Zakaria/LearnGO
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

whatcanGOwrong

Browse Source
This commit is contained in:
dadgam3er
2024-09-19 21:38:24 -04:00
commit d0ae4d841d
17908 changed files with 4096831 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/common.go
+16
View File
@@ -0,0 +1,16 @@
// Code generated by running "go generate" in golang.org/x/text. DO NOT EDIT.
package language
// This file contains code common to the maketables.go and the package code.
// AliasType is the type of an alias in AliasMap.
type AliasType int8
const (
Deprecated AliasType = iota
Macro
Legacy
AliasTypeUnknown AliasType = -1
)
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compact.go
+29
View File
@@ -0,0 +1,29 @@
// Copyright 2018 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 language
// CompactCoreInfo is a compact integer with the three core tags encoded.
type CompactCoreInfo uint32
// GetCompactCore generates a uint32 value that is guaranteed to be unique for
// different language, region, and script values.
func GetCompactCore(t Tag) (cci CompactCoreInfo, ok bool) {
if t.LangID > langNoIndexOffset {
return 0, false
}
cci |= CompactCoreInfo(t.LangID) << (8 + 12)
cci |= CompactCoreInfo(t.ScriptID) << 12
cci |= CompactCoreInfo(t.RegionID)
return cci, true
}
// Tag generates a tag from c.
func (c CompactCoreInfo) Tag() Tag {
return Tag{
LangID: Language(c >> 20),
RegionID: Region(c & 0x3ff),
ScriptID: Script(c>>12) & 0xff,
}
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compact/compact.go
+61
View File
@@ -0,0 +1,61 @@
// Copyright 2018 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 compact defines a compact representation of language tags.
//
// Common language tags (at least all for which locale information is defined
// in CLDR) are assigned a unique index. Each Tag is associated with such an
// ID for selecting language-related resources (such as translations) as well
// as one for selecting regional defaults (currency, number formatting, etc.)
//
// It may want to export this functionality at some point, but at this point
// this is only available for use within x/text.
package compact // import "golang.org/x/text/internal/language/compact"
import (
"sort"
"strings"
"golang.org/x/text/internal/language"
)
// ID is an integer identifying a single tag.
type ID uint16
func getCoreIndex(t language.Tag) (id ID, ok bool) {
cci, ok := language.GetCompactCore(t)
if !ok {
return 0, false
}
i := sort.Search(len(coreTags), func(i int) bool {
return cci <= coreTags[i]
})
if i == len(coreTags) || coreTags[i] != cci {
return 0, false
}
return ID(i), true
}
// Parent returns the ID of the parent or the root ID if id is already the root.
func (id ID) Parent() ID {
return parents[id]
}
// Tag converts id to an internal language Tag.
func (id ID) Tag() language.Tag {
if int(id) >= len(coreTags) {
return specialTags[int(id)-len(coreTags)]
}
return coreTags[id].Tag()
}
var specialTags []language.Tag
func init() {
tags := strings.Split(specialTagsStr, " ")
specialTags = make([]language.Tag, len(tags))
for i, t := range tags {
specialTags[i] = language.MustParse(t)
}
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compact/gen.go
+64
View File
@@ -0,0 +1,64 @@
// 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.
//go:build ignore
// Language tag table generator.
// Data read from the web.
package main
import (
"flag"
"fmt"
"log"
"golang.org/x/text/internal/gen"
"golang.org/x/text/unicode/cldr"
)
var (
test = flag.Bool("test",
false,
"test existing tables; can be used to compare web data with package data.")
outputFile = flag.String("output",
"tables.go",
"output file for generated tables")
)
func main() {
gen.Init()
w := gen.NewCodeWriter()
defer w.WriteGoFile("tables.go", "compact")
fmt.Fprintln(w, `import "golang.org/x/text/internal/language"`)
b := newBuilder(w)
gen.WriteCLDRVersion(w)
b.writeCompactIndex()
}
type builder struct {
w *gen.CodeWriter
data *cldr.CLDR
supp *cldr.SupplementalData
}
func newBuilder(w *gen.CodeWriter) *builder {
r := gen.OpenCLDRCoreZip()
defer r.Close()
d := &cldr.Decoder{}
data, err := d.DecodeZip(r)
if err != nil {
log.Fatal(err)
}
b := builder{
w: w,
data: data,
supp: data.Supplemental(),
}
return &b
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compact/gen_index.go
+113
View File
@@ -0,0 +1,113 @@
// Copyright 2015 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.
//go:build ignore
package main
// This file generates derivative tables based on the language package itself.
import (
"fmt"
"log"
"sort"
"strings"
"golang.org/x/text/internal/language"
)
// Compact indices:
// Note -va-X variants only apply to localization variants.
// BCP variants only ever apply to language.
// The only ambiguity between tags is with regions.
func (b *builder) writeCompactIndex() {
// Collect all language tags for which we have any data in CLDR.
m := map[language.Tag]bool{}
for _, lang := range b.data.Locales() {
// We include all locales unconditionally to be consistent with en_US.
// We want en_US, even though it has no data associated with it.
// TODO: put any of the languages for which no data exists at the end
// of the index. This allows all components based on ICU to use that
// as the cutoff point.
// if x := data.RawLDML(lang); false ||
// x.LocaleDisplayNames != nil ||
// x.Characters != nil ||
// x.Delimiters != nil ||
// x.Measurement != nil ||
// x.Dates != nil ||
// x.Numbers != nil ||
// x.Units != nil ||
// x.ListPatterns != nil ||
// x.Collations != nil ||
// x.Segmentations != nil ||
// x.Rbnf != nil ||
// x.Annotations != nil ||
// x.Metadata != nil {
// TODO: support POSIX natively, albeit non-standard.
tag := language.Make(strings.Replace(lang, "_POSIX", "-u-va-posix", 1))
m[tag] = true
// }
}
// TODO: plural rules are also defined for the deprecated tags:
// iw mo sh tl
// Consider removing these as compact tags.
// Include locales for plural rules, which uses a different structure.
for _, plurals := range b.supp.Plurals {
for _, rules := range plurals.PluralRules {
for _, lang := range strings.Split(rules.Locales, " ") {
m[language.Make(lang)] = true
}
}
}
var coreTags []language.CompactCoreInfo
var special []string
for t := range m {
if x := t.Extensions(); len(x) != 0 && fmt.Sprint(x) != "[u-va-posix]" {
log.Fatalf("Unexpected extension %v in %v", x, t)
}
if len(t.Variants()) == 0 && len(t.Extensions()) == 0 {
cci, ok := language.GetCompactCore(t)
if !ok {
log.Fatalf("Locale for non-basic language %q", t)
}
coreTags = append(coreTags, cci)
} else {
special = append(special, t.String())
}
}
w := b.w
sort.Slice(coreTags, func(i, j int) bool { return coreTags[i] < coreTags[j] })
sort.Strings(special)
w.WriteComment(`
NumCompactTags is the number of common tags. The maximum tag is
NumCompactTags-1.`)
w.WriteConst("NumCompactTags", len(m))
fmt.Fprintln(w, "const (")
for i, t := range coreTags {
fmt.Fprintf(w, "%s ID = %d\n", ident(t.Tag().String()), i)
}
for i, t := range special {
fmt.Fprintf(w, "%s ID = %d\n", ident(t), i+len(coreTags))
}
fmt.Fprintln(w, ")")
w.WriteVar("coreTags", coreTags)
w.WriteConst("specialTagsStr", strings.Join(special, " "))
}
func ident(s string) string {
return strings.Replace(s, "-", "", -1) + "Index"
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compact/gen_parents.go
+54
View File
@@ -0,0 +1,54 @@
// Copyright 2018 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.
//go:build ignore
package main
import (
"log"
"golang.org/x/text/internal/gen"
"golang.org/x/text/internal/language"
"golang.org/x/text/internal/language/compact"
"golang.org/x/text/unicode/cldr"
)
func main() {
r := gen.OpenCLDRCoreZip()
defer r.Close()
d := &cldr.Decoder{}
data, err := d.DecodeZip(r)
if err != nil {
log.Fatalf("DecodeZip: %v", err)
}
w := gen.NewCodeWriter()
defer w.WriteGoFile("parents.go", "compact")
// Create parents table.
type ID uint16
parents := make([]ID, compact.NumCompactTags)
for _, loc := range data.Locales() {
tag := language.MustParse(loc)
index, ok := compact.FromTag(tag)
if !ok {
continue
}
parentIndex := compact.ID(0) // und
for p := tag.Parent(); p != language.Und; p = p.Parent() {
if x, ok := compact.FromTag(p); ok {
parentIndex = x
break
}
}
parents[index] = ID(parentIndex)
}
w.WriteComment(`
parents maps a compact index of a tag to the compact index of the parent of
this tag.`)
w.WriteVar("parents", parents)
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compact/gen_test.go
+38
View File
@@ -0,0 +1,38 @@
// Copyright 2015 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 compact
import (
"testing"
"golang.org/x/text/internal/language"
)
func TestParents(t *testing.T) {
testCases := []struct {
tag, parent string
}{
{"af", "und"},
{"en", "und"},
{"en-001", "en"},
{"en-AU", "en-001"},
{"en-US", "en"},
{"en-US-u-va-posix", "en-US"},
{"ca-ES-valencia", "ca-ES"},
}
for _, tc := range testCases {
tag, ok := LanguageID(Make(language.MustParse(tc.tag)))
if !ok {
t.Fatalf("Could not get index of flag %s", tc.tag)
}
want, ok := LanguageID(Make(language.MustParse(tc.parent)))
if !ok {
t.Fatalf("Could not get index of parent %s of tag %s", tc.parent, tc.tag)
}
if got := parents[tag]; got != want {
t.Errorf("Parent[%s] = %d; want %d (%s)", tc.tag, got, want, tc.parent)
}
}
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compact/language.go
+260
View File
@@ -0,0 +1,260 @@
// 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.
//go:generate go run gen.go gen_index.go -output tables.go
//go:generate go run gen_parents.go
package compact
// TODO: Remove above NOTE after:
// - verifying that tables are dropped correctly (most notably matcher tables).
import (
"strings"
"golang.org/x/text/internal/language"
)
// Tag represents a BCP 47 language tag. It is used to specify an instance of a
// specific language or locale. All language tag values are guaranteed to be
// well-formed.
type Tag struct {
// NOTE: exported tags will become part of the public API.
language ID
locale ID
full fullTag // always a language.Tag for now.
}
const _und = 0
type fullTag interface {
IsRoot() bool
Parent() language.Tag
}
// Make a compact Tag from a fully specified internal language Tag.
func Make(t language.Tag) (tag Tag) {
if region := t.TypeForKey("rg"); len(region) == 6 && region[2:] == "zzzz" {
if r, err := language.ParseRegion(region[:2]); err == nil {
tFull := t
t, _ = t.SetTypeForKey("rg", "")
// TODO: should we not consider "va" for the language tag?
var exact1, exact2 bool
tag.language, exact1 = FromTag(t)
t.RegionID = r
tag.locale, exact2 = FromTag(t)
if !exact1 || !exact2 {
tag.full = tFull
}
return tag
}
}
lang, ok := FromTag(t)
tag.language = lang
tag.locale = lang
if !ok {
tag.full = t
}
return tag
}
// Tag returns an internal language Tag version of this tag.
func (t Tag) Tag() language.Tag {
if t.full != nil {
return t.full.(language.Tag)
}
tag := t.language.Tag()
if t.language != t.locale {
loc := t.locale.Tag()
tag, _ = tag.SetTypeForKey("rg", strings.ToLower(loc.RegionID.String())+"zzzz")
}
return tag
}
// IsCompact reports whether this tag is fully defined in terms of ID.
func (t *Tag) IsCompact() bool {
return t.full == nil
}
// MayHaveVariants reports whether a tag may have variants. If it returns false
// it is guaranteed the tag does not have variants.
func (t Tag) MayHaveVariants() bool {
return t.full != nil || int(t.language) >= len(coreTags)
}
// MayHaveExtensions reports whether a tag may have extensions. If it returns
// false it is guaranteed the tag does not have them.
func (t Tag) MayHaveExtensions() bool {
return t.full != nil ||
int(t.language) >= len(coreTags) ||
t.language != t.locale
}
// IsRoot returns true if t is equal to language "und".
func (t Tag) IsRoot() bool {
if t.full != nil {
return t.full.IsRoot()
}
return t.language == _und
}
// Parent returns the CLDR parent of t. In CLDR, missing fields in data for a
// specific language are substituted with fields from the parent language.
// The parent for a language may change for newer versions of CLDR.
func (t Tag) Parent() Tag {
if t.full != nil {
return Make(t.full.Parent())
}
if t.language != t.locale {
// Simulate stripping -u-rg-xxxxxx
return Tag{language: t.language, locale: t.language}
}
// TODO: use parent lookup table once cycle from internal package is
// removed. Probably by internalizing the table and declaring this fast
// enough.
// lang := compactID(internal.Parent(uint16(t.language)))
lang, _ := FromTag(t.language.Tag().Parent())
return Tag{language: lang, locale: lang}
}
// nextToken returns token t and the rest of the string.
func nextToken(s string) (t, tail string) {
p := strings.Index(s[1:], "-")
if p == -1 {
return s[1:], ""
}
p++
return s[1:p], s[p:]
}
// LanguageID returns an index, where 0 <= index < NumCompactTags, for tags
// for which data exists in the text repository.The index will change over time
// and should not be stored in persistent storage. If t does not match a compact
// index, exact will be false and the compact index will be returned for the
// first match after repeatedly taking the Parent of t.
func LanguageID(t Tag) (id ID, exact bool) {
return t.language, t.full == nil
}
// RegionalID returns the ID for the regional variant of this tag. This index is
// used to indicate region-specific overrides, such as default currency, default
// calendar and week data, default time cycle, and default measurement system
// and unit preferences.
//
// For instance, the tag en-GB-u-rg-uszzzz specifies British English with US
// settings for currency, number formatting, etc. The CompactIndex for this tag
// will be that for en-GB, while the RegionalID will be the one corresponding to
// en-US.
func RegionalID(t Tag) (id ID, exact bool) {
return t.locale, t.full == nil
}
// LanguageTag returns t stripped of regional variant indicators.
//
// At the moment this means it is stripped of a regional and variant subtag "rg"
// and "va" in the "u" extension.
func (t Tag) LanguageTag() Tag {
if t.full == nil {
return Tag{language: t.language, locale: t.language}
}
tt := t.Tag()
tt.SetTypeForKey("rg", "")
tt.SetTypeForKey("va", "")
return Make(tt)
}
// RegionalTag returns the regional variant of the tag.
//
// At the moment this means that the region is set from the regional subtag
// "rg" in the "u" extension.
func (t Tag) RegionalTag() Tag {
rt := Tag{language: t.locale, locale: t.locale}
if t.full == nil {
return rt
}
b := language.Builder{}
tag := t.Tag()
// tag, _ = tag.SetTypeForKey("rg", "")
b.SetTag(t.locale.Tag())
if v := tag.Variants(); v != "" {
for _, v := range strings.Split(v, "-") {
b.AddVariant(v)
}
}
for _, e := range tag.Extensions() {
b.AddExt(e)
}
return t
}
// FromTag reports closest matching ID for an internal language Tag.
func FromTag(t language.Tag) (id ID, exact bool) {
// TODO: perhaps give more frequent tags a lower index.
// TODO: we could make the indexes stable. This will excluded some
// possibilities for optimization, so don't do this quite yet.
exact = true
b, s, r := t.Raw()
if t.HasString() {
if t.IsPrivateUse() {
// We have no entries for user-defined tags.
return 0, false
}
hasExtra := false
if t.HasVariants() {
if t.HasExtensions() {
build := language.Builder{}
build.SetTag(language.Tag{LangID: b, ScriptID: s, RegionID: r})
build.AddVariant(t.Variants())
exact = false
t = build.Make()
}
hasExtra = true
} else if _, ok := t.Extension('u'); ok {
// TODO: va may mean something else. Consider not considering it.
// Strip all but the 'va' entry.
old := t
variant := t.TypeForKey("va")
t = language.Tag{LangID: b, ScriptID: s, RegionID: r}
if variant != "" {
t, _ = t.SetTypeForKey("va", variant)
hasExtra = true
}
exact = old == t
} else {
exact = false
}
if hasExtra {
// We have some variants.
for i, s := range specialTags {
if s == t {
return ID(i + len(coreTags)), exact
}
}
exact = false
}
}
if x, ok := getCoreIndex(t); ok {
return x, exact
}
exact = false
if r != 0 && s == 0 {
// Deal with cases where an extra script is inserted for the region.
t, _ := t.Maximize()
if x, ok := getCoreIndex(t); ok {
return x, exact
}
}
for t = t.Parent(); t != root; t = t.Parent() {
// No variants specified: just compare core components.
// The key has the form lllssrrr, where l, s, and r are nibbles for
// respectively the langID, scriptID, and regionID.
if x, ok := getCoreIndex(t); ok {
return x, exact
}
}
return 0, exact
}
var root = language.Tag{}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compact/language_test.go
+236
View File
@@ -0,0 +1,236 @@
// 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 compact
import (
"reflect"
"testing"
"golang.org/x/text/internal/language"
)
func mustParse(s string) Tag {
t, err := language.Parse(s)
if err != nil {
panic(err)
}
return Make(t)
}
func TestTagSize(t *testing.T) {
id := Tag{}
typ := reflect.TypeOf(id)
if typ.Size() > 24 {
t.Errorf("size of Tag was %d; want 24", typ.Size())
}
}
func TestNoPublic(t *testing.T) {
noExportedField(t, reflect.TypeOf(Tag{}))
}
func noExportedField(t *testing.T, typ reflect.Type) {
for i := 0; i < typ.NumField(); i++ {
f := typ.Field(i)
if f.PkgPath == "" {
t.Errorf("Tag may not have exported fields, but has field %q", f.Name)
}
if f.Anonymous {
noExportedField(t, f.Type)
}
}
}
func TestEquality(t *testing.T) {
for i, tt := range parseTests() {
s := tt.in
tag := mk(s)
t1 := mustParse(tag.Tag().String())
if tag != t1 {
t.Errorf("%d:%s: equality test 1 failed\n got: %#v\nwant: %#v)", i, s, t1, tag)
}
}
}
type compactTest struct {
tag string
index ID
ok bool
}
var compactTests = []compactTest{
// TODO: these values will change with each CLDR update. This issue
// will be solved if we decide to fix the indexes.
{"und", undIndex, true},
{"ca-ES-valencia", caESvalenciaIndex, true},
{"ca-ES-valencia-u-va-posix", caESvalenciaIndex, false},
{"ca-ES-valencia-u-co-phonebk", caESvalenciaIndex, false},
{"ca-ES-valencia-u-co-phonebk-va-posix", caESvalenciaIndex, false},
{"x-klingon", 0, false},
{"en-US", enUSIndex, true},
{"en-US-u-va-posix", enUSuvaposixIndex, true},
{"en", enIndex, true},
{"en-u-co-phonebk", enIndex, false},
{"en-001", en001Index, true},
{"zh-Hant-HK", zhHantHKIndex, true},
{"zh-HK", zhHantHKIndex, false}, // maximized to zh-Hant-HK
{"nl-Beng", 0, false}, // parent skips script
{"nl-NO", nlIndex, false}, // region is ignored
{"nl-Latn-NO", nlIndex, false},
{"nl-Latn-NO-u-co-phonebk", nlIndex, false},
{"nl-Latn-NO-valencia", nlIndex, false},
{"nl-Latn-NO-oxendict", nlIndex, false},
{"sh", shIndex, true}, // From plural rules.
}
func TestLanguageID(t *testing.T) {
tests := append(compactTests, []compactTest{
{"en-GB", enGBIndex, true},
{"en-GB-u-rg-uszzzz", enGBIndex, true},
{"en-GB-u-rg-USZZZZ", enGBIndex, true},
{"en-GB-u-rg-uszzzz-va-posix", enGBIndex, false},
{"en-GB-u-co-phonebk-rg-uszzzz", enGBIndex, false},
// Invalid region specifications are ignored.
{"en-GB-u-rg-usz-va-posix", enGBIndex, false},
{"en-GB-u-co-phonebk-rg-usz", enGBIndex, false},
}...)
for _, tt := range tests {
x, ok := LanguageID(mustParse(tt.tag))
if ID(x) != tt.index || ok != tt.ok {
t.Errorf("%s: got %d, %v; want %d %v", tt.tag, x, ok, tt.index, tt.ok)
}
}
}
func TestRegionalID(t *testing.T) {
tests := append(compactTests, []compactTest{
{"en-GB", enGBIndex, true},
{"en-GB-u-rg-uszzzz", enUSIndex, true},
{"en-GB-u-rg-USZZZZ", enUSIndex, true},
// TODO: use different exact values for language and regional tag?
{"en-GB-u-rg-uszzzz-va-posix", enUSuvaposixIndex, false},
{"en-GB-u-co-phonebk-rg-uszzzz-va-posix", enUSuvaposixIndex, false},
{"en-GB-u-co-phonebk-rg-uszzzz", enUSIndex, false},
// Invalid region specifications are ignored.
{"en-GB-u-rg-usz-va-posix", enGBIndex, false},
{"en-GB-u-co-phonebk-rg-usz", enGBIndex, false},
}...)
for _, tt := range tests {
x, ok := RegionalID(mustParse(tt.tag))
if ID(x) != tt.index || ok != tt.ok {
t.Errorf("%s: got %d, %v; want %d %v", tt.tag, x, ok, tt.index, tt.ok)
}
}
}
func TestParent(t *testing.T) {
tests := []struct{ in, out string }{
// Strip variants and extensions first
{"de-u-co-phonebk", "de"},
{"de-1994", "de"},
{"de-Latn-1994", "de"}, // remove superfluous script.
// Ensure the canonical Tag for an entry is in the chain for base-script
// pairs.
{"zh-Hans", "zh"},
// Skip the script if it is the maximized version. CLDR files for the
// skipped tag are always empty.
{"zh-Hans-TW", "zh"},
{"zh-Hans-CN", "zh"},
// Insert the script if the maximized script is not the same as the
// maximized script of the base language.
{"zh-TW", "zh-Hant"},
{"zh-HK", "zh-Hant"},
{"zh-Hant-TW", "zh-Hant"},
{"zh-Hant-HK", "zh-Hant"},
// Non-default script skips to und.
// CLDR
{"az-Cyrl", "und"},
{"bs-Cyrl", "und"},
{"en-Dsrt", "und"},
{"ha-Arab", "und"},
{"mn-Mong", "und"},
{"pa-Arab", "und"},
{"shi-Latn", "und"},
{"sr-Latn", "und"},
{"uz-Arab", "und"},
{"uz-Cyrl", "und"},
{"vai-Latn", "und"},
{"zh-Hant", "und"},
// extra
{"nl-Cyrl", "und"},
// World english inherits from en-001.
