chore: update golang dependencies
This commit is contained in:
parent
849be69299
commit
383de2a7df
2
go.mod
2
go.mod
|
@ -90,6 +90,7 @@ require (
|
|||
go.uber.org/multierr v1.11.0
|
||||
golang.org/x/exp v0.0.0-20230321023759-10a507213a29
|
||||
golang.org/x/net v0.10.0
|
||||
golang.org/x/text v0.11.0
|
||||
golang.org/x/time v0.0.0-20220922220347-f3bd1da661af
|
||||
)
|
||||
|
||||
|
@ -272,7 +273,6 @@ require (
|
|||
golang.org/x/sync v0.2.0 // indirect
|
||||
golang.org/x/sys v0.8.0 // indirect
|
||||
golang.org/x/term v0.8.0 // indirect
|
||||
golang.org/x/text v0.9.0 // indirect
|
||||
golang.org/x/tools v0.9.1 // indirect
|
||||
golang.org/x/xerrors v0.0.0-20220609144429-65e65417b02f // indirect
|
||||
gopkg.in/natefinch/npipe.v2 v2.0.0-20160621034901-c1b8fa8bdcce // indirect
|
||||
|
|
4
go.sum
4
go.sum
|
@ -2646,8 +2646,8 @@ golang.org/x/text v0.3.5/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
|
|||
golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
|
||||
golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
|
||||
golang.org/x/text v0.5.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
|
||||
golang.org/x/text v0.9.0 h1:2sjJmO8cDvYveuX97RDLsxlyUxLl+GHoLxBiRdHllBE=
|
||||
golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
|
||||
golang.org/x/text v0.11.0 h1:LAntKIrcmeSKERyiOh0XMV39LXS8IE9UL2yP7+f5ij4=
|
||||
golang.org/x/text v0.11.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
|
||||
golang.org/x/time v0.0.0-20180412165947-fbb02b2291d2/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
|
||||
golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
|
||||
golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
|
||||
|
|
|
@ -0,0 +1,162 @@
|
|||
// 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:generate go run gen.go gen_trieval.go
|
||||
|
||||
// Package cases provides general and language-specific case mappers.
|
||||
package cases // import "golang.org/x/text/cases"
|
||||
|
||||
import (
|
||||
"golang.org/x/text/language"
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// References:
|
||||
// - Unicode Reference Manual Chapter 3.13, 4.2, and 5.18.
|
||||
// - https://www.unicode.org/reports/tr29/
|
||||
// - https://www.unicode.org/Public/6.3.0/ucd/CaseFolding.txt
|
||||
// - https://www.unicode.org/Public/6.3.0/ucd/SpecialCasing.txt
|
||||
// - https://www.unicode.org/Public/6.3.0/ucd/DerivedCoreProperties.txt
|
||||
// - https://www.unicode.org/Public/6.3.0/ucd/auxiliary/WordBreakProperty.txt
|
||||
// - https://www.unicode.org/Public/6.3.0/ucd/auxiliary/WordBreakTest.txt
|
||||
// - http://userguide.icu-project.org/transforms/casemappings
|
||||
|
||||
// TODO:
|
||||
// - Case folding
|
||||
// - Wide and Narrow?
|
||||
// - Segmenter option for title casing.
|
||||
// - ASCII fast paths
|
||||
// - Encode Soft-Dotted property within trie somehow.
|
||||
|
||||
// A Caser transforms given input to a certain case. It implements
|
||||
// transform.Transformer.
|
||||
//
|
||||
// A Caser may be stateful and should therefore not be shared between
|
||||
// goroutines.
|
||||
type Caser struct {
|
||||
t transform.SpanningTransformer
|
||||
}
|
||||
|
||||
// Bytes returns a new byte slice with the result of converting b to the case
|
||||
// form implemented by c.
|
||||
func (c Caser) Bytes(b []byte) []byte {
|
||||
b, _, _ = transform.Bytes(c.t, b)
|
||||
return b
|
||||
}
|
||||
|
||||
// String returns a string with the result of transforming s to the case form
|
||||
// implemented by c.
|
||||
func (c Caser) String(s string) string {
|
||||
s, _, _ = transform.String(c.t, s)
|
||||
return s
|
||||
}
|
||||
|
||||
// Reset resets the Caser to be reused for new input after a previous call to
|
||||
// Transform.
|
||||
func (c Caser) Reset() { c.t.Reset() }
|
||||
|
||||
// Transform implements the transform.Transformer interface and transforms the
|
||||
// given input to the case form implemented by c.
|
||||
func (c Caser) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
return c.t.Transform(dst, src, atEOF)
|
||||
}
|
||||
|
||||
// Span implements the transform.SpanningTransformer interface.
|
||||
func (c Caser) Span(src []byte, atEOF bool) (n int, err error) {
|
||||
return c.t.Span(src, atEOF)
|
||||
}
|
||||
|
||||
// Upper returns a Caser for language-specific uppercasing.
|
||||
func Upper(t language.Tag, opts ...Option) Caser {
|
||||
return Caser{makeUpper(t, getOpts(opts...))}
|
||||
}
|
||||
|
||||
// Lower returns a Caser for language-specific lowercasing.
|
||||
func Lower(t language.Tag, opts ...Option) Caser {
|
||||
return Caser{makeLower(t, getOpts(opts...))}
|
||||
}
|
||||
|
||||
// Title returns a Caser for language-specific title casing. It uses an
|
||||
// approximation of the default Unicode Word Break algorithm.
|
||||
func Title(t language.Tag, opts ...Option) Caser {
|
||||
return Caser{makeTitle(t, getOpts(opts...))}
|
||||
}
|
||||
|
||||
// Fold returns a Caser that implements Unicode case folding. The returned Caser
|
||||
// is stateless and safe to use concurrently by multiple goroutines.
|
||||
//
|
||||
// Case folding does not normalize the input and may not preserve a normal form.
|
||||
// Use the collate or search package for more convenient and linguistically
|
||||
// sound comparisons. Use golang.org/x/text/secure/precis for string comparisons
|
||||
// where security aspects are a concern.
|
||||
func Fold(opts ...Option) Caser {
|
||||
return Caser{makeFold(getOpts(opts...))}
|
||||
}
|
||||
|
||||
// An Option is used to modify the behavior of a Caser.
|
||||
type Option func(o options) options
|
||||
|
||||
// TODO: consider these options to take a boolean as well, like FinalSigma.
|
||||
// The advantage of using this approach is that other providers of a lower-case
|
||||
// algorithm could set different defaults by prefixing a user-provided slice
|
||||
// of options with their own. This is handy, for instance, for the precis
|
||||
// package which would override the default to not handle the Greek final sigma.
|
||||
|
||||
var (
|
||||
// NoLower disables the lowercasing of non-leading letters for a title
|
||||
// caser.
|
||||
NoLower Option = noLower
|
||||
|
||||
// Compact omits mappings in case folding for characters that would grow the
|
||||
// input. (Unimplemented.)
|
||||
Compact Option = compact
|
||||
)
|
||||
|
||||
// TODO: option to preserve a normal form, if applicable?
|
||||
|
||||
type options struct {
|
||||
noLower bool
|
||||
simple bool
|
||||
|
||||
// TODO: segmenter, max ignorable, alternative versions, etc.
|
||||
|
||||
ignoreFinalSigma bool
|
||||
}
|
||||
|
||||
func getOpts(o ...Option) (res options) {
|
||||
for _, f := range o {
|
||||
res = f(res)
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
func noLower(o options) options {
|
||||
o.noLower = true
|
||||
return o
|
||||
}
|
||||
|
||||
func compact(o options) options {
|
||||
o.simple = true
|
||||
return o
|
||||
}
|
||||
|
||||
// HandleFinalSigma specifies whether the special handling of Greek final sigma
|
||||
// should be enabled. Unicode prescribes handling the Greek final sigma for all
|
||||
// locales, but standards like IDNA and PRECIS override this default.
|
||||
func HandleFinalSigma(enable bool) Option {
|
||||
if enable {
|
||||
return handleFinalSigma
|
||||
}
|
||||
return ignoreFinalSigma
|
||||
}
|
||||
|
||||
func ignoreFinalSigma(o options) options {
|
||||
o.ignoreFinalSigma = true
|
||||
return o
|
||||
}
|
||||
|
||||
func handleFinalSigma(o options) options {
|
||||
o.ignoreFinalSigma = false
|
||||
return o
|
||||
}
|
|
@ -0,0 +1,376 @@
|
|||
// 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 cases
|
||||
|
||||
import "golang.org/x/text/transform"
|
||||
|
||||
// A context is used for iterating over source bytes, fetching case info and
|
||||
// writing to a destination buffer.
|
||||
//
|
||||
// Casing operations may need more than one rune of context to decide how a rune
|
||||
// should be cased. Casing implementations should call checkpoint on context
|
||||
// whenever it is known to be safe to return the runes processed so far.
|
||||
//
|
||||
// It is recommended for implementations to not allow for more than 30 case
|
||||
// ignorables as lookahead (analogous to the limit in norm) and to use state if
|
||||
// unbounded lookahead is needed for cased runes.
|
||||
type context struct {
|
||||
dst, src []byte
|
||||
atEOF bool
|
||||
|
||||
pDst int // pDst points past the last written rune in dst.
|
||||
pSrc int // pSrc points to the start of the currently scanned rune.
|
||||
|
||||
// checkpoints safe to return in Transform, where nDst <= pDst and nSrc <= pSrc.
|
||||
nDst, nSrc int
|
||||
err error
|
||||
|
||||
sz int // size of current rune
|
||||
info info // case information of currently scanned rune
|
||||
|
||||
// State preserved across calls to Transform.
|
||||
isMidWord bool // false if next cased letter needs to be title-cased.
|
||||
}
|
||||
|
||||
func (c *context) Reset() {
|
||||
c.isMidWord = false
|
||||
}
|
||||
|
||||
// ret returns the return values for the Transform method. It checks whether
|
||||
// there were insufficient bytes in src to complete and introduces an error
|
||||
// accordingly, if necessary.
|
||||
func (c *context) ret() (nDst, nSrc int, err error) {
|
||||
if c.err != nil || c.nSrc == len(c.src) {
|
||||
return c.nDst, c.nSrc, c.err
|
||||
}
|
||||
// This point is only reached by mappers if there was no short destination
|
||||
// buffer. This means that the source buffer was exhausted and that c.sz was
|
||||
// set to 0 by next.
|
||||
if c.atEOF && c.pSrc == len(c.src) {
|
||||
return c.pDst, c.pSrc, nil
|
||||
}
|
||||
return c.nDst, c.nSrc, transform.ErrShortSrc
|
||||
}
|
||||
|
||||
// retSpan returns the return values for the Span method. It checks whether
|
||||
// there were insufficient bytes in src to complete and introduces an error
|
||||
// accordingly, if necessary.
|
||||
func (c *context) retSpan() (n int, err error) {
|
||||
_, nSrc, err := c.ret()
|
||||
return nSrc, err
|
||||
}
|
||||
|
||||
// checkpoint sets the return value buffer points for Transform to the current
|
||||
// positions.
|
||||
func (c *context) checkpoint() {
|
||||
if c.err == nil {
|
||||
c.nDst, c.nSrc = c.pDst, c.pSrc+c.sz
|
||||
}
|
||||
}
|
||||
|
||||
// unreadRune causes the last rune read by next to be reread on the next
|
||||
// invocation of next. Only one unreadRune may be called after a call to next.
|
||||
func (c *context) unreadRune() {
|
||||
c.sz = 0
|
||||
}
|
||||
|
||||
func (c *context) next() bool {
|
||||
c.pSrc += c.sz
|
||||
if c.pSrc == len(c.src) || c.err != nil {
|
||||
c.info, c.sz = 0, 0
|
||||
return false
|
||||
}
|
||||
v, sz := trie.lookup(c.src[c.pSrc:])
|
||||
c.info, c.sz = info(v), sz
|
||||
if c.sz == 0 {
|
||||
if c.atEOF {
|
||||
// A zero size means we have an incomplete rune. If we are atEOF,
|
||||
// this means it is an illegal rune, which we will consume one
|
||||
// byte at a time.
|
||||
c.sz = 1
|
||||
} else {
|
||||
c.err = transform.ErrShortSrc
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// writeBytes adds bytes to dst.
|
||||
func (c *context) writeBytes(b []byte) bool {
|
||||
if len(c.dst)-c.pDst < len(b) {
|
||||
c.err = transform.ErrShortDst
|
||||
return false
|
||||
}
|
||||
// This loop is faster than using copy.
|
||||
for _, ch := range b {
|
||||
c.dst[c.pDst] = ch
|
||||
c.pDst++
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// writeString writes the given string to dst.
|
||||
func (c *context) writeString(s string) bool {
|
||||
if len(c.dst)-c.pDst < len(s) {
|
||||
c.err = transform.ErrShortDst
|
||||
return false
|
||||
}
|
||||
// This loop is faster than using copy.
|
||||
for i := 0; i < len(s); i++ {
|
||||
c.dst[c.pDst] = s[i]
|
||||
c.pDst++
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// copy writes the current rune to dst.
|
||||
func (c *context) copy() bool {
|
||||
return c.writeBytes(c.src[c.pSrc : c.pSrc+c.sz])
|
||||
}
|
||||
|
||||
// copyXOR copies the current rune to dst and modifies it by applying the XOR
|
||||
// pattern of the case info. It is the responsibility of the caller to ensure
|
||||
// that this is a rune with a XOR pattern defined.
|
||||
func (c *context) copyXOR() bool {
|
||||
if !c.copy() {
|
||||
return false
|
||||
}
|
||||
if c.info&xorIndexBit == 0 {
|
||||
// Fast path for 6-bit XOR pattern, which covers most cases.
|
||||
c.dst[c.pDst-1] ^= byte(c.info >> xorShift)
|
||||
} else {
|
||||
// Interpret XOR bits as an index.
|
||||
// TODO: test performance for unrolling this loop. Verify that we have
|
||||
// at least two bytes and at most three.
|
||||
idx := c.info >> xorShift
|
||||
for p := c.pDst - 1; ; p-- {
|
||||
c.dst[p] ^= xorData[idx]
|
||||
idx--
|
||||
if xorData[idx] == 0 {
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// hasPrefix returns true if src[pSrc:] starts with the given string.
|
||||
func (c *context) hasPrefix(s string) bool {
|
||||
b := c.src[c.pSrc:]
|
||||
if len(b) < len(s) {
|
||||
return false
|
||||
}
|
||||
for i, c := range b[:len(s)] {
|
||||
if c != s[i] {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// caseType returns an info with only the case bits, normalized to either
|
||||
// cLower, cUpper, cTitle or cUncased.
|
||||
func (c *context) caseType() info {
|
||||
cm := c.info & 0x7
|
||||
if cm < 4 {
|
||||
return cm
|
||||
}
|
||||
if cm >= cXORCase {
|
||||
// xor the last bit of the rune with the case type bits.
|
||||
b := c.src[c.pSrc+c.sz-1]
|
||||
return info(b&1) ^ cm&0x3
|
||||
}
|
||||
if cm == cIgnorableCased {
|
||||
return cLower
|
||||
}
|
||||
return cUncased
|
||||
}
|
||||
|
||||
// lower writes the lowercase version of the current rune to dst.
