Vendor cleanup

Signed-off-by: Madhu Rajanna <mrajanna@redhat.com>
This commit is contained in:
Madhu Rajanna
2019-01-16 18:11:54 +05:30
parent 661818bd79
commit 0f836c62fa
16816 changed files with 20 additions and 4611100 deletions

View File

@ -1,290 +0,0 @@
// Copyright 2012 The 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 build
import "testing"
// cjk returns an implicit collation element for a CJK rune.
func cjk(r rune) []rawCE {
// A CJK character C is represented in the DUCET as
// [.AAAA.0020.0002.C][.BBBB.0000.0000.C]
// Where AAAA is the most significant 15 bits plus a base value.
// Any base value will work for the test, so we pick the common value of FB40.
const base = 0xFB40
return []rawCE{
{w: []int{base + int(r>>15), defaultSecondary, defaultTertiary, int(r)}},
{w: []int{int(r&0x7FFF) | 0x8000, 0, 0, int(r)}},
}
}
func pCE(p int) []rawCE {
return mkCE([]int{p, defaultSecondary, defaultTertiary, 0}, 0)
}
func pqCE(p, q int) []rawCE {
return mkCE([]int{p, defaultSecondary, defaultTertiary, q}, 0)
}
func ptCE(p, t int) []rawCE {
return mkCE([]int{p, defaultSecondary, t, 0}, 0)
}
func ptcCE(p, t int, ccc uint8) []rawCE {
return mkCE([]int{p, defaultSecondary, t, 0}, ccc)
}
func sCE(s int) []rawCE {
return mkCE([]int{0, s, defaultTertiary, 0}, 0)
}
func stCE(s, t int) []rawCE {
return mkCE([]int{0, s, t, 0}, 0)
}
func scCE(s int, ccc uint8) []rawCE {
return mkCE([]int{0, s, defaultTertiary, 0}, ccc)
}
func mkCE(w []int, ccc uint8) []rawCE {
return []rawCE{rawCE{w, ccc}}
}
// ducetElem is used to define test data that is used to generate a table.
type ducetElem struct {
str string
ces []rawCE
}
func newBuilder(t *testing.T, ducet []ducetElem) *Builder {
b := NewBuilder()
for _, e := range ducet {
ces := [][]int{}
for _, ce := range e.ces {
ces = append(ces, ce.w)
}
if err := b.Add([]rune(e.str), ces, nil); err != nil {
t.Errorf(err.Error())
}
}
b.t = &table{}
b.root.sort()
return b
}
type convertTest struct {
in, out []rawCE
err bool
}
var convLargeTests = []convertTest{
{pCE(0xFB39), pCE(0xFB39), false},
{cjk(0x2F9B2), pqCE(0x3F9B2, 0x2F9B2), false},
{pCE(0xFB40), pCE(0), true},
{append(pCE(0xFB40), pCE(0)[0]), pCE(0), true},
{pCE(0xFFFE), pCE(illegalOffset), false},
{pCE(0xFFFF), pCE(illegalOffset + 1), false},
}
func TestConvertLarge(t *testing.T) {
for i, tt := range convLargeTests {
e := new(entry)
for _, ce := range tt.in {
e.elems = append(e.elems, makeRawCE(ce.w, ce.ccc))
}
elems, err := convertLargeWeights(e.elems)
if tt.err {
if err == nil {
t.Errorf("%d: expected error; none found", i)
}
continue
} else if err != nil {
t.Errorf("%d: unexpected error: %v", i, err)
}
if !equalCEArrays(elems, tt.out) {
t.Errorf("%d: conversion was %x; want %x", i, elems, tt.out)
}
}
}
// Collation element table for simplify tests.
var simplifyTest = []ducetElem{
{"\u0300", sCE(30)}, // grave
{"\u030C", sCE(40)}, // caron
{"A", ptCE(100, 8)},
{"D", ptCE(104, 8)},
{"E", ptCE(105, 8)},
{"I", ptCE(110, 8)},
{"z", ptCE(130, 8)},
{"\u05F2", append(ptCE(200, 4), ptCE(200, 4)[0])},
{"\u05B7", sCE(80)},
{"\u00C0", append(ptCE(100, 8), sCE(30)...)}, // A with grave, can be removed
{"\u00C8", append(ptCE(105, 8), sCE(30)...)}, // E with grave
{"\uFB1F", append(ptCE(200, 4), ptCE(200, 4)[0], sCE(80)[0])}, // eliminated by NFD
{"\u00C8\u0302", ptCE(106, 8)}, // block previous from simplifying
{"\u01C5", append(ptCE(104, 9), ptCE(130, 4)[0], stCE(40, maxTertiary)[0])}, // eliminated by NFKD
// no removal: tertiary value of third element is not maxTertiary
{"\u2162", append(ptCE(110, 9), ptCE(110, 4)[0], ptCE(110, 8)[0])},
}
var genColTests = []ducetElem{
{"\uFA70", pqCE(0x1FA70, 0xFA70)},
{"A\u0300", append(ptCE(100, 8), sCE(30)...)},
{"A\u0300\uFA70", append(ptCE(100, 8), sCE(30)[0], pqCE(0x1FA70, 0xFA70)[0])},
{"A\u0300A\u0300", append(ptCE(100, 8), sCE(30)[0], ptCE(100, 8)[0], sCE(30)[0])},
}
func TestGenColElems(t *testing.T) {
b := newBuilder(t, simplifyTest[:5])
for i, tt := range genColTests {
res := b.root.genColElems(tt.str)
if !equalCEArrays(tt.ces, res) {
t.Errorf("%d: result %X; want %X", i, res, tt.ces)
}
}
}
type strArray []string
func (sa strArray) contains(s string) bool {
for _, e := range sa {
if e == s {
return true
}
}
return false
}
var simplifyRemoved = strArray{"\u00C0", "\uFB1F"}
var simplifyMarked = strArray{"\u01C5"}
func TestSimplify(t *testing.T) {
b := newBuilder(t, simplifyTest)
o := &b.root
simplify(o)
for i, tt := range simplifyTest {
if simplifyRemoved.contains(tt.str) {
continue
}
e := o.find(tt.str)
if e.str != tt.str || !equalCEArrays(e.elems, tt.ces) {
t.Errorf("%d: found element %s -> %X; want %s -> %X", i, e.str, e.elems, tt.str, tt.ces)
break
}
}
var i, k int
for e := o.front(); e != nil; e, _ = e.nextIndexed() {
gold := simplifyMarked.contains(e.str)
if gold {
k++
}
if gold != e.decompose {
t.Errorf("%d: %s has decompose %v; want %v", i, e.str, e.decompose, gold)
}
i++
}
if k != len(simplifyMarked) {
t.Errorf(" an entry that should be marked as decompose was deleted")
}
}
var expandTest = []ducetElem{
{"\u0300", append(scCE(29, 230), scCE(30, 230)...)},
{"\u00C0", append(ptCE(100, 8), scCE(30, 230)...)},
{"\u00C8", append(ptCE(105, 8), scCE(30, 230)...)},
{"\u00C9", append(ptCE(105, 8), scCE(30, 230)...)}, // identical expansion
{"\u05F2", append(ptCE(200, 4), ptCE(200, 4)[0], ptCE(200, 4)[0])},
{"\u01FF", append(ptCE(200, 4), ptcCE(201, 4, 0)[0], scCE(30, 230)[0])},
}
func TestExpand(t *testing.T) {
const (
totalExpansions = 5
totalElements = 2 + 2 + 2 + 3 + 3 + totalExpansions
)
b := newBuilder(t, expandTest)
o := &b.root
b.processExpansions(o)
e := o.front()
for _, tt := range expandTest {
exp := b.t.ExpandElem[e.expansionIndex:]
if int(exp[0]) != len(tt.ces) {
t.Errorf("%U: len(expansion)==%d; want %d", []rune(tt.str)[0], exp[0], len(tt.ces))
}
exp = exp[1:]
for j, w := range tt.ces {
if ce, _ := makeCE(w); exp[j] != ce {
t.Errorf("%U: element %d is %X; want %X", []rune(tt.str)[0], j, exp[j], ce)
}
}
e, _ = e.nextIndexed()
}
// Verify uniquing.
if len(b.t.ExpandElem) != totalElements {
t.Errorf("len(expandElem)==%d; want %d", len(b.t.ExpandElem), totalElements)
}
}
var contractTest = []ducetElem{
{"abc", pCE(102)},
{"abd", pCE(103)},
{"a", pCE(100)},
{"ab", pCE(101)},
{"ac", pCE(104)},
{"bcd", pCE(202)},
{"b", pCE(200)},
{"bc", pCE(201)},
{"bd", pCE(203)},
// shares suffixes with a*
{"Ab", pCE(301)},
{"A", pCE(300)},
{"Ac", pCE(304)},
{"Abc", pCE(302)},
{"Abd", pCE(303)},
// starter to be ignored
{"z", pCE(1000)},
}
func TestContract(t *testing.T) {
const (
totalElements = 5 + 5 + 4
)
b := newBuilder(t, contractTest)
o := &b.root
b.processContractions(o)
indexMap := make(map[int]bool)
handleMap := make(map[rune]*entry)
for e := o.front(); e != nil; e, _ = e.nextIndexed() {
if e.contractionHandle.n > 0 {
handleMap[e.runes[0]] = e
indexMap[e.contractionHandle.index] = true
}
}
// Verify uniquing.
if len(indexMap) != 2 {
t.Errorf("number of tries is %d; want %d", len(indexMap), 2)
}
for _, tt := range contractTest {
e, ok := handleMap[[]rune(tt.str)[0]]
if !ok {
continue
}
str := tt.str[1:]
offset, n := lookup(&b.t.ContractTries, e.contractionHandle, []byte(str))
if len(str) != n {
t.Errorf("%s: bytes consumed==%d; want %d", tt.str, n, len(str))
}
ce := b.t.ContractElem[offset+e.contractionIndex]
if want, _ := makeCE(tt.ces[0]); want != ce {
t.Errorf("%s: element %X; want %X", tt.str, ce, want)
}
}
if len(b.t.ContractElem) != totalElements {
t.Errorf("len(expandElem)==%d; want %d", len(b.t.ContractElem), totalElements)
}
}

