, hist.decoders.offsets.fse))
|
||||
buf.Write(in)
|
||||
os.WriteFile(filepath.Join("testdata", "seqs", fn), buf.Bytes(), os.ModePerm)
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func (b *blockDec) decodeSequences(hist *history) error {
|
||||
if cap(b.sequence) < hist.decoders.nSeqs {
|
||||
if b.lowMem {
|
||||
b.sequence = make([]seqVals, 0, hist.decoders.nSeqs)
|
||||
} else {
|
||||
b.sequence = make([]seqVals, 0, 0x7F00+0xffff)
|
||||
}
|
||||
}
|
||||
b.sequence = b.sequence[:hist.decoders.nSeqs]
|
||||
if hist.decoders.nSeqs == 0 {
|
||||
hist.decoders.seqSize = len(hist.decoders.literals)
|
||||
return nil
|
||||
}
|
||||
hist.decoders.windowSize = hist.windowSize
|
||||
hist.decoders.prevOffset = hist.recentOffsets
|
||||
|
||||
err := hist.decoders.decode(b.sequence)
|
||||
hist.recentOffsets = hist.decoders.prevOffset
|
||||
return err
|
||||
}
|
||||
|
||||
func (b *blockDec) executeSequences(hist *history) error {
|
||||
hbytes := hist.b
|
||||
if len(hbytes) > hist.windowSize {
|
||||
hbytes = hbytes[len(hbytes)-hist.windowSize:]
|
||||
// We do not need history anymore.
|
||||
if hist.dict != nil {
|
||||
hist.dict.content = nil
|
||||
}
|
||||
}
|
||||
hist.decoders.windowSize = hist.windowSize
|
||||
hist.decoders.out = b.dst[:0]
|
||||
err := hist.decoders.execute(b.sequence, hbytes)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
return b.updateHistory(hist)
|
||||
}
|
||||
|
||||
func (b *blockDec) updateHistory(hist *history) error {
|
||||
if len(b.data) > maxCompressedBlockSize {
|
||||
return fmt.Errorf("compressed block size too large (%d)", len(b.data))
|
||||
}
|
||||
// Set output and release references.
|
||||
b.dst = hist.decoders.out
|
||||
hist.recentOffsets = hist.decoders.prevOffset
|
||||
|
||||
if b.Last {
|
||||
// if last block we don't care about history.
|
||||
println("Last block, no history returned")
|
||||
hist.b = hist.b[:0]
|
||||
return nil
|
||||
} else {
|
||||
hist.append(b.dst)
|
||||
if debugDecoder {
|
||||
println("Finished block with ", len(b.sequence), "sequences. Added", len(b.dst), "to history, now length", len(hist.b))
|
||||
}
|
||||
}
|
||||
hist.decoders.out, hist.decoders.literals = nil, nil
|
||||
|
||||
return nil
|
||||
}
|
||||
909
vendor/github.com/klauspost/compress/zstd/blockenc.go
generated
vendored
909
vendor/github.com/klauspost/compress/zstd/blockenc.go
generated
vendored
@ -1,909 +0,0 @@
|
||||
// Copyright 2019+ Klaus Post. All rights reserved.
|
||||
// License information can be found in the LICENSE file.
|
||||
// Based on work by Yann Collet, released under BSD License.
|
||||
|
||||
package zstd
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"math"
|
||||
"math/bits"
|
||||
|
||||
"github.com/klauspost/compress/huff0"
|
||||
)
|
||||
|
||||
type blockEnc struct {
|
||||
size int
|
||||
literals []byte
|
||||
sequences []seq
|
||||
coders seqCoders
|
||||
litEnc *huff0.Scratch
|
||||
dictLitEnc *huff0.Scratch
|
||||
wr bitWriter
|
||||
|
||||
extraLits int
|
||||
output []byte
|
||||
recentOffsets [3]uint32
|
||||
prevRecentOffsets [3]uint32
|
||||
|
||||
last bool
|
||||
lowMem bool
|
||||
}
|
||||
|
||||
// init should be used once the block has been created.
|
||||
// If called more than once, the effect is the same as calling reset.
|
||||
func (b *blockEnc) init() {
|
||||
if b.lowMem {
|
||||
// 1K literals
|
||||
if cap(b.literals) < 1<<10 {
|
||||
b.literals = make([]byte, 0, 1<<10)
|
||||
}
|
||||
const defSeqs = 20
|
||||
if cap(b.sequences) < defSeqs {
|
||||
b.sequences = make([]seq, 0, defSeqs)
|
||||
}
|
||||
// 1K
|
||||
if cap(b.output) < 1<<10 {
|
||||
b.output = make([]byte, 0, 1<<10)
|
||||
}
|
||||
} else {
|
||||
if cap(b.literals) < maxCompressedBlockSize {
|
||||
b.literals = make([]byte, 0, maxCompressedBlockSize)
|
||||
}
|
||||
const defSeqs = 2000
|
||||
if cap(b.sequences) < defSeqs {
|
||||
b.sequences = make([]seq, 0, defSeqs)
|
||||
}
|
||||
if cap(b.output) < maxCompressedBlockSize {
|
||||
b.output = make([]byte, 0, maxCompressedBlockSize)
|
||||
}
|
||||
}
|
||||
|
||||
if b.coders.mlEnc == nil {
|
||||
b.coders.mlEnc = &fseEncoder{}
|
||||
b.coders.mlPrev = &fseEncoder{}
|
||||
b.coders.ofEnc = &fseEncoder{}
|
||||
b.coders.ofPrev = &fseEncoder{}
|
||||
b.coders.llEnc = &fseEncoder{}
|
||||
b.coders.llPrev = &fseEncoder{}
|
||||
}
|
||||
b.litEnc = &huff0.Scratch{WantLogLess: 4}
|
||||
b.reset(nil)
|
||||
}
|
||||
|
||||
// initNewEncode can be used to reset offsets and encoders to the initial state.
|
||||
func (b *blockEnc) initNewEncode() {
|
||||
b.recentOffsets = [3]uint32{1, 4, 8}
|
||||
b.litEnc.Reuse = huff0.ReusePolicyNone
|
||||
b.coders.setPrev(nil, nil, nil)
|
||||
}
|
||||
|
||||
// reset will reset the block for a new encode, but in the same stream,
|
||||
// meaning that state will be carried over, but the block content is reset.
|
||||
// If a previous block is provided, the recent offsets are carried over.
|
||||
func (b *blockEnc) reset(prev *blockEnc) {
|
||||
b.extraLits = 0
|
||||
b.literals = b.literals[:0]
|
||||
b.size = 0
|
||||
b.sequences = b.sequences[:0]
|
||||
b.output = b.output[:0]
|
||||
b.last = false
|
||||
if prev != nil {
|
||||
b.recentOffsets = prev.prevRecentOffsets
|
||||
}
|
||||
b.dictLitEnc = nil
|
||||
}
|
||||
|
||||
// reset will reset the block for a new encode, but in the same stream,
|
||||
// meaning that state will be carried over, but the block content is reset.
|
||||
// If a previous block is provided, the recent offsets are carried over.
|
||||
func (b *blockEnc) swapEncoders(prev *blockEnc) {
|
||||
b.coders.swap(&prev.coders)
|
||||
b.litEnc, prev.litEnc = prev.litEnc, b.litEnc
|
||||
}
|
||||
|
||||
// blockHeader contains the information for a block header.
|
||||
type blockHeader uint32
|
||||
|
||||
// setLast sets the 'last' indicator on a block.
|
||||
func (h *blockHeader) setLast(b bool) {
|
||||
if b {
|
||||
*h = *h | 1
|
||||
} else {
|
||||
const mask = (1 << 24) - 2
|
||||
*h = *h & mask
|
||||
}
|
||||
}
|
||||
|
||||
// setSize will store the compressed size of a block.
|
||||
func (h *blockHeader) setSize(v uint32) {
|
||||
const mask = 7
|
||||
*h = (*h)&mask | blockHeader(v<<3)
|
||||
}
|
||||
|
||||
// setType sets the block type.
|
||||
func (h *blockHeader) setType(t blockType) {
|
||||
const mask = 1 | (((1 << 24) - 1) ^ 7)
|
||||
*h = (*h & mask) | blockHeader(t<<1)
|
||||
}
|
||||
|
||||
// appendTo will append the block header to a slice.
|
||||
func (h blockHeader) appendTo(b []byte) []byte {
|
||||
return append(b, uint8(h), uint8(h>>8), uint8(h>>16))
|
||||
}
|
||||
|
||||
// String returns a string representation of the block.
|
||||
func (h blockHeader) String() string {
|
||||
return fmt.Sprintf("Type: %d, Size: %d, Last:%t", (h>>1)&3, h>>3, h&1 == 1)
|
||||
}
|
||||
|
||||
// literalsHeader contains literals header information.
|
||||
type literalsHeader uint64
|
||||
|
||||
// setType can be used to set the type of literal block.
|
||||
func (h *literalsHeader) setType(t literalsBlockType) {
|
||||
const mask = math.MaxUint64 - 3
|
||||
*h = (*h & mask) | literalsHeader(t)
|
||||
}
|
||||
|
||||
// setSize can be used to set a single size, for uncompressed and RLE content.
|
||||
func (h *literalsHeader) setSize(regenLen int) {
|
||||
inBits := bits.Len32(uint32(regenLen))
|
||||
// Only retain 2 bits
|
||||
const mask = 3
|
||||
lh := uint64(*h & mask)
|
||||
switch {
|
||||
case inBits < 5:
|
||||
lh |= (uint64(regenLen) << 3) | (1 << 60)
|
||||
if debugEncoder {
|
||||
got := int(lh>>3) & 0xff
|
||||
if got != regenLen {
|
||||
panic(fmt.Sprint("litRegenSize = ", regenLen, "(want) != ", got, "(got)"))
|
||||
}
|
||||
}
|
||||
case inBits < 12:
|
||||
lh |= (1 << 2) | (uint64(regenLen) << 4) | (2 << 60)
|
||||
case inBits < 20:
|
||||
lh |= (3 << 2) | (uint64(regenLen) << 4) | (3 << 60)
|
||||
default:
|
||||
panic(fmt.Errorf("internal error: block too big (%d)", regenLen))
|
||||
}
|
||||
*h = literalsHeader(lh)
|
||||
}
|
||||
|
||||
// setSizes will set the size of a compressed literals section and the input length.
|
||||
func (h *literalsHeader) setSizes(compLen, inLen int, single bool) {
|
||||
compBits, inBits := bits.Len32(uint32(compLen)), bits.Len32(uint32(inLen))
|
||||
// Only retain 2 bits
|
||||
const mask = 3
|
||||
lh := uint64(*h & mask)
|
||||
switch {
|
||||
case compBits <= 10 && inBits <= 10:
|
||||
if !single {
|
||||
lh |= 1 << 2
|
||||
}
|
||||
lh |= (uint64(inLen) << 4) | (uint64(compLen) << (10 + 4)) | (3 << 60)
|
||||
if debugEncoder {
|
||||
const mmask = (1 << 24) - 1
|
||||
n := (lh >> 4) & mmask
|
||||
if int(n&1023) != inLen {
|
||||
panic(fmt.Sprint("regensize:", int(n&1023), "!=", inLen, inBits))
|
||||
}
|
||||
if int(n>>10) != compLen {
|
||||
panic(fmt.Sprint("compsize:", int(n>>10), "!=", compLen, compBits))
|
||||
}
|
||||
}
|
||||
case compBits <= 14 && inBits <= 14:
|
||||
lh |= (2 << 2) | (uint64(inLen) << 4) | (uint64(compLen) << (14 + 4)) | (4 << 60)
|
||||
if single {
|
||||
panic("single stream used with more than 10 bits length.")
|
||||
}
|
||||
case compBits <= 18 && inBits <= 18:
|
||||
lh |= (3 << 2) | (uint64(inLen) << 4) | (uint64(compLen) << (18 + 4)) | (5 << 60)
|
||||
if single {
|
||||
panic("single stream used with more than 10 bits length.")
|
||||
}
|
||||
default:
|
||||
panic("internal error: block too big")
|
||||
}
|
||||
*h = literalsHeader(lh)
|
||||
}
|
||||
|
||||
// appendTo will append the literals header to a byte slice.
|
||||
func (h literalsHeader) appendTo(b []byte) []byte {
|
||||
size := uint8(h >> 60)
|
||||
switch size {
|
||||
case 1:
|
||||
b = append(b, uint8(h))
|
||||
case 2:
|
||||
b = append(b, uint8(h), uint8(h>>8))
|
||||
case 3:
|
||||
b = append(b, uint8(h), uint8(h>>8), uint8(h>>16))
|
||||
case 4:
|
||||
b = append(b, uint8(h), uint8(h>>8), uint8(h>>16), uint8(h>>24))
|
||||
case 5:
|
||||
b = append(b, uint8(h), uint8(h>>8), uint8(h>>16), uint8(h>>24), uint8(h>>32))
|
||||
default:
|
||||
panic(fmt.Errorf("internal error: literalsHeader has invalid size (%d)", size))
|
||||
}
|
||||
return b
|
||||
}
|
||||
|
||||
// size returns the output size with currently set values.
|
||||
func (h literalsHeader) size() int {
|
||||
return int(h >> 60)
|
||||
}
|
||||
|
||||
func (h literalsHeader) String() string {
|
||||
return fmt.Sprintf("Type: %d, SizeFormat: %d, Size: 0x%d, Bytes:%d", literalsBlockType(h&3), (h>>2)&3, h&((1<<60)-1)>>4, h>>60)
|
||||
}
|
||||
|
||||
// pushOffsets will push the recent offsets to the backup store.
|
||||
func (b *blockEnc) pushOffsets() {
|
||||
b.prevRecentOffsets = b.recentOffsets
|
||||
}
|
||||
|
||||
// pushOffsets will push the recent offsets to the backup store.
|
||||
func (b *blockEnc) popOffsets() {
|
||||
b.recentOffsets = b.prevRecentOffsets
|
||||
}
|
||||
|
||||
// matchOffset will adjust recent offsets and return the adjusted one,
|
||||
// if it matches a previous offset.
|
||||
func (b *blockEnc) matchOffset(offset, lits uint32) uint32 {
|
||||
// Check if offset is one of the recent offsets.
|
||||
// Adjusts the output offset accordingly.
|
||||
// Gives a tiny bit of compression, typically around 1%.
|
||||
if true {
|
||||
if lits > 0 {
|
||||
switch offset {
|
||||
case b.recentOffsets[0]:
|
||||
offset = 1
|
||||
case b.recentOffsets[1]:
|
||||
b.recentOffsets[1] = b.recentOffsets[0]
|
||||
b.recentOffsets[0] = offset
|
||||
offset = 2
|
||||
case b.recentOffsets[2]:
|
||||
b.recentOffsets[2] = b.recentOffsets[1]
|
||||
b.recentOffsets[1] = b.recentOffsets[0]
|
||||
b.recentOffsets[0] = offset
|
||||
offset = 3
|
||||
default:
|
||||
b.recentOffsets[2] = b.recentOffsets[1]
|
||||
b.recentOffsets[1] = b.recentOffsets[0]
|
||||
b.recentOffsets[0] = offset
|
||||
offset += 3
|
||||
}
|
||||
} else {
|
||||
switch offset {
|
||||
case b.recentOffsets[1]:
|
||||
b.recentOffsets[1] = b.recentOffsets[0]
|
||||
b.recentOffsets[0] = offset
|
||||
offset = 1
|
||||
case b.recentOffsets[2]:
|
||||
b.recentOffsets[2] = b.recentOffsets[1]
|
||||
b.recentOffsets[1] = b.recentOffsets[0]
|
||||
b.recentOffsets[0] = offset
|
||||
offset = 2
|
||||
case b.recentOffsets[0] - 1:
|
||||
b.recentOffsets[2] = b.recentOffsets[1]
|
||||
b.recentOffsets[1] = b.recentOffsets[0]
|
||||
b.recentOffsets[0] = offset
|
||||
offset = 3
|
||||
default:
|
||||
b.recentOffsets[2] = b.recentOffsets[1]
|
||||
b.recentOffsets[1] = b.recentOffsets[0]
|
||||
b.recentOffsets[0] = offset
|
||||
offset += 3
|
||||
}
|
||||
}
|
||||
} else {
|
||||
offset += 3
|
||||
}
|
||||
return offset
|
||||
}
|
||||
|
||||
// encodeRaw can be used to set the output to a raw representation of supplied bytes.
|
||||
func (b *blockEnc) encodeRaw(a []byte) {
|
||||
var bh blockHeader
|
||||
bh.setLast(b.last)
|
||||
bh.setSize(uint32(len(a)))
|
||||
bh.setType(blockTypeRaw)
|
||||
b.output = bh.appendTo(b.output[:0])
|
||||
b.output = append(b.output, a...)
|
||||
if debugEncoder {
|
||||
println("Adding RAW block, length", len(a), "last:", b.last)
|
||||
}
|
||||
}
|
||||
|
||||
// encodeRaw can be used to set the output to a raw representation of supplied bytes.
|
||||
func (b *blockEnc) encodeRawTo(dst, src []byte) []byte {
|
||||
var bh blockHeader
|
||||
bh.setLast(b.last)
|
||||
bh.setSize(uint32(len(src)))
|
||||
bh.setType(blockTypeRaw)
|
||||
dst = bh.appendTo(dst)
|
||||
dst = append(dst, src...)
|
||||
if debugEncoder {
|
||||
println("Adding RAW block, length", len(src), "last:", b.last)
|
||||
}
|
||||
return dst
|
||||
}
|
||||
|
||||
// encodeLits can be used if the block is only litLen.
|
||||
func (b *blockEnc) encodeLits(lits []byte, raw bool) error {
|
||||
var bh blockHeader
|
||||
bh.setLast(b.last)
|
||||
bh.setSize(uint32(len(lits)))
|
||||
|
||||
// Don't compress extremely small blocks
|
||||
if len(lits) < 8 || (len(lits) < 32 && b.dictLitEnc == nil) || raw {
|
||||
if debugEncoder {
|
||||
println("Adding RAW block, length", len(lits), "last:", b.last)
|
||||
}
|
||||
bh.setType(blockTypeRaw)
|
||||
b.output = bh.appendTo(b.output)
|
||||
b.output = append(b.output, lits...)
|
||||
return nil
|
||||
}
|
||||
|
||||
var (
|
||||
out []byte
|
||||
reUsed, single bool
|
||||
err error
|
||||
)
|
||||
if b.dictLitEnc != nil {
|
||||
b.litEnc.TransferCTable(b.dictLitEnc)
|
||||
b.litEnc.Reuse = huff0.ReusePolicyAllow
|
||||
b.dictLitEnc = nil
|
||||
}
|
||||
if len(lits) >= 1024 {
|
||||
// Use 4 Streams.
|
||||
out, reUsed, err = huff0.Compress4X(lits, b.litEnc)
|
||||
} else if len(lits) > 16 {
|
||||
// Use 1 stream
|
||||
single = true
|
||||
out, reUsed, err = huff0.Compress1X(lits, b.litEnc)
|
||||
} else {
|
||||
err = huff0.ErrIncompressible
|
||||
}
|
||||
if err == nil && len(out)+5 > len(lits) {
|
||||
// If we are close, we may still be worse or equal to raw.
|
||||
var lh literalsHeader
|
||||
lh.setSizes(len(out), len(lits), single)
|
||||
if len(out)+lh.size() >= len(lits) {
|
||||
err = huff0.ErrIncompressible
|
||||
}
|
||||
}
|
||||
switch err {
|
||||
case huff0.ErrIncompressible:
|
||||
if debugEncoder {
|
||||
println("Adding RAW block, length", len(lits), "last:", b.last)
|
||||
}
|
||||
bh.setType(blockTypeRaw)
|
||||
b.output = bh.appendTo(b.output)
|
||||
b.output = append(b.output, lits...)
|
||||
return nil
|
||||
case huff0.ErrUseRLE:
|
||||
if debugEncoder {
|
||||
println("Adding RLE block, length", len(lits))
|
||||
}
|
||||
bh.setType(blockTypeRLE)
|
||||
b.output = bh.appendTo(b.output)
|
||||
b.output = append(b.output, lits[0])
|
||||
return nil
|
||||
case nil:
|
||||
default:
|
||||
return err
|
||||
}
|
||||
// Compressed...
|
||||
// Now, allow reuse
|
||||
b.litEnc.Reuse = huff0.ReusePolicyAllow
|
||||
bh.setType(blockTypeCompressed)
|
||||
var lh literalsHeader
|
||||
if reUsed {
|
||||
if debugEncoder {
|
||||
println("Reused tree, compressed to", len(out))
|
||||
}
|
||||
lh.setType(literalsBlockTreeless)
|
||||
} else {
|
||||
if debugEncoder {
|
||||
println("New tree, compressed to", len(out), "tree size:", len(b.litEnc.OutTable))
|
||||
}
|
||||
lh.setType(literalsBlockCompressed)
|
||||
}
|
||||
// Set sizes
|
||||
lh.setSizes(len(out), len(lits), single)
|
||||
bh.setSize(uint32(len(out) + lh.size() + 1))
|
||||
|
||||
// Write block headers.
|
||||
b.output = bh.appendTo(b.output)
|
||||
b.output = lh.appendTo(b.output)
|
||||
// Add compressed data.
|
||||
b.output = append(b.output, out...)
|
||||
// No sequences.
|
||||
b.output = append(b.output, 0)
|
||||
return nil
|
||||
}
|
||||
|
||||
// encodeRLE will encode an RLE block.
|
||||
func (b *blockEnc) encodeRLE(val byte, length uint32) {
|
||||
var bh blockHeader
|
||||
bh.setLast(b.last)
|
||||
bh.setSize(length)
|
||||
bh.setType(blockTypeRLE)
|
||||
b.output = bh.appendTo(b.output)
|
||||
b.output = append(b.output, val)
|
||||
}
|
||||
|
||||
// fuzzFseEncoder can be used to fuzz the FSE encoder.
|
||||
func fuzzFseEncoder(data []byte) int {
|
||||
if len(data) > maxSequences || len(data) < 2 {
|
||||
return 0
|
||||
}
|
||||
enc := fseEncoder{}
|
||||
hist := enc.Histogram()
|
||||
maxSym := uint8(0)
|
||||
for i, v := range data {
|
||||
v = v & 63
|
||||
data[i] = v
|
||||
hist[v]++
|
||||
if v > maxSym {
|
||||
maxSym = v
|
||||
}
|
||||
}
|
||||
if maxSym == 0 {
|
||||
// All 0
|
||||
return 0
|
||||
}
|
||||
maxCount := func(a []uint32) int {
|
||||
var max uint32
|
||||
for _, v := range a {
|
||||
if v > max {
|
||||
max = v
|
||||
}
|
||||
}
|
||||
return int(max)
|
||||
}
|
||||
cnt := maxCount(hist[:maxSym])
|
||||
if cnt == len(data) {
|
||||
// RLE
|
||||
return 0
|
||||
}
|
||||
enc.HistogramFinished(maxSym, cnt)
|
||||
err := enc.normalizeCount(len(data))
|
||||
if err != nil {
|
||||
return 0
|
||||
}
|
||||
_, err = enc.writeCount(nil)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
return 1
|
||||
}
|
||||
|
||||
// encode will encode the block and append the output in b.output.
|
||||
// Previous offset codes must be pushed if more blocks are expected.
|
||||
func (b *blockEnc) encode(org []byte, raw, rawAllLits bool) error {
|
||||
if len(b.sequences) == 0 {
|
||||
return b.encodeLits(b.literals, rawAllLits)
|
||||
}
|
||||
if len(b.sequences) == 1 && len(org) > 0 && len(b.literals) <= 1 {
|
||||
// Check common RLE cases.
|
||||
seq := b.sequences[0]
|
||||
if seq.litLen == uint32(len(b.literals)) && seq.offset-3 == 1 {
|
||||
// Offset == 1 and 0 or 1 literals.
|
||||
b.encodeRLE(org[0], b.sequences[0].matchLen+zstdMinMatch+seq.litLen)
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
// We want some difference to at least account for the headers.
|
||||
saved := b.size - len(b.literals) - (b.size >> 6)
|
||||
if saved < 16 {
|
||||
if org == nil {
|
||||
return errIncompressible
|
||||
}
|
||||
b.popOffsets()
|
||||
return b.encodeLits(org, rawAllLits)
|
||||
}
|
||||
|
||||
var bh blockHeader
|
||||
var lh literalsHeader
|
||||
bh.setLast(b.last)
|
||||
bh.setType(blockTypeCompressed)
|
||||
// Store offset of the block header. Needed when we know the size.
|
||||
bhOffset := len(b.output)
|
||||
b.output = bh.appendTo(b.output)
|
||||
|
||||
var (
|
||||
out []byte
|
||||
reUsed, single bool
|
||||
err error
|
||||
)
|
||||
if b.dictLitEnc != nil {
|
||||
b.litEnc.TransferCTable(b.dictLitEnc)
|
||||
b.litEnc.Reuse = huff0.ReusePolicyAllow
|
||||
b.dictLitEnc = nil
|
||||
}
|
||||
if len(b.literals) >= 1024 && !raw {
|
||||
// Use 4 Streams.
|
||||
out, reUsed, err = huff0.Compress4X(b.literals, b.litEnc)
|
||||
} else if len(b.literals) > 16 && !raw {
|
||||
// Use 1 stream
|
||||
single = true
|
||||
out, reUsed, err = huff0.Compress1X(b.literals, b.litEnc)
|
||||
} else {
|
||||
err = huff0.ErrIncompressible
|
||||
}
|
||||
|
||||
if err == nil && len(out)+5 > len(b.literals) {
|
||||
// If we are close, we may still be worse or equal to raw.
|
||||
var lh literalsHeader
|
||||
lh.setSize(len(b.literals))
|
||||
szRaw := lh.size()
|
||||
lh.setSizes(len(out), len(b.literals), single)
|
||||
szComp := lh.size()
|
||||
if len(out)+szComp >= len(b.literals)+szRaw {
|
||||
err = huff0.ErrIncompressible
|
||||
}
|
||||
}
|
||||
switch err {
|
||||
case huff0.ErrIncompressible:
|
||||
lh.setType(literalsBlockRaw)
|
||||
lh.setSize(len(b.literals))
|
||||
b.output = lh.appendTo(b.output)
|
||||
b.output = append(b.output, b.literals...)
|
||||
if debugEncoder {
|
||||
println("Adding literals RAW, length", len(b.literals))
|
||||
}
|
||||
case huff0.ErrUseRLE:
|
||||
lh.setType(literalsBlockRLE)
|
||||
lh.setSize(len(b.literals))
|
||||
b.output = lh.appendTo(b.output)
|
||||
b.output = append(b.output, b.literals[0])
|
||||
if debugEncoder {
|
||||
println("Adding literals RLE")
|
||||
}
|
||||
case nil:
|
||||
// Compressed litLen...
|
||||
if reUsed {
|
||||
if debugEncoder {
|
||||
println("reused tree")
|
||||
}
|
||||
lh.setType(literalsBlockTreeless)
|
||||
} else {
|
||||
if debugEncoder {
|
||||
println("new tree, size:", len(b.litEnc.OutTable))
|
||||
}
|
||||
lh.setType(literalsBlockCompressed)
|
||||
if debugEncoder {
|
||||
_, _, err := huff0.ReadTable(out, nil)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
}
|
||||
}
|
||||
lh.setSizes(len(out), len(b.literals), single)
|
||||
if debugEncoder {
|
||||
printf("Compressed %d literals to %d bytes", len(b.literals), len(out))
|
||||
println("Adding literal header:", lh)
|
||||
}
|
||||
b.output = lh.appendTo(b.output)
|
||||
b.output = append(b.output, out...)