{"en-150", "en-001"},
{"en-AU", "en-001"},
{"en-BE", "en-001"},
{"en-GG", "en-001"},
{"en-GI", "en-001"},
{"en-HK", "en-001"},
{"en-IE", "en-001"},
{"en-IM", "en-001"},
{"en-IN", "en-001"},
{"en-JE", "en-001"},
{"en-MT", "en-001"},
{"en-NZ", "en-001"},
{"en-PK", "en-001"},
{"en-SG", "en-001"},
// Spanish in Latin-American countries have es-419 as parent.
{"es-AR", "es-419"},
{"es-BO", "es-419"},
{"es-CL", "es-419"},
{"es-CO", "es-419"},
{"es-CR", "es-419"},
{"es-CU", "es-419"},
{"es-DO", "es-419"},
{"es-EC", "es-419"},
{"es-GT", "es-419"},
{"es-HN", "es-419"},
{"es-MX", "es-419"},
{"es-NI", "es-419"},
{"es-PA", "es-419"},
{"es-PE", "es-419"},
{"es-PR", "es-419"},
{"es-PY", "es-419"},
{"es-SV", "es-419"},
{"es-US", "es-419"},
{"es-UY", "es-419"},
{"es-VE", "es-419"},
// exceptions (according to CLDR)
{"es-CW", "es"},
// Inherit from pt-PT, instead of pt for these countries.
{"pt-AO", "pt-PT"},
{"pt-CV", "pt-PT"},
{"pt-GW", "pt-PT"},
{"pt-MO", "pt-PT"},
{"pt-MZ", "pt-PT"},
{"pt-ST", "pt-PT"},
{"pt-TL", "pt-PT"},
{"en-GB-u-co-phonebk-rg-uszzzz", "en-GB"},
{"en-GB-u-rg-uszzzz", "en-GB"},
{"en-US-u-va-posix", "en-US"},
// Difference between language and regional tag.
{"ca-ES-valencia", "ca-ES"},
{"ca-ES-valencia-u-rg-ptzzzz", "ca-ES"}, // t.full != nil
{"en-US-u-va-variant", "en-US"},
{"en-u-va-variant", "en"}, // t.full != nil
{"en-u-rg-gbzzzz", "en"},
{"en-US-u-rg-gbzzzz", "en-US"},
{"nl-US-u-rg-gbzzzz", "nl-US"}, // t.full != nil
}
for _, tt := range tests {
tag := mustParse(tt.in)
if p := mustParse(tt.out); p != tag.Parent() {
t.Errorf("%s: was %v; want %v", tt.in, tag.Parent(), p)
}
}
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compact/parents.go
+120
View File
@@ -0,0 +1,120 @@
// Code generated by running "go generate" in golang.org/x/text. DO NOT EDIT.
package compact
// parents maps a compact index of a tag to the compact index of the parent of
// this tag.
var parents = []ID{ // 775 elements
// Entry 0 - 3F
0x0000, 0x0000, 0x0001, 0x0001, 0x0000, 0x0004, 0x0000, 0x0006,
0x0000, 0x0008, 0x0000, 0x000a, 0x000a, 0x000a, 0x000a, 0x000a,
0x000a, 0x000a, 0x000a, 0x000a, 0x000a, 0x000a, 0x000a, 0x000a,
0x000a, 0x000a, 0x000a, 0x000a, 0x000a, 0x000a, 0x000a, 0x000a,
0x000a, 0x000a, 0x000a, 0x000a, 0x000a, 0x000a, 0x000a, 0x0000,
0x0000, 0x0028, 0x0000, 0x002a, 0x0000, 0x002c, 0x0000, 0x0000,
0x002f, 0x002e, 0x002e, 0x0000, 0x0033, 0x0000, 0x0035, 0x0000,
0x0037, 0x0000, 0x0039, 0x0000, 0x003b, 0x0000, 0x0000, 0x003e,
// Entry 40 - 7F
0x0000, 0x0040, 0x0040, 0x0000, 0x0043, 0x0043, 0x0000, 0x0046,
0x0000, 0x0048, 0x0000, 0x0000, 0x004b, 0x004a, 0x004a, 0x0000,
0x004f, 0x004f, 0x004f, 0x004f, 0x0000, 0x0054, 0x0054, 0x0000,
0x0057, 0x0000, 0x0059, 0x0000, 0x005b, 0x0000, 0x005d, 0x005d,
0x0000, 0x0060, 0x0000, 0x0062, 0x0000, 0x0064, 0x0000, 0x0066,
0x0066, 0x0000, 0x0069, 0x0000, 0x006b, 0x006b, 0x006b, 0x006b,
0x006b, 0x006b, 0x006b, 0x0000, 0x0073, 0x0000, 0x0075, 0x0000,
0x0077, 0x0000, 0x0000, 0x007a, 0x0000, 0x007c, 0x0000, 0x007e,
// Entry 80 - BF
0x0000, 0x0080, 0x0080, 0x0000, 0x0083, 0x0083, 0x0000, 0x0086,
0x0087, 0x0087, 0x0087, 0x0086, 0x0088, 0x0087, 0x0087, 0x0087,
0x0086, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0088,
0x0087, 0x0087, 0x0087, 0x0087, 0x0088, 0x0087, 0x0088, 0x0087,
0x0087, 0x0088, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087,
0x0087, 0x0087, 0x0087, 0x0086, 0x0087, 0x0087, 0x0087, 0x0087,
0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087,
0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0086, 0x0087, 0x0086,
// Entry C0 - FF
0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087,
0x0088, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087,
0x0086, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0088, 0x0087,
0x0087, 0x0088, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087,
0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0086, 0x0086, 0x0087,
0x0087, 0x0086, 0x0087, 0x0087, 0x0087, 0x0087, 0x0087, 0x0000,
0x00ef, 0x0000, 0x00f1, 0x00f2, 0x00f2, 0x00f2, 0x00f2, 0x00f2,
0x00f2, 0x00f2, 0x00f2, 0x00f2, 0x00f1, 0x00f2, 0x00f1, 0x00f1,
// Entry 100 - 13F
0x00f2, 0x00f2, 0x00f1, 0x00f2, 0x00f2, 0x00f2, 0x00f2, 0x00f1,
0x00f2, 0x00f2, 0x00f2, 0x00f2, 0x00f2, 0x00f2, 0x0000, 0x010e,
0x0000, 0x0110, 0x0000, 0x0112, 0x0000, 0x0114, 0x0114, 0x0000,
0x0117, 0x0117, 0x0117, 0x0117, 0x0000, 0x011c, 0x0000, 0x011e,
0x0000, 0x0120, 0x0120, 0x0000, 0x0123, 0x0123, 0x0123, 0x0123,
0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123,
0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123,
0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123,
// Entry 140 - 17F
0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123,
0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123, 0x0123,
0x0123, 0x0123, 0x0000, 0x0152, 0x0000, 0x0154, 0x0000, 0x0156,
0x0000, 0x0158, 0x0000, 0x015a, 0x0000, 0x015c, 0x015c, 0x015c,
0x0000, 0x0160, 0x0000, 0x0000, 0x0163, 0x0000, 0x0165, 0x0000,
0x0167, 0x0167, 0x0167, 0x0000, 0x016b, 0x0000, 0x016d, 0x0000,
0x016f, 0x0000, 0x0171, 0x0171, 0x0000, 0x0174, 0x0000, 0x0176,
0x0000, 0x0178, 0x0000, 0x017a, 0x0000, 0x017c, 0x0000, 0x017e,
// Entry 180 - 1BF
0x0000, 0x0000, 0x0000, 0x0182, 0x0000, 0x0184, 0x0184, 0x0184,
0x0184, 0x0000, 0x0000, 0x0000, 0x018b, 0x0000, 0x0000, 0x018e,
0x0000, 0x0000, 0x0191, 0x0000, 0x0000, 0x0000, 0x0195, 0x0000,
0x0197, 0x0000, 0x0000, 0x019a, 0x0000, 0x0000, 0x019d, 0x0000,
0x019f, 0x0000, 0x01a1, 0x0000, 0x01a3, 0x0000, 0x01a5, 0x0000,
0x01a7, 0x0000, 0x01a9, 0x0000, 0x01ab, 0x0000, 0x01ad, 0x0000,
0x01af, 0x0000, 0x01b1, 0x01b1, 0x0000, 0x01b4, 0x0000, 0x01b6,
0x0000, 0x01b8, 0x0000, 0x01ba, 0x0000, 0x01bc, 0x0000, 0x0000,
// Entry 1C0 - 1FF
0x01bf, 0x0000, 0x01c1, 0x0000, 0x01c3, 0x0000, 0x01c5, 0x0000,
0x01c7, 0x0000, 0x01c9, 0x0000, 0x01cb, 0x01cb, 0x01cb, 0x01cb,
0x0000, 0x01d0, 0x0000, 0x01d2, 0x01d2, 0x0000, 0x01d5, 0x0000,
0x01d7, 0x0000, 0x01d9, 0x0000, 0x01db, 0x0000, 0x01dd, 0x0000,
0x01df, 0x01df, 0x0000, 0x01e2, 0x0000, 0x01e4, 0x0000, 0x01e6,
0x0000, 0x01e8, 0x0000, 0x01ea, 0x0000, 0x01ec, 0x0000, 0x01ee,
0x0000, 0x01f0, 0x0000, 0x0000, 0x01f3, 0x0000, 0x01f5, 0x01f5,
0x01f5, 0x0000, 0x01f9, 0x0000, 0x01fb, 0x0000, 0x01fd, 0x0000,
// Entry 200 - 23F
0x01ff, 0x0000, 0x0000, 0x0202, 0x0000, 0x0204, 0x0204, 0x0000,
0x0207, 0x0000, 0x0209, 0x0209, 0x0000, 0x020c, 0x020c, 0x0000,
0x020f, 0x020f, 0x020f, 0x020f, 0x020f, 0x020f, 0x020f, 0x0000,
0x0217, 0x0000, 0x0219, 0x0000, 0x021b, 0x0000, 0x0000, 0x0000,
0x0000, 0x0000, 0x0221, 0x0000, 0x0000, 0x0224, 0x0000, 0x0226,
0x0226, 0x0000, 0x0229, 0x0000, 0x022b, 0x022b, 0x0000, 0x0000,
0x022f, 0x022e, 0x022e, 0x0000, 0x0000, 0x0234, 0x0000, 0x0236,
0x0000, 0x0238, 0x0000, 0x0244, 0x023a, 0x0244, 0x0244, 0x0244,
// Entry 240 - 27F
0x0244, 0x0244, 0x0244, 0x0244, 0x023a, 0x0244, 0x0244, 0x0000,
0x0247, 0x0247, 0x0247, 0x0000, 0x024b, 0x0000, 0x024d, 0x0000,
0x024f, 0x024f, 0x0000, 0x0252, 0x0000, 0x0254, 0x0254, 0x0254,
0x0254, 0x0254, 0x0254, 0x0000, 0x025b, 0x0000, 0x025d, 0x0000,
0x025f, 0x0000, 0x0261, 0x0000, 0x0263, 0x0000, 0x0265, 0x0000,
0x0000, 0x0268, 0x0268, 0x0268, 0x0000, 0x026c, 0x0000, 0x026e,
0x0000, 0x0270, 0x0000, 0x0000, 0x0000, 0x0274, 0x0273, 0x0273,
0x0000, 0x0278, 0x0000, 0x027a, 0x0000, 0x027c, 0x0000, 0x0000,
// Entry 280 - 2BF
0x0000, 0x0000, 0x0281, 0x0000, 0x0000, 0x0284, 0x0000, 0x0286,
0x0286, 0x0286, 0x0286, 0x0000, 0x028b, 0x028b, 0x028b, 0x0000,
0x028f, 0x028f, 0x028f, 0x028f, 0x028f, 0x0000, 0x0295, 0x0295,
0x0295, 0x0295, 0x0000, 0x0000, 0x0000, 0x0000, 0x029d, 0x029d,
0x029d, 0x0000, 0x02a1, 0x02a1, 0x02a1, 0x02a1, 0x0000, 0x0000,
0x02a7, 0x02a7, 0x02a7, 0x02a7, 0x0000, 0x02ac, 0x0000, 0x02ae,
0x02ae, 0x0000, 0x02b1, 0x0000, 0x02b3, 0x0000, 0x02b5, 0x02b5,
0x0000, 0x0000, 0x02b9, 0x0000, 0x0000, 0x0000, 0x02bd, 0x0000,
// Entry 2C0 - 2FF
0x02bf, 0x02bf, 0x0000, 0x0000, 0x02c3, 0x0000, 0x02c5, 0x0000,
0x02c7, 0x0000, 0x02c9, 0x0000, 0x02cb, 0x0000, 0x02cd, 0x02cd,
0x0000, 0x0000, 0x02d1, 0x0000, 0x02d3, 0x02d0, 0x02d0, 0x0000,
0x0000, 0x02d8, 0x02d7, 0x02d7, 0x0000, 0x0000, 0x02dd, 0x0000,
0x02df, 0x0000, 0x02e1, 0x0000, 0x0000, 0x02e4, 0x0000, 0x02e6,
0x0000, 0x0000, 0x02e9, 0x0000, 0x02eb, 0x0000, 0x02ed, 0x0000,
0x02ef, 0x02ef, 0x0000, 0x0000, 0x02f3, 0x02f2, 0x02f2, 0x0000,
0x02f7, 0x0000, 0x02f9, 0x02f9, 0x02f9, 0x02f9, 0x02f9, 0x0000,
// Entry 300 - 33F
0x02ff, 0x0300, 0x02ff, 0x0000, 0x0303, 0x0051, 0x00e6,
} // Size: 1574 bytes
// Total table size 1574 bytes (1KiB); checksum: 895AAF0B
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compact/parse_test.go
+201
View File
@@ -0,0 +1,201 @@
// 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 compact
import (
"strings"
"testing"
"golang.org/x/text/internal/language"
)
var errSyntax = language.ErrSyntax
type parseTest struct {
i int // the index of this test
in string
lang, script, region string
variants, ext string
extList []string // only used when more than one extension is present
invalid bool
rewrite bool // special rewrite not handled by parseTag
changed bool // string needed to be reformatted
}
func parseTests() []parseTest {
tests := []parseTest{
{in: "root", lang: "und"},
{in: "und", lang: "und"},
{in: "en", lang: "en"},
{in: "en-US-u-va-posix", lang: "en", region: "US", ext: "u-va-posix"},
{in: "ca-ES-valencia", lang: "ca", region: "ES", variants: "valencia"},
{in: "en-US-u-rg-gbzzzz", lang: "en", region: "US", ext: "u-rg-gbzzzz"},
{in: "xy", lang: "und", invalid: true},
{in: "en-ZY", lang: "en", invalid: true},
{in: "gsw", lang: "gsw"},
{in: "sr_Latn", lang: "sr", script: "Latn"},
{in: "af-Arab", lang: "af", script: "Arab"},
{in: "nl-BE", lang: "nl", region: "BE"},
{in: "es-419", lang: "es", region: "419"},
{in: "und-001", lang: "und", region: "001"},
{in: "de-latn-be", lang: "de", script: "Latn", region: "BE"},
// Variants
{in: "de-1901", lang: "de", variants: "1901"},
// Accept with unsuppressed script.
{in: "de-Latn-1901", lang: "de", script: "Latn", variants: "1901"},
// Specialized.
{in: "sl-rozaj", lang: "sl", variants: "rozaj"},
{in: "sl-rozaj-lipaw", lang: "sl", variants: "rozaj-lipaw"},
{in: "sl-rozaj-biske", lang: "sl", variants: "rozaj-biske"},
{in: "sl-rozaj-biske-1994", lang: "sl", variants: "rozaj-biske-1994"},
{in: "sl-rozaj-1994", lang: "sl", variants: "rozaj-1994"},
// Maximum number of variants while adhering to prefix rules.
{in: "sl-rozaj-biske-1994-alalc97-fonipa-fonupa-fonxsamp", lang: "sl", variants: "rozaj-biske-1994-alalc97-fonipa-fonupa-fonxsamp"},
// Sorting.
{in: "sl-1994-biske-rozaj", lang: "sl", variants: "rozaj-biske-1994", changed: true},
{in: "sl-rozaj-biske-1994-alalc97-fonupa-fonipa-fonxsamp", lang: "sl", variants: "rozaj-biske-1994-alalc97-fonipa-fonupa-fonxsamp", changed: true},
{in: "nl-fonxsamp-alalc97-fonipa-fonupa", lang: "nl", variants: "alalc97-fonipa-fonupa-fonxsamp", changed: true},
// Duplicates variants are removed, but not an error.
{in: "nl-fonupa-fonupa", lang: "nl", variants: "fonupa"},
// Variants that do not have correct prefixes. We still accept these.
{in: "de-Cyrl-1901", lang: "de", script: "Cyrl", variants: "1901"},
{in: "sl-rozaj-lipaw-1994", lang: "sl", variants: "rozaj-lipaw-1994"},
{in: "sl-1994-biske-rozaj-1994-biske-rozaj", lang: "sl", variants: "rozaj-biske-1994", changed: true},
{in: "de-Cyrl-1901", lang: "de", script: "Cyrl", variants: "1901"},
// Invalid variant.
{in: "de-1902", lang: "de", variants: "", invalid: true},
{in: "EN_CYRL", lang: "en", script: "Cyrl"},
// private use and extensions
{in: "x-a-b-c-d", ext: "x-a-b-c-d"},
{in: "x_A.-B-C_D", ext: "x-b-c-d", invalid: true, changed: true},
{in: "x-aa-bbbb-cccccccc-d", ext: "x-aa-bbbb-cccccccc-d"},
{in: "en-c_cc-b-bbb-a-aaa", lang: "en", changed: true, extList: []string{"a-aaa", "b-bbb", "c-cc"}},
{in: "en-x_cc-b-bbb-a-aaa", lang: "en", ext: "x-cc-b-bbb-a-aaa", changed: true},
{in: "en-c_cc-b-bbb-a-aaa-x-x", lang: "en", changed: true, extList: []string{"a-aaa", "b-bbb", "c-cc", "x-x"}},
{in: "en-v-c", lang: "en", ext: "", invalid: true},
{in: "en-v-abcdefghi", lang: "en", ext: "", invalid: true},
{in: "en-v-abc-x", lang: "en", ext: "v-abc", invalid: true},
{in: "en-v-abc-x-", lang: "en", ext: "v-abc", invalid: true},
{in: "en-v-abc-w-x-xx", lang: "en", extList: []string{"v-abc", "x-xx"}, invalid: true, changed: true},
{in: "en-v-abc-w-y-yx", lang: "en", extList: []string{"v-abc", "y-yx"}, invalid: true, changed: true},
{in: "en-v-c-abc", lang: "en", ext: "c-abc", invalid: true, changed: true},
{in: "en-v-w-abc", lang: "en", ext: "w-abc", invalid: true, changed: true},
{in: "en-v-x-abc", lang: "en", ext: "x-abc", invalid: true, changed: true},
{in: "en-v-x-a", lang: "en", ext: "x-a", invalid: true, changed: true},
{in: "en-9-aa-0-aa-z-bb-x-a", lang: "en", extList: []string{"0-aa", "9-aa", "z-bb", "x-a"}, changed: true},
{in: "en-u-c", lang: "en", ext: "", invalid: true},
{in: "en-u-co-phonebk", lang: "en", ext: "u-co-phonebk"},
{in: "en-u-co-phonebk-ca", lang: "en", ext: "u-co-phonebk", invalid: true},
{in: "en-u-nu-arabic-co-phonebk-ca", lang: "en", ext: "u-co-phonebk-nu-arabic", invalid: true, changed: true},
{in: "en-u-nu-arabic-co-phonebk-ca-x", lang: "en", ext: "u-co-phonebk-nu-arabic", invalid: true, changed: true},
{in: "en-u-nu-arabic-co-phonebk-ca-s", lang: "en", ext: "u-co-phonebk-nu-arabic", invalid: true, changed: true},
{in: "en-u-nu-arabic-co-phonebk-ca-a12345678", lang: "en", ext: "u-co-phonebk-nu-arabic", invalid: true, changed: true},
{in: "en-u-co-phonebook", lang: "en", ext: "", invalid: true},
{in: "en-u-co-phonebook-cu-xau", lang: "en", ext: "u-cu-xau", invalid: true, changed: true},
{in: "en-Cyrl-u-co-phonebk", lang: "en", script: "Cyrl", ext: "u-co-phonebk"},
{in: "en-US-u-co-phonebk", lang: "en", region: "US", ext: "u-co-phonebk"},
{in: "en-US-u-co-phonebk-cu-xau", lang: "en", region: "US", ext: "u-co-phonebk-cu-xau"},
{in: "en-scotland-u-co-phonebk", lang: "en", variants: "scotland", ext: "u-co-phonebk"},
{in: "en-u-cu-xua-co-phonebk", lang: "en", ext: "u-co-phonebk-cu-xua", changed: true},
{in: "en-u-def-abc-cu-xua-co-phonebk", lang: "en", ext: "u-abc-def-co-phonebk-cu-xua", changed: true},
{in: "en-u-def-abc", lang: "en", ext: "u-abc-def", changed: true},
{in: "en-u-cu-xua-co-phonebk-a-cd", lang: "en", extList: []string{"a-cd", "u-co-phonebk-cu-xua"}, changed: true},
// Invalid "u" extension. Drop invalid parts.
{in: "en-u-cu-co-phonebk", lang: "en", extList: []string{"u-co-phonebk"}, invalid: true, changed: true},
{in: "en-u-cu-xau-co", lang: "en", extList: []string{"u-cu-xau"}, invalid: true},
// We allow duplicate keys as the LDML spec does not explicitly prohibit it.
// TODO: Consider eliminating duplicates and returning an error.
{in: "en-u-cu-xau-co-phonebk-cu-xau", lang: "en", ext: "u-co-phonebk-cu-xau", changed: true},
{in: "en-t-en-Cyrl-NL-fonipa", lang: "en", ext: "t-en-cyrl-nl-fonipa", changed: true},
{in: "en-t-en-Cyrl-NL-fonipa-t0-abc-def", lang: "en", ext: "t-en-cyrl-nl-fonipa-t0-abc-def", changed: true},
{in: "en-t-t0-abcd", lang: "en", ext: "t-t0-abcd"},
// Not necessary to have changed here.