View File

@ -1,215 +0,0 @@
// Copyright 2012 The 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 build
import (
"testing"
"golang.org/x/text/internal/colltab"
)
type ceTest struct {
f func(in []int) (uint32, error)
arg []int
val uint32
}
func normalCE(in []int) (ce uint32, err error) {
return makeCE(rawCE{w: in[:3], ccc: uint8(in[3])})
}
func expandCE(in []int) (ce uint32, err error) {
return makeExpandIndex(in[0])
}
func contractCE(in []int) (ce uint32, err error) {
return makeContractIndex(ctHandle{in[0], in[1]}, in[2])
}
func decompCE(in []int) (ce uint32, err error) {
return makeDecompose(in[0], in[1])
}
var ceTests = []ceTest{
{normalCE, []int{0, 0, 0, 0}, 0xA0000000},
{normalCE, []int{0, 0x28, 3, 0}, 0xA0002803},
{normalCE, []int{0, 0x28, 3, 0xFF}, 0xAFF02803},
{normalCE, []int{100, defaultSecondary, 3, 0}, 0x0000C883},
// non-ignorable primary with non-default secondary
{normalCE, []int{100, 0x28, defaultTertiary, 0}, 0x4000C828},
{normalCE, []int{100, defaultSecondary + 8, 3, 0}, 0x0000C983},
{normalCE, []int{100, 0, 3, 0}, 0xFFFF}, // non-ignorable primary with non-supported secondary
{normalCE, []int{100, 1, 3, 0}, 0xFFFF},
{normalCE, []int{1 << maxPrimaryBits, defaultSecondary, 0, 0}, 0xFFFF},
{normalCE, []int{0, 1 << maxSecondaryBits, 0, 0}, 0xFFFF},
{normalCE, []int{100, defaultSecondary, 1 << maxTertiaryBits, 0}, 0xFFFF},
{normalCE, []int{0x123, defaultSecondary, 8, 0xFF}, 0x88FF0123},
{normalCE, []int{0x123, defaultSecondary + 1, 8, 0xFF}, 0xFFFF},
{contractCE, []int{0, 0, 0}, 0xC0000000},
{contractCE, []int{1, 1, 1}, 0xC0010011},
{contractCE, []int{1, (1 << maxNBits) - 1, 1}, 0xC001001F},
{contractCE, []int{(1 << maxTrieIndexBits) - 1, 1, 1}, 0xC001FFF1},
{contractCE, []int{1, 1, (1 << maxContractOffsetBits) - 1}, 0xDFFF0011},
{contractCE, []int{1, (1 << maxNBits), 1}, 0xFFFF},
{contractCE, []int{(1 << maxTrieIndexBits), 1, 1}, 0xFFFF},
{contractCE, []int{1, (1 << maxContractOffsetBits), 1}, 0xFFFF},
{expandCE, []int{0}, 0xE0000000},
{expandCE, []int{5}, 0xE0000005},
{expandCE, []int{(1 << maxExpandIndexBits) - 1}, 0xE000FFFF},
{expandCE, []int{1 << maxExpandIndexBits}, 0xFFFF},
{decompCE, []int{0, 0}, 0xF0000000},
{decompCE, []int{1, 1}, 0xF0000101},
{decompCE, []int{0x1F, 0x1F}, 0xF0001F1F},
{decompCE, []int{256, 0x1F}, 0xFFFF},
{decompCE, []int{0x1F, 256}, 0xFFFF},
}
func TestColElem(t *testing.T) {
for i, tt := range ceTests {
in := make([]int, len(tt.arg))
copy(in, tt.arg)
ce, err := tt.f(in)
if tt.val == 0xFFFF {
if err == nil {
t.Errorf("%d: expected error for args %x", i, tt.arg)
}
continue
}
if err != nil {
t.Errorf("%d: unexpected error: %v", i, err.Error())
}
if ce != tt.val {
t.Errorf("%d: colElem=%X; want %X", i, ce, tt.val)
}
}
}
func mkRawCES(in [][]int) []rawCE {
out := []rawCE{}
for _, w := range in {
out = append(out, rawCE{w: w})
}
return out
}
type weightsTest struct {
a, b [][]int
level colltab.Level
result int
}
var nextWeightTests = []weightsTest{
{
a: [][]int{{100, 20, 5, 0}},
b: [][]int{{101, defaultSecondary, defaultTertiary, 0}},
level: colltab.Primary,
},
{
a: [][]int{{100, 20, 5, 0}},
b: [][]int{{100, 21, defaultTertiary, 0}},
level: colltab.Secondary,
},
{
a: [][]int{{100, 20, 5, 0}},
b: [][]int{{100, 20, 6, 0}},
level: colltab.Tertiary,
},
{
a: [][]int{{100, 20, 5, 0}},
b: [][]int{{100, 20, 5, 0}},
level: colltab.Identity,
},
}
var extra = [][]int{{200, 32, 8, 0}, {0, 32, 8, 0}, {0, 0, 8, 0}, {0, 0, 0, 0}}
func TestNextWeight(t *testing.T) {
for i, tt := range nextWeightTests {
test := func(l colltab.Level, tt weightsTest, a, gold [][]int) {
res := nextWeight(tt.level, mkRawCES(a))
if !equalCEArrays(mkRawCES(gold), res) {
t.Errorf("%d:%d: expected weights %d; found %d", i, l, gold, res)
}
}
test(-1, tt, tt.a, tt.b)
for l := colltab.Primary; l <= colltab.Tertiary; l++ {
if tt.level <= l {
test(l, tt, append(tt.a, extra[l]), tt.b)
} else {
test(l, tt, append(tt.a, extra[l]), append(tt.b, extra[l]))
}
}
}
}
var compareTests = []weightsTest{
{
[][]int{{100, 20, 5, 0}},
[][]int{{100, 20, 5, 0}},
colltab.Identity,
0,
},
{
[][]int{{100, 20, 5, 0}, extra[0]},
[][]int{{100, 20, 5, 1}},
colltab.Primary,
1,
},
{
[][]int{{100, 20, 5, 0}},
[][]int{{101, 20, 5, 0}},
colltab.Primary,
-1,
},
{
[][]int{{101, 20, 5, 0}},
[][]int{{100, 20, 5, 0}},
colltab.Primary,
1,
},
{
[][]int{{100, 0, 0, 0}, {0, 20, 5, 0}},
[][]int{{0, 20, 5, 0}, {100, 0, 0, 0}},
colltab.Identity,
0,
},
{
[][]int{{100, 20, 5, 0}},
[][]int{{100, 21, 5, 0}},
colltab.Secondary,
-1,
},
{
[][]int{{100, 20, 5, 0}},
[][]int{{100, 20, 2, 0}},
colltab.Tertiary,
1,
},
{
[][]int{{100, 20, 5, 1}},
[][]int{{100, 20, 5, 2}},
colltab.Quaternary,
-1,
},
}
func TestCompareWeights(t *testing.T) {
for i, tt := range compareTests {
test := func(tt weightsTest, a, b [][]int) {
res, level := compareWeights(mkRawCES(a), mkRawCES(b))
if res != tt.result {
t.Errorf("%d: expected comparison result %d; found %d", i, tt.result, res)
}
if level != tt.level {
t.Errorf("%d: expected level %d; found %d", i, tt.level, level)
}
}
test(tt, tt.a, tt.b)
test(tt, append(tt.a, extra[0]), append(tt.b, extra[0]))
}
}

View File

@ -1,266 +0,0 @@
// Copyright 2012 The 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 build
import (
"bytes"
"sort"
"testing"
"golang.org/x/text/internal/colltab"
)
var largetosmall = []stridx{
{"a", 5},
{"ab", 4},
{"abc", 3},
{"abcd", 2},
{"abcde", 1},
{"abcdef", 0},
}
var offsetSortTests = [][]stridx{
{
{"bcde", 1},
{"bc", 5},
{"ab", 4},
{"bcd", 3},
{"abcd", 0},
{"abc", 2},
},
largetosmall,
}
func TestOffsetSort(t *testing.T) {
for i, st := range offsetSortTests {
sort.Sort(offsetSort(st))
for j, si := range st {
if j != si.index {
t.Errorf("%d: failed: %v", i, st)
}
}
}
for i, tt := range genStateTests {
// ensure input is well-formed
sort.Sort(offsetSort(tt.in))
for j, si := range tt.in {
if si.index != j+1 {
t.Errorf("%dth sort failed: %v", i, tt.in)
}
}
}
}
var genidxtest1 = []stridx{
{"bcde", 3},
{"bc", 6},
{"ab", 2},
{"bcd", 5},
{"abcd", 0},
{"abc", 1},
{"bcdf", 4},
}
var genidxSortTests = [][]stridx{
genidxtest1,
largetosmall,
}
func TestGenIdxSort(t *testing.T) {
for i, st := range genidxSortTests {
sort.Sort(genidxSort(st))
for j, si := range st {
if j != si.index {
t.Errorf("%dth sort failed %v", i, st)
break
}
}
}
}
var entrySortTests = []colltab.ContractTrieSet{
{
{10, 0, 1, 3},
{99, 0, 1, 0},
{20, 50, 0, 2},
{30, 0, 1, 1},
},
}
func TestEntrySort(t *testing.T) {
for i, et := range entrySortTests {
sort.Sort(entrySort(et))
for j, fe := range et {
if j != int(fe.I) {
t.Errorf("%dth sort failed %v", i, et)
break
}
}
}
}
type GenStateTest struct {
in []stridx
firstBlockLen int
out colltab.ContractTrieSet
}
var genStateTests = []GenStateTest{
{[]stridx{
{"abc", 1},
},
1,
colltab.ContractTrieSet{
{'a', 0, 1, noIndex},
{'b', 0, 1, noIndex},
{'c', 'c', final, 1},
},
},
{[]stridx{
{"abc", 1},
{"abd", 2},
{"abe", 3},
},
1,
colltab.ContractTrieSet{
{'a', 0, 1, noIndex},
{'b', 0, 1, noIndex},
{'c', 'e', final, 1},
},
},
{[]stridx{
{"abc", 1},
{"ab", 2},
{"a", 3},
},
1,
colltab.ContractTrieSet{
{'a', 0, 1, 3},
{'b', 0, 1, 2},
{'c', 'c', final, 1},
},
},
{[]stridx{
{"abc", 1},
{"abd", 2},
{"ab", 3},
{"ac", 4},
{"a", 5},
{"b", 6},
},
2,
colltab.ContractTrieSet{
{'b', 'b', final, 6},
{'a', 0, 2, 5},
{'c', 'c', final, 4},
{'b', 0, 1, 3},
{'c', 'd', final, 1},
},
},
{[]stridx{
{"bcde", 2},
{"bc", 7},
{"ab", 6},
{"bcd", 5},
{"abcd", 1},
{"abc", 4},
{"bcdf", 3},
},
2,
colltab.ContractTrieSet{
{'b', 3, 1, noIndex},
{'a', 0, 1, noIndex},
{'b', 0, 1, 6},
{'c', 0, 1, 4},
{'d', 'd', final, 1},
{'c', 0, 1, 7},
{'d', 0, 1, 5},
{'e', 'f', final, 2},
},
},
}
func TestGenStates(t *testing.T) {
for i, tt := range genStateTests {
si := []stridx{}
for _, e := range tt.in {
si = append(si, e)
}
// ensure input is well-formed
sort.Sort(genidxSort(si))
ct := colltab.ContractTrieSet{}
n, _ := genStates(&ct, si)
if nn := tt.firstBlockLen; nn != n {
t.Errorf("%d: block len %v; want %v", i, n, nn)
}
if lv, lw := len(ct), len(tt.out); lv != lw {
t.Errorf("%d: len %v; want %v", i, lv, lw)
continue
}
for j, fe := range tt.out {
const msg = "%d:%d: value %s=%v; want %v"
if fe.L != ct[j].L {
t.Errorf(msg, i, j, "l", ct[j].L, fe.L)
}
if fe.H != ct[j].H {
t.Errorf(msg, i, j, "h", ct[j].H, fe.H)
}
if fe.N != ct[j].N {
t.Errorf(msg, i, j, "n", ct[j].N, fe.N)
}
if fe.I != ct[j].I {
t.Errorf(msg, i, j, "i", ct[j].I, fe.I)
}
}
}
}
func TestLookupContraction(t *testing.T) {
for i, tt := range genStateTests {
input := []string{}
for _, e := range tt.in {
input = append(input, e.str)
}
cts := colltab.ContractTrieSet{}
h, _ := appendTrie(&cts, input)
for j, si := range tt.in {
str := si.str
for _, s := range []string{str, str + "X"} {
msg := "%d:%d: %s(%s) %v; want %v"
idx, sn := lookup(&cts, h, []byte(s))
if idx != si.index {
t.Errorf(msg, i, j, "index", s, idx, si.index)
}
if sn != len(str) {
t.Errorf(msg, i, j, "sn", s, sn, len(str))
}
}
}
}
}
func TestPrintContractionTrieSet(t *testing.T) {
testdata := colltab.ContractTrieSet(genStateTests[4].out)
buf := &bytes.Buffer{}
print(&testdata, buf, "test")
if contractTrieOutput != buf.String() {
t.Errorf("output differs; found\n%s", buf.String())
println(string(buf.Bytes()))
}
}
const contractTrieOutput = `// testCTEntries: 8 entries, 32 bytes
var testCTEntries = [8]struct{L,H,N,I uint8}{
{0x62, 0x3, 1, 255},
{0x61, 0x0, 1, 255},
{0x62, 0x0, 1, 6},
{0x63, 0x0, 1, 4},
{0x64, 0x64, 0, 1},
{0x63, 0x0, 1, 7},
{0x64, 0x0, 1, 5},
{0x65, 0x66, 0, 2},
}
var testContractTrieSet = colltab.ContractTrieSet( testCTEntries[:] )
`

View File

@ -1,229 +0,0 @@
// Copyright 2012 The 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 build
import (
"strconv"
"testing"
"golang.org/x/text/internal/colltab"
)
type entryTest struct {
f func(in []int) (uint32, error)
arg []int
val uint32
}
// makeList returns a list of entries of length n+2, with n normal
// entries plus a leading and trailing anchor.
func makeList(n int) []*entry {
es := make([]*entry, n+2)
weights := []rawCE{{w: []int{100, 20, 5, 0}}}
for i := range es {
runes := []rune{rune(i)}
es[i] = &entry{
runes: runes,
elems: weights,
}
weights = nextWeight(colltab.Primary, weights)
}
for i := 1; i < len(es); i++ {
es[i-1].next = es[i]
es[i].prev = es[i-1]
_, es[i-1].level = compareWeights(es[i-1].elems, es[i].elems)
}
es[0].exclude = true
es[0].logical = firstAnchor
es[len(es)-1].exclude = true
es[len(es)-1].logical = lastAnchor
return es
}
func TestNextIndexed(t *testing.T) {
const n = 5
es := makeList(n)
for i := int64(0); i < 1<<n; i++ {
mask := strconv.FormatInt(i+(1<<n), 2)
for i, c := range mask {
es[i].exclude = c == '1'
}
e := es[0]
for i, c := range mask {
if c == '0' {
e, _ = e.nextIndexed()
if e != es[i] {
t.Errorf("%d: expected entry %d; found %d", i, es[i].elems, e.elems)
}
}
}
if e, _ = e.nextIndexed(); e != nil {
t.Errorf("%d: expected nil entry; found %d", i, e.elems)
}
}
}
func TestRemove(t *testing.T) {
const n = 5
for i := int64(0); i < 1<<n; i++ {
es := makeList(n)
mask := strconv.FormatInt(i+(1<<n), 2)
for i, c := range mask {
if c == '0' {
es[i].remove()
}
}
e := es[0]
for i, c := range mask {
if c == '1' {
if e != es[i] {
t.Errorf("%d: expected entry %d; found %d", i, es[i].elems, e.elems)
}
e, _ = e.nextIndexed()
}
}
if e != nil {
t.Errorf("%d: expected nil entry; found %d", i, e.elems)
}
}
}
// nextPerm generates the next permutation of the array. The starting
// permutation is assumed to be a list of integers sorted in increasing order.
// It returns false if there are no more permuations left.
func nextPerm(a []int) bool {
i := len(a) - 2
for ; i >= 0; i-- {
if a[i] < a[i+1] {
break
}
}
if i < 0 {
return false
}
for j := len(a) - 1; j >= i; j-- {
if a[j] > a[i] {
a[i], a[j] = a[j], a[i]
break
}
}
for j := i + 1; j < (len(a)+i+1)/2; j++ {
a[j], a[len(a)+i-j] = a[len(a)+i-j], a[j]
}
return true
}
func TestInsertAfter(t *testing.T) {
const n = 5
orig := makeList(n)
perm := make([]int, n)
for i := range perm {
perm[i] = i + 1
}
for ok := true; ok; ok = nextPerm(perm) {
es := makeList(n)
last := es[0]
for _, i := range perm {
last.insertAfter(es[i])
last = es[i]
}
for _, e := range es {
e.elems = es[0].elems
}
e := es[0]
for _, i := range perm {
e, _ = e.nextIndexed()
if e.runes[0] != orig[i].runes[0] {
t.Errorf("%d:%d: expected entry %X; found %X", perm, i, orig[i].runes, e.runes)
break
}
}
}
}
func TestInsertBefore(t *testing.T) {
const n = 5
orig := makeList(n)
perm := make([]int, n)
for i := range perm {
perm[i] = i + 1
}
for ok := true; ok; ok = nextPerm(perm) {
es := makeList(n)
last := es[len(es)-1]
for _, i := range perm {
last.insertBefore(es[i])
last = es[i]
}
for _, e := range es {
e.elems = es[0].elems
}
e := es[0]
for i := n - 1; i >= 0; i-- {
e, _ = e.nextIndexed()
if e.runes[0] != rune(perm[i]) {
t.Errorf("%d:%d: expected entry %X; found %X", perm, i, orig[i].runes, e.runes)
break
}
}
}
}
type entryLessTest struct {
a, b *entry
res bool
}
var (
w1 = []rawCE{{w: []int{100, 20, 5, 5}}}
w2 = []rawCE{{w: []int{101, 20, 5, 5}}}
)
var entryLessTests = []entryLessTest{
{&entry{str: "a", elems: w1},
&entry{str: "a", elems: w1},
false,
},
{&entry{str: "a", elems: w1},
&entry{str: "a", elems: w2},
true,
},
{&entry{str: "a", elems: w1},
&entry{str: "b", elems: w1},
true,
},
{&entry{str: "a", elems: w2},
&entry{str: "a", elems: w1},
false,
},
{&entry{str: "c", elems: w1},
&entry{str: "b", elems: w1},
false,
},
{&entry{str: "a", elems: w1, logical: firstAnchor},
&entry{str: "a", elems: w1},
true,
},
{&entry{str: "a", elems: w1},
&entry{str: "b", elems: w1, logical: firstAnchor},
false,
},
{&entry{str: "b", elems: w1},
&entry{str: "a", elems: w1, logical: lastAnchor},
true,
},
{&entry{str: "a", elems: w1, logical: lastAnchor},
&entry{str: "c", elems: w1},
false,
},
}
func TestEntryLess(t *testing.T) {
for i, tt := range entryLessTests {
if res := entryLess(tt.a, tt.b); res != tt.res {
t.Errorf("%d: was %v; want %v", i, res, tt.res)
}
}
}