|
||||
b.litEnc.Reuse = huff0.ReusePolicyAllow
|
||||
if debugEncoder {
|
||||
println("Adding literals compressed")
|
||||
}
|
||||
default:
|
||||
if debugEncoder {
|
||||
println("Adding literals ERROR:", err)
|
||||
}
|
||||
return err
|
||||
}
|
||||
// Sequence compression
|
||||
|
||||
// Write the number of sequences
|
||||
switch {
|
||||
case len(b.sequences) < 128:
|
||||
b.output = append(b.output, uint8(len(b.sequences)))
|
||||
case len(b.sequences) < 0x7f00: // TODO: this could be wrong
|
||||
n := len(b.sequences)
|
||||
b.output = append(b.output, 128+uint8(n>>8), uint8(n))
|
||||
default:
|
||||
n := len(b.sequences) - 0x7f00
|
||||
b.output = append(b.output, 255, uint8(n), uint8(n>>8))
|
||||
}
|
||||
if debugEncoder {
|
||||
println("Encoding", len(b.sequences), "sequences")
|
||||
}
|
||||
b.genCodes()
|
||||
llEnc := b.coders.llEnc
|
||||
ofEnc := b.coders.ofEnc
|
||||
mlEnc := b.coders.mlEnc
|
||||
err = llEnc.normalizeCount(len(b.sequences))
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
err = ofEnc.normalizeCount(len(b.sequences))
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
err = mlEnc.normalizeCount(len(b.sequences))
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
// Choose the best compression mode for each type.
|
||||
// Will evaluate the new vs predefined and previous.
|
||||
chooseComp := func(cur, prev, preDef *fseEncoder) (*fseEncoder, seqCompMode) {
|
||||
// See if predefined/previous is better
|
||||
hist := cur.count[:cur.symbolLen]
|
||||
nSize := cur.approxSize(hist) + cur.maxHeaderSize()
|
||||
predefSize := preDef.approxSize(hist)
|
||||
prevSize := prev.approxSize(hist)
|
||||
|
||||
// Add a small penalty for new encoders.
|
||||
// Don't bother with extremely small (<2 byte gains).
|
||||
nSize = nSize + (nSize+2*8*16)>>4
|
||||
switch {
|
||||
case predefSize <= prevSize && predefSize <= nSize || forcePreDef:
|
||||
if debugEncoder {
|
||||
println("Using predefined", predefSize>>3, "<=", nSize>>3)
|
||||
}
|
||||
return preDef, compModePredefined
|
||||
case prevSize <= nSize:
|
||||
if debugEncoder {
|
||||
println("Using previous", prevSize>>3, "<=", nSize>>3)
|
||||
}
|
||||
return prev, compModeRepeat
|
||||
default:
|
||||
if debugEncoder {
|
||||
println("Using new, predef", predefSize>>3, ". previous:", prevSize>>3, ">", nSize>>3, "header max:", cur.maxHeaderSize()>>3, "bytes")
|
||||
println("tl:", cur.actualTableLog, "symbolLen:", cur.symbolLen, "norm:", cur.norm[:cur.symbolLen], "hist", cur.count[:cur.symbolLen])
|
||||
}
|
||||
return cur, compModeFSE
|
||||
}
|
||||
}
|
||||
|
||||
// Write compression mode
|
||||
var mode uint8
|
||||
if llEnc.useRLE {
|
||||
mode |= uint8(compModeRLE) << 6
|
||||
llEnc.setRLE(b.sequences[0].llCode)
|
||||
if debugEncoder {
|
||||
println("llEnc.useRLE")
|
||||
}
|
||||
} else {
|
||||
var m seqCompMode
|
||||
llEnc, m = chooseComp(llEnc, b.coders.llPrev, &fsePredefEnc[tableLiteralLengths])
|
||||
mode |= uint8(m) << 6
|
||||
}
|
||||
if ofEnc.useRLE {
|
||||
mode |= uint8(compModeRLE) << 4
|
||||
ofEnc.setRLE(b.sequences[0].ofCode)
|
||||
if debugEncoder {
|
||||
println("ofEnc.useRLE")
|
||||
}
|
||||
} else {
|
||||
var m seqCompMode
|
||||
ofEnc, m = chooseComp(ofEnc, b.coders.ofPrev, &fsePredefEnc[tableOffsets])
|
||||
mode |= uint8(m) << 4
|
||||
}
|
||||
|
||||
if mlEnc.useRLE {
|
||||
mode |= uint8(compModeRLE) << 2
|
||||
mlEnc.setRLE(b.sequences[0].mlCode)
|
||||
if debugEncoder {
|
||||
println("mlEnc.useRLE, code: ", b.sequences[0].mlCode, "value", b.sequences[0].matchLen)
|
||||
}
|
||||
} else {
|
||||
var m seqCompMode
|
||||
mlEnc, m = chooseComp(mlEnc, b.coders.mlPrev, &fsePredefEnc[tableMatchLengths])
|
||||
mode |= uint8(m) << 2
|
||||
}
|
||||
b.output = append(b.output, mode)
|
||||
if debugEncoder {
|
||||
printf("Compression modes: 0b%b", mode)
|
||||
}
|
||||
b.output, err = llEnc.writeCount(b.output)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
start := len(b.output)
|
||||
b.output, err = ofEnc.writeCount(b.output)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if false {
|
||||
println("block:", b.output[start:], "tablelog", ofEnc.actualTableLog, "maxcount:", ofEnc.maxCount)
|
||||
fmt.Printf("selected TableLog: %d, Symbol length: %d\n", ofEnc.actualTableLog, ofEnc.symbolLen)
|
||||
for i, v := range ofEnc.norm[:ofEnc.symbolLen] {
|
||||
fmt.Printf("%3d: %5d -> %4d \n", i, ofEnc.count[i], v)
|
||||
}
|
||||
}
|
||||
b.output, err = mlEnc.writeCount(b.output)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
// Maybe in block?
|
||||
wr := &b.wr
|
||||
wr.reset(b.output)
|
||||
|
||||
var ll, of, ml cState
|
||||
|
||||
// Current sequence
|
||||
seq := len(b.sequences) - 1
|
||||
s := b.sequences[seq]
|
||||
llEnc.setBits(llBitsTable[:])
|
||||
mlEnc.setBits(mlBitsTable[:])
|
||||
ofEnc.setBits(nil)
|
||||
|
||||
llTT, ofTT, mlTT := llEnc.ct.symbolTT[:256], ofEnc.ct.symbolTT[:256], mlEnc.ct.symbolTT[:256]
|
||||
|
||||
// We have 3 bounds checks here (and in the loop).
|
||||
// Since we are iterating backwards it is kinda hard to avoid.
|
||||
llB, ofB, mlB := llTT[s.llCode], ofTT[s.ofCode], mlTT[s.mlCode]
|
||||
ll.init(wr, &llEnc.ct, llB)
|
||||
of.init(wr, &ofEnc.ct, ofB)
|
||||
wr.flush32()
|
||||
ml.init(wr, &mlEnc.ct, mlB)
|
||||
|
||||
// Each of these lookups also generates a bounds check.
|
||||
wr.addBits32NC(s.litLen, llB.outBits)
|
||||
wr.addBits32NC(s.matchLen, mlB.outBits)
|
||||
wr.flush32()
|
||||
wr.addBits32NC(s.offset, ofB.outBits)
|
||||
if debugSequences {
|
||||
println("Encoded seq", seq, s, "codes:", s.llCode, s.mlCode, s.ofCode, "states:", ll.state, ml.state, of.state, "bits:", llB, mlB, ofB)
|
||||
}
|
||||
seq--
|
||||
// Store sequences in reverse...
|
||||
for seq >= 0 {
|
||||
s = b.sequences[seq]
|
||||
|
||||
ofB := ofTT[s.ofCode]
|
||||
wr.flush32() // tablelog max is below 8 for each, so it will fill max 24 bits.
|
||||
//of.encode(ofB)
|
||||
nbBitsOut := (uint32(of.state) + ofB.deltaNbBits) >> 16
|
||||
dstState := int32(of.state>>(nbBitsOut&15)) + int32(ofB.deltaFindState)
|
||||
wr.addBits16NC(of.state, uint8(nbBitsOut))
|
||||
of.state = of.stateTable[dstState]
|
||||
|
||||
// Accumulate extra bits.
|
||||
outBits := ofB.outBits & 31
|
||||
extraBits := uint64(s.offset & bitMask32[outBits])
|
||||
extraBitsN := outBits
|
||||
|
||||
mlB := mlTT[s.mlCode]
|
||||
//ml.encode(mlB)
|
||||
nbBitsOut = (uint32(ml.state) + mlB.deltaNbBits) >> 16
|
||||
dstState = int32(ml.state>>(nbBitsOut&15)) + int32(mlB.deltaFindState)
|
||||
wr.addBits16NC(ml.state, uint8(nbBitsOut))
|
||||
ml.state = ml.stateTable[dstState]
|
||||
|
||||
outBits = mlB.outBits & 31
|
||||
extraBits = extraBits<<outBits | uint64(s.matchLen&bitMask32[outBits])
|
||||
extraBitsN += outBits
|
||||
|
||||
llB := llTT[s.llCode]
|
||||
//ll.encode(llB)
|
||||
nbBitsOut = (uint32(ll.state) + llB.deltaNbBits) >> 16
|
||||
dstState = int32(ll.state>>(nbBitsOut&15)) + int32(llB.deltaFindState)
|
||||
wr.addBits16NC(ll.state, uint8(nbBitsOut))
|
||||
ll.state = ll.stateTable[dstState]
|
||||
|
||||
outBits = llB.outBits & 31
|
||||
extraBits = extraBits<<outBits | uint64(s.litLen&bitMask32[outBits])
|
||||
extraBitsN += outBits
|
||||
|
||||
wr.flush32()
|
||||
wr.addBits64NC(extraBits, extraBitsN)
|
||||
|
||||
if debugSequences {
|
||||
println("Encoded seq", seq, s)
|
||||
}
|
||||
|
||||
seq--
|
||||
}
|
||||
ml.flush(mlEnc.actualTableLog)
|
||||
of.flush(ofEnc.actualTableLog)
|
||||
ll.flush(llEnc.actualTableLog)
|
||||
wr.close()
|
||||
b.output = wr.out
|
||||
|
||||
// Maybe even add a bigger margin.
|
||||
if len(b.output)-3-bhOffset >= b.size {
|
||||
// Discard and encode as raw block.
|
||||
b.output = b.encodeRawTo(b.output[:bhOffset], org)
|
||||
b.popOffsets()
|
||||
b.litEnc.Reuse = huff0.ReusePolicyNone
|
||||
return nil
|
||||
}
|
||||
|
||||
// Size is output minus block header.
|
||||
bh.setSize(uint32(len(b.output)-bhOffset) - 3)
|
||||
if debugEncoder {
|
||||
println("Rewriting block header", bh)
|
||||
}
|
||||
_ = bh.appendTo(b.output[bhOffset:bhOffset])
|
||||
b.coders.setPrev(llEnc, mlEnc, ofEnc)
|
||||
return nil
|
||||
}
|
||||
|
||||
var errIncompressible = errors.New("incompressible")
|
||||
|
||||
func (b *blockEnc) genCodes() {
|
||||
if len(b.sequences) == 0 {
|
||||
// nothing to do
|
||||
return
|
||||
}
|
||||
if len(b.sequences) > math.MaxUint16 {
|
||||
panic("can only encode up to 64K sequences")
|
||||
}
|
||||
// No bounds checks after here:
|
||||
llH := b.coders.llEnc.Histogram()
|
||||
ofH := b.coders.ofEnc.Histogram()
|
||||
mlH := b.coders.mlEnc.Histogram()
|
||||
for i := range llH {
|
||||
llH[i] = 0
|
||||
}
|
||||
for i := range ofH {
|
||||
ofH[i] = 0
|
||||
}
|
||||
for i := range mlH {
|
||||
mlH[i] = 0
|
||||
}
|
||||
|
||||
var llMax, ofMax, mlMax uint8
|
||||
for i := range b.sequences {
|
||||
seq := &b.sequences[i]
|
||||
v := llCode(seq.litLen)
|
||||
seq.llCode = v
|
||||
llH[v]++
|
||||
if v > llMax {
|
||||
llMax = v
|
||||
}
|
||||
|
||||
v = ofCode(seq.offset)
|
||||
seq.ofCode = v
|
||||
ofH[v]++
|
||||
if v > ofMax {
|
||||
ofMax = v
|
||||
}
|
||||
|
||||
v = mlCode(seq.matchLen)
|
||||
seq.mlCode = v
|
||||
mlH[v]++
|
||||
if v > mlMax {
|
||||
mlMax = v
|
||||
if debugAsserts && mlMax > maxMatchLengthSymbol {
|
||||
panic(fmt.Errorf("mlMax > maxMatchLengthSymbol (%d), matchlen: %d", mlMax, seq.matchLen))
|
||||
}
|
||||
}
|
||||
}
|
||||
maxCount := func(a []uint32) int {
|
||||
var max uint32
|
||||
for _, v := range a {
|
||||
if v > max {
|
||||
max = v
|
||||
}
|
||||
}
|
||||
return int(max)
|
||||
}
|
||||
if debugAsserts && mlMax > maxMatchLengthSymbol {
|
||||
panic(fmt.Errorf("mlMax > maxMatchLengthSymbol (%d)", mlMax))
|
||||
}
|
||||
if debugAsserts && ofMax > maxOffsetBits {
|
||||
panic(fmt.Errorf("ofMax > maxOffsetBits (%d)", ofMax))
|
||||
}
|
||||
if debugAsserts && llMax > maxLiteralLengthSymbol {
|
||||
panic(fmt.Errorf("llMax > maxLiteralLengthSymbol (%d)", llMax))
|
||||
}
|
||||
|
||||
b.coders.mlEnc.HistogramFinished(mlMax, maxCount(mlH[:mlMax+1]))
|
||||
b.coders.ofEnc.HistogramFinished(ofMax, maxCount(ofH[:ofMax+1]))
|
||||
b.coders.llEnc.HistogramFinished(llMax, maxCount(llH[:llMax+1]))
|
||||
}
|
||||
85
vendor/github.com/klauspost/compress/zstd/blocktype_string.go
generated
vendored
85
vendor/github.com/klauspost/compress/zstd/blocktype_string.go
generated
vendored
@ -1,85 +0,0 @@
|
||||
// Code generated by "stringer -type=blockType,literalsBlockType,seqCompMode,tableIndex"; DO NOT EDIT.
|
||||
|
||||
package zstd
|
||||
|
||||
import "strconv"
|
||||
|
||||
func _() {
|
||||
// An "invalid array index" compiler error signifies that the constant values have changed.
|
||||
// Re-run the stringer command to generate them again.
|
||||
var x [1]struct{}
|
||||
_ = x[blockTypeRaw-0]
|
||||
_ = x[blockTypeRLE-1]
|
||||
_ = x[blockTypeCompressed-2]
|
||||
_ = x[blockTypeReserved-3]
|
||||
}
|
||||
|
||||
const _blockType_name = "blockTypeRawblockTypeRLEblockTypeCompressedblockTypeReserved"
|
||||
|
||||
var _blockType_index = [...]uint8{0, 12, 24, 43, 60}
|
||||
|
||||
func (i blockType) String() string {
|
||||
if i >= blockType(len(_blockType_index)-1) {
|
||||
return "blockType(" + strconv.FormatInt(int64(i), 10) + ")"
|
||||
}
|
||||
return _blockType_name[_blockType_index[i]:_blockType_index[i+1]]
|
||||
}
|
||||
func _() {
|
||||
// An "invalid array index" compiler error signifies that the constant values have changed.
|
||||
// Re-run the stringer command to generate them again.
|
||||
var x [1]struct{}
|
||||
_ = x[literalsBlockRaw-0]
|
||||
_ = x[literalsBlockRLE-1]
|
||||
_ = x[literalsBlockCompressed-2]
|
||||
_ = x[literalsBlockTreeless-3]
|
||||
}
|
||||
|
||||
const _literalsBlockType_name = "literalsBlockRawliteralsBlockRLEliteralsBlockCompressedliteralsBlockTreeless"
|
||||
|
||||
var _literalsBlockType_index = [...]uint8{0, 16, 32, 55, 76}
|
||||
|
||||
func (i literalsBlockType) String() string {
|
||||
if i >= literalsBlockType(len(_literalsBlockType_index)-1) {
|
||||
return "literalsBlockType(" + strconv.FormatInt(int64(i), 10) + ")"
|
||||
}
|
||||
return _literalsBlockType_name[_literalsBlockType_index[i]:_literalsBlockType_index[i+1]]
|
||||
}
|
||||
func _() {
|
||||
// An "invalid array index" compiler error signifies that the constant values have changed.
|
||||
// Re-run the stringer command to generate them again.
|
||||
var x [1]struct{}
|
||||
_ = x[compModePredefined-0]
|
||||
_ = x[compModeRLE-1]
|
||||
_ = x[compModeFSE-2]
|
||||
_ = x[compModeRepeat-3]
|
||||
}
|
||||
|
||||
const _seqCompMode_name = "compModePredefinedcompModeRLEcompModeFSEcompModeRepeat"
|
||||
|
||||
var _seqCompMode_index = [...]uint8{0, 18, 29, 40, 54}
|
||||
|
||||
func (i seqCompMode) String() string {
|
||||
if i >= seqCompMode(len(_seqCompMode_index)-1) {
|
||||
return "seqCompMode(" + strconv.FormatInt(int64(i), 10) + ")"
|
||||
}
|
||||
return _seqCompMode_name[_seqCompMode_index[i]:_seqCompMode_index[i+1]]
|
||||
}
|
||||
func _() {
|
||||
// An "invalid array index" compiler error signifies that the constant values have changed.
|
||||
// Re-run the stringer command to generate them again.
|
||||
var x [1]struct{}
|
||||
_ = x[tableLiteralLengths-0]
|
||||
_ = x[tableOffsets-1]
|
||||
_ = x[tableMatchLengths-2]
|
||||
}
|
||||
|
||||
const _tableIndex_name = "tableLiteralLengthstableOffsetstableMatchLengths"
|
||||
|
||||
var _tableIndex_index = [...]uint8{0, 19, 31, 48}
|
||||
|
||||
func (i tableIndex) String() string {
|
||||
if i >= tableIndex(len(_tableIndex_index)-1) {
|
||||
return "tableIndex(" + strconv.FormatInt(int64(i), 10) + ")"
|
||||
}
|
||||
return _tableIndex_name[_tableIndex_index[i]:_tableIndex_index[i+1]]
|
||||
}
|
||||
131
vendor/github.com/klauspost/compress/zstd/bytebuf.go
generated
vendored
131
vendor/github.com/klauspost/compress/zstd/bytebuf.go
generated
vendored
@ -1,131 +0,0 @@
|
||||
// Copyright 2019+ Klaus Post. All rights reserved.
|
||||
// License information can be found in the LICENSE file.
|
||||
// Based on work by Yann Collet, released under BSD License.
|
||||
|
||||
package zstd
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"io"
|
||||
)
|
||||
|
||||
type byteBuffer interface {
|
||||
// Read up to 8 bytes.
|
||||
// Returns io.ErrUnexpectedEOF if this cannot be satisfied.
|
||||
readSmall(n int) ([]byte, error)
|
||||
|
||||
// Read >8 bytes.
|
||||
// MAY use the destination slice.
|
||||
readBig(n int, dst []byte) ([]byte, error)
|
||||
|
||||
// Read a single byte.
|
||||
readByte() (byte, error)
|
||||
|
||||
// Skip n bytes.
|
||||
skipN(n int64) error
|
||||
}
|
||||
|
||||
// in-memory buffer
|
||||
type byteBuf []byte
|
||||
|
||||
func (b *byteBuf) readSmall(n int) ([]byte, error) {
|
||||
if debugAsserts && n > 8 {
|
||||
panic(fmt.Errorf("small read > 8 (%d). use readBig", n))
|
||||
}
|
||||
bb := *b
|
||||
if len(bb) < n {
|
||||
return nil, io.ErrUnexpectedEOF
|
||||
}
|
||||
r := bb[:n]
|
||||
*b = bb[n:]
|
||||
return r, nil
|
||||
}
|
||||
|
||||
func (b *byteBuf) readBig(n int, dst []byte) ([]byte, error) {
|
||||
bb := *b
|
||||
if len(bb) < n {
|
||||
return nil, io.ErrUnexpectedEOF
|
||||
}
|
||||
r := bb[:n]
|
||||
*b = bb[n:]
|
||||
return r, nil
|
||||
}
|
||||
|
||||
func (b *byteBuf) readByte() (byte, error) {
|
||||
bb := *b
|
||||
if len(bb) < 1 {
|
||||
return 0, io.ErrUnexpectedEOF
|
||||
}
|
||||
r := bb[0]
|
||||
*b = bb[1:]
|
||||
return r, nil
|
||||
}
|
||||
|
||||
func (b *byteBuf) skipN(n int64) error {
|
||||
bb := *b
|
||||
if n < 0 {
|
||||
return fmt.Errorf("negative skip (%d) requested", n)
|
||||
}
|
||||
if int64(len(bb)) < n {
|
||||
return io.ErrUnexpectedEOF
|
||||
}
|
||||
*b = bb[n:]
|
||||
return nil
|
||||
}
|
||||
|
||||
// wrapper around a reader.
|
||||
type readerWrapper struct {
|
||||
r io.Reader
|
||||
tmp [8]byte
|
||||
}
|
||||
|
||||
func (r *readerWrapper) readSmall(n int) ([]byte, error) {
|
||||
if debugAsserts && n > 8 {
|
||||
panic(fmt.Errorf("small read > 8 (%d). use readBig", n))
|
||||
}
|
||||
n2, err := io.ReadFull(r.r, r.tmp[:n])
|
||||
// We only really care about the actual bytes read.
|
||||
if err != nil {
|
||||
if err == io.EOF {
|
||||
return nil, io.ErrUnexpectedEOF
|
||||
}
|
||||
if debugDecoder {
|
||||
println("readSmall: got", n2, "want", n, "err", err)
|
||||
}
|
||||
return nil, err
|
||||
}
|
||||
return r.tmp[:n], nil
|
||||
}
|
||||
|
||||
func (r *readerWrapper) readBig(n int, dst []byte) ([]byte, error) {
|
||||
if cap(dst) < n {
|
||||
dst = make([]byte, n)
|
||||
}
|
||||
n2, err := io.ReadFull(r.r, dst[:n])
|
||||
if err == io.EOF && n > 0 {
|
||||
err = io.ErrUnexpectedEOF
|
||||
}
|
||||
return dst[:n2], err
|
||||
}
|
||||
|
||||
func (r *readerWrapper) readByte() (byte, error) {
|
||||
n2, err := io.ReadFull(r.r, r.tmp[:1])
|
||||
if err != nil {
|
||||
if err == io.EOF {
|
||||
err = io.ErrUnexpectedEOF
|
||||
}
|
||||
return 0, err
|
||||
}
|
||||
if n2 != 1 {
|
||||
return 0, io.ErrUnexpectedEOF
|
||||
}
|
||||
return r.tmp[0], nil
|
||||
}
|
||||
|
||||
func (r *readerWrapper) skipN(n int64) error {
|
||||
n2, err := io.CopyN(io.Discard, r.r, n)
|
||||
if n2 != n {
|
||||
err = io.ErrUnexpectedEOF
|
||||
}
|
||||
return err
|
||||
}
|
||||
82
vendor/github.com/klauspost/compress/zstd/bytereader.go
generated
vendored
82
vendor/github.com/klauspost/compress/zstd/bytereader.go
generated
vendored
@ -1,82 +0,0 @@
|
||||
// Copyright 2019+ Klaus Post. All rights reserved.
|
||||
// License information can be found in the LICENSE file.
|
||||
// Based on work by Yann Collet, released under BSD License.
|
||||
|
||||
package zstd
|
||||
|
||||
// byteReader provides a byte reader that reads
|
||||
// little endian values from a byte stream.
|
||||
// The input stream is manually advanced.
|
||||
// The reader performs no bounds checks.
|
||||
type byteReader struct {
|
||||
b []byte
|
||||
off int
|
||||
}
|
||||
|
||||
// advance the stream b n bytes.
|
||||
func (b *byteReader) advance(n uint) {
|
||||
b.off += int(n)
|
||||
}
|
||||
|
||||
// overread returns whether we have advanced too far.
|
||||
func (b *byteReader) overread() bool {
|
||||
return b.off > len(b.b)
|
||||
}
|
||||
|
||||
// Int32 returns a little endian int32 starting at current offset.
|
||||
func (b byteReader) Int32() int32 {
|
||||
b2 := b.b[b.off:]
|
||||
b2 = b2[:4]
|
||||
v3 := int32(b2[3])
|
||||
v2 := int32(b2[2])
|
||||
v1 := int32(b2[1])
|
||||
v0 := int32(b2[0])
|
||||
return v0 | (v1 << 8) | (v2 << 16) | (v3 << 24)
|
||||
}
|
||||
|
||||
// Uint8 returns the next byte
|
||||
func (b *byteReader) Uint8() uint8 {
|
||||
v := b.b[b.off]
|
||||
return v
|
||||
}
|
||||
|
||||
// Uint32 returns a little endian uint32 starting at current offset.
|
||||
func (b byteReader) Uint32() uint32 {
|
||||
if r := b.remain(); r < 4 {
|
||||
// Very rare
|
||||
v := uint32(0)
|
||||
for i := 1; i <= r; i++ {
|
||||
v = (v << 8) | uint32(b.b[len(b.b)-i])
|
||||
}
|
||||
return v
|
||||
}
|
||||
b2 := b.b[b.off:]
|
||||
b2 = b2[:4]
|
||||
v3 := uint32(b2[3])
|
||||
v2 := uint32(b2[2])
|
||||
v1 := uint32(b2[1])
|
||||
v0 := uint32(b2[0])
|
||||
return v0 | (v1 << 8) | (v2 << 16) | (v3 << 24)
|
||||
}
|
||||
|
||||
// Uint32NC returns a little endian uint32 starting at current offset.
|
||||
// The caller must be sure if there are at least 4 bytes left.
|
||||
func (b byteReader) Uint32NC() uint32 {
|
||||
b2 := b.b[b.off:]
|
||||
b2 = b2[:4]
|
||||
v3 := uint32(b2[3])
|
||||
v2 := uint32(b2[2])
|
||||
v1 := uint32(b2[1])
|
||||
v0 := uint32(b2[0])
|
||||
return v0 | (v1 << 8) | (v2 << 16) | (v3 << 24)
|
||||
}
|
||||
|
||||
// unread returns the unread portion of the input.
|
||||
func (b byteReader) unread() []byte {
|
||||
return b.b[b.off:]
|
||||
}
|
||||
|
||||
// remain will return the number of bytes remaining.
|
||||
func (b byteReader) remain() int {
|
||||
return len(b.b) - b.off
|
||||
}
|
||||
261
vendor/github.com/klauspost/compress/zstd/decodeheader.go
generated
vendored
261
vendor/github.com/klauspost/compress/zstd/decodeheader.go
generated
vendored
@ -1,261 +0,0 @@
|
||||
// Copyright 2020+ Klaus Post. All rights reserved.
|
||||
// License information can be found in the LICENSE file.
|
||||
|
||||
package zstd
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
"io"
|
||||
)
|
||||
|
||||
// HeaderMaxSize is the maximum size of a Frame and Block Header.
|
||||
// If less is sent to Header.Decode it *may* still contain enough information.
|
||||
const HeaderMaxSize = 14 + 3
|
||||
|
||||
// Header contains information about the first frame and block within that.
|
||||
type Header struct {
|
||||
// SingleSegment specifies whether the data is to be decompressed into a
|
||||
// single contiguous memory segment.
|
||||
// It implies that WindowSize is invalid and that FrameContentSize is valid.