{in: "en-t-nl-abcd", lang: "en", ext: "t-nl", invalid: true},
{in: "en-t-nl-latn", lang: "en", ext: "t-nl-latn"},
{in: "en-t-t0-abcd-x-a", lang: "en", extList: []string{"t-t0-abcd", "x-a"}},
{in: "en_t_pt_MLt", lang: "en", ext: "t-pt-mlt", changed: true},
{in: "en-t-fr-est", lang: "en", ext: "t-fr-est", changed: false},
{in: "fr-est", lang: "et", changed: true},
{in: "fr-est-t-fr-est", lang: "et", ext: "t-fr-est", changed: true},
{in: "fr-est-Cyrl", lang: "et", script: "Cyrl", changed: true},
// invalid
{in: "", lang: "und", invalid: true},
{in: "-", lang: "und", invalid: true},
{in: "x", lang: "und", invalid: true},
{in: "x-", lang: "und", invalid: true},
{in: "x--", lang: "und", invalid: true},
{in: "a-a-b-c-d", lang: "und", invalid: true},
{in: "en-", lang: "en", invalid: true},
{in: "enne-", lang: "und", invalid: true},
{in: "en.", lang: "und", invalid: true},
{in: "en.-latn", lang: "und", invalid: true},
{in: "en.-en", lang: "en", invalid: true},
{in: "x-a-tooManyChars-c-d", ext: "x-a-c-d", invalid: true, changed: true},
{in: "a-tooManyChars-c-d", lang: "und", invalid: true},
// TODO: check key-value validity
// { in: "en-u-cu-xd", lang: "en", ext: "u-cu-xd", invalid: true },
{in: "en-t-abcd", lang: "en", invalid: true},
{in: "en-Latn-US-en", lang: "en", script: "Latn", region: "US", invalid: true},
// rewrites (more tests in TestGrandfathered)
{in: "zh-min-nan", lang: "nan"},
{in: "zh-yue", lang: "yue"},
{in: "zh-xiang", lang: "hsn", rewrite: true},
{in: "zh-guoyu", lang: "cmn", rewrite: true},
{in: "iw", lang: "iw"},
{in: "sgn-BE-FR", lang: "sfb", rewrite: true},
{in: "i-klingon", lang: "tlh", rewrite: true},
}
for i, tt := range tests {
tests[i].i = i
if tt.extList != nil {
tests[i].ext = strings.Join(tt.extList, "-")
}
if tt.ext != "" && tt.extList == nil {
tests[i].extList = []string{tt.ext}
}
}
return tests
}
// partChecks runs checks for each part by calling the function returned by f.
func partChecks(t *testing.T, f func(*parseTest) (Tag, bool)) {
for i, tt := range parseTests() {
tag, skip := f(&tt)
if skip {
continue
}
if l, _ := language.ParseBase(tt.lang); l != tag.Tag().LangID {
t.Errorf("%d: lang was %q; want %q", i, tag.Tag().LangID, l)
}
if sc, _ := language.ParseScript(tt.script); sc != tag.Tag().ScriptID {
t.Errorf("%d: script was %q; want %q", i, tag.Tag().ScriptID, sc)
}
if r, _ := language.ParseRegion(tt.region); r != tag.Tag().RegionID {
t.Errorf("%d: region was %q; want %q", i, tag.Tag().RegionID, r)
}
v := tag.Tag().Variants()
if v != "" {
v = v[1:]
}
if v != tt.variants {
t.Errorf("%d: variants was %q; want %q", i, v, tt.variants)
}
if e := strings.Join(tag.Tag().Extensions(), "-"); e != tt.ext {
t.Errorf("%d: extensions were %q; want %q", i, e, tt.ext)
}
}
}
func mk(s string) Tag {
tag, _ := language.Parse(s)
return Make(tag)
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compact/tables.go
+1015
View File
File diff suppressed because it is too large Load Diff
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compact/tags.go
+91
View File
@@ -0,0 +1,91 @@
// 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 compact
var (
und = Tag{}
Und Tag = Tag{}
Afrikaans Tag = Tag{language: afIndex, locale: afIndex}
Amharic Tag = Tag{language: amIndex, locale: amIndex}
Arabic Tag = Tag{language: arIndex, locale: arIndex}
ModernStandardArabic Tag = Tag{language: ar001Index, locale: ar001Index}
Azerbaijani Tag = Tag{language: azIndex, locale: azIndex}
Bulgarian Tag = Tag{language: bgIndex, locale: bgIndex}
Bengali Tag = Tag{language: bnIndex, locale: bnIndex}
Catalan Tag = Tag{language: caIndex, locale: caIndex}
Czech Tag = Tag{language: csIndex, locale: csIndex}
Danish Tag = Tag{language: daIndex, locale: daIndex}
German Tag = Tag{language: deIndex, locale: deIndex}
Greek Tag = Tag{language: elIndex, locale: elIndex}
English Tag = Tag{language: enIndex, locale: enIndex}
AmericanEnglish Tag = Tag{language: enUSIndex, locale: enUSIndex}
BritishEnglish Tag = Tag{language: enGBIndex, locale: enGBIndex}
Spanish Tag = Tag{language: esIndex, locale: esIndex}
EuropeanSpanish Tag = Tag{language: esESIndex, locale: esESIndex}
LatinAmericanSpanish Tag = Tag{language: es419Index, locale: es419Index}
Estonian Tag = Tag{language: etIndex, locale: etIndex}
Persian Tag = Tag{language: faIndex, locale: faIndex}
Finnish Tag = Tag{language: fiIndex, locale: fiIndex}
Filipino Tag = Tag{language: filIndex, locale: filIndex}
French Tag = Tag{language: frIndex, locale: frIndex}
CanadianFrench Tag = Tag{language: frCAIndex, locale: frCAIndex}
Gujarati Tag = Tag{language: guIndex, locale: guIndex}
Hebrew Tag = Tag{language: heIndex, locale: heIndex}
Hindi Tag = Tag{language: hiIndex, locale: hiIndex}
Croatian Tag = Tag{language: hrIndex, locale: hrIndex}
Hungarian Tag = Tag{language: huIndex, locale: huIndex}
Armenian Tag = Tag{language: hyIndex, locale: hyIndex}
Indonesian Tag = Tag{language: idIndex, locale: idIndex}
Icelandic Tag = Tag{language: isIndex, locale: isIndex}
Italian Tag = Tag{language: itIndex, locale: itIndex}
Japanese Tag = Tag{language: jaIndex, locale: jaIndex}
Georgian Tag = Tag{language: kaIndex, locale: kaIndex}
Kazakh Tag = Tag{language: kkIndex, locale: kkIndex}
Khmer Tag = Tag{language: kmIndex, locale: kmIndex}
Kannada Tag = Tag{language: knIndex, locale: knIndex}
Korean Tag = Tag{language: koIndex, locale: koIndex}
Kirghiz Tag = Tag{language: kyIndex, locale: kyIndex}
Lao Tag = Tag{language: loIndex, locale: loIndex}
Lithuanian Tag = Tag{language: ltIndex, locale: ltIndex}
Latvian Tag = Tag{language: lvIndex, locale: lvIndex}
Macedonian Tag = Tag{language: mkIndex, locale: mkIndex}
Malayalam Tag = Tag{language: mlIndex, locale: mlIndex}
Mongolian Tag = Tag{language: mnIndex, locale: mnIndex}
Marathi Tag = Tag{language: mrIndex, locale: mrIndex}
Malay Tag = Tag{language: msIndex, locale: msIndex}
Burmese Tag = Tag{language: myIndex, locale: myIndex}
Nepali Tag = Tag{language: neIndex, locale: neIndex}
Dutch Tag = Tag{language: nlIndex, locale: nlIndex}
Norwegian Tag = Tag{language: noIndex, locale: noIndex}
Punjabi Tag = Tag{language: paIndex, locale: paIndex}
Polish Tag = Tag{language: plIndex, locale: plIndex}
Portuguese Tag = Tag{language: ptIndex, locale: ptIndex}
BrazilianPortuguese Tag = Tag{language: ptBRIndex, locale: ptBRIndex}
EuropeanPortuguese Tag = Tag{language: ptPTIndex, locale: ptPTIndex}
Romanian Tag = Tag{language: roIndex, locale: roIndex}
Russian Tag = Tag{language: ruIndex, locale: ruIndex}
Sinhala Tag = Tag{language: siIndex, locale: siIndex}
Slovak Tag = Tag{language: skIndex, locale: skIndex}
Slovenian Tag = Tag{language: slIndex, locale: slIndex}
Albanian Tag = Tag{language: sqIndex, locale: sqIndex}
Serbian Tag = Tag{language: srIndex, locale: srIndex}
SerbianLatin Tag = Tag{language: srLatnIndex, locale: srLatnIndex}
Swedish Tag = Tag{language: svIndex, locale: svIndex}
Swahili Tag = Tag{language: swIndex, locale: swIndex}
Tamil Tag = Tag{language: taIndex, locale: taIndex}
Telugu Tag = Tag{language: teIndex, locale: teIndex}
Thai Tag = Tag{language: thIndex, locale: thIndex}
Turkish Tag = Tag{language: trIndex, locale: trIndex}
Ukrainian Tag = Tag{language: ukIndex, locale: ukIndex}
Urdu Tag = Tag{language: urIndex, locale: urIndex}
Uzbek Tag = Tag{language: uzIndex, locale: uzIndex}
Vietnamese Tag = Tag{language: viIndex, locale: viIndex}
Chinese Tag = Tag{language: zhIndex, locale: zhIndex}
SimplifiedChinese Tag = Tag{language: zhHansIndex, locale: zhHansIndex}
TraditionalChinese Tag = Tag{language: zhHantIndex, locale: zhHantIndex}
Zulu Tag = Tag{language: zuIndex, locale: zuIndex}
)
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compose.go
+167
View File
@@ -0,0 +1,167 @@
// Copyright 2018 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 language
import (
"sort"
"strings"
)
// A Builder allows constructing a Tag from individual components.
// Its main user is Compose in the top-level language package.
type Builder struct {
Tag Tag
private string // the x extension
variants []string
extensions []string
}
// Make returns a new Tag from the current settings.
func (b *Builder) Make() Tag {
t := b.Tag
if len(b.extensions) > 0 || len(b.variants) > 0 {
sort.Sort(sortVariants(b.variants))
sort.Strings(b.extensions)
if b.private != "" {
b.extensions = append(b.extensions, b.private)
}
n := maxCoreSize + tokenLen(b.variants...) + tokenLen(b.extensions...)
buf := make([]byte, n)
p := t.genCoreBytes(buf)
t.pVariant = byte(p)
p += appendTokens(buf[p:], b.variants...)
t.pExt = uint16(p)
p += appendTokens(buf[p:], b.extensions...)
t.str = string(buf[:p])
// We may not always need to remake the string, but when or when not
// to do so is rather tricky.
scan := makeScanner(buf[:p])
t, _ = parse(&scan, "")
return t
} else if b.private != "" {
t.str = b.private
t.RemakeString()
}
return t
}
// SetTag copies all the settings from a given Tag. Any previously set values
// are discarded.
func (b *Builder) SetTag(t Tag) {
b.Tag.LangID = t.LangID
b.Tag.RegionID = t.RegionID
b.Tag.ScriptID = t.ScriptID
// TODO: optimize
b.variants = b.variants[:0]
if variants := t.Variants(); variants != "" {
for _, vr := range strings.Split(variants[1:], "-") {
b.variants = append(b.variants, vr)
}
}
b.extensions, b.private = b.extensions[:0], ""
for _, e := range t.Extensions() {
b.AddExt(e)
}
}
// AddExt adds extension e to the tag. e must be a valid extension as returned
// by Tag.Extension. If the extension already exists, it will be discarded,
// except for a -u extension, where non-existing key-type pairs will added.
func (b *Builder) AddExt(e string) {
if e[0] == 'x' {
if b.private == "" {
b.private = e
}
return
}
for i, s := range b.extensions {
if s[0] == e[0] {
if e[0] == 'u' {
b.extensions[i] += e[1:]
}
return
}
}
b.extensions = append(b.extensions, e)
}
// SetExt sets the extension e to the tag. e must be a valid extension as
// returned by Tag.Extension. If the extension already exists, it will be
// overwritten, except for a -u extension, where the individual key-type pairs
// will be set.
func (b *Builder) SetExt(e string) {
if e[0] == 'x' {
b.private = e
return
}
for i, s := range b.extensions {
if s[0] == e[0] {
if e[0] == 'u' {
b.extensions[i] = e + s[1:]
} else {
b.extensions[i] = e
}
return
}
}
b.extensions = append(b.extensions, e)
}
// AddVariant adds any number of variants.
func (b *Builder) AddVariant(v ...string) {
for _, v := range v {
if v != "" {
b.variants = append(b.variants, v)
}
}
}
// ClearVariants removes any variants previously added, including those
// copied from a Tag in SetTag.
func (b *Builder) ClearVariants() {
b.variants = b.variants[:0]
}
// ClearExtensions removes any extensions previously added, including those
// copied from a Tag in SetTag.
func (b *Builder) ClearExtensions() {
b.private = ""
b.extensions = b.extensions[:0]
}
func tokenLen(token ...string) (n int) {
for _, t := range token {
n += len(t) + 1
}
return
}
func appendTokens(b []byte, token ...string) int {
p := 0
for _, t := range token {
b[p] = '-'
copy(b[p+1:], t)
p += 1 + len(t)
}
return p
}
type sortVariants []string
func (s sortVariants) Len() int {
return len(s)
}
func (s sortVariants) Swap(i, j int) {
s[j], s[i] = s[i], s[j]
}
func (s sortVariants) Less(i, j int) bool {
return variantIndex[s[i]] < variantIndex[s[j]]
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/compose_test.go
+67
View File
@@ -0,0 +1,67 @@
// Copyright 2018 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 language
import (
"strings"
"testing"
)
func parseBase(s string) Language {
if s == "" {
return 0
}
return MustParseBase(s)
}
func parseScript(s string) Script {
if s == "" {
return 0
}
return MustParseScript(s)
}
func parseRegion(s string) Region {
if s == "" {
return 0
}
return MustParseRegion(s)
}
func TestBuilder(t *testing.T) {
partChecks(t, func(t *testing.T, tt *parseTest) (id Tag, skip bool) {
tag := Make(tt.in)
b := Builder{}
b.SetTag(Tag{
LangID: parseBase(tt.lang),
ScriptID: parseScript(tt.script),
RegionID: parseRegion(tt.region),
})
if tt.variants != "" {
b.AddVariant(strings.Split(tt.variants, "-")...)
}
for _, e := range tag.Extensions() {
b.AddExt(e)
}
got := b.Make()
if got != tag {
t.Errorf("%s: got %v; want %v", tt.in, got, tag)
}
return got, false
})
}
func TestSetTag(t *testing.T) {
partChecks(t, func(t *testing.T, tt *parseTest) (id Tag, skip bool) {
tag := Make(tt.in)
b := Builder{}
b.SetTag(tag)
got := b.Make()
if got != tag {
t.Errorf("%s: got %v; want %v", tt.in, got, tag)
}
return got, false
})
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/coverage.go
+28
View File
@@ -0,0 +1,28 @@
// 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 language
// BaseLanguages returns the list of all supported base languages. It generates
// the list by traversing the internal structures.
func BaseLanguages() []Language {
base := make([]Language, 0, NumLanguages)
for i := 0; i < langNoIndexOffset; i++ {
// We included "und" already for the value 0.
if i != nonCanonicalUnd {
base = append(base, Language(i))
}
}
i := langNoIndexOffset
for _, v := range langNoIndex {
for k := 0; k < 8; k++ {
if v&1 == 1 {
base = append(base, Language(i))
}
v >>= 1
i++
}
}
return base
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/gen.go
+1519
View File
File diff suppressed because it is too large Load Diff
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/gen_common.go
+20
View File
@@ -0,0 +1,20 @@
// 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.
//go:build ignore
package main
// This file contains code common to the maketables.go and the package code.
// AliasType is the type of an alias in AliasMap.
type AliasType int8
const (
Deprecated AliasType = iota
Macro
Legacy
AliasTypeUnknown AliasType = -1
)
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/language.go
+627
View File
@@ -0,0 +1,627 @@
// 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.
//go:generate go run gen.go gen_common.go -output tables.go
package language // import "golang.org/x/text/internal/language"
// TODO: Remove above NOTE after:
// - verifying that tables are dropped correctly (most notably matcher tables).
import (
"errors"
"fmt"
"strings"
)
const (
// maxCoreSize is the maximum size of a BCP 47 tag without variants and
// extensions. Equals max lang (3) + script (4) + max reg (3) + 2 dashes.
maxCoreSize = 12
// max99thPercentileSize is a somewhat arbitrary buffer size that presumably
// is large enough to hold at least 99% of the BCP 47 tags.
max99thPercentileSize = 32
// maxSimpleUExtensionSize is the maximum size of a -u extension with one
// key-type pair. Equals len("-u-") + key (2) + dash + max value (8).
maxSimpleUExtensionSize = 14
)
// Tag represents a BCP 47 language tag. It is used to specify an instance of a
// specific language or locale. All language tag values are guaranteed to be
// well-formed. The zero value of Tag is Und.
type Tag struct {
// TODO: the following fields have the form TagTypeID. This name is chosen
// to allow refactoring the public package without conflicting with its
// Base, Script, and Region methods. Once the transition is fully completed
// the ID can be stripped from the name.
LangID Language
RegionID Region
// TODO: we will soon run out of positions for ScriptID. Idea: instead of
// storing lang, region, and ScriptID codes, store only the compact index and
// have a lookup table from this code to its expansion. This greatly speeds
// up table lookup, speed up common variant cases.
// This will also immediately free up 3 extra bytes. Also, the pVariant
// field can now be moved to the lookup table, as the compact index uniquely
// determines the offset of a possible variant.
ScriptID Script
pVariant byte // offset in str, includes preceding '-'
pExt uint16 // offset of first extension, includes preceding '-'
// str is the string representation of the Tag. It will only be used if the
// tag has variants or extensions.
str string
}
// Make is a convenience wrapper for Parse that omits the error.
// In case of an error, a sensible default is returned.
func Make(s string) Tag {
t, _ := Parse(s)
return t
}
// Raw returns the raw base language, script and region, without making an
// attempt to infer their values.
// TODO: consider removing
func (t Tag) Raw() (b Language, s Script, r Region) {
return t.LangID, t.ScriptID, t.RegionID
}
// equalTags compares language, script and region subtags only.
func (t Tag) equalTags(a Tag) bool {
return t.LangID == a.LangID && t.ScriptID == a.ScriptID && t.RegionID == a.RegionID
}
// IsRoot returns true if t is equal to language "und".
func (t Tag) IsRoot() bool {
if int(t.pVariant) < len(t.str) {
return false
}
return t.equalTags(Und)
}
// IsPrivateUse reports whether the Tag consists solely of an IsPrivateUse use
// tag.
func (t Tag) IsPrivateUse() bool {
return t.str != "" && t.pVariant == 0
}
// RemakeString is used to update t.str in case lang, script or region changed.
// It is assumed that pExt and pVariant still point to the start of the
// respective parts.
func (t *Tag) RemakeString() {
if t.str == "" {
return
}
extra := t.str[t.pVariant:]
if t.pVariant > 0 {
extra = extra[1:]
}
if t.equalTags(Und) && strings.HasPrefix(extra, "x-") {
t.str = extra
t.pVariant = 0
t.pExt = 0
return
}
var buf [max99thPercentileSize]byte // avoid extra memory allocation in most cases.
b := buf[:t.genCoreBytes(buf[:])]
if extra != "" {
diff := len(b) - int(t.pVariant)
b = append(b, '-')
b = append(b, extra...)
t.pVariant = uint8(int(t.pVariant) + diff)
t.pExt = uint16(int(t.pExt) + diff)
} else {
t.pVariant = uint8(len(b))
t.pExt = uint16(len(b))
}
t.str = string(b)
}
// genCoreBytes writes a string for the base languages, script and region tags
// to the given buffer and returns the number of bytes written. It will never
// write more than maxCoreSize bytes.
func (t *Tag) genCoreBytes(buf []byte) int {
n := t.LangID.StringToBuf(buf[:])
if t.ScriptID != 0 {
n += copy(buf[n:], "-")
n += copy(buf[n:], t.ScriptID.String())
}
if t.RegionID != 0 {
n += copy(buf[n:], "-")
n += copy(buf[n:], t.RegionID.String())
}
return n
}
// String returns the canonical string representation of the language tag.
func (t Tag) String() string {
if t.str != "" {
return t.str
}
if t.ScriptID == 0 && t.RegionID == 0 {
return t.LangID.String()
}
buf := [maxCoreSize]byte{}
return string(buf[:t.genCoreBytes(buf[:])])
}
// MarshalText implements encoding.TextMarshaler.
func (t Tag) MarshalText() (text []byte, err error) {
if t.str != "" {
text = append(text, t.str...)
} else if t.ScriptID == 0 && t.RegionID == 0 {
text = append(text, t.LangID.String()...)
} else {
buf := [maxCoreSize]byte{}
text = buf[:t.genCoreBytes(buf[:])]
}
return text, nil
}
// UnmarshalText implements encoding.TextUnmarshaler.
func (t *Tag) UnmarshalText(text []byte) error {
tag, err := Parse(string(text))
*t = tag
return err
}
// Variants returns the part of the tag holding all variants or the empty string
// if there are no variants defined.
func (t Tag) Variants() string {
if t.pVariant == 0 {
return ""
}
return t.str[t.pVariant:t.pExt]
}
// VariantOrPrivateUseTags returns variants or private use tags.
func (t Tag) VariantOrPrivateUseTags() string {
if t.pExt > 0 {
return t.str[t.pVariant:t.pExt]
}
return t.str[t.pVariant:]
}
// HasString reports whether this tag defines more than just the raw
// components.
func (t Tag) HasString() bool {
return t.str != ""
}
// Parent returns the CLDR parent of t. In CLDR, missing fields in data for a
// specific language are substituted with fields from the parent language.