View File

@ -1,107 +0,0 @@
// Copyright 2012 The 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 build
import (
"bytes"
"fmt"
"testing"
)
// We take the smallest, largest and an arbitrary value for each
// of the UTF-8 sequence lengths.
var testRunes = []rune{
0x01, 0x0C, 0x7F, // 1-byte sequences
0x80, 0x100, 0x7FF, // 2-byte sequences
0x800, 0x999, 0xFFFF, // 3-byte sequences
0x10000, 0x10101, 0x10FFFF, // 4-byte sequences
0x200, 0x201, 0x202, 0x210, 0x215, // five entries in one sparse block
}
func makeTestTrie(t *testing.T) trie {
n := newNode()
for i, r := range testRunes {
n.insert(r, uint32(i))
}
idx := newTrieBuilder()
idx.addTrie(n)
tr, err := idx.generate()
if err != nil {
t.Errorf(err.Error())
}
return *tr
}
func TestGenerateTrie(t *testing.T) {
testdata := makeTestTrie(t)
buf := &bytes.Buffer{}
testdata.printArrays(buf, "test")
fmt.Fprintf(buf, "var testTrie = ")
testdata.printStruct(buf, &trieHandle{19, 0}, "test")
if output != buf.String() {
t.Error("output differs")
}
}
var output = `// testValues: 832 entries, 3328 bytes
// Block 2 is the null block.
var testValues = [832]uint32 {
// Block 0x0, offset 0x0
0x000c:0x00000001,
// Block 0x1, offset 0x40
0x007f:0x00000002,
// Block 0x2, offset 0x80
// Block 0x3, offset 0xc0
0x00c0:0x00000003,
// Block 0x4, offset 0x100
0x0100:0x00000004,
// Block 0x5, offset 0x140
0x0140:0x0000000c, 0x0141:0x0000000d, 0x0142:0x0000000e,
0x0150:0x0000000f,
0x0155:0x00000010,
// Block 0x6, offset 0x180
0x01bf:0x00000005,
// Block 0x7, offset 0x1c0
0x01c0:0x00000006,
// Block 0x8, offset 0x200
0x0219:0x00000007,
// Block 0x9, offset 0x240
0x027f:0x00000008,
// Block 0xa, offset 0x280
0x0280:0x00000009,
// Block 0xb, offset 0x2c0
0x02c1:0x0000000a,
// Block 0xc, offset 0x300
0x033f:0x0000000b,
}
// testLookup: 640 entries, 1280 bytes
// Block 0 is the null block.
var testLookup = [640]uint16 {
// Block 0x0, offset 0x0
// Block 0x1, offset 0x40
// Block 0x2, offset 0x80
// Block 0x3, offset 0xc0
0x0e0:0x05, 0x0e6:0x06,
// Block 0x4, offset 0x100
0x13f:0x07,
// Block 0x5, offset 0x140
0x140:0x08, 0x144:0x09,
// Block 0x6, offset 0x180
0x190:0x03,
// Block 0x7, offset 0x1c0
0x1ff:0x0a,
// Block 0x8, offset 0x200
0x20f:0x05,
// Block 0x9, offset 0x240
0x242:0x01, 0x244:0x02,
0x248:0x03,
0x25f:0x04,
0x260:0x01,
0x26f:0x02,
0x270:0x04, 0x274:0x06,
}
var testTrie = trie{ testLookup[1216:], testValues[0:], testLookup[:], testValues[:]}`