|
||||
func lower(c *context) bool {
|
||||
ct := c.caseType()
|
||||
if c.info&hasMappingMask == 0 || ct == cLower {
|
||||
return c.copy()
|
||||
}
|
||||
if c.info&exceptionBit == 0 {
|
||||
return c.copyXOR()
|
||||
}
|
||||
e := exceptions[c.info>>exceptionShift:]
|
||||
offset := 2 + e[0]&lengthMask // size of header + fold string
|
||||
if nLower := (e[1] >> lengthBits) & lengthMask; nLower != noChange {
|
||||
return c.writeString(e[offset : offset+nLower])
|
||||
}
|
||||
return c.copy()
|
||||
}
|
||||
|
||||
func isLower(c *context) bool {
|
||||
ct := c.caseType()
|
||||
if c.info&hasMappingMask == 0 || ct == cLower {
|
||||
return true
|
||||
}
|
||||
if c.info&exceptionBit == 0 {
|
||||
c.err = transform.ErrEndOfSpan
|
||||
return false
|
||||
}
|
||||
e := exceptions[c.info>>exceptionShift:]
|
||||
if nLower := (e[1] >> lengthBits) & lengthMask; nLower != noChange {
|
||||
c.err = transform.ErrEndOfSpan
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// upper writes the uppercase version of the current rune to dst.
|
||||
func upper(c *context) bool {
|
||||
ct := c.caseType()
|
||||
if c.info&hasMappingMask == 0 || ct == cUpper {
|
||||
return c.copy()
|
||||
}
|
||||
if c.info&exceptionBit == 0 {
|
||||
return c.copyXOR()
|
||||
}
|
||||
e := exceptions[c.info>>exceptionShift:]
|
||||
offset := 2 + e[0]&lengthMask // size of header + fold string
|
||||
// Get length of first special case mapping.
|
||||
n := (e[1] >> lengthBits) & lengthMask
|
||||
if ct == cTitle {
|
||||
// The first special case mapping is for lower. Set n to the second.
|
||||
if n == noChange {
|
||||
n = 0
|
||||
}
|
||||
n, e = e[1]&lengthMask, e[n:]
|
||||
}
|
||||
if n != noChange {
|
||||
return c.writeString(e[offset : offset+n])
|
||||
}
|
||||
return c.copy()
|
||||
}
|
||||
|
||||
// isUpper writes the isUppercase version of the current rune to dst.
|
||||
func isUpper(c *context) bool {
|
||||
ct := c.caseType()
|
||||
if c.info&hasMappingMask == 0 || ct == cUpper {
|
||||
return true
|
||||
}
|
||||
if c.info&exceptionBit == 0 {
|
||||
c.err = transform.ErrEndOfSpan
|
||||
return false
|
||||
}
|
||||
e := exceptions[c.info>>exceptionShift:]
|
||||
// Get length of first special case mapping.
|
||||
n := (e[1] >> lengthBits) & lengthMask
|
||||
if ct == cTitle {
|
||||
n = e[1] & lengthMask
|
||||
}
|
||||
if n != noChange {
|
||||
c.err = transform.ErrEndOfSpan
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// title writes the title case version of the current rune to dst.
|
||||
func title(c *context) bool {
|
||||
ct := c.caseType()
|
||||
if c.info&hasMappingMask == 0 || ct == cTitle {
|
||||
return c.copy()
|
||||
}
|
||||
if c.info&exceptionBit == 0 {
|
||||
if ct == cLower {
|
||||
return c.copyXOR()
|
||||
}
|
||||
return c.copy()
|
||||
}
|
||||
// Get the exception data.
|
||||
e := exceptions[c.info>>exceptionShift:]
|
||||
offset := 2 + e[0]&lengthMask // size of header + fold string
|
||||
|
||||
nFirst := (e[1] >> lengthBits) & lengthMask
|
||||
if nTitle := e[1] & lengthMask; nTitle != noChange {
|
||||
if nFirst != noChange {
|
||||
e = e[nFirst:]
|
||||
}
|
||||
return c.writeString(e[offset : offset+nTitle])
|
||||
}
|
||||
if ct == cLower && nFirst != noChange {
|
||||
// Use the uppercase version instead.
|
||||
return c.writeString(e[offset : offset+nFirst])
|
||||
}
|
||||
// Already in correct case.
|
||||
return c.copy()
|
||||
}
|
||||
|
||||
// isTitle reports whether the current rune is in title case.
|
||||
func isTitle(c *context) bool {
|
||||
ct := c.caseType()
|
||||
if c.info&hasMappingMask == 0 || ct == cTitle {
|
||||
return true
|
||||
}
|
||||
if c.info&exceptionBit == 0 {
|
||||
if ct == cLower {
|
||||
c.err = transform.ErrEndOfSpan
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
// Get the exception data.
|
||||
e := exceptions[c.info>>exceptionShift:]
|
||||
if nTitle := e[1] & lengthMask; nTitle != noChange {
|
||||
c.err = transform.ErrEndOfSpan
|
||||
return false
|
||||
}
|
||||
nFirst := (e[1] >> lengthBits) & lengthMask
|
||||
if ct == cLower && nFirst != noChange {
|
||||
c.err = transform.ErrEndOfSpan
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// foldFull writes the foldFull version of the current rune to dst.
|
||||
func foldFull(c *context) bool {
|
||||
if c.info&hasMappingMask == 0 {
|
||||
return c.copy()
|
||||
}
|
||||
ct := c.caseType()
|
||||
if c.info&exceptionBit == 0 {
|
||||
if ct != cLower || c.info&inverseFoldBit != 0 {
|
||||
return c.copyXOR()
|
||||
}
|
||||
return c.copy()
|
||||
}
|
||||
e := exceptions[c.info>>exceptionShift:]
|
||||
n := e[0] & lengthMask
|
||||
if n == 0 {
|
||||
if ct == cLower {
|
||||
return c.copy()
|
||||
}
|
||||
n = (e[1] >> lengthBits) & lengthMask
|
||||
}
|
||||
return c.writeString(e[2 : 2+n])
|
||||
}
|
||||
|
||||
// isFoldFull reports whether the current run is mapped to foldFull
|
||||
func isFoldFull(c *context) bool {
|
||||
if c.info&hasMappingMask == 0 {
|
||||
return true
|
||||
}
|
||||
ct := c.caseType()
|
||||
if c.info&exceptionBit == 0 {
|
||||
if ct != cLower || c.info&inverseFoldBit != 0 {
|
||||
c.err = transform.ErrEndOfSpan
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
e := exceptions[c.info>>exceptionShift:]
|
||||
n := e[0] & lengthMask
|
||||
if n == 0 && ct == cLower {
|
||||
return true
|
||||
}
|
||||
c.err = transform.ErrEndOfSpan
|
||||
return false
|
||||
}
|
|
@ -0,0 +1,34 @@
|
|||
// Copyright 2016 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 cases
|
||||
|
||||
import "golang.org/x/text/transform"
|
||||
|
||||
type caseFolder struct{ transform.NopResetter }
|
||||
|
||||
// caseFolder implements the Transformer interface for doing case folding.
|
||||
func (t *caseFolder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
c := context{dst: dst, src: src, atEOF: atEOF}
|
||||
for c.next() {
|
||||
foldFull(&c)
|
||||
c.checkpoint()
|
||||
}
|
||||
return c.ret()
|
||||
}
|
||||
|
||||
func (t *caseFolder) Span(src []byte, atEOF bool) (n int, err error) {
|
||||
c := context{src: src, atEOF: atEOF}
|
||||
for c.next() && isFoldFull(&c) {
|
||||
c.checkpoint()
|
||||
}
|
||||
return c.retSpan()
|
||||
}
|
||||
|
||||
func makeFold(o options) transform.SpanningTransformer {
|
||||
// TODO: Special case folding, through option Language, Special/Turkic, or
|
||||
// both.
|
||||
// TODO: Implement Compact options.
|
||||
return &caseFolder{}
|
||||
}
|
|
@ -0,0 +1,62 @@
|
|||
// Copyright 2016 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 icu
|
||||
// +build icu
|
||||
|
||||
package cases
|
||||
|
||||
// Ideally these functions would be defined in a test file, but go test doesn't
|
||||
// allow CGO in tests. The build tag should ensure either way that these
|
||||
// functions will not end up in the package.
|
||||
|
||||
// TODO: Ensure that the correct ICU version is set.
|
||||
|
||||
/*
|
||||
#cgo LDFLAGS: -licui18n.57 -licuuc.57
|
||||
#include <stdlib.h>
|
||||
#include <unicode/ustring.h>
|
||||
#include <unicode/utypes.h>
|
||||
#include <unicode/localpointer.h>
|
||||
#include <unicode/ucasemap.h>
|
||||
*/
|
||||
import "C"
|
||||
|
||||
import "unsafe"
|
||||
|
||||
func doICU(tag, caser, input string) string {
|
||||
err := C.UErrorCode(0)
|
||||
loc := C.CString(tag)
|
||||
cm := C.ucasemap_open(loc, C.uint32_t(0), &err)
|
||||
|
||||
buf := make([]byte, len(input)*4)
|
||||
dst := (*C.char)(unsafe.Pointer(&buf[0]))
|
||||
src := C.CString(input)
|
||||
|
||||
cn := C.int32_t(0)
|
||||
|
||||
switch caser {
|
||||
case "fold":
|
||||
cn = C.ucasemap_utf8FoldCase(cm,
|
||||
dst, C.int32_t(len(buf)),
|
||||
src, C.int32_t(len(input)),
|
||||
&err)
|
||||
case "lower":
|
||||
cn = C.ucasemap_utf8ToLower(cm,
|
||||
dst, C.int32_t(len(buf)),
|
||||
src, C.int32_t(len(input)),
|
||||
&err)
|
||||
case "upper":
|
||||
cn = C.ucasemap_utf8ToUpper(cm,
|
||||
dst, C.int32_t(len(buf)),
|
||||
src, C.int32_t(len(input)),
|
||||
&err)
|
||||
case "title":
|
||||
cn = C.ucasemap_utf8ToTitle(cm,
|
||||
dst, C.int32_t(len(buf)),
|
||||
src, C.int32_t(len(input)),
|
||||
&err)
|
||||
}
|
||||
return string(buf[:cn])
|
||||
}
|
|
@ -0,0 +1,82 @@
|
|||
// 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 cases
|
||||
|
||||
func (c info) cccVal() info {
|
||||
if c&exceptionBit != 0 {
|
||||
return info(exceptions[c>>exceptionShift]) & cccMask
|
||||
}
|
||||
return c & cccMask
|
||||
}
|
||||
|
||||
func (c info) cccType() info {
|
||||
ccc := c.cccVal()
|
||||
if ccc <= cccZero {
|
||||
return cccZero
|
||||
}
|
||||
return ccc
|
||||
}
|
||||
|
||||
// TODO: Implement full Unicode breaking algorithm:
|
||||
// 1) Implement breaking in separate package.
|
||||
// 2) Use the breaker here.
|
||||
// 3) Compare table size and performance of using the more generic breaker.
|
||||
//
|
||||
// Note that we can extend the current algorithm to be much more accurate. This
|
||||
// only makes sense, though, if the performance and/or space penalty of using
|
||||
// the generic breaker is big. Extra data will only be needed for non-cased
|
||||
// runes, which means there are sufficient bits left in the caseType.
|
||||
// ICU prohibits breaking in such cases as well.
|
||||
|
||||
// For the purpose of title casing we use an approximation of the Unicode Word
|
||||
// Breaking algorithm defined in Annex #29:
|
||||
// https://www.unicode.org/reports/tr29/#Default_Grapheme_Cluster_Table.
|
||||
//
|
||||
// For our approximation, we group the Word Break types into the following
|
||||
// categories, with associated rules:
|
||||
//
|
||||
// 1) Letter:
|
||||
// ALetter, Hebrew_Letter, Numeric, ExtendNumLet, Extend, Format_FE, ZWJ.
|
||||
// Rule: Never break between consecutive runes of this category.
|
||||
//
|
||||
// 2) Mid:
|
||||
// MidLetter, MidNumLet, Single_Quote.
|
||||
// (Cf. case-ignorable: MidLetter, MidNumLet, Single_Quote or cat is Mn,
|
||||
// Me, Cf, Lm or Sk).
|
||||
// Rule: Don't break between Letter and Mid, but break between two Mids.
|
||||
//
|
||||
// 3) Break:
|
||||
// Any other category: NewLine, MidNum, CR, LF, Double_Quote, Katakana, and
|
||||
// Other.
|
||||
// These categories should always result in a break between two cased letters.
|
||||
// Rule: Always break.
|
||||
//
|
||||
// Note 1: the Katakana and MidNum categories can, in esoteric cases, result in
|
||||
// preventing a break between two cased letters. For now we will ignore this
|
||||
// (e.g. [ALetter] [ExtendNumLet] [Katakana] [ExtendNumLet] [ALetter] and
|
||||
// [ALetter] [Numeric] [MidNum] [Numeric] [ALetter].)
|
||||
//
|
||||
// Note 2: the rule for Mid is very approximate, but works in most cases. To
|
||||
// improve, we could store the categories in the trie value and use a FA to
|
||||
// manage breaks. See TODO comment above.
|
||||
//
|
||||
// Note 3: according to the spec, it is possible for the Extend category to
|
||||
// introduce breaks between other categories grouped in Letter. However, this
|
||||
// is undesirable for our purposes. ICU prevents breaks in such cases as well.
|
||||
|
||||
// isBreak returns whether this rune should introduce a break.
|
||||
func (c info) isBreak() bool {
|
||||
return c.cccVal() == cccBreak
|
||||
}
|
||||
|
||||
// isLetter returns whether the rune is of break type ALetter, Hebrew_Letter,
|
||||
// Numeric, ExtendNumLet, or Extend.
|
||||
func (c info) isLetter() bool {
|
||||
ccc := c.cccVal()
|
||||
if ccc == cccZero {
|
||||
return !c.isCaseIgnorable()
|
||||
}
|
||||
return ccc != cccBreak
|
||||
}
|
|
@ -0,0 +1,816 @@
|
|||
// 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 cases
|
||||
|
||||
// This file contains the definitions of case mappings for all supported
|
||||
// languages. The rules for the language-specific tailorings were taken and
|
||||
// modified from the CLDR transform definitions in common/transforms.