// The parent for a language may change for newer versions of CLDR.
func (t Tag) Parent() Tag {
if t.str != "" {
// Strip the variants and extensions.
b, s, r := t.Raw()
t = Tag{LangID: b, ScriptID: s, RegionID: r}
if t.RegionID == 0 && t.ScriptID != 0 && t.LangID != 0 {
base, _ := addTags(Tag{LangID: t.LangID})
if base.ScriptID == t.ScriptID {
return Tag{LangID: t.LangID}
}
}
return t
}
if t.LangID != 0 {
if t.RegionID != 0 {
maxScript := t.ScriptID
if maxScript == 0 {
max, _ := addTags(t)
maxScript = max.ScriptID
}
for i := range parents {
if Language(parents[i].lang) == t.LangID && Script(parents[i].maxScript) == maxScript {
for _, r := range parents[i].fromRegion {
if Region(r) == t.RegionID {
return Tag{
LangID: t.LangID,
ScriptID: Script(parents[i].script),
RegionID: Region(parents[i].toRegion),
}
}
}
}
}
// Strip the script if it is the default one.
base, _ := addTags(Tag{LangID: t.LangID})
if base.ScriptID != maxScript {
return Tag{LangID: t.LangID, ScriptID: maxScript}
}
return Tag{LangID: t.LangID}
} else if t.ScriptID != 0 {
// The parent for an base-script pair with a non-default script is
// "und" instead of the base language.
base, _ := addTags(Tag{LangID: t.LangID})
if base.ScriptID != t.ScriptID {
return Und
}
return Tag{LangID: t.LangID}
}
}
return Und
}
// ParseExtension parses s as an extension and returns it on success.
func ParseExtension(s string) (ext string, err error) {
defer func() {
if recover() != nil {
ext = ""
err = ErrSyntax
}
}()
scan := makeScannerString(s)
var end int
if n := len(scan.token); n != 1 {
return "", ErrSyntax
}
scan.toLower(0, len(scan.b))
end = parseExtension(&scan)
if end != len(s) {
return "", ErrSyntax
}
return string(scan.b), nil
}
// HasVariants reports whether t has variants.
func (t Tag) HasVariants() bool {
return uint16(t.pVariant) < t.pExt
}
// HasExtensions reports whether t has extensions.
func (t Tag) HasExtensions() bool {
return int(t.pExt) < len(t.str)
}
// Extension returns the extension of type x for tag t. It will return
// false for ok if t does not have the requested extension. The returned
// extension will be invalid in this case.
func (t Tag) Extension(x byte) (ext string, ok bool) {
for i := int(t.pExt); i < len(t.str)-1; {
var ext string
i, ext = getExtension(t.str, i)
if ext[0] == x {
return ext, true
}
}
return "", false
}
// Extensions returns all extensions of t.
func (t Tag) Extensions() []string {
e := []string{}
for i := int(t.pExt); i < len(t.str)-1; {
var ext string
i, ext = getExtension(t.str, i)
e = append(e, ext)
}
return e
}
// TypeForKey returns the type associated with the given key, where key and type
// are of the allowed values defined for the Unicode locale extension ('u') in
// https://www.unicode.org/reports/tr35/#Unicode_Language_and_Locale_Identifiers.
// TypeForKey will traverse the inheritance chain to get the correct value.
//
// If there are multiple types associated with a key, only the first will be
// returned. If there is no type associated with a key, it returns the empty
// string.
func (t Tag) TypeForKey(key string) string {
if _, start, end, _ := t.findTypeForKey(key); end != start {
s := t.str[start:end]
if p := strings.IndexByte(s, '-'); p >= 0 {
s = s[:p]
}
return s
}
return ""
}
var (
errPrivateUse = errors.New("cannot set a key on a private use tag")
errInvalidArguments = errors.New("invalid key or type")
)
// SetTypeForKey returns a new Tag with the key set to type, where key and type
// are of the allowed values defined for the Unicode locale extension ('u') in
// https://www.unicode.org/reports/tr35/#Unicode_Language_and_Locale_Identifiers.
// An empty value removes an existing pair with the same key.
func (t Tag) SetTypeForKey(key, value string) (Tag, error) {
if t.IsPrivateUse() {
return t, errPrivateUse
}
if len(key) != 2 {
return t, errInvalidArguments
}
// Remove the setting if value is "".
if value == "" {
start, sep, end, _ := t.findTypeForKey(key)
if start != sep {
// Remove a possible empty extension.
switch {
case t.str[start-2] != '-': // has previous elements.
case end == len(t.str), // end of string
end+2 < len(t.str) && t.str[end+2] == '-': // end of extension
start -= 2
}
if start == int(t.pVariant) && end == len(t.str) {
t.str = ""
t.pVariant, t.pExt = 0, 0
} else {
t.str = fmt.Sprintf("%s%s", t.str[:start], t.str[end:])
}
}
return t, nil
}
if len(value) < 3 || len(value) > 8 {
return t, errInvalidArguments
}
var (
buf [maxCoreSize + maxSimpleUExtensionSize]byte
uStart int // start of the -u extension.
)
// Generate the tag string if needed.
if t.str == "" {
uStart = t.genCoreBytes(buf[:])
buf[uStart] = '-'
uStart++
}
// Create new key-type pair and parse it to verify.
b := buf[uStart:]
copy(b, "u-")
copy(b[2:], key)
b[4] = '-'
b = b[:5+copy(b[5:], value)]
scan := makeScanner(b)
if parseExtensions(&scan); scan.err != nil {
return t, scan.err
}
// Assemble the replacement string.
if t.str == "" {
t.pVariant, t.pExt = byte(uStart-1), uint16(uStart-1)
t.str = string(buf[:uStart+len(b)])
} else {
s := t.str
start, sep, end, hasExt := t.findTypeForKey(key)
if start == sep {
if hasExt {
b = b[2:]
}
t.str = fmt.Sprintf("%s-%s%s", s[:sep], b, s[end:])
} else {
t.str = fmt.Sprintf("%s-%s%s", s[:start+3], value, s[end:])
}
}
return t, nil
}
// findTypeForKey returns the start and end position for the type corresponding
// to key or the point at which to insert the key-value pair if the type
// wasn't found. The hasExt return value reports whether an -u extension was present.
// Note: the extensions are typically very small and are likely to contain
// only one key-type pair.
func (t Tag) findTypeForKey(key string) (start, sep, end int, hasExt bool) {
p := int(t.pExt)
if len(key) != 2 || p == len(t.str) || p == 0 {
return p, p, p, false
}
s := t.str
// Find the correct extension.
for p++; s[p] != 'u'; p++ {
if s[p] > 'u' {
p--
return p, p, p, false
}
if p = nextExtension(s, p); p == len(s) {
return len(s), len(s), len(s), false
}
}
// Proceed to the hyphen following the extension name.
p++
// curKey is the key currently being processed.
curKey := ""
// Iterate over keys until we get the end of a section.
for {
end = p
for p++; p < len(s) && s[p] != '-'; p++ {
}
n := p - end - 1
if n <= 2 && curKey == key {
if sep < end {
sep++
}
return start, sep, end, true
}
switch n {
case 0, // invalid string
1: // next extension
return end, end, end, true
case 2:
// next key
curKey = s[end+1 : p]
if curKey > key {
return end, end, end, true
}
start = end
sep = p
}
}
}
// ParseBase parses a 2- or 3-letter ISO 639 code.
// It returns a ValueError if s is a well-formed but unknown language identifier
// or another error if another error occurred.
func ParseBase(s string) (l Language, err error) {
defer func() {
if recover() != nil {
l = 0
err = ErrSyntax
}
}()
if n := len(s); n < 2 || 3 < n {
return 0, ErrSyntax
}
var buf [3]byte
return getLangID(buf[:copy(buf[:], s)])
}
// ParseScript parses a 4-letter ISO 15924 code.
// It returns a ValueError if s is a well-formed but unknown script identifier
// or another error if another error occurred.
func ParseScript(s string) (scr Script, err error) {
defer func() {
if recover() != nil {
scr = 0
err = ErrSyntax
}
}()
if len(s) != 4 {
return 0, ErrSyntax
}
var buf [4]byte
return getScriptID(script, buf[:copy(buf[:], s)])
}
// EncodeM49 returns the Region for the given UN M.49 code.
// It returns an error if r is not a valid code.
func EncodeM49(r int) (Region, error) {
return getRegionM49(r)
}
// ParseRegion parses a 2- or 3-letter ISO 3166-1 or a UN M.49 code.
// It returns a ValueError if s is a well-formed but unknown region identifier
// or another error if another error occurred.
func ParseRegion(s string) (r Region, err error) {
defer func() {
if recover() != nil {
r = 0
err = ErrSyntax
}
}()
if n := len(s); n < 2 || 3 < n {
return 0, ErrSyntax
}
var buf [3]byte
return getRegionID(buf[:copy(buf[:], s)])
}
// IsCountry returns whether this region is a country or autonomous area. This
// includes non-standard definitions from CLDR.
func (r Region) IsCountry() bool {
if r == 0 || r.IsGroup() || r.IsPrivateUse() && r != _XK {
return false
}
return true
}
// IsGroup returns whether this region defines a collection of regions. This
// includes non-standard definitions from CLDR.
func (r Region) IsGroup() bool {
if r == 0 {
return false
}
return int(regionInclusion[r]) < len(regionContainment)
}
// Contains returns whether Region c is contained by Region r. It returns true
// if c == r.
func (r Region) Contains(c Region) bool {
if r == c {
return true
}
g := regionInclusion[r]
if g >= nRegionGroups {
return false
}
m := regionContainment[g]
d := regionInclusion[c]
b := regionInclusionBits[d]
// A contained country may belong to multiple disjoint groups. Matching any
// of these indicates containment. If the contained region is a group, it
// must strictly be a subset.
if d >= nRegionGroups {
return b&m != 0
}
return b&^m == 0
}
var errNoTLD = errors.New("language: region is not a valid ccTLD")
// TLD returns the country code top-level domain (ccTLD). UK is returned for GB.
// In all other cases it returns either the region itself or an error.
//
// This method may return an error for a region for which there exists a
// canonical form with a ccTLD. To get that ccTLD canonicalize r first. The
// region will already be canonicalized it was obtained from a Tag that was
// obtained using any of the default methods.
func (r Region) TLD() (Region, error) {
// See http://en.wikipedia.org/wiki/Country_code_top-level_domain for the
// difference between ISO 3166-1 and IANA ccTLD.
if r == _GB {
r = _UK
}
if (r.typ() & ccTLD) == 0 {
return 0, errNoTLD
}
return r, nil
}
// Canonicalize returns the region or a possible replacement if the region is
// deprecated. It will not return a replacement for deprecated regions that
// are split into multiple regions.
func (r Region) Canonicalize() Region {
if cr := normRegion(r); cr != 0 {
return cr
}
return r
}
// Variant represents a registered variant of a language as defined by BCP 47.
type Variant struct {
ID uint8
str string
}
// ParseVariant parses and returns a Variant. An error is returned if s is not
// a valid variant.
func ParseVariant(s string) (v Variant, err error) {
defer func() {
if recover() != nil {
v = Variant{}
err = ErrSyntax
}
}()
s = strings.ToLower(s)
if id, ok := variantIndex[s]; ok {
return Variant{id, s}, nil
}
return Variant{}, NewValueError([]byte(s))
}
// String returns the string representation of the variant.
func (v Variant) String() string {
return v.str
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/language_test.go
+746
View File
@@ -0,0 +1,746 @@
// 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 language
import (
"reflect"
"testing"
"golang.org/x/text/internal/testtext"
)
func TestTagSize(t *testing.T) {
id := Tag{}
typ := reflect.TypeOf(id)
if typ.Size() > 32 {
t.Errorf("size of Tag was %d; want <= 32", typ.Size())
}
}
func TestIsRoot(t *testing.T) {
loc := Tag{}
if !loc.IsRoot() {
t.Errorf("unspecified should be root.")
}
for i, tt := range parseTests() {
loc, _ := Parse(tt.in)
undef := tt.lang == "und" && tt.script == "" && tt.region == "" && tt.ext == ""
if loc.IsRoot() != undef {
t.Errorf("%d: was %v; want %v", i, loc.IsRoot(), undef)
}
}
}
func TestEquality(t *testing.T) {
for i, tt := range parseTests() {
s := tt.in
tag := Make(s)
t1 := Make(tag.String())
if tag != t1 {
t.Errorf("%d:%s: equality test 1 failed\n got: %#v\nwant: %#v)", i, s, t1, tag)
}
}
}
func TestMakeString(t *testing.T) {
tests := []struct{ in, out string }{
{"und", "und"},
{"und", "und-CW"},
{"nl", "nl-NL"},
{"de-1901", "nl-1901"},
{"de-1901", "de-Arab-1901"},
{"x-a-b", "de-Arab-x-a-b"},
{"x-a-b", "x-a-b"},
}
for i, tt := range tests {
id, _ := Parse(tt.in)
mod, _ := Parse(tt.out)
id.setTagsFrom(mod)
for j := 0; j < 2; j++ {
id.RemakeString()
if str := id.String(); str != tt.out {
t.Errorf("%d:%d: found %s; want %s", i, j, id.String(), tt.out)
}
}
// The bytes to string conversion as used in remakeString
// occasionally measures as more than one alloc, breaking this test.
// To alleviate this we set the number of runs to more than 1.
if n := testtext.AllocsPerRun(8, id.RemakeString); n > 1 {
t.Errorf("%d: # allocs got %.1f; want <= 1", i, n)
}
}
}
func TestMarshal(t *testing.T) {
testCases := []string{
// TODO: these values will change with each CLDR update. This issue
// will be solved if we decide to fix the indexes.
"und",
"ca-ES-valencia",
"ca-ES-valencia-u-va-posix",
"ca-ES-valencia-u-co-phonebk",
"ca-ES-valencia-u-co-phonebk-va-posix",
"x-klingon",
"en-US",
"en-US-u-va-posix",
"en",
"en-u-co-phonebk",
"en-001",
"sh",
}
for _, tc := range testCases {
var tag Tag
err := tag.UnmarshalText([]byte(tc))
if err != nil {
t.Errorf("UnmarshalText(%q): unexpected error: %v", tc, err)
}
b, err := tag.MarshalText()
if err != nil {
t.Errorf("MarshalText(%q): unexpected error: %v", tc, err)
}
if got := string(b); got != tc {
t.Errorf("%s: got %q; want %q", tc, got, tc)
}
}
}
func TestParseBase(t *testing.T) {
tests := []struct {
in string
out string
ok bool
}{
{"en", "en", true},
{"EN", "en", true},
{"nld", "nl", true},
{"dut", "dut", true}, // bibliographic
{"aaj", "und", false}, // unknown
{"qaa", "qaa", true},
{"a", "und", false},
{"", "und", false},
{"aaaa", "und", false},
}
for i, tt := range tests {
x, err := ParseBase(tt.in)
if x.String() != tt.out || err == nil != tt.ok {
t.Errorf("%d:%s: was %s, %v; want %s, %v", i, tt.in, x, err == nil, tt.out, tt.ok)
}
if y, _, _ := Make(tt.out).Raw(); x != y {
t.Errorf("%d:%s: tag was %s; want %s", i, tt.in, x, y)
}
}
}
func TestParseScript(t *testing.T) {
tests := []struct {
in string
out string
ok bool
}{
{"Latn", "Latn", true},
{"zzzz", "Zzzz", true},
{"zyyy", "Zyyy", true},
{"Latm", "Zzzz", false},
{"Zzz", "Zzzz", false},
{"", "Zzzz", false},
{"Zzzxx", "Zzzz", false},
}
for i, tt := range tests {
x, err := ParseScript(tt.in)
if x.String() != tt.out || err == nil != tt.ok {
t.Errorf("%d:%s: was %s, %v; want %s, %v", i, tt.in, x, err == nil, tt.out, tt.ok)
}
if err == nil {
if _, y, _ := Make("und-" + tt.out).Raw(); x != y {
t.Errorf("%d:%s: tag was %s; want %s", i, tt.in, x, y)
}
}
}
}
func TestEncodeM49(t *testing.T) {
tests := []struct {
m49 int
code string
ok bool
}{
{1, "001", true},
{840, "US", true},
{899, "ZZ", false},
}
for i, tt := range tests {
if r, err := EncodeM49(tt.m49); r.String() != tt.code || err == nil != tt.ok {
t.Errorf("%d:%d: was %s, %v; want %s, %v", i, tt.m49, r, err == nil, tt.code, tt.ok)
}
}
for i := 1; i <= 1000; i++ {
if r, err := EncodeM49(i); err == nil && r.M49() == 0 {
t.Errorf("%d has no error, but maps to undefined region", i)
}
}
}
func TestParseRegion(t *testing.T) {
tests := []struct {
in string
out string
ok bool
}{
{"001", "001", true},
{"840", "US", true},
{"899", "ZZ", false},
{"USA", "US", true},
{"US", "US", true},
{"BC", "ZZ", false},
{"C", "ZZ", false},
{"CCCC", "ZZ", false},
{"01", "ZZ", false},
}
for i, tt := range tests {
r, err := ParseRegion(tt.in)
if r.String() != tt.out || err == nil != tt.ok {
t.Errorf("%d:%s: was %s, %v; want %s, %v", i, tt.in, r, err == nil, tt.out, tt.ok)
}
if err == nil {
if _, _, y := Make("und-" + tt.out).Raw(); r != y {
t.Errorf("%d:%s: tag was %s; want %s", i, tt.in, r, y)
}
}
}
}
func TestIsCountry(t *testing.T) {
tests := []struct {
reg string
country bool
}{
{"US", true},
{"001", false},
{"958", false},
{"419", false},
{"203", true},
{"020", true},
{"900", false},
{"999", false},
{"QO", false},
{"EU", false},
{"AA", false},
{"XK", true},
}
for i, tt := range tests {
r, _ := getRegionID([]byte(tt.reg))
if r.IsCountry() != tt.country {
t.Errorf("%d: IsCountry(%s) was %v; want %v", i, tt.reg, r.IsCountry(), tt.country)
}
}
}
func TestIsGroup(t *testing.T) {
tests := []struct {
reg string
group bool
}{
{"US", false},
{"001", true},
{"958", false},
{"419", true},
{"203", false},
{"020", false},
{"900", false},
{"999", false},
{"QO", true},
{"EU", true},
{"AA", false},
{"XK", false},
}
for i, tt := range tests {
r, _ := getRegionID([]byte(tt.reg))
if r.IsGroup() != tt.group {
t.Errorf("%d: IsGroup(%s) was %v; want %v", i, tt.reg, r.IsGroup(), tt.group)
}
}
}
func TestContains(t *testing.T) {
tests := []struct {
enclosing, contained string
contains bool
}{
// A region contains itself.
{"US", "US", true},
{"001", "001", true},
// Direct containment.
{"001", "002", true},
{"039", "XK", true},
{"150", "XK", true},
{"EU", "AT", true},
{"QO", "AQ", true},
// Indirect containemnt.
{"001", "US", true},
{"001", "419", true},
{"001", "013", true},
// No containment.
{"US", "001", false},
{"155", "EU", false},
}
for i, tt := range tests {
enc, _ := getRegionID([]byte(tt.enclosing))
con, _ := getRegionID([]byte(tt.contained))
r := enc
if got := r.Contains(con); got != tt.contains {
t.Errorf("%d: %s.Contains(%s) was %v; want %v", i, tt.enclosing, tt.contained, got, tt.contains)
}
}
}
func TestRegionCanonicalize(t *testing.T) {
for i, tt := range []struct{ in, out string }{
{"UK", "GB"},
{"TP", "TL"},
{"QU", "EU"},
{"SU", "SU"},
{"VD", "VN"},
{"DD", "DE"},
} {
r := MustParseRegion(tt.in)
want := MustParseRegion(tt.out)
if got := r.Canonicalize(); got != want {
t.Errorf("%d: got %v; want %v", i, got, want)
}
}
}
func TestRegionTLD(t *testing.T) {
for _, tt := range []struct {
in, out string
ok bool
}{
{"EH", "EH", true},
{"FR", "FR", true},
{"TL", "TL", true},
// In ccTLD before in ISO.
{"GG", "GG", true},
// Non-standard assignment of ccTLD to ISO code.
{"GB", "UK", true},
// Exceptionally reserved in ISO and valid ccTLD.
{"UK", "UK", true},
{"AC", "AC", true},
{"EU", "EU", true},
{"SU", "SU", true},
// Exceptionally reserved in ISO and invalid ccTLD.
{"CP", "ZZ", false},
{"DG", "ZZ", false},
{"EA", "ZZ", false},
{"FX", "ZZ", false},
{"IC", "ZZ", false},
{"TA", "ZZ", false},
// Transitionally reserved in ISO (e.g. deprecated) but valid ccTLD as
// it is still being phased out.
{"AN", "AN", true},
{"TP", "TP", true},
// Transitionally reserved in ISO (e.g. deprecated) and invalid ccTLD.
// Defined in package language as it has a mapping in CLDR.
{"BU", "ZZ", false},
{"CS", "ZZ", false},
{"NT", "ZZ", false},
{"YU", "ZZ", false},
{"ZR", "ZZ", false},
// Not defined in package: SF.
// Indeterminately reserved in ISO.
// Defined in package language as it has a legacy mapping in CLDR.
{"DY", "ZZ", false},
{"RH", "ZZ", false},
{"VD", "ZZ", false},
// Not defined in package: EW, FL, JA, LF, PI, RA, RB, RC, RI, RL, RM,
// RN, RP, WG, WL, WV, and YV.
// Not assigned in ISO, but legacy definitions in CLDR.
{"DD", "ZZ", false},
{"YD", "ZZ", false},
// Normal mappings but somewhat special status in ccTLD.
{"BL", "BL", true},
{"MF", "MF", true},
{"BV", "BV", true},
{"SJ", "SJ", true},
// Have values when normalized, but not as is.
{"QU", "ZZ", false},
// ISO Private Use.
{"AA", "ZZ", false},
{"QM", "ZZ", false},
{"QO", "ZZ", false},
{"XA", "ZZ", false},
{"XK", "ZZ", false}, // Sometimes used for Kosovo, but invalid ccTLD.