View File

@ -1,482 +0,0 @@
// Copyright 2012 The 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 collate
import (
"bytes"
"testing"
"golang.org/x/text/internal/colltab"
"golang.org/x/text/language"
)
type weightsTest struct {
opt opts
in, out ColElems
}
type opts struct {
lev int
alt alternateHandling
top int
backwards bool
caseLevel bool
}
// ignore returns an initialized boolean array based on the given Level.
// A negative value means using the default setting of quaternary.
func ignore(level colltab.Level) (ignore [colltab.NumLevels]bool) {
if level < 0 {
level = colltab.Quaternary
}
for i := range ignore {
ignore[i] = level < colltab.Level(i)
}
return ignore
}
func makeCE(w []int) colltab.Elem {
ce, err := colltab.MakeElem(w[0], w[1], w[2], uint8(w[3]))
if err != nil {
panic(err)
}
return ce
}
func (o opts) collator() *Collator {
c := &Collator{
options: options{
ignore: ignore(colltab.Level(o.lev - 1)),
alternate: o.alt,
backwards: o.backwards,
caseLevel: o.caseLevel,
variableTop: uint32(o.top),
},
}
return c
}
const (
maxQ = 0x1FFFFF
)
func wpq(p, q int) Weights {
return W(p, defaults.Secondary, defaults.Tertiary, q)
}
func wsq(s, q int) Weights {
return W(0, s, defaults.Tertiary, q)
}
func wq(q int) Weights {
return W(0, 0, 0, q)
}
var zero = W(0, 0, 0, 0)
var processTests = []weightsTest{
// Shifted
{ // simple sequence of non-variables
opt: opts{alt: altShifted, top: 100},
in: ColElems{W(200), W(300), W(400)},
out: ColElems{wpq(200, maxQ), wpq(300, maxQ), wpq(400, maxQ)},
},
{ // first is a variable
opt: opts{alt: altShifted, top: 250},
in: ColElems{W(200), W(300), W(400)},
out: ColElems{wq(200), wpq(300, maxQ), wpq(400, maxQ)},
},
{ // all but first are variable
opt: opts{alt: altShifted, top: 999},
in: ColElems{W(1000), W(200), W(300), W(400)},
out: ColElems{wpq(1000, maxQ), wq(200), wq(300), wq(400)},
},
{ // first is a modifier
opt: opts{alt: altShifted, top: 999},
in: ColElems{W(0, 10), W(1000)},
out: ColElems{wsq(10, maxQ), wpq(1000, maxQ)},
},
{ // primary ignorables
opt: opts{alt: altShifted, top: 250},
in: ColElems{W(200), W(0, 10), W(300), W(0, 15), W(400)},
out: ColElems{wq(200), zero, wpq(300, maxQ), wsq(15, maxQ), wpq(400, maxQ)},
},
{ // secondary ignorables
opt: opts{alt: altShifted, top: 250},
in: ColElems{W(200), W(0, 0, 10), W(300), W(0, 0, 15), W(400)},
out: ColElems{wq(200), zero, wpq(300, maxQ), W(0, 0, 15, maxQ), wpq(400, maxQ)},
},
{ // tertiary ignorables, no change
opt: opts{alt: altShifted, top: 250},
in: ColElems{W(200), zero, W(300), zero, W(400)},
out: ColElems{wq(200), zero, wpq(300, maxQ), zero, wpq(400, maxQ)},
},
// ShiftTrimmed (same as Shifted)
{ // simple sequence of non-variables
opt: opts{alt: altShiftTrimmed, top: 100},
in: ColElems{W(200), W(300), W(400)},
out: ColElems{wpq(200, maxQ), wpq(300, maxQ), wpq(400, maxQ)},
},
{ // first is a variable
opt: opts{alt: altShiftTrimmed, top: 250},
in: ColElems{W(200), W(300), W(400)},
out: ColElems{wq(200), wpq(300, maxQ), wpq(400, maxQ)},
},
{ // all but first are variable
opt: opts{alt: altShiftTrimmed, top: 999},
in: ColElems{W(1000), W(200), W(300), W(400)},
out: ColElems{wpq(1000, maxQ), wq(200), wq(300), wq(400)},
},
{ // first is a modifier
opt: opts{alt: altShiftTrimmed, top: 999},
in: ColElems{W(0, 10), W(1000)},
out: ColElems{wsq(10, maxQ), wpq(1000, maxQ)},
},
{ // primary ignorables
opt: opts{alt: altShiftTrimmed, top: 250},
in: ColElems{W(200), W(0, 10), W(300), W(0, 15), W(400)},
out: ColElems{wq(200), zero, wpq(300, maxQ), wsq(15, maxQ), wpq(400, maxQ)},
},
{ // secondary ignorables
opt: opts{alt: altShiftTrimmed, top: 250},
in: ColElems{W(200), W(0, 0, 10), W(300), W(0, 0, 15), W(400)},
out: ColElems{wq(200), zero, wpq(300, maxQ), W(0, 0, 15, maxQ), wpq(400, maxQ)},
},
{ // tertiary ignorables, no change
opt: opts{alt: altShiftTrimmed, top: 250},
in: ColElems{W(200), zero, W(300), zero, W(400)},
out: ColElems{wq(200), zero, wpq(300, maxQ), zero, wpq(400, maxQ)},
},
// Blanked
{ // simple sequence of non-variables
opt: opts{alt: altBlanked, top: 100},
in: ColElems{W(200), W(300), W(400)},
out: ColElems{W(200), W(300), W(400)},
},
{ // first is a variable
opt: opts{alt: altBlanked, top: 250},
in: ColElems{W(200), W(300), W(400)},
out: ColElems{zero, W(300), W(400)},
},
{ // all but first are variable
opt: opts{alt: altBlanked, top: 999},
in: ColElems{W(1000), W(200), W(300), W(400)},
out: ColElems{W(1000), zero, zero, zero},
},
{ // first is a modifier
opt: opts{alt: altBlanked, top: 999},
in: ColElems{W(0, 10), W(1000)},
out: ColElems{W(0, 10), W(1000)},
},
{ // primary ignorables
opt: opts{alt: altBlanked, top: 250},
in: ColElems{W(200), W(0, 10), W(300), W(0, 15), W(400)},
out: ColElems{zero, zero, W(300), W(0, 15), W(400)},
},
{ // secondary ignorables
opt: opts{alt: altBlanked, top: 250},
in: ColElems{W(200), W(0, 0, 10), W(300), W(0, 0, 15), W(400)},
out: ColElems{zero, zero, W(300), W(0, 0, 15), W(400)},
},
{ // tertiary ignorables, no change
opt: opts{alt: altBlanked, top: 250},
in: ColElems{W(200), zero, W(300), zero, W(400)},
out: ColElems{zero, zero, W(300), zero, W(400)},
},
// Non-ignorable: input is always equal to output.
{ // all but first are variable
opt: opts{alt: altNonIgnorable, top: 999},
in: ColElems{W(1000), W(200), W(300), W(400)},
out: ColElems{W(1000), W(200), W(300), W(400)},
},
{ // primary ignorables
opt: opts{alt: altNonIgnorable, top: 250},
in: ColElems{W(200), W(0, 10), W(300), W(0, 15), W(400)},
out: ColElems{W(200), W(0, 10), W(300), W(0, 15), W(400)},
},
{ // secondary ignorables
opt: opts{alt: altNonIgnorable, top: 250},
in: ColElems{W(200), W(0, 0, 10), W(300), W(0, 0, 15), W(400)},
out: ColElems{W(200), W(0, 0, 10), W(300), W(0, 0, 15), W(400)},
},
{ // tertiary ignorables, no change
opt: opts{alt: altNonIgnorable, top: 250},
in: ColElems{W(200), zero, W(300), zero, W(400)},
out: ColElems{W(200), zero, W(300), zero, W(400)},
},
}
func TestProcessWeights(t *testing.T) {
for i, tt := range processTests {
in := convertFromWeights(tt.in)
out := convertFromWeights(tt.out)
processWeights(tt.opt.alt, uint32(tt.opt.top), in)
for j, w := range in {
if w != out[j] {
t.Errorf("%d: Weights %d was %v; want %v", i, j, w, out[j])
}
}
}
}
type keyFromElemTest struct {
opt opts
in ColElems
out []byte
}
var defS = byte(defaults.Secondary)
var defT = byte(defaults.Tertiary)
const sep = 0 // separator byte
var keyFromElemTests = []keyFromElemTest{
{ // simple primary and secondary weights.
opts{alt: altShifted},
ColElems{W(0x200), W(0x7FFF), W(0, 0x30), W(0x100)},
[]byte{0x2, 0, 0x7F, 0xFF, 0x1, 0x00, // primary
sep, sep, 0, defS, 0, defS, 0, 0x30, 0, defS, // secondary
sep, sep, defT, defT, defT, defT, // tertiary
sep, 0xFF, 0xFF, 0xFF, 0xFF, // quaternary
},
},
{ // same as first, but with zero element that need to be removed
opts{alt: altShifted},
ColElems{W(0x200), zero, W(0x7FFF), W(0, 0x30), zero, W(0x100)},
[]byte{0x2, 0, 0x7F, 0xFF, 0x1, 0x00, // primary
sep, sep, 0, defS, 0, defS, 0, 0x30, 0, defS, // secondary
sep, sep, defT, defT, defT, defT, // tertiary
sep, 0xFF, 0xFF, 0xFF, 0xFF, // quaternary
},
},
{ // same as first, with large primary values
opts{alt: altShifted},
ColElems{W(0x200), W(0x8000), W(0, 0x30), W(0x12345)},
[]byte{0x2, 0, 0x80, 0x80, 0x00, 0x81, 0x23, 0x45, // primary
sep, sep, 0, defS, 0, defS, 0, 0x30, 0, defS, // secondary
sep, sep, defT, defT, defT, defT, // tertiary
sep, 0xFF, 0xFF, 0xFF, 0xFF, // quaternary
},
},
{ // same as first, but with the secondary level backwards
opts{alt: altShifted, backwards: true},
ColElems{W(0x200), W(0x7FFF), W(0, 0x30), W(0x100)},
[]byte{0x2, 0, 0x7F, 0xFF, 0x1, 0x00, // primary
sep, sep, 0, defS, 0, 0x30, 0, defS, 0, defS, // secondary
sep, sep, defT, defT, defT, defT, // tertiary
sep, 0xFF, 0xFF, 0xFF, 0xFF, // quaternary
},
},
{ // same as first, ignoring quaternary level
opts{alt: altShifted, lev: 3},
ColElems{W(0x200), zero, W(0x7FFF), W(0, 0x30), zero, W(0x100)},
[]byte{0x2, 0, 0x7F, 0xFF, 0x1, 0x00, // primary
sep, sep, 0, defS, 0, defS, 0, 0x30, 0, defS, // secondary
sep, sep, defT, defT, defT, defT, // tertiary
},
},
{ // same as first, ignoring tertiary level
opts{alt: altShifted, lev: 2},
ColElems{W(0x200), zero, W(0x7FFF), W(0, 0x30), zero, W(0x100)},
[]byte{0x2, 0, 0x7F, 0xFF, 0x1, 0x00, // primary
sep, sep, 0, defS, 0, defS, 0, 0x30, 0, defS, // secondary
},
},
{ // same as first, ignoring secondary level
opts{alt: altShifted, lev: 1},
ColElems{W(0x200), zero, W(0x7FFF), W(0, 0x30), zero, W(0x100)},
[]byte{0x2, 0, 0x7F, 0xFF, 0x1, 0x00},
},
{ // simple primary and secondary weights.
opts{alt: altShiftTrimmed, top: 0x250},
ColElems{W(0x300), W(0x200), W(0x7FFF), W(0, 0x30), W(0x800)},
[]byte{0x3, 0, 0x7F, 0xFF, 0x8, 0x00, // primary
sep, sep, 0, defS, 0, defS, 0, 0x30, 0, defS, // secondary
sep, sep, defT, defT, defT, defT, // tertiary
sep, 0xFF, 0x2, 0, // quaternary
},
},
{ // as first, primary with case level enabled
opts{alt: altShifted, lev: 1, caseLevel: true},
ColElems{W(0x200), W(0x7FFF), W(0, 0x30), W(0x100)},
[]byte{0x2, 0, 0x7F, 0xFF, 0x1, 0x00, // primary
sep, sep, // secondary
sep, sep, defT, defT, defT, defT, // tertiary
},
},
}
func TestKeyFromElems(t *testing.T) {
buf := Buffer{}
for i, tt := range keyFromElemTests {
buf.Reset()
in := convertFromWeights(tt.in)
processWeights(tt.opt.alt, uint32(tt.opt.top), in)
tt.opt.collator().keyFromElems(&buf, in)
res := buf.key
if len(res) != len(tt.out) {
t.Errorf("%d: len(ws) was %d; want %d (%X should be %X)", i, len(res), len(tt.out), res, tt.out)
}
n := len(res)
if len(tt.out) < n {
n = len(tt.out)
}
for j, c := range res[:n] {
if c != tt.out[j] {
t.Errorf("%d: byte %d was %X; want %X", i, j, c, tt.out[j])
}
}
}
}
func TestGetColElems(t *testing.T) {
for i, tt := range appendNextTests {
c, err := makeTable(tt.in)
if err != nil {
// error is reported in TestAppendNext
continue
}
// Create one large test per table
str := make([]byte, 0, 4000)
out := ColElems{}
for len(str) < 3000 {
for _, chk := range tt.chk {
str = append(str, chk.in[:chk.n]...)
out = append(out, chk.out...)
}
}
for j, chk := range append(tt.chk, check{string(str), len(str), out}) {
out := convertFromWeights(chk.out)
ce := c.getColElems([]byte(chk.in)[:chk.n])
if len(ce) != len(out) {
t.Errorf("%d:%d: len(ws) was %d; want %d", i, j, len(ce), len(out))
continue
}
cnt := 0
for k, w := range ce {
w, _ = colltab.MakeElem(w.Primary(), w.Secondary(), int(w.Tertiary()), 0)
if w != out[k] {
t.Errorf("%d:%d: Weights %d was %X; want %X", i, j, k, w, out[k])
cnt++
}
if cnt > 10 {
break
}
}
}
}
}
type keyTest struct {
in string
out []byte
}
var keyTests = []keyTest{
{"abc",
[]byte{0, 100, 0, 200, 1, 44, 0, 0, 0, 32, 0, 32, 0, 32, 0, 0, 2, 2, 2, 0, 255, 255, 255},
},
{"a\u0301",
[]byte{0, 102, 0, 0, 0, 32, 0, 0, 2, 0, 255},
},
{"aaaaa",
[]byte{0, 100, 0, 100, 0, 100, 0, 100, 0, 100, 0, 0,
0, 32, 0, 32, 0, 32, 0, 32, 0, 32, 0, 0,
2, 2, 2, 2, 2, 0,
255, 255, 255, 255, 255,
},
},
// Issue 16391: incomplete rune at end of UTF-8 sequence.
{"\xc2", []byte{133, 255, 253, 0, 0, 0, 32, 0, 0, 2, 0, 255}},
{"\xc2a", []byte{133, 255, 253, 0, 100, 0, 0, 0, 32, 0, 32, 0, 0, 2, 2, 0, 255, 255}},
}
func TestKey(t *testing.T) {
c, _ := makeTable(appendNextTests[4].in)
c.alternate = altShifted
c.ignore = ignore(colltab.Quaternary)
buf := Buffer{}
keys1 := [][]byte{}
keys2 := [][]byte{}
for _, tt := range keyTests {
keys1 = append(keys1, c.Key(&buf, []byte(tt.in)))
keys2 = append(keys2, c.KeyFromString(&buf, tt.in))
}
// Separate generation from testing to ensure buffers are not overwritten.
for i, tt := range keyTests {
if !bytes.Equal(keys1[i], tt.out) {
t.Errorf("%d: Key(%q) = %d; want %d", i, tt.in, keys1[i], tt.out)
}
if !bytes.Equal(keys2[i], tt.out) {
t.Errorf("%d: KeyFromString(%q) = %d; want %d", i, tt.in, keys2[i], tt.out)
}
}
}
type compareTest struct {
a, b string
res int // comparison result
}
var compareTests = []compareTest{
{"a\u0301", "a", 1},
{"a\u0301b", "ab", 1},
{"a", "a\u0301", -1},
{"ab", "a\u0301b", -1},
{"bc", "a\u0301c", 1},
{"ab", "aB", -1},
{"a\u0301", "a\u0301", 0},
{"a", "a", 0},
// Only clip prefixes of whole runes.
{"\u302E", "\u302F", 1},
// Don't clip prefixes when last rune of prefix may be part of contraction.
{"a\u035E", "a\u0301\u035F", -1},
{"a\u0301\u035Fb", "a\u0301\u035F", -1},
}
func TestCompare(t *testing.T) {
c, _ := makeTable(appendNextTests[4].in)
for i, tt := range compareTests {
if res := c.Compare([]byte(tt.a), []byte(tt.b)); res != tt.res {
t.Errorf("%d: Compare(%q, %q) == %d; want %d", i, tt.a, tt.b, res, tt.res)
}
if res := c.CompareString(tt.a, tt.b); res != tt.res {
t.Errorf("%d: CompareString(%q, %q) == %d; want %d", i, tt.a, tt.b, res, tt.res)
}
}
}
func TestNumeric(t *testing.T) {
c := New(language.English, Loose, Numeric)
for i, tt := range []struct {
a, b string
want int
}{
{"1", "2", -1},
{"2", "12", -1},
{"", "", -1}, // Fullwidth is sorted as usual.
{"₂", "₁₂", 1}, // Subscript is not sorted as numbers.
{"②", "①②", 1}, // Circled is not sorted as numbers.
{ // Imperial Aramaic, is not sorted as number.
"\U00010859",
"\U00010858\U00010859",
1,
},
{"12", "2", 1},
{"A-1", "A-2", -1},
{"A-2", "A-12", -1},
{"A-12", "A-2", 1},
{"A-0001", "A-1", 0},
} {
if got := c.CompareString(tt.a, tt.b); got != tt.want {
t.Errorf("%d: CompareString(%s, %s) = %d; want %d", i, tt.a, tt.b, got, tt.want)
}
}
}

View File

@ -1,51 +0,0 @@
// Copyright 2012 The 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 collate
// Export for testing.
// TODO: no longer necessary. Remove at some point.
import (
"fmt"
"golang.org/x/text/internal/colltab"
)
const (
defaultSecondary = 0x20
defaultTertiary = 0x2
)
type Weights struct {
Primary, Secondary, Tertiary, Quaternary int
}
func W(ce ...int) Weights {
w := Weights{ce[0], defaultSecondary, defaultTertiary, 0}
if len(ce) > 1 {
w.Secondary = ce[1]
}
if len(ce) > 2 {
w.Tertiary = ce[2]
}
if len(ce) > 3 {
w.Quaternary = ce[3]
}
return w
}
func (w Weights) String() string {
return fmt.Sprintf("[%X.%X.%X.%X]", w.Primary, w.Secondary, w.Tertiary, w.Quaternary)
}
func convertFromWeights(ws []Weights) []colltab.Elem {
out := make([]colltab.Elem, len(ws))
for i, w := range ws {
out[i], _ = colltab.MakeElem(w.Primary, w.Secondary, w.Tertiary, 0)
if out[i] == colltab.Ignore && w.Quaternary > 0 {
out[i] = colltab.MakeQuaternary(w.Quaternary)
}
}
return out
}