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"unicode"
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/text/internal"
|
||||
"golang.org/x/text/language"
|
||||
"golang.org/x/text/transform"
|
||||
"golang.org/x/text/unicode/norm"
|
||||
)
|
||||
|
||||
// A mapFunc takes a context set to the current rune and writes the mapped
|
||||
// version to the same context. It may advance the context to the next rune. It
|
||||
// returns whether a checkpoint is possible: whether the pDst bytes written to
|
||||
// dst so far won't need changing as we see more source bytes.
|
||||
type mapFunc func(*context) bool
|
||||
|
||||
// A spanFunc takes a context set to the current rune and returns whether this
|
||||
// rune would be altered when written to the output. It may advance the context
|
||||
// to the next rune. It returns whether a checkpoint is possible.
|
||||
type spanFunc func(*context) bool
|
||||
|
||||
// maxIgnorable defines the maximum number of ignorables to consider for
|
||||
// lookahead operations.
|
||||
const maxIgnorable = 30
|
||||
|
||||
// supported lists the language tags for which we have tailorings.
|
||||
const supported = "und af az el lt nl tr"
|
||||
|
||||
func init() {
|
||||
tags := []language.Tag{}
|
||||
for _, s := range strings.Split(supported, " ") {
|
||||
tags = append(tags, language.MustParse(s))
|
||||
}
|
||||
matcher = internal.NewInheritanceMatcher(tags)
|
||||
Supported = language.NewCoverage(tags)
|
||||
}
|
||||
|
||||
var (
|
||||
matcher *internal.InheritanceMatcher
|
||||
|
||||
Supported language.Coverage
|
||||
|
||||
// We keep the following lists separate, instead of having a single per-
|
||||
// language struct, to give the compiler a chance to remove unused code.
|
||||
|
||||
// Some uppercase mappers are stateless, so we can precompute the
|
||||
// Transformers and save a bit on runtime allocations.
|
||||
upperFunc = []struct {
|
||||
upper mapFunc
|
||||
span spanFunc
|
||||
}{
|
||||
{nil, nil}, // und
|
||||
{nil, nil}, // af
|
||||
{aztrUpper(upper), isUpper}, // az
|
||||
{elUpper, noSpan}, // el
|
||||
{ltUpper(upper), noSpan}, // lt
|
||||
{nil, nil}, // nl
|
||||
{aztrUpper(upper), isUpper}, // tr
|
||||
}
|
||||
|
||||
undUpper transform.SpanningTransformer = &undUpperCaser{}
|
||||
undLower transform.SpanningTransformer = &undLowerCaser{}
|
||||
undLowerIgnoreSigma transform.SpanningTransformer = &undLowerIgnoreSigmaCaser{}
|
||||
|
||||
lowerFunc = []mapFunc{
|
||||
nil, // und
|
||||
nil, // af
|
||||
aztrLower, // az
|
||||
nil, // el
|
||||
ltLower, // lt
|
||||
nil, // nl
|
||||
aztrLower, // tr
|
||||
}
|
||||
|
||||
titleInfos = []struct {
|
||||
title mapFunc
|
||||
lower mapFunc
|
||||
titleSpan spanFunc
|
||||
rewrite func(*context)
|
||||
}{
|
||||
{title, lower, isTitle, nil}, // und
|
||||
{title, lower, isTitle, afnlRewrite}, // af
|
||||
{aztrUpper(title), aztrLower, isTitle, nil}, // az
|
||||
{title, lower, isTitle, nil}, // el
|
||||
{ltUpper(title), ltLower, noSpan, nil}, // lt
|
||||
{nlTitle, lower, nlTitleSpan, afnlRewrite}, // nl
|
||||
{aztrUpper(title), aztrLower, isTitle, nil}, // tr
|
||||
}
|
||||
)
|
||||
|
||||
func makeUpper(t language.Tag, o options) transform.SpanningTransformer {
|
||||
_, i, _ := matcher.Match(t)
|
||||
f := upperFunc[i].upper
|
||||
if f == nil {
|
||||
return undUpper
|
||||
}
|
||||
return &simpleCaser{f: f, span: upperFunc[i].span}
|
||||
}
|
||||
|
||||
func makeLower(t language.Tag, o options) transform.SpanningTransformer {
|
||||
_, i, _ := matcher.Match(t)
|
||||
f := lowerFunc[i]
|
||||
if f == nil {
|
||||
if o.ignoreFinalSigma {
|
||||
return undLowerIgnoreSigma
|
||||
}
|
||||
return undLower
|
||||
}
|
||||
if o.ignoreFinalSigma {
|
||||
return &simpleCaser{f: f, span: isLower}
|
||||
}
|
||||
return &lowerCaser{
|
||||
first: f,
|
||||
midWord: finalSigma(f),
|
||||
}
|
||||
}
|
||||
|
||||
func makeTitle(t language.Tag, o options) transform.SpanningTransformer {
|
||||
_, i, _ := matcher.Match(t)
|
||||
x := &titleInfos[i]
|
||||
lower := x.lower
|
||||
if o.noLower {
|
||||
lower = (*context).copy
|
||||
} else if !o.ignoreFinalSigma {
|
||||
lower = finalSigma(lower)
|
||||
}
|
||||
return &titleCaser{
|
||||
title: x.title,
|
||||
lower: lower,
|
||||
titleSpan: x.titleSpan,
|
||||
rewrite: x.rewrite,
|
||||
}
|
||||
}
|
||||
|
||||
func noSpan(c *context) bool {
|
||||
c.err = transform.ErrEndOfSpan
|
||||
return false
|
||||
}
|
||||
|
||||
// TODO: consider a similar special case for the fast majority lower case. This
|
||||
// is a bit more involved so will require some more precise benchmarking to
|
||||
// justify it.
|
||||
|
||||
type undUpperCaser struct{ transform.NopResetter }
|
||||
|
||||
// undUpperCaser implements the Transformer interface for doing an upper case
|
||||
// mapping for the root locale (und). It eliminates the need for an allocation
|
||||
// as it prevents escaping by not using function pointers.
|
||||
func (t undUpperCaser) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
c := context{dst: dst, src: src, atEOF: atEOF}
|
||||
for c.next() {
|
||||
upper(&c)
|
||||
c.checkpoint()
|
||||
}
|
||||
return c.ret()
|
||||
}
|
||||
|
||||
func (t undUpperCaser) Span(src []byte, atEOF bool) (n int, err error) {
|
||||
c := context{src: src, atEOF: atEOF}
|
||||
for c.next() && isUpper(&c) {
|
||||
c.checkpoint()
|
||||
}
|
||||
return c.retSpan()
|
||||
}
|
||||
|
||||
// undLowerIgnoreSigmaCaser implements the Transformer interface for doing
|
||||
// a lower case mapping for the root locale (und) ignoring final sigma
|
||||
// handling. This casing algorithm is used in some performance-critical packages
|
||||
// like secure/precis and x/net/http/idna, which warrants its special-casing.
|
||||
type undLowerIgnoreSigmaCaser struct{ transform.NopResetter }
|
||||
|
||||
func (t undLowerIgnoreSigmaCaser) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
c := context{dst: dst, src: src, atEOF: atEOF}
|
||||
for c.next() && lower(&c) {
|
||||
c.checkpoint()
|
||||
}
|
||||
return c.ret()
|
||||
|
||||
}
|
||||
|
||||
// Span implements a generic lower-casing. This is possible as isLower works
|
||||
// for all lowercasing variants. All lowercase variants only vary in how they
|
||||
// transform a non-lowercase letter. They will never change an already lowercase
|
||||
// letter. In addition, there is no state.
|
||||
func (t undLowerIgnoreSigmaCaser) Span(src []byte, atEOF bool) (n int, err error) {
|
||||
c := context{src: src, atEOF: atEOF}
|
||||
for c.next() && isLower(&c) {
|
||||
c.checkpoint()
|
||||
}
|
||||
return c.retSpan()
|
||||
}
|
||||
|
||||
type simpleCaser struct {
|
||||
context
|
||||
f mapFunc
|
||||
span spanFunc
|
||||
}
|
||||
|
||||
// simpleCaser implements the Transformer interface for doing a case operation
|
||||
// on a rune-by-rune basis.
|
||||
func (t *simpleCaser) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
c := context{dst: dst, src: src, atEOF: atEOF}
|
||||
for c.next() && t.f(&c) {
|
||||
c.checkpoint()
|
||||
}
|
||||
return c.ret()
|
||||
}
|
||||
|
||||
func (t *simpleCaser) Span(src []byte, atEOF bool) (n int, err error) {
|
||||
c := context{src: src, atEOF: atEOF}
|
||||
for c.next() && t.span(&c) {
|
||||
c.checkpoint()
|
||||
}
|
||||
return c.retSpan()
|
||||
}
|
||||
|
||||
// undLowerCaser implements the Transformer interface for doing a lower case
|
||||
// mapping for the root locale (und) ignoring final sigma handling. This casing
|
||||
// algorithm is used in some performance-critical packages like secure/precis
|
||||
// and x/net/http/idna, which warrants its special-casing.
|
||||
type undLowerCaser struct{ transform.NopResetter }
|
||||
|
||||
func (t undLowerCaser) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
c := context{dst: dst, src: src, atEOF: atEOF}
|
||||
|
||||
for isInterWord := true; c.next(); {
|
||||
if isInterWord {
|
||||
if c.info.isCased() {
|
||||
if !lower(&c) {
|
||||
break
|
||||
}
|
||||
isInterWord = false
|
||||
} else if !c.copy() {
|
||||
break
|
||||
}
|
||||
} else {
|
||||
if c.info.isNotCasedAndNotCaseIgnorable() {
|
||||
if !c.copy() {
|
||||
break
|
||||
}
|
||||
isInterWord = true
|
||||
} else if !c.hasPrefix("Σ") {
|
||||
if !lower(&c) {
|
||||
break
|
||||
}
|
||||
} else if !finalSigmaBody(&c) {
|
||||
break
|
||||
}
|
||||
}
|
||||
c.checkpoint()
|
||||
}
|
||||
return c.ret()
|
||||
}
|
||||
|
||||
func (t undLowerCaser) Span(src []byte, atEOF bool) (n int, err error) {
|
||||
c := context{src: src, atEOF: atEOF}
|
||||
for c.next() && isLower(&c) {
|
||||
c.checkpoint()
|
||||
}
|
||||
return c.retSpan()
|
||||
}
|
||||
|
||||
// lowerCaser implements the Transformer interface. The default Unicode lower
|
||||
// casing requires different treatment for the first and subsequent characters
|
||||
// of a word, most notably to handle the Greek final Sigma.
|
||||
type lowerCaser struct {
|
||||
undLowerIgnoreSigmaCaser
|
||||
|
||||
context
|
||||
|
||||
first, midWord mapFunc
|
||||
}
|
||||
|
||||
func (t *lowerCaser) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
t.context = context{dst: dst, src: src, atEOF: atEOF}
|
||||
c := &t.context
|
||||
|
||||
for isInterWord := true; c.next(); {
|
||||
if isInterWord {
|
||||
if c.info.isCased() {
|
||||
if !t.first(c) {
|
||||
break
|
||||
}
|
||||
isInterWord = false
|
||||
} else if !c.copy() {
|
||||
break
|
||||
}
|
||||
} else {
|
||||
if c.info.isNotCasedAndNotCaseIgnorable() {
|
||||
if !c.copy() {
|
||||
break
|
||||
}
|
||||
isInterWord = true
|
||||
} else if !t.midWord(c) {
|
||||
break
|
||||
}
|
||||
}
|
||||
c.checkpoint()
|
||||
}
|
||||
return c.ret()
|
||||
}
|
||||
|
||||
// titleCaser implements the Transformer interface. Title casing algorithms
|
||||
// distinguish between the first letter of a word and subsequent letters of the
|
||||
// same word. It uses state to avoid requiring a potentially infinite lookahead.
|
||||
type titleCaser struct {
|
||||
context
|
||||
|
||||
// rune mappings used by the actual casing algorithms.
|
||||
title mapFunc
|
||||
lower mapFunc
|
||||
titleSpan spanFunc
|
||||
|
||||
rewrite func(*context)
|
||||
}
|
||||
|
||||
// Transform implements the standard Unicode title case algorithm as defined in
|
||||
// Chapter 3 of The Unicode Standard:
|
||||
// toTitlecase(X): Find the word boundaries in X according to Unicode Standard
|
||||
// Annex #29, "Unicode Text Segmentation." For each word boundary, find the
|
||||
// first cased character F following the word boundary. If F exists, map F to
|
||||
// Titlecase_Mapping(F); then map all characters C between F and the following
|
||||
// word boundary to Lowercase_Mapping(C).
|
||||
func (t *titleCaser) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
t.context = context{dst: dst, src: src, atEOF: atEOF, isMidWord: t.isMidWord}
|
||||
c := &t.context
|
||||
|
||||
if !c.next() {
|
||||
return c.ret()
|
||||
}
|
||||
|
||||
for {
|
||||
p := c.info
|
||||
if t.rewrite != nil {
|
||||
t.rewrite(c)
|
||||
}
|
||||
|
||||
wasMid := p.isMid()
|
||||
// Break out of this loop on failure to ensure we do not modify the
|
||||
// state incorrectly.
|
||||
if p.isCased() {
|
||||
if !c.isMidWord {
|
||||
if !t.title(c) {
|
||||
break
|
||||
}
|
||||
c.isMidWord = true
|
||||
} else if !t.lower(c) {
|
||||
break
|
||||
}
|
||||
} else if !c.copy() {
|
||||
break
|
||||
} else if p.isBreak() {
|
||||
c.isMidWord = false
|
||||
}
|
||||
|
||||
// As we save the state of the transformer, it is safe to call
|
||||
// checkpoint after any successful write.
|
||||
if !(c.isMidWord && wasMid) {
|
||||
c.checkpoint()
|
||||
}
|
||||
|
||||
if !c.next() {
|
||||
break
|
||||
}
|
||||
if wasMid && c.info.isMid() {
|
||||
c.isMidWord = false
|
||||
}
|
||||
}
|
||||
return c.ret()
|
||||
}
|
||||
|
||||
func (t *titleCaser) Span(src []byte, atEOF bool) (n int, err error) {
|
||||
t.context = context{src: src, atEOF: atEOF, isMidWord: t.isMidWord}
|
||||
c := &t.context
|
||||
|
||||
if !c.next() {
|
||||
return c.retSpan()
|
||||
}
|
||||
|
||||
for {
|
||||
p := c.info
|
||||
if t.rewrite != nil {
|
||||
t.rewrite(c)
|
||||
}
|
||||
|
||||
wasMid := p.isMid()
|
||||
// Break out of this loop on failure to ensure we do not modify the
|
||||
// state incorrectly.
|
||||
if p.isCased() {
|
||||
if !c.isMidWord {
|
||||
if !t.titleSpan(c) {
|
||||
break
|
||||
}
|
||||
c.isMidWord = true
|
||||
} else if !isLower(c) {
|
||||
break
|
||||
}
|
||||
} else if p.isBreak() {
|
||||
c.isMidWord = false
|
||||
}
|
||||
// As we save the state of the transformer, it is safe to call
|
||||
// checkpoint after any successful write.
|
||||
if !(c.isMidWord && wasMid) {
|
||||
c.checkpoint()
|
||||
}
|
||||
|
||||
if !c.next() {
|
||||
break
|
||||
}
|
||||
if wasMid && c.info.isMid() {
|
||||
c.isMidWord = false
|
||||
}
|
||||
}
|
||||
return c.retSpan()
|
||||
}
|
||||
|
||||
// finalSigma adds Greek final Sigma handing to another casing function. It
|
||||
// determines whether a lowercased sigma should be σ or ς, by looking ahead for
|
||||
// case-ignorables and a cased letters.
|
||||
func finalSigma(f mapFunc) mapFunc {
|
||||
return func(c *context) bool {
|
||||
if !c.hasPrefix("Σ") {
|
||||
return f(c)
|
||||
}
|
||||
return finalSigmaBody(c)
|
||||
}
|
||||
}
|
||||
|
||||
func finalSigmaBody(c *context) bool {
|
||||
// Current rune must be ∑.
|
||||
|
||||
// ::NFD();
|
||||
// # 03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
|
||||
// Σ } [:case-ignorable:]* [:cased:] → σ;
|
||||
// [:cased:] [:case-ignorable:]* { Σ → ς;
|
||||
// ::Any-Lower;
|
||||
// ::NFC();
|
||||
|
||||
p := c.pDst
|
||||
c.writeString("ς")
|
||||
|
||||
// TODO: we should do this here, but right now this will never have an
|
||||
// effect as this is called when the prefix is Sigma, whereas Dutch and
|
||||
// Afrikaans only test for an apostrophe.
|
||||
//
|
||||
// if t.rewrite != nil {
|
||||
// t.rewrite(c)
|
||||
// }
|
||||
|
||||
// We need to do one more iteration after maxIgnorable, as a cased
|
||||
// letter is not an ignorable and may modify the result.
|
||||
wasMid := false
|
||||
for i := 0; i < maxIgnorable+1; i++ {
|
||||
if !c.next() {
|
||||
return false
|
||||
}
|
||||
if !c.info.isCaseIgnorable() {
|
||||
// All Midword runes are also case ignorable, so we are
|
||||
// guaranteed to have a letter or word break here. As we are
|
||||
// unreading the run, there is no need to unset c.isMidWord;
|
||||
// the title caser will handle this.