|
||||
SingleSegment bool
|
||||
|
||||
// WindowSize is the window of data to keep while decoding.
|
||||
// Will only be set if SingleSegment is false.
|
||||
WindowSize uint64
|
||||
|
||||
// Dictionary ID.
|
||||
// If 0, no dictionary.
|
||||
DictionaryID uint32
|
||||
|
||||
// HasFCS specifies whether FrameContentSize has a valid value.
|
||||
HasFCS bool
|
||||
|
||||
// FrameContentSize is the expected uncompressed size of the entire frame.
|
||||
FrameContentSize uint64
|
||||
|
||||
// Skippable will be true if the frame is meant to be skipped.
|
||||
// This implies that FirstBlock.OK is false.
|
||||
Skippable bool
|
||||
|
||||
// SkippableID is the user-specific ID for the skippable frame.
|
||||
// Valid values are between 0 to 15, inclusive.
|
||||
SkippableID int
|
||||
|
||||
// SkippableSize is the length of the user data to skip following
|
||||
// the header.
|
||||
SkippableSize uint32
|
||||
|
||||
// HeaderSize is the raw size of the frame header.
|
||||
//
|
||||
// For normal frames, it includes the size of the magic number and
|
||||
// the size of the header (per section 3.1.1.1).
|
||||
// It does not include the size for any data blocks (section 3.1.1.2) nor
|
||||
// the size for the trailing content checksum.
|
||||
//
|
||||
// For skippable frames, this counts the size of the magic number
|
||||
// along with the size of the size field of the payload.
|
||||
// It does not include the size of the skippable payload itself.
|
||||
// The total frame size is the HeaderSize plus the SkippableSize.
|
||||
HeaderSize int
|
||||
|
||||
// First block information.
|
||||
FirstBlock struct {
|
||||
// OK will be set if first block could be decoded.
|
||||
OK bool
|
||||
|
||||
// Is this the last block of a frame?
|
||||
Last bool
|
||||
|
||||
// Is the data compressed?
|
||||
// If true CompressedSize will be populated.
|
||||
// Unfortunately DecompressedSize cannot be determined
|
||||
// without decoding the blocks.
|
||||
Compressed bool
|
||||
|
||||
// DecompressedSize is the expected decompressed size of the block.
|
||||
// Will be 0 if it cannot be determined.
|
||||
DecompressedSize int
|
||||
|
||||
// CompressedSize of the data in the block.
|
||||
// Does not include the block header.
|
||||
// Will be equal to DecompressedSize if not Compressed.
|
||||
CompressedSize int
|
||||
}
|
||||
|
||||
// If set there is a checksum present for the block content.
|
||||
// The checksum field at the end is always 4 bytes long.
|
||||
HasCheckSum bool
|
||||
}
|
||||
|
||||
// Decode the header from the beginning of the stream.
|
||||
// This will decode the frame header and the first block header if enough bytes are provided.
|
||||
// It is recommended to provide at least HeaderMaxSize bytes.
|
||||
// If the frame header cannot be read an error will be returned.
|
||||
// If there isn't enough input, io.ErrUnexpectedEOF is returned.
|
||||
// The FirstBlock.OK will indicate if enough information was available to decode the first block header.
|
||||
func (h *Header) Decode(in []byte) error {
|
||||
_, err := h.DecodeAndStrip(in)
|
||||
return err
|
||||
}
|
||||
|
||||
// DecodeAndStrip will decode the header from the beginning of the stream
|
||||
// and on success return the remaining bytes.
|
||||
// This will decode the frame header and the first block header if enough bytes are provided.
|
||||
// It is recommended to provide at least HeaderMaxSize bytes.
|
||||
// If the frame header cannot be read an error will be returned.
|
||||
// If there isn't enough input, io.ErrUnexpectedEOF is returned.
|
||||
// The FirstBlock.OK will indicate if enough information was available to decode the first block header.
|
||||
func (h *Header) DecodeAndStrip(in []byte) (remain []byte, err error) {
|
||||
*h = Header{}
|
||||
if len(in) < 4 {
|
||||
return nil, io.ErrUnexpectedEOF
|
||||
}
|
||||
h.HeaderSize += 4
|
||||
b, in := in[:4], in[4:]
|
||||
if string(b) != frameMagic {
|
||||
if string(b[1:4]) != skippableFrameMagic || b[0]&0xf0 != 0x50 {
|
||||
return nil, ErrMagicMismatch
|
||||
}
|
||||
if len(in) < 4 {
|
||||
return nil, io.ErrUnexpectedEOF
|
||||
}
|
||||
h.HeaderSize += 4
|
||||
h.Skippable = true
|
||||
h.SkippableID = int(b[0] & 0xf)
|
||||
h.SkippableSize = binary.LittleEndian.Uint32(in)
|
||||
return in[4:], nil
|
||||
}
|
||||
|
||||
// Read Window_Descriptor
|
||||
// https://github.com/facebook/zstd/blob/dev/doc/zstd_compression_format.md#window_descriptor
|
||||
if len(in) < 1 {
|
||||
return nil, io.ErrUnexpectedEOF
|
||||
}
|
||||
fhd, in := in[0], in[1:]
|
||||
h.HeaderSize++
|
||||
h.SingleSegment = fhd&(1<<5) != 0
|
||||
h.HasCheckSum = fhd&(1<<2) != 0
|
||||
if fhd&(1<<3) != 0 {
|
||||
return nil, errors.New("reserved bit set on frame header")
|
||||
}
|
||||
|
||||
if !h.SingleSegment {
|
||||
if len(in) < 1 {
|
||||
return nil, io.ErrUnexpectedEOF
|
||||
}
|
||||
var wd byte
|
||||
wd, in = in[0], in[1:]
|
||||
h.HeaderSize++
|
||||
windowLog := 10 + (wd >> 3)
|
||||
windowBase := uint64(1) << windowLog
|
||||
windowAdd := (windowBase / 8) * uint64(wd&0x7)
|
||||
h.WindowSize = windowBase + windowAdd
|
||||
}
|
||||
|
||||
// Read Dictionary_ID
|
||||
// https://github.com/facebook/zstd/blob/dev/doc/zstd_compression_format.md#dictionary_id
|
||||
if size := fhd & 3; size != 0 {
|
||||
if size == 3 {
|
||||
size = 4
|
||||
}
|
||||
if len(in) < int(size) {
|
||||
return nil, io.ErrUnexpectedEOF
|
||||
}
|
||||
b, in = in[:size], in[size:]
|
||||
h.HeaderSize += int(size)
|
||||
switch len(b) {
|
||||
case 1:
|
||||
h.DictionaryID = uint32(b[0])
|
||||
case 2:
|
||||
h.DictionaryID = uint32(b[0]) | (uint32(b[1]) << 8)
|
||||
case 4:
|
||||
h.DictionaryID = uint32(b[0]) | (uint32(b[1]) << 8) | (uint32(b[2]) << 16) | (uint32(b[3]) << 24)
|
||||
}
|
||||
}
|
||||
|
||||
// Read Frame_Content_Size
|
||||
// https://github.com/facebook/zstd/blob/dev/doc/zstd_compression_format.md#frame_content_size
|
||||
var fcsSize int
|
||||
v := fhd >> 6
|
||||
switch v {
|
||||
case 0:
|
||||
if h.SingleSegment {
|
||||
fcsSize = 1
|
||||
}
|
||||
default:
|
||||
fcsSize = 1 << v
|
||||
}
|
||||
|
||||
if fcsSize > 0 {
|
||||
h.HasFCS = true
|
||||
if len(in) < fcsSize {
|
||||
return nil, io.ErrUnexpectedEOF
|
||||
}
|
||||
b, in = in[:fcsSize], in[fcsSize:]
|
||||
h.HeaderSize += int(fcsSize)
|
||||
switch len(b) {
|
||||
case 1:
|
||||
h.FrameContentSize = uint64(b[0])
|
||||
case 2:
|
||||
// When FCS_Field_Size is 2, the offset of 256 is added.
|
||||
h.FrameContentSize = uint64(b[0]) | (uint64(b[1]) << 8) + 256
|
||||
case 4:
|
||||
h.FrameContentSize = uint64(b[0]) | (uint64(b[1]) << 8) | (uint64(b[2]) << 16) | (uint64(b[3]) << 24)
|
||||
case 8:
|
||||
d1 := uint32(b[0]) | (uint32(b[1]) << 8) | (uint32(b[2]) << 16) | (uint32(b[3]) << 24)
|
||||
d2 := uint32(b[4]) | (uint32(b[5]) << 8) | (uint32(b[6]) << 16) | (uint32(b[7]) << 24)
|
||||
h.FrameContentSize = uint64(d1) | (uint64(d2) << 32)
|
||||
}
|
||||
}
|
||||
|
||||
// Frame Header done, we will not fail from now on.
|
||||
if len(in) < 3 {
|
||||
return in, nil
|
||||
}
|
||||
tmp := in[:3]
|
||||
bh := uint32(tmp[0]) | (uint32(tmp[1]) << 8) | (uint32(tmp[2]) << 16)
|
||||
h.FirstBlock.Last = bh&1 != 0
|
||||
blockType := blockType((bh >> 1) & 3)
|
||||
// find size.
|
||||
cSize := int(bh >> 3)
|
||||
switch blockType {
|
||||
case blockTypeReserved:
|
||||
return in, nil
|
||||
case blockTypeRLE:
|
||||
h.FirstBlock.Compressed = true
|
||||
h.FirstBlock.DecompressedSize = cSize
|
||||
h.FirstBlock.CompressedSize = 1
|
||||
case blockTypeCompressed:
|
||||
h.FirstBlock.Compressed = true
|
||||
h.FirstBlock.CompressedSize = cSize
|
||||
case blockTypeRaw:
|
||||
h.FirstBlock.DecompressedSize = cSize
|
||||
h.FirstBlock.CompressedSize = cSize
|
||||
default:
|
||||
panic("Invalid block type")
|
||||
}
|
||||
|
||||
h.FirstBlock.OK = true
|
||||
return in, nil
|
||||
}
|
||||
|
||||
// AppendTo will append the encoded header to the dst slice.
|
||||
// There is no error checking performed on the header values.
|
||||
func (h *Header) AppendTo(dst []byte) ([]byte, error) {
|
||||
if h.Skippable {
|
||||
magic := [4]byte{0x50, 0x2a, 0x4d, 0x18}
|
||||
magic[0] |= byte(h.SkippableID & 0xf)
|
||||
dst = append(dst, magic[:]...)
|
||||
f := h.SkippableSize
|
||||
return append(dst, uint8(f), uint8(f>>8), uint8(f>>16), uint8(f>>24)), nil
|
||||
}
|
||||
f := frameHeader{
|
||||
ContentSize: h.FrameContentSize,
|
||||
WindowSize: uint32(h.WindowSize),
|
||||
SingleSegment: h.SingleSegment,
|
||||
Checksum: h.HasCheckSum,
|
||||
DictID: h.DictionaryID,
|
||||
}
|
||||
return f.appendTo(dst), nil
|
||||
}
|
||||
948
vendor/github.com/klauspost/compress/zstd/decoder.go
generated
vendored
948
vendor/github.com/klauspost/compress/zstd/decoder.go
generated
vendored
@ -1,948 +0,0 @@
|
||||
// Copyright 2019+ Klaus Post. All rights reserved.
|
||||
// License information can be found in the LICENSE file.
|
||||
// Based on work by Yann Collet, released under BSD License.
|
||||
|
||||
package zstd
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/binary"
|
||||
"io"
|
||||
"sync"
|
||||
|
||||
"github.com/klauspost/compress/zstd/internal/xxhash"
|
||||
)
|
||||
|
||||
// Decoder provides decoding of zstandard streams.
|
||||
// The decoder has been designed to operate without allocations after a warmup.
|
||||
// This means that you should store the decoder for best performance.
|
||||
// To re-use a stream decoder, use the Reset(r io.Reader) error to switch to another stream.
|
||||
// A decoder can safely be re-used even if the previous stream failed.
|
||||
// To release the resources, you must call the Close() function on a decoder.
|
||||
type Decoder struct {
|
||||
o decoderOptions
|
||||
|
||||
// Unreferenced decoders, ready for use.
|
||||
decoders chan *blockDec
|
||||
|
||||
// Current read position used for Reader functionality.
|
||||
current decoderState
|
||||
|
||||
// sync stream decoding
|
||||
syncStream struct {
|
||||
decodedFrame uint64
|
||||
br readerWrapper
|
||||
enabled bool
|
||||
inFrame bool
|
||||
dstBuf []byte
|
||||
}
|
||||
|
||||
frame *frameDec
|
||||
|
||||
// Custom dictionaries.
|
||||
dicts map[uint32]*dict
|
||||
|
||||
// streamWg is the waitgroup for all streams
|
||||
streamWg sync.WaitGroup
|
||||
}
|
||||
|
||||
// decoderState is used for maintaining state when the decoder
|
||||
// is used for streaming.
|
||||
type decoderState struct {
|
||||
// current block being written to stream.
|
||||
decodeOutput
|
||||
|
||||
// output in order to be written to stream.
|
||||
output chan decodeOutput
|
||||
|
||||
// cancel remaining output.
|
||||
cancel context.CancelFunc
|
||||
|
||||
// crc of current frame
|
||||
crc *xxhash.Digest
|
||||
|
||||
flushed bool
|
||||
}
|
||||
|
||||
var (
|
||||
// Check the interfaces we want to support.
|
||||
_ = io.WriterTo(&Decoder{})
|
||||
_ = io.Reader(&Decoder{})
|
||||
)
|
||||
|
||||
// NewReader creates a new decoder.
|
||||
// A nil Reader can be provided in which case Reset can be used to start a decode.
|
||||
//
|
||||
// A Decoder can be used in two modes:
|
||||
//
|
||||
// 1) As a stream, or
|
||||
// 2) For stateless decoding using DecodeAll.
|
||||
//
|
||||
// Only a single stream can be decoded concurrently, but the same decoder
|
||||
// can run multiple concurrent stateless decodes. It is even possible to
|
||||
// use stateless decodes while a stream is being decoded.
|
||||
//
|
||||
// The Reset function can be used to initiate a new stream, which will considerably
|
||||
// reduce the allocations normally caused by NewReader.
|
||||
func NewReader(r io.Reader, opts ...DOption) (*Decoder, error) {
|
||||
initPredefined()
|
||||
var d Decoder
|
||||
d.o.setDefault()
|
||||
for _, o := range opts {
|
||||
err := o(&d.o)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
d.current.crc = xxhash.New()
|
||||
d.current.flushed = true
|
||||
|
||||
if r == nil {
|
||||
d.current.err = ErrDecoderNilInput
|
||||
}
|
||||
|
||||
// Transfer option dicts.
|
||||
d.dicts = make(map[uint32]*dict, len(d.o.dicts))
|
||||
for _, dc := range d.o.dicts {
|
||||
d.dicts[dc.id] = dc
|
||||
}
|
||||
d.o.dicts = nil
|
||||
|
||||
// Create decoders
|
||||
d.decoders = make(chan *blockDec, d.o.concurrent)
|
||||
for i := 0; i < d.o.concurrent; i++ {
|
||||
dec := newBlockDec(d.o.lowMem)
|
||||
dec.localFrame = newFrameDec(d.o)
|
||||
d.decoders <- dec
|
||||
}
|
||||
|
||||
if r == nil {
|
||||
return &d, nil
|
||||
}
|
||||
return &d, d.Reset(r)
|
||||
}
|
||||
|
||||
// Read bytes from the decompressed stream into p.
|
||||
// Returns the number of bytes written and any error that occurred.
|
||||
// When the stream is done, io.EOF will be returned.
|
||||
func (d *Decoder) Read(p []byte) (int, error) {
|
||||
var n int
|
||||
for {
|
||||
if len(d.current.b) > 0 {
|
||||
filled := copy(p, d.current.b)
|
||||
p = p[filled:]
|
||||
d.current.b = d.current.b[filled:]
|
||||
n += filled
|
||||
}
|
||||
if len(p) == 0 {
|
||||
break
|
||||
}
|
||||
if len(d.current.b) == 0 {
|
||||
// We have an error and no more data
|
||||
if d.current.err != nil {
|
||||
break
|
||||
}
|
||||
if !d.nextBlock(n == 0) {
|
||||
return n, d.current.err
|
||||
}
|
||||
}
|
||||
}
|
||||
if len(d.current.b) > 0 {
|
||||
if debugDecoder {
|
||||
println("returning", n, "still bytes left:", len(d.current.b))
|
||||
}
|
||||
// Only return error at end of block
|
||||
return n, nil
|
||||
}
|
||||
if d.current.err != nil {
|
||||
d.drainOutput()
|
||||
}
|
||||
if debugDecoder {
|
||||
println("returning", n, d.current.err, len(d.decoders))
|
||||
}
|
||||
return n, d.current.err
|
||||
}
|
||||
|
||||
// Reset will reset the decoder the supplied stream after the current has finished processing.
|
||||
// Note that this functionality cannot be used after Close has been called.
|
||||
// Reset can be called with a nil reader to release references to the previous reader.
|
||||
// After being called with a nil reader, no other operations than Reset or DecodeAll or Close
|
||||
// should be used.
|
||||
func (d *Decoder) Reset(r io.Reader) error {
|
||||
if d.current.err == ErrDecoderClosed {
|
||||
return d.current.err
|
||||
}
|
||||
|
||||
d.drainOutput()
|
||||
|
||||
d.syncStream.br.r = nil
|
||||
if r == nil {
|
||||
d.current.err = ErrDecoderNilInput
|
||||
if len(d.current.b) > 0 {
|
||||
d.current.b = d.current.b[:0]
|
||||
}
|
||||
d.current.flushed = true
|
||||
return nil
|
||||
}
|
||||
|
||||
// If bytes buffer and < 5MB, do sync decoding anyway.
|
||||
if bb, ok := r.(byter); ok && bb.Len() < d.o.decodeBufsBelow && !d.o.limitToCap {
|
||||
bb2 := bb
|
||||
if debugDecoder {
|
||||
println("*bytes.Buffer detected, doing sync decode, len:", bb.Len())
|
||||
}
|
||||
b := bb2.Bytes()
|
||||
var dst []byte
|
||||
if cap(d.syncStream.dstBuf) > 0 {
|
||||
dst = d.syncStream.dstBuf[:0]
|
||||
}
|
||||
|
||||
dst, err := d.DecodeAll(b, dst)
|
||||
if err == nil {
|
||||
err = io.EOF
|
||||
}
|
||||
// Save output buffer
|
||||
d.syncStream.dstBuf = dst
|
||||
d.current.b = dst
|
||||
d.current.err = err
|
||||
d.current.flushed = true
|
||||
if debugDecoder {
|
||||
println("sync decode to", len(dst), "bytes, err:", err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
// Remove current block.
|
||||
d.stashDecoder()
|
||||
d.current.decodeOutput = decodeOutput{}
|
||||
d.current.err = nil
|
||||
d.current.flushed = false
|
||||
d.current.d = nil
|
||||
d.syncStream.dstBuf = nil
|
||||
|
||||
// Ensure no-one else is still running...
|
||||
d.streamWg.Wait()
|
||||
if d.frame == nil {
|
||||
d.frame = newFrameDec(d.o)
|
||||
}
|
||||
|
||||
if d.o.concurrent == 1 {
|
||||
return d.startSyncDecoder(r)
|
||||
}
|
||||
|
||||
d.current.output = make(chan decodeOutput, d.o.concurrent)
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
d.current.cancel = cancel
|
||||
d.streamWg.Add(1)
|
||||
go d.startStreamDecoder(ctx, r, d.current.output)
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// drainOutput will drain the output until errEndOfStream is sent.
|
||||
func (d *Decoder) drainOutput() {
|
||||
if d.current.cancel != nil {
|
||||
if debugDecoder {
|
||||
println("cancelling current")
|
||||
}
|
||||
d.current.cancel()
|
||||
d.current.cancel = nil
|
||||
}
|
||||
if d.current.d != nil {
|
||||
if debugDecoder {
|
||||
printf("re-adding current decoder %p, decoders: %d", d.current.d, len(d.decoders))
|
||||
}
|
||||
d.decoders <- d.current.d
|
||||
d.current.d = nil
|
||||
d.current.b = nil
|
||||
}
|
||||
if d.current.output == nil || d.current.flushed {
|
||||
println("current already flushed")
|
||||
return
|
||||
}
|
||||
for v := range d.current.output {
|
||||
if v.d != nil {
|
||||
if debugDecoder {
|
||||
printf("re-adding decoder %p", v.d)
|
||||
}
|
||||
d.decoders <- v.d
|
||||
}
|
||||
}
|
||||
d.current.output = nil
|
||||
d.current.flushed = true
|
||||
}
|
||||
|
||||
// WriteTo writes data to w until there's no more data to write or when an error occurs.
|
||||
// The return value n is the number of bytes written.
|
||||
// Any error encountered during the write is also returned.
|
||||
func (d *Decoder) WriteTo(w io.Writer) (int64, error) {
|
||||
var n int64
|
||||
for {
|
||||
if len(d.current.b) > 0 {
|
||||
n2, err2 := w.Write(d.current.b)
|
||||
n += int64(n2)
|
||||
if err2 != nil && (d.current.err == nil || d.current.err == io.EOF) {
|
||||
d.current.err = err2
|
||||
} else if n2 != len(d.current.b) {
|
||||
d.current.err = io.ErrShortWrite
|
||||
}
|
||||
}
|
||||
if d.current.err != nil {
|
||||
break
|
||||
}
|
||||
d.nextBlock(true)
|
||||
}
|
||||
err := d.current.err
|
||||
if err != nil {
|
||||
d.drainOutput()
|
||||
}
|
||||
if err == io.EOF {
|
||||
err = nil
|
||||
}
|
||||
return n, err
|
||||
}
|
||||
|
||||
// DecodeAll allows stateless decoding of a blob of bytes.
|
||||
// Output will be appended to dst, so if the destination size is known
|
||||
// you can pre-allocate the destination slice to avoid allocations.
|
||||
// DecodeAll can be used concurrently.
|
||||
// The Decoder concurrency limits will be respected.
|
||||
func (d *Decoder) DecodeAll(input, dst []byte) ([]byte, error) {
|
||||
if d.decoders == nil {
|
||||
return dst, ErrDecoderClosed
|
||||
}
|
||||
|
||||
// Grab a block decoder and frame decoder.
|
||||
block := <-d.decoders
|
||||
frame := block.localFrame
|
||||
initialSize := len(dst)
|
||||
defer func() {
|
||||
if debugDecoder {
|
||||
printf("re-adding decoder: %p", block)
|
||||
}
|
||||
frame.rawInput = nil
|
||||
frame.bBuf = nil
|
||||
if frame.history.decoders.br != nil {
|
||||
frame.history.decoders.br.in = nil
|
||||
}
|
||||
d.decoders <- block
|
||||
}()
|
||||
frame.bBuf = input
|
||||
|
||||
for {
|
||||
frame.history.reset()
|
||||
err := frame.reset(&frame.bBuf)
|
||||
if err != nil {
|
||||
if err == io.EOF {
|
||||
if debugDecoder {
|
||||
println("frame reset return EOF")
|
||||
}
|
||||
return dst, nil
|
||||
}
|
||||
return dst, err
|
||||
}
|
||||
if err = d.setDict(frame); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if frame.WindowSize > d.o.maxWindowSize {
|
||||
if debugDecoder {
|
||||
println("window size exceeded:", frame.WindowSize, ">", d.o.maxWindowSize)
|
||||
}
|
||||
return dst, ErrWindowSizeExceeded
|
||||
}
|
||||
if frame.FrameContentSize != fcsUnknown {
|
||||
if frame.FrameContentSize > d.o.maxDecodedSize-uint64(len(dst)-initialSize) {
|
||||
if debugDecoder {
|
||||
println("decoder size exceeded; fcs:", frame.FrameContentSize, "> mcs:", d.o.maxDecodedSize-uint64(len(dst)-initialSize), "len:", len(dst))
|
||||
}
|
||||
return dst, ErrDecoderSizeExceeded
|
||||
}
|
||||
if d.o.limitToCap && frame.FrameContentSize > uint64(cap(dst)-len(dst)) {
|
||||
if debugDecoder {
|
||||
println("decoder size exceeded; fcs:", frame.FrameContentSize, "> (cap-len)", cap(dst)-len(dst))
|
||||
}
|
||||
return dst, ErrDecoderSizeExceeded
|
||||
}
|
||||
if cap(dst)-len(dst) < int(frame.FrameContentSize) {
|
||||
dst2 := make([]byte, len(dst), len(dst)+int(frame.FrameContentSize)+compressedBlockOverAlloc)
|
||||
copy(dst2, dst)
|
||||
dst = dst2
|
||||
}
|
||||
}
|
||||
|
||||
if cap(dst) == 0 && !d.o.limitToCap {
|
||||
// Allocate len(input) * 2 by default if nothing is provided
|
||||
// and we didn't get frame content size.
|
||||
size := len(input) * 2
|
||||
// Cap to 1 MB.
|
||||
if size > 1<<20 {
|
||||
size = 1 << 20
|
||||
}
|
||||
if uint64(size) > d.o.maxDecodedSize {
|
||||
size = int(d.o.maxDecodedSize)
|
||||
}
|
||||
dst = make([]byte, 0, size)
|
||||
}
|
||||
|
||||
dst, err = frame.runDecoder(dst, block)
|
||||
if err != nil {
|
||||
return dst, err
|
||||
}
|
||||
if uint64(len(dst)-initialSize) > d.o.maxDecodedSize {
|
||||
return dst, ErrDecoderSizeExceeded
|
||||
}
|
||||
if len(frame.bBuf) == 0 {
|
||||
if debugDecoder {
|
||||
println("frame dbuf empty")
|
||||
}
|
||||
break
|
||||
}
|
||||
}
|
||||
return dst, nil
|
||||
}
|
||||
|
||||
// nextBlock returns the next block.
|
||||
// If an error occurs d.err will be set.
|
||||
// Optionally the function can block for new output.
|
||||
// If non-blocking mode is used the returned boolean will be false
|
||||
// if no data was available without blocking.
|
||||
func (d *Decoder) nextBlock(blocking bool) (ok bool) {
|
||||
if d.current.err != nil {
|
||||
// Keep error state.
|
||||
return false
|
||||
}
|
||||
d.current.b = d.current.b[:0]
|
||||
|
||||
// SYNC:
|
||||
if d.syncStream.enabled {
|
||||
if !blocking {
|
||||
return false
|
||||
}
|
||||
ok = d.nextBlockSync()
|
||||
if !ok {
|
||||
d.stashDecoder()
|
||||
}
|
||||
return ok
|
||||
}
|
||||
|
||||
//ASYNC:
|
||||
d.stashDecoder()
|
||||
if blocking {
|
||||
d.current.decodeOutput, ok = <-d.current.output
|
||||
} else {
|
||||
select {
|
||||
case d.current.decodeOutput, ok = <-d.current.output:
|
||||
default:
|
||||
return false
|
||||
}
|
||||
}
|
||||
if !ok {
|
||||
// This should not happen, so signal error state...