View File

@ -1,209 +0,0 @@
// Copyright 2014 The 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 collate
import (
"reflect"
"strings"
"testing"
"golang.org/x/text/internal/colltab"
"golang.org/x/text/language"
)
var (
defaultIgnore = ignore(colltab.Tertiary)
defaultTable = getTable(locales[0])
)
func TestOptions(t *testing.T) {
for i, tt := range []struct {
in []Option
out options
}{
0: {
out: options{
ignore: defaultIgnore,
},
},
1: {
in: []Option{IgnoreDiacritics},
out: options{
ignore: [colltab.NumLevels]bool{false, true, false, true, true},
},
},
2: {
in: []Option{IgnoreCase, IgnoreDiacritics},
out: options{
ignore: ignore(colltab.Primary),
},
},
3: {
in: []Option{ignoreDiacritics, IgnoreWidth},
out: options{
ignore: ignore(colltab.Primary),
caseLevel: true,
},
},
4: {
in: []Option{IgnoreWidth, ignoreDiacritics},
out: options{
ignore: ignore(colltab.Primary),
caseLevel: true,
},
},
5: {
in: []Option{IgnoreCase, IgnoreWidth},
out: options{
ignore: ignore(colltab.Secondary),
},
},
6: {
in: []Option{IgnoreCase, IgnoreWidth, Loose},
out: options{
ignore: ignore(colltab.Primary),
},
},
7: {
in: []Option{Force, IgnoreCase, IgnoreWidth, Loose},
out: options{
ignore: [colltab.NumLevels]bool{false, true, true, true, false},
},
},
8: {
in: []Option{IgnoreDiacritics, IgnoreCase},
out: options{
ignore: ignore(colltab.Primary),
},
},
9: {
in: []Option{Numeric},
out: options{
ignore: defaultIgnore,
numeric: true,
},
},
10: {
in: []Option{OptionsFromTag(language.MustParse("und-u-ks-level1"))},
out: options{
ignore: ignore(colltab.Primary),
},
},
11: {
in: []Option{OptionsFromTag(language.MustParse("und-u-ks-level4"))},
out: options{
ignore: ignore(colltab.Quaternary),
},
},
12: {
in: []Option{OptionsFromTag(language.MustParse("und-u-ks-identic"))},
out: options{},
},
13: {
in: []Option{
OptionsFromTag(language.MustParse("und-u-kn-true-kb-true-kc-true")),
},
out: options{
ignore: defaultIgnore,
caseLevel: true,
backwards: true,
numeric: true,
},
},
14: {
in: []Option{
OptionsFromTag(language.MustParse("und-u-kn-true-kb-true-kc-true")),
OptionsFromTag(language.MustParse("und-u-kn-false-kb-false-kc-false")),
},
out: options{
ignore: defaultIgnore,
},
},
15: {
in: []Option{
OptionsFromTag(language.MustParse("und-u-kn-true-kb-true-kc-true")),
OptionsFromTag(language.MustParse("und-u-kn-foo-kb-foo-kc-foo")),
},
out: options{
ignore: defaultIgnore,
caseLevel: true,
backwards: true,
numeric: true,
},
},
16: { // Normal options take precedence over tag options.
in: []Option{
Numeric, IgnoreCase,
OptionsFromTag(language.MustParse("und-u-kn-false-kc-true")),
},
out: options{
ignore: ignore(colltab.Secondary),
caseLevel: false,
numeric: true,
},
},
17: {
in: []Option{
OptionsFromTag(language.MustParse("und-u-ka-shifted")),
},
out: options{
ignore: defaultIgnore,
alternate: altShifted,
},
},
18: {
in: []Option{
OptionsFromTag(language.MustParse("und-u-ka-blanked")),
},
out: options{
ignore: defaultIgnore,
alternate: altBlanked,
},
},
19: {
in: []Option{
OptionsFromTag(language.MustParse("und-u-ka-posix")),
},
out: options{
ignore: defaultIgnore,
alternate: altShiftTrimmed,
},
},
} {
c := newCollator(defaultTable)
c.t = nil
c.variableTop = 0
c.f = 0
c.setOptions(tt.in)
if !reflect.DeepEqual(c.options, tt.out) {
t.Errorf("%d: got %v; want %v", i, c.options, tt.out)
}
}
}
func TestAlternateSortTypes(t *testing.T) {
testCases := []struct {
lang string
in []string
want []string
}{{
lang: "zh,cmn,zh-Hant-u-co-pinyin,zh-HK-u-co-pinyin,zh-pinyin",
in: []string{"爸爸", "妈妈", "儿子", "女儿"},
want: []string{"爸爸", "儿子", "妈妈", "女儿"},
}, {
lang: "zh-Hant,zh-u-co-stroke,zh-Hant-u-co-stroke",
in: []string{"爸爸", "妈妈", "儿子", "女儿"},
want: []string{"儿子", "女儿", "妈妈", "爸爸"},
}}
for _, tc := range testCases {
for _, tag := range strings.Split(tc.lang, ",") {
got := append([]string{}, tc.in...)
New(language.MustParse(tag)).SortStrings(got)
if !reflect.DeepEqual(got, tc.want) {
t.Errorf("New(%s).SortStrings(%v) = %v; want %v", tag, tc.in, got, tc.want)
}
}
}
}

View File

@ -1,230 +0,0 @@
// Copyright 2012 The 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 collate
import (
"archive/zip"
"bufio"
"bytes"
"flag"
"io"
"io/ioutil"
"log"
"path"
"regexp"
"strconv"
"strings"
"testing"
"unicode/utf8"
"golang.org/x/text/collate/build"
"golang.org/x/text/internal/gen"
"golang.org/x/text/language"
)
var long = flag.Bool("long", false,
"run time-consuming tests, such as tests that fetch data online")
// This regression test runs tests for the test files in CollationTest.zip
// (taken from http://www.unicode.org/Public/UCA/<gen.UnicodeVersion()>/).
//
// The test files have the following form:
// # header
// 0009 0021; # ('\u0009') <CHARACTER TABULATION> [| | | 0201 025E]
// 0009 003F; # ('\u0009') <CHARACTER TABULATION> [| | | 0201 0263]
// 000A 0021; # ('\u000A') <LINE FEED (LF)> [| | | 0202 025E]
// 000A 003F; # ('\u000A') <LINE FEED (LF)> [| | | 0202 0263]
//
// The part before the semicolon is the hex representation of a sequence
// of runes. After the hash mark is a comment. The strings
// represented by rune sequence are in the file in sorted order, as
// defined by the DUCET.
type Test struct {
name string
str [][]byte
comment []string
}
var versionRe = regexp.MustCompile(`# UCA Version: (.*)\n?$`)
var testRe = regexp.MustCompile(`^([\dA-F ]+);.*# (.*)\n?$`)
func TestCollation(t *testing.T) {
if !gen.IsLocal() && !*long {
t.Skip("skipping test to prevent downloading; to run use -long or use -local to specify a local source")
}
t.Skip("must first update to new file format to support test")
for _, test := range loadTestData() {
doTest(t, test)
}
}
func Error(e error) {
if e != nil {
log.Fatal(e)
}
}
// parseUCA parses a Default Unicode Collation Element Table of the format
// specified in http://www.unicode.org/reports/tr10/#File_Format.
// It returns the variable top.
func parseUCA(builder *build.Builder) {
r := gen.OpenUnicodeFile("UCA", "", "allkeys.txt")
defer r.Close()
input := bufio.NewReader(r)
colelem := regexp.MustCompile(`\[([.*])([0-9A-F.]+)\]`)
for i := 1; true; i++ {
l, prefix, err := input.ReadLine()
if err == io.EOF {
break
}
Error(err)
line := string(l)
if prefix {
log.Fatalf("%d: buffer overflow", i)
}
if len(line) == 0 || line[0] == '#' {
continue
}
if line[0] == '@' {
if strings.HasPrefix(line[1:], "version ") {
if v := strings.Split(line[1:], " ")[1]; v != gen.UnicodeVersion() {
log.Fatalf("incompatible version %s; want %s", v, gen.UnicodeVersion())
}
}
} else {
// parse entries
part := strings.Split(line, " ; ")
if len(part) != 2 {
log.Fatalf("%d: production rule without ';': %v", i, line)
}
lhs := []rune{}
for _, v := range strings.Split(part[0], " ") {
if v != "" {
lhs = append(lhs, rune(convHex(i, v)))
}
}
vars := []int{}
rhs := [][]int{}
for i, m := range colelem.FindAllStringSubmatch(part[1], -1) {
if m[1] == "*" {
vars = append(vars, i)
}
elem := []int{}
for _, h := range strings.Split(m[2], ".") {
elem = append(elem, convHex(i, h))
}
rhs = append(rhs, elem)
}
builder.Add(lhs, rhs, vars)
}
}
}
func convHex(line int, s string) int {
r, e := strconv.ParseInt(s, 16, 32)
if e != nil {
log.Fatalf("%d: %v", line, e)
}
return int(r)
}
func loadTestData() []Test {
f := gen.OpenUnicodeFile("UCA", "", "CollationTest.zip")
buffer, err := ioutil.ReadAll(f)
f.Close()
Error(err)
archive, err := zip.NewReader(bytes.NewReader(buffer), int64(len(buffer)))
Error(err)
tests := []Test{}
for _, f := range archive.File {
// Skip the short versions, which are simply duplicates of the long versions.
if strings.Contains(f.Name, "SHORT") || f.FileInfo().IsDir() {
continue
}
ff, err := f.Open()
Error(err)
defer ff.Close()
scanner := bufio.NewScanner(ff)
test := Test{name: path.Base(f.Name)}
for scanner.Scan() {
line := scanner.Text()
if len(line) <= 1 || line[0] == '#' {
if m := versionRe.FindStringSubmatch(line); m != nil {
if m[1] != gen.UnicodeVersion() {
log.Printf("warning:%s: version is %s; want %s", f.Name, m[1], gen.UnicodeVersion())
}
}
continue
}
m := testRe.FindStringSubmatch(line)
if m == nil || len(m) < 3 {
log.Fatalf(`Failed to parse: "%s" result: %#v`, line, m)
}
str := []byte{}
// In the regression test data (unpaired) surrogates are assigned a weight
// corresponding to their code point value. However, utf8.DecodeRune,
// which is used to compute the implicit weight, assigns FFFD to surrogates.
// We therefore skip tests with surrogates. This skips about 35 entries
// per test.
valid := true
for _, split := range strings.Split(m[1], " ") {
r, err := strconv.ParseUint(split, 16, 64)
Error(err)
valid = valid && utf8.ValidRune(rune(r))
str = append(str, string(rune(r))...)
}
if valid {
test.str = append(test.str, str)
test.comment = append(test.comment, m[2])
}
}
if scanner.Err() != nil {
log.Fatal(scanner.Err())
}
tests = append(tests, test)
}
return tests
}
var errorCount int
func runes(b []byte) []rune {
return []rune(string(b))
}
var shifted = language.MustParse("und-u-ka-shifted-ks-level4")
func doTest(t *testing.T, tc Test) {
bld := build.NewBuilder()
parseUCA(bld)
w, err := bld.Build()
Error(err)
var tag language.Tag
if !strings.Contains(tc.name, "NON_IGNOR") {
tag = shifted
}
c := NewFromTable(w, OptionsFromTag(tag))
b := &Buffer{}
prev := tc.str[0]
for i := 1; i < len(tc.str); i++ {
b.Reset()
s := tc.str[i]
ka := c.Key(b, prev)
kb := c.Key(b, s)
if r := bytes.Compare(ka, kb); r == 1 {
t.Errorf("%s:%d: Key(%.4X) < Key(%.4X) (%X < %X) == %d; want -1 or 0", tc.name, i, []rune(string(prev)), []rune(string(s)), ka, kb, r)
prev = s
continue
}
if r := c.Compare(prev, s); r == 1 {
t.Errorf("%s:%d: Compare(%.4X, %.4X) == %d; want -1 or 0", tc.name, i, runes(prev), runes(s), r)
}
if r := c.Compare(s, prev); r == -1 {
t.Errorf("%s:%d: Compare(%.4X, %.4X) == %d; want 1 or 0", tc.name, i, runes(s), runes(prev), r)
}
prev = s
}
}

View File

@ -1,55 +0,0 @@
// Copyright 2013 The 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 collate_test
import (
"fmt"
"testing"
"golang.org/x/text/collate"
"golang.org/x/text/language"
)
func ExampleCollator_Strings() {
c := collate.New(language.Und)
strings := []string{
"ad",
"ab",
"äb",
"ac",
}
c.SortStrings(strings)
fmt.Println(strings)
// Output: [ab äb ac ad]
}
type sorter []string
func (s sorter) Len() int {
return len(s)
}
func (s sorter) Swap(i, j int) {
s[j], s[i] = s[i], s[j]
}
func (s sorter) Bytes(i int) []byte {
return []byte(s[i])
}
func TestSort(t *testing.T) {
c := collate.New(language.English)
strings := []string{
"bcd",
"abc",
"ddd",
}
c.Sort(sorter(strings))
res := fmt.Sprint(strings)
want := "[abc bcd ddd]"
if res != want {
t.Errorf("found %s; want %s", res, want)
}
}