} {
if tt.in == "" {
continue
}
r := MustParseRegion(tt.in)
var want Region
if tt.out != "ZZ" {
want = MustParseRegion(tt.out)
}
tld, err := r.TLD()
if got := err == nil; got != tt.ok {
t.Errorf("error(%v): got %v; want %v", r, got, tt.ok)
}
if tld != want {
t.Errorf("TLD(%v): got %v; want %v", r, tld, want)
}
}
}
func TestTypeForKey(t *testing.T) {
tests := []struct{ key, in, out string }{
{"co", "en", ""},
{"co", "en-u-abc", ""},
{"co", "en-u-co-phonebk", "phonebk"},
{"co", "en-u-co-phonebk-cu-aud", "phonebk"},
{"co", "x-foo-u-co-phonebk", ""},
{"nu", "en-u-co-phonebk-nu-arabic", "arabic"},
{"kc", "cmn-u-co-stroke", ""},
}
for _, tt := range tests {
if v := Make(tt.in).TypeForKey(tt.key); v != tt.out {
t.Errorf("%q[%q]: was %q; want %q", tt.in, tt.key, v, tt.out)
}
}
}
func TestSetTypeForKey(t *testing.T) {
tests := []struct {
key, value, in, out string
err bool
}{
// replace existing value
{"co", "pinyin", "en-u-co-phonebk", "en-u-co-pinyin", false},
{"co", "pinyin", "en-u-co-phonebk-cu-xau", "en-u-co-pinyin-cu-xau", false},
{"co", "pinyin", "en-u-co-phonebk-v-xx", "en-u-co-pinyin-v-xx", false},
{"co", "pinyin", "en-u-co-phonebk-x-x", "en-u-co-pinyin-x-x", false},
{"co", "pinyin", "en-u-co-x-x", "en-u-co-pinyin-x-x", false},
{"nu", "arabic", "en-u-co-phonebk-nu-vaai", "en-u-co-phonebk-nu-arabic", false},
{"nu", "arabic", "en-u-co-phonebk-nu", "en-u-co-phonebk-nu-arabic", false},
// add to existing -u extension
{"co", "pinyin", "en-u-ca-gregory", "en-u-ca-gregory-co-pinyin", false},
{"co", "pinyin", "en-u-ca-gregory-nu-vaai", "en-u-ca-gregory-co-pinyin-nu-vaai", false},
{"co", "pinyin", "en-u-ca-gregory-v-va", "en-u-ca-gregory-co-pinyin-v-va", false},
{"co", "pinyin", "en-u-ca-gregory-x-a", "en-u-ca-gregory-co-pinyin-x-a", false},
{"ca", "gregory", "en-u-co-pinyin", "en-u-ca-gregory-co-pinyin", false},
// remove pair
{"co", "", "en-u-co-phonebk", "en", false},
{"co", "", "en-u-co", "en", false},
{"co", "", "en-u-co-v", "en", false},
{"co", "", "en-u-co-v-", "en", false},
{"co", "", "en-u-ca-gregory-co-phonebk", "en-u-ca-gregory", false},
{"co", "", "en-u-co-phonebk-nu-arabic", "en-u-nu-arabic", false},
{"co", "", "en-u-co-nu-arabic", "en-u-nu-arabic", false},
{"co", "", "en", "en", false},
// add -u extension
{"co", "pinyin", "en", "en-u-co-pinyin", false},
{"co", "pinyin", "und", "und-u-co-pinyin", false},
{"co", "pinyin", "en-a-aaa", "en-a-aaa-u-co-pinyin", false},
{"co", "pinyin", "en-x-aaa", "en-u-co-pinyin-x-aaa", false},
{"co", "pinyin", "en-v-aa", "en-u-co-pinyin-v-aa", false},
{"co", "pinyin", "en-a-aaa-x-x", "en-a-aaa-u-co-pinyin-x-x", false},
{"co", "pinyin", "en-a-aaa-v-va", "en-a-aaa-u-co-pinyin-v-va", false},
// error on invalid values
{"co", "pinyinxxx", "en", "en", true},
{"co", "piny.n", "en", "en", true},
{"co", "pinyinxxx", "en-a-aaa", "en-a-aaa", true},
{"co", "pinyinxxx", "en-u-aaa", "en-u-aaa", true},
{"co", "pinyinxxx", "en-u-aaa-co-pinyin", "en-u-aaa-co-pinyin", true},
{"co", "pinyi.", "en-u-aaa-co-pinyin", "en-u-aaa-co-pinyin", true},
{"col", "pinyin", "en", "en", true},
{"co", "cu", "en", "en", true},
// error when setting on a private use tag
{"co", "phonebook", "x-foo", "x-foo", true},
}
for i, tt := range tests {
tag := Make(tt.in)
if v, err := tag.SetTypeForKey(tt.key, tt.value); v.String() != tt.out {
t.Errorf("%d:%q[%q]=%q: was %q; want %q", i, tt.in, tt.key, tt.value, v, tt.out)
} else if (err != nil) != tt.err {
t.Errorf("%d:%q[%q]=%q: error was %v; want %v", i, tt.in, tt.key, tt.value, err != nil, tt.err)
} else if val := v.TypeForKey(tt.key); err == nil && val != tt.value {
t.Errorf("%d:%q[%q]==%q: was %v; want %v", i, tt.out, tt.key, tt.value, val, tt.value)
}
if len(tag.String()) <= 3 {
// Simulate a tag for which the string has not been set.
tag.str, tag.pExt, tag.pVariant = "", 0, 0
if tag, err := tag.SetTypeForKey(tt.key, tt.value); err == nil {
if val := tag.TypeForKey(tt.key); err == nil && val != tt.value {
t.Errorf("%d:%q[%q]==%q: was %v; want %v", i, tt.out, tt.key, tt.value, val, tt.value)
}
}
}
}
}
func TestFindKeyAndType(t *testing.T) {
// out is either the matched type in case of a match or the original
// string up till the insertion point.
tests := []struct {
key string
hasExt bool
in, out string
}{
// Don't search past a private use extension.
{"co", false, "en-x-foo-u-co-pinyin", "en"},
{"co", false, "x-foo-u-co-pinyin", ""},
{"co", false, "en-s-fff-x-foo", "en-s-fff"},
// Insertion points in absence of -u extension.
{"cu", false, "en", ""}, // t.str is ""
{"cu", false, "en-v-va", "en"},
{"cu", false, "en-a-va", "en-a-va"},
{"cu", false, "en-a-va-v-va", "en-a-va"},
{"cu", false, "en-x-a", "en"},
// Tags with the -u extension.
{"nu", true, "en-u-cu-nu", "en-u-cu"},
{"cu", true, "en-u-cu-nu", "en-u"},
{"co", true, "en-u-co-standard", "standard"},
{"co", true, "yue-u-co-pinyin", "pinyin"},
{"co", true, "en-u-co-abc", "abc"},
{"co", true, "en-u-co-abc-def", "abc-def"},
{"co", true, "en-u-co-abc-def-x-foo", "abc-def"},
{"co", true, "en-u-co-standard-nu-arab", "standard"},
{"co", true, "yue-u-co-pinyin-nu-arab", "pinyin"},
// Insertion points.
{"cu", true, "en-u-co-standard", "en-u-co-standard"},
{"cu", true, "yue-u-co-pinyin-x-foo", "yue-u-co-pinyin"},
{"cu", true, "en-u-co-abc", "en-u-co-abc"},
{"cu", true, "en-u-nu-arabic", "en-u"},
{"cu", true, "en-u-co-abc-def-nu-arabic", "en-u-co-abc-def"},
}
for i, tt := range tests {
start, sep, end, hasExt := Make(tt.in).findTypeForKey(tt.key)
if sep != end {
res := tt.in[sep:end]
if res != tt.out {
t.Errorf("%d:%s: was %q; want %q", i, tt.in, res, tt.out)
}
} else {
if hasExt != tt.hasExt {
t.Errorf("%d:%s: hasExt was %v; want %v", i, tt.in, hasExt, tt.hasExt)
continue
}
if tt.in[:start] != tt.out {
t.Errorf("%d:%s: insertion point was %q; want %q", i, tt.in, tt.in[:start], tt.out)
}
}
}
}
func TestParent(t *testing.T) {
tests := []struct{ in, out string }{
// Strip variants and extensions first
{"de-u-co-phonebk", "de"},
{"de-1994", "de"},
{"de-Latn-1994", "de"}, // remove superfluous script.
// Ensure the canonical Tag for an entry is in the chain for base-script
// pairs.
{"zh-Hans", "zh"},
// Skip the script if it is the maximized version. CLDR files for the
// skipped tag are always empty.
{"zh-Hans-TW", "zh"},
{"zh-Hans-CN", "zh"},
// Insert the script if the maximized script is not the same as the
// maximized script of the base language.
{"zh-TW", "zh-Hant"},
{"zh-HK", "zh-Hant"},
{"zh-Hant-TW", "zh-Hant"},
{"zh-Hant-HK", "zh-Hant"},
// Non-default script skips to und.
// CLDR
{"az-Cyrl", "und"},
{"bs-Cyrl", "und"},
{"en-Dsrt", "und"},
{"ha-Arab", "und"},
{"mn-Mong", "und"},
{"pa-Arab", "und"},
{"shi-Latn", "und"},
{"sr-Latn", "und"},
{"uz-Arab", "und"},
{"uz-Cyrl", "und"},
{"vai-Latn", "und"},
{"zh-Hant", "und"},
// extra
{"nl-Cyrl", "und"},
// World english inherits from en-001.
{"en-150", "en-001"},
{"en-AU", "en-001"},
{"en-BE", "en-001"},
{"en-GG", "en-001"},
{"en-GI", "en-001"},
{"en-HK", "en-001"},
{"en-IE", "en-001"},
{"en-IM", "en-001"},
{"en-IN", "en-001"},
{"en-JE", "en-001"},
{"en-MT", "en-001"},
{"en-NZ", "en-001"},
{"en-PK", "en-001"},
{"en-SG", "en-001"},
// Spanish in Latin-American countries have es-419 as parent.
{"es-AR", "es-419"},
{"es-BO", "es-419"},
{"es-CL", "es-419"},
{"es-CO", "es-419"},
{"es-CR", "es-419"},
{"es-CU", "es-419"},
{"es-DO", "es-419"},
{"es-EC", "es-419"},
{"es-GT", "es-419"},
{"es-HN", "es-419"},
{"es-MX", "es-419"},
{"es-NI", "es-419"},
{"es-PA", "es-419"},
{"es-PE", "es-419"},
{"es-PR", "es-419"},
{"es-PY", "es-419"},
{"es-SV", "es-419"},
{"es-US", "es-419"},
{"es-UY", "es-419"},
{"es-VE", "es-419"},
// exceptions (according to CLDR)
{"es-CW", "es"},
// Inherit from pt-PT, instead of pt for these countries.
{"pt-AO", "pt-PT"},
{"pt-CV", "pt-PT"},
{"pt-GW", "pt-PT"},
{"pt-MO", "pt-PT"},
{"pt-MZ", "pt-PT"},
{"pt-ST", "pt-PT"},
{"pt-TL", "pt-PT"},
}
for _, tt := range tests {
tag := MustParse(tt.in)
if p := MustParse(tt.out); p != tag.Parent() {
t.Errorf("%s: was %v; want %v", tt.in, tag.Parent(), p)
}
}
}
var (
// Tags without error that don't need to be changed.
benchBasic = []string{
"en",
"en-Latn",
"en-GB",
"za",
"zh-Hant",
"zh",
"zh-HK",
"ar-MK",
"en-CA",
"fr-CA",
"fr-CH",
"fr",
"lv",
"he-IT",
"tlh",
"ja",
"ja-Jpan",
"ja-Jpan-JP",
"de-1996",
"de-CH",
"sr",
"sr-Latn",
}
// Tags with extensions, not changes required.
benchExt = []string{
"x-a-b-c-d",
"x-aa-bbbb-cccccccc-d",
"en-x_cc-b-bbb-a-aaa",
"en-c_cc-b-bbb-a-aaa-x-x",
"en-u-co-phonebk",
"en-Cyrl-u-co-phonebk",
"en-US-u-co-phonebk-cu-xau",
"en-nedix-u-co-phonebk",
"en-t-t0-abcd",
"en-t-nl-latn",
"en-t-t0-abcd-x-a",
"en_t_pt_MLt",
"en-t-fr-est",
}
// Change, but not memory allocation required.
benchSimpleChange = []string{
"EN",
"i-klingon",
"en-latn",
"zh-cmn-Hans-CN",
"iw-NL",
}
// Change and memory allocation required.
benchChangeAlloc = []string{
"en-c_cc-b-bbb-a-aaa",
"en-u-cu-xua-co-phonebk",
"en-u-cu-xua-co-phonebk-a-cd",
"en-u-def-abc-cu-xua-co-phonebk",
"en-t-en-Cyrl-NL-1994",
"en-t-en-Cyrl-NL-1994-t0-abc-def",
}
// Tags that result in errors.
benchErr = []string{
// IllFormed
"x_A.-B-C_D",
"en-u-cu-co-phonebk",
"en-u-cu-xau-co",
"en-t-nl-abcd",
// Invalid
"xx",
"nl-Uuuu",
"nl-QB",
}
benchChange = append(benchSimpleChange, benchChangeAlloc...)
benchAll = append(append(append(benchBasic, benchExt...), benchChange...), benchErr...)
)
func doParse(b *testing.B, tag []string) {
for i := 0; i < b.N; i++ {
// Use the modulo instead of looping over all tags so that we get a somewhat
// meaningful ns/op.
Parse(tag[i%len(tag)])
}
}
func BenchmarkParse(b *testing.B) {
doParse(b, benchAll)
}
func BenchmarkParseBasic(b *testing.B) {
doParse(b, benchBasic)
}
func BenchmarkParseError(b *testing.B) {
doParse(b, benchErr)
}
func BenchmarkParseSimpleChange(b *testing.B) {
doParse(b, benchSimpleChange)
}
func BenchmarkParseChangeAlloc(b *testing.B) {
doParse(b, benchChangeAlloc)
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/lookup.go
+412
View File
@@ -0,0 +1,412 @@
// 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 language
import (
"bytes"
"fmt"
"sort"
"strconv"
"golang.org/x/text/internal/tag"
)
// findIndex tries to find the given tag in idx and returns a standardized error
// if it could not be found.
func findIndex(idx tag.Index, key []byte, form string) (index int, err error) {
if !tag.FixCase(form, key) {
return 0, ErrSyntax
}
i := idx.Index(key)
if i == -1 {
return 0, NewValueError(key)
}
return i, nil
}
func searchUint(imap []uint16, key uint16) int {
return sort.Search(len(imap), func(i int) bool {
return imap[i] >= key
})
}
type Language uint16
// getLangID returns the langID of s if s is a canonical subtag
// or langUnknown if s is not a canonical subtag.
func getLangID(s []byte) (Language, error) {
if len(s) == 2 {
return getLangISO2(s)
}
return getLangISO3(s)
}
// TODO language normalization as well as the AliasMaps could be moved to the
// higher level package, but it is a bit tricky to separate the generation.
func (id Language) Canonicalize() (Language, AliasType) {
return normLang(id)
}
// normLang returns the mapped langID of id according to mapping m.
func normLang(id Language) (Language, AliasType) {
k := sort.Search(len(AliasMap), func(i int) bool {
return AliasMap[i].From >= uint16(id)
})
if k < len(AliasMap) && AliasMap[k].From == uint16(id) {
return Language(AliasMap[k].To), AliasTypes[k]
}
return id, AliasTypeUnknown
}
// getLangISO2 returns the langID for the given 2-letter ISO language code
// or unknownLang if this does not exist.
func getLangISO2(s []byte) (Language, error) {
if !tag.FixCase("zz", s) {
return 0, ErrSyntax
}
if i := lang.Index(s); i != -1 && lang.Elem(i)[3] != 0 {
return Language(i), nil
}
return 0, NewValueError(s)
}
const base = 'z' - 'a' + 1
func strToInt(s []byte) uint {
v := uint(0)
for i := 0; i < len(s); i++ {
v *= base
v += uint(s[i] - 'a')
}
return v
}
// converts the given integer to the original ASCII string passed to strToInt.
// len(s) must match the number of characters obtained.
func intToStr(v uint, s []byte) {
for i := len(s) - 1; i >= 0; i-- {
s[i] = byte(v%base) + 'a'
v /= base
}
}
// getLangISO3 returns the langID for the given 3-letter ISO language code
// or unknownLang if this does not exist.
func getLangISO3(s []byte) (Language, error) {
if tag.FixCase("und", s) {
// first try to match canonical 3-letter entries
for i := lang.Index(s[:2]); i != -1; i = lang.Next(s[:2], i) {
if e := lang.Elem(i); e[3] == 0 && e[2] == s[2] {
// We treat "und" as special and always translate it to "unspecified".
// Note that ZZ and Zzzz are private use and are not treated as
// unspecified by default.
id := Language(i)
if id == nonCanonicalUnd {
return 0, nil
}
return id, nil
}
}
if i := altLangISO3.Index(s); i != -1 {
return Language(altLangIndex[altLangISO3.Elem(i)[3]]), nil
}
n := strToInt(s)
if langNoIndex[n/8]&(1<<(n%8)) != 0 {
return Language(n) + langNoIndexOffset, nil
}
// Check for non-canonical uses of ISO3.
for i := lang.Index(s[:1]); i != -1; i = lang.Next(s[:1], i) {
if e := lang.Elem(i); e[2] == s[1] && e[3] == s[2] {
return Language(i), nil
}
}
return 0, NewValueError(s)
}
return 0, ErrSyntax
}
// StringToBuf writes the string to b and returns the number of bytes
// written. cap(b) must be >= 3.
func (id Language) StringToBuf(b []byte) int {
if id >= langNoIndexOffset {
intToStr(uint(id)-langNoIndexOffset, b[:3])
return 3
} else if id == 0 {
return copy(b, "und")
}
l := lang[id<<2:]
if l[3] == 0 {
return copy(b, l[:3])
}
return copy(b, l[:2])
}
// String returns the BCP 47 representation of the langID.
// Use b as variable name, instead of id, to ensure the variable
// used is consistent with that of Base in which this type is embedded.
func (b Language) String() string {
if b == 0 {
return "und"
} else if b >= langNoIndexOffset {
b -= langNoIndexOffset
buf := [3]byte{}
intToStr(uint(b), buf[:])
return string(buf[:])
}
l := lang.Elem(int(b))
if l[3] == 0 {
return l[:3]
}
return l[:2]
}
// ISO3 returns the ISO 639-3 language code.
func (b Language) ISO3() string {
if b == 0 || b >= langNoIndexOffset {
return b.String()
}
l := lang.Elem(int(b))
if l[3] == 0 {
return l[:3]
} else if l[2] == 0 {
return altLangISO3.Elem(int(l[3]))[:3]
}
// This allocation will only happen for 3-letter ISO codes
// that are non-canonical BCP 47 language identifiers.
return l[0:1] + l[2:4]
}
// IsPrivateUse reports whether this language code is reserved for private use.
func (b Language) IsPrivateUse() bool {
return langPrivateStart <= b && b <= langPrivateEnd
}
// SuppressScript returns the script marked as SuppressScript in the IANA
// language tag repository, or 0 if there is no such script.
func (b Language) SuppressScript() Script {
if b < langNoIndexOffset {
return Script(suppressScript[b])
}
return 0
}
type Region uint16
// getRegionID returns the region id for s if s is a valid 2-letter region code
// or unknownRegion.
func getRegionID(s []byte) (Region, error) {
if len(s) == 3 {
if isAlpha(s[0]) {
return getRegionISO3(s)
}
if i, err := strconv.ParseUint(string(s), 10, 10); err == nil {
return getRegionM49(int(i))
}
}
return getRegionISO2(s)
}
// getRegionISO2 returns the regionID for the given 2-letter ISO country code
// or unknownRegion if this does not exist.
func getRegionISO2(s []byte) (Region, error) {
i, err := findIndex(regionISO, s, "ZZ")
if err != nil {
return 0, err
}
return Region(i) + isoRegionOffset, nil
}
// getRegionISO3 returns the regionID for the given 3-letter ISO country code
// or unknownRegion if this does not exist.
func getRegionISO3(s []byte) (Region, error) {
if tag.FixCase("ZZZ", s) {
for i := regionISO.Index(s[:1]); i != -1; i = regionISO.Next(s[:1], i) {
if e := regionISO.Elem(i); e[2] == s[1] && e[3] == s[2] {
return Region(i) + isoRegionOffset, nil
}
}
for i := 0; i < len(altRegionISO3); i += 3 {
if tag.Compare(altRegionISO3[i:i+3], s) == 0 {
return Region(altRegionIDs[i/3]), nil
}
}
return 0, NewValueError(s)
}
return 0, ErrSyntax
}
func getRegionM49(n int) (Region, error) {
if 0 < n && n <= 999 {
const (
searchBits = 7
regionBits = 9
regionMask = 1<<regionBits - 1
)
idx := n >> searchBits
buf := fromM49[m49Index[idx]:m49Index[idx+1]]
val := uint16(n) << regionBits // we rely on bits shifting out
i := sort.Search(len(buf), func(i int) bool {
return buf[i] >= val
})
if r := fromM49[int(m49Index[idx])+i]; r&^regionMask == val {
return Region(r & regionMask), nil
}
}
var e ValueError
fmt.Fprint(bytes.NewBuffer([]byte(e.v[:])), n)
return 0, e
}
// normRegion returns a region if r is deprecated or 0 otherwise.
// TODO: consider supporting BYS (-> BLR), CSK (-> 200 or CZ), PHI (-> PHL) and AFI (-> DJ).
// TODO: consider mapping split up regions to new most populous one (like CLDR).
func normRegion(r Region) Region {
m := regionOldMap
k := sort.Search(len(m), func(i int) bool {
return m[i].From >= uint16(r)
})
if k < len(m) && m[k].From == uint16(r) {
return Region(m[k].To)
}
return 0
}
const (
iso3166UserAssigned = 1 << iota
ccTLD
bcp47Region
)
func (r Region) typ() byte {
return regionTypes[r]
}
// String returns the BCP 47 representation for the region.
// It returns "ZZ" for an unspecified region.
func (r Region) String() string {
if r < isoRegionOffset {
if r == 0 {
return "ZZ"
}
return fmt.Sprintf("%03d", r.M49())
}
r -= isoRegionOffset
return regionISO.Elem(int(r))[:2]
}
// ISO3 returns the 3-letter ISO code of r.
// Note that not all regions have a 3-letter ISO code.
// In such cases this method returns "ZZZ".
func (r Region) ISO3() string {
if r < isoRegionOffset {
return "ZZZ"
}
r -= isoRegionOffset
reg := regionISO.Elem(int(r))
switch reg[2] {
case 0:
return altRegionISO3[reg[3]:][:3]
case ' ':
return "ZZZ"
}
return reg[0:1] + reg[2:4]
}
// M49 returns the UN M.49 encoding of r, or 0 if this encoding
// is not defined for r.
func (r Region) M49() int {
return int(m49[r])
}
// IsPrivateUse reports whether r has the ISO 3166 User-assigned status. This
// may include private-use tags that are assigned by CLDR and used in this
// implementation. So IsPrivateUse and IsCountry can be simultaneously true.
func (r Region) IsPrivateUse() bool {
return r.typ()&iso3166UserAssigned != 0
}
type Script uint16
// getScriptID returns the script id for string s. It assumes that s
// is of the format [A-Z][a-z]{3}.
func getScriptID(idx tag.Index, s []byte) (Script, error) {
i, err := findIndex(idx, s, "Zzzz")
return Script(i), err
}
// String returns the script code in title case.