|
||||
if c.info.isCased() {
|
||||
// p+1 is guaranteed to be in bounds: if writing ς was
|
||||
// successful, p+1 will contain the second byte of ς. If not,
|
||||
// this function will have returned after c.next returned false.
|
||||
c.dst[p+1]++ // ς → σ
|
||||
}
|
||||
c.unreadRune()
|
||||
return true
|
||||
}
|
||||
// A case ignorable may also introduce a word break, so we may need
|
||||
// to continue searching even after detecting a break.
|
||||
isMid := c.info.isMid()
|
||||
if (wasMid && isMid) || c.info.isBreak() {
|
||||
c.isMidWord = false
|
||||
}
|
||||
wasMid = isMid
|
||||
c.copy()
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// finalSigmaSpan would be the same as isLower.
|
||||
|
||||
// elUpper implements Greek upper casing, which entails removing a predefined
|
||||
// set of non-blocked modifiers. Note that these accents should not be removed
|
||||
// for title casing!
|
||||
// Example: "Οδός" -> "ΟΔΟΣ".
|
||||
func elUpper(c *context) bool {
|
||||
// From CLDR:
|
||||
// [:Greek:] [^[:ccc=Not_Reordered:][:ccc=Above:]]*? { [\u0313\u0314\u0301\u0300\u0306\u0342\u0308\u0304] → ;
|
||||
// [:Greek:] [^[:ccc=Not_Reordered:][:ccc=Iota_Subscript:]]*? { \u0345 → ;
|
||||
|
||||
r, _ := utf8.DecodeRune(c.src[c.pSrc:])
|
||||
oldPDst := c.pDst
|
||||
if !upper(c) {
|
||||
return false
|
||||
}
|
||||
if !unicode.Is(unicode.Greek, r) {
|
||||
return true
|
||||
}
|
||||
i := 0
|
||||
// Take the properties of the uppercased rune that is already written to the
|
||||
// destination. This saves us the trouble of having to uppercase the
|
||||
// decomposed rune again.
|
||||
if b := norm.NFD.Properties(c.dst[oldPDst:]).Decomposition(); b != nil {
|
||||
// Restore the destination position and process the decomposed rune.
|
||||
r, sz := utf8.DecodeRune(b)
|
||||
if r <= 0xFF { // See A.6.1
|
||||
return true
|
||||
}
|
||||
c.pDst = oldPDst
|
||||
// Insert the first rune and ignore the modifiers. See A.6.2.
|
||||
c.writeBytes(b[:sz])
|
||||
i = len(b[sz:]) / 2 // Greek modifiers are always of length 2.
|
||||
}
|
||||
|
||||
for ; i < maxIgnorable && c.next(); i++ {
|
||||
switch r, _ := utf8.DecodeRune(c.src[c.pSrc:]); r {
|
||||
// Above and Iota Subscript
|
||||
case 0x0300, // U+0300 COMBINING GRAVE ACCENT
|
||||
0x0301, // U+0301 COMBINING ACUTE ACCENT
|
||||
0x0304, // U+0304 COMBINING MACRON
|
||||
0x0306, // U+0306 COMBINING BREVE
|
||||
0x0308, // U+0308 COMBINING DIAERESIS
|
||||
0x0313, // U+0313 COMBINING COMMA ABOVE
|
||||
0x0314, // U+0314 COMBINING REVERSED COMMA ABOVE
|
||||
0x0342, // U+0342 COMBINING GREEK PERISPOMENI
|
||||
0x0345: // U+0345 COMBINING GREEK YPOGEGRAMMENI
|
||||
// No-op. Gobble the modifier.
|
||||
|
||||
default:
|
||||
switch v, _ := trie.lookup(c.src[c.pSrc:]); info(v).cccType() {
|
||||
case cccZero:
|
||||
c.unreadRune()
|
||||
return true
|
||||
|
||||
// We don't need to test for IotaSubscript as the only rune that
|
||||
// qualifies (U+0345) was already excluded in the switch statement
|
||||
// above. See A.4.
|
||||
|
||||
case cccAbove:
|
||||
return c.copy()
|
||||
default:
|
||||
// Some other modifier. We're still allowed to gobble Greek
|
||||
// modifiers after this.
|
||||
c.copy()
|
||||
}
|
||||
}
|
||||
}
|
||||
return i == maxIgnorable
|
||||
}
|
||||
|
||||
// TODO: implement elUpperSpan (low-priority: complex and infrequent).
|
||||
|
||||
func ltLower(c *context) bool {
|
||||
// From CLDR:
|
||||
// # Introduce an explicit dot above when lowercasing capital I's and J's
|
||||
// # whenever there are more accents above.
|
||||
// # (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek)
|
||||
// # 0049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I
|
||||
// # 004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J
|
||||
// # 012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK
|
||||
// # 00CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
// # 00CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
// # 0128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE
|
||||
// ::NFD();
|
||||
// I } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → i \u0307;
|
||||
// J } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → j \u0307;
|
||||
// I \u0328 (Į) } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → i \u0328 \u0307;
|
||||
// I \u0300 (Ì) → i \u0307 \u0300;
|
||||
// I \u0301 (Í) → i \u0307 \u0301;
|
||||
// I \u0303 (Ĩ) → i \u0307 \u0303;
|
||||
// ::Any-Lower();
|
||||
// ::NFC();
|
||||
|
||||
i := 0
|
||||
if r := c.src[c.pSrc]; r < utf8.RuneSelf {
|
||||
lower(c)
|
||||
if r != 'I' && r != 'J' {
|
||||
return true
|
||||
}
|
||||
} else {
|
||||
p := norm.NFD.Properties(c.src[c.pSrc:])
|
||||
if d := p.Decomposition(); len(d) >= 3 && (d[0] == 'I' || d[0] == 'J') {
|
||||
// UTF-8 optimization: the decomposition will only have an above
|
||||
// modifier if the last rune of the decomposition is in [U+300-U+311].
|
||||
// In all other cases, a decomposition starting with I is always
|
||||
// an I followed by modifiers that are not cased themselves. See A.2.
|
||||
if d[1] == 0xCC && d[2] <= 0x91 { // A.2.4.
|
||||
if !c.writeBytes(d[:1]) {
|
||||
return false
|
||||
}
|
||||
c.dst[c.pDst-1] += 'a' - 'A' // lower
|
||||
|
||||
// Assumption: modifier never changes on lowercase. See A.1.
|
||||
// Assumption: all modifiers added have CCC = Above. See A.2.3.
|
||||
return c.writeString("\u0307") && c.writeBytes(d[1:])
|
||||
}
|
||||
// In all other cases the additional modifiers will have a CCC
|
||||
// that is less than 230 (Above). We will insert the U+0307, if
|
||||
// needed, after these modifiers so that a string in FCD form
|
||||
// will remain so. See A.2.2.
|
||||
lower(c)
|
||||
i = 1
|
||||
} else {
|
||||
return lower(c)
|
||||
}
|
||||
}
|
||||
|
||||
for ; i < maxIgnorable && c.next(); i++ {
|
||||
switch c.info.cccType() {
|
||||
case cccZero:
|
||||
c.unreadRune()
|
||||
return true
|
||||
case cccAbove:
|
||||
return c.writeString("\u0307") && c.copy() // See A.1.
|
||||
default:
|
||||
c.copy() // See A.1.
|
||||
}
|
||||
}
|
||||
return i == maxIgnorable
|
||||
}
|
||||
|
||||
// ltLowerSpan would be the same as isLower.
|
||||
|
||||
func ltUpper(f mapFunc) mapFunc {
|
||||
return func(c *context) bool {
|
||||
// Unicode:
|
||||
// 0307; 0307; ; ; lt After_Soft_Dotted; # COMBINING DOT ABOVE
|
||||
//
|
||||
// From CLDR:
|
||||
// # Remove \u0307 following soft-dotteds (i, j, and the like), with possible
|
||||
// # intervening non-230 marks.
|
||||
// ::NFD();
|
||||
// [:Soft_Dotted:] [^[:ccc=Not_Reordered:][:ccc=Above:]]* { \u0307 → ;
|
||||
// ::Any-Upper();
|
||||
// ::NFC();
|
||||
|
||||
// TODO: See A.5. A soft-dotted rune never has an exception. This would
|
||||
// allow us to overload the exception bit and encode this property in
|
||||
// info. Need to measure performance impact of this.
|
||||
r, _ := utf8.DecodeRune(c.src[c.pSrc:])
|
||||
oldPDst := c.pDst
|
||||
if !f(c) {
|
||||
return false
|
||||
}
|
||||
if !unicode.Is(unicode.Soft_Dotted, r) {
|
||||
return true
|
||||
}
|
||||
|
||||
// We don't need to do an NFD normalization, as a soft-dotted rune never
|
||||
// contains U+0307. See A.3.
|
||||
|
||||
i := 0
|
||||
for ; i < maxIgnorable && c.next(); i++ {
|
||||
switch c.info.cccType() {
|
||||
case cccZero:
|
||||
c.unreadRune()
|
||||
return true
|
||||
case cccAbove:
|
||||
if c.hasPrefix("\u0307") {
|
||||
// We don't do a full NFC, but rather combine runes for
|
||||
// some of the common cases. (Returning NFC or
|
||||
// preserving normal form is neither a requirement nor
|
||||
// a possibility anyway).
|
||||
if !c.next() {
|
||||
return false
|
||||
}
|
||||
if c.dst[oldPDst] == 'I' && c.pDst == oldPDst+1 && c.src[c.pSrc] == 0xcc {
|
||||
s := ""
|
||||
switch c.src[c.pSrc+1] {
|
||||
case 0x80: // U+0300 COMBINING GRAVE ACCENT
|
||||
s = "\u00cc" // U+00CC LATIN CAPITAL LETTER I WITH GRAVE
|
||||
case 0x81: // U+0301 COMBINING ACUTE ACCENT
|
||||
s = "\u00cd" // U+00CD LATIN CAPITAL LETTER I WITH ACUTE
|
||||
case 0x83: // U+0303 COMBINING TILDE
|
||||
s = "\u0128" // U+0128 LATIN CAPITAL LETTER I WITH TILDE
|
||||
case 0x88: // U+0308 COMBINING DIAERESIS
|
||||
s = "\u00cf" // U+00CF LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
default:
|
||||
}
|
||||
if s != "" {
|
||||
c.pDst = oldPDst
|
||||
return c.writeString(s)
|
||||
}
|
||||
}
|
||||
}
|
||||
return c.copy()
|
||||
default:
|
||||
c.copy()
|
||||
}
|
||||
}
|
||||
return i == maxIgnorable
|
||||
}
|
||||
}
|
||||
|
||||
// TODO: implement ltUpperSpan (low priority: complex and infrequent).
|
||||
|
||||
func aztrUpper(f mapFunc) mapFunc {
|
||||
return func(c *context) bool {
|
||||
// i→İ;
|
||||
if c.src[c.pSrc] == 'i' {
|
||||
return c.writeString("İ")
|
||||
}
|
||||
return f(c)
|
||||
}
|
||||
}
|
||||
|
||||
func aztrLower(c *context) (done bool) {
|
||||
// From CLDR:
|
||||
// # I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
|
||||
// # 0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
// İ→i;
|
||||
// # When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
|
||||
// # This matches the behavior of the canonically equivalent I-dot_above
|
||||
// # 0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
|
||||
// # When lowercasing, unless an I is before a dot_above, it turns into a dotless i.
|
||||
// # 0049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
|
||||
// I([^[:ccc=Not_Reordered:][:ccc=Above:]]*)\u0307 → i$1 ;
|
||||
// I→ı ;
|
||||
// ::Any-Lower();
|
||||
if c.hasPrefix("\u0130") { // İ
|
||||
return c.writeString("i")
|
||||
}
|
||||
if c.src[c.pSrc] != 'I' {
|
||||
return lower(c)
|
||||
}
|
||||
|
||||
// We ignore the lower-case I for now, but insert it later when we know
|
||||
// which form we need.
|
||||
start := c.pSrc + c.sz
|
||||
|
||||
i := 0
|
||||
Loop:
|
||||
// We check for up to n ignorables before \u0307. As \u0307 is an
|
||||
// ignorable as well, n is maxIgnorable-1.
|
||||
for ; i < maxIgnorable && c.next(); i++ {
|
||||
switch c.info.cccType() {
|
||||
case cccAbove:
|
||||
if c.hasPrefix("\u0307") {
|
||||
return c.writeString("i") && c.writeBytes(c.src[start:c.pSrc]) // ignore U+0307
|
||||
}
|
||||
done = true
|
||||
break Loop
|
||||
case cccZero:
|
||||
c.unreadRune()
|
||||
done = true
|
||||
break Loop
|
||||
default:
|
||||
// We'll write this rune after we know which starter to use.
|
||||
}
|
||||
}
|
||||
if i == maxIgnorable {
|
||||
done = true
|
||||
}
|
||||
return c.writeString("ı") && c.writeBytes(c.src[start:c.pSrc+c.sz]) && done
|
||||
}
|
||||
|
||||
// aztrLowerSpan would be the same as isLower.
|
||||
|
||||
func nlTitle(c *context) bool {
|
||||
// From CLDR:
|
||||
// # Special titlecasing for Dutch initial "ij".
|
||||
// ::Any-Title();
|
||||
// # Fix up Ij at the beginning of a "word" (per Any-Title, notUAX #29)
|
||||
// [:^WB=ALetter:] [:WB=Extend:]* [[:WB=MidLetter:][:WB=MidNumLet:]]? { Ij } → IJ ;
|
||||
if c.src[c.pSrc] != 'I' && c.src[c.pSrc] != 'i' {
|
||||
return title(c)
|
||||
}
|
||||
|
||||
if !c.writeString("I") || !c.next() {
|
||||
return false
|
||||
}
|
||||
if c.src[c.pSrc] == 'j' || c.src[c.pSrc] == 'J' {
|
||||
return c.writeString("J")
|
||||
}
|
||||
c.unreadRune()
|
||||
return true
|
||||
}
|
||||
|
||||
func nlTitleSpan(c *context) bool {
|
||||
// From CLDR:
|
||||
// # Special titlecasing for Dutch initial "ij".
|
||||
// ::Any-Title();
|
||||
// # Fix up Ij at the beginning of a "word" (per Any-Title, notUAX #29)
|
||||
// [:^WB=ALetter:] [:WB=Extend:]* [[:WB=MidLetter:][:WB=MidNumLet:]]? { Ij } → IJ ;
|
||||
if c.src[c.pSrc] != 'I' {
|
||||
return isTitle(c)
|
||||
}
|
||||
if !c.next() || c.src[c.pSrc] == 'j' {
|
||||
return false
|
||||
}
|
||||
if c.src[c.pSrc] != 'J' {
|
||||
c.unreadRune()
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// Not part of CLDR, but see https://unicode.org/cldr/trac/ticket/7078.
|
||||
func afnlRewrite(c *context) {
|
||||
if c.hasPrefix("'") || c.hasPrefix("’") {
|
||||
c.isMidWord = true
|
||||
}
|
||||
}
|
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
@ -0,0 +1,217 @@
|
|||
// Code generated by running "go generate" in golang.org/x/text. DO NOT EDIT.
|
||||
|
||||
package cases
|
||||
|
||||
// This file contains definitions for interpreting the trie value of the case
|
||||
// trie generated by "go run gen*.go". It is shared by both the generator
|
||||
// program and the resultant package. Sharing is achieved by the generator
|
||||
// copying gen_trieval.go to trieval.go and changing what's above this comment.
|
||||
|
||||
// info holds case information for a single rune. It is the value returned
|
||||
// by a trie lookup. Most mapping information can be stored in a single 16-bit
|
||||
// value. If not, for example when a rune is mapped to multiple runes, the value
|
||||
// stores some basic case data and an index into an array with additional data.