|
||||
d.current.err = io.ErrUnexpectedEOF
|
||||
return false
|
||||
}
|
||||
next := d.current.decodeOutput
|
||||
if next.d != nil && next.d.async.newHist != nil {
|
||||
d.current.crc.Reset()
|
||||
}
|
||||
if debugDecoder {
|
||||
var tmp [4]byte
|
||||
binary.LittleEndian.PutUint32(tmp[:], uint32(xxhash.Sum64(next.b)))
|
||||
println("got", len(d.current.b), "bytes, error:", d.current.err, "data crc:", tmp)
|
||||
}
|
||||
|
||||
if d.o.ignoreChecksum {
|
||||
return true
|
||||
}
|
||||
|
||||
if len(next.b) > 0 {
|
||||
d.current.crc.Write(next.b)
|
||||
}
|
||||
if next.err == nil && next.d != nil && next.d.hasCRC {
|
||||
got := uint32(d.current.crc.Sum64())
|
||||
if got != next.d.checkCRC {
|
||||
if debugDecoder {
|
||||
printf("CRC Check Failed: %08x (got) != %08x (on stream)\n", got, next.d.checkCRC)
|
||||
}
|
||||
d.current.err = ErrCRCMismatch
|
||||
} else {
|
||||
if debugDecoder {
|
||||
printf("CRC ok %08x\n", got)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return true
|
||||
}
|
||||
|
||||
func (d *Decoder) nextBlockSync() (ok bool) {
|
||||
if d.current.d == nil {
|
||||
d.current.d = <-d.decoders
|
||||
}
|
||||
for len(d.current.b) == 0 {
|
||||
if !d.syncStream.inFrame {
|
||||
d.frame.history.reset()
|
||||
d.current.err = d.frame.reset(&d.syncStream.br)
|
||||
if d.current.err == nil {
|
||||
d.current.err = d.setDict(d.frame)
|
||||
}
|
||||
if d.current.err != nil {
|
||||
return false
|
||||
}
|
||||
if d.frame.WindowSize > d.o.maxDecodedSize || d.frame.WindowSize > d.o.maxWindowSize {
|
||||
d.current.err = ErrDecoderSizeExceeded
|
||||
return false
|
||||
}
|
||||
|
||||
d.syncStream.decodedFrame = 0
|
||||
d.syncStream.inFrame = true
|
||||
}
|
||||
d.current.err = d.frame.next(d.current.d)
|
||||
if d.current.err != nil {
|
||||
return false
|
||||
}
|
||||
d.frame.history.ensureBlock()
|
||||
if debugDecoder {
|
||||
println("History trimmed:", len(d.frame.history.b), "decoded already:", d.syncStream.decodedFrame)
|
||||
}
|
||||
histBefore := len(d.frame.history.b)
|
||||
d.current.err = d.current.d.decodeBuf(&d.frame.history)
|
||||
|
||||
if d.current.err != nil {
|
||||
println("error after:", d.current.err)
|
||||
return false
|
||||
}
|
||||
d.current.b = d.frame.history.b[histBefore:]
|
||||
if debugDecoder {
|
||||
println("history after:", len(d.frame.history.b))
|
||||
}
|
||||
|
||||
// Check frame size (before CRC)
|
||||
d.syncStream.decodedFrame += uint64(len(d.current.b))
|
||||
if d.syncStream.decodedFrame > d.frame.FrameContentSize {
|
||||
if debugDecoder {
|
||||
printf("DecodedFrame (%d) > FrameContentSize (%d)\n", d.syncStream.decodedFrame, d.frame.FrameContentSize)
|
||||
}
|
||||
d.current.err = ErrFrameSizeExceeded
|
||||
return false
|
||||
}
|
||||
|
||||
// Check FCS
|
||||
if d.current.d.Last && d.frame.FrameContentSize != fcsUnknown && d.syncStream.decodedFrame != d.frame.FrameContentSize {
|
||||
if debugDecoder {
|
||||
printf("DecodedFrame (%d) != FrameContentSize (%d)\n", d.syncStream.decodedFrame, d.frame.FrameContentSize)
|
||||
}
|
||||
d.current.err = ErrFrameSizeMismatch
|
||||
return false
|
||||
}
|
||||
|
||||
// Update/Check CRC
|
||||
if d.frame.HasCheckSum {
|
||||
if !d.o.ignoreChecksum {
|
||||
d.frame.crc.Write(d.current.b)
|
||||
}
|
||||
if d.current.d.Last {
|
||||
if !d.o.ignoreChecksum {
|
||||
d.current.err = d.frame.checkCRC()
|
||||
} else {
|
||||
d.current.err = d.frame.consumeCRC()
|
||||
}
|
||||
if d.current.err != nil {
|
||||
println("CRC error:", d.current.err)
|
||||
return false
|
||||
}
|
||||
}
|
||||
}
|
||||
d.syncStream.inFrame = !d.current.d.Last
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
func (d *Decoder) stashDecoder() {
|
||||
if d.current.d != nil {
|
||||
if debugDecoder {
|
||||
printf("re-adding current decoder %p", d.current.d)
|
||||
}
|
||||
d.decoders <- d.current.d
|
||||
d.current.d = nil
|
||||
}
|
||||
}
|
||||
|
||||
// Close will release all resources.
|
||||
// It is NOT possible to reuse the decoder after this.
|
||||
func (d *Decoder) Close() {
|
||||
if d.current.err == ErrDecoderClosed {
|
||||
return
|
||||
}
|
||||
d.drainOutput()
|
||||
if d.current.cancel != nil {
|
||||
d.current.cancel()
|
||||
d.streamWg.Wait()
|
||||
d.current.cancel = nil
|
||||
}
|
||||
if d.decoders != nil {
|
||||
close(d.decoders)
|
||||
for dec := range d.decoders {
|
||||
dec.Close()
|
||||
}
|
||||
d.decoders = nil
|
||||
}
|
||||
if d.current.d != nil {
|
||||
d.current.d.Close()
|
||||
d.current.d = nil
|
||||
}
|
||||
d.current.err = ErrDecoderClosed
|
||||
}
|
||||
|
||||
// IOReadCloser returns the decoder as an io.ReadCloser for convenience.
|
||||
// Any changes to the decoder will be reflected, so the returned ReadCloser
|
||||
// can be reused along with the decoder.
|
||||
// io.WriterTo is also supported by the returned ReadCloser.
|
||||
func (d *Decoder) IOReadCloser() io.ReadCloser {
|
||||
return closeWrapper{d: d}
|
||||
}
|
||||
|
||||
// closeWrapper wraps a function call as a closer.
|
||||
type closeWrapper struct {
|
||||
d *Decoder
|
||||
}
|
||||
|
||||
// WriteTo forwards WriteTo calls to the decoder.
|
||||
func (c closeWrapper) WriteTo(w io.Writer) (n int64, err error) {
|
||||
return c.d.WriteTo(w)
|
||||
}
|
||||
|
||||
// Read forwards read calls to the decoder.
|
||||
func (c closeWrapper) Read(p []byte) (n int, err error) {
|
||||
return c.d.Read(p)
|
||||
}
|
||||
|
||||
// Close closes the decoder.
|
||||
func (c closeWrapper) Close() error {
|
||||
c.d.Close()
|
||||
return nil
|
||||
}
|
||||
|
||||
type decodeOutput struct {
|
||||
d *blockDec
|
||||
b []byte
|
||||
err error
|
||||
}
|
||||
|
||||
func (d *Decoder) startSyncDecoder(r io.Reader) error {
|
||||
d.frame.history.reset()
|
||||
d.syncStream.br = readerWrapper{r: r}
|
||||
d.syncStream.inFrame = false
|
||||
d.syncStream.enabled = true
|
||||
d.syncStream.decodedFrame = 0
|
||||
return nil
|
||||
}
|
||||
|
||||
// Create Decoder:
|
||||
// ASYNC:
|
||||
// Spawn 3 go routines.
|
||||
// 0: Read frames and decode block literals.
|
||||
// 1: Decode sequences.
|
||||
// 2: Execute sequences, send to output.
|
||||
func (d *Decoder) startStreamDecoder(ctx context.Context, r io.Reader, output chan decodeOutput) {
|
||||
defer d.streamWg.Done()
|
||||
br := readerWrapper{r: r}
|
||||
|
||||
var seqDecode = make(chan *blockDec, d.o.concurrent)
|
||||
var seqExecute = make(chan *blockDec, d.o.concurrent)
|
||||
|
||||
// Async 1: Decode sequences...
|
||||
go func() {
|
||||
var hist history
|
||||
var hasErr bool
|
||||
|
||||
for block := range seqDecode {
|
||||
if hasErr {
|
||||
if block != nil {
|
||||
seqExecute <- block
|
||||
}
|
||||
continue
|
||||
}
|
||||
if block.async.newHist != nil {
|
||||
if debugDecoder {
|
||||
println("Async 1: new history, recent:", block.async.newHist.recentOffsets)
|
||||
}
|
||||
hist.reset()
|
||||
hist.decoders = block.async.newHist.decoders
|
||||
hist.recentOffsets = block.async.newHist.recentOffsets
|
||||
hist.windowSize = block.async.newHist.windowSize
|
||||
if block.async.newHist.dict != nil {
|
||||
hist.setDict(block.async.newHist.dict)
|
||||
}
|
||||
}
|
||||
if block.err != nil || block.Type != blockTypeCompressed {
|
||||
hasErr = block.err != nil
|
||||
seqExecute <- block
|
||||
continue
|
||||
}
|
||||
|
||||
hist.decoders.literals = block.async.literals
|
||||
block.err = block.prepareSequences(block.async.seqData, &hist)
|
||||
if debugDecoder && block.err != nil {
|
||||
println("prepareSequences returned:", block.err)
|
||||
}
|
||||
hasErr = block.err != nil
|
||||
if block.err == nil {
|
||||
block.err = block.decodeSequences(&hist)
|
||||
if debugDecoder && block.err != nil {
|
||||
println("decodeSequences returned:", block.err)
|
||||
}
|
||||
hasErr = block.err != nil
|
||||
// block.async.sequence = hist.decoders.seq[:hist.decoders.nSeqs]
|
||||
block.async.seqSize = hist.decoders.seqSize
|
||||
}
|
||||
seqExecute <- block
|
||||
}
|
||||
close(seqExecute)
|
||||
hist.reset()
|
||||
}()
|
||||
|
||||
var wg sync.WaitGroup
|
||||
wg.Add(1)
|
||||
|
||||
// Async 3: Execute sequences...
|
||||
frameHistCache := d.frame.history.b
|
||||
go func() {
|
||||
var hist history
|
||||
var decodedFrame uint64
|
||||
var fcs uint64
|
||||
var hasErr bool
|
||||
for block := range seqExecute {
|
||||
out := decodeOutput{err: block.err, d: block}
|
||||
if block.err != nil || hasErr {
|
||||
hasErr = true
|
||||
output <- out
|
||||
continue
|
||||
}
|
||||
if block.async.newHist != nil {
|
||||
if debugDecoder {
|
||||
println("Async 2: new history")
|
||||
}
|
||||
hist.reset()
|
||||
hist.windowSize = block.async.newHist.windowSize
|
||||
hist.allocFrameBuffer = block.async.newHist.allocFrameBuffer
|
||||
if block.async.newHist.dict != nil {
|
||||
hist.setDict(block.async.newHist.dict)
|
||||
}
|
||||
|
||||
if cap(hist.b) < hist.allocFrameBuffer {
|
||||
if cap(frameHistCache) >= hist.allocFrameBuffer {
|
||||
hist.b = frameHistCache
|
||||
} else {
|
||||
hist.b = make([]byte, 0, hist.allocFrameBuffer)
|
||||
println("Alloc history sized", hist.allocFrameBuffer)
|
||||
}
|
||||
}
|
||||
hist.b = hist.b[:0]
|
||||
fcs = block.async.fcs
|
||||
decodedFrame = 0
|
||||
}
|
||||
do := decodeOutput{err: block.err, d: block}
|
||||
switch block.Type {
|
||||
case blockTypeRLE:
|
||||
if debugDecoder {
|
||||
println("add rle block length:", block.RLESize)
|
||||
}
|
||||
|
||||
if cap(block.dst) < int(block.RLESize) {
|
||||
if block.lowMem {
|
||||
block.dst = make([]byte, block.RLESize)
|
||||
} else {
|
||||
block.dst = make([]byte, maxCompressedBlockSize)
|
||||
}
|
||||
}
|
||||
block.dst = block.dst[:block.RLESize]
|
||||
v := block.data[0]
|
||||
for i := range block.dst {
|
||||
block.dst[i] = v
|
||||
}
|
||||
hist.append(block.dst)
|
||||
do.b = block.dst
|
||||
case blockTypeRaw:
|
||||
if debugDecoder {
|
||||
println("add raw block length:", len(block.data))
|
||||
}
|
||||
hist.append(block.data)
|
||||
do.b = block.data
|
||||
case blockTypeCompressed:
|
||||
if debugDecoder {
|
||||
println("execute with history length:", len(hist.b), "window:", hist.windowSize)
|
||||
}
|
||||
hist.decoders.seqSize = block.async.seqSize
|
||||
hist.decoders.literals = block.async.literals
|
||||
do.err = block.executeSequences(&hist)
|
||||
hasErr = do.err != nil
|
||||
if debugDecoder && hasErr {
|
||||
println("executeSequences returned:", do.err)
|
||||
}
|
||||
do.b = block.dst
|
||||
}
|
||||
if !hasErr {
|
||||
decodedFrame += uint64(len(do.b))
|
||||
if decodedFrame > fcs {
|
||||
println("fcs exceeded", block.Last, fcs, decodedFrame)
|
||||
do.err = ErrFrameSizeExceeded
|
||||
hasErr = true
|
||||
} else if block.Last && fcs != fcsUnknown && decodedFrame != fcs {
|
||||
do.err = ErrFrameSizeMismatch
|
||||
hasErr = true
|
||||
} else {
|
||||
if debugDecoder {
|
||||
println("fcs ok", block.Last, fcs, decodedFrame)
|
||||
}
|
||||
}
|
||||
}
|
||||
output <- do
|
||||
}
|
||||
close(output)
|
||||
frameHistCache = hist.b
|
||||
wg.Done()
|
||||
if debugDecoder {
|
||||
println("decoder goroutines finished")
|
||||
}
|
||||
hist.reset()
|
||||
}()
|
||||
|
||||
var hist history
|
||||
decodeStream:
|
||||
for {
|
||||
var hasErr bool
|
||||
hist.reset()
|
||||
decodeBlock := func(block *blockDec) {
|
||||
if hasErr {
|
||||
if block != nil {
|
||||
seqDecode <- block
|
||||
}
|
||||
return
|
||||
}
|
||||
if block.err != nil || block.Type != blockTypeCompressed {
|
||||
hasErr = block.err != nil
|
||||
seqDecode <- block
|
||||
return
|
||||
}
|
||||
|
||||
remain, err := block.decodeLiterals(block.data, &hist)
|
||||
block.err = err
|
||||
hasErr = block.err != nil
|
||||
if err == nil {
|
||||
block.async.literals = hist.decoders.literals
|
||||
block.async.seqData = remain
|
||||
} else if debugDecoder {
|
||||
println("decodeLiterals error:", err)
|
||||
}
|
||||
seqDecode <- block
|
||||
}
|
||||
frame := d.frame
|
||||
if debugDecoder {
|
||||
println("New frame...")
|
||||
}
|
||||
var historySent bool
|
||||
frame.history.reset()
|
||||
err := frame.reset(&br)
|
||||
if debugDecoder && err != nil {
|
||||
println("Frame decoder returned", err)
|
||||
}
|
||||
if err == nil {
|
||||
err = d.setDict(frame)
|
||||
}
|
||||
if err == nil && d.frame.WindowSize > d.o.maxWindowSize {
|
||||
if debugDecoder {
|
||||
println("decoder size exceeded, fws:", d.frame.WindowSize, "> mws:", d.o.maxWindowSize)
|
||||
}
|
||||
|
||||
err = ErrDecoderSizeExceeded
|
||||
}
|
||||
if err != nil {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
case dec := <-d.decoders:
|
||||
dec.sendErr(err)
|
||||
decodeBlock(dec)
|
||||
}
|
||||
break decodeStream
|
||||
}
|
||||
|
||||
// Go through all blocks of the frame.
|
||||
for {
|
||||
var dec *blockDec
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
break decodeStream
|
||||
case dec = <-d.decoders:
|
||||
// Once we have a decoder, we MUST return it.
|
||||
}
|
||||
err := frame.next(dec)
|
||||
if !historySent {
|
||||
h := frame.history
|
||||
if debugDecoder {
|
||||
println("Alloc History:", h.allocFrameBuffer)
|
||||
}
|
||||
hist.reset()
|
||||
if h.dict != nil {
|
||||
hist.setDict(h.dict)
|
||||
}
|
||||
dec.async.newHist = &h
|
||||
dec.async.fcs = frame.FrameContentSize
|
||||
historySent = true
|
||||
} else {
|
||||
dec.async.newHist = nil
|
||||
}
|
||||
if debugDecoder && err != nil {
|
||||
println("next block returned error:", err)
|
||||
}
|
||||
dec.err = err
|
||||
dec.hasCRC = false
|
||||
if dec.Last && frame.HasCheckSum && err == nil {
|
||||
crc, err := frame.rawInput.readSmall(4)
|
||||
if len(crc) < 4 {
|
||||
if err == nil {
|
||||
err = io.ErrUnexpectedEOF
|
||||
|
||||
}
|
||||
println("CRC missing?", err)
|
||||
dec.err = err
|
||||
} else {
|
||||
dec.checkCRC = binary.LittleEndian.Uint32(crc)
|
||||
dec.hasCRC = true
|
||||
if debugDecoder {
|
||||
printf("found crc to check: %08x\n", dec.checkCRC)
|
||||
}
|
||||
}
|
||||
}
|
||||
err = dec.err
|
||||
last := dec.Last
|
||||
decodeBlock(dec)
|
||||
if err != nil {
|
||||
break decodeStream
|
||||
}
|
||||
if last {
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
close(seqDecode)
|
||||
wg.Wait()
|
||||
hist.reset()
|
||||
d.frame.history.b = frameHistCache
|
||||
}
|
||||
|
||||
func (d *Decoder) setDict(frame *frameDec) (err error) {
|
||||
dict, ok := d.dicts[frame.DictionaryID]
|
||||
if ok {
|
||||
if debugDecoder {
|
||||
println("setting dict", frame.DictionaryID)
|
||||
}
|
||||
frame.history.setDict(dict)
|
||||
} else if frame.DictionaryID != 0 {
|
||||
// A zero or missing dictionary id is ambiguous:
|
||||
// either dictionary zero, or no dictionary. In particular,
|
||||
// zstd --patch-from uses this id for the source file,
|
||||
// so only return an error if the dictionary id is not zero.
|
||||
err = ErrUnknownDictionary
|
||||
}
|
||||
return err
|
||||
}
|
||||
169
vendor/github.com/klauspost/compress/zstd/decoder_options.go
generated
vendored
169
vendor/github.com/klauspost/compress/zstd/decoder_options.go
generated
vendored
@ -1,169 +0,0 @@
|
||||
// Copyright 2019+ Klaus Post. All rights reserved.
|
||||
// License information can be found in the LICENSE file.
|
||||
// Based on work by Yann Collet, released under BSD License.
|
||||
|
||||
package zstd
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"math/bits"
|
||||
"runtime"
|
||||
)
|
||||
|
||||
// DOption is an option for creating a decoder.
|
||||
type DOption func(*decoderOptions) error
|
||||
|
||||
// options retains accumulated state of multiple options.
|
||||
type decoderOptions struct {
|
||||
lowMem bool
|
||||
concurrent int
|
||||
maxDecodedSize uint64
|
||||
maxWindowSize uint64
|
||||
dicts []*dict
|
||||
ignoreChecksum bool
|
||||
limitToCap bool
|
||||
decodeBufsBelow int
|
||||
}
|
||||
|
||||
func (o *decoderOptions) setDefault() {
|
||||
*o = decoderOptions{
|
||||
// use less ram: true for now, but may change.
|
||||
lowMem: true,
|
||||
concurrent: runtime.GOMAXPROCS(0),
|
||||
maxWindowSize: MaxWindowSize,
|
||||
decodeBufsBelow: 128 << 10,
|
||||
}
|
||||
if o.concurrent > 4 {
|
||||
o.concurrent = 4
|
||||
}
|
||||
o.maxDecodedSize = 64 << 30
|
||||
}
|
||||
|
||||
// WithDecoderLowmem will set whether to use a lower amount of memory,
|
||||
// but possibly have to allocate more while running.
|
||||
func WithDecoderLowmem(b bool) DOption {
|
||||
return func(o *decoderOptions) error { o.lowMem = b; return nil }
|
||||
}
|
||||
|
||||
// WithDecoderConcurrency sets the number of created decoders.
|
||||
// When decoding block with DecodeAll, this will limit the number
|
||||
// of possible concurrently running decodes.
|
||||
// When decoding streams, this will limit the number of
|
||||
// inflight blocks.
|
||||
// When decoding streams and setting maximum to 1,
|
||||
// no async decoding will be done.
|
||||
// When a value of 0 is provided GOMAXPROCS will be used.
|
||||
// By default this will be set to 4 or GOMAXPROCS, whatever is lower.
|
||||
func WithDecoderConcurrency(n int) DOption {
|
||||
return func(o *decoderOptions) error {
|
||||
if n < 0 {
|
||||
return errors.New("concurrency must be at least 1")
|
||||
}
|
||||
if n == 0 {
|
||||
o.concurrent = runtime.GOMAXPROCS(0)
|
||||
} else {
|
||||
o.concurrent = n
|
||||
}
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
// WithDecoderMaxMemory allows to set a maximum decoded size for in-memory
|
||||
// non-streaming operations or maximum window size for streaming operations.
|
||||
// This can be used to control memory usage of potentially hostile content.
|
||||
// Maximum is 1 << 63 bytes. Default is 64GiB.
|
||||
func WithDecoderMaxMemory(n uint64) DOption {
|
||||
return func(o *decoderOptions) error {
|
||||
if n == 0 {
|
||||
return errors.New("WithDecoderMaxMemory must be at least 1")
|
||||
}
|
||||
if n > 1<<63 {
|
||||
return errors.New("WithDecoderMaxmemory must be less than 1 << 63")
|
||||
}
|
||||
o.maxDecodedSize = n
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
// WithDecoderDicts allows to register one or more dictionaries for the decoder.
|
||||
//
|
||||
// Each slice in dict must be in the [dictionary format] produced by
|
||||
// "zstd --train" from the Zstandard reference implementation.
|
||||
//
|
||||
// If several dictionaries with the same ID are provided, the last one will be used.
|
||||
//
|
||||
// [dictionary format]: https://github.com/facebook/zstd/blob/dev/doc/zstd_compression_format.md#dictionary-format
|
||||
func WithDecoderDicts(dicts ...[]byte) DOption {
|
||||
return func(o *decoderOptions) error {
|
||||
for _, b := range dicts {
|
||||
d, err := loadDict(b)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
o.dicts = append(o.dicts, d)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
// WithDecoderDictRaw registers a dictionary that may be used by the decoder.
|
||||
// The slice content can be arbitrary data.
|
||||
func WithDecoderDictRaw(id uint32, content []byte) DOption {
|
||||
return func(o *decoderOptions) error {
|
||||
if bits.UintSize > 32 && uint(len(content)) > dictMaxLength {
|
||||
return fmt.Errorf("dictionary of size %d > 2GiB too large", len(content))
|
||||
}
|
||||
o.dicts = append(o.dicts, &dict{id: id, content: content, offsets: [3]int{1, 4, 8}})
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
// WithDecoderMaxWindow allows to set a maximum window size for decodes.
|
||||
// This allows rejecting packets that will cause big memory usage.
|
||||
// The Decoder will likely allocate more memory based on the WithDecoderLowmem setting.
|
||||
// If WithDecoderMaxMemory is set to a lower value, that will be used.
|
||||
// Default is 512MB, Maximum is ~3.75 TB as per zstandard spec.
|
||||
func WithDecoderMaxWindow(size uint64) DOption {
|
||||
return func(o *decoderOptions) error {
|
||||
if size < MinWindowSize {
|
||||
return errors.New("WithMaxWindowSize must be at least 1KB, 1024 bytes")
|
||||
}
|
||||
if size > (1<<41)+7*(1<<38) {
|
||||
return errors.New("WithMaxWindowSize must be less than (1<<41) + 7*(1<<38) ~ 3.75TB")
|
||||
}
|
||||
o.maxWindowSize = size
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
// WithDecodeAllCapLimit will limit DecodeAll to decoding cap(dst)-len(dst) bytes,
|
||||
// or any size set in WithDecoderMaxMemory.
|
||||
// This can be used to limit decoding to a specific maximum output size.
|
||||
// Disabled by default.
|
||||
func WithDecodeAllCapLimit(b bool) DOption {
|
||||
return func(o *decoderOptions) error {
|
||||
o.limitToCap = b
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
// WithDecodeBuffersBelow will fully decode readers that have a
|
||||
// `Bytes() []byte` and `Len() int` interface similar to bytes.Buffer.
|
||||
// This typically uses less allocations but will have the full decompressed object in memory.
|
||||
// Note that DecodeAllCapLimit will disable this, as well as giving a size of 0 or less.
|
||||
// Default is 128KiB.
|
||||
func WithDecodeBuffersBelow(size int) DOption {
|
||||
return func(o *decoderOptions) error {
|
||||
o.decodeBufsBelow = size
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
// IgnoreChecksum allows to forcibly ignore checksum checking.
|
||||
func IgnoreChecksum(b bool) DOption {
|
||||
return func(o *decoderOptions) error {
|
||||
o.ignoreChecksum = b
|
||||
return nil
|
||||
}
|
||||
}
|
||||
565
vendor/github.com/klauspost/compress/zstd/dict.go
generated
vendored
565
vendor/github.com/klauspost/compress/zstd/dict.go
generated
vendored
@ -1,565 +0,0 @@
|
||||
package zstd
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"math"
|
||||
"sort"
|
||||
|
||||
"github.com/klauspost/compress/huff0"
|
||||
)
|
||||
|
||||
type dict struct {
|
||||
id uint32
|
||||
|
||||
litEnc *huff0.Scratch
|
||||
llDec, ofDec, mlDec sequenceDec
|
||||
offsets [3]int
|
||||
content []byte
|
||||
}
|
||||
|
||||
const dictMagic = "\x37\xa4\x30\xec"
|
||||
|
||||
// Maximum dictionary size for the reference implementation (1.5.3) is 2 GiB.
|
||||
const dictMaxLength = 1 << 31
|
||||
|
||||
// ID returns the dictionary id or 0 if d is nil.
|
||||
func (d *dict) ID() uint32 {
|
||||
if d == nil {
|
||||
return 0
|
||||
}
|
||||
return d.id
|
||||
}
|
||||
|
||||
// ContentSize returns the dictionary content size or 0 if d is nil.
|
||||
func (d *dict) ContentSize() int {
|
||||
if d == nil {
|
||||
return 0
|
||||
}
|
||||
return len(d.content)
|
||||
}
|
||||
|
||||
// Content returns the dictionary content.
|
||||
func (d *dict) Content() []byte {
|
||||
if d == nil {
|
||||
return nil
|
||||
}
|
||||
return d.content
|
||||
}
|
||||
|
||||
// Offsets returns the initial offsets.
|
||||
func (d *dict) Offsets() [3]int {
|
||||
if d == nil {
|
||||
return [3]int{}
|
||||
}
|
||||
return d.offsets
|
||||
}
|
||||
|
||||
// LitEncoder returns the literal encoder.
|
||||
func (d *dict) LitEncoder() *huff0.Scratch {
|
||||
if d == nil {
|
||||
return nil
|
||||
}
|
||||
return d.litEnc
|
||||
}
|
||||
|
||||
// Load a dictionary as described in
|
||||
// https://github.com/facebook/zstd/blob/master/doc/zstd_compression_format.md#dictionary-format
|
||||
func loadDict(b []byte) (*dict, error) {
|
||||
// Check static field size.