// It returns "Zzzz" for an unspecified script.
func (s Script) String() string {
if s == 0 {
return "Zzzz"
}
return script.Elem(int(s))
}
// IsPrivateUse reports whether this script code is reserved for private use.
func (s Script) IsPrivateUse() bool {
return _Qaaa <= s && s <= _Qabx
}
const (
maxAltTaglen = len("en-US-POSIX")
maxLen = maxAltTaglen
)
var (
// grandfatheredMap holds a mapping from legacy and grandfathered tags to
// their base language or index to more elaborate tag.
grandfatheredMap = map[[maxLen]byte]int16{
[maxLen]byte{'a', 'r', 't', '-', 'l', 'o', 'j', 'b', 'a', 'n'}: _jbo, // art-lojban
[maxLen]byte{'i', '-', 'a', 'm', 'i'}: _ami, // i-ami
[maxLen]byte{'i', '-', 'b', 'n', 'n'}: _bnn, // i-bnn
[maxLen]byte{'i', '-', 'h', 'a', 'k'}: _hak, // i-hak
[maxLen]byte{'i', '-', 'k', 'l', 'i', 'n', 'g', 'o', 'n'}: _tlh, // i-klingon
[maxLen]byte{'i', '-', 'l', 'u', 'x'}: _lb, // i-lux
[maxLen]byte{'i', '-', 'n', 'a', 'v', 'a', 'j', 'o'}: _nv, // i-navajo
[maxLen]byte{'i', '-', 'p', 'w', 'n'}: _pwn, // i-pwn
[maxLen]byte{'i', '-', 't', 'a', 'o'}: _tao, // i-tao
[maxLen]byte{'i', '-', 't', 'a', 'y'}: _tay, // i-tay
[maxLen]byte{'i', '-', 't', 's', 'u'}: _tsu, // i-tsu
[maxLen]byte{'n', 'o', '-', 'b', 'o', 'k'}: _nb, // no-bok
[maxLen]byte{'n', 'o', '-', 'n', 'y', 'n'}: _nn, // no-nyn
[maxLen]byte{'s', 'g', 'n', '-', 'b', 'e', '-', 'f', 'r'}: _sfb, // sgn-BE-FR
[maxLen]byte{'s', 'g', 'n', '-', 'b', 'e', '-', 'n', 'l'}: _vgt, // sgn-BE-NL
[maxLen]byte{'s', 'g', 'n', '-', 'c', 'h', '-', 'd', 'e'}: _sgg, // sgn-CH-DE
[maxLen]byte{'z', 'h', '-', 'g', 'u', 'o', 'y', 'u'}: _cmn, // zh-guoyu
[maxLen]byte{'z', 'h', '-', 'h', 'a', 'k', 'k', 'a'}: _hak, // zh-hakka
[maxLen]byte{'z', 'h', '-', 'm', 'i', 'n', '-', 'n', 'a', 'n'}: _nan, // zh-min-nan
[maxLen]byte{'z', 'h', '-', 'x', 'i', 'a', 'n', 'g'}: _hsn, // zh-xiang
// Grandfathered tags with no modern replacement will be converted as
// follows:
[maxLen]byte{'c', 'e', 'l', '-', 'g', 'a', 'u', 'l', 'i', 's', 'h'}: -1, // cel-gaulish
[maxLen]byte{'e', 'n', '-', 'g', 'b', '-', 'o', 'e', 'd'}: -2, // en-GB-oed
[maxLen]byte{'i', '-', 'd', 'e', 'f', 'a', 'u', 'l', 't'}: -3, // i-default
[maxLen]byte{'i', '-', 'e', 'n', 'o', 'c', 'h', 'i', 'a', 'n'}: -4, // i-enochian
[maxLen]byte{'i', '-', 'm', 'i', 'n', 'g', 'o'}: -5, // i-mingo
[maxLen]byte{'z', 'h', '-', 'm', 'i', 'n'}: -6, // zh-min
// CLDR-specific tag.
[maxLen]byte{'r', 'o', 'o', 't'}: 0, // root
[maxLen]byte{'e', 'n', '-', 'u', 's', '-', 'p', 'o', 's', 'i', 'x'}: -7, // en_US_POSIX"
}
altTagIndex = [...]uint8{0, 17, 31, 45, 61, 74, 86, 102}
altTags = "xtg-x-cel-gaulishen-GB-oxendicten-x-i-defaultund-x-i-enochiansee-x-i-mingonan-x-zh-minen-US-u-va-posix"
)
func grandfathered(s [maxAltTaglen]byte) (t Tag, ok bool) {
if v, ok := grandfatheredMap[s]; ok {
if v < 0 {
return Make(altTags[altTagIndex[-v-1]:altTagIndex[-v]]), true
}
t.LangID = Language(v)
return t, true
}
return t, false
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/lookup_test.go
+457
View File
@@ -0,0 +1,457 @@
// 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 language
import (
"testing"
"golang.org/x/text/internal/tag"
)
func b(s string) []byte {
return []byte(s)
}
func TestLangID(t *testing.T) {
tests := []struct {
id, bcp47, iso3, norm string
err error
}{
{id: "", bcp47: "und", iso3: "und", err: ErrSyntax},
{id: " ", bcp47: "und", iso3: "und", err: ErrSyntax},
{id: " ", bcp47: "und", iso3: "und", err: ErrSyntax},
{id: " ", bcp47: "und", iso3: "und", err: ErrSyntax},
{id: "xxx", bcp47: "und", iso3: "und", err: NewValueError([]byte("xxx"))},
{id: "und", bcp47: "und", iso3: "und"},
{id: "aju", bcp47: "aju", iso3: "aju", norm: "jrb"},
{id: "jrb", bcp47: "jrb", iso3: "jrb"},
{id: "es", bcp47: "es", iso3: "spa"},
{id: "spa", bcp47: "es", iso3: "spa"},
{id: "ji", bcp47: "ji", iso3: "yid-", norm: "yi"},
{id: "jw", bcp47: "jw", iso3: "jav-", norm: "jv"},
{id: "ar", bcp47: "ar", iso3: "ara"},
{id: "kw", bcp47: "kw", iso3: "cor"},
{id: "arb", bcp47: "arb", iso3: "arb", norm: "ar"},
{id: "ar", bcp47: "ar", iso3: "ara"},
{id: "kur", bcp47: "ku", iso3: "kur"},
{id: "nl", bcp47: "nl", iso3: "nld"},
{id: "NL", bcp47: "nl", iso3: "nld"},
{id: "gsw", bcp47: "gsw", iso3: "gsw"},
{id: "gSW", bcp47: "gsw", iso3: "gsw"},
{id: "und", bcp47: "und", iso3: "und"},
{id: "sh", bcp47: "sh", iso3: "hbs", norm: "sr"},
{id: "hbs", bcp47: "sh", iso3: "hbs", norm: "sr"},
{id: "no", bcp47: "no", iso3: "nor", norm: "no"},
{id: "nor", bcp47: "no", iso3: "nor", norm: "no"},
{id: "cmn", bcp47: "cmn", iso3: "cmn", norm: "zh"},
}
for i, tt := range tests {
want, err := getLangID(b(tt.id))
if err != tt.err {
t.Errorf("%d:err(%s): found %q; want %q", i, tt.id, err, tt.err)
}
if err != nil {
continue
}
if id, _ := getLangISO2(b(tt.bcp47)); len(tt.bcp47) == 2 && want != id {
t.Errorf("%d:getISO2(%s): found %v; want %v", i, tt.bcp47, id, want)
}
if len(tt.iso3) == 3 {
if id, _ := getLangISO3(b(tt.iso3)); want != id {
t.Errorf("%d:getISO3(%s): found %q; want %q", i, tt.iso3, id, want)
}
if id, _ := getLangID(b(tt.iso3)); want != id {
t.Errorf("%d:getID3(%s): found %v; want %v", i, tt.iso3, id, want)
}
}
norm := want
if tt.norm != "" {
norm, _ = getLangID(b(tt.norm))
}
id, _ := normLang(want)
if id != norm {
t.Errorf("%d:norm(%s): found %v; want %v", i, tt.id, id, norm)
}
if id := want.String(); tt.bcp47 != id {
t.Errorf("%d:String(): found %s; want %s", i, id, tt.bcp47)
}
if id := want.ISO3(); tt.iso3[:3] != id {
t.Errorf("%d:iso3(): found %s; want %s", i, id, tt.iso3[:3])
}
}
}
func TestGrandfathered(t *testing.T) {
for _, tt := range []struct{ in, out string }{
{"art-lojban", "jbo"},
{"i-ami", "ami"},
{"i-bnn", "bnn"},
{"i-hak", "hak"},
{"i-klingon", "tlh"},
{"i-lux", "lb"},
{"i-navajo", "nv"},
{"i-pwn", "pwn"},
{"i-tao", "tao"},
{"i-tay", "tay"},
{"i-tsu", "tsu"},
{"no-bok", "nb"},
{"no-nyn", "nn"},
{"sgn-BE-FR", "sfb"},
{"sgn-BE-NL", "vgt"},
{"sgn-CH-DE", "sgg"},
{"sgn-ch-de", "sgg"},
{"zh-guoyu", "cmn"},
{"zh-hakka", "hak"},
{"zh-min-nan", "nan"},
{"zh-xiang", "hsn"},
// Grandfathered tags with no modern replacement will be converted as follows:
{"cel-gaulish", "xtg-x-cel-gaulish"},
{"en-GB-oed", "en-GB-oxendict"},
{"en-gb-oed", "en-GB-oxendict"},
{"i-default", "en-x-i-default"},
{"i-enochian", "und-x-i-enochian"},
{"i-mingo", "see-x-i-mingo"},
{"zh-min", "nan-x-zh-min"},
{"root", "und"},
{"en_US_POSIX", "en-US-u-va-posix"},
{"en_us_posix", "en-US-u-va-posix"},
{"en-us-posix", "en-US-u-va-posix"},
} {
got := Make(tt.in)
want := MustParse(tt.out)
if got != want {
t.Errorf("%s: got %q; want %q", tt.in, got, want)
}
}
}
func TestRegionID(t *testing.T) {
tests := []struct {
in, out string
}{
{"_ ", ""},
{"_000", ""},
{"419", "419"},
{"AA", "AA"},
{"ATF", "TF"},
{"HV", "HV"},
{"CT", "CT"},
{"DY", "DY"},
{"IC", "IC"},
{"FQ", "FQ"},
{"JT", "JT"},
{"ZZ", "ZZ"},
{"EU", "EU"},
{"QO", "QO"},
{"FX", "FX"},
}
for i, tt := range tests {
if tt.in[0] == '_' {
id := tt.in[1:]
if _, err := getRegionID(b(id)); err == nil {
t.Errorf("%d:err(%s): found nil; want error", i, id)
}
continue
}
want, _ := getRegionID(b(tt.in))
if s := want.String(); s != tt.out {
t.Errorf("%d:%s: found %q; want %q", i, tt.in, s, tt.out)
}
if len(tt.in) == 2 {
want, _ := getRegionISO2(b(tt.in))
if s := want.String(); s != tt.out {
t.Errorf("%d:getISO2(%s): found %q; want %q", i, tt.in, s, tt.out)
}
}
}
}
func TestRegionType(t *testing.T) {
for _, tt := range []struct {
r string
t byte
}{
{"NL", bcp47Region | ccTLD},
{"EU", bcp47Region | ccTLD}, // exceptionally reserved
{"AN", bcp47Region | ccTLD}, // transitionally reserved
{"DD", bcp47Region}, // deleted in ISO, deprecated in BCP 47
{"NT", bcp47Region}, // transitionally reserved, deprecated in BCP 47
{"XA", iso3166UserAssigned | bcp47Region},
{"ZZ", iso3166UserAssigned | bcp47Region},
{"AA", iso3166UserAssigned | bcp47Region},
{"QO", iso3166UserAssigned | bcp47Region},
{"QM", iso3166UserAssigned | bcp47Region},
{"XK", iso3166UserAssigned | bcp47Region},
{"CT", 0}, // deleted in ISO, not in BCP 47, canonicalized in CLDR
} {
r := MustParseRegion(tt.r)
if tp := r.typ(); tp != tt.t {
t.Errorf("Type(%s): got %x; want %x", tt.r, tp, tt.t)
}
}
}
func TestRegionISO3(t *testing.T) {
tests := []struct {
from, iso3, to string
}{
{" ", "ZZZ", "ZZ"},
{"000", "ZZZ", "ZZ"},
{"AA", "AAA", ""},
{"CT", "CTE", ""},
{"DY", "DHY", ""},
{"EU", "QUU", ""},
{"HV", "HVO", ""},
{"IC", "ZZZ", "ZZ"},
{"JT", "JTN", ""},
{"PZ", "PCZ", ""},
{"QU", "QUU", "EU"},
{"QO", "QOO", ""},
{"YD", "YMD", ""},
{"FQ", "ATF", "TF"},
{"TF", "ATF", ""},
{"FX", "FXX", ""},
{"ZZ", "ZZZ", ""},
{"419", "ZZZ", "ZZ"},
}
for _, tt := range tests {
r, _ := getRegionID(b(tt.from))
if s := r.ISO3(); s != tt.iso3 {
t.Errorf("iso3(%q): found %q; want %q", tt.from, s, tt.iso3)
}
if tt.iso3 == "" {
continue
}
want := tt.to
if tt.to == "" {
want = tt.from
}
r, _ = getRegionID(b(want))
if id, _ := getRegionISO3(b(tt.iso3)); id != r {
t.Errorf("%s: found %q; want %q", tt.iso3, id, want)
}
}
}
func TestRegionM49(t *testing.T) {
fromTests := []struct {
m49 int
id string
}{
{0, ""},
{-1, ""},
{1000, ""},
{10000, ""},
{001, "001"},
{104, "MM"},
{180, "CD"},
{230, "ET"},
{231, "ET"},
{249, "FX"},
{250, "FR"},
{276, "DE"},
{278, "DD"},
{280, "DE"},
{419, "419"},
{626, "TL"},
{736, "SD"},
{840, "US"},
{854, "BF"},
{891, "CS"},
{899, ""},
{958, "AA"},
{966, "QT"},
{967, "EU"},
{999, "ZZ"},
}
for _, tt := range fromTests {
id, err := getRegionM49(tt.m49)
if want, have := err != nil, tt.id == ""; want != have {
t.Errorf("error(%d): have %v; want %v", tt.m49, have, want)
continue
}
r, _ := getRegionID(b(tt.id))
if r != id {
t.Errorf("region(%d): have %s; want %s", tt.m49, id, r)
}
}
toTests := []struct {
m49 int
id string
}{
{0, "000"},
{0, "IC"}, // Some codes don't have an ID
{001, "001"},
{104, "MM"},
{104, "BU"},
{180, "CD"},
{180, "ZR"},
{231, "ET"},
{250, "FR"},
{249, "FX"},
{276, "DE"},
{278, "DD"},
{419, "419"},
{626, "TL"},
{626, "TP"},
{729, "SD"},
{826, "GB"},
{840, "US"},
{854, "BF"},
{891, "YU"},
{891, "CS"},
{958, "AA"},
{966, "QT"},
{967, "EU"},
{967, "QU"},
{999, "ZZ"},
// For codes that don't have an M49 code use the replacement value,
// if available.
{854, "HV"}, // maps to Burkino Faso
}
for _, tt := range toTests {
r, _ := getRegionID(b(tt.id))
if r.M49() != tt.m49 {
t.Errorf("m49(%q): have %d; want %d", tt.id, r.M49(), tt.m49)
}
}
}
func TestRegionDeprecation(t *testing.T) {
tests := []struct{ in, out string }{
{"BU", "MM"},
{"BUR", "MM"},
{"CT", "KI"},
{"DD", "DE"},
{"DDR", "DE"},
{"DY", "BJ"},
{"FX", "FR"},
{"HV", "BF"},
{"JT", "UM"},
{"MI", "UM"},
{"NH", "VU"},
{"NQ", "AQ"},
{"PU", "UM"},
{"PZ", "PA"},
{"QU", "EU"},
{"RH", "ZW"},
{"TP", "TL"},
{"UK", "GB"},
{"VD", "VN"},
{"WK", "UM"},
{"YD", "YE"},
{"NL", "NL"},
}
for _, tt := range tests {
rIn, _ := getRegionID([]byte(tt.in))
rOut, _ := getRegionISO2([]byte(tt.out))
r := normRegion(rIn)
if rOut == rIn && r != 0 {
t.Errorf("%s: was %q; want %q", tt.in, r, tt.in)
}
if rOut != rIn && r != rOut {
t.Errorf("%s: was %q; want %q", tt.in, r, tt.out)
}
}
}
func TestGetScriptID(t *testing.T) {
idx := tag.Index("0000BbbbDdddEeeeZzzz\xff\xff\xff\xff")
tests := []struct {
in string
out Script
}{
{" ", 0},
{" ", 0},
{" ", 0},
{"", 0},
{"Aaaa", 0},
{"Bbbb", 1},
{"Dddd", 2},
{"dddd", 2},
{"dDDD", 2},
{"Eeee", 3},
{"Zzzz", 4},
}
for i, tt := range tests {
if id, err := getScriptID(idx, b(tt.in)); id != tt.out {
t.Errorf("%d:%s: found %d; want %d", i, tt.in, id, tt.out)
} else if id == 0 && err == nil {
t.Errorf("%d:%s: no error; expected one", i, tt.in)
}
}
}
func TestIsPrivateUse(t *testing.T) {
type test struct {
s string
private bool
}
tests := []test{
{"en", false},
{"und", false},
{"pzn", false},
{"qaa", true},
{"qtz", true},
{"qua", false},
}
for i, tt := range tests {
x, _ := getLangID([]byte(tt.s))
if b := x.IsPrivateUse(); b != tt.private {
t.Errorf("%d: langID.IsPrivateUse(%s) was %v; want %v", i, tt.s, b, tt.private)
}
}
tests = []test{
{"001", false},
{"419", false},
{"899", false},
{"900", false},
{"957", false},
{"958", true},
{"AA", true},
{"AC", false},
{"EU", false}, // CLDR grouping, exceptionally reserved in ISO.
{"QU", true}, // Canonicalizes to EU, User-assigned in ISO.
{"QO", true}, // CLDR grouping, User-assigned in ISO.
{"QA", false},
{"QM", true},
{"QZ", true},
{"XA", true},
{"XK", true}, // Assigned to Kosovo in CLDR, User-assigned in ISO.
{"XZ", true},
{"ZW", false},
{"ZZ", true},
}
for i, tt := range tests {
x, _ := getRegionID([]byte(tt.s))
if b := x.IsPrivateUse(); b != tt.private {
t.Errorf("%d: regionID.IsPrivateUse(%s) was %v; want %v", i, tt.s, b, tt.private)
}
}
tests = []test{
{"Latn", false},
{"Laaa", false}, // invalid
{"Qaaa", true},
{"Qabx", true},
{"Qaby", false},
{"Zyyy", false},
{"Zzzz", false},
}
for i, tt := range tests {
x, _ := getScriptID(script, []byte(tt.s))
if b := x.IsPrivateUse(); b != tt.private {
t.Errorf("%d: scriptID.IsPrivateUse(%s) was %v; want %v", i, tt.s, b, tt.private)
}
}
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/match.go
+226
View File
@@ -0,0 +1,226 @@
// 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 language
import "errors"
type scriptRegionFlags uint8
const (
isList = 1 << iota
scriptInFrom
regionInFrom
)
func (t *Tag) setUndefinedLang(id Language) {
if t.LangID == 0 {
t.LangID = id
}
}
func (t *Tag) setUndefinedScript(id Script) {
if t.ScriptID == 0 {
t.ScriptID = id
}
}
func (t *Tag) setUndefinedRegion(id Region) {
if t.RegionID == 0 || t.RegionID.Contains(id) {
t.RegionID = id
}
}
// ErrMissingLikelyTagsData indicates no information was available
// to compute likely values of missing tags.
var ErrMissingLikelyTagsData = errors.New("missing likely tags data")
// addLikelySubtags sets subtags to their most likely value, given the locale.