|
||||
//
|
||||
// The per-rune values have the following format:
|
||||
//
|
||||
// if (exception) {
|
||||
// 15..4 unsigned exception index
|
||||
// } else {
|
||||
// 15..8 XOR pattern or index to XOR pattern for case mapping
|
||||
// Only 13..8 are used for XOR patterns.
|
||||
// 7 inverseFold (fold to upper, not to lower)
|
||||
// 6 index: interpret the XOR pattern as an index
|
||||
// or isMid if case mode is cIgnorableUncased.
|
||||
// 5..4 CCC: zero (normal or break), above or other
|
||||
// }
|
||||
// 3 exception: interpret this value as an exception index
|
||||
// (TODO: is this bit necessary? Probably implied from case mode.)
|
||||
// 2..0 case mode
|
||||
//
|
||||
// For the non-exceptional cases, a rune must be either uncased, lowercase or
|
||||
// uppercase. If the rune is cased, the XOR pattern maps either a lowercase
|
||||
// rune to uppercase or an uppercase rune to lowercase (applied to the 10
|
||||
// least-significant bits of the rune).
|
||||
//
|
||||
// See the definitions below for a more detailed description of the various
|
||||
// bits.
|
||||
type info uint16
|
||||
|
||||
const (
|
||||
casedMask = 0x0003
|
||||
fullCasedMask = 0x0007
|
||||
ignorableMask = 0x0006
|
||||
ignorableValue = 0x0004
|
||||
|
||||
inverseFoldBit = 1 << 7
|
||||
isMidBit = 1 << 6
|
||||
|
||||
exceptionBit = 1 << 3
|
||||
exceptionShift = 4
|
||||
numExceptionBits = 12
|
||||
|
||||
xorIndexBit = 1 << 6
|
||||
xorShift = 8
|
||||
|
||||
// There is no mapping if all xor bits and the exception bit are zero.
|
||||
hasMappingMask = 0xff80 | exceptionBit
|
||||
)
|
||||
|
||||
// The case mode bits encodes the case type of a rune. This includes uncased,
|
||||
// title, upper and lower case and case ignorable. (For a definition of these
|
||||
// terms see Chapter 3 of The Unicode Standard Core Specification.) In some rare
|
||||
// cases, a rune can be both cased and case-ignorable. This is encoded by
|
||||
// cIgnorableCased. A rune of this type is always lower case. Some runes are
|
||||
// cased while not having a mapping.
|
||||
//
|
||||
// A common pattern for scripts in the Unicode standard is for upper and lower
|
||||
// case runes to alternate for increasing rune values (e.g. the accented Latin
|
||||
// ranges starting from U+0100 and U+1E00 among others and some Cyrillic
|
||||
// characters). We use this property by defining a cXORCase mode, where the case
|
||||
// mode (always upper or lower case) is derived from the rune value. As the XOR
|
||||
// pattern for case mappings is often identical for successive runes, using
|
||||
// cXORCase can result in large series of identical trie values. This, in turn,
|
||||
// allows us to better compress the trie blocks.
|
||||
const (
|
||||
cUncased info = iota // 000
|
||||
cTitle // 001
|
||||
cLower // 010
|
||||
cUpper // 011
|
||||
cIgnorableUncased // 100
|
||||
cIgnorableCased // 101 // lower case if mappings exist
|
||||
cXORCase // 11x // case is cLower | ((rune&1) ^ x)
|
||||
|
||||
maxCaseMode = cUpper
|
||||
)
|
||||
|
||||
func (c info) isCased() bool {
|
||||
return c&casedMask != 0
|
||||
}
|
||||
|
||||
func (c info) isCaseIgnorable() bool {
|
||||
return c&ignorableMask == ignorableValue
|
||||
}
|
||||
|
||||
func (c info) isNotCasedAndNotCaseIgnorable() bool {
|
||||
return c&fullCasedMask == 0
|
||||
}
|
||||
|
||||
func (c info) isCaseIgnorableAndNotCased() bool {
|
||||
return c&fullCasedMask == cIgnorableUncased
|
||||
}
|
||||
|
||||
func (c info) isMid() bool {
|
||||
return c&(fullCasedMask|isMidBit) == isMidBit|cIgnorableUncased
|
||||
}
|
||||
|
||||
// The case mapping implementation will need to know about various Canonical
|
||||
// Combining Class (CCC) values. We encode two of these in the trie value:
|
||||
// cccZero (0) and cccAbove (230). If the value is cccOther, it means that
|
||||
// CCC(r) > 0, but not 230. A value of cccBreak means that CCC(r) == 0 and that
|
||||
// the rune also has the break category Break (see below).
|
||||
const (
|
||||
cccBreak info = iota << 4
|
||||
cccZero
|
||||
cccAbove
|
||||
cccOther
|
||||
|
||||
cccMask = cccBreak | cccZero | cccAbove | cccOther
|
||||
)
|
||||
|
||||
const (
|
||||
starter = 0
|
||||
above = 230
|
||||
iotaSubscript = 240
|
||||
)
|
||||
|
||||
// The exceptions slice holds data that does not fit in a normal info entry.
|
||||
// The entry is pointed to by the exception index in an entry. It has the
|
||||
// following format:
|
||||
//
|
||||
// Header:
|
||||
//
|
||||
// byte 0:
|
||||
// 7..6 unused
|
||||
// 5..4 CCC type (same bits as entry)
|
||||
// 3 unused
|
||||
// 2..0 length of fold
|
||||
//
|
||||
// byte 1:
|
||||
// 7..6 unused
|
||||
// 5..3 length of 1st mapping of case type
|
||||
// 2..0 length of 2nd mapping of case type
|
||||
//
|
||||
// case 1st 2nd
|
||||
// lower -> upper, title
|
||||
// upper -> lower, title
|
||||
// title -> lower, upper
|
||||
//
|
||||
// Lengths with the value 0x7 indicate no value and implies no change.
|
||||
// A length of 0 indicates a mapping to zero-length string.
|
||||
//
|
||||
// Body bytes:
|
||||
//
|
||||
// case folding bytes
|
||||
// lowercase mapping bytes
|
||||
// uppercase mapping bytes
|
||||
// titlecase mapping bytes
|
||||
// closure mapping bytes (for NFKC_Casefold). (TODO)
|
||||
//
|
||||
// Fallbacks:
|
||||
//
|
||||
// missing fold -> lower
|
||||
// missing title -> upper
|
||||
// all missing -> original rune
|
||||
//
|
||||
// exceptions starts with a dummy byte to enforce that there is no zero index
|
||||
// value.
|
||||
const (
|
||||
lengthMask = 0x07
|
||||
lengthBits = 3
|
||||
noChange = 0
|
||||
)
|
||||
|
||||
// References to generated trie.
|
||||
|
||||
var trie = newCaseTrie(0)
|
||||
|
||||
var sparse = sparseBlocks{
|
||||
values: sparseValues[:],
|
||||
offsets: sparseOffsets[:],
|
||||
}
|
||||
|
||||
// Sparse block lookup code.
|
||||
|
||||
// valueRange is an entry in a sparse block.
|
||||
type valueRange struct {
|
||||
value uint16
|
||||
lo, hi byte
|
||||
}
|
||||
|
||||
type sparseBlocks struct {
|
||||
values []valueRange
|
||||
offsets []uint16
|
||||
}
|
||||
|
||||
// lookup returns the value from values block n for byte b using binary search.
|
||||
func (s *sparseBlocks) lookup(n uint32, b byte) uint16 {
|
||||
lo := s.offsets[n]
|
||||
hi := s.offsets[n+1]
|
||||
for lo < hi {
|
||||
m := lo + (hi-lo)/2
|
||||
r := s.values[m]
|
||||
if r.lo <= b && b <= r.hi {
|
||||
return r.value
|
||||
}
|
||||
if b < r.lo {
|
||||
hi = m
|
||||
} else {
|
||||
lo = m + 1
|
||||
}
|
||||
}
|
||||
return 0
|
||||
}
|
||||
|
||||
// lastRuneForTesting is the last rune used for testing. Everything after this
|
||||
// is boring.
|
||||
const lastRuneForTesting = rune(0x1FFFF)
|
|
@ -0,0 +1,49 @@
|
|||
// 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 internal contains non-exported functionality that are used by
|
||||
// packages in the text repository.
|
||||
package internal // import "golang.org/x/text/internal"
|
||||
|
||||
import (
|
||||
"sort"
|
||||
|
||||
"golang.org/x/text/language"
|
||||
)
|
||||
|
||||
// SortTags sorts tags in place.
|
||||
func SortTags(tags []language.Tag) {
|
||||
sort.Sort(sorter(tags))
|
||||
}
|
||||
|
||||
type sorter []language.Tag
|
||||
|
||||
func (s sorter) Len() int {
|
||||
return len(s)
|
||||
}
|
||||
|
||||
func (s sorter) Swap(i, j int) {
|
||||
s[i], s[j] = s[j], s[i]
|
||||
}
|
||||
|
||||
func (s sorter) Less(i, j int) bool {
|
||||
return s[i].String() < s[j].String()
|
||||
}
|
||||
|
||||
// UniqueTags sorts and filters duplicate tags in place and returns a slice with
|
||||
// only unique tags.
|
||||
func UniqueTags(tags []language.Tag) []language.Tag {
|
||||
if len(tags) <= 1 {
|
||||
return tags
|
||||
}
|
||||
SortTags(tags)
|
||||
k := 0
|
||||
for i := 1; i < len(tags); i++ {
|
||||
if tags[k].String() < tags[i].String() {
|
||||
k++
|
||||
tags[k] = tags[i]
|
||||
}
|
||||
}
|
||||
return tags[:k+1]
|
||||
}
|
|
@ -790,226 +790,226 @@ const (
|
|||
|
||||
var coreTags = []language.CompactCoreInfo{ // 773 elements
|
||||
// Entry 0 - 1F
|
||||
0x00000000, 0x01600000, 0x016000d2, 0x01600161,
|
||||
0x01c00000, 0x01c00052, 0x02100000, 0x02100080,
|
||||
0x02700000, 0x0270006f, 0x03a00000, 0x03a00001,
|
||||
0x03a00023, 0x03a00039, 0x03a00062, 0x03a00067,
|
||||
0x03a0006b, 0x03a0006c, 0x03a0006d, 0x03a00097,
|
||||
0x03a0009b, 0x03a000a1, 0x03a000a8, 0x03a000ac,
|
||||
0x03a000b0, 0x03a000b9, 0x03a000ba, 0x03a000c9,
|
||||
0x03a000e1, 0x03a000ed, 0x03a000f3, 0x03a00108,
|
||||
0x00000000, 0x01600000, 0x016000d3, 0x01600162,
|
||||
0x01c00000, 0x01c00052, 0x02100000, 0x02100081,
|
||||
0x02700000, 0x02700070, 0x03a00000, 0x03a00001,
|
||||
0x03a00023, 0x03a00039, 0x03a00063, 0x03a00068,
|
||||
0x03a0006c, 0x03a0006d, 0x03a0006e, 0x03a00098,
|
||||
0x03a0009c, 0x03a000a2, 0x03a000a9, 0x03a000ad,
|
||||
0x03a000b1, 0x03a000ba, 0x03a000bb, 0x03a000ca,
|
||||
0x03a000e2, 0x03a000ee, 0x03a000f4, 0x03a00109,
|
||||
// Entry 20 - 3F
|
||||
0x03a0010b, 0x03a00115, 0x03a00117, 0x03a0011c,
|
||||
0x03a00120, 0x03a00128, 0x03a0015e, 0x04000000,
|
||||
0x04300000, 0x04300099, 0x04400000, 0x0440012f,
|
||||
0x04800000, 0x0480006e, 0x05800000, 0x05820000,
|
||||
0x05820032, 0x0585a000, 0x0585a032, 0x05e00000,
|
||||
0x03a0010c, 0x03a00116, 0x03a00118, 0x03a0011d,
|
||||
0x03a00121, 0x03a00129, 0x03a0015f, 0x04000000,
|
||||
0x04300000, 0x0430009a, 0x04400000, 0x04400130,
|
||||
0x04800000, 0x0480006f, 0x05800000, 0x05820000,
|
||||
0x05820032, 0x0585b000, 0x0585b032, 0x05e00000,
|
||||
0x05e00052, 0x07100000, 0x07100047, 0x07500000,
|
||||
0x07500162, 0x07900000, 0x0790012f, 0x07e00000,
|
||||
0x07e00038, 0x08200000, 0x0a000000, 0x0a0000c3,
|
||||
0x07500163, 0x07900000, 0x07900130, 0x07e00000,
|
||||
0x07e00038, 0x08200000, 0x0a000000, 0x0a0000c4,
|
||||
// Entry 40 - 5F
|
||||
0x0a500000, 0x0a500035, 0x0a500099, 0x0a900000,
|
||||
0x0a900053, 0x0a900099, 0x0b200000, 0x0b200078,
|
||||
0x0b500000, 0x0b500099, 0x0b700000, 0x0b720000,
|
||||
0x0b720033, 0x0b75a000, 0x0b75a033, 0x0d700000,
|
||||
0x0d700022, 0x0d70006e, 0x0d700078, 0x0d70009e,
|
||||
0x0db00000, 0x0db00035, 0x0db00099, 0x0dc00000,