View File

@ -1,291 +0,0 @@
// Copyright 2012 The 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 collate
import (
"testing"
"golang.org/x/text/collate/build"
"golang.org/x/text/internal/colltab"
"golang.org/x/text/unicode/norm"
)
type ColElems []Weights
type input struct {
str string
ces [][]int
}
type check struct {
in string
n int
out ColElems
}
type tableTest struct {
in []input
chk []check
}
func w(ce ...int) Weights {
return W(ce...)
}
var defaults = w(0)
func pt(p, t int) []int {
return []int{p, defaults.Secondary, t}
}
func makeTable(in []input) (*Collator, error) {
b := build.NewBuilder()
for _, r := range in {
if e := b.Add([]rune(r.str), r.ces, nil); e != nil {
panic(e)
}
}
t, err := b.Build()
if err != nil {
return nil, err
}
return NewFromTable(t), nil
}
// modSeq holds a seqeunce of modifiers in increasing order of CCC long enough
// to cause a segment overflow if not handled correctly. The last rune in this
// list has a CCC of 214.
var modSeq = []rune{
0x05B1, 0x05B2, 0x05B3, 0x05B4, 0x05B5, 0x05B6, 0x05B7, 0x05B8, 0x05B9, 0x05BB,
0x05BC, 0x05BD, 0x05BF, 0x05C1, 0x05C2, 0xFB1E, 0x064B, 0x064C, 0x064D, 0x064E,
0x064F, 0x0650, 0x0651, 0x0652, 0x0670, 0x0711, 0x0C55, 0x0C56, 0x0E38, 0x0E48,
0x0EB8, 0x0EC8, 0x0F71, 0x0F72, 0x0F74, 0x0321, 0x1DCE,
}
var mods []input
var modW = func() ColElems {
ws := ColElems{}
for _, r := range modSeq {
rune := norm.NFC.PropertiesString(string(r))
ws = append(ws, w(0, int(rune.CCC())))
mods = append(mods, input{string(r), [][]int{{0, int(rune.CCC())}}})
}
return ws
}()
var appendNextTests = []tableTest{
{ // test getWeights
[]input{
{"a", [][]int{{100}}},
{"b", [][]int{{105}}},
{"c", [][]int{{110}}},
{"ß", [][]int{{120}}},
},
[]check{
{"a", 1, ColElems{w(100)}},
{"b", 1, ColElems{w(105)}},
{"c", 1, ColElems{w(110)}},
{"d", 1, ColElems{w(0x50064)}},
{"ab", 1, ColElems{w(100)}},
{"bc", 1, ColElems{w(105)}},
{"dd", 1, ColElems{w(0x50064)}},
{"ß", 2, ColElems{w(120)}},
},
},
{ // test expansion
[]input{
{"u", [][]int{{100}}},
{"U", [][]int{{100}, {0, 25}}},
{"w", [][]int{{100}, {100}}},
{"W", [][]int{{100}, {0, 25}, {100}, {0, 25}}},
},
[]check{
{"u", 1, ColElems{w(100)}},
{"U", 1, ColElems{w(100), w(0, 25)}},
{"w", 1, ColElems{w(100), w(100)}},
{"W", 1, ColElems{w(100), w(0, 25), w(100), w(0, 25)}},
},
},
{ // test decompose
[]input{
{"D", [][]int{pt(104, 8)}},
{"z", [][]int{pt(130, 8)}},
{"\u030C", [][]int{{0, 40}}}, // Caron
{"\u01C5", [][]int{pt(104, 9), pt(130, 4), {0, 40, 0x1F}}}, // Dž = D+z+caron
},
[]check{
{"\u01C5", 2, ColElems{w(pt(104, 9)...), w(pt(130, 4)...), w(0, 40, 0x1F)}},
},
},
{ // test basic contraction
[]input{
{"a", [][]int{{100}}},
{"ab", [][]int{{101}}},
{"aab", [][]int{{101}, {101}}},
{"abc", [][]int{{102}}},
{"b", [][]int{{200}}},
{"c", [][]int{{300}}},
{"d", [][]int{{400}}},
},
[]check{
{"a", 1, ColElems{w(100)}},
{"aa", 1, ColElems{w(100)}},
{"aac", 1, ColElems{w(100)}},
{"d", 1, ColElems{w(400)}},
{"ab", 2, ColElems{w(101)}},
{"abb", 2, ColElems{w(101)}},
{"aab", 3, ColElems{w(101), w(101)}},
{"aaba", 3, ColElems{w(101), w(101)}},
{"abc", 3, ColElems{w(102)}},
{"abcd", 3, ColElems{w(102)}},
},
},
{ // test discontinuous contraction
append(mods, []input{
// modifiers; secondary weight equals ccc
{"\u0316", [][]int{{0, 220}}},
{"\u0317", [][]int{{0, 220}, {0, 220}}},
{"\u302D", [][]int{{0, 222}}},
{"\u302E", [][]int{{0, 225}}}, // used as starter
{"\u302F", [][]int{{0, 224}}}, // used as starter
{"\u18A9", [][]int{{0, 228}}},
{"\u0300", [][]int{{0, 230}}},
{"\u0301", [][]int{{0, 230}}},
{"\u0315", [][]int{{0, 232}}},
{"\u031A", [][]int{{0, 232}}},
{"\u035C", [][]int{{0, 233}}},
{"\u035F", [][]int{{0, 233}}},
{"\u035D", [][]int{{0, 234}}},
{"\u035E", [][]int{{0, 234}}},
{"\u0345", [][]int{{0, 240}}},
// starters
{"a", [][]int{{100}}},
{"b", [][]int{{200}}},
{"c", [][]int{{300}}},
{"\u03B1", [][]int{{900}}},
{"\x01", [][]int{{0, 0, 0, 0}}},
// contractions
{"a\u0300", [][]int{{101}}},
{"a\u0301", [][]int{{102}}},
{"a\u035E", [][]int{{110}}},
{"a\u035Eb\u035E", [][]int{{115}}},
{"ac\u035Eaca\u035E", [][]int{{116}}},
{"a\u035Db\u035D", [][]int{{117}}},
{"a\u0301\u035Db", [][]int{{120}}},
{"a\u0301\u035F", [][]int{{121}}},
{"a\u0301\u035Fb", [][]int{{119}}},
{"\u03B1\u0345", [][]int{{901}, {902}}},
{"\u302E\u302F", [][]int{{0, 131}, {0, 131}}},
{"\u302F\u18A9", [][]int{{0, 130}}},
}...),
[]check{
{"a\x01\u0300", 1, ColElems{w(100)}},
{"ab", 1, ColElems{w(100)}}, // closing segment
{"a\u0316\u0300b", 5, ColElems{w(101), w(0, 220)}}, // closing segment
{"a\u0316\u0300", 5, ColElems{w(101), w(0, 220)}}, // no closing segment
{"a\u0316\u0300\u035Cb", 5, ColElems{w(101), w(0, 220)}}, // completes before segment end
{"a\u0316\u0300\u035C", 5, ColElems{w(101), w(0, 220)}}, // completes before segment end
{"a\u0316\u0301b", 5, ColElems{w(102), w(0, 220)}}, // closing segment
{"a\u0316\u0301", 5, ColElems{w(102), w(0, 220)}}, // no closing segment
{"a\u0316\u0301\u035Cb", 5, ColElems{w(102), w(0, 220)}}, // completes before segment end
{"a\u0316\u0301\u035C", 5, ColElems{w(102), w(0, 220)}}, // completes before segment end
// match blocked by modifier with same ccc
{"a\u0301\u0315\u031A\u035Fb", 3, ColElems{w(102)}},
// multiple gaps
{"a\u0301\u035Db", 6, ColElems{w(120)}},
{"a\u0301\u035F", 5, ColElems{w(121)}},
{"a\u0301\u035Fb", 6, ColElems{w(119)}},
{"a\u0316\u0301\u035F", 7, ColElems{w(121), w(0, 220)}},
{"a\u0301\u0315\u035Fb", 7, ColElems{w(121), w(0, 232)}},
{"a\u0316\u0301\u0315\u035Db", 5, ColElems{w(102), w(0, 220)}},
{"a\u0316\u0301\u0315\u035F", 9, ColElems{w(121), w(0, 220), w(0, 232)}},
{"a\u0316\u0301\u0315\u035Fb", 9, ColElems{w(121), w(0, 220), w(0, 232)}},
{"a\u0316\u0301\u0315\u035F\u035D", 9, ColElems{w(121), w(0, 220), w(0, 232)}},
{"a\u0316\u0301\u0315\u035F\u035Db", 9, ColElems{w(121), w(0, 220), w(0, 232)}},
// handling of segment overflow
{ // just fits within segment
"a" + string(modSeq[:30]) + "\u0301",
3 + len(string(modSeq[:30])),
append(ColElems{w(102)}, modW[:30]...),
},
{"a" + string(modSeq[:31]) + "\u0301", 1, ColElems{w(100)}}, // overflow
{"a" + string(modSeq) + "\u0301", 1, ColElems{w(100)}},
{ // just fits within segment with two interstitial runes
"a" + string(modSeq[:28]) + "\u0301\u0315\u035F",
7 + len(string(modSeq[:28])),
append(append(ColElems{w(121)}, modW[:28]...), w(0, 232)),
},
{ // second half does not fit within segment
"a" + string(modSeq[:29]) + "\u0301\u0315\u035F",
3 + len(string(modSeq[:29])),
append(ColElems{w(102)}, modW[:29]...),
},
// discontinuity can only occur in last normalization segment
{"a\u035Eb\u035E", 6, ColElems{w(115)}},
{"a\u0316\u035Eb\u035E", 5, ColElems{w(110), w(0, 220)}},
{"a\u035Db\u035D", 6, ColElems{w(117)}},
{"a\u0316\u035Db\u035D", 1, ColElems{w(100)}},
{"a\u035Eb\u0316\u035E", 8, ColElems{w(115), w(0, 220)}},
{"a\u035Db\u0316\u035D", 8, ColElems{w(117), w(0, 220)}},
{"ac\u035Eaca\u035E", 9, ColElems{w(116)}},
{"a\u0316c\u035Eaca\u035E", 1, ColElems{w(100)}},
{"ac\u035Eac\u0316a\u035E", 1, ColElems{w(100)}},
// expanding contraction
{"\u03B1\u0345", 4, ColElems{w(901), w(902)}},
// Theoretical possibilities
// contraction within a gap
{"a\u302F\u18A9\u0301", 9, ColElems{w(102), w(0, 130)}},
// expansion within a gap
{"a\u0317\u0301", 5, ColElems{w(102), w(0, 220), w(0, 220)}},
// repeating CCC blocks last modifier
{"a\u302E\u302F\u0301", 1, ColElems{w(100)}},
// The trailing combining characters (with lower CCC) should block the first one.
// TODO: make the following pass.
// {"a\u035E\u0316\u0316", 1, ColElems{w(100)}},
{"a\u035F\u035Eb", 5, ColElems{w(110), w(0, 233)}},
// Last combiner should match after normalization.
// TODO: make the following pass.
// {"a\u035D\u0301", 3, ColElems{w(102), w(0, 234)}},
// The first combiner is blocking the second one as they have the same CCC.
{"a\u035D\u035Eb", 1, ColElems{w(100)}},
},
},
}
func TestAppendNext(t *testing.T) {
for i, tt := range appendNextTests {
c, err := makeTable(tt.in)
if err != nil {
t.Errorf("%d: error creating table: %v", i, err)
continue
}
for j, chk := range tt.chk {
ws, n := c.t.AppendNext(nil, []byte(chk.in))
if n != chk.n {
t.Errorf("%d:%d: bytes consumed was %d; want %d", i, j, n, chk.n)
}
out := convertFromWeights(chk.out)
if len(ws) != len(out) {
t.Errorf("%d:%d: len(ws) was %d; want %d (%X vs %X)\n%X", i, j, len(ws), len(out), ws, out, chk.in)
continue
}
for k, w := range ws {
w, _ = colltab.MakeElem(w.Primary(), w.Secondary(), int(w.Tertiary()), 0)
if w != out[k] {
t.Errorf("%d:%d: Weights %d was %X; want %X", i, j, k, w, out[k])
}
}
}
}
}

View File

@ -1,7 +0,0 @@
# Copyright 2012 The 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.
chars:
go run ../../maketables.go -tables=chars -package=main > chars.go
gofmt -w -s chars.go

File diff suppressed because one or more lines are too long

View File

@ -1,97 +0,0 @@
// Copyright 2012 The 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 main
import (
"log"
"unicode/utf16"
"golang.org/x/text/collate"
"golang.org/x/text/language"
)
// Input holds an input string in both UTF-8 and UTF-16 format.
type Input struct {
index int // used for restoring to original random order
UTF8 []byte
UTF16 []uint16
key []byte // used for sorting
}
func (i Input) String() string {
return string(i.UTF8)
}
func makeInput(s8 []byte, s16 []uint16) Input {
return Input{UTF8: s8, UTF16: s16}
}
func makeInputString(s string) Input {
return Input{
UTF8: []byte(s),
UTF16: utf16.Encode([]rune(s)),
}
}
// Collator is an interface for architecture-specific implementations of collation.
type Collator interface {
// Key generates a sort key for the given input. Implemenations
// may return nil if a collator does not support sort keys.
Key(s Input) []byte
// Compare returns -1 if a < b, 1 if a > b and 0 if a == b.
Compare(a, b Input) int
}
// CollatorFactory creates a Collator for a given language tag.
type CollatorFactory struct {
name string
makeFn func(tag string) (Collator, error)
description string
}
var collators = []CollatorFactory{}
// AddFactory registers f as a factory for an implementation of Collator.
func AddFactory(f CollatorFactory) {
collators = append(collators, f)
}
func getCollator(name, locale string) Collator {
for _, f := range collators {
if f.name == name {
col, err := f.makeFn(locale)
if err != nil {
log.Fatal(err)
}
return col
}
}
log.Fatalf("collator of type %q not found", name)
return nil
}
// goCollator is an implemention of Collator using go's own collator.
type goCollator struct {
c *collate.Collator
buf collate.Buffer
}
func init() {
AddFactory(CollatorFactory{"go", newGoCollator, "Go's native collator implementation."})
}
func newGoCollator(loc string) (Collator, error) {
c := &goCollator{c: collate.New(language.Make(loc))}
return c, nil
}
func (c *goCollator) Key(b Input) []byte {
return c.c.Key(&c.buf, b.UTF8)
}
func (c *goCollator) Compare(a, b Input) int {
return c.c.Compare(a.UTF8, b.UTF8)
}