|
||||
if len(b) <= 8+(3*4) {
|
||||
return nil, io.ErrUnexpectedEOF
|
||||
}
|
||||
d := dict{
|
||||
llDec: sequenceDec{fse: &fseDecoder{}},
|
||||
ofDec: sequenceDec{fse: &fseDecoder{}},
|
||||
mlDec: sequenceDec{fse: &fseDecoder{}},
|
||||
}
|
||||
if string(b[:4]) != dictMagic {
|
||||
return nil, ErrMagicMismatch
|
||||
}
|
||||
d.id = binary.LittleEndian.Uint32(b[4:8])
|
||||
if d.id == 0 {
|
||||
return nil, errors.New("dictionaries cannot have ID 0")
|
||||
}
|
||||
|
||||
// Read literal table
|
||||
var err error
|
||||
d.litEnc, b, err = huff0.ReadTable(b[8:], nil)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("loading literal table: %w", err)
|
||||
}
|
||||
d.litEnc.Reuse = huff0.ReusePolicyMust
|
||||
|
||||
br := byteReader{
|
||||
b: b,
|
||||
off: 0,
|
||||
}
|
||||
readDec := func(i tableIndex, dec *fseDecoder) error {
|
||||
if err := dec.readNCount(&br, uint16(maxTableSymbol[i])); err != nil {
|
||||
return err
|
||||
}
|
||||
if br.overread() {
|
||||
return io.ErrUnexpectedEOF
|
||||
}
|
||||
err = dec.transform(symbolTableX[i])
|
||||
if err != nil {
|
||||
println("Transform table error:", err)
|
||||
return err
|
||||
}
|
||||
if debugDecoder || debugEncoder {
|
||||
println("Read table ok", "symbolLen:", dec.symbolLen)
|
||||
}
|
||||
// Set decoders as predefined so they aren't reused.
|
||||
dec.preDefined = true
|
||||
return nil
|
||||
}
|
||||
|
||||
if err := readDec(tableOffsets, d.ofDec.fse); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if err := readDec(tableMatchLengths, d.mlDec.fse); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if err := readDec(tableLiteralLengths, d.llDec.fse); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if br.remain() < 12 {
|
||||
return nil, io.ErrUnexpectedEOF
|
||||
}
|
||||
|
||||
d.offsets[0] = int(br.Uint32())
|
||||
br.advance(4)
|
||||
d.offsets[1] = int(br.Uint32())
|
||||
br.advance(4)
|
||||
d.offsets[2] = int(br.Uint32())
|
||||
br.advance(4)
|
||||
if d.offsets[0] <= 0 || d.offsets[1] <= 0 || d.offsets[2] <= 0 {
|
||||
return nil, errors.New("invalid offset in dictionary")
|
||||
}
|
||||
d.content = make([]byte, br.remain())
|
||||
copy(d.content, br.unread())
|
||||
if d.offsets[0] > len(d.content) || d.offsets[1] > len(d.content) || d.offsets[2] > len(d.content) {
|
||||
return nil, fmt.Errorf("initial offset bigger than dictionary content size %d, offsets: %v", len(d.content), d.offsets)
|
||||
}
|
||||
|
||||
return &d, nil
|
||||
}
|
||||
|
||||
// InspectDictionary loads a zstd dictionary and provides functions to inspect the content.
|
||||
func InspectDictionary(b []byte) (interface {
|
||||
ID() uint32
|
||||
ContentSize() int
|
||||
Content() []byte
|
||||
Offsets() [3]int
|
||||
LitEncoder() *huff0.Scratch
|
||||
}, error) {
|
||||
initPredefined()
|
||||
d, err := loadDict(b)
|
||||
return d, err
|
||||
}
|
||||
|
||||
type BuildDictOptions struct {
|
||||
// Dictionary ID.
|
||||
ID uint32
|
||||
|
||||
// Content to use to create dictionary tables.
|
||||
Contents [][]byte
|
||||
|
||||
// History to use for all blocks.
|
||||
History []byte
|
||||
|
||||
// Offsets to use.
|
||||
Offsets [3]int
|
||||
|
||||
// CompatV155 will make the dictionary compatible with Zstd v1.5.5 and earlier.
|
||||
// See https://github.com/facebook/zstd/issues/3724
|
||||
CompatV155 bool
|
||||
|
||||
// Use the specified encoder level.
|
||||
// The dictionary will be built using the specified encoder level,
|
||||
// which will reflect speed and make the dictionary tailored for that level.
|
||||
// If not set SpeedBestCompression will be used.
|
||||
Level EncoderLevel
|
||||
|
||||
// DebugOut will write stats and other details here if set.
|
||||
DebugOut io.Writer
|
||||
}
|
||||
|
||||
func BuildDict(o BuildDictOptions) ([]byte, error) {
|
||||
initPredefined()
|
||||
hist := o.History
|
||||
contents := o.Contents
|
||||
debug := o.DebugOut != nil
|
||||
println := func(args ...interface{}) {
|
||||
if o.DebugOut != nil {
|
||||
fmt.Fprintln(o.DebugOut, args...)
|
||||
}
|
||||
}
|
||||
printf := func(s string, args ...interface{}) {
|
||||
if o.DebugOut != nil {
|
||||
fmt.Fprintf(o.DebugOut, s, args...)
|
||||
}
|
||||
}
|
||||
print := func(args ...interface{}) {
|
||||
if o.DebugOut != nil {
|
||||
fmt.Fprint(o.DebugOut, args...)
|
||||
}
|
||||
}
|
||||
|
||||
if int64(len(hist)) > dictMaxLength {
|
||||
return nil, fmt.Errorf("dictionary of size %d > %d", len(hist), int64(dictMaxLength))
|
||||
}
|
||||
if len(hist) < 8 {
|
||||
return nil, fmt.Errorf("dictionary of size %d < %d", len(hist), 8)
|
||||
}
|
||||
if len(contents) == 0 {
|
||||
return nil, errors.New("no content provided")
|
||||
}
|
||||
d := dict{
|
||||
id: o.ID,
|
||||
litEnc: nil,
|
||||
llDec: sequenceDec{},
|
||||
ofDec: sequenceDec{},
|
||||
mlDec: sequenceDec{},
|
||||
offsets: o.Offsets,
|
||||
content: hist,
|
||||
}
|
||||
block := blockEnc{lowMem: false}
|
||||
block.init()
|
||||
enc := encoder(&bestFastEncoder{fastBase: fastBase{maxMatchOff: int32(maxMatchLen), bufferReset: math.MaxInt32 - int32(maxMatchLen*2), lowMem: false}})
|
||||
if o.Level != 0 {
|
||||
eOpts := encoderOptions{
|
||||
level: o.Level,
|
||||
blockSize: maxMatchLen,
|
||||
windowSize: maxMatchLen,
|
||||
dict: &d,
|
||||
lowMem: false,
|
||||
}
|
||||
enc = eOpts.encoder()
|
||||
} else {
|
||||
o.Level = SpeedBestCompression
|
||||
}
|
||||
var (
|
||||
remain [256]int
|
||||
ll [256]int
|
||||
ml [256]int
|
||||
of [256]int
|
||||
)
|
||||
addValues := func(dst *[256]int, src []byte) {
|
||||
for _, v := range src {
|
||||
dst[v]++
|
||||
}
|
||||
}
|
||||
addHist := func(dst *[256]int, src *[256]uint32) {
|
||||
for i, v := range src {
|
||||
dst[i] += int(v)
|
||||
}
|
||||
}
|
||||
seqs := 0
|
||||
nUsed := 0
|
||||
litTotal := 0
|
||||
newOffsets := make(map[uint32]int, 1000)
|
||||
for _, b := range contents {
|
||||
block.reset(nil)
|
||||
if len(b) < 8 {
|
||||
continue
|
||||
}
|
||||
nUsed++
|
||||
enc.Reset(&d, true)
|
||||
enc.Encode(&block, b)
|
||||
addValues(&remain, block.literals)
|
||||
litTotal += len(block.literals)
|
||||
if len(block.sequences) == 0 {
|
||||
continue
|
||||
}
|
||||
seqs += len(block.sequences)
|
||||
block.genCodes()
|
||||
addHist(&ll, block.coders.llEnc.Histogram())
|
||||
addHist(&ml, block.coders.mlEnc.Histogram())
|
||||
addHist(&of, block.coders.ofEnc.Histogram())
|
||||
for i, seq := range block.sequences {
|
||||
if i > 3 {
|
||||
break
|
||||
}
|
||||
offset := seq.offset
|
||||
if offset == 0 {
|
||||
continue
|
||||
}
|
||||
if int(offset) >= len(o.History) {
|
||||
continue
|
||||
}
|
||||
if offset > 3 {
|
||||
newOffsets[offset-3]++
|
||||
} else {
|
||||
newOffsets[uint32(o.Offsets[offset-1])]++
|
||||
}
|
||||
}
|
||||
}
|
||||
// Find most used offsets.
|
||||
var sortedOffsets []uint32
|
||||
for k := range newOffsets {
|
||||
sortedOffsets = append(sortedOffsets, k)
|
||||
}
|
||||
sort.Slice(sortedOffsets, func(i, j int) bool {
|
||||
a, b := sortedOffsets[i], sortedOffsets[j]
|
||||
if a == b {
|
||||
// Prefer the longer offset
|
||||
return sortedOffsets[i] > sortedOffsets[j]
|
||||
}
|
||||
return newOffsets[sortedOffsets[i]] > newOffsets[sortedOffsets[j]]
|
||||
})
|
||||
if len(sortedOffsets) > 3 {
|
||||
if debug {
|
||||
print("Offsets:")
|
||||
for i, v := range sortedOffsets {
|
||||
if i > 20 {
|
||||
break
|
||||
}
|
||||
printf("[%d: %d],", v, newOffsets[v])
|
||||
}
|
||||
println("")
|
||||
}
|
||||
|
||||
sortedOffsets = sortedOffsets[:3]
|
||||
}
|
||||
for i, v := range sortedOffsets {
|
||||
o.Offsets[i] = int(v)
|
||||
}
|
||||
if debug {
|
||||
println("New repeat offsets", o.Offsets)
|
||||
}
|
||||
|
||||
if nUsed == 0 || seqs == 0 {
|
||||
return nil, fmt.Errorf("%d blocks, %d sequences found", nUsed, seqs)
|
||||
}
|
||||
if debug {
|
||||
println("Sequences:", seqs, "Blocks:", nUsed, "Literals:", litTotal)
|
||||
}
|
||||
if seqs/nUsed < 512 {
|
||||
// Use 512 as minimum.
|
||||
nUsed = seqs / 512
|
||||
if nUsed == 0 {
|
||||
nUsed = 1
|
||||
}
|
||||
}
|
||||
copyHist := func(dst *fseEncoder, src *[256]int) ([]byte, error) {
|
||||
hist := dst.Histogram()
|
||||
var maxSym uint8
|
||||
var maxCount int
|
||||
var fakeLength int
|
||||
for i, v := range src {
|
||||
if v > 0 {
|
||||
v = v / nUsed
|
||||
if v == 0 {
|
||||
v = 1
|
||||
}
|
||||
}
|
||||
if v > maxCount {
|
||||
maxCount = v
|
||||
}
|
||||
if v != 0 {
|
||||
maxSym = uint8(i)
|
||||
}
|
||||
fakeLength += v
|
||||
hist[i] = uint32(v)
|
||||
}
|
||||
|
||||
// Ensure we aren't trying to represent RLE.
|
||||
if maxCount == fakeLength {
|
||||
for i := range hist {
|
||||
if uint8(i) == maxSym {
|
||||
fakeLength++
|
||||
maxSym++
|
||||
hist[i+1] = 1
|
||||
if maxSym > 1 {
|
||||
break
|
||||
}
|
||||
}
|
||||
if hist[0] == 0 {
|
||||
fakeLength++
|
||||
hist[i] = 1
|
||||
if maxSym > 1 {
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
dst.HistogramFinished(maxSym, maxCount)
|
||||
dst.reUsed = false
|
||||
dst.useRLE = false
|
||||
err := dst.normalizeCount(fakeLength)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if debug {
|
||||
println("RAW:", dst.count[:maxSym+1], "NORM:", dst.norm[:maxSym+1], "LEN:", fakeLength)
|
||||
}
|
||||
return dst.writeCount(nil)
|
||||
}
|
||||
if debug {
|
||||
print("Literal lengths: ")
|
||||
}
|
||||
llTable, err := copyHist(block.coders.llEnc, &ll)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if debug {
|
||||
print("Match lengths: ")
|
||||
}
|
||||
mlTable, err := copyHist(block.coders.mlEnc, &ml)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if debug {
|
||||
print("Offsets: ")
|
||||
}
|
||||
ofTable, err := copyHist(block.coders.ofEnc, &of)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
// Literal table
|
||||
avgSize := litTotal
|
||||
if avgSize > huff0.BlockSizeMax/2 {
|
||||
avgSize = huff0.BlockSizeMax / 2
|
||||
}
|
||||
huffBuff := make([]byte, 0, avgSize)
|
||||
// Target size
|
||||
div := litTotal / avgSize
|
||||
if div < 1 {
|
||||
div = 1
|
||||
}
|
||||
if debug {
|
||||
println("Huffman weights:")
|
||||
}
|
||||
for i, n := range remain[:] {
|
||||
if n > 0 {
|
||||
n = n / div
|
||||
// Allow all entries to be represented.
|
||||
if n == 0 {
|
||||
n = 1
|
||||
}
|
||||
huffBuff = append(huffBuff, bytes.Repeat([]byte{byte(i)}, n)...)
|
||||
if debug {
|
||||
printf("[%d: %d], ", i, n)
|
||||
}
|
||||
}
|
||||
}
|
||||
if o.CompatV155 && remain[255]/div == 0 {
|
||||
huffBuff = append(huffBuff, 255)
|
||||
}
|
||||
scratch := &huff0.Scratch{TableLog: 11}
|
||||
for tries := 0; tries < 255; tries++ {
|
||||
scratch = &huff0.Scratch{TableLog: 11}
|
||||
_, _, err = huff0.Compress1X(huffBuff, scratch)
|
||||
if err == nil {
|
||||
break
|
||||
}
|
||||
if debug {
|
||||
printf("Try %d: Huffman error: %v\n", tries+1, err)
|
||||
}
|
||||
huffBuff = huffBuff[:0]
|
||||
if tries == 250 {
|
||||
if debug {
|
||||
println("Huffman: Bailing out with predefined table")
|
||||
}
|
||||
|
||||
// Bail out.... Just generate something
|
||||
huffBuff = append(huffBuff, bytes.Repeat([]byte{255}, 10000)...)
|
||||
for i := 0; i < 128; i++ {
|
||||
huffBuff = append(huffBuff, byte(i))
|
||||
}
|
||||
continue
|
||||
}
|
||||
if errors.Is(err, huff0.ErrIncompressible) {
|
||||
// Try truncating least common.
|
||||
for i, n := range remain[:] {
|
||||
if n > 0 {
|
||||
n = n / (div * (i + 1))
|
||||
if n > 0 {
|
||||
huffBuff = append(huffBuff, bytes.Repeat([]byte{byte(i)}, n)...)
|
||||
}
|
||||
}
|
||||
}
|
||||
if o.CompatV155 && len(huffBuff) > 0 && huffBuff[len(huffBuff)-1] != 255 {
|
||||
huffBuff = append(huffBuff, 255)
|
||||
}
|
||||
if len(huffBuff) == 0 {
|
||||
huffBuff = append(huffBuff, 0, 255)
|
||||
}
|
||||
}
|
||||
if errors.Is(err, huff0.ErrUseRLE) {
|
||||
for i, n := range remain[:] {
|
||||
n = n / (div * (i + 1))
|
||||
// Allow all entries to be represented.
|
||||
if n == 0 {
|
||||
n = 1
|
||||
}
|
||||
huffBuff = append(huffBuff, bytes.Repeat([]byte{byte(i)}, n)...)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
var out bytes.Buffer
|
||||
out.Write([]byte(dictMagic))
|
||||
out.Write(binary.LittleEndian.AppendUint32(nil, o.ID))
|
||||
out.Write(scratch.OutTable)
|
||||
if debug {
|
||||
println("huff table:", len(scratch.OutTable), "bytes")
|
||||
println("of table:", len(ofTable), "bytes")
|
||||
println("ml table:", len(mlTable), "bytes")
|
||||
println("ll table:", len(llTable), "bytes")
|
||||
}
|
||||
out.Write(ofTable)
|
||||
out.Write(mlTable)
|
||||
out.Write(llTable)
|
||||
out.Write(binary.LittleEndian.AppendUint32(nil, uint32(o.Offsets[0])))
|
||||
out.Write(binary.LittleEndian.AppendUint32(nil, uint32(o.Offsets[1])))
|
||||
out.Write(binary.LittleEndian.AppendUint32(nil, uint32(o.Offsets[2])))
|
||||
out.Write(hist)
|
||||
if debug {
|
||||
_, err := loadDict(out.Bytes())
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
i, err := InspectDictionary(out.Bytes())
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
println("ID:", i.ID())
|
||||
println("Content size:", i.ContentSize())
|
||||
println("Encoder:", i.LitEncoder() != nil)
|
||||
println("Offsets:", i.Offsets())
|
||||
var totalSize int
|
||||
for _, b := range contents {
|
||||
totalSize += len(b)
|
||||
}
|
||||
|
||||
encWith := func(opts ...EOption) int {
|
||||
enc, err := NewWriter(nil, opts...)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
defer enc.Close()
|
||||
var dst []byte
|
||||
var totalSize int
|
||||
for _, b := range contents {
|
||||
dst = enc.EncodeAll(b, dst[:0])
|
||||
totalSize += len(dst)
|
||||
}
|
||||
return totalSize
|
||||
}
|
||||
plain := encWith(WithEncoderLevel(o.Level))
|
||||
withDict := encWith(WithEncoderLevel(o.Level), WithEncoderDict(out.Bytes()))
|
||||
println("Input size:", totalSize)
|
||||
println("Plain Compressed:", plain)
|
||||
println("Dict Compressed:", withDict)
|
||||
println("Saved:", plain-withDict, (plain-withDict)/len(contents), "bytes per input (rounded down)")
|
||||
}
|
||||
return out.Bytes(), nil
|
||||
}
|
||||
173
vendor/github.com/klauspost/compress/zstd/enc_base.go
generated
vendored
173
vendor/github.com/klauspost/compress/zstd/enc_base.go
generated
vendored
@ -1,173 +0,0 @@
|
||||
package zstd
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"math/bits"
|
||||
|
||||
"github.com/klauspost/compress/zstd/internal/xxhash"
|
||||
)
|
||||
|
||||
const (
|
||||
dictShardBits = 6
|
||||
)
|
||||
|
||||
type fastBase struct {
|
||||
// cur is the offset at the start of hist
|
||||
cur int32
|
||||
// maximum offset. Should be at least 2x block size.
|
||||
maxMatchOff int32
|
||||
bufferReset int32
|
||||
hist []byte
|
||||
crc *xxhash.Digest
|
||||
tmp [8]byte
|
||||
blk *blockEnc
|
||||
lastDictID uint32
|
||||
lowMem bool
|
||||
}
|
||||
|
||||
// CRC returns the underlying CRC writer.
|
||||
func (e *fastBase) CRC() *xxhash.Digest {
|
||||
return e.crc
|
||||
}
|
||||
|
||||
// AppendCRC will append the CRC to the destination slice and return it.
|
||||
func (e *fastBase) AppendCRC(dst []byte) []byte {
|
||||
crc := e.crc.Sum(e.tmp[:0])
|
||||
dst = append(dst, crc[7], crc[6], crc[5], crc[4])
|
||||
return dst
|
||||
}
|
||||
|
||||
// WindowSize returns the window size of the encoder,
|
||||
// or a window size small enough to contain the input size, if > 0.
|
||||
func (e *fastBase) WindowSize(size int64) int32 {
|
||||
if size > 0 && size < int64(e.maxMatchOff) {
|
||||
b := int32(1) << uint(bits.Len(uint(size)))
|
||||
// Keep minimum window.
|
||||
if b < 1024 {
|
||||
b = 1024
|
||||
}
|
||||
return b
|
||||
}
|
||||
return e.maxMatchOff
|
||||
}
|
||||
|
||||
// Block returns the current block.
|
||||
func (e *fastBase) Block() *blockEnc {
|
||||
return e.blk
|
||||
}
|
||||
|
||||
func (e *fastBase) addBlock(src []byte) int32 {
|
||||
if debugAsserts && e.cur > e.bufferReset {
|
||||
panic(fmt.Sprintf("ecur (%d) > buffer reset (%d)", e.cur, e.bufferReset))
|
||||
}
|
||||
// check if we have space already
|
||||
if len(e.hist)+len(src) > cap(e.hist) {
|
||||
if cap(e.hist) == 0 {
|
||||
e.ensureHist(len(src))
|
||||
} else {
|
||||
if cap(e.hist) < int(e.maxMatchOff+maxCompressedBlockSize) {
|
||||
panic(fmt.Errorf("unexpected buffer cap %d, want at least %d with window %d", cap(e.hist), e.maxMatchOff+maxCompressedBlockSize, e.maxMatchOff))
|
||||
}
|
||||
// Move down
|
||||
offset := int32(len(e.hist)) - e.maxMatchOff
|
||||
copy(e.hist[0:e.maxMatchOff], e.hist[offset:])
|
||||
e.cur += offset
|
||||
e.hist = e.hist[:e.maxMatchOff]
|
||||
}
|
||||
}
|
||||
s := int32(len(e.hist))
|
||||
e.hist = append(e.hist, src...)
|
||||
return s
|
||||
}
|
||||
|
||||
// ensureHist will ensure that history can keep at least this many bytes.
|
||||
func (e *fastBase) ensureHist(n int) {
|
||||
if cap(e.hist) >= n {
|
||||
return
|
||||
}
|
||||
l := e.maxMatchOff
|
||||
if (e.lowMem && e.maxMatchOff > maxCompressedBlockSize) || e.maxMatchOff <= maxCompressedBlockSize {
|
||||
l += maxCompressedBlockSize
|
||||
} else {
|
||||
l += e.maxMatchOff
|
||||
}
|
||||
// Make it at least 1MB.
|
||||
if l < 1<<20 && !e.lowMem {
|
||||
l = 1 << 20
|
||||
}
|
||||
// Make it at least the requested size.
|
||||
if l < int32(n) {
|
||||
l = int32(n)
|
||||
}
|
||||
e.hist = make([]byte, 0, l)
|
||||
}
|
||||
|
||||
// useBlock will replace the block with the provided one,
|
||||
// but transfer recent offsets from the previous.
|
||||
func (e *fastBase) UseBlock(enc *blockEnc) {
|
||||
enc.reset(e.blk)
|
||||
e.blk = enc
|
||||
}
|
||||
|
||||
func (e *fastBase) matchlen(s, t int32, src []byte) int32 {
|
||||
if debugAsserts {
|
||||
if s < 0 {
|
||||
err := fmt.Sprintf("s (%d) < 0", s)
|
||||
panic(err)
|
||||
}
|
||||
if t < 0 {
|
||||
err := fmt.Sprintf("s (%d) < 0", s)
|
||||
panic(err)
|
||||
}
|
||||
if s-t > e.maxMatchOff {
|
||||
err := fmt.Sprintf("s (%d) - t (%d) > maxMatchOff (%d)", s, t, e.maxMatchOff)
|
||||
panic(err)
|
||||
}
|
||||
if len(src)-int(s) > maxCompressedBlockSize {
|
||||
panic(fmt.Sprintf("len(src)-s (%d) > maxCompressedBlockSize (%d)", len(src)-int(s), maxCompressedBlockSize))
|
||||
}
|
||||
}
|
||||
return int32(matchLen(src[s:], src[t:]))
|
||||
}
|
||||
|
||||
// Reset the encoding table.
|
||||
func (e *fastBase) resetBase(d *dict, singleBlock bool) {
|
||||
if e.blk == nil {
|
||||
e.blk = &blockEnc{lowMem: e.lowMem}
|
||||
e.blk.init()
|
||||
} else {
|
||||
e.blk.reset(nil)
|
||||
}
|
||||
e.blk.initNewEncode()
|
||||
if e.crc == nil {
|
||||
e.crc = xxhash.New()
|
||||
} else {
|
||||
e.crc.Reset()
|
||||
}
|
||||
e.blk.dictLitEnc = nil
|
||||
if d != nil {
|
||||
low := e.lowMem
|
||||
if singleBlock {
|
||||
e.lowMem = true
|
||||
}
|
||||
e.ensureHist(d.ContentSize() + maxCompressedBlockSize)
|
||||
e.lowMem = low
|
||||
}
|
||||
|
||||
// We offset current position so everything will be out of reach.
|
||||
// If above reset line, history will be purged.
|
||||
if e.cur < e.bufferReset {
|
||||
e.cur += e.maxMatchOff + int32(len(e.hist))
|
||||
}
|
||||
e.hist = e.hist[:0]
|
||||
if d != nil {
|
||||
// Set offsets (currently not used)
|
||||
for i, off := range d.offsets {
|
||||
e.blk.recentOffsets[i] = uint32(off)
|
||||
e.blk.prevRecentOffsets[i] = e.blk.recentOffsets[i]
|
||||
}
|
||||
// Transfer litenc.
|
||||
e.blk.dictLitEnc = d.litEnc
|
||||
e.hist = append(e.hist, d.content...)
|
||||
}
|
||||
}
|
||||
560
vendor/github.com/klauspost/compress/zstd/enc_best.go
generated
vendored
560
vendor/github.com/klauspost/compress/zstd/enc_best.go
generated
vendored
@ -1,560 +0,0 @@
|
||||
// Copyright 2019+ Klaus Post. All rights reserved.
|
||||
// License information can be found in the LICENSE file.
|
||||
// Based on work by Yann Collet, released under BSD License.
|
||||
|
||||
package zstd
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
|
||||
"github.com/klauspost/compress"
|
||||
)
|
||||
|
||||
const (
|
||||
bestLongTableBits = 22 // Bits used in the long match table
|
||||
bestLongTableSize = 1 << bestLongTableBits // Size of the table
|
||||
bestLongLen = 8 // Bytes used for table hash
|
||||
|
||||
// Note: Increasing the short table bits or making the hash shorter
|
||||
// can actually lead to compression degradation since it will 'steal' more from the
|
||||
// long match table and match offsets are quite big.
|
||||
// This greatly depends on the type of input.
|
||||
bestShortTableBits = 18 // Bits used in the short match table
|
||||
bestShortTableSize = 1 << bestShortTableBits // Size of the table
|
||||
bestShortLen = 4 // Bytes used for table hash
|
||||
|
||||
)
|
||||
|
||||
type match struct {
|
||||
offset int32
|
||||
s int32
|
||||
length int32
|
||||
rep int32
|
||||
est int32
|
||||
}
|
||||
|
||||
const highScore = maxMatchLen * 8
|
||||
|
||||
// estBits will estimate output bits from predefined tables.
|
||||
func (m *match) estBits(bitsPerByte int32) {
|
||||
mlc := mlCode(uint32(m.length - zstdMinMatch))
|
||||
var ofc uint8
|
||||
if m.rep < 0 {
|
||||
ofc = ofCode(uint32(m.s-m.offset) + 3)
|
||||
} else {
|
||||
ofc = ofCode(uint32(m.rep) & 3)
|
||||
}
|
||||
// Cost, excluding
|
||||
ofTT, mlTT := fsePredefEnc[tableOffsets].ct.symbolTT[ofc], fsePredefEnc[tableMatchLengths].ct.symbolTT[mlc]
|
||||
|
||||
// Add cost of match encoding...
|
||||
m.est = int32(ofTT.outBits + mlTT.outBits)
|
||||
m.est += int32(ofTT.deltaNbBits>>16 + mlTT.deltaNbBits>>16)
|
||||
// Subtract savings compared to literal encoding...
|
||||
m.est -= (m.length * bitsPerByte) >> 10
|
||||
if m.est > 0 {
|
||||
// Unlikely gain..