|
||||
0x0dc00106, 0x0df00000, 0x0df00131, 0x0e500000,
|
||||
0x0e500135, 0x0e900000, 0x0e90009b, 0x0e90009c,
|
||||
0x0a500000, 0x0a500035, 0x0a50009a, 0x0a900000,
|
||||
0x0a900053, 0x0a90009a, 0x0b200000, 0x0b200079,
|
||||
0x0b500000, 0x0b50009a, 0x0b700000, 0x0b720000,
|
||||
0x0b720033, 0x0b75b000, 0x0b75b033, 0x0d700000,
|
||||
0x0d700022, 0x0d70006f, 0x0d700079, 0x0d70009f,
|
||||
0x0db00000, 0x0db00035, 0x0db0009a, 0x0dc00000,
|
||||
0x0dc00107, 0x0df00000, 0x0df00132, 0x0e500000,
|
||||
0x0e500136, 0x0e900000, 0x0e90009c, 0x0e90009d,
|
||||
// Entry 60 - 7F
|
||||
0x0fa00000, 0x0fa0005e, 0x0fe00000, 0x0fe00106,
|
||||
0x10000000, 0x1000007b, 0x10100000, 0x10100063,
|
||||
0x10100082, 0x10800000, 0x108000a4, 0x10d00000,
|
||||
0x10d0002e, 0x10d00036, 0x10d0004e, 0x10d00060,
|
||||
0x10d0009e, 0x10d000b2, 0x10d000b7, 0x11700000,
|
||||
0x117000d4, 0x11f00000, 0x11f00060, 0x12400000,
|
||||
0x12400052, 0x12800000, 0x12b00000, 0x12b00114,
|
||||
0x12d00000, 0x12d00043, 0x12f00000, 0x12f000a4,
|
||||
0x0fa00000, 0x0fa0005f, 0x0fe00000, 0x0fe00107,
|
||||
0x10000000, 0x1000007c, 0x10100000, 0x10100064,
|
||||
0x10100083, 0x10800000, 0x108000a5, 0x10d00000,
|
||||
0x10d0002e, 0x10d00036, 0x10d0004e, 0x10d00061,
|
||||
0x10d0009f, 0x10d000b3, 0x10d000b8, 0x11700000,
|
||||
0x117000d5, 0x11f00000, 0x11f00061, 0x12400000,
|
||||
0x12400052, 0x12800000, 0x12b00000, 0x12b00115,
|
||||
0x12d00000, 0x12d00043, 0x12f00000, 0x12f000a5,
|
||||
// Entry 80 - 9F
|
||||
0x13000000, 0x13000080, 0x13000122, 0x13600000,
|
||||
0x1360005d, 0x13600087, 0x13900000, 0x13900001,
|
||||
0x13000000, 0x13000081, 0x13000123, 0x13600000,
|
||||
0x1360005e, 0x13600088, 0x13900000, 0x13900001,
|
||||
0x1390001a, 0x13900025, 0x13900026, 0x1390002d,
|
||||
0x1390002e, 0x1390002f, 0x13900034, 0x13900036,
|
||||
0x1390003a, 0x1390003d, 0x13900042, 0x13900046,
|
||||
0x13900048, 0x13900049, 0x1390004a, 0x1390004e,
|
||||
0x13900050, 0x13900052, 0x1390005c, 0x1390005d,
|
||||
0x13900060, 0x13900061, 0x13900063, 0x13900064,
|
||||
0x13900050, 0x13900052, 0x1390005d, 0x1390005e,
|
||||
0x13900061, 0x13900062, 0x13900064, 0x13900065,
|
||||
// Entry A0 - BF
|
||||
0x1390006d, 0x13900072, 0x13900073, 0x13900074,
|
||||
0x13900075, 0x1390007b, 0x1390007c, 0x1390007f,
|
||||
0x13900080, 0x13900081, 0x13900083, 0x1390008a,
|
||||
0x1390008c, 0x1390008d, 0x13900096, 0x13900097,
|
||||
0x13900098, 0x13900099, 0x1390009a, 0x1390009f,
|
||||
0x139000a0, 0x139000a4, 0x139000a7, 0x139000a9,
|
||||
0x139000ad, 0x139000b1, 0x139000b4, 0x139000b5,
|
||||
0x139000bf, 0x139000c0, 0x139000c6, 0x139000c7,
|
||||
0x1390006e, 0x13900073, 0x13900074, 0x13900075,
|
||||
0x13900076, 0x1390007c, 0x1390007d, 0x13900080,
|
||||
0x13900081, 0x13900082, 0x13900084, 0x1390008b,
|
||||
0x1390008d, 0x1390008e, 0x13900097, 0x13900098,
|
||||
0x13900099, 0x1390009a, 0x1390009b, 0x139000a0,
|
||||
0x139000a1, 0x139000a5, 0x139000a8, 0x139000aa,
|
||||
0x139000ae, 0x139000b2, 0x139000b5, 0x139000b6,
|
||||
0x139000c0, 0x139000c1, 0x139000c7, 0x139000c8,
|
||||
// Entry C0 - DF
|
||||
0x139000ca, 0x139000cb, 0x139000cc, 0x139000ce,
|
||||
0x139000d0, 0x139000d2, 0x139000d5, 0x139000d6,
|
||||
0x139000d9, 0x139000dd, 0x139000df, 0x139000e0,
|
||||
0x139000e6, 0x139000e7, 0x139000e8, 0x139000eb,
|
||||
0x139000ec, 0x139000f0, 0x13900107, 0x13900109,
|
||||
0x1390010a, 0x1390010b, 0x1390010c, 0x1390010d,
|
||||
0x1390010e, 0x1390010f, 0x13900112, 0x13900117,
|
||||
0x1390011b, 0x1390011d, 0x1390011f, 0x13900125,
|
||||
0x139000cb, 0x139000cc, 0x139000cd, 0x139000cf,
|
||||
0x139000d1, 0x139000d3, 0x139000d6, 0x139000d7,
|
||||
0x139000da, 0x139000de, 0x139000e0, 0x139000e1,
|
||||
0x139000e7, 0x139000e8, 0x139000e9, 0x139000ec,
|
||||
0x139000ed, 0x139000f1, 0x13900108, 0x1390010a,
|
||||
0x1390010b, 0x1390010c, 0x1390010d, 0x1390010e,
|
||||
0x1390010f, 0x13900110, 0x13900113, 0x13900118,
|
||||
0x1390011c, 0x1390011e, 0x13900120, 0x13900126,
|
||||
// Entry E0 - FF
|
||||
0x13900129, 0x1390012c, 0x1390012d, 0x1390012f,
|
||||
0x13900131, 0x13900133, 0x13900135, 0x13900139,
|
||||
0x1390013c, 0x1390013d, 0x1390013f, 0x13900142,
|
||||
0x13900161, 0x13900162, 0x13900164, 0x13c00000,
|
||||
0x1390012a, 0x1390012d, 0x1390012e, 0x13900130,
|
||||
0x13900132, 0x13900134, 0x13900136, 0x1390013a,
|
||||
0x1390013d, 0x1390013e, 0x13900140, 0x13900143,
|
||||
0x13900162, 0x13900163, 0x13900165, 0x13c00000,
|
||||
0x13c00001, 0x13e00000, 0x13e0001f, 0x13e0002c,
|
||||
0x13e0003f, 0x13e00041, 0x13e00048, 0x13e00051,
|
||||
0x13e00054, 0x13e00056, 0x13e00059, 0x13e00065,
|
||||
0x13e00068, 0x13e00069, 0x13e0006e, 0x13e00086,
|
||||
0x13e00054, 0x13e00057, 0x13e0005a, 0x13e00066,
|
||||
0x13e00069, 0x13e0006a, 0x13e0006f, 0x13e00087,
|
||||
// Entry 100 - 11F
|
||||
0x13e00089, 0x13e0008f, 0x13e00094, 0x13e000cf,
|
||||
0x13e000d8, 0x13e000e2, 0x13e000e4, 0x13e000e7,
|
||||
0x13e000ec, 0x13e000f1, 0x13e0011a, 0x13e00135,
|
||||
0x13e00136, 0x13e0013b, 0x14000000, 0x1400006a,
|
||||
0x14500000, 0x1450006e, 0x14600000, 0x14600052,
|
||||
0x14800000, 0x14800024, 0x1480009c, 0x14e00000,
|
||||
0x14e00052, 0x14e00084, 0x14e000c9, 0x14e00114,
|
||||
0x15100000, 0x15100072, 0x15300000, 0x153000e7,
|
||||
0x13e0008a, 0x13e00090, 0x13e00095, 0x13e000d0,
|
||||
0x13e000d9, 0x13e000e3, 0x13e000e5, 0x13e000e8,
|
||||
0x13e000ed, 0x13e000f2, 0x13e0011b, 0x13e00136,
|
||||
0x13e00137, 0x13e0013c, 0x14000000, 0x1400006b,
|
||||
0x14500000, 0x1450006f, 0x14600000, 0x14600052,
|
||||
0x14800000, 0x14800024, 0x1480009d, 0x14e00000,
|
||||
0x14e00052, 0x14e00085, 0x14e000ca, 0x14e00115,
|
||||
0x15100000, 0x15100073, 0x15300000, 0x153000e8,
|
||||
// Entry 120 - 13F
|
||||
0x15800000, 0x15800063, 0x15800076, 0x15e00000,
|
||||
0x15800000, 0x15800064, 0x15800077, 0x15e00000,
|
||||
0x15e00036, 0x15e00037, 0x15e0003a, 0x15e0003b,
|
||||
0x15e0003c, 0x15e00049, 0x15e0004b, 0x15e0004c,
|
||||
0x15e0004d, 0x15e0004e, 0x15e0004f, 0x15e00052,
|
||||
0x15e00062, 0x15e00067, 0x15e00078, 0x15e0007a,
|
||||
0x15e0007e, 0x15e00084, 0x15e00085, 0x15e00086,
|
||||
0x15e00091, 0x15e000a8, 0x15e000b7, 0x15e000ba,
|
||||
0x15e000bb, 0x15e000be, 0x15e000bf, 0x15e000c3,
|
||||
0x15e00063, 0x15e00068, 0x15e00079, 0x15e0007b,
|
||||
0x15e0007f, 0x15e00085, 0x15e00086, 0x15e00087,
|
||||
0x15e00092, 0x15e000a9, 0x15e000b8, 0x15e000bb,
|
||||
0x15e000bc, 0x15e000bf, 0x15e000c0, 0x15e000c4,
|
||||
// Entry 140 - 15F
|
||||
0x15e000c8, 0x15e000c9, 0x15e000cc, 0x15e000d3,
|
||||
0x15e000d4, 0x15e000e5, 0x15e000ea, 0x15e00102,
|
||||
0x15e00107, 0x15e0010a, 0x15e00114, 0x15e0011c,
|
||||
0x15e00120, 0x15e00122, 0x15e00128, 0x15e0013f,
|
||||
0x15e00140, 0x15e0015f, 0x16900000, 0x1690009e,
|
||||
0x16d00000, 0x16d000d9, 0x16e00000, 0x16e00096,
|
||||
0x17e00000, 0x17e0007b, 0x19000000, 0x1900006e,
|
||||
0x1a300000, 0x1a30004e, 0x1a300078, 0x1a3000b2,
|
||||
0x15e000c9, 0x15e000ca, 0x15e000cd, 0x15e000d4,
|
||||
0x15e000d5, 0x15e000e6, 0x15e000eb, 0x15e00103,
|
||||
0x15e00108, 0x15e0010b, 0x15e00115, 0x15e0011d,
|
||||
0x15e00121, 0x15e00123, 0x15e00129, 0x15e00140,
|
||||
0x15e00141, 0x15e00160, 0x16900000, 0x1690009f,
|
||||
0x16d00000, 0x16d000da, 0x16e00000, 0x16e00097,
|
||||
0x17e00000, 0x17e0007c, 0x19000000, 0x1900006f,
|
||||
0x1a300000, 0x1a30004e, 0x1a300079, 0x1a3000b3,
|
||||
// Entry 160 - 17F
|
||||
0x1a400000, 0x1a400099, 0x1a900000, 0x1ab00000,
|
||||
0x1ab000a4, 0x1ac00000, 0x1ac00098, 0x1b400000,
|
||||
0x1b400080, 0x1b4000d4, 0x1b4000d6, 0x1b800000,
|
||||
0x1b800135, 0x1bc00000, 0x1bc00097, 0x1be00000,
|
||||
0x1be00099, 0x1d100000, 0x1d100033, 0x1d100090,
|
||||
0x1d200000, 0x1d200060, 0x1d500000, 0x1d500092,
|
||||
0x1d700000, 0x1d700028, 0x1e100000, 0x1e100095,
|
||||
0x1e700000, 0x1e7000d6, 0x1ea00000, 0x1ea00053,
|
||||
0x1a400000, 0x1a40009a, 0x1a900000, 0x1ab00000,
|
||||
0x1ab000a5, 0x1ac00000, 0x1ac00099, 0x1b400000,
|
||||
0x1b400081, 0x1b4000d5, 0x1b4000d7, 0x1b800000,
|
||||
0x1b800136, 0x1bc00000, 0x1bc00098, 0x1be00000,
|
||||
0x1be0009a, 0x1d100000, 0x1d100033, 0x1d100091,
|
||||
0x1d200000, 0x1d200061, 0x1d500000, 0x1d500093,
|
||||
0x1d700000, 0x1d700028, 0x1e100000, 0x1e100096,
|
||||
0x1e700000, 0x1e7000d7, 0x1ea00000, 0x1ea00053,
|
||||
// Entry 180 - 19F
|
||||
0x1f300000, 0x1f500000, 0x1f800000, 0x1f80009d,
|
||||
0x1f900000, 0x1f90004e, 0x1f90009e, 0x1f900113,
|
||||
0x1f900138, 0x1fa00000, 0x1fb00000, 0x20000000,
|
||||
0x200000a2, 0x20300000, 0x20700000, 0x20700052,
|
||||
0x20800000, 0x20a00000, 0x20a0012f, 0x20e00000,
|
||||
0x20f00000, 0x21000000, 0x2100007d, 0x21200000,
|
||||
0x21200067, 0x21600000, 0x21700000, 0x217000a4,
|
||||
0x21f00000, 0x22300000, 0x2230012f, 0x22700000,
|
||||
0x1f300000, 0x1f500000, 0x1f800000, 0x1f80009e,
|
||||
0x1f900000, 0x1f90004e, 0x1f90009f, 0x1f900114,
|
||||
0x1f900139, 0x1fa00000, 0x1fb00000, 0x20000000,
|
||||
0x200000a3, 0x20300000, 0x20700000, 0x20700052,
|
||||
0x20800000, 0x20a00000, 0x20a00130, 0x20e00000,
|
||||
0x20f00000, 0x21000000, 0x2100007e, 0x21200000,
|
||||
0x21200068, 0x21600000, 0x21700000, 0x217000a5,
|
||||
0x21f00000, 0x22300000, 0x22300130, 0x22700000,
|
||||
// Entry 1A0 - 1BF
|
||||
0x2270005a, 0x23400000, 0x234000c3, 0x23900000,
|
||||
0x239000a4, 0x24200000, 0x242000ae, 0x24400000,
|
||||
0x24400052, 0x24500000, 0x24500082, 0x24600000,
|
||||
0x246000a4, 0x24a00000, 0x24a000a6, 0x25100000,
|
||||
0x25100099, 0x25400000, 0x254000aa, 0x254000ab,
|
||||
0x25600000, 0x25600099, 0x26a00000, 0x26a00099,
|
||||
0x26b00000, 0x26b0012f, 0x26d00000, 0x26d00052,
|
||||
0x26e00000, 0x26e00060, 0x27400000, 0x28100000,
|
||||
0x2270005b, 0x23400000, 0x234000c4, 0x23900000,
|
||||
0x239000a5, 0x24200000, 0x242000af, 0x24400000,
|
||||
0x24400052, 0x24500000, 0x24500083, 0x24600000,
|
||||
0x246000a5, 0x24a00000, 0x24a000a7, 0x25100000,
|
||||
0x2510009a, 0x25400000, 0x254000ab, 0x254000ac,
|
||||
0x25600000, 0x2560009a, 0x26a00000, 0x26a0009a,
|
||||
0x26b00000, 0x26b00130, 0x26d00000, 0x26d00052,
|
||||
0x26e00000, 0x26e00061, 0x27400000, 0x28100000,
|
||||
// Entry 1C0 - 1DF
|
||||
0x2810007b, 0x28a00000, 0x28a000a5, 0x29100000,
|
||||
0x2910012f, 0x29500000, 0x295000b7, 0x2a300000,
|
||||
0x2a300131, 0x2af00000, 0x2af00135, 0x2b500000,