View File

@ -1,529 +0,0 @@
// Copyright 2012 The 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 main // import "golang.org/x/text/collate/tools/colcmp"
import (
"bytes"
"flag"
"fmt"
"io"
"log"
"os"
"runtime/pprof"
"sort"
"strconv"
"strings"
"text/template"
"time"
"golang.org/x/text/unicode/norm"
)
var (
doNorm = flag.Bool("norm", false, "normalize input strings")
cases = flag.Bool("case", false, "generate case variants")
verbose = flag.Bool("verbose", false, "print results")
debug = flag.Bool("debug", false, "output debug information")
locales = flag.String("locale", "en_US", "the locale to use. May be a comma-separated list for some commands.")
col = flag.String("col", "go", "collator to test")
gold = flag.String("gold", "go", "collator used as the gold standard")
usecmp = flag.Bool("usecmp", false,
`use comparison instead of sort keys when sorting. Must be "test", "gold" or "both"`)
cpuprofile = flag.String("cpuprofile", "", "write cpu profile to file")
exclude = flag.String("exclude", "", "exclude errors that contain any of the characters")
limit = flag.Int("limit", 5000000, "maximum number of samples to generate for one run")
)
func failOnError(err error) {
if err != nil {
log.Panic(err)
}
}
// Test holds test data for testing a locale-collator pair.
// Test also provides functionality that is commonly used by the various commands.
type Test struct {
ctxt *Context
Name string
Locale string
ColName string
Col Collator
UseCompare bool
Input []Input
Duration time.Duration
start time.Time
msg string
count int
}
func (t *Test) clear() {
t.Col = nil
t.Input = nil
}
const (
msgGeneratingInput = "generating input"
msgGeneratingKeys = "generating keys"
msgSorting = "sorting"
)
var lastLen = 0
func (t *Test) SetStatus(msg string) {
if *debug || *verbose {
fmt.Printf("%s: %s...\n", t.Name, msg)
} else if t.ctxt.out != nil {
fmt.Fprint(t.ctxt.out, strings.Repeat(" ", lastLen))
fmt.Fprint(t.ctxt.out, strings.Repeat("\b", lastLen))
fmt.Fprint(t.ctxt.out, msg, "...")
lastLen = len(msg) + 3
fmt.Fprint(t.ctxt.out, strings.Repeat("\b", lastLen))
}
}
// Start is used by commands to signal the start of an operation.
func (t *Test) Start(msg string) {
t.SetStatus(msg)
t.count = 0
t.msg = msg
t.start = time.Now()
}
// Stop is used by commands to signal the end of an operation.
func (t *Test) Stop() (time.Duration, int) {
d := time.Now().Sub(t.start)
t.Duration += d
if *debug || *verbose {
fmt.Printf("%s: %s done. (%.3fs /%dK ops)\n", t.Name, t.msg, d.Seconds(), t.count/1000)
}
return d, t.count
}
// generateKeys generates sort keys for all the inputs.
func (t *Test) generateKeys() {
for i, s := range t.Input {
b := t.Col.Key(s)
t.Input[i].key = b
if *debug {
fmt.Printf("%s (%X): %X\n", string(s.UTF8), s.UTF16, b)
}
}
}
// Sort sorts the inputs. It generates sort keys if this is required by the
// chosen sort method.
func (t *Test) Sort() (tkey, tsort time.Duration, nkey, nsort int) {
if *cpuprofile != "" {
f, err := os.Create(*cpuprofile)
failOnError(err)
pprof.StartCPUProfile(f)
defer pprof.StopCPUProfile()
}
if t.UseCompare || t.Col.Key(t.Input[0]) == nil {
t.Start(msgSorting)
sort.Sort(&testCompare{*t})
tsort, nsort = t.Stop()
} else {
t.Start(msgGeneratingKeys)
t.generateKeys()
t.count = len(t.Input)
tkey, nkey = t.Stop()
t.Start(msgSorting)
sort.Sort(t)
tsort, nsort = t.Stop()
}
return
}
func (t *Test) Swap(a, b int) {
t.Input[a], t.Input[b] = t.Input[b], t.Input[a]
}
func (t *Test) Less(a, b int) bool {
t.count++
return bytes.Compare(t.Input[a].key, t.Input[b].key) == -1
}
func (t Test) Len() int {
return len(t.Input)
}
type testCompare struct {
Test
}
func (t *testCompare) Less(a, b int) bool {
t.count++
return t.Col.Compare(t.Input[a], t.Input[b]) == -1
}
type testRestore struct {
Test
}
func (t *testRestore) Less(a, b int) bool {
return t.Input[a].index < t.Input[b].index
}
// GenerateInput generates input phrases for the locale tested by t.
func (t *Test) GenerateInput() {
t.Input = nil
if t.ctxt.lastLocale != t.Locale {
gen := phraseGenerator{}
gen.init(t.Locale)
t.SetStatus(msgGeneratingInput)
t.ctxt.lastInput = nil // allow the previous value to be garbage collected.
t.Input = gen.generate(*doNorm)
t.ctxt.lastInput = t.Input
t.ctxt.lastLocale = t.Locale
} else {
t.Input = t.ctxt.lastInput
for i := range t.Input {
t.Input[i].key = nil
}
sort.Sort(&testRestore{*t})
}
}
// Context holds all tests and settings translated from command line options.
type Context struct {
test []*Test
last *Test
lastLocale string
lastInput []Input
out io.Writer
}
func (ts *Context) Printf(format string, a ...interface{}) {
ts.assertBuf()
fmt.Fprintf(ts.out, format, a...)
}
func (ts *Context) Print(a ...interface{}) {
ts.assertBuf()
fmt.Fprint(ts.out, a...)
}
// assertBuf sets up an io.Writer for output, if it doesn't already exist.
// In debug and verbose mode, output is buffered so that the regular output
// will not interfere with the additional output. Otherwise, output is
// written directly to stdout for a more responsive feel.
func (ts *Context) assertBuf() {
if ts.out != nil {
return
}
if *debug || *verbose {
ts.out = &bytes.Buffer{}
} else {
ts.out = os.Stdout
}
}
// flush flushes the contents of ts.out to stdout, if it is not stdout already.
func (ts *Context) flush() {
if ts.out != nil {
if _, ok := ts.out.(io.ReadCloser); !ok {
io.Copy(os.Stdout, ts.out.(io.Reader))
}
}
}
// parseTests creates all tests from command lines and returns
// a Context to hold them.
func parseTests() *Context {
ctxt := &Context{}
colls := strings.Split(*col, ",")
for _, loc := range strings.Split(*locales, ",") {
loc = strings.TrimSpace(loc)
for _, name := range colls {
name = strings.TrimSpace(name)
col := getCollator(name, loc)
ctxt.test = append(ctxt.test, &Test{
ctxt: ctxt,
Locale: loc,
ColName: name,
UseCompare: *usecmp,
Col: col,
})
}
}
return ctxt
}
func (c *Context) Len() int {
return len(c.test)
}
func (c *Context) Test(i int) *Test {
if c.last != nil {
c.last.clear()
}
c.last = c.test[i]
return c.last
}
func parseInput(args []string) []Input {
input := []Input{}
for _, s := range args {
rs := []rune{}
for len(s) > 0 {
var r rune
r, _, s, _ = strconv.UnquoteChar(s, '\'')
rs = append(rs, r)
}
s = string(rs)
if *doNorm {
s = norm.NFD.String(s)
}
input = append(input, makeInputString(s))
}
return input
}
// A Command is an implementation of a colcmp command.
type Command struct {
Run func(cmd *Context, args []string)
Usage string
Short string
Long string
}
func (cmd Command) Name() string {
return strings.SplitN(cmd.Usage, " ", 2)[0]
}
var commands = []*Command{
cmdSort,
cmdBench,
cmdRegress,
}
const sortHelp = `
Sort sorts a given list of strings. Strings are separated by whitespace.
`
var cmdSort = &Command{
Run: runSort,
Usage: "sort <string>*",
Short: "sort a given list of strings",
Long: sortHelp,
}
func runSort(ctxt *Context, args []string) {
input := parseInput(args)
if len(input) == 0 {
log.Fatalf("Nothing to sort.")
}
if ctxt.Len() > 1 {
ctxt.Print("COLL LOCALE RESULT\n")
}
for i := 0; i < ctxt.Len(); i++ {
t := ctxt.Test(i)
t.Input = append(t.Input, input...)
t.Sort()
if ctxt.Len() > 1 {
ctxt.Printf("%-5s %-5s ", t.ColName, t.Locale)
}
for _, s := range t.Input {
ctxt.Print(string(s.UTF8), " ")
}
ctxt.Print("\n")
}
}
const benchHelp = `
Bench runs a benchmark for the given list of collator implementations.
If no collator implementations are given, the go collator will be used.
`
var cmdBench = &Command{
Run: runBench,
Usage: "bench",
Short: "benchmark a given list of collator implementations",
Long: benchHelp,
}
func runBench(ctxt *Context, args []string) {
ctxt.Printf("%-7s %-5s %-6s %-24s %-24s %-5s %s\n", "LOCALE", "COLL", "N", "KEYS", "SORT", "AVGLN", "TOTAL")
for i := 0; i < ctxt.Len(); i++ {
t := ctxt.Test(i)
ctxt.Printf("%-7s %-5s ", t.Locale, t.ColName)
t.GenerateInput()
ctxt.Printf("%-6s ", fmt.Sprintf("%dK", t.Len()/1000))
tkey, tsort, nkey, nsort := t.Sort()
p := func(dur time.Duration, n int) {
s := ""
if dur > 0 {
s = fmt.Sprintf("%6.3fs ", dur.Seconds())
if n > 0 {
s += fmt.Sprintf("%15s", fmt.Sprintf("(%4.2f ns/op)", float64(dur)/float64(n)))
}
}
ctxt.Printf("%-24s ", s)
}
p(tkey, nkey)
p(tsort, nsort)
total := 0
for _, s := range t.Input {
total += len(s.key)
}
ctxt.Printf("%-5d ", total/t.Len())
ctxt.Printf("%6.3fs\n", t.Duration.Seconds())
if *debug {
for _, s := range t.Input {
fmt.Print(string(s.UTF8), " ")
}
fmt.Println()
}
}
}
const regressHelp = `
Regress runs a monkey test by comparing the results of randomly generated tests
between two implementations of a collator. The user may optionally pass a list
of strings to regress against instead of the default test set.
`
var cmdRegress = &Command{
Run: runRegress,
Usage: "regress -gold=<col> -test=<col> [string]*",
Short: "run a monkey test between two collators",
Long: regressHelp,
}
const failedKeyCompare = `
%s:%d: incorrect comparison result for input:
a: %q (%.4X)
key: %s
b: %q (%.4X)
key: %s
Compare(a, b) = %d; want %d.
gold keys:
a: %s
b: %s
`
const failedCompare = `
%s:%d: incorrect comparison result for input:
a: %q (%.4X)
b: %q (%.4X)
Compare(a, b) = %d; want %d.
`
func keyStr(b []byte) string {
buf := &bytes.Buffer{}
for _, v := range b {
fmt.Fprintf(buf, "%.2X ", v)
}
return buf.String()
}
func runRegress(ctxt *Context, args []string) {
input := parseInput(args)
for i := 0; i < ctxt.Len(); i++ {
t := ctxt.Test(i)
if len(input) > 0 {
t.Input = append(t.Input, input...)
} else {
t.GenerateInput()
}
t.Sort()
count := 0
gold := getCollator(*gold, t.Locale)
for i := 1; i < len(t.Input); i++ {
ia := t.Input[i-1]
ib := t.Input[i]
if bytes.IndexAny(ib.UTF8, *exclude) != -1 {
i++
continue
}
if bytes.IndexAny(ia.UTF8, *exclude) != -1 {
continue
}
goldCmp := gold.Compare(ia, ib)
if cmp := bytes.Compare(ia.key, ib.key); cmp != goldCmp {
count++
a := string(ia.UTF8)
b := string(ib.UTF8)
fmt.Printf(failedKeyCompare, t.Locale, i-1, a, []rune(a), keyStr(ia.key), b, []rune(b), keyStr(ib.key), cmp, goldCmp, keyStr(gold.Key(ia)), keyStr(gold.Key(ib)))
} else if cmp := t.Col.Compare(ia, ib); cmp != goldCmp {
count++
a := string(ia.UTF8)
b := string(ib.UTF8)
fmt.Printf(failedCompare, t.Locale, i-1, a, []rune(a), b, []rune(b), cmp, goldCmp)
}
}
if count > 0 {
ctxt.Printf("Found %d inconsistencies in %d entries.\n", count, t.Len()-1)
}
}
}
const helpTemplate = `
colcmp is a tool for testing and benchmarking collation
Usage: colcmp command [arguments]
The commands are:
{{range .}}
{{.Name | printf "%-11s"}} {{.Short}}{{end}}
Use "col help [topic]" for more information about that topic.
`
const detailedHelpTemplate = `
Usage: colcmp {{.Usage}}
{{.Long | trim}}
`
func runHelp(args []string) {
t := template.New("help")
t.Funcs(template.FuncMap{"trim": strings.TrimSpace})
if len(args) < 1 {
template.Must(t.Parse(helpTemplate))
failOnError(t.Execute(os.Stderr, &commands))
} else {
for _, cmd := range commands {
if cmd.Name() == args[0] {
template.Must(t.Parse(detailedHelpTemplate))
failOnError(t.Execute(os.Stderr, cmd))
os.Exit(0)
}
}
log.Fatalf("Unknown command %q. Run 'colcmp help'.", args[0])
}
os.Exit(0)
}
func main() {
flag.Parse()
log.SetFlags(0)
ctxt := parseTests()
if flag.NArg() < 1 {
runHelp(nil)
}
args := flag.Args()[1:]
if flag.Arg(0) == "help" {
runHelp(args)
}
for _, cmd := range commands {
if cmd.Name() == flag.Arg(0) {
cmd.Run(ctxt, args)
ctxt.flush()
return
}
}
runHelp(flag.Args())
}