|
||||
m.length = 0
|
||||
m.est = highScore
|
||||
}
|
||||
}
|
||||
|
||||
// bestFastEncoder uses 2 tables, one for short matches (5 bytes) and one for long matches.
|
||||
// The long match table contains the previous entry with the same hash,
|
||||
// effectively making it a "chain" of length 2.
|
||||
// When we find a long match we choose between the two values and select the longest.
|
||||
// When we find a short match, after checking the long, we check if we can find a long at n+1
|
||||
// and that it is longer (lazy matching).
|
||||
type bestFastEncoder struct {
|
||||
fastBase
|
||||
table [bestShortTableSize]prevEntry
|
||||
longTable [bestLongTableSize]prevEntry
|
||||
dictTable []prevEntry
|
||||
dictLongTable []prevEntry
|
||||
}
|
||||
|
||||
// Encode improves compression...
|
||||
func (e *bestFastEncoder) Encode(blk *blockEnc, src []byte) {
|
||||
const (
|
||||
// Input margin is the number of bytes we read (8)
|
||||
// and the maximum we will read ahead (2)
|
||||
inputMargin = 8 + 4
|
||||
minNonLiteralBlockSize = 16
|
||||
)
|
||||
|
||||
// Protect against e.cur wraparound.
|
||||
for e.cur >= e.bufferReset-int32(len(e.hist)) {
|
||||
if len(e.hist) == 0 {
|
||||
e.table = [bestShortTableSize]prevEntry{}
|
||||
e.longTable = [bestLongTableSize]prevEntry{}
|
||||
e.cur = e.maxMatchOff
|
||||
break
|
||||
}
|
||||
// Shift down everything in the table that isn't already too far away.
|
||||
minOff := e.cur + int32(len(e.hist)) - e.maxMatchOff
|
||||
for i := range e.table[:] {
|
||||
v := e.table[i].offset
|
||||
v2 := e.table[i].prev
|
||||
if v < minOff {
|
||||
v = 0
|
||||
v2 = 0
|
||||
} else {
|
||||
v = v - e.cur + e.maxMatchOff
|
||||
if v2 < minOff {
|
||||
v2 = 0
|
||||
} else {
|
||||
v2 = v2 - e.cur + e.maxMatchOff
|
||||
}
|
||||
}
|
||||
e.table[i] = prevEntry{
|
||||
offset: v,
|
||||
prev: v2,
|
||||
}
|
||||
}
|
||||
for i := range e.longTable[:] {
|
||||
v := e.longTable[i].offset
|
||||
v2 := e.longTable[i].prev
|
||||
if v < minOff {
|
||||
v = 0
|
||||
v2 = 0
|
||||
} else {
|
||||
v = v - e.cur + e.maxMatchOff
|
||||
if v2 < minOff {
|
||||
v2 = 0
|
||||
} else {
|
||||
v2 = v2 - e.cur + e.maxMatchOff
|
||||
}
|
||||
}
|
||||
e.longTable[i] = prevEntry{
|
||||
offset: v,
|
||||
prev: v2,
|
||||
}
|
||||
}
|
||||
e.cur = e.maxMatchOff
|
||||
break
|
||||
}
|
||||
|
||||
// Add block to history
|
||||
s := e.addBlock(src)
|
||||
blk.size = len(src)
|
||||
|
||||
// Check RLE first
|
||||
if len(src) > zstdMinMatch {
|
||||
ml := matchLen(src[1:], src)
|
||||
if ml == len(src)-1 {
|
||||
blk.literals = append(blk.literals, src[0])
|
||||
blk.sequences = append(blk.sequences, seq{litLen: 1, matchLen: uint32(len(src)-1) - zstdMinMatch, offset: 1 + 3})
|
||||
return
|
||||
}
|
||||
}
|
||||
|
||||
if len(src) < minNonLiteralBlockSize {
|
||||
blk.extraLits = len(src)
|
||||
blk.literals = blk.literals[:len(src)]
|
||||
copy(blk.literals, src)
|
||||
return
|
||||
}
|
||||
|
||||
// Use this to estimate literal cost.
|
||||
// Scaled by 10 bits.
|
||||
bitsPerByte := int32((compress.ShannonEntropyBits(src) * 1024) / len(src))
|
||||
// Huffman can never go < 1 bit/byte
|
||||
if bitsPerByte < 1024 {
|
||||
bitsPerByte = 1024
|
||||
}
|
||||
|
||||
// Override src
|
||||
src = e.hist
|
||||
sLimit := int32(len(src)) - inputMargin
|
||||
const kSearchStrength = 10
|
||||
|
||||
// nextEmit is where in src the next emitLiteral should start from.
|
||||
nextEmit := s
|
||||
|
||||
// Relative offsets
|
||||
offset1 := int32(blk.recentOffsets[0])
|
||||
offset2 := int32(blk.recentOffsets[1])
|
||||
offset3 := int32(blk.recentOffsets[2])
|
||||
|
||||
addLiterals := func(s *seq, until int32) {
|
||||
if until == nextEmit {
|
||||
return
|
||||
}
|
||||
blk.literals = append(blk.literals, src[nextEmit:until]...)
|
||||
s.litLen = uint32(until - nextEmit)
|
||||
}
|
||||
|
||||
if debugEncoder {
|
||||
println("recent offsets:", blk.recentOffsets)
|
||||
}
|
||||
|
||||
encodeLoop:
|
||||
for {
|
||||
// We allow the encoder to optionally turn off repeat offsets across blocks
|
||||
canRepeat := len(blk.sequences) > 2
|
||||
|
||||
if debugAsserts && canRepeat && offset1 == 0 {
|
||||
panic("offset0 was 0")
|
||||
}
|
||||
|
||||
const goodEnough = 250
|
||||
|
||||
cv := load6432(src, s)
|
||||
|
||||
nextHashL := hashLen(cv, bestLongTableBits, bestLongLen)
|
||||
nextHashS := hashLen(cv, bestShortTableBits, bestShortLen)
|
||||
candidateL := e.longTable[nextHashL]
|
||||
candidateS := e.table[nextHashS]
|
||||
|
||||
// Set m to a match at offset if it looks like that will improve compression.
|
||||
improve := func(m *match, offset int32, s int32, first uint32, rep int32) {
|
||||
delta := s - offset
|
||||
if delta >= e.maxMatchOff || delta <= 0 || load3232(src, offset) != first {
|
||||
return
|
||||
}
|
||||
// Try to quick reject if we already have a long match.
|
||||
if m.length > 16 {
|
||||
left := len(src) - int(m.s+m.length)
|
||||
// If we are too close to the end, keep as is.
|
||||
if left <= 0 {
|
||||
return
|
||||
}
|
||||
checkLen := m.length - (s - m.s) - 8
|
||||
if left > 2 && checkLen > 4 {
|
||||
// Check 4 bytes, 4 bytes from the end of the current match.
|
||||
a := load3232(src, offset+checkLen)
|
||||
b := load3232(src, s+checkLen)
|
||||
if a != b {
|
||||
return
|
||||
}
|
||||
}
|
||||
}
|
||||
l := 4 + e.matchlen(s+4, offset+4, src)
|
||||
if m.rep <= 0 {
|
||||
// Extend candidate match backwards as far as possible.
|
||||
// Do not extend repeats as we can assume they are optimal
|
||||
// and offsets change if s == nextEmit.
|
||||
tMin := s - e.maxMatchOff
|
||||
if tMin < 0 {
|
||||
tMin = 0
|
||||
}
|
||||
for offset > tMin && s > nextEmit && src[offset-1] == src[s-1] && l < maxMatchLength {
|
||||
s--
|
||||
offset--
|
||||
l++
|
||||
}
|
||||
}
|
||||
if debugAsserts {
|
||||
if offset >= s {
|
||||
panic(fmt.Sprintf("offset: %d - s:%d - rep: %d - cur :%d - max: %d", offset, s, rep, e.cur, e.maxMatchOff))
|
||||
}
|
||||
if !bytes.Equal(src[s:s+l], src[offset:offset+l]) {
|
||||
panic(fmt.Sprintf("second match mismatch: %v != %v, first: %08x", src[s:s+4], src[offset:offset+4], first))
|
||||
}
|
||||
}
|
||||
cand := match{offset: offset, s: s, length: l, rep: rep}
|
||||
cand.estBits(bitsPerByte)
|
||||
if m.est >= highScore || cand.est-m.est+(cand.s-m.s)*bitsPerByte>>10 < 0 {
|
||||
*m = cand
|
||||
}
|
||||
}
|
||||
|
||||
best := match{s: s, est: highScore}
|
||||
improve(&best, candidateL.offset-e.cur, s, uint32(cv), -1)
|
||||
improve(&best, candidateL.prev-e.cur, s, uint32(cv), -1)
|
||||
improve(&best, candidateS.offset-e.cur, s, uint32(cv), -1)
|
||||
improve(&best, candidateS.prev-e.cur, s, uint32(cv), -1)
|
||||
|
||||
if canRepeat && best.length < goodEnough {
|
||||
if s == nextEmit {
|
||||
// Check repeats straight after a match.
|
||||
improve(&best, s-offset2, s, uint32(cv), 1|4)
|
||||
improve(&best, s-offset3, s, uint32(cv), 2|4)
|
||||
if offset1 > 1 {
|
||||
improve(&best, s-(offset1-1), s, uint32(cv), 3|4)
|
||||
}
|
||||
}
|
||||
|
||||
// If either no match or a non-repeat match, check at + 1
|
||||
if best.rep <= 0 {
|
||||
cv32 := uint32(cv >> 8)
|
||||
spp := s + 1
|
||||
improve(&best, spp-offset1, spp, cv32, 1)
|
||||
improve(&best, spp-offset2, spp, cv32, 2)
|
||||
improve(&best, spp-offset3, spp, cv32, 3)
|
||||
if best.rep < 0 {
|
||||
cv32 = uint32(cv >> 24)
|
||||
spp += 2
|
||||
improve(&best, spp-offset1, spp, cv32, 1)
|
||||
improve(&best, spp-offset2, spp, cv32, 2)
|
||||
improve(&best, spp-offset3, spp, cv32, 3)
|
||||
}
|
||||
}
|
||||
}
|
||||
// Load next and check...
|
||||
e.longTable[nextHashL] = prevEntry{offset: s + e.cur, prev: candidateL.offset}
|
||||
e.table[nextHashS] = prevEntry{offset: s + e.cur, prev: candidateS.offset}
|
||||
index0 := s + 1
|
||||
|
||||
// Look far ahead, unless we have a really long match already...
|
||||
if best.length < goodEnough {
|
||||
// No match found, move forward on input, no need to check forward...
|
||||
if best.length < 4 {
|
||||
s += 1 + (s-nextEmit)>>(kSearchStrength-1)
|
||||
if s >= sLimit {
|
||||
break encodeLoop
|
||||
}
|
||||
continue
|
||||
}
|
||||
|
||||
candidateS = e.table[hashLen(cv>>8, bestShortTableBits, bestShortLen)]
|
||||
cv = load6432(src, s+1)
|
||||
cv2 := load6432(src, s+2)
|
||||
candidateL = e.longTable[hashLen(cv, bestLongTableBits, bestLongLen)]
|
||||
candidateL2 := e.longTable[hashLen(cv2, bestLongTableBits, bestLongLen)]
|
||||
|
||||
// Short at s+1
|
||||
improve(&best, candidateS.offset-e.cur, s+1, uint32(cv), -1)
|
||||
// Long at s+1, s+2
|
||||
improve(&best, candidateL.offset-e.cur, s+1, uint32(cv), -1)
|
||||
improve(&best, candidateL.prev-e.cur, s+1, uint32(cv), -1)
|
||||
improve(&best, candidateL2.offset-e.cur, s+2, uint32(cv2), -1)
|
||||
improve(&best, candidateL2.prev-e.cur, s+2, uint32(cv2), -1)
|
||||
if false {
|
||||
// Short at s+3.
|
||||
// Too often worse...
|
||||
improve(&best, e.table[hashLen(cv2>>8, bestShortTableBits, bestShortLen)].offset-e.cur, s+3, uint32(cv2>>8), -1)
|
||||
}
|
||||
|
||||
// Start check at a fixed offset to allow for a few mismatches.
|
||||
// For this compression level 2 yields the best results.
|
||||
// We cannot do this if we have already indexed this position.
|
||||
const skipBeginning = 2
|
||||
if best.s > s-skipBeginning {
|
||||
// See if we can find a better match by checking where the current best ends.
|
||||
// Use that offset to see if we can find a better full match.
|
||||
if sAt := best.s + best.length; sAt < sLimit {
|
||||
nextHashL := hashLen(load6432(src, sAt), bestLongTableBits, bestLongLen)
|
||||
candidateEnd := e.longTable[nextHashL]
|
||||
|
||||
if off := candidateEnd.offset - e.cur - best.length + skipBeginning; off >= 0 {
|
||||
improve(&best, off, best.s+skipBeginning, load3232(src, best.s+skipBeginning), -1)
|
||||
if off := candidateEnd.prev - e.cur - best.length + skipBeginning; off >= 0 {
|
||||
improve(&best, off, best.s+skipBeginning, load3232(src, best.s+skipBeginning), -1)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if debugAsserts {
|
||||
if best.offset >= best.s {
|
||||
panic(fmt.Sprintf("best.offset > s: %d >= %d", best.offset, best.s))
|
||||
}
|
||||
if best.s < nextEmit {
|
||||
panic(fmt.Sprintf("s %d < nextEmit %d", best.s, nextEmit))
|
||||
}
|
||||
if best.offset < s-e.maxMatchOff {
|
||||
panic(fmt.Sprintf("best.offset < s-e.maxMatchOff: %d < %d", best.offset, s-e.maxMatchOff))
|
||||
}
|
||||
if !bytes.Equal(src[best.s:best.s+best.length], src[best.offset:best.offset+best.length]) {
|
||||
panic(fmt.Sprintf("match mismatch: %v != %v", src[best.s:best.s+best.length], src[best.offset:best.offset+best.length]))
|
||||
}
|
||||
}
|
||||
|
||||
// We have a match, we can store the forward value
|
||||
s = best.s
|
||||
if best.rep > 0 {
|
||||
var seq seq
|
||||
seq.matchLen = uint32(best.length - zstdMinMatch)
|
||||
addLiterals(&seq, best.s)
|
||||
|
||||
// Repeat. If bit 4 is set, this is a non-lit repeat.
|
||||
seq.offset = uint32(best.rep & 3)
|
||||
if debugSequences {
|
||||
println("repeat sequence", seq, "next s:", best.s, "off:", best.s-best.offset)
|
||||
}
|
||||
blk.sequences = append(blk.sequences, seq)
|
||||
|
||||
// Index old s + 1 -> s - 1
|
||||
s = best.s + best.length
|
||||
nextEmit = s
|
||||
|
||||
// Index skipped...
|
||||
end := s
|
||||
if s > sLimit+4 {
|
||||
end = sLimit + 4
|
||||
}
|
||||
off := index0 + e.cur
|
||||
for index0 < end {
|
||||
cv0 := load6432(src, index0)
|
||||
h0 := hashLen(cv0, bestLongTableBits, bestLongLen)
|
||||
h1 := hashLen(cv0, bestShortTableBits, bestShortLen)
|
||||
e.longTable[h0] = prevEntry{offset: off, prev: e.longTable[h0].offset}
|
||||
e.table[h1] = prevEntry{offset: off, prev: e.table[h1].offset}
|
||||
off++
|
||||
index0++
|
||||
}
|
||||
|
||||
switch best.rep {
|
||||
case 2, 4 | 1:
|
||||
offset1, offset2 = offset2, offset1
|
||||
case 3, 4 | 2:
|
||||
offset1, offset2, offset3 = offset3, offset1, offset2
|
||||
case 4 | 3:
|
||||
offset1, offset2, offset3 = offset1-1, offset1, offset2
|
||||
}
|
||||
if s >= sLimit {
|
||||
if debugEncoder {
|
||||
println("repeat ended", s, best.length)
|
||||
}
|
||||
break encodeLoop
|
||||
}
|
||||
continue
|
||||
}
|
||||
|
||||
// A 4-byte match has been found. Update recent offsets.
|
||||
// We'll later see if more than 4 bytes.
|
||||
t := best.offset
|
||||
offset1, offset2, offset3 = s-t, offset1, offset2
|
||||
|
||||
if debugAsserts && s <= t {
|
||||
panic(fmt.Sprintf("s (%d) <= t (%d)", s, t))
|
||||
}
|
||||
|
||||
if debugAsserts && int(offset1) > len(src) {
|
||||
panic("invalid offset")
|
||||
}
|
||||
|
||||
// Write our sequence
|
||||
var seq seq
|
||||
l := best.length
|
||||
seq.litLen = uint32(s - nextEmit)
|
||||
seq.matchLen = uint32(l - zstdMinMatch)
|
||||
if seq.litLen > 0 {
|
||||
blk.literals = append(blk.literals, src[nextEmit:s]...)
|
||||
}
|
||||
seq.offset = uint32(s-t) + 3
|
||||
s += l
|
||||
if debugSequences {
|
||||
println("sequence", seq, "next s:", s)
|
||||
}
|
||||
blk.sequences = append(blk.sequences, seq)
|
||||
nextEmit = s
|
||||
|
||||
// Index old s + 1 -> s - 1 or sLimit
|
||||
end := s
|
||||
if s > sLimit-4 {
|
||||
end = sLimit - 4
|
||||
}
|
||||
|
||||
off := index0 + e.cur
|
||||
for index0 < end {
|
||||
cv0 := load6432(src, index0)
|
||||
h0 := hashLen(cv0, bestLongTableBits, bestLongLen)
|
||||
h1 := hashLen(cv0, bestShortTableBits, bestShortLen)
|
||||
e.longTable[h0] = prevEntry{offset: off, prev: e.longTable[h0].offset}
|
||||
e.table[h1] = prevEntry{offset: off, prev: e.table[h1].offset}
|
||||
index0++
|
||||
off++
|
||||
}
|
||||
if s >= sLimit {
|
||||
break encodeLoop
|
||||
}
|
||||
}
|
||||
|
||||
if int(nextEmit) < len(src) {
|
||||
blk.literals = append(blk.literals, src[nextEmit:]...)
|
||||
blk.extraLits = len(src) - int(nextEmit)
|
||||
}
|
||||
blk.recentOffsets[0] = uint32(offset1)
|
||||
blk.recentOffsets[1] = uint32(offset2)
|
||||
blk.recentOffsets[2] = uint32(offset3)
|
||||
if debugEncoder {
|
||||
println("returning, recent offsets:", blk.recentOffsets, "extra literals:", blk.extraLits)
|
||||
}
|
||||
}
|
||||
|
||||
// EncodeNoHist will encode a block with no history and no following blocks.
|
||||
// Most notable difference is that src will not be copied for history and
|
||||
// we do not need to check for max match length.
|
||||
func (e *bestFastEncoder) EncodeNoHist(blk *blockEnc, src []byte) {
|
||||
e.ensureHist(len(src))
|
||||
e.Encode(blk, src)
|
||||
}
|
||||
|
||||
// Reset will reset and set a dictionary if not nil
|
||||
func (e *bestFastEncoder) Reset(d *dict, singleBlock bool) {
|
||||
e.resetBase(d, singleBlock)
|
||||
if d == nil {
|
||||
return
|
||||
}
|
||||
// Init or copy dict table
|
||||
if len(e.dictTable) != len(e.table) || d.id != e.lastDictID {
|
||||
if len(e.dictTable) != len(e.table) {
|
||||
e.dictTable = make([]prevEntry, len(e.table))
|
||||
}
|
||||
end := int32(len(d.content)) - 8 + e.maxMatchOff
|
||||
for i := e.maxMatchOff; i < end; i += 4 {
|
||||
const hashLog = bestShortTableBits
|
||||
|
||||
cv := load6432(d.content, i-e.maxMatchOff)
|
||||
nextHash := hashLen(cv, hashLog, bestShortLen) // 0 -> 4
|
||||
nextHash1 := hashLen(cv>>8, hashLog, bestShortLen) // 1 -> 5
|
||||
nextHash2 := hashLen(cv>>16, hashLog, bestShortLen) // 2 -> 6
|
||||
nextHash3 := hashLen(cv>>24, hashLog, bestShortLen) // 3 -> 7
|
||||
e.dictTable[nextHash] = prevEntry{
|
||||
prev: e.dictTable[nextHash].offset,
|
||||
offset: i,
|
||||
}
|
||||
e.dictTable[nextHash1] = prevEntry{
|
||||
prev: e.dictTable[nextHash1].offset,
|
||||
offset: i + 1,
|
||||
}
|
||||
e.dictTable[nextHash2] = prevEntry{
|
||||
prev: e.dictTable[nextHash2].offset,
|
||||
offset: i + 2,
|
||||
}
|
||||
e.dictTable[nextHash3] = prevEntry{
|
||||
prev: e.dictTable[nextHash3].offset,
|
||||
offset: i + 3,
|
||||
}
|
||||
}
|
||||
e.lastDictID = d.id
|
||||
}
|
||||
|
||||
// Init or copy dict table
|
||||
if len(e.dictLongTable) != len(e.longTable) || d.id != e.lastDictID {
|
||||
if len(e.dictLongTable) != len(e.longTable) {
|
||||
e.dictLongTable = make([]prevEntry, len(e.longTable))
|
||||
}
|
||||
if len(d.content) >= 8 {
|
||||
cv := load6432(d.content, 0)
|
||||
h := hashLen(cv, bestLongTableBits, bestLongLen)
|
||||
e.dictLongTable[h] = prevEntry{
|
||||
offset: e.maxMatchOff,
|
||||
prev: e.dictLongTable[h].offset,
|
||||
}
|
||||
|
||||
end := int32(len(d.content)) - 8 + e.maxMatchOff
|
||||
off := 8 // First to read
|
||||
for i := e.maxMatchOff + 1; i < end; i++ {
|
||||
cv = cv>>8 | (uint64(d.content[off]) << 56)
|
||||
h := hashLen(cv, bestLongTableBits, bestLongLen)
|
||||
e.dictLongTable[h] = prevEntry{
|
||||
offset: i,
|
||||
prev: e.dictLongTable[h].offset,
|
||||
}
|
||||
off++
|
||||
}
|
||||
}
|
||||
e.lastDictID = d.id
|
||||
}
|
||||
// Reset table to initial state
|
||||
copy(e.longTable[:], e.dictLongTable)
|
||||
|
||||
e.cur = e.maxMatchOff
|
||||
// Reset table to initial state
|
||||
copy(e.table[:], e.dictTable)
|
||||
}
|
||||
1252
vendor/github.com/klauspost/compress/zstd/enc_better.go
generated
vendored
1252
vendor/github.com/klauspost/compress/zstd/enc_better.go
generated
vendored
File diff suppressed because it is too large
Load Diff
1123
vendor/github.com/klauspost/compress/zstd/enc_dfast.go
generated
vendored
1123
vendor/github.com/klauspost/compress/zstd/enc_dfast.go
generated
vendored
File diff suppressed because it is too large
Load Diff
891
vendor/github.com/klauspost/compress/zstd/enc_fast.go
generated
vendored
891
vendor/github.com/klauspost/compress/zstd/enc_fast.go
generated
vendored
@ -1,891 +0,0 @@
|
||||
// Copyright 2019+ Klaus Post. All rights reserved.
|
||||
// License information can be found in the LICENSE file.
|
||||
// Based on work by Yann Collet, released under BSD License.
|
||||
|
||||
package zstd
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
)
|
||||
|
||||
const (
|
||||
tableBits = 15 // Bits used in the table
|
||||
tableSize = 1 << tableBits // Size of the table
|
||||
tableShardCnt = 1 << (tableBits - dictShardBits) // Number of shards in the table
|
||||
tableShardSize = tableSize / tableShardCnt // Size of an individual shard
|
||||
tableFastHashLen = 6
|
||||
tableMask = tableSize - 1 // Mask for table indices. Redundant, but can eliminate bounds checks.
|
||||
maxMatchLength = 131074
|
||||
)
|
||||
|
||||
type tableEntry struct {
|
||||
val uint32
|
||||
offset int32
|
||||
}
|
||||
|
||||
type fastEncoder struct {
|
||||
fastBase
|
||||
table [tableSize]tableEntry
|
||||
}
|
||||
|
||||
type fastEncoderDict struct {
|
||||
fastEncoder
|
||||
dictTable []tableEntry
|
||||
tableShardDirty [tableShardCnt]bool
|
||||
allDirty bool
|
||||
}
|
||||
|
||||
// Encode mimmics functionality in zstd_fast.c
|
||||
func (e *fastEncoder) Encode(blk *blockEnc, src []byte) {
|
||||
const (
|
||||
inputMargin = 8
|
||||
minNonLiteralBlockSize = 1 + 1 + inputMargin
|
||||
)
|
||||
|
||||
// Protect against e.cur wraparound.
|
||||
for e.cur >= e.bufferReset-int32(len(e.hist)) {
|
||||
if len(e.hist) == 0 {
|
||||
for i := range e.table[:] {
|
||||
e.table[i] = tableEntry{}
|
||||
}
|
||||
e.cur = e.maxMatchOff
|
||||
break
|
||||
}
|
||||
// Shift down everything in the table that isn't already too far away.
|
||||
minOff := e.cur + int32(len(e.hist)) - e.maxMatchOff
|
||||
for i := range e.table[:] {
|
||||
v := e.table[i].offset
|
||||
if v < minOff {
|
||||
v = 0
|
||||
} else {
|
||||
v = v - e.cur + e.maxMatchOff
|
||||
}
|
||||
e.table[i].offset = v
|
||||
}
|
||||
e.cur = e.maxMatchOff
|
||||
break
|
||||
}
|
||||
|
||||
s := e.addBlock(src)
|
||||
blk.size = len(src)
|
||||
if len(src) < minNonLiteralBlockSize {
|
||||
blk.extraLits = len(src)
|
||||
blk.literals = blk.literals[:len(src)]
|
||||
copy(blk.literals, src)
|
||||
return
|
||||
}
|
||||
|
||||
// Override src
|
||||
src = e.hist
|
||||
sLimit := int32(len(src)) - inputMargin
|
||||
// stepSize is the number of bytes to skip on every main loop iteration.
|
||||
// It should be >= 2.
|
||||
const stepSize = 2
|
||||
|
||||
// TEMPLATE
|
||||
const hashLog = tableBits
|
||||
// seems global, but would be nice to tweak.
|
||||
const kSearchStrength = 6
|
||||
|
||||
// nextEmit is where in src the next emitLiteral should start from.
|
||||
nextEmit := s
|
||||
cv := load6432(src, s)
|
||||
|
||||
// Relative offsets
|
||||
offset1 := int32(blk.recentOffsets[0])
|
||||
offset2 := int32(blk.recentOffsets[1])
|
||||
|
||||
addLiterals := func(s *seq, until int32) {
|
||||
if until == nextEmit {
|
||||
return
|
||||
}
|
||||
blk.literals = append(blk.literals, src[nextEmit:until]...)
|
||||
s.litLen = uint32(until - nextEmit)
|
||||
}
|
||||
if debugEncoder {
|
||||
println("recent offsets:", blk.recentOffsets)
|
||||
}
|
||||
|
||||
encodeLoop:
|
||||
for {
|
||||
// t will contain the match offset when we find one.
|
||||
// When existing the search loop, we have already checked 4 bytes.
|
||||
var t int32
|
||||
|
||||
// We will not use repeat offsets across blocks.