// In most cases this means setting fields for unknown values, but in some
// cases it may alter a value. It returns an ErrMissingLikelyTagsData error
// if the given locale cannot be expanded.
func (t Tag) addLikelySubtags() (Tag, error) {
id, err := addTags(t)
if err != nil {
return t, err
} else if id.equalTags(t) {
return t, nil
}
id.RemakeString()
return id, nil
}
// specializeRegion attempts to specialize a group region.
func specializeRegion(t *Tag) bool {
if i := regionInclusion[t.RegionID]; i < nRegionGroups {
x := likelyRegionGroup[i]
if Language(x.lang) == t.LangID && Script(x.script) == t.ScriptID {
t.RegionID = Region(x.region)
}
return true
}
return false
}
// Maximize returns a new tag with missing tags filled in.
func (t Tag) Maximize() (Tag, error) {
return addTags(t)
}
func addTags(t Tag) (Tag, error) {
// We leave private use identifiers alone.
if t.IsPrivateUse() {
return t, nil
}
if t.ScriptID != 0 && t.RegionID != 0 {
if t.LangID != 0 {
// already fully specified
specializeRegion(&t)
return t, nil
}
// Search matches for und-script-region. Note that for these cases
// region will never be a group so there is no need to check for this.
list := likelyRegion[t.RegionID : t.RegionID+1]
if x := list[0]; x.flags&isList != 0 {
list = likelyRegionList[x.lang : x.lang+uint16(x.script)]
}
for _, x := range list {
// Deviating from the spec. See match_test.go for details.
if Script(x.script) == t.ScriptID {
t.setUndefinedLang(Language(x.lang))
return t, nil
}
}
}
if t.LangID != 0 {
// Search matches for lang-script and lang-region, where lang != und.
if t.LangID < langNoIndexOffset {
x := likelyLang[t.LangID]
if x.flags&isList != 0 {
list := likelyLangList[x.region : x.region+uint16(x.script)]
if t.ScriptID != 0 {
for _, x := range list {
if Script(x.script) == t.ScriptID && x.flags&scriptInFrom != 0 {
t.setUndefinedRegion(Region(x.region))
return t, nil
}
}
} else if t.RegionID != 0 {
count := 0
goodScript := true
tt := t
for _, x := range list {
// We visit all entries for which the script was not
// defined, including the ones where the region was not
// defined. This allows for proper disambiguation within
// regions.
if x.flags&scriptInFrom == 0 && t.RegionID.Contains(Region(x.region)) {
tt.RegionID = Region(x.region)
tt.setUndefinedScript(Script(x.script))
goodScript = goodScript && tt.ScriptID == Script(x.script)
count++
}
}
if count == 1 {
return tt, nil
}
// Even if we fail to find a unique Region, we might have
// an unambiguous script.
if goodScript {
t.ScriptID = tt.ScriptID
}
}
}
}
} else {
// Search matches for und-script.
if t.ScriptID != 0 {
x := likelyScript[t.ScriptID]
if x.region != 0 {
t.setUndefinedRegion(Region(x.region))
t.setUndefinedLang(Language(x.lang))
return t, nil
}
}
// Search matches for und-region. If und-script-region exists, it would
// have been found earlier.
if t.RegionID != 0 {
if i := regionInclusion[t.RegionID]; i < nRegionGroups {
x := likelyRegionGroup[i]
if x.region != 0 {
t.setUndefinedLang(Language(x.lang))
t.setUndefinedScript(Script(x.script))
t.RegionID = Region(x.region)
}
} else {
x := likelyRegion[t.RegionID]
if x.flags&isList != 0 {
x = likelyRegionList[x.lang]
}
if x.script != 0 && x.flags != scriptInFrom {
t.setUndefinedLang(Language(x.lang))
t.setUndefinedScript(Script(x.script))
return t, nil
}
}
}
}
// Search matches for lang.
if t.LangID < langNoIndexOffset {
x := likelyLang[t.LangID]
if x.flags&isList != 0 {
x = likelyLangList[x.region]
}
if x.region != 0 {
t.setUndefinedScript(Script(x.script))
t.setUndefinedRegion(Region(x.region))
}
specializeRegion(&t)
if t.LangID == 0 {
t.LangID = _en // default language
}
return t, nil
}
return t, ErrMissingLikelyTagsData
}
func (t *Tag) setTagsFrom(id Tag) {
t.LangID = id.LangID
t.ScriptID = id.ScriptID
t.RegionID = id.RegionID
}
// minimize removes the region or script subtags from t such that
// t.addLikelySubtags() == t.minimize().addLikelySubtags().
func (t Tag) minimize() (Tag, error) {
t, err := minimizeTags(t)
if err != nil {
return t, err
}
t.RemakeString()
return t, nil
}
// minimizeTags mimics the behavior of the ICU 51 C implementation.
func minimizeTags(t Tag) (Tag, error) {
if t.equalTags(Und) {
return t, nil
}
max, err := addTags(t)
if err != nil {
return t, err
}
for _, id := range [...]Tag{
{LangID: t.LangID},
{LangID: t.LangID, RegionID: t.RegionID},
{LangID: t.LangID, ScriptID: t.ScriptID},
} {
if x, err := addTags(id); err == nil && max.equalTags(x) {
t.setTagsFrom(id)
break
}
}
return t, nil
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/match_test.go
+161
View File
@@ -0,0 +1,161 @@
// 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 language
import (
"flag"
"testing"
)
var verbose = flag.Bool("verbose", false, "set to true to print the internal tables of matchers")
func TestAddLikelySubtags(t *testing.T) {
tests := []struct{ in, out string }{
{"aa", "aa-Latn-ET"},
{"aa-Latn", "aa-Latn-ET"},
{"aa-Arab", "aa-Arab-ET"},
{"aa-Arab-ER", "aa-Arab-ER"},
{"kk", "kk-Cyrl-KZ"},
{"kk-CN", "kk-Arab-CN"},
{"cmn", "cmn"},
{"zh-AU", "zh-Hant-AU"},
{"zh-VN", "zh-Hant-VN"},
{"zh-SG", "zh-Hans-SG"},
{"zh-Hant", "zh-Hant-TW"},
{"zh-Hani", "zh-Hani-CN"},
{"und-Hani", "zh-Hani-CN"},
{"und", "en-Latn-US"},
{"und-GB", "en-Latn-GB"},
{"und-CW", "pap-Latn-CW"},
{"und-YT", "fr-Latn-YT"},
{"und-Arab", "ar-Arab-EG"},
{"und-AM", "hy-Armn-AM"},
{"und-TW", "zh-Hant-TW"},
{"und-002", "en-Latn-NG"},
{"und-Latn-002", "en-Latn-NG"},
{"en-Latn-002", "en-Latn-NG"},
{"en-002", "en-Latn-NG"},
{"en-001", "en-Latn-US"},
{"und-003", "en-Latn-US"},
{"und-GB", "en-Latn-GB"},
{"Latn-001", "en-Latn-US"},
{"en-001", "en-Latn-US"},
{"es-419", "es-Latn-419"},
{"he-145", "he-Hebr-IL"},
{"ky-145", "ky-Latn-TR"},
{"kk", "kk-Cyrl-KZ"},
// Don't specialize duplicate and ambiguous matches.
{"kk-034", "kk-Arab-034"}, // Matches IR and AF. Both are Arab.
{"ku-145", "ku-Latn-TR"}, // Matches IQ, TR, and LB, but kk -> TR.
{"und-Arab-CC", "ms-Arab-CC"},
{"und-Arab-GB", "ks-Arab-GB"},
{"und-Hans-CC", "zh-Hans-CC"},
{"und-CC", "en-Latn-CC"},
{"sr", "sr-Cyrl-RS"},
{"sr-151", "sr-Latn-151"}, // Matches RO and RU.
// We would like addLikelySubtags to generate the same results if the input
// only changes by adding tags that would otherwise have been added
// by the expansion.
// In other words:
// und-AA -> xx-Scrp-AA implies und-Scrp-AA -> xx-Scrp-AA
// und-AA -> xx-Scrp-AA implies xx-AA -> xx-Scrp-AA
// und-Scrp -> xx-Scrp-AA implies und-Scrp-AA -> xx-Scrp-AA
// und-Scrp -> xx-Scrp-AA implies xx-Scrp -> xx-Scrp-AA
// xx -> xx-Scrp-AA implies xx-Scrp -> xx-Scrp-AA
// xx -> xx-Scrp-AA implies xx-AA -> xx-Scrp-AA
//
// The algorithm specified in
// https://unicode.org/reports/tr35/tr35-9.html#Supplemental_Data,
// Section C.10, does not handle the first case. For example,
// the CLDR data contains an entry und-BJ -> fr-Latn-BJ, but not
// there is no rule for und-Latn-BJ. According to spec, und-Latn-BJ
// would expand to en-Latn-BJ, violating the aforementioned principle.
// We deviate from the spec by letting und-Scrp-AA expand to xx-Scrp-AA
// if a rule of the form und-AA -> xx-Scrp-AA is defined.
// Note that as of version 23, CLDR has some explicitly specified
// entries that do not conform to these rules. The implementation
// will not correct these explicit inconsistencies. A later versions of CLDR
// is supposed to fix this.
{"und-Latn-BJ", "fr-Latn-BJ"},
{"und-Bugi-ID", "bug-Bugi-ID"},
// regions, scripts and languages without definitions
{"und-Arab-AA", "ar-Arab-AA"},
{"und-Afak-RE", "fr-Afak-RE"},
{"und-Arab-GB", "ks-Arab-GB"},
{"abp-Arab-GB", "abp-Arab-GB"},
// script has preference over region
{"und-Arab-NL", "ar-Arab-NL"},
{"zza", "zza-Latn-TR"},
// preserve variants and extensions
{"de-1901", "de-Latn-DE-1901"},
{"de-x-abc", "de-Latn-DE-x-abc"},
{"de-1901-x-abc", "de-Latn-DE-1901-x-abc"},
{"x-abc", "x-abc"}, // TODO: is this the desired behavior?
}
for i, tt := range tests {
in, _ := Parse(tt.in)
out, _ := Parse(tt.out)
in, _ = in.addLikelySubtags()
if in.String() != out.String() {
t.Errorf("%d: add(%s) was %s; want %s", i, tt.in, in, tt.out)
}
}
}
func TestMinimize(t *testing.T) {
tests := []struct{ in, out string }{
{"aa", "aa"},
{"aa-Latn", "aa"},
{"aa-Latn-ET", "aa"},
{"aa-ET", "aa"},
{"aa-Arab", "aa-Arab"},
{"aa-Arab-ER", "aa-Arab-ER"},
{"aa-Arab-ET", "aa-Arab"},
{"und", "und"},
{"und-Latn", "und"},
{"und-Latn-US", "und"},
{"en-Latn-US", "en"},
{"cmn", "cmn"},
{"cmn-Hans", "cmn-Hans"},
{"cmn-Hant", "cmn-Hant"},
{"zh-AU", "zh-AU"},
{"zh-VN", "zh-VN"},
{"zh-SG", "zh-SG"},
{"zh-Hant", "zh-Hant"},
{"zh-Hant-TW", "zh-TW"},
{"zh-Hans", "zh"},
{"zh-Hani", "zh-Hani"},
{"und-Hans", "und-Hans"},
{"und-Hani", "und-Hani"},
{"und-CW", "und-CW"},
{"und-YT", "und-YT"},
{"und-Arab", "und-Arab"},
{"und-AM", "und-AM"},
{"und-Arab-CC", "und-Arab-CC"},
{"und-CC", "und-CC"},
{"und-Latn-BJ", "und-BJ"},
{"und-Bugi-ID", "und-Bugi"},
{"bug-Bugi-ID", "bug-Bugi"},
// regions, scripts and languages without definitions
{"und-Arab-AA", "und-Arab-AA"},
// preserve variants and extensions
{"de-Latn-1901", "de-1901"},
{"de-Latn-x-abc", "de-x-abc"},
{"de-DE-1901-x-abc", "de-1901-x-abc"},
{"x-abc", "x-abc"}, // TODO: is this the desired behavior?
}
for i, tt := range tests {
in, _ := Parse(tt.in)
out, _ := Parse(tt.out)
min, _ := in.minimize()
if min.String() != out.String() {
t.Errorf("%d: min(%s) was %s; want %s", i, tt.in, min, tt.out)
}
max, _ := min.addLikelySubtags()
if x, _ := in.addLikelySubtags(); x.String() != max.String() {
t.Errorf("%d: max(min(%s)) = %s; want %s", i, tt.in, max, x)
}
}
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/parse.go
+608
View File
@@ -0,0 +1,608 @@
// 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 language
import (
"bytes"
"errors"
"fmt"
"sort"
"golang.org/x/text/internal/tag"
)
// isAlpha returns true if the byte is not a digit.
// b must be an ASCII letter or digit.
func isAlpha(b byte) bool {
return b > '9'
}
// isAlphaNum returns true if the string contains only ASCII letters or digits.
func isAlphaNum(s []byte) bool {
for _, c := range s {
if !('a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' || '0' <= c && c <= '9') {
return false
}
}
return true
}
// ErrSyntax is returned by any of the parsing functions when the
// input is not well-formed, according to BCP 47.
// TODO: return the position at which the syntax error occurred?
var ErrSyntax = errors.New("language: tag is not well-formed")
// ErrDuplicateKey is returned when a tag contains the same key twice with
// different values in the -u section.
var ErrDuplicateKey = errors.New("language: different values for same key in -u extension")
// ValueError is returned by any of the parsing functions when the
// input is well-formed but the respective subtag is not recognized
// as a valid value.
type ValueError struct {
v [8]byte
}
// NewValueError creates a new ValueError.
func NewValueError(tag []byte) ValueError {
var e ValueError
copy(e.v[:], tag)
return e
}
func (e ValueError) tag() []byte {
n := bytes.IndexByte(e.v[:], 0)
if n == -1 {
n = 8
}
return e.v[:n]
}
// Error implements the error interface.
func (e ValueError) Error() string {
return fmt.Sprintf("language: subtag %q is well-formed but unknown", e.tag())
}
// Subtag returns the subtag for which the error occurred.
func (e ValueError) Subtag() string {
return string(e.tag())
}
// scanner is used to scan BCP 47 tokens, which are separated by _ or -.
type scanner struct {
b []byte
bytes [max99thPercentileSize]byte
token []byte
start int // start position of the current token
end int // end position of the current token
next int // next point for scan
err error
done bool
}
func makeScannerString(s string) scanner {
scan := scanner{}
if len(s) <= len(scan.bytes) {
scan.b = scan.bytes[:copy(scan.bytes[:], s)]
} else {
scan.b = []byte(s)
}
scan.init()
return scan
}
// makeScanner returns a scanner using b as the input buffer.
// b is not copied and may be modified by the scanner routines.
func makeScanner(b []byte) scanner {
scan := scanner{b: b}
scan.init()
return scan
}
func (s *scanner) init() {
for i, c := range s.b {
if c == '_' {
s.b[i] = '-'
}
}
s.scan()
}
// restToLower converts the string between start and end to lower case.
func (s *scanner) toLower(start, end int) {
for i := start; i < end; i++ {
c := s.b[i]
if 'A' <= c && c <= 'Z' {
s.b[i] += 'a' - 'A'
}
}
}
func (s *scanner) setError(e error) {
if s.err == nil || (e == ErrSyntax && s.err != ErrSyntax) {
s.err = e
}
}
// resizeRange shrinks or grows the array at position oldStart such that
// a new string of size newSize can fit between oldStart and oldEnd.
// Sets the scan point to after the resized range.
func (s *scanner) resizeRange(oldStart, oldEnd, newSize int) {
s.start = oldStart
if end := oldStart + newSize; end != oldEnd {
diff := end - oldEnd
var b []byte
if n := len(s.b) + diff; n > cap(s.b) {
b = make([]byte, n)
copy(b, s.b[:oldStart])
} else {
b = s.b[:n]
}
copy(b[end:], s.b[oldEnd:])
s.b = b
s.next = end + (s.next - s.end)
s.end = end
}
}
// replace replaces the current token with repl.
func (s *scanner) replace(repl string) {
s.resizeRange(s.start, s.end, len(repl))
copy(s.b[s.start:], repl)
}
// gobble removes the current token from the input.
// Caller must call scan after calling gobble.
func (s *scanner) gobble(e error) {
s.setError(e)
if s.start == 0 {
s.b = s.b[:+copy(s.b, s.b[s.next:])]
s.end = 0
} else {
s.b = s.b[:s.start-1+copy(s.b[s.start-1:], s.b[s.end:])]
s.end = s.start - 1
}
s.next = s.start
}
// deleteRange removes the given range from s.b before the current token.
func (s *scanner) deleteRange(start, end int) {
s.b = s.b[:start+copy(s.b[start:], s.b[end:])]
diff := end - start
s.next -= diff
s.start -= diff
s.end -= diff
}
// scan parses the next token of a BCP 47 string. Tokens that are larger
// than 8 characters or include non-alphanumeric characters result in an error
// and are gobbled and removed from the output.
// It returns the end position of the last token consumed.
func (s *scanner) scan() (end int) {
end = s.end
s.token = nil
for s.start = s.next; s.next < len(s.b); {
i := bytes.IndexByte(s.b[s.next:], '-')
if i == -1 {
s.end = len(s.b)
s.next = len(s.b)
i = s.end - s.start
} else {
s.end = s.next + i
s.next = s.end + 1
}
token := s.b[s.start:s.end]
if i < 1 || i > 8 || !isAlphaNum(token) {
s.gobble(ErrSyntax)
continue
}
s.token = token
return end
}
if n := len(s.b); n > 0 && s.b[n-1] == '-' {
s.setError(ErrSyntax)
s.b = s.b[:len(s.b)-1]
}
s.done = true
return end
}
// acceptMinSize parses multiple tokens of the given size or greater.
// It returns the end position of the last token consumed.
func (s *scanner) acceptMinSize(min int) (end int) {
end = s.end
s.scan()
for ; len(s.token) >= min; s.scan() {
end = s.end
}
return end
}
// Parse parses the given BCP 47 string and returns a valid Tag. If parsing
// failed it returns an error and any part of the tag that could be parsed.
// If parsing succeeded but an unknown value was found, it returns
// ValueError. The Tag returned in this case is just stripped of the unknown
// value. All other values are preserved. It accepts tags in the BCP 47 format
// and extensions to this standard defined in
// https://www.unicode.org/reports/tr35/#Unicode_Language_and_Locale_Identifiers.
func Parse(s string) (t Tag, err error) {
// TODO: consider supporting old-style locale key-value pairs.
if s == "" {
return Und, ErrSyntax
}
defer func() {
if recover() != nil {
t = Und
err = ErrSyntax
return
}
}()
if len(s) <= maxAltTaglen {
b := [maxAltTaglen]byte{}
for i, c := range s {
// Generating invalid UTF-8 is okay as it won't match.
if 'A' <= c && c <= 'Z' {
c += 'a' - 'A'
} else if c == '_' {
c = '-'
}
b[i] = byte(c)
}
if t, ok := grandfathered(b); ok {
return t, nil
}
}
scan := makeScannerString(s)
return parse(&scan, s)
}
func parse(scan *scanner, s string) (t Tag, err error) {
t = Und
var end int
if n := len(scan.token); n <= 1 {
scan.toLower(0, len(scan.b))
if n == 0 || scan.token[0] != 'x' {
return t, ErrSyntax
}
end = parseExtensions(scan)
} else if n >= 4 {
return Und, ErrSyntax
} else { // the usual case
t, end = parseTag(scan, true)
if n := len(scan.token); n == 1 {
t.pExt = uint16(end)
end = parseExtensions(scan)
} else if end < len(scan.b) {
scan.setError(ErrSyntax)
scan.b = scan.b[:end]
}
}
if int(t.pVariant) < len(scan.b) {
if end < len(s) {
s = s[:end]
}
if len(s) > 0 && tag.Compare(s, scan.b) == 0 {
t.str = s
} else {
t.str = string(scan.b)
}
} else {
t.pVariant, t.pExt = 0, 0
}
return t, scan.err
}
// parseTag parses language, script, region and variants.
// It returns a Tag and the end position in the input that was parsed.
// If doNorm is true, then <lang>-<extlang> will be normalized to <extlang>.
func parseTag(scan *scanner, doNorm bool) (t Tag, end int) {
var e error
// TODO: set an error if an unknown lang, script or region is encountered.
t.LangID, e = getLangID(scan.token)
scan.setError(e)
scan.replace(t.LangID.String())
langStart := scan.start
end = scan.scan()
for len(scan.token) == 3 && isAlpha(scan.token[0]) {
// From http://tools.ietf.org/html/bcp47, <lang>-<extlang> tags are equivalent
// to a tag of the form <extlang>.
if doNorm {
lang, e := getLangID(scan.token)
if lang != 0 {
t.LangID = lang
langStr := lang.String()
copy(scan.b[langStart:], langStr)
scan.b[langStart+len(langStr)] = '-'
scan.start = langStart + len(langStr) + 1
}
scan.gobble(e)
}
end = scan.scan()
}
if len(scan.token) == 4 && isAlpha(scan.token[0]) {
t.ScriptID, e = getScriptID(script, scan.token)
if t.ScriptID == 0 {
scan.gobble(e)
}
end = scan.scan()
}
if n := len(scan.token); n >= 2 && n <= 3 {
t.RegionID, e = getRegionID(scan.token)
if t.RegionID == 0 {
scan.gobble(e)
} else {
scan.replace(t.RegionID.String())
}
end = scan.scan()
}
scan.toLower(scan.start, len(scan.b))
t.pVariant = byte(end)
end = parseVariants(scan, end, t)
t.pExt = uint16(end)
return t, end
}
var separator = []byte{'-'}
// parseVariants scans tokens as long as each token is a valid variant string.
// Duplicate variants are removed.
func parseVariants(scan *scanner, end int, t Tag) int {
start := scan.start
varIDBuf := [4]uint8{}
variantBuf := [4][]byte{}
varID := varIDBuf[:0]
variant := variantBuf[:0]
last := -1
needSort := false
for ; len(scan.token) >= 4; scan.scan() {
// TODO: measure the impact of needing this conversion and redesign
// the data structure if there is an issue.
v, ok := variantIndex[string(scan.token)]
if !ok {
// unknown variant
// TODO: allow user-defined variants?
scan.gobble(NewValueError(scan.token))
continue
}
varID = append(varID, v)
variant = append(variant, scan.token)
if !needSort {
if last < int(v) {
last = int(v)
} else {
needSort = true
// There is no legal combinations of more than 7 variants
// (and this is by no means a useful sequence).
const maxVariants = 8
if len(varID) > maxVariants {
break
}
}
}
end = scan.end
}
if needSort {
sort.Sort(variantsSort{varID, variant})
k, l := 0, -1
for i, v := range varID {
w := int(v)
if l == w {
// Remove duplicates.
continue
}
varID[k] = varID[i]
variant[k] = variant[i]
k++
l = w
}
if str := bytes.Join(variant[:k], separator); len(str) == 0 {
end = start - 1
} else {
scan.resizeRange(start, end, len(str))
copy(scan.b[scan.start:], str)
end = scan.end
}
}
return end
}
type variantsSort struct {
i []uint8
v [][]byte
}
func (s variantsSort) Len() int {
return len(s.i)
}
func (s variantsSort) Swap(i, j int) {
s.i[i], s.i[j] = s.i[j], s.i[i]
s.v[i], s.v[j] = s.v[j], s.v[i]
}
func (s variantsSort) Less(i, j int) bool {
return s.i[i] < s.i[j]
}
type bytesSort struct {
b [][]byte
n int // first n bytes to compare
}
func (b bytesSort) Len() int {
return len(b.b)
}
func (b bytesSort) Swap(i, j int) {
b.b[i], b.b[j] = b.b[j], b.b[i]
}
func (b bytesSort) Less(i, j int) bool {
for k := 0; k < b.n; k++ {
if b.b[i][k] == b.b[j][k] {
continue
}
return b.b[i][k] < b.b[j][k]
}
return false
}
// parseExtensions parses and normalizes the extensions in the buffer.
// It returns the last position of scan.b that is part of any extension.
// It also trims scan.b to remove excess parts accordingly.
func parseExtensions(scan *scanner) int {
start := scan.start
exts := [][]byte{}
private := []byte{}
end := scan.end
for len(scan.token) == 1 {
extStart := scan.start
ext := scan.token[0]
end = parseExtension(scan)
extension := scan.b[extStart:end]
if len(extension) < 3 || (ext != 'x' && len(extension) < 4) {
scan.setError(ErrSyntax)
end = extStart
continue
} else if start == extStart && (ext == 'x' || scan.start == len(scan.b)) {
scan.b = scan.b[:end]
return end
} else if ext == 'x' {
private = extension
break
}
exts = append(exts, extension)
}
sort.Sort(bytesSort{exts, 1})
if len(private) > 0 {
exts = append(exts, private)
}
scan.b = scan.b[:start]
if len(exts) > 0 {
scan.b = append(scan.b, bytes.Join(exts, separator)...)