View File

@ -1,111 +0,0 @@
// Copyright 2012 The 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.
// +build darwin
package main
/*
#cgo LDFLAGS: -framework CoreFoundation
#include <CoreFoundation/CFBase.h>
#include <CoreFoundation/CoreFoundation.h>
*/
import "C"
import (
"unsafe"
)
func init() {
AddFactory(CollatorFactory{"osx", newOSX16Collator,
"OS X/Darwin collator, using native strings."})
AddFactory(CollatorFactory{"osx8", newOSX8Collator,
"OS X/Darwin collator for UTF-8."})
}
func osxUInt8P(s []byte) *C.UInt8 {
return (*C.UInt8)(unsafe.Pointer(&s[0]))
}
func osxCharP(s []uint16) *C.UniChar {
return (*C.UniChar)(unsafe.Pointer(&s[0]))
}
// osxCollator implements an Collator based on OS X's CoreFoundation.
type osxCollator struct {
loc C.CFLocaleRef
opt C.CFStringCompareFlags
}
func (c *osxCollator) init(locale string) {
l := C.CFStringCreateWithBytes(
C.kCFAllocatorDefault,
osxUInt8P([]byte(locale)),
C.CFIndex(len(locale)),
C.kCFStringEncodingUTF8,
C.Boolean(0),
)
c.loc = C.CFLocaleCreate(C.kCFAllocatorDefault, l)
}
func newOSX8Collator(locale string) (Collator, error) {
c := &osx8Collator{}
c.init(locale)
return c, nil
}
func newOSX16Collator(locale string) (Collator, error) {
c := &osx16Collator{}
c.init(locale)
return c, nil
}
func (c osxCollator) Key(s Input) []byte {
return nil // sort keys not supported by OS X CoreFoundation
}
type osx8Collator struct {
osxCollator
}
type osx16Collator struct {
osxCollator
}
func (c osx16Collator) Compare(a, b Input) int {
sa := C.CFStringCreateWithCharactersNoCopy(
C.kCFAllocatorDefault,
osxCharP(a.UTF16),
C.CFIndex(len(a.UTF16)),
C.kCFAllocatorDefault,
)
sb := C.CFStringCreateWithCharactersNoCopy(
C.kCFAllocatorDefault,
osxCharP(b.UTF16),
C.CFIndex(len(b.UTF16)),
C.kCFAllocatorDefault,
)
_range := C.CFRangeMake(0, C.CFStringGetLength(sa))
return int(C.CFStringCompareWithOptionsAndLocale(sa, sb, _range, c.opt, c.loc))
}
func (c osx8Collator) Compare(a, b Input) int {
sa := C.CFStringCreateWithBytesNoCopy(
C.kCFAllocatorDefault,
osxUInt8P(a.UTF8),
C.CFIndex(len(a.UTF8)),
C.kCFStringEncodingUTF8,
C.Boolean(0),
C.kCFAllocatorDefault,
)
sb := C.CFStringCreateWithBytesNoCopy(
C.kCFAllocatorDefault,
osxUInt8P(b.UTF8),
C.CFIndex(len(b.UTF8)),
C.kCFStringEncodingUTF8,
C.Boolean(0),
C.kCFAllocatorDefault,
)
_range := C.CFRangeMake(0, C.CFStringGetLength(sa))
return int(C.CFStringCompareWithOptionsAndLocale(sa, sb, _range, c.opt, c.loc))
}

View File

@ -1,183 +0,0 @@
// Copyright 2012 The 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 main
import (
"math"
"math/rand"
"strings"
"unicode"
"unicode/utf16"
"unicode/utf8"
"golang.org/x/text/language"
"golang.org/x/text/unicode/norm"
)
// TODO: replace with functionality in language package.
// parent computes the parent language for the given language.
// It returns false if the parent is already root.
func parent(locale string) (parent string, ok bool) {
if locale == "und" {
return "", false
}
if i := strings.LastIndex(locale, "-"); i != -1 {
return locale[:i], true
}
return "und", true
}
// rewriter is used to both unique strings and create variants of strings
// to add to the test set.
type rewriter struct {
seen map[string]bool
addCases bool
}
func newRewriter() *rewriter {
return &rewriter{
seen: make(map[string]bool),
}
}
func (r *rewriter) insert(a []string, s string) []string {
if !r.seen[s] {
r.seen[s] = true
a = append(a, s)
}
return a
}
// rewrite takes a sequence of strings in, adds variants of the these strings
// based on options and removes duplicates.
func (r *rewriter) rewrite(ss []string) []string {
ns := []string{}
for _, s := range ss {
ns = r.insert(ns, s)
if r.addCases {
rs := []rune(s)
rn := rs[0]
for c := unicode.SimpleFold(rn); c != rn; c = unicode.SimpleFold(c) {
rs[0] = c
ns = r.insert(ns, string(rs))
}
}
}
return ns
}
// exemplarySet holds a parsed set of characters from the exemplarCharacters table.
type exemplarySet struct {
typ exemplarType
set []string
charIndex int // cumulative total of phrases, including this set
}
type phraseGenerator struct {
sets [exN]exemplarySet
n int
}
func (g *phraseGenerator) init(id string) {
ec := exemplarCharacters
loc := language.Make(id).String()
// get sets for locale or parent locale if the set is not defined.
for i := range g.sets {
for p, ok := loc, true; ok; p, ok = parent(p) {
if set, ok := ec[p]; ok && set[i] != "" {
g.sets[i].set = strings.Split(set[i], " ")
break
}
}
}
r := newRewriter()
r.addCases = *cases
for i := range g.sets {
g.sets[i].set = r.rewrite(g.sets[i].set)
}
// compute indexes
for i, set := range g.sets {
g.n += len(set.set)
g.sets[i].charIndex = g.n
}
}
// phrase returns the ith phrase, where i < g.n.
func (g *phraseGenerator) phrase(i int) string {
for _, set := range g.sets {
if i < set.charIndex {
return set.set[i-(set.charIndex-len(set.set))]
}
}
panic("index out of range")
}
// generate generates inputs by combining all pairs of examplar strings.
// If doNorm is true, all input strings are normalized to NFC.
// TODO: allow other variations, statistical models, and random
// trailing sequences.
func (g *phraseGenerator) generate(doNorm bool) []Input {
const (
M = 1024 * 1024
buf8Size = 30 * M
buf16Size = 10 * M
)
// TODO: use a better way to limit the input size.
if sq := int(math.Sqrt(float64(*limit))); g.n > sq {
g.n = sq
}
size := g.n * g.n
a := make([]Input, 0, size)
buf8 := make([]byte, 0, buf8Size)
buf16 := make([]uint16, 0, buf16Size)
addInput := func(str string) {
buf8 = buf8[len(buf8):]
buf16 = buf16[len(buf16):]
if len(str) > cap(buf8) {
buf8 = make([]byte, 0, buf8Size)
}
if len(str) > cap(buf16) {
buf16 = make([]uint16, 0, buf16Size)
}
if doNorm {
buf8 = norm.NFD.AppendString(buf8, str)
} else {
buf8 = append(buf8, str...)
}
buf16 = appendUTF16(buf16, buf8)
a = append(a, makeInput(buf8, buf16))
}
for i := 0; i < g.n; i++ {
p1 := g.phrase(i)
addInput(p1)
for j := 0; j < g.n; j++ {
p2 := g.phrase(j)
addInput(p1 + p2)
}
}
// permutate
rnd := rand.New(rand.NewSource(int64(rand.Int())))
for i := range a {
j := i + rnd.Intn(len(a)-i)
a[i], a[j] = a[j], a[i]
a[i].index = i // allow restoring this order if input is used multiple times.
}
return a
}
func appendUTF16(buf []uint16, s []byte) []uint16 {
for len(s) > 0 {
r, sz := utf8.DecodeRune(s)
s = s[sz:]
r1, r2 := utf16.EncodeRune(r)
if r1 != 0xFFFD {
buf = append(buf, uint16(r1), uint16(r2))
} else {
buf = append(buf, uint16(r))
}
}
return buf
}

View File

@ -1,209 +0,0 @@
// Copyright 2012 The 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.
// +build icu
package main
/*
#cgo LDFLAGS: -licui18n -licuuc
#include <stdlib.h>
#include <unicode/ucol.h>
#include <unicode/uiter.h>
#include <unicode/utypes.h>
*/
import "C"
import (
"fmt"
"log"
"unicode/utf16"
"unicode/utf8"
"unsafe"
)
func init() {
AddFactory(CollatorFactory{"icu", newUTF16,
"Main ICU collator, using native strings."})
AddFactory(CollatorFactory{"icu8", newUTF8iter,
"ICU collator using ICU iterators to process UTF8."})
AddFactory(CollatorFactory{"icu16", newUTF8conv,
"ICU collation by first converting UTF8 to UTF16."})
}
func icuCharP(s []byte) *C.char {
return (*C.char)(unsafe.Pointer(&s[0]))
}
func icuUInt8P(s []byte) *C.uint8_t {
return (*C.uint8_t)(unsafe.Pointer(&s[0]))
}
func icuUCharP(s []uint16) *C.UChar {
return (*C.UChar)(unsafe.Pointer(&s[0]))
}
func icuULen(s []uint16) C.int32_t {
return C.int32_t(len(s))
}
func icuSLen(s []byte) C.int32_t {
return C.int32_t(len(s))
}
// icuCollator implements a Collator based on ICU.
type icuCollator struct {
loc *C.char
col *C.UCollator
keyBuf []byte
}
const growBufSize = 10 * 1024 * 1024
func (c *icuCollator) init(locale string) error {
err := C.UErrorCode(0)
c.loc = C.CString(locale)
c.col = C.ucol_open(c.loc, &err)
if err > 0 {
return fmt.Errorf("failed opening collator for %q", locale)
} else if err < 0 {
loc := C.ucol_getLocaleByType(c.col, 0, &err)
fmt, ok := map[int]string{
-127: "warning: using default collator: %s",
-128: "warning: using fallback collator: %s",
}[int(err)]
if ok {
log.Printf(fmt, C.GoString(loc))
}
}
c.keyBuf = make([]byte, 0, growBufSize)
return nil
}
func (c *icuCollator) buf() (*C.uint8_t, C.int32_t) {
if len(c.keyBuf) == cap(c.keyBuf) {
c.keyBuf = make([]byte, 0, growBufSize)
}
b := c.keyBuf[len(c.keyBuf):cap(c.keyBuf)]
return icuUInt8P(b), icuSLen(b)
}
func (c *icuCollator) extendBuf(n C.int32_t) []byte {
end := len(c.keyBuf) + int(n)
if end > cap(c.keyBuf) {
if len(c.keyBuf) == 0 {
log.Fatalf("icuCollator: max string size exceeded: %v > %v", n, growBufSize)
}
c.keyBuf = make([]byte, 0, growBufSize)
return nil
}
b := c.keyBuf[len(c.keyBuf):end]
c.keyBuf = c.keyBuf[:end]
return b
}
func (c *icuCollator) Close() error {
C.ucol_close(c.col)
C.free(unsafe.Pointer(c.loc))
return nil
}
// icuUTF16 implements the Collator interface.
type icuUTF16 struct {
icuCollator
}
func newUTF16(locale string) (Collator, error) {
c := &icuUTF16{}
return c, c.init(locale)
}
func (c *icuUTF16) Compare(a, b Input) int {
return int(C.ucol_strcoll(c.col, icuUCharP(a.UTF16), icuULen(a.UTF16), icuUCharP(b.UTF16), icuULen(b.UTF16)))
}
func (c *icuUTF16) Key(s Input) []byte {
bp, bn := c.buf()
n := C.ucol_getSortKey(c.col, icuUCharP(s.UTF16), icuULen(s.UTF16), bp, bn)
if b := c.extendBuf(n); b != nil {
return b
}
return c.Key(s)
}
// icuUTF8iter implements the Collator interface
// This implementation wraps the UTF8 string in an iterator
// which is passed to the collator.
type icuUTF8iter struct {
icuCollator
a, b C.UCharIterator
}
func newUTF8iter(locale string) (Collator, error) {
c := &icuUTF8iter{}
return c, c.init(locale)
}
func (c *icuUTF8iter) Compare(a, b Input) int {
err := C.UErrorCode(0)
C.uiter_setUTF8(&c.a, icuCharP(a.UTF8), icuSLen(a.UTF8))
C.uiter_setUTF8(&c.b, icuCharP(b.UTF8), icuSLen(b.UTF8))
return int(C.ucol_strcollIter(c.col, &c.a, &c.b, &err))
}
func (c *icuUTF8iter) Key(s Input) []byte {
err := C.UErrorCode(0)
state := [2]C.uint32_t{}
C.uiter_setUTF8(&c.a, icuCharP(s.UTF8), icuSLen(s.UTF8))
bp, bn := c.buf()
n := C.ucol_nextSortKeyPart(c.col, &c.a, &(state[0]), bp, bn, &err)
if n >= bn {
// Force failure.
if c.extendBuf(n+1) != nil {
log.Fatal("expected extension to fail")
}
return c.Key(s)
}
return c.extendBuf(n)
}
// icuUTF8conv implements the Collator interface.
// This implementation first converts the give UTF8 string
// to UTF16 and then calls the main ICU collation function.
type icuUTF8conv struct {
icuCollator
}
func newUTF8conv(locale string) (Collator, error) {
c := &icuUTF8conv{}
return c, c.init(locale)
}
func (c *icuUTF8conv) Compare(sa, sb Input) int {
a := encodeUTF16(sa.UTF8)
b := encodeUTF16(sb.UTF8)
return int(C.ucol_strcoll(c.col, icuUCharP(a), icuULen(a), icuUCharP(b), icuULen(b)))
}
func (c *icuUTF8conv) Key(s Input) []byte {
a := encodeUTF16(s.UTF8)
bp, bn := c.buf()
n := C.ucol_getSortKey(c.col, icuUCharP(a), icuULen(a), bp, bn)
if b := c.extendBuf(n); b != nil {
return b
}
return c.Key(s)
}
func encodeUTF16(b []byte) []uint16 {
a := []uint16{}
for len(b) > 0 {
r, sz := utf8.DecodeRune(b)
b = b[sz:]
r1, r2 := utf16.EncodeRune(r)
if r1 != 0xFFFD {
a = append(a, uint16(r1), uint16(r2))
} else {
a = append(a, uint16(r))
}
}
return a
}