|
||||
// By not using them for the first 3 matches
|
||||
canRepeat := len(blk.sequences) > 2
|
||||
|
||||
for {
|
||||
if debugAsserts && canRepeat && offset1 == 0 {
|
||||
panic("offset0 was 0")
|
||||
}
|
||||
|
||||
nextHash := hashLen(cv, hashLog, tableFastHashLen)
|
||||
nextHash2 := hashLen(cv>>8, hashLog, tableFastHashLen)
|
||||
candidate := e.table[nextHash]
|
||||
candidate2 := e.table[nextHash2]
|
||||
repIndex := s - offset1 + 2
|
||||
|
||||
e.table[nextHash] = tableEntry{offset: s + e.cur, val: uint32(cv)}
|
||||
e.table[nextHash2] = tableEntry{offset: s + e.cur + 1, val: uint32(cv >> 8)}
|
||||
|
||||
if canRepeat && repIndex >= 0 && load3232(src, repIndex) == uint32(cv>>16) {
|
||||
// Consider history as well.
|
||||
var seq seq
|
||||
length := 4 + e.matchlen(s+6, repIndex+4, src)
|
||||
seq.matchLen = uint32(length - zstdMinMatch)
|
||||
|
||||
// We might be able to match backwards.
|
||||
// Extend as long as we can.
|
||||
start := s + 2
|
||||
// We end the search early, so we don't risk 0 literals
|
||||
// and have to do special offset treatment.
|
||||
startLimit := nextEmit + 1
|
||||
|
||||
sMin := s - e.maxMatchOff
|
||||
if sMin < 0 {
|
||||
sMin = 0
|
||||
}
|
||||
for repIndex > sMin && start > startLimit && src[repIndex-1] == src[start-1] && seq.matchLen < maxMatchLength-zstdMinMatch {
|
||||
repIndex--
|
||||
start--
|
||||
seq.matchLen++
|
||||
}
|
||||
addLiterals(&seq, start)
|
||||
|
||||
// rep 0
|
||||
seq.offset = 1
|
||||
if debugSequences {
|
||||
println("repeat sequence", seq, "next s:", s)
|
||||
}
|
||||
blk.sequences = append(blk.sequences, seq)
|
||||
s += length + 2
|
||||
nextEmit = s
|
||||
if s >= sLimit {
|
||||
if debugEncoder {
|
||||
println("repeat ended", s, length)
|
||||
|
||||
}
|
||||
break encodeLoop
|
||||
}
|
||||
cv = load6432(src, s)
|
||||
continue
|
||||
}
|
||||
coffset0 := s - (candidate.offset - e.cur)
|
||||
coffset1 := s - (candidate2.offset - e.cur) + 1
|
||||
if coffset0 < e.maxMatchOff && uint32(cv) == candidate.val {
|
||||
// found a regular match
|
||||
t = candidate.offset - e.cur
|
||||
if debugAsserts && s <= t {
|
||||
panic(fmt.Sprintf("s (%d) <= t (%d)", s, t))
|
||||
}
|
||||
if debugAsserts && s-t > e.maxMatchOff {
|
||||
panic("s - t >e.maxMatchOff")
|
||||
}
|
||||
break
|
||||
}
|
||||
|
||||
if coffset1 < e.maxMatchOff && uint32(cv>>8) == candidate2.val {
|
||||
// found a regular match
|
||||
t = candidate2.offset - e.cur
|
||||
s++
|
||||
if debugAsserts && s <= t {
|
||||
panic(fmt.Sprintf("s (%d) <= t (%d)", s, t))
|
||||
}
|
||||
if debugAsserts && s-t > e.maxMatchOff {
|
||||
panic("s - t >e.maxMatchOff")
|
||||
}
|
||||
if debugAsserts && t < 0 {
|
||||
panic("t<0")
|
||||
}
|
||||
break
|
||||
}
|
||||
s += stepSize + ((s - nextEmit) >> (kSearchStrength - 1))
|
||||
if s >= sLimit {
|
||||
break encodeLoop
|
||||
}
|
||||
cv = load6432(src, s)
|
||||
}
|
||||
// A 4-byte match has been found. We'll later see if more than 4 bytes.
|
||||
offset2 = offset1
|
||||
offset1 = s - t
|
||||
|
||||
if debugAsserts && s <= t {
|
||||
panic(fmt.Sprintf("s (%d) <= t (%d)", s, t))
|
||||
}
|
||||
|
||||
if debugAsserts && canRepeat && int(offset1) > len(src) {
|
||||
panic("invalid offset")
|
||||
}
|
||||
|
||||
// Extend the 4-byte match as long as possible.
|
||||
l := e.matchlen(s+4, t+4, src) + 4
|
||||
|
||||
// Extend backwards
|
||||
tMin := s - e.maxMatchOff
|
||||
if tMin < 0 {
|
||||
tMin = 0
|
||||
}
|
||||
for t > tMin && s > nextEmit && src[t-1] == src[s-1] && l < maxMatchLength {
|
||||
s--
|
||||
t--
|
||||
l++
|
||||
}
|
||||
|
||||
// Write our sequence.
|
||||
var seq seq
|
||||
seq.litLen = uint32(s - nextEmit)
|
||||
seq.matchLen = uint32(l - zstdMinMatch)
|
||||
if seq.litLen > 0 {
|
||||
blk.literals = append(blk.literals, src[nextEmit:s]...)
|
||||
}
|
||||
// Don't use repeat offsets
|
||||
seq.offset = uint32(s-t) + 3
|
||||
s += l
|
||||
if debugSequences {
|
||||
println("sequence", seq, "next s:", s)
|
||||
}
|
||||
blk.sequences = append(blk.sequences, seq)
|
||||
nextEmit = s
|
||||
if s >= sLimit {
|
||||
break encodeLoop
|
||||
}
|
||||
cv = load6432(src, s)
|
||||
|
||||
// Check offset 2
|
||||
if o2 := s - offset2; canRepeat && load3232(src, o2) == uint32(cv) {
|
||||
// We have at least 4 byte match.
|
||||
// No need to check backwards. We come straight from a match
|
||||
l := 4 + e.matchlen(s+4, o2+4, src)
|
||||
|
||||
// Store this, since we have it.
|
||||
nextHash := hashLen(cv, hashLog, tableFastHashLen)
|
||||
e.table[nextHash] = tableEntry{offset: s + e.cur, val: uint32(cv)}
|
||||
seq.matchLen = uint32(l) - zstdMinMatch
|
||||
seq.litLen = 0
|
||||
// Since litlen is always 0, this is offset 1.
|
||||
seq.offset = 1
|
||||
s += l
|
||||
nextEmit = s
|
||||
if debugSequences {
|
||||
println("sequence", seq, "next s:", s)
|
||||
}
|
||||
blk.sequences = append(blk.sequences, seq)
|
||||
|
||||
// Swap offset 1 and 2.
|
||||
offset1, offset2 = offset2, offset1
|
||||
if s >= sLimit {
|
||||
break encodeLoop
|
||||
}
|
||||
// Prepare next loop.
|
||||
cv = load6432(src, s)
|
||||
}
|
||||
}
|
||||
|
||||
if int(nextEmit) < len(src) {
|
||||
blk.literals = append(blk.literals, src[nextEmit:]...)
|
||||
blk.extraLits = len(src) - int(nextEmit)
|
||||
}
|
||||
blk.recentOffsets[0] = uint32(offset1)
|
||||
blk.recentOffsets[1] = uint32(offset2)
|
||||
if debugEncoder {
|
||||
println("returning, recent offsets:", blk.recentOffsets, "extra literals:", blk.extraLits)
|
||||
}
|
||||
}
|
||||
|
||||
// EncodeNoHist will encode a block with no history and no following blocks.
|
||||
// Most notable difference is that src will not be copied for history and
|
||||
// we do not need to check for max match length.
|
||||
func (e *fastEncoder) EncodeNoHist(blk *blockEnc, src []byte) {
|
||||
const (
|
||||
inputMargin = 8
|
||||
minNonLiteralBlockSize = 1 + 1 + inputMargin
|
||||
)
|
||||
if debugEncoder {
|
||||
if len(src) > maxCompressedBlockSize {
|
||||
panic("src too big")
|
||||
}
|
||||
}
|
||||
|
||||
// Protect against e.cur wraparound.
|
||||
if e.cur >= e.bufferReset {
|
||||
for i := range e.table[:] {
|
||||
e.table[i] = tableEntry{}
|
||||
}
|
||||
e.cur = e.maxMatchOff
|
||||
}
|
||||
|
||||
s := int32(0)
|
||||
blk.size = len(src)
|
||||
if len(src) < minNonLiteralBlockSize {
|
||||
blk.extraLits = len(src)
|
||||
blk.literals = blk.literals[:len(src)]
|
||||
copy(blk.literals, src)
|
||||
return
|
||||
}
|
||||
|
||||
sLimit := int32(len(src)) - inputMargin
|
||||
// stepSize is the number of bytes to skip on every main loop iteration.
|
||||
// It should be >= 2.
|
||||
const stepSize = 2
|
||||
|
||||
// TEMPLATE
|
||||
const hashLog = tableBits
|
||||
// seems global, but would be nice to tweak.
|
||||
const kSearchStrength = 6
|
||||
|
||||
// nextEmit is where in src the next emitLiteral should start from.
|
||||
nextEmit := s
|
||||
cv := load6432(src, s)
|
||||
|
||||
// Relative offsets
|
||||
offset1 := int32(blk.recentOffsets[0])
|
||||
offset2 := int32(blk.recentOffsets[1])
|
||||
|
||||
addLiterals := func(s *seq, until int32) {
|
||||
if until == nextEmit {
|
||||
return
|
||||
}
|
||||
blk.literals = append(blk.literals, src[nextEmit:until]...)
|
||||
s.litLen = uint32(until - nextEmit)
|
||||
}
|
||||
if debugEncoder {
|
||||
println("recent offsets:", blk.recentOffsets)
|
||||
}
|
||||
|
||||
encodeLoop:
|
||||
for {
|
||||
// t will contain the match offset when we find one.
|
||||
// When existing the search loop, we have already checked 4 bytes.
|
||||
var t int32
|
||||
|
||||
// We will not use repeat offsets across blocks.
|
||||
// By not using them for the first 3 matches
|
||||
|
||||
for {
|
||||
nextHash := hashLen(cv, hashLog, tableFastHashLen)
|
||||
nextHash2 := hashLen(cv>>8, hashLog, tableFastHashLen)
|
||||
candidate := e.table[nextHash]
|
||||
candidate2 := e.table[nextHash2]
|
||||
repIndex := s - offset1 + 2
|
||||
|
||||
e.table[nextHash] = tableEntry{offset: s + e.cur, val: uint32(cv)}
|
||||
e.table[nextHash2] = tableEntry{offset: s + e.cur + 1, val: uint32(cv >> 8)}
|
||||
|
||||
if len(blk.sequences) > 2 && load3232(src, repIndex) == uint32(cv>>16) {
|
||||
// Consider history as well.
|
||||
var seq seq
|
||||
length := 4 + e.matchlen(s+6, repIndex+4, src)
|
||||
|
||||
seq.matchLen = uint32(length - zstdMinMatch)
|
||||
|
||||
// We might be able to match backwards.
|
||||
// Extend as long as we can.
|
||||
start := s + 2
|
||||
// We end the search early, so we don't risk 0 literals
|
||||
// and have to do special offset treatment.
|
||||
startLimit := nextEmit + 1
|
||||
|
||||
sMin := s - e.maxMatchOff
|
||||
if sMin < 0 {
|
||||
sMin = 0
|
||||
}
|
||||
for repIndex > sMin && start > startLimit && src[repIndex-1] == src[start-1] {
|
||||
repIndex--
|
||||
start--
|
||||
seq.matchLen++
|
||||
}
|
||||
addLiterals(&seq, start)
|
||||
|
||||
// rep 0
|
||||
seq.offset = 1
|
||||
if debugSequences {
|
||||
println("repeat sequence", seq, "next s:", s)
|
||||
}
|
||||
blk.sequences = append(blk.sequences, seq)
|
||||
s += length + 2
|
||||
nextEmit = s
|
||||
if s >= sLimit {
|
||||
if debugEncoder {
|
||||
println("repeat ended", s, length)
|
||||
|
||||
}
|
||||
break encodeLoop
|
||||
}
|
||||
cv = load6432(src, s)
|
||||
continue
|
||||
}
|
||||
coffset0 := s - (candidate.offset - e.cur)
|
||||
coffset1 := s - (candidate2.offset - e.cur) + 1
|
||||
if coffset0 < e.maxMatchOff && uint32(cv) == candidate.val {
|
||||
// found a regular match
|
||||
t = candidate.offset - e.cur
|
||||
if debugAsserts && s <= t {
|
||||
panic(fmt.Sprintf("s (%d) <= t (%d)", s, t))
|
||||
}
|
||||
if debugAsserts && s-t > e.maxMatchOff {
|
||||
panic("s - t >e.maxMatchOff")
|
||||
}
|
||||
if debugAsserts && t < 0 {
|
||||
panic(fmt.Sprintf("t (%d) < 0, candidate.offset: %d, e.cur: %d, coffset0: %d, e.maxMatchOff: %d", t, candidate.offset, e.cur, coffset0, e.maxMatchOff))
|
||||
}
|
||||
break
|
||||
}
|
||||
|
||||
if coffset1 < e.maxMatchOff && uint32(cv>>8) == candidate2.val {
|
||||
// found a regular match
|
||||
t = candidate2.offset - e.cur
|
||||
s++
|
||||
if debugAsserts && s <= t {
|
||||
panic(fmt.Sprintf("s (%d) <= t (%d)", s, t))
|
||||
}
|
||||
if debugAsserts && s-t > e.maxMatchOff {
|
||||
panic("s - t >e.maxMatchOff")
|
||||
}
|
||||
if debugAsserts && t < 0 {
|
||||
panic("t<0")
|
||||
}
|
||||
break
|
||||
}
|
||||
s += stepSize + ((s - nextEmit) >> (kSearchStrength - 1))
|
||||
if s >= sLimit {
|
||||
break encodeLoop
|
||||
}
|
||||
cv = load6432(src, s)
|
||||
}
|
||||
// A 4-byte match has been found. We'll later see if more than 4 bytes.
|
||||
offset2 = offset1
|
||||
offset1 = s - t
|
||||
|
||||
if debugAsserts && s <= t {
|
||||
panic(fmt.Sprintf("s (%d) <= t (%d)", s, t))
|
||||
}
|
||||
|
||||
if debugAsserts && t < 0 {
|
||||
panic(fmt.Sprintf("t (%d) < 0 ", t))
|
||||
}
|
||||
// Extend the 4-byte match as long as possible.
|
||||
l := e.matchlen(s+4, t+4, src) + 4
|
||||
|
||||
// Extend backwards
|
||||
tMin := s - e.maxMatchOff
|
||||
if tMin < 0 {
|
||||
tMin = 0
|
||||
}
|
||||
for t > tMin && s > nextEmit && src[t-1] == src[s-1] {
|
||||
s--
|
||||
t--
|
||||
l++
|
||||
}
|
||||
|
||||
// Write our sequence.
|
||||
var seq seq
|
||||
seq.litLen = uint32(s - nextEmit)
|
||||
seq.matchLen = uint32(l - zstdMinMatch)
|
||||
if seq.litLen > 0 {
|
||||
blk.literals = append(blk.literals, src[nextEmit:s]...)
|
||||
}
|
||||
// Don't use repeat offsets
|
||||
seq.offset = uint32(s-t) + 3
|
||||
s += l
|
||||
if debugSequences {
|
||||
println("sequence", seq, "next s:", s)
|
||||
}
|
||||
blk.sequences = append(blk.sequences, seq)
|
||||
nextEmit = s
|
||||
if s >= sLimit {
|
||||
break encodeLoop
|
||||
}
|
||||
cv = load6432(src, s)
|
||||
|
||||
// Check offset 2
|
||||
if o2 := s - offset2; len(blk.sequences) > 2 && load3232(src, o2) == uint32(cv) {
|
||||
// We have at least 4 byte match.
|
||||
// No need to check backwards. We come straight from a match
|
||||
l := 4 + e.matchlen(s+4, o2+4, src)
|
||||
|
||||
// Store this, since we have it.
|
||||
nextHash := hashLen(cv, hashLog, tableFastHashLen)
|
||||
e.table[nextHash] = tableEntry{offset: s + e.cur, val: uint32(cv)}
|
||||
seq.matchLen = uint32(l) - zstdMinMatch
|
||||
seq.litLen = 0
|
||||
// Since litlen is always 0, this is offset 1.
|
||||
seq.offset = 1
|
||||
s += l
|
||||
nextEmit = s
|
||||
if debugSequences {
|
||||
println("sequence", seq, "next s:", s)
|
||||
}
|
||||
blk.sequences = append(blk.sequences, seq)
|
||||
|
||||
// Swap offset 1 and 2.
|
||||
offset1, offset2 = offset2, offset1
|
||||
if s >= sLimit {
|
||||
break encodeLoop
|
||||
}
|
||||
// Prepare next loop.
|
||||
cv = load6432(src, s)
|
||||
}
|
||||
}
|
||||
|
||||
if int(nextEmit) < len(src) {
|
||||
blk.literals = append(blk.literals, src[nextEmit:]...)
|
||||
blk.extraLits = len(src) - int(nextEmit)
|
||||
}
|
||||
if debugEncoder {
|
||||
println("returning, recent offsets:", blk.recentOffsets, "extra literals:", blk.extraLits)
|
||||
}
|
||||
// We do not store history, so we must offset e.cur to avoid false matches for next user.
|
||||
if e.cur < e.bufferReset {
|
||||
e.cur += int32(len(src))
|
||||
}
|
||||
}
|
||||
|
||||
// Encode will encode the content, with a dictionary if initialized for it.
|
||||
func (e *fastEncoderDict) Encode(blk *blockEnc, src []byte) {
|
||||
const (
|
||||
inputMargin = 8
|
||||
minNonLiteralBlockSize = 1 + 1 + inputMargin
|
||||
)
|
||||
if e.allDirty || len(src) > 32<<10 {
|
||||
e.fastEncoder.Encode(blk, src)
|
||||
e.allDirty = true
|
||||
return
|
||||
}
|
||||
// Protect against e.cur wraparound.
|
||||
for e.cur >= e.bufferReset-int32(len(e.hist)) {
|
||||
if len(e.hist) == 0 {
|
||||
e.table = [tableSize]tableEntry{}
|
||||
e.cur = e.maxMatchOff
|
||||
break
|
||||
}
|
||||
// Shift down everything in the table that isn't already too far away.
|
||||
minOff := e.cur + int32(len(e.hist)) - e.maxMatchOff
|
||||
for i := range e.table[:] {
|
||||
v := e.table[i].offset
|
||||
if v < minOff {
|
||||
v = 0
|
||||
} else {
|
||||
v = v - e.cur + e.maxMatchOff
|
||||
}
|
||||
e.table[i].offset = v
|
||||
}
|
||||
e.cur = e.maxMatchOff
|
||||
break
|
||||
}
|
||||
|
||||
s := e.addBlock(src)
|
||||
blk.size = len(src)
|
||||
if len(src) < minNonLiteralBlockSize {
|
||||
blk.extraLits = len(src)
|
||||
blk.literals = blk.literals[:len(src)]
|
||||
copy(blk.literals, src)
|
||||
return
|
||||
}
|
||||
|
||||
// Override src
|
||||
src = e.hist
|
||||
sLimit := int32(len(src)) - inputMargin
|
||||
// stepSize is the number of bytes to skip on every main loop iteration.
|
||||
// It should be >= 2.
|
||||
const stepSize = 2
|
||||
|
||||
// TEMPLATE
|
||||
const hashLog = tableBits
|
||||
// seems global, but would be nice to tweak.
|
||||
const kSearchStrength = 7
|
||||
|
||||
// nextEmit is where in src the next emitLiteral should start from.
|
||||
nextEmit := s
|
||||
cv := load6432(src, s)
|
||||
|
||||
// Relative offsets
|
||||
offset1 := int32(blk.recentOffsets[0])
|
||||
offset2 := int32(blk.recentOffsets[1])
|
||||
|
||||
addLiterals := func(s *seq, until int32) {
|
||||
if until == nextEmit {
|
||||
return
|
||||
}
|
||||
blk.literals = append(blk.literals, src[nextEmit:until]...)
|
||||
s.litLen = uint32(until - nextEmit)
|
||||
}
|
||||
if debugEncoder {
|
||||
println("recent offsets:", blk.recentOffsets)
|
||||
}
|
||||
|
||||
encodeLoop:
|
||||
for {
|
||||
// t will contain the match offset when we find one.
|
||||
// When existing the search loop, we have already checked 4 bytes.
|
||||
var t int32
|
||||
|
||||
// We will not use repeat offsets across blocks.
|
||||
// By not using them for the first 3 matches
|
||||
canRepeat := len(blk.sequences) > 2
|
||||
|
||||
for {
|
||||
if debugAsserts && canRepeat && offset1 == 0 {
|
||||
panic("offset0 was 0")
|
||||
}
|
||||
|
||||
nextHash := hashLen(cv, hashLog, tableFastHashLen)
|
||||
nextHash2 := hashLen(cv>>8, hashLog, tableFastHashLen)
|
||||
candidate := e.table[nextHash]
|
||||
candidate2 := e.table[nextHash2]
|
||||
repIndex := s - offset1 + 2
|
||||
|
||||
e.table[nextHash] = tableEntry{offset: s + e.cur, val: uint32(cv)}
|
||||
e.markShardDirty(nextHash)
|
||||
e.table[nextHash2] = tableEntry{offset: s + e.cur + 1, val: uint32(cv >> 8)}
|
||||
e.markShardDirty(nextHash2)
|
||||
|
||||
if canRepeat && repIndex >= 0 && load3232(src, repIndex) == uint32(cv>>16) {
|
||||
// Consider history as well.
|
||||
var seq seq
|
||||
length := 4 + e.matchlen(s+6, repIndex+4, src)
|
||||
|
||||
seq.matchLen = uint32(length - zstdMinMatch)
|
||||
|
||||
// We might be able to match backwards.
|
||||
// Extend as long as we can.
|
||||
start := s + 2
|
||||
// We end the search early, so we don't risk 0 literals
|
||||
// and have to do special offset treatment.
|
||||
startLimit := nextEmit + 1
|
||||
|
||||
sMin := s - e.maxMatchOff
|
||||
if sMin < 0 {
|
||||
sMin = 0
|
||||
}
|
||||
for repIndex > sMin && start > startLimit && src[repIndex-1] == src[start-1] && seq.matchLen < maxMatchLength-zstdMinMatch {
|
||||
repIndex--
|
||||
start--
|
||||
seq.matchLen++
|
||||
}
|
||||
addLiterals(&seq, start)
|
||||
|
||||
// rep 0
|
||||
seq.offset = 1
|
||||
if debugSequences {
|
||||
println("repeat sequence", seq, "next s:", s)
|
||||
}
|
||||
blk.sequences = append(blk.sequences, seq)
|
||||
s += length + 2
|
||||
nextEmit = s
|
||||
if s >= sLimit {
|
||||
if debugEncoder {
|
||||
println("repeat ended", s, length)
|
||||
|
||||
}
|
||||
break encodeLoop
|
||||
}
|
||||
cv = load6432(src, s)
|
||||
continue
|
||||
}
|
||||
coffset0 := s - (candidate.offset - e.cur)
|
||||
coffset1 := s - (candidate2.offset - e.cur) + 1
|
||||
if coffset0 < e.maxMatchOff && uint32(cv) == candidate.val {
|
||||
// found a regular match
|
||||
t = candidate.offset - e.cur
|
||||
if debugAsserts && s <= t {
|
||||
panic(fmt.Sprintf("s (%d) <= t (%d)", s, t))
|
||||
}
|
||||
if debugAsserts && s-t > e.maxMatchOff {
|
||||
panic("s - t >e.maxMatchOff")
|
||||
}
|
||||
break
|
||||
}
|
||||
|
||||
if coffset1 < e.maxMatchOff && uint32(cv>>8) == candidate2.val {
|
||||
// found a regular match
|
||||
t = candidate2.offset - e.cur
|
||||
s++
|
||||
if debugAsserts && s <= t {
|
||||
panic(fmt.Sprintf("s (%d) <= t (%d)", s, t))
|
||||
}
|
||||
if debugAsserts && s-t > e.maxMatchOff {
|
||||
panic("s - t >e.maxMatchOff")
|
||||
}
|
||||
if debugAsserts && t < 0 {
|
||||
panic("t<0")
|
||||
}
|
||||
break
|
||||
}
|
||||
s += stepSize + ((s - nextEmit) >> (kSearchStrength - 1))
|
||||
if s >= sLimit {
|
||||
break encodeLoop
|
||||
}
|
||||
cv = load6432(src, s)
|
||||
}
|
||||
// A 4-byte match has been found. We'll later see if more than 4 bytes.
|
||||
offset2 = offset1
|
||||
offset1 = s - t
|
||||
|
||||
if debugAsserts && s <= t {
|
||||
panic(fmt.Sprintf("s (%d) <= t (%d)", s, t))
|
||||
}
|
||||
|
||||
if debugAsserts && canRepeat && int(offset1) > len(src) {
|
||||
panic("invalid offset")
|
||||
}
|
||||
|
||||
// Extend the 4-byte match as long as possible.
|
||||
l := e.matchlen(s+4, t+4, src) + 4
|
||||
|
||||
// Extend backwards
|
||||
tMin := s - e.maxMatchOff
|
||||
if tMin < 0 {
|
||||
tMin = 0
|
||||
}
|
||||
for t > tMin && s > nextEmit && src[t-1] == src[s-1] && l < maxMatchLength {
|
||||
s--
|
||||
t--
|
||||
l++
|
||||
}
|
||||
|
||||
// Write our sequence.
|
||||
var seq seq
|
||||
seq.litLen = uint32(s - nextEmit)
|
||||
seq.matchLen = uint32(l - zstdMinMatch)
|
||||
if seq.litLen > 0 {
|
||||
blk.literals = append(blk.literals, src[nextEmit:s]...)
|
||||
}
|
||||
// Don't use repeat offsets
|
||||
seq.offset = uint32(s-t) + 3
|
||||
s += l
|
||||
if debugSequences {
|
||||
println("sequence", seq, "next s:", s)
|
||||
}
|
||||
blk.sequences = append(blk.sequences, seq)
|
||||
nextEmit = s
|
||||
if s >= sLimit {
|
||||
break encodeLoop
|
||||
}
|
||||
cv = load6432(src, s)
|
||||
|
||||
// Check offset 2
|
||||
if o2 := s - offset2; canRepeat && load3232(src, o2) == uint32(cv) {
|
||||
// We have at least 4 byte match.
|
||||
// No need to check backwards. We come straight from a match
|
||||
l := 4 + e.matchlen(s+4, o2+4, src)
|
||||
|
||||
// Store this, since we have it.
|
||||
nextHash := hashLen(cv, hashLog, tableFastHashLen)
|
||||
e.table[nextHash] = tableEntry{offset: s + e.cur, val: uint32(cv)}
|
||||
e.markShardDirty(nextHash)
|
||||
seq.matchLen = uint32(l) - zstdMinMatch
|
||||
seq.litLen = 0
|
||||
// Since litlen is always 0, this is offset 1.
|
||||
seq.offset = 1
|
||||
s += l
|
||||
nextEmit = s
|
||||
if debugSequences {
|
||||
println("sequence", seq, "next s:", s)
|
||||
}
|
||||
blk.sequences = append(blk.sequences, seq)
|
||||
|
||||
// Swap offset 1 and 2.
|
||||
offset1, offset2 = offset2, offset1
|
||||
if s >= sLimit {
|
||||
break encodeLoop
|
||||
}
|
||||
// Prepare next loop.
|
||||
cv = load6432(src, s)
|
||||
}
|
||||
}
|
||||
|
||||
if int(nextEmit) < len(src) {
|
||||
blk.literals = append(blk.literals, src[nextEmit:]...)