} else if start > 0 {
// Strip trailing '-'.
scan.b = scan.b[:start-1]
}
return end
}
// parseExtension parses a single extension and returns the position of
// the extension end.
func parseExtension(scan *scanner) int {
start, end := scan.start, scan.end
switch scan.token[0] {
case 'u': // https://www.ietf.org/rfc/rfc6067.txt
attrStart := end
scan.scan()
for last := []byte{}; len(scan.token) > 2; scan.scan() {
if bytes.Compare(scan.token, last) != -1 {
// Attributes are unsorted. Start over from scratch.
p := attrStart + 1
scan.next = p
attrs := [][]byte{}
for scan.scan(); len(scan.token) > 2; scan.scan() {
attrs = append(attrs, scan.token)
end = scan.end
}
sort.Sort(bytesSort{attrs, 3})
copy(scan.b[p:], bytes.Join(attrs, separator))
break
}
last = scan.token
end = scan.end
}
// Scan key-type sequences. A key is of length 2 and may be followed
// by 0 or more "type" subtags from 3 to the maximum of 8 letters.
var last, key []byte
for attrEnd := end; len(scan.token) == 2; last = key {
key = scan.token
end = scan.end
for scan.scan(); end < scan.end && len(scan.token) > 2; scan.scan() {
end = scan.end
}
// TODO: check key value validity
if bytes.Compare(key, last) != 1 || scan.err != nil {
// We have an invalid key or the keys are not sorted.
// Start scanning keys from scratch and reorder.
p := attrEnd + 1
scan.next = p
keys := [][]byte{}
for scan.scan(); len(scan.token) == 2; {
keyStart := scan.start
end = scan.end
for scan.scan(); end < scan.end && len(scan.token) > 2; scan.scan() {
end = scan.end
}
keys = append(keys, scan.b[keyStart:end])
}
sort.Stable(bytesSort{keys, 2})
if n := len(keys); n > 0 {
k := 0
for i := 1; i < n; i++ {
if !bytes.Equal(keys[k][:2], keys[i][:2]) {
k++
keys[k] = keys[i]
} else if !bytes.Equal(keys[k], keys[i]) {
scan.setError(ErrDuplicateKey)
}
}
keys = keys[:k+1]
}
reordered := bytes.Join(keys, separator)
if e := p + len(reordered); e < end {
scan.deleteRange(e, end)
end = e
}
copy(scan.b[p:], reordered)
break
}
}
case 't': // https://www.ietf.org/rfc/rfc6497.txt
scan.scan()
if n := len(scan.token); n >= 2 && n <= 3 && isAlpha(scan.token[1]) {
_, end = parseTag(scan, false)
scan.toLower(start, end)
}
for len(scan.token) == 2 && !isAlpha(scan.token[1]) {
end = scan.acceptMinSize(3)
}
case 'x':
end = scan.acceptMinSize(1)
default:
end = scan.acceptMinSize(2)
}
return end
}
// getExtension returns the name, body and end position of the extension.
func getExtension(s string, p int) (end int, ext string) {
if s[p] == '-' {
p++
}
if s[p] == 'x' {
return len(s), s[p:]
}
end = nextExtension(s, p)
return end, s[p:end]
}
// nextExtension finds the next extension within the string, searching
// for the -<char>- pattern from position p.
// In the fast majority of cases, language tags will have at most
// one extension and extensions tend to be small.
func nextExtension(s string, p int) int {
for n := len(s) - 3; p < n; {
if s[p] == '-' {
if s[p+2] == '-' {
return p
}
p += 3
} else {
p++
}
}
return len(s)
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/parse_test.go
+371
View File
@@ -0,0 +1,371 @@
// 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 language
import (
"bytes"
"strings"
"testing"
"golang.org/x/text/internal/tag"
)
type scanTest struct {
ok bool // true if scanning does not result in an error
in string
tok []string // the expected tokens
}
var tests = []scanTest{
{true, "", []string{}},
{true, "1", []string{"1"}},
{true, "en", []string{"en"}},
{true, "root", []string{"root"}},
{true, "maxchars", []string{"maxchars"}},
{false, "bad/", []string{}},
{false, "morethan8", []string{}},
{false, "-", []string{}},
{false, "----", []string{}},
{false, "_", []string{}},
{true, "en-US", []string{"en", "US"}},
{true, "en_US", []string{"en", "US"}},
{false, "en-US-", []string{"en", "US"}},
{false, "en-US--", []string{"en", "US"}},
{false, "en-US---", []string{"en", "US"}},
{false, "en--US", []string{"en", "US"}},
{false, "-en-US", []string{"en", "US"}},
{false, "-en--US-", []string{"en", "US"}},
{false, "-en--US-", []string{"en", "US"}},
{false, "en-.-US", []string{"en", "US"}},
{false, ".-en--US-.", []string{"en", "US"}},
{false, "en-u.-US", []string{"en", "US"}},
{true, "en-u1-US", []string{"en", "u1", "US"}},
{true, "maxchar1_maxchar2-maxchar3", []string{"maxchar1", "maxchar2", "maxchar3"}},
{false, "moreThan8-moreThan8-e", []string{"e"}},
}
func TestScan(t *testing.T) {
for i, tt := range tests {
scan := makeScannerString(tt.in)
for j := 0; !scan.done; j++ {
if j >= len(tt.tok) {
t.Errorf("%d: extra token %q", i, scan.token)
} else if tag.Compare(tt.tok[j], scan.token) != 0 {
t.Errorf("%d: token %d: found %q; want %q", i, j, scan.token, tt.tok[j])
break
}
scan.scan()
}
if s := strings.Join(tt.tok, "-"); tag.Compare(s, bytes.Replace(scan.b, b("_"), b("-"), -1)) != 0 {
t.Errorf("%d: input: found %q; want %q", i, scan.b, s)
}
if (scan.err == nil) != tt.ok {
t.Errorf("%d: ok: found %v; want %v", i, scan.err == nil, tt.ok)
}
}
}
func TestAcceptMinSize(t *testing.T) {
for i, tt := range tests {
// count number of successive tokens with a minimum size.
for sz := 1; sz <= 8; sz++ {
scan := makeScannerString(tt.in)
scan.end, scan.next = 0, 0
end := scan.acceptMinSize(sz)
n := 0
for i := 0; i < len(tt.tok) && len(tt.tok[i]) >= sz; i++ {
n += len(tt.tok[i])
if i > 0 {
n++
}
}
if end != n {
t.Errorf("%d:%d: found len %d; want %d", i, sz, end, n)
}
}
}
}
type parseTest struct {
i int // the index of this test
in string
lang, script, region string
variants, ext string
extList []string // only used when more than one extension is present
invalid bool
rewrite bool // special rewrite not handled by parseTag
changed bool // string needed to be reformatted
}
func parseTests() []parseTest {
tests := []parseTest{
{in: "root", lang: "und"},
{in: "und", lang: "und"},
{in: "en", lang: "en"},
{in: "xy", lang: "und", invalid: true},
{in: "en-ZY", lang: "en", invalid: true},
{in: "gsw", lang: "gsw"},
{in: "sr_Latn", lang: "sr", script: "Latn"},
{in: "af-Arab", lang: "af", script: "Arab"},
{in: "nl-BE", lang: "nl", region: "BE"},
{in: "es-419", lang: "es", region: "419"},
{in: "und-001", lang: "und", region: "001"},
{in: "de-latn-be", lang: "de", script: "Latn", region: "BE"},
// Variants
{in: "de-1901", lang: "de", variants: "1901"},
// Accept with unsuppressed script.
{in: "de-Latn-1901", lang: "de", script: "Latn", variants: "1901"},
// Specialized.
{in: "sl-rozaj", lang: "sl", variants: "rozaj"},
{in: "sl-rozaj-lipaw", lang: "sl", variants: "rozaj-lipaw"},
{in: "sl-rozaj-biske", lang: "sl", variants: "rozaj-biske"},
{in: "sl-rozaj-biske-1994", lang: "sl", variants: "rozaj-biske-1994"},
{in: "sl-rozaj-1994", lang: "sl", variants: "rozaj-1994"},
// Maximum number of variants while adhering to prefix rules.
{in: "sl-rozaj-biske-1994-alalc97-fonipa-fonupa-fonxsamp", lang: "sl", variants: "rozaj-biske-1994-alalc97-fonipa-fonupa-fonxsamp"},
// Sorting.
{in: "sl-1994-biske-rozaj", lang: "sl", variants: "rozaj-biske-1994", changed: true},
{in: "sl-rozaj-biske-1994-alalc97-fonupa-fonipa-fonxsamp", lang: "sl", variants: "rozaj-biske-1994-alalc97-fonipa-fonupa-fonxsamp", changed: true},
{in: "nl-fonxsamp-alalc97-fonipa-fonupa", lang: "nl", variants: "alalc97-fonipa-fonupa-fonxsamp", changed: true},
// Duplicates variants are removed, but not an error.
{in: "nl-fonupa-fonupa", lang: "nl", variants: "fonupa"},
// Variants that do not have correct prefixes. We still accept these.
{in: "de-Cyrl-1901", lang: "de", script: "Cyrl", variants: "1901"},
{in: "sl-rozaj-lipaw-1994", lang: "sl", variants: "rozaj-lipaw-1994"},
{in: "sl-1994-biske-rozaj-1994-biske-rozaj", lang: "sl", variants: "rozaj-biske-1994", changed: true},
{in: "de-Cyrl-1901", lang: "de", script: "Cyrl", variants: "1901"},
// Invalid variant.
{in: "de-1902", lang: "de", variants: "", invalid: true},
{in: "EN_CYRL", lang: "en", script: "Cyrl"},
// private use and extensions
{in: "x-a-b-c-d", ext: "x-a-b-c-d"},
{in: "x_A.-B-C_D", ext: "x-b-c-d", invalid: true, changed: true},
{in: "x-aa-bbbb-cccccccc-d", ext: "x-aa-bbbb-cccccccc-d"},
{in: "en-c_cc-b-bbb-a-aaa", lang: "en", changed: true, extList: []string{"a-aaa", "b-bbb", "c-cc"}},
{in: "en-x_cc-b-bbb-a-aaa", lang: "en", ext: "x-cc-b-bbb-a-aaa", changed: true},
{in: "en-c_cc-b-bbb-a-aaa-x-x", lang: "en", changed: true, extList: []string{"a-aaa", "b-bbb", "c-cc", "x-x"}},
{in: "en-v-c", lang: "en", ext: "", invalid: true},
{in: "en-v-abcdefghi", lang: "en", ext: "", invalid: true},
{in: "en-v-abc-x", lang: "en", ext: "v-abc", invalid: true},
{in: "en-v-abc-x-", lang: "en", ext: "v-abc", invalid: true},
{in: "en-v-abc-w-x-xx", lang: "en", extList: []string{"v-abc", "x-xx"}, invalid: true, changed: true},
{in: "en-v-abc-w-y-yx", lang: "en", extList: []string{"v-abc", "y-yx"}, invalid: true, changed: true},
{in: "en-v-c-abc", lang: "en", ext: "c-abc", invalid: true, changed: true},
{in: "en-v-w-abc", lang: "en", ext: "w-abc", invalid: true, changed: true},
{in: "en-v-x-abc", lang: "en", ext: "x-abc", invalid: true, changed: true},
{in: "en-v-x-a", lang: "en", ext: "x-a", invalid: true, changed: true},
{in: "en-9-aa-0-aa-z-bb-x-a", lang: "en", extList: []string{"0-aa", "9-aa", "z-bb", "x-a"}, changed: true},
{in: "en-u-c", lang: "en", ext: "", invalid: true},
{in: "en-u-co-phonebk", lang: "en", ext: "u-co-phonebk"},
{in: "en-u-co-phonebk-ca", lang: "en", ext: "u-ca-co-phonebk", changed: true},
{in: "en-u-nu-arabic-co-phonebk-ca", lang: "en", ext: "u-ca-co-phonebk-nu-arabic", changed: true},
{in: "en-u-nu-arabic-co-phonebk-ca-x", lang: "en", ext: "u-ca-co-phonebk-nu-arabic", invalid: true, changed: true},
{in: "en-u-nu-arabic-co-phonebk-ca-s", lang: "en", ext: "u-ca-co-phonebk-nu-arabic", invalid: true, changed: true},
{in: "en-u-nu-arabic-co-phonebk-ca-a12345678", lang: "en", ext: "u-ca-co-phonebk-nu-arabic", invalid: true, changed: true},
{in: "en-u-co-phonebook", lang: "en", ext: "u-co", invalid: true},
{in: "en-u-co-phonebook-cu-xau", lang: "en", ext: "u-co-cu-xau", invalid: true, changed: true},
{in: "en-Cyrl-u-co-phonebk", lang: "en", script: "Cyrl", ext: "u-co-phonebk"},
{in: "en-US-u-co-phonebk", lang: "en", region: "US", ext: "u-co-phonebk"},
{in: "en-US-u-co-phonebk-cu-xau", lang: "en", region: "US", ext: "u-co-phonebk-cu-xau"},
{in: "en-scotland-u-co-phonebk", lang: "en", variants: "scotland", ext: "u-co-phonebk"},
{in: "en-u-cu-xua-co-phonebk", lang: "en", ext: "u-co-phonebk-cu-xua", changed: true},
{in: "en-u-def-abc-cu-xua-co-phonebk", lang: "en", ext: "u-abc-def-co-phonebk-cu-xua", changed: true},
{in: "en-u-def-abc", lang: "en", ext: "u-abc-def", changed: true},
{in: "en-u-cu-xua-co-phonebk-a-cd", lang: "en", extList: []string{"a-cd", "u-co-phonebk-cu-xua"}, changed: true},
{in: "en-u-cu-co-phonebk", lang: "en", extList: []string{"u-co-phonebk-cu"}, changed: true},
{in: "en-u-cu-xau-co", lang: "en", extList: []string{"u-co-cu-xau"}, changed: true},
// LDML spec is not specific about it, but remove duplicates and return an error if the values differ.
{in: "en-u-cu-xau-co-phonebk-cu-xau", lang: "en", ext: "u-co-phonebk-cu-xau", changed: true},
// No change as the result is a substring of the original!
{in: "en-US-u-cu-xau-cu-eur", lang: "en", region: "US", ext: "u-cu-xau", invalid: true, changed: false},
{in: "en-t-en-Cyrl-NL-fonipa", lang: "en", ext: "t-en-cyrl-nl-fonipa", changed: true},
{in: "en-t-en-Cyrl-NL-fonipa-t0-abc-def", lang: "en", ext: "t-en-cyrl-nl-fonipa-t0-abc-def", changed: true},
{in: "en-t-t0-abcd", lang: "en", ext: "t-t0-abcd"},
// Not necessary to have changed here.
{in: "en-t-nl-abcd", lang: "en", ext: "t-nl", invalid: true},
{in: "en-t-nl-latn", lang: "en", ext: "t-nl-latn"},
{in: "en-t-t0-abcd-x-a", lang: "en", extList: []string{"t-t0-abcd", "x-a"}},
{in: "en_t_pt_MLt", lang: "en", ext: "t-pt-mlt", changed: true},
{in: "en-t-fr-est", lang: "en", ext: "t-fr-est", changed: false},
{in: "fr-est", lang: "et", changed: false},
{in: "fr-est-Cyrl", lang: "et", script: "Cyrl", changed: false},
// The same input here is used in both TestParse and TestParseExtensions.
// changed should be true for this input in TestParse but changed should be false for this input in TestParseExtensions
// because the entire input has been reformatted but the extension part hasn't.
// {in: "fr-est-t-fr-est", lang: "et", ext: "t-fr-est", changed: true},
// invalid
{in: "", lang: "und", invalid: true},
{in: "-", lang: "und", invalid: true},
{in: "x", lang: "und", invalid: true},
{in: "x-", lang: "und", invalid: true},
{in: "x--", lang: "und", invalid: true},
{in: "a-a-b-c-d", lang: "und", invalid: true},
{in: "en-", lang: "en", invalid: true},
{in: "enne-", lang: "und", invalid: true},
{in: "en.", lang: "und", invalid: true},
{in: "en.-latn", lang: "und", invalid: true},
{in: "en.-en", lang: "en", invalid: true},
{in: "x-a-tooManyChars-c-d", ext: "x-a-c-d", invalid: true, changed: true},
{in: "a-tooManyChars-c-d", lang: "und", invalid: true},
// TODO: check key-value validity
// { in: "en-u-cu-xd", lang: "en", ext: "u-cu-xd", invalid: true },
{in: "en-t-abcd", lang: "en", invalid: true},
{in: "en-Latn-US-en", lang: "en", script: "Latn", region: "US", invalid: true},
// rewrites (more tests in TestGrandfathered)
{in: "zh-min-nan", lang: "nan"},
{in: "zh-yue", lang: "yue"},
{in: "zh-xiang", lang: "hsn", rewrite: true},
{in: "zh-guoyu", lang: "cmn", rewrite: true},
{in: "iw", lang: "iw"},
{in: "sgn-BE-FR", lang: "sfb", rewrite: true},
{in: "i-klingon", lang: "tlh", rewrite: true},
}
for i, tt := range tests {
tests[i].i = i
if tt.extList != nil {
tests[i].ext = strings.Join(tt.extList, "-")
}
if tt.ext != "" && tt.extList == nil {
tests[i].extList = []string{tt.ext}
}
}
return tests
}
func TestParseExtensions(t *testing.T) {
for i, tt := range parseTests() {
if tt.ext == "" || tt.rewrite {
continue
}
scan := makeScannerString(tt.in)
if len(scan.b) > 1 && scan.b[1] != '-' {
scan.end = nextExtension(string(scan.b), 0)
scan.next = scan.end + 1
scan.scan()
}
start := scan.start
scan.toLower(start, len(scan.b))
parseExtensions(&scan)
ext := string(scan.b[start:])
if ext != tt.ext {
t.Errorf("%d(%s): ext was %v; want %v", i, tt.in, ext, tt.ext)
}
if changed := !strings.HasPrefix(tt.in[start:], ext); changed != tt.changed {
t.Errorf("%d(%s): changed was %v; want %v", i, tt.in, changed, tt.changed)
}
}
}
// partChecks runs checks for each part by calling the function returned by f.
func partChecks(t *testing.T, f func(*testing.T, *parseTest) (Tag, bool)) {
for i, tt := range parseTests() {
t.Run(tt.in, func(t *testing.T) {
tag, skip := f(t, &tt)
if skip {
return
}
if l, _ := getLangID(b(tt.lang)); l != tag.LangID {
t.Errorf("%d: lang was %q; want %q", i, tag.LangID, l)
}
if sc, _ := getScriptID(script, b(tt.script)); sc != tag.ScriptID {
t.Errorf("%d: script was %q; want %q", i, tag.ScriptID, sc)
}
if r, _ := getRegionID(b(tt.region)); r != tag.RegionID {
t.Errorf("%d: region was %q; want %q", i, tag.RegionID, r)
}
if tag.str == "" {
return
}
p := int(tag.pVariant)
if p < int(tag.pExt) {
p++
}
if s, g := tag.str[p:tag.pExt], tt.variants; s != g {
t.Errorf("%d: variants was %q; want %q", i, s, g)
}
p = int(tag.pExt)
if p > 0 && p < len(tag.str) {
p++
}
if s, g := (tag.str)[p:], tt.ext; s != g {
t.Errorf("%d: extensions were %q; want %q", i, s, g)
}
})
}
}
func TestParseTag(t *testing.T) {
partChecks(t, func(t *testing.T, tt *parseTest) (id Tag, skip bool) {
if strings.HasPrefix(tt.in, "x-") || tt.rewrite {
return Tag{}, true
}
scan := makeScannerString(tt.in)
id, end := parseTag(&scan, true)
id.str = string(scan.b[:end])
tt.ext = ""
tt.extList = []string{}
return id, false
})
}
func TestParse(t *testing.T) {
partChecks(t, func(t *testing.T, tt *parseTest) (id Tag, skip bool) {
id, err := Parse(tt.in)
ext := ""
if id.str != "" {
if strings.HasPrefix(id.str, "x-") {
ext = id.str
} else if int(id.pExt) < len(id.str) && id.pExt > 0 {
ext = id.str[id.pExt+1:]
}
}
if tag, _ := Parse(id.String()); tag.String() != id.String() {
t.Errorf("%d:%s: reparse was %q; want %q", tt.i, tt.in, id.String(), tag.String())
}
if ext != tt.ext {
t.Errorf("%d:%s: ext was %q; want %q", tt.i, tt.in, ext, tt.ext)
}
changed := id.str != "" && !strings.HasPrefix(tt.in, id.str)
if changed != tt.changed {
t.Errorf("%d:%s: changed was %v; want %v", tt.i, tt.in, changed, tt.changed)
}
if (err != nil) != tt.invalid {
t.Errorf("%d:%s: invalid was %v; want %v. Error: %v", tt.i, tt.in, err != nil, tt.invalid, err)
}
return id, false
})
}
func TestErrors(t *testing.T) {
mkInvalid := func(s string) error {
return NewValueError([]byte(s))
}
tests := []struct {
in string
out error
}{
// invalid subtags.
{"ac", mkInvalid("ac")},
{"AC", mkInvalid("ac")},
{"aa-Uuuu", mkInvalid("Uuuu")},
{"aa-AB", mkInvalid("AB")},
// ill-formed wins over invalid.
{"ac-u", ErrSyntax},
{"ac-u-ca", mkInvalid("ac")},
{"ac-u-ca-co-pinyin", mkInvalid("ac")},
{"noob", ErrSyntax},
}
for _, tt := range tests {
_, err := Parse(tt.in)
if err != tt.out {
t.Errorf("%s: was %q; want %q", tt.in, err, tt.out)
}
}
}
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/tables.go
+3494
View File
File diff suppressed because it is too large Load Diff
go/pkg/mod/golang.org/x/text@v0.16.0/internal/language/tags.go
+48
View File
@@ -0,0 +1,48 @@
// 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 language
// MustParse is like Parse, but panics if the given BCP 47 tag cannot be parsed.
// It simplifies safe initialization of Tag values.
func MustParse(s string) Tag {
t, err := Parse(s)
if err != nil {
panic(err)
}
return t
}
// MustParseBase is like ParseBase, but panics if the given base cannot be parsed.
// It simplifies safe initialization of Base values.
func MustParseBase(s string) Language {
b, err := ParseBase(s)
if err != nil {
panic(err)
}
return b
}
// MustParseScript is like ParseScript, but panics if the given script cannot be
// parsed. It simplifies safe initialization of Script values.
func MustParseScript(s string) Script {
scr, err := ParseScript(s)
if err != nil {
panic(err)
}
return scr
}
// MustParseRegion is like ParseRegion, but panics if the given region cannot be
// parsed. It simplifies safe initialization of Region values.
func MustParseRegion(s string) Region {
r, err := ParseRegion(s)
if err != nil {
panic(err)
}
return r
}
// Und is the root language.
var Und Tag