|
||||
0x2810007c, 0x28a00000, 0x28a000a6, 0x29100000,
|
||||
0x29100130, 0x29500000, 0x295000b8, 0x2a300000,
|
||||
0x2a300132, 0x2af00000, 0x2af00136, 0x2b500000,
|
||||
0x2b50002a, 0x2b50004b, 0x2b50004c, 0x2b50004d,
|
||||
0x2b800000, 0x2b8000af, 0x2bf00000, 0x2bf0009b,
|
||||
0x2bf0009c, 0x2c000000, 0x2c0000b6, 0x2c200000,
|
||||
0x2c20004b, 0x2c400000, 0x2c4000a4, 0x2c500000,
|
||||
0x2c5000a4, 0x2c700000, 0x2c7000b8, 0x2d100000,
|
||||
0x2b800000, 0x2b8000b0, 0x2bf00000, 0x2bf0009c,
|
||||
0x2bf0009d, 0x2c000000, 0x2c0000b7, 0x2c200000,
|
||||
0x2c20004b, 0x2c400000, 0x2c4000a5, 0x2c500000,
|
||||
0x2c5000a5, 0x2c700000, 0x2c7000b9, 0x2d100000,
|
||||
// Entry 1E0 - 1FF
|
||||
0x2d1000a4, 0x2d10012f, 0x2e900000, 0x2e9000a4,
|
||||
0x2ed00000, 0x2ed000cc, 0x2f100000, 0x2f1000bf,
|
||||
0x2f200000, 0x2f2000d1, 0x2f400000, 0x2f400052,
|
||||
0x2ff00000, 0x2ff000c2, 0x30400000, 0x30400099,
|
||||
0x30b00000, 0x30b000c5, 0x31000000, 0x31b00000,
|
||||
0x31b00099, 0x31f00000, 0x31f0003e, 0x31f000d0,
|
||||
0x31f0010d, 0x32000000, 0x320000cb, 0x32500000,
|
||||
0x32500052, 0x33100000, 0x331000c4, 0x33a00000,
|
||||
0x2d1000a5, 0x2d100130, 0x2e900000, 0x2e9000a5,
|
||||
0x2ed00000, 0x2ed000cd, 0x2f100000, 0x2f1000c0,
|
||||
0x2f200000, 0x2f2000d2, 0x2f400000, 0x2f400052,
|
||||
0x2ff00000, 0x2ff000c3, 0x30400000, 0x3040009a,
|
||||
0x30b00000, 0x30b000c6, 0x31000000, 0x31b00000,
|
||||
0x31b0009a, 0x31f00000, 0x31f0003e, 0x31f000d1,
|
||||
0x31f0010e, 0x32000000, 0x320000cc, 0x32500000,
|
||||
0x32500052, 0x33100000, 0x331000c5, 0x33a00000,
|
||||
// Entry 200 - 21F
|
||||
0x33a0009c, 0x34100000, 0x34500000, 0x345000d2,
|
||||
0x34700000, 0x347000da, 0x34700110, 0x34e00000,
|
||||
0x34e00164, 0x35000000, 0x35000060, 0x350000d9,
|
||||
0x35100000, 0x35100099, 0x351000db, 0x36700000,
|
||||
0x36700030, 0x36700036, 0x36700040, 0x3670005b,
|
||||
0x367000d9, 0x36700116, 0x3670011b, 0x36800000,
|
||||
0x36800052, 0x36a00000, 0x36a000da, 0x36c00000,
|
||||
0x33a0009d, 0x34100000, 0x34500000, 0x345000d3,
|
||||
0x34700000, 0x347000db, 0x34700111, 0x34e00000,
|
||||
0x34e00165, 0x35000000, 0x35000061, 0x350000da,
|
||||
0x35100000, 0x3510009a, 0x351000dc, 0x36700000,
|
||||
0x36700030, 0x36700036, 0x36700040, 0x3670005c,
|
||||
0x367000da, 0x36700117, 0x3670011c, 0x36800000,
|
||||
0x36800052, 0x36a00000, 0x36a000db, 0x36c00000,
|
||||
0x36c00052, 0x36f00000, 0x37500000, 0x37600000,
|
||||
// Entry 220 - 23F
|
||||
0x37a00000, 0x38000000, 0x38000117, 0x38700000,
|
||||
0x38900000, 0x38900131, 0x39000000, 0x3900006f,
|
||||
0x390000a4, 0x39500000, 0x39500099, 0x39800000,
|
||||
0x3980007d, 0x39800106, 0x39d00000, 0x39d05000,
|
||||
0x39d050e8, 0x39d36000, 0x39d36099, 0x3a100000,
|
||||
0x3b300000, 0x3b3000e9, 0x3bd00000, 0x3bd00001,
|
||||
0x37a00000, 0x38000000, 0x38000118, 0x38700000,
|
||||
0x38900000, 0x38900132, 0x39000000, 0x39000070,
|
||||
0x390000a5, 0x39500000, 0x3950009a, 0x39800000,
|
||||
0x3980007e, 0x39800107, 0x39d00000, 0x39d05000,
|
||||
0x39d050e9, 0x39d36000, 0x39d3609a, 0x3a100000,
|
||||
0x3b300000, 0x3b3000ea, 0x3bd00000, 0x3bd00001,
|
||||
0x3be00000, 0x3be00024, 0x3c000000, 0x3c00002a,
|
||||
0x3c000041, 0x3c00004e, 0x3c00005a, 0x3c000086,
|
||||
0x3c000041, 0x3c00004e, 0x3c00005b, 0x3c000087,
|
||||
// Entry 240 - 25F
|
||||
0x3c00008b, 0x3c0000b7, 0x3c0000c6, 0x3c0000d1,
|
||||
0x3c0000ee, 0x3c000118, 0x3c000126, 0x3c400000,
|
||||
0x3c40003f, 0x3c400069, 0x3c4000e4, 0x3d400000,
|
||||
0x3c00008c, 0x3c0000b8, 0x3c0000c7, 0x3c0000d2,
|
||||
0x3c0000ef, 0x3c000119, 0x3c000127, 0x3c400000,
|
||||
0x3c40003f, 0x3c40006a, 0x3c4000e5, 0x3d400000,
|
||||
0x3d40004e, 0x3d900000, 0x3d90003a, 0x3dc00000,
|
||||
0x3dc000bc, 0x3dc00104, 0x3de00000, 0x3de0012f,
|
||||
0x3e200000, 0x3e200047, 0x3e2000a5, 0x3e2000ae,
|
||||
0x3e2000bc, 0x3e200106, 0x3e200130, 0x3e500000,
|
||||
0x3e500107, 0x3e600000, 0x3e60012f, 0x3eb00000,
|
||||
0x3dc000bd, 0x3dc00105, 0x3de00000, 0x3de00130,
|
||||
0x3e200000, 0x3e200047, 0x3e2000a6, 0x3e2000af,
|
||||
0x3e2000bd, 0x3e200107, 0x3e200131, 0x3e500000,
|
||||
0x3e500108, 0x3e600000, 0x3e600130, 0x3eb00000,
|
||||
// Entry 260 - 27F
|
||||
0x3eb00106, 0x3ec00000, 0x3ec000a4, 0x3f300000,
|
||||
0x3f30012f, 0x3fa00000, 0x3fa000e8, 0x3fc00000,
|
||||
0x3fd00000, 0x3fd00072, 0x3fd000da, 0x3fd0010c,
|
||||
0x3ff00000, 0x3ff000d1, 0x40100000, 0x401000c3,
|
||||
0x3eb00107, 0x3ec00000, 0x3ec000a5, 0x3f300000,
|
||||
0x3f300130, 0x3fa00000, 0x3fa000e9, 0x3fc00000,
|
||||
0x3fd00000, 0x3fd00073, 0x3fd000db, 0x3fd0010d,
|
||||
0x3ff00000, 0x3ff000d2, 0x40100000, 0x401000c4,
|
||||
0x40200000, 0x4020004c, 0x40700000, 0x40800000,
|
||||
0x4085a000, 0x4085a0ba, 0x408e8000, 0x408e80ba,
|
||||
0x40c00000, 0x40c000b3, 0x41200000, 0x41200111,
|
||||
0x41600000, 0x4160010f, 0x41c00000, 0x41d00000,
|
||||
0x4085b000, 0x4085b0bb, 0x408eb000, 0x408eb0bb,
|
||||
0x40c00000, 0x40c000b4, 0x41200000, 0x41200112,
|
||||
0x41600000, 0x41600110, 0x41c00000, 0x41d00000,
|
||||
// Entry 280 - 29F
|
||||
0x41e00000, 0x41f00000, 0x41f00072, 0x42200000,
|
||||
0x42300000, 0x42300164, 0x42900000, 0x42900062,
|
||||
0x4290006f, 0x429000a4, 0x42900115, 0x43100000,
|
||||
0x43100027, 0x431000c2, 0x4310014d, 0x43200000,
|
||||
0x43220000, 0x43220033, 0x432200bd, 0x43220105,
|
||||
0x4322014d, 0x4325a000, 0x4325a033, 0x4325a0bd,
|
||||
0x4325a105, 0x4325a14d, 0x43700000, 0x43a00000,
|
||||
0x43b00000, 0x44400000, 0x44400031, 0x44400072,
|
||||
0x41e00000, 0x41f00000, 0x41f00073, 0x42200000,
|
||||
0x42300000, 0x42300165, 0x42900000, 0x42900063,
|
||||
0x42900070, 0x429000a5, 0x42900116, 0x43100000,
|
||||
0x43100027, 0x431000c3, 0x4310014e, 0x43200000,
|
||||
0x43220000, 0x43220033, 0x432200be, 0x43220106,
|
||||
0x4322014e, 0x4325b000, 0x4325b033, 0x4325b0be,
|
||||
0x4325b106, 0x4325b14e, 0x43700000, 0x43a00000,
|
||||
0x43b00000, 0x44400000, 0x44400031, 0x44400073,
|
||||
// Entry 2A0 - 2BF
|
||||
0x4440010c, 0x44500000, 0x4450004b, 0x445000a4,
|
||||
0x4450012f, 0x44500131, 0x44e00000, 0x45000000,
|
||||
0x45000099, 0x450000b3, 0x450000d0, 0x4500010d,
|
||||
0x46100000, 0x46100099, 0x46400000, 0x464000a4,
|
||||
0x46400131, 0x46700000, 0x46700124, 0x46b00000,
|
||||
0x46b00123, 0x46f00000, 0x46f0006d, 0x46f0006f,
|
||||
0x47100000, 0x47600000, 0x47600127, 0x47a00000,
|
||||
0x48000000, 0x48200000, 0x48200129, 0x48a00000,
|
||||
0x4440010d, 0x44500000, 0x4450004b, 0x445000a5,
|
||||
0x44500130, 0x44500132, 0x44e00000, 0x45000000,
|
||||
0x4500009a, 0x450000b4, 0x450000d1, 0x4500010e,
|
||||
0x46100000, 0x4610009a, 0x46400000, 0x464000a5,
|
||||
0x46400132, 0x46700000, 0x46700125, 0x46b00000,
|
||||
0x46b00124, 0x46f00000, 0x46f0006e, 0x46f00070,
|
||||
0x47100000, 0x47600000, 0x47600128, 0x47a00000,
|
||||
0x48000000, 0x48200000, 0x4820012a, 0x48a00000,
|
||||
// Entry 2C0 - 2DF
|
||||
0x48a0005d, 0x48a0012b, 0x48e00000, 0x49400000,
|
||||
0x49400106, 0x4a400000, 0x4a4000d4, 0x4a900000,
|
||||
0x4a9000ba, 0x4ac00000, 0x4ac00053, 0x4ae00000,
|
||||
0x4ae00130, 0x4b400000, 0x4b400099, 0x4b4000e8,
|
||||
0x48a0005e, 0x48a0012c, 0x48e00000, 0x49400000,
|
||||
0x49400107, 0x4a400000, 0x4a4000d5, 0x4a900000,
|
||||
0x4a9000bb, 0x4ac00000, 0x4ac00053, 0x4ae00000,
|
||||
0x4ae00131, 0x4b400000, 0x4b40009a, 0x4b4000e9,
|
||||
0x4bc00000, 0x4bc05000, 0x4bc05024, 0x4bc20000,
|
||||
0x4bc20137, 0x4bc5a000, 0x4bc5a137, 0x4be00000,
|
||||
0x4be5a000, 0x4be5a0b4, 0x4bef1000, 0x4bef10b4,
|
||||
0x4c000000, 0x4c300000, 0x4c30013e, 0x4c900000,
|
||||
0x4bc20138, 0x4bc5b000, 0x4bc5b138, 0x4be00000,
|
||||
0x4be5b000, 0x4be5b0b5, 0x4bef4000, 0x4bef40b5,
|
||||
0x4c000000, 0x4c300000, 0x4c30013f, 0x4c900000,
|
||||
// Entry 2E0 - 2FF
|
||||
0x4c900001, 0x4cc00000, 0x4cc0012f, 0x4ce00000,
|
||||
0x4cf00000, 0x4cf0004e, 0x4e500000, 0x4e500114,
|
||||
0x4f200000, 0x4fb00000, 0x4fb00131, 0x50900000,
|
||||
0x4c900001, 0x4cc00000, 0x4cc00130, 0x4ce00000,
|
||||
0x4cf00000, 0x4cf0004e, 0x4e500000, 0x4e500115,
|
||||
0x4f200000, 0x4fb00000, 0x4fb00132, 0x50900000,
|
||||
0x50900052, 0x51200000, 0x51200001, 0x51800000,
|
||||
0x5180003b, 0x518000d6, 0x51f00000, 0x51f3b000,
|
||||
0x51f3b053, 0x51f3c000, 0x51f3c08d, 0x52800000,
|
||||
0x528000ba, 0x52900000, 0x5293b000, 0x5293b053,
|
||||
0x5293b08d, 0x5293b0c6, 0x5293b10d, 0x5293c000,
|
||||
0x5180003b, 0x518000d7, 0x51f00000, 0x51f3b000,
|
||||
0x51f3b053, 0x51f3c000, 0x51f3c08e, 0x52800000,
|
||||
0x528000bb, 0x52900000, 0x5293b000, 0x5293b053,
|
||||
0x5293b08e, 0x5293b0c7, 0x5293b10e, 0x5293c000,
|
||||
// Entry 300 - 31F
|
||||
0x5293c08d, 0x5293c0c6, 0x5293c12e, 0x52f00000,
|
||||
0x52f00161,
|
||||
0x5293c08e, 0x5293c0c7, 0x5293c12f, 0x52f00000,
|
||||
0x52f00162,
|
||||
} // Size: 3116 bytes
|
||||
|
||||
const specialTagsStr string = "ca-ES-valencia en-US-u-va-posix"
|
||||
|
||||
// Total table size 3147 bytes (3KiB); checksum: 6772C83C
|
||||
// Total table size 3147 bytes (3KiB); checksum: 5A8FFFA5
|
||||
|
|
File diff suppressed because it is too large
Load Diff
|
@ -0,0 +1,67 @@
|
|||
// 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 internal
|
||||
|
||||
// This file contains matchers that implement CLDR inheritance.
|
||||
//
|
||||
// See https://unicode.org/reports/tr35/#Locale_Inheritance.
|
||||
//
|
||||
// Some of the inheritance described in this document is already handled by
|
||||
// the cldr package.
|
||||
|
||||
import (
|
||||
"golang.org/x/text/language"
|
||||
)
|
||||
|
||||
// TODO: consider if (some of the) matching algorithm needs to be public after
|
||||
// getting some feel about what is generic and what is specific.
|
||||
|
||||
// NewInheritanceMatcher returns a matcher that matches based on the inheritance
|
||||
// chain.
|
||||
//
|
||||
// The matcher uses canonicalization and the parent relationship to find a
|
||||
// match. The resulting match will always be either Und or a language with the
|
||||
// same language and script as the requested language. It will not match
|
||||
// languages for which there is understood to be mutual or one-directional
|
||||
// intelligibility.
|
||||
//
|
||||
// A Match will indicate an Exact match if the language matches after
|
||||
// canonicalization and High if the matched tag is a parent.