|
||||
blk.extraLits = len(src) - int(nextEmit)
|
||||
}
|
||||
blk.recentOffsets[0] = uint32(offset1)
|
||||
blk.recentOffsets[1] = uint32(offset2)
|
||||
if debugEncoder {
|
||||
println("returning, recent offsets:", blk.recentOffsets, "extra literals:", blk.extraLits)
|
||||
}
|
||||
}
|
||||
|
||||
// ResetDict will reset and set a dictionary if not nil
|
||||
func (e *fastEncoder) Reset(d *dict, singleBlock bool) {
|
||||
e.resetBase(d, singleBlock)
|
||||
if d != nil {
|
||||
panic("fastEncoder: Reset with dict")
|
||||
}
|
||||
}
|
||||
|
||||
// ResetDict will reset and set a dictionary if not nil
|
||||
func (e *fastEncoderDict) Reset(d *dict, singleBlock bool) {
|
||||
e.resetBase(d, singleBlock)
|
||||
if d == nil {
|
||||
return
|
||||
}
|
||||
|
||||
// Init or copy dict table
|
||||
if len(e.dictTable) != len(e.table) || d.id != e.lastDictID {
|
||||
if len(e.dictTable) != len(e.table) {
|
||||
e.dictTable = make([]tableEntry, len(e.table))
|
||||
}
|
||||
if true {
|
||||
end := e.maxMatchOff + int32(len(d.content)) - 8
|
||||
for i := e.maxMatchOff; i < end; i += 2 {
|
||||
const hashLog = tableBits
|
||||
|
||||
cv := load6432(d.content, i-e.maxMatchOff)
|
||||
nextHash := hashLen(cv, hashLog, tableFastHashLen) // 0 -> 6
|
||||
nextHash1 := hashLen(cv>>8, hashLog, tableFastHashLen) // 1 -> 7
|
||||
e.dictTable[nextHash] = tableEntry{
|
||||
val: uint32(cv),
|
||||
offset: i,
|
||||
}
|
||||
e.dictTable[nextHash1] = tableEntry{
|
||||
val: uint32(cv >> 8),
|
||||
offset: i + 1,
|
||||
}
|
||||
}
|
||||
}
|
||||
e.lastDictID = d.id
|
||||
e.allDirty = true
|
||||
}
|
||||
|
||||
e.cur = e.maxMatchOff
|
||||
dirtyShardCnt := 0
|
||||
if !e.allDirty {
|
||||
for i := range e.tableShardDirty {
|
||||
if e.tableShardDirty[i] {
|
||||
dirtyShardCnt++
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const shardCnt = tableShardCnt
|
||||
const shardSize = tableShardSize
|
||||
if e.allDirty || dirtyShardCnt > shardCnt*4/6 {
|
||||
//copy(e.table[:], e.dictTable)
|
||||
e.table = *(*[tableSize]tableEntry)(e.dictTable)
|
||||
for i := range e.tableShardDirty {
|
||||
e.tableShardDirty[i] = false
|
||||
}
|
||||
e.allDirty = false
|
||||
return
|
||||
}
|
||||
for i := range e.tableShardDirty {
|
||||
if !e.tableShardDirty[i] {
|
||||
continue
|
||||
}
|
||||
|
||||
//copy(e.table[i*shardSize:(i+1)*shardSize], e.dictTable[i*shardSize:(i+1)*shardSize])
|
||||
*(*[shardSize]tableEntry)(e.table[i*shardSize:]) = *(*[shardSize]tableEntry)(e.dictTable[i*shardSize:])
|
||||
e.tableShardDirty[i] = false
|
||||
}
|
||||
e.allDirty = false
|
||||
}
|
||||
|
||||
func (e *fastEncoderDict) markAllShardsDirty() {
|
||||
e.allDirty = true
|
||||
}
|
||||
|
||||
func (e *fastEncoderDict) markShardDirty(entryNum uint32) {
|
||||
e.tableShardDirty[entryNum/tableShardSize] = true
|
||||
}
|
||||
642
vendor/github.com/klauspost/compress/zstd/encoder.go
generated
vendored
642
vendor/github.com/klauspost/compress/zstd/encoder.go
generated
vendored
@ -1,642 +0,0 @@
|
||||
// Copyright 2019+ Klaus Post. All rights reserved.
|
||||
// License information can be found in the LICENSE file.
|
||||
// Based on work by Yann Collet, released under BSD License.
|
||||
|
||||
package zstd
|
||||
|
||||
import (
|
||||
"crypto/rand"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"math"
|
||||
rdebug "runtime/debug"
|
||||
"sync"
|
||||
|
||||
"github.com/klauspost/compress/zstd/internal/xxhash"
|
||||
)
|
||||
|
||||
// Encoder provides encoding to Zstandard.
|
||||
// An Encoder can be used for either compressing a stream via the
|
||||
// io.WriteCloser interface supported by the Encoder or as multiple independent
|
||||
// tasks via the EncodeAll function.
|
||||
// Smaller encodes are encouraged to use the EncodeAll function.
|
||||
// Use NewWriter to create a new instance.
|
||||
type Encoder struct {
|
||||
o encoderOptions
|
||||
encoders chan encoder
|
||||
state encoderState
|
||||
init sync.Once
|
||||
}
|
||||
|
||||
type encoder interface {
|
||||
Encode(blk *blockEnc, src []byte)
|
||||
EncodeNoHist(blk *blockEnc, src []byte)
|
||||
Block() *blockEnc
|
||||
CRC() *xxhash.Digest
|
||||
AppendCRC([]byte) []byte
|
||||
WindowSize(size int64) int32
|
||||
UseBlock(*blockEnc)
|
||||
Reset(d *dict, singleBlock bool)
|
||||
}
|
||||
|
||||
type encoderState struct {
|
||||
w io.Writer
|
||||
filling []byte
|
||||
current []byte
|
||||
previous []byte
|
||||
encoder encoder
|
||||
writing *blockEnc
|
||||
err error
|
||||
writeErr error
|
||||
nWritten int64
|
||||
nInput int64
|
||||
frameContentSize int64
|
||||
headerWritten bool
|
||||
eofWritten bool
|
||||
fullFrameWritten bool
|
||||
|
||||
// This waitgroup indicates an encode is running.
|
||||
wg sync.WaitGroup
|
||||
// This waitgroup indicates we have a block encoding/writing.
|
||||
wWg sync.WaitGroup
|
||||
}
|
||||
|
||||
// NewWriter will create a new Zstandard encoder.
|
||||
// If the encoder will be used for encoding blocks a nil writer can be used.
|
||||
func NewWriter(w io.Writer, opts ...EOption) (*Encoder, error) {
|
||||
initPredefined()
|
||||
var e Encoder
|
||||
e.o.setDefault()
|
||||
for _, o := range opts {
|
||||
err := o(&e.o)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
if w != nil {
|
||||
e.Reset(w)
|
||||
}
|
||||
return &e, nil
|
||||
}
|
||||
|
||||
func (e *Encoder) initialize() {
|
||||
if e.o.concurrent == 0 {
|
||||
e.o.setDefault()
|
||||
}
|
||||
e.encoders = make(chan encoder, e.o.concurrent)
|
||||
for i := 0; i < e.o.concurrent; i++ {
|
||||
enc := e.o.encoder()
|
||||
e.encoders <- enc
|
||||
}
|
||||
}
|
||||
|
||||
// Reset will re-initialize the writer and new writes will encode to the supplied writer
|
||||
// as a new, independent stream.
|
||||
func (e *Encoder) Reset(w io.Writer) {
|
||||
s := &e.state
|
||||
s.wg.Wait()
|
||||
s.wWg.Wait()
|
||||
if cap(s.filling) == 0 {
|
||||
s.filling = make([]byte, 0, e.o.blockSize)
|
||||
}
|
||||
if e.o.concurrent > 1 {
|
||||
if cap(s.current) == 0 {
|
||||
s.current = make([]byte, 0, e.o.blockSize)
|
||||
}
|
||||
if cap(s.previous) == 0 {
|
||||
s.previous = make([]byte, 0, e.o.blockSize)
|
||||
}
|
||||
s.current = s.current[:0]
|
||||
s.previous = s.previous[:0]
|
||||
if s.writing == nil {
|
||||
s.writing = &blockEnc{lowMem: e.o.lowMem}
|
||||
s.writing.init()
|
||||
}
|
||||
s.writing.initNewEncode()
|
||||
}
|
||||
if s.encoder == nil {
|
||||
s.encoder = e.o.encoder()
|
||||
}
|
||||
s.filling = s.filling[:0]
|
||||
s.encoder.Reset(e.o.dict, false)
|
||||
s.headerWritten = false
|
||||
s.eofWritten = false
|
||||
s.fullFrameWritten = false
|
||||
s.w = w
|
||||
s.err = nil
|
||||
s.nWritten = 0
|
||||
s.nInput = 0
|
||||
s.writeErr = nil
|
||||
s.frameContentSize = 0
|
||||
}
|
||||
|
||||
// ResetContentSize will reset and set a content size for the next stream.
|
||||
// If the bytes written does not match the size given an error will be returned
|
||||
// when calling Close().
|
||||
// This is removed when Reset is called.
|
||||
// Sizes <= 0 results in no content size set.
|
||||
func (e *Encoder) ResetContentSize(w io.Writer, size int64) {
|
||||
e.Reset(w)
|
||||
if size >= 0 {
|
||||
e.state.frameContentSize = size
|
||||
}
|
||||
}
|
||||
|
||||
// Write data to the encoder.
|
||||
// Input data will be buffered and as the buffer fills up
|
||||
// content will be compressed and written to the output.
|
||||
// When done writing, use Close to flush the remaining output
|
||||
// and write CRC if requested.
|
||||
func (e *Encoder) Write(p []byte) (n int, err error) {
|
||||
s := &e.state
|
||||
if s.eofWritten {
|
||||
return 0, ErrEncoderClosed
|
||||
}
|
||||
for len(p) > 0 {
|
||||
if len(p)+len(s.filling) < e.o.blockSize {
|
||||
if e.o.crc {
|
||||
_, _ = s.encoder.CRC().Write(p)
|
||||
}
|
||||
s.filling = append(s.filling, p...)
|
||||
return n + len(p), nil
|
||||
}
|
||||
add := p
|
||||
if len(p)+len(s.filling) > e.o.blockSize {
|
||||
add = add[:e.o.blockSize-len(s.filling)]
|
||||
}
|
||||
if e.o.crc {
|
||||
_, _ = s.encoder.CRC().Write(add)
|
||||
}
|
||||
s.filling = append(s.filling, add...)
|
||||
p = p[len(add):]
|
||||
n += len(add)
|
||||
if len(s.filling) < e.o.blockSize {
|
||||
return n, nil
|
||||
}
|
||||
err := e.nextBlock(false)
|
||||
if err != nil {
|
||||
return n, err
|
||||
}
|
||||
if debugAsserts && len(s.filling) > 0 {
|
||||
panic(len(s.filling))
|
||||
}
|
||||
}
|
||||
return n, nil
|
||||
}
|
||||
|
||||
// nextBlock will synchronize and start compressing input in e.state.filling.
|
||||
// If an error has occurred during encoding it will be returned.
|
||||
func (e *Encoder) nextBlock(final bool) error {
|
||||
s := &e.state
|
||||
// Wait for current block.
|
||||
s.wg.Wait()
|
||||
if s.err != nil {
|
||||
return s.err
|
||||
}
|
||||
if len(s.filling) > e.o.blockSize {
|
||||
return fmt.Errorf("block > maxStoreBlockSize")
|
||||
}
|
||||
if !s.headerWritten {
|
||||
// If we have a single block encode, do a sync compression.
|
||||
if final && len(s.filling) == 0 && !e.o.fullZero {
|
||||
s.headerWritten = true
|
||||
s.fullFrameWritten = true
|
||||
s.eofWritten = true
|
||||
return nil
|
||||
}
|
||||
if final && len(s.filling) > 0 {
|
||||
s.current = e.encodeAll(s.encoder, s.filling, s.current[:0])
|
||||
var n2 int
|
||||
n2, s.err = s.w.Write(s.current)
|
||||
if s.err != nil {
|
||||
return s.err
|
||||
}
|
||||
s.nWritten += int64(n2)
|
||||
s.nInput += int64(len(s.filling))
|
||||
s.current = s.current[:0]
|
||||
s.filling = s.filling[:0]
|
||||
s.headerWritten = true
|
||||
s.fullFrameWritten = true
|
||||
s.eofWritten = true
|
||||
return nil
|
||||
}
|
||||
|
||||
var tmp [maxHeaderSize]byte
|
||||
fh := frameHeader{
|
||||
ContentSize: uint64(s.frameContentSize),
|
||||
WindowSize: uint32(s.encoder.WindowSize(s.frameContentSize)),
|
||||
SingleSegment: false,
|
||||
Checksum: e.o.crc,
|
||||
DictID: e.o.dict.ID(),
|
||||
}
|
||||
|
||||
dst := fh.appendTo(tmp[:0])
|
||||
s.headerWritten = true
|
||||
s.wWg.Wait()
|
||||
var n2 int
|
||||
n2, s.err = s.w.Write(dst)
|
||||
if s.err != nil {
|
||||
return s.err
|
||||
}
|
||||
s.nWritten += int64(n2)
|
||||
}
|
||||
if s.eofWritten {
|
||||
// Ensure we only write it once.
|
||||
final = false
|
||||
}
|
||||
|
||||
if len(s.filling) == 0 {
|
||||
// Final block, but no data.
|
||||
if final {
|
||||
enc := s.encoder
|
||||
blk := enc.Block()
|
||||
blk.reset(nil)
|
||||
blk.last = true
|
||||
blk.encodeRaw(nil)
|
||||
s.wWg.Wait()
|
||||
_, s.err = s.w.Write(blk.output)
|
||||
s.nWritten += int64(len(blk.output))
|
||||
s.eofWritten = true
|
||||
}
|
||||
return s.err
|
||||
}
|
||||
|
||||
// SYNC:
|
||||
if e.o.concurrent == 1 {
|
||||
src := s.filling
|
||||
s.nInput += int64(len(s.filling))
|
||||
if debugEncoder {
|
||||
println("Adding sync block,", len(src), "bytes, final:", final)
|
||||
}
|
||||
enc := s.encoder
|
||||
blk := enc.Block()
|
||||
blk.reset(nil)
|
||||
enc.Encode(blk, src)
|
||||
blk.last = final
|
||||
if final {
|
||||
s.eofWritten = true
|
||||
}
|
||||
|
||||
s.err = blk.encode(src, e.o.noEntropy, !e.o.allLitEntropy)
|
||||
if s.err != nil {
|
||||
return s.err
|
||||
}
|
||||
_, s.err = s.w.Write(blk.output)
|
||||
s.nWritten += int64(len(blk.output))
|
||||
s.filling = s.filling[:0]
|
||||
return s.err
|
||||
}
|
||||
|
||||
// Move blocks forward.
|
||||
s.filling, s.current, s.previous = s.previous[:0], s.filling, s.current
|
||||
s.nInput += int64(len(s.current))
|
||||
s.wg.Add(1)
|
||||
if final {
|
||||
s.eofWritten = true
|
||||
}
|
||||
go func(src []byte) {
|
||||
if debugEncoder {
|
||||
println("Adding block,", len(src), "bytes, final:", final)
|
||||
}
|
||||
defer func() {
|
||||
if r := recover(); r != nil {
|
||||
s.err = fmt.Errorf("panic while encoding: %v", r)
|
||||
rdebug.PrintStack()
|
||||
}
|
||||
s.wg.Done()
|
||||
}()
|
||||
enc := s.encoder
|
||||
blk := enc.Block()
|
||||
enc.Encode(blk, src)
|
||||
blk.last = final
|
||||
// Wait for pending writes.
|
||||
s.wWg.Wait()
|
||||
if s.writeErr != nil {
|
||||
s.err = s.writeErr
|
||||
return
|
||||
}
|
||||
// Transfer encoders from previous write block.
|
||||
blk.swapEncoders(s.writing)
|
||||
// Transfer recent offsets to next.
|
||||
enc.UseBlock(s.writing)
|
||||
s.writing = blk
|
||||
s.wWg.Add(1)
|
||||
go func() {
|
||||
defer func() {
|
||||
if r := recover(); r != nil {
|
||||
s.writeErr = fmt.Errorf("panic while encoding/writing: %v", r)
|
||||
rdebug.PrintStack()
|
||||
}
|
||||
s.wWg.Done()
|
||||
}()
|
||||
s.writeErr = blk.encode(src, e.o.noEntropy, !e.o.allLitEntropy)
|
||||
if s.writeErr != nil {
|
||||
return
|
||||
}
|
||||
_, s.writeErr = s.w.Write(blk.output)
|
||||
s.nWritten += int64(len(blk.output))
|
||||
}()
|
||||
}(s.current)
|
||||
return nil
|
||||
}
|
||||
|
||||
// ReadFrom reads data from r until EOF or error.
|
||||
// The return value n is the number of bytes read.
|
||||
// Any error except io.EOF encountered during the read is also returned.
|
||||
//
|
||||
// The Copy function uses ReaderFrom if available.
|
||||
func (e *Encoder) ReadFrom(r io.Reader) (n int64, err error) {
|
||||
if debugEncoder {
|
||||
println("Using ReadFrom")
|
||||
}
|
||||
|
||||
// Flush any current writes.
|
||||
if len(e.state.filling) > 0 {
|
||||
if err := e.nextBlock(false); err != nil {
|
||||
return 0, err
|
||||
}
|
||||
}
|
||||
e.state.filling = e.state.filling[:e.o.blockSize]
|
||||
src := e.state.filling
|
||||
for {
|
||||
n2, err := r.Read(src)
|
||||
if e.o.crc {
|
||||
_, _ = e.state.encoder.CRC().Write(src[:n2])
|
||||
}
|
||||
// src is now the unfilled part...
|
||||
src = src[n2:]
|
||||
n += int64(n2)
|
||||
switch err {
|
||||
case io.EOF:
|
||||
e.state.filling = e.state.filling[:len(e.state.filling)-len(src)]
|
||||
if debugEncoder {
|
||||
println("ReadFrom: got EOF final block:", len(e.state.filling))
|
||||
}
|
||||
return n, nil
|
||||
case nil:
|
||||
default:
|
||||
if debugEncoder {
|
||||
println("ReadFrom: got error:", err)
|
||||
}
|
||||
e.state.err = err
|
||||
return n, err
|
||||
}
|
||||
if len(src) > 0 {
|
||||
if debugEncoder {
|
||||
println("ReadFrom: got space left in source:", len(src))
|
||||
}
|
||||
continue
|
||||
}
|
||||
err = e.nextBlock(false)
|
||||
if err != nil {
|
||||
return n, err
|
||||
}
|
||||
e.state.filling = e.state.filling[:e.o.blockSize]
|
||||
src = e.state.filling
|
||||
}
|
||||
}
|
||||
|
||||
// Flush will send the currently written data to output
|
||||
// and block until everything has been written.
|
||||
// This should only be used on rare occasions where pushing the currently queued data is critical.
|
||||
func (e *Encoder) Flush() error {
|
||||
s := &e.state
|
||||
if len(s.filling) > 0 {
|
||||
err := e.nextBlock(false)
|
||||
if err != nil {
|
||||
// Ignore Flush after Close.
|
||||
if errors.Is(s.err, ErrEncoderClosed) {
|
||||
return nil
|
||||
}
|
||||
return err
|
||||
}
|
||||
}
|
||||
s.wg.Wait()
|
||||
s.wWg.Wait()
|
||||
if s.err != nil {
|
||||
// Ignore Flush after Close.
|
||||
if errors.Is(s.err, ErrEncoderClosed) {
|
||||
return nil
|
||||
}
|
||||
return s.err
|
||||
}
|
||||
return s.writeErr
|
||||
}
|
||||
|
||||
// Close will flush the final output and close the stream.
|
||||
// The function will block until everything has been written.
|
||||
// The Encoder can still be re-used after calling this.
|
||||
func (e *Encoder) Close() error {
|
||||
s := &e.state
|
||||
if s.encoder == nil {
|
||||
return nil
|
||||
}
|
||||
err := e.nextBlock(true)
|
||||
if err != nil {
|
||||
if errors.Is(s.err, ErrEncoderClosed) {
|
||||
return nil
|
||||
}
|
||||
return err
|
||||
}
|
||||
if s.frameContentSize > 0 {
|
||||
if s.nInput != s.frameContentSize {
|
||||
return fmt.Errorf("frame content size %d given, but %d bytes was written", s.frameContentSize, s.nInput)
|
||||
}
|
||||
}
|
||||
if e.state.fullFrameWritten {
|
||||
return s.err
|
||||
}
|
||||
s.wg.Wait()
|
||||
s.wWg.Wait()
|
||||
|
||||
if s.err != nil {
|
||||
return s.err
|
||||
}
|
||||
if s.writeErr != nil {
|
||||
return s.writeErr
|
||||
}
|
||||
|
||||
// Write CRC
|
||||
if e.o.crc && s.err == nil {
|
||||
// heap alloc.
|
||||
var tmp [4]byte
|
||||
_, s.err = s.w.Write(s.encoder.AppendCRC(tmp[:0]))
|
||||
s.nWritten += 4
|
||||
}
|
||||
|
||||
// Add padding with content from crypto/rand.Reader
|
||||
if s.err == nil && e.o.pad > 0 {
|
||||
add := calcSkippableFrame(s.nWritten, int64(e.o.pad))
|
||||
frame, err := skippableFrame(s.filling[:0], add, rand.Reader)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
_, s.err = s.w.Write(frame)
|
||||
}
|
||||
if s.err == nil {
|
||||
s.err = ErrEncoderClosed
|
||||
return nil
|
||||
}
|
||||
|
||||
return s.err
|
||||
}
|
||||
|
||||
// EncodeAll will encode all input in src and append it to dst.
|
||||
// This function can be called concurrently, but each call will only run on a single goroutine.
|
||||
// If empty input is given, nothing is returned, unless WithZeroFrames is specified.
|
||||
// Encoded blocks can be concatenated and the result will be the combined input stream.
|
||||
// Data compressed with EncodeAll can be decoded with the Decoder,
|
||||
// using either a stream or DecodeAll.
|
||||
func (e *Encoder) EncodeAll(src, dst []byte) []byte {
|
||||
e.init.Do(e.initialize)
|
||||
enc := <-e.encoders
|
||||
defer func() {
|
||||
e.encoders <- enc
|
||||
}()
|
||||
return e.encodeAll(enc, src, dst)
|
||||
}
|
||||
|
||||
func (e *Encoder) encodeAll(enc encoder, src, dst []byte) []byte {
|
||||
if len(src) == 0 {
|
||||
if e.o.fullZero {
|
||||
// Add frame header.
|
||||
fh := frameHeader{
|
||||
ContentSize: 0,
|
||||
WindowSize: MinWindowSize,
|
||||
SingleSegment: true,
|
||||
// Adding a checksum would be a waste of space.
|
||||
Checksum: false,
|
||||
DictID: 0,
|
||||
}
|
||||
dst = fh.appendTo(dst)
|
||||
|
||||
// Write raw block as last one only.
|
||||
var blk blockHeader
|
||||
blk.setSize(0)
|
||||
blk.setType(blockTypeRaw)
|
||||
blk.setLast(true)
|
||||
dst = blk.appendTo(dst)
|
||||
}
|
||||
return dst
|
||||
}
|
||||
|
||||
// Use single segments when above minimum window and below window size.
|
||||
single := len(src) <= e.o.windowSize && len(src) > MinWindowSize
|
||||
if e.o.single != nil {
|
||||
single = *e.o.single
|
||||
}
|
||||
fh := frameHeader{
|
||||
ContentSize: uint64(len(src)),
|
||||
WindowSize: uint32(enc.WindowSize(int64(len(src)))),
|
||||
SingleSegment: single,
|
||||
Checksum: e.o.crc,
|
||||
DictID: e.o.dict.ID(),
|
||||
}
|
||||
|
||||
// If less than 1MB, allocate a buffer up front.
|
||||
if len(dst) == 0 && cap(dst) == 0 && len(src) < 1<<20 && !e.o.lowMem {
|
||||
dst = make([]byte, 0, len(src))
|
||||
}
|
||||
dst = fh.appendTo(dst)
|
||||
|
||||
// If we can do everything in one block, prefer that.
|
||||
if len(src) <= e.o.blockSize {
|
||||
enc.Reset(e.o.dict, true)
|
||||
// Slightly faster with no history and everything in one block.
|
||||
if e.o.crc {
|
||||
_, _ = enc.CRC().Write(src)
|
||||
}
|
||||
blk := enc.Block()
|
||||
blk.last = true
|
||||
if e.o.dict == nil {
|
||||
enc.EncodeNoHist(blk, src)
|
||||
} else {
|
||||
enc.Encode(blk, src)
|
||||
}
|
||||
|
||||
// If we got the exact same number of literals as input,
|
||||
// assume the literals cannot be compressed.
|
||||
oldout := blk.output
|
||||
// Output directly to dst
|
||||
blk.output = dst
|
||||
|
||||
err := blk.encode(src, e.o.noEntropy, !e.o.allLitEntropy)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
dst = blk.output
|
||||
blk.output = oldout
|
||||
} else {
|
||||
enc.Reset(e.o.dict, false)
|
||||
blk := enc.Block()
|
||||
for len(src) > 0 {
|
||||
todo := src
|
||||
if len(todo) > e.o.blockSize {
|
||||
todo = todo[:e.o.blockSize]
|
||||
}
|
||||
src = src[len(todo):]
|
||||
if e.o.crc {
|
||||
_, _ = enc.CRC().Write(todo)
|
||||
}
|
||||
blk.pushOffsets()
|
||||
enc.Encode(blk, todo)
|
||||
if len(src) == 0 {
|
||||
blk.last = true
|
||||
}
|
||||
err := blk.encode(todo, e.o.noEntropy, !e.o.allLitEntropy)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
dst = append(dst, blk.output...)
|
||||
blk.reset(nil)
|
||||
}
|
||||
}
|
||||
if e.o.crc {
|
||||
dst = enc.AppendCRC(dst)
|
||||
}
|
||||
// Add padding with content from crypto/rand.Reader
|
||||
if e.o.pad > 0 {
|
||||
add := calcSkippableFrame(int64(len(dst)), int64(e.o.pad))
|
||||
var err error
|
||||
dst, err = skippableFrame(dst, add, rand.Reader)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
}
|
||||
return dst
|
||||
}
|
||||
|
||||
// MaxEncodedSize returns the expected maximum
|
||||
// size of an encoded block or stream.
|
||||
func (e *Encoder) MaxEncodedSize(size int) int {
|
||||
frameHeader := 4 + 2 // magic + frame header & window descriptor
|
||||
if e.o.dict != nil {
|
||||
frameHeader += 4
|
||||
}
|
||||
// Frame content size:
|
||||
if size < 256 {
|
||||
frameHeader++
|
||||
} else if size < 65536+256 {
|
||||
frameHeader += 2
|
||||
} else if size < math.MaxInt32 {
|
||||
frameHeader += 4
|
||||
} else {
|
||||
frameHeader += 8
|
||||
}
|
||||
// Final crc
|
||||
if e.o.crc {
|
||||
frameHeader += 4
|
||||
}
|
||||
|
||||
// Max overhead is 3 bytes/block.
|
||||
// There cannot be 0 blocks.
|
||||
blocks := (size + e.o.blockSize) / e.o.blockSize
|
||||
|
||||
// Combine, add padding.
|
||||
maxSz := frameHeader + 3*blocks + size
|
||||
if e.o.pad > 1 {
|
||||
maxSz += calcSkippableFrame(int64(maxSz), int64(e.o.pad))
|
||||
}
|
||||
return maxSz
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
x
Reference in New Issue
Block a user