|
||||
func NewInheritanceMatcher(t []language.Tag) *InheritanceMatcher {
|
||||
tags := &InheritanceMatcher{make(map[language.Tag]int)}
|
||||
for i, tag := range t {
|
||||
ct, err := language.All.Canonicalize(tag)
|
||||
if err != nil {
|
||||
ct = tag
|
||||
}
|
||||
tags.index[ct] = i
|
||||
}
|
||||
return tags
|
||||
}
|
||||
|
||||
type InheritanceMatcher struct {
|
||||
index map[language.Tag]int
|
||||
}
|
||||
|
||||
func (m InheritanceMatcher) Match(want ...language.Tag) (language.Tag, int, language.Confidence) {
|
||||
for _, t := range want {
|
||||
ct, err := language.All.Canonicalize(t)
|
||||
if err != nil {
|
||||
ct = t
|
||||
}
|
||||
conf := language.Exact
|
||||
for {
|
||||
if index, ok := m.index[ct]; ok {
|
||||
return ct, index, conf
|
||||
}
|
||||
if ct == language.Und {
|
||||
break
|
||||
}
|
||||
ct = ct.Parent()
|
||||
conf = language.High
|
||||
}
|
||||
}
|
||||
return language.Und, 0, language.No
|
||||
}
|
|
@ -23,31 +23,31 @@ const (
|
|||
_419 = 31
|
||||
_BR = 65
|
||||
_CA = 73
|
||||
_ES = 110
|
||||
_GB = 123
|
||||
_MD = 188
|
||||
_PT = 238
|
||||
_UK = 306
|
||||
_US = 309
|
||||
_ZZ = 357
|
||||
_XA = 323
|
||||
_XC = 325
|
||||
_XK = 333
|
||||
_ES = 111
|
||||
_GB = 124
|
||||
_MD = 189
|
||||
_PT = 239
|
||||
_UK = 307
|
||||
_US = 310
|
||||
_ZZ = 358
|
||||
_XA = 324
|
||||
_XC = 326
|
||||
_XK = 334
|
||||
)
|
||||
const (
|
||||
_Latn = 90
|
||||
_Latn = 91
|
||||
_Hani = 57
|
||||
_Hans = 59
|
||||
_Hant = 60
|
||||
_Qaaa = 147
|
||||
_Qaai = 155
|
||||
_Qabx = 196
|
||||
_Zinh = 252
|
||||
_Zyyy = 257
|
||||
_Zzzz = 258
|
||||
_Qaaa = 149
|
||||
_Qaai = 157
|
||||
_Qabx = 198
|
||||
_Zinh = 255
|
||||
_Zyyy = 260
|
||||
_Zzzz = 261
|
||||
)
|
||||
|
||||
var regionToGroups = []uint8{ // 358 elements
|
||||
var regionToGroups = []uint8{ // 359 elements
|
||||
// Entry 0 - 3F
|
||||
0x00, 0x00, 0x00, 0x04, 0x04, 0x00, 0x00, 0x04,
|
||||
0x00, 0x00, 0x00, 0x00, 0x04, 0x04, 0x04, 0x00,
|
||||
|
@ -60,51 +60,51 @@ var regionToGroups = []uint8{ // 358 elements
|
|||
// Entry 40 - 7F
|
||||
0x04, 0x04, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x04, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x04, 0x00, 0x00, 0x04, 0x00, 0x04, 0x00,
|
||||
0x00, 0x04, 0x00, 0x04, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x04, 0x04, 0x00, 0x08,
|
||||
0x00, 0x04, 0x00, 0x00, 0x08, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x04, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x04, 0x00, 0x04, 0x00,
|
||||
// Entry 80 - BF
|
||||
0x00, 0x00, 0x04, 0x00, 0x00, 0x04, 0x00, 0x00,
|
||||
0x00, 0x04, 0x01, 0x00, 0x04, 0x02, 0x00, 0x04,
|
||||
0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x04, 0x00, 0x00, 0x00, 0x04, 0x00, 0x00,
|
||||
0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x08, 0x08, 0x00, 0x00, 0x00, 0x04, 0x00,
|
||||
// Entry C0 - FF
|
||||
0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x01,
|
||||
0x04, 0x08, 0x04, 0x00, 0x00, 0x00, 0x00, 0x04,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x04, 0x00, 0x00, 0x04, 0x00, 0x00, 0x04,
|
||||
0x00, 0x00, 0x04, 0x00, 0x04, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x04, 0x00, 0x05, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x04, 0x04, 0x00,
|
||||
0x08, 0x00, 0x04, 0x00, 0x00, 0x08, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x04, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x04, 0x00, 0x04,
|
||||
// Entry 80 - BF
|
||||
0x00, 0x00, 0x00, 0x04, 0x00, 0x00, 0x04, 0x00,
|
||||
0x00, 0x00, 0x04, 0x01, 0x00, 0x04, 0x02, 0x00,
|
||||
0x04, 0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x04, 0x00, 0x00, 0x00, 0x04, 0x00,
|
||||
0x00, 0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x08, 0x08, 0x00, 0x00, 0x00, 0x04,
|
||||
// Entry C0 - FF
|
||||
0x00, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02,
|
||||
0x01, 0x04, 0x08, 0x04, 0x00, 0x00, 0x00, 0x00,
|
||||
0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x04, 0x00, 0x04, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x04, 0x00, 0x05, 0x00, 0x00,
|
||||
0x00, 0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
// Entry 100 - 13F
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x04, 0x00,
|
||||
0x00, 0x00, 0x04, 0x04, 0x00, 0x00, 0x00, 0x04,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x08, 0x00, 0x00, 0x00, 0x04, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x01, 0x00, 0x05, 0x04, 0x00,
|
||||
0x00, 0x04, 0x00, 0x04, 0x04, 0x05, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x04,
|
||||
0x00, 0x00, 0x00, 0x04, 0x04, 0x00, 0x00, 0x00,
|
||||
0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x08, 0x00, 0x00, 0x00, 0x04, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x05, 0x04,
|
||||
0x00, 0x00, 0x04, 0x00, 0x04, 0x04, 0x05, 0x00,
|
||||
// Entry 140 - 17F
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
} // Size: 382 bytes
|
||||
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
|
||||
} // Size: 383 bytes
|
||||
|
||||
var paradigmLocales = [][3]uint16{ // 3 elements
|
||||
0: [3]uint16{0x139, 0x0, 0x7b},
|
||||
0: [3]uint16{0x139, 0x0, 0x7c},
|
||||
1: [3]uint16{0x13e, 0x0, 0x1f},
|
||||
2: [3]uint16{0x3c0, 0x41, 0xee},
|
||||
2: [3]uint16{0x3c0, 0x41, 0xef},
|
||||
} // Size: 42 bytes
|
||||
|
||||
type mutualIntelligibility struct {
|
||||
|
@ -249,30 +249,30 @@ var matchLang = []mutualIntelligibility{ // 113 elements
|
|||
// matchScript holds pairs of scriptIDs where readers of one script
|
||||
// can typically also read the other. Each is associated with a confidence.
|
||||
var matchScript = []scriptIntelligibility{ // 26 elements
|
||||
0: {wantLang: 0x432, haveLang: 0x432, wantScript: 0x5a, haveScript: 0x20, distance: 0x5},
|
||||
1: {wantLang: 0x432, haveLang: 0x432, wantScript: 0x20, haveScript: 0x5a, distance: 0x5},
|
||||
2: {wantLang: 0x58, haveLang: 0x3e2, wantScript: 0x5a, haveScript: 0x20, distance: 0xa},
|
||||
3: {wantLang: 0xa5, haveLang: 0x139, wantScript: 0xe, haveScript: 0x5a, distance: 0xa},
|
||||
0: {wantLang: 0x432, haveLang: 0x432, wantScript: 0x5b, haveScript: 0x20, distance: 0x5},
|
||||
1: {wantLang: 0x432, haveLang: 0x432, wantScript: 0x20, haveScript: 0x5b, distance: 0x5},
|
||||
2: {wantLang: 0x58, haveLang: 0x3e2, wantScript: 0x5b, haveScript: 0x20, distance: 0xa},
|
||||
3: {wantLang: 0xa5, haveLang: 0x139, wantScript: 0xe, haveScript: 0x5b, distance: 0xa},
|
||||
4: {wantLang: 0x1d7, haveLang: 0x3e2, wantScript: 0x8, haveScript: 0x20, distance: 0xa},
|
||||
5: {wantLang: 0x210, haveLang: 0x139, wantScript: 0x2e, haveScript: 0x5a, distance: 0xa},
|
||||
6: {wantLang: 0x24a, haveLang: 0x139, wantScript: 0x4e, haveScript: 0x5a, distance: 0xa},
|
||||
7: {wantLang: 0x251, haveLang: 0x139, wantScript: 0x52, haveScript: 0x5a, distance: 0xa},
|
||||
8: {wantLang: 0x2b8, haveLang: 0x139, wantScript: 0x57, haveScript: 0x5a, distance: 0xa},
|
||||
9: {wantLang: 0x304, haveLang: 0x139, wantScript: 0x6e, haveScript: 0x5a, distance: 0xa},
|
||||
10: {wantLang: 0x331, haveLang: 0x139, wantScript: 0x75, haveScript: 0x5a, distance: 0xa},
|
||||
11: {wantLang: 0x351, haveLang: 0x139, wantScript: 0x22, haveScript: 0x5a, distance: 0xa},
|
||||
12: {wantLang: 0x395, haveLang: 0x139, wantScript: 0x81, haveScript: 0x5a, distance: 0xa},
|
||||
13: {wantLang: 0x39d, haveLang: 0x139, wantScript: 0x36, haveScript: 0x5a, distance: 0xa},
|
||||
14: {wantLang: 0x3be, haveLang: 0x139, wantScript: 0x5, haveScript: 0x5a, distance: 0xa},
|
||||
15: {wantLang: 0x3fa, haveLang: 0x139, wantScript: 0x5, haveScript: 0x5a, distance: 0xa},
|
||||
16: {wantLang: 0x40c, haveLang: 0x139, wantScript: 0xd4, haveScript: 0x5a, distance: 0xa},
|
||||
17: {wantLang: 0x450, haveLang: 0x139, wantScript: 0xe3, haveScript: 0x5a, distance: 0xa},
|
||||
18: {wantLang: 0x461, haveLang: 0x139, wantScript: 0xe6, haveScript: 0x5a, distance: 0xa},
|
||||
19: {wantLang: 0x46f, haveLang: 0x139, wantScript: 0x2c, haveScript: 0x5a, distance: 0xa},
|
||||
20: {wantLang: 0x476, haveLang: 0x3e2, wantScript: 0x5a, haveScript: 0x20, distance: 0xa},
|
||||
21: {wantLang: 0x4b4, haveLang: 0x139, wantScript: 0x5, haveScript: 0x5a, distance: 0xa},
|
||||
22: {wantLang: 0x4bc, haveLang: 0x3e2, wantScript: 0x5a, haveScript: 0x20, distance: 0xa},
|
||||
23: {wantLang: 0x512, haveLang: 0x139, wantScript: 0x3e, haveScript: 0x5a, distance: 0xa},
|
||||
5: {wantLang: 0x210, haveLang: 0x139, wantScript: 0x2e, haveScript: 0x5b, distance: 0xa},
|
||||
6: {wantLang: 0x24a, haveLang: 0x139, wantScript: 0x4f, haveScript: 0x5b, distance: 0xa},
|
||||
7: {wantLang: 0x251, haveLang: 0x139, wantScript: 0x53, haveScript: 0x5b, distance: 0xa},
|
||||
8: {wantLang: 0x2b8, haveLang: 0x139, wantScript: 0x58, haveScript: 0x5b, distance: 0xa},
|
||||
9: {wantLang: 0x304, haveLang: 0x139, wantScript: 0x6f, haveScript: 0x5b, distance: 0xa},
|
||||
10: {wantLang: 0x331, haveLang: 0x139, wantScript: 0x76, haveScript: 0x5b, distance: 0xa},
|
||||
11: {wantLang: 0x351, haveLang: 0x139, wantScript: 0x22, haveScript: 0x5b, distance: 0xa},
|
||||
12: {wantLang: 0x395, haveLang: 0x139, wantScript: 0x83, haveScript: 0x5b, distance: 0xa},
|
||||
13: {wantLang: 0x39d, haveLang: 0x139, wantScript: 0x36, haveScript: 0x5b, distance: 0xa},
|
||||
14: {wantLang: 0x3be, haveLang: 0x139, wantScript: 0x5, haveScript: 0x5b, distance: 0xa},
|
||||
15: {wantLang: 0x3fa, haveLang: 0x139, wantScript: 0x5, haveScript: 0x5b, distance: 0xa},
|
||||
16: {wantLang: 0x40c, haveLang: 0x139, wantScript: 0xd6, haveScript: 0x5b, distance: 0xa},
|
||||
17: {wantLang: 0x450, haveLang: 0x139, wantScript: 0xe6, haveScript: 0x5b, distance: 0xa},
|
||||
18: {wantLang: 0x461, haveLang: 0x139, wantScript: 0xe9, haveScript: 0x5b, distance: 0xa},
|
||||
19: {wantLang: 0x46f, haveLang: 0x139, wantScript: 0x2c, haveScript: 0x5b, distance: 0xa},
|
||||
20: {wantLang: 0x476, haveLang: 0x3e2, wantScript: 0x5b, haveScript: 0x20, distance: 0xa},
|
||||
21: {wantLang: 0x4b4, haveLang: 0x139, wantScript: 0x5, haveScript: 0x5b, distance: 0xa},
|
||||
22: {wantLang: 0x4bc, haveLang: 0x3e2, wantScript: 0x5b, haveScript: 0x20, distance: 0xa},
|
||||
23: {wantLang: 0x512, haveLang: 0x139, wantScript: 0x3e, haveScript: 0x5b, distance: 0xa},
|
||||
24: {wantLang: 0x529, haveLang: 0x529, wantScript: 0x3b, haveScript: 0x3c, distance: 0xf},
|
||||
25: {wantLang: 0x529, haveLang: 0x529, wantScript: 0x3c, haveScript: 0x3b, distance: 0x13},
|
||||
} // Size: 232 bytes
|
||||
|
@ -295,4 +295,4 @@ var matchRegion = []regionIntelligibility{ // 15 elements
|
|||
14: {lang: 0x529, script: 0x3c, group: 0x80, distance: 0x5},
|
||||
} // Size: 114 bytes
|
||||
|
||||
// Total table size 1472 bytes (1KiB); checksum: F86C669
|
||||
// Total table size 1473 bytes (1KiB); checksum: 7BB90B5C
|
||||
|
|
|
@ -1,7 +1,7 @@
|
|||
// Code generated by running "go generate" in golang.org/x/text. DO NOT EDIT.
|
||||
|
||||
//go:build go1.16
|
||||
// +build go1.16
|
||||
//go:build go1.16 && !go1.21
|
||||
// +build go1.16,!go1.21
|
||||
|
||||
package bidi
|
||||
|
||||
|
|
File diff suppressed because it is too large
Load Diff
|
@ -1,7 +1,7 @@
|
|||
// Code generated by running "go generate" in golang.org/x/text. DO NOT EDIT.
|
||||
|
||||
//go:build go1.16
|
||||
// +build go1.16
|
||||
//go:build go1.16 && !go1.21
|
||||
// +build go1.16,!go1.21
|
||||
|
||||
package norm
|
||||
|
||||
|
|
File diff suppressed because it is too large
Load Diff
|
@ -1215,8 +1215,9 @@ golang.org/x/sys/windows
|
|||
# golang.org/x/term v0.8.0
|
||||
## explicit; go 1.17
|
||||
golang.org/x/term
|
||||
# golang.org/x/text v0.9.0
|
||||
# golang.org/x/text v0.11.0
|
||||
## explicit; go 1.17
|
||||
golang.org/x/text/cases
|
||||
golang.org/x/text/encoding
|
||||
golang.org/x/text/encoding/charmap
|
||||
golang.org/x/text/encoding/htmlindex
|
||||
|
@ -1227,6 +1228,7 @@ golang.org/x/text/encoding/korean
|
|||
golang.org/x/text/encoding/simplifiedchinese
|
||||
golang.org/x/text/encoding/traditionalchinese
|
||||
golang.org/x/text/encoding/unicode
|
||||
golang.org/x/text/internal
|
||||
golang.org/x/text/internal/language
|
||||
golang.org/x/text/internal/language/compact
|
||||
golang.org/x/text/internal/tag
|
||||
|
|
Loading…
Reference in New Issue