mirror of https://github.com/k3s-io/k3s
bump(golang.org/x/text): 2910a502d2bf9e43193af9d68ca516529614eed3
Brendan Burns
parent
7e1cacaa91
commit
7201562cc3
|
|
@ -2448,10 +2448,30 @@
|
|||
"ImportPath": "golang.org/x/text/cases",
|
||||
"Rev": "2910a502d2bf9e43193af9d68ca516529614eed3"
|
||||
},
|
||||
{
|
||||
"ImportPath": "golang.org/x/text/encoding",
|
||||
"Rev": "2910a502d2bf9e43193af9d68ca516529614eed3"
|
||||
},
|
||||
{
|
||||
"ImportPath": "golang.org/x/text/encoding/internal",
|
||||
"Rev": "2910a502d2bf9e43193af9d68ca516529614eed3"
|
||||
},
|
||||
{
|
||||
"ImportPath": "golang.org/x/text/encoding/internal/identifier",
|
||||
"Rev": "2910a502d2bf9e43193af9d68ca516529614eed3"
|
||||
},
|
||||
{
|
||||
"ImportPath": "golang.org/x/text/encoding/unicode",
|
||||
"Rev": "2910a502d2bf9e43193af9d68ca516529614eed3"
|
||||
},
|
||||
{
|
||||
"ImportPath": "golang.org/x/text/internal/tag",
|
||||
"Rev": "2910a502d2bf9e43193af9d68ca516529614eed3"
|
||||
},
|
||||
{
|
||||
"ImportPath": "golang.org/x/text/internal/utf8internal",
|
||||
"Rev": "2910a502d2bf9e43193af9d68ca516529614eed3"
|
||||
},
|
||||
{
|
||||
"ImportPath": "golang.org/x/text/language",
|
||||
"Rev": "2910a502d2bf9e43193af9d68ca516529614eed3"
|
||||
|
|
|
|||
|
|
@ -0,0 +1,335 @@
|
|||
// Copyright 2013 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// Package encoding defines an interface for character encodings, such as Shift
|
||||
// JIS and Windows 1252, that can convert to and from UTF-8.
|
||||
//
|
||||
// Encoding implementations are provided in other packages, such as
|
||||
// golang.org/x/text/encoding/charmap and
|
||||
// golang.org/x/text/encoding/japanese.
|
||||
package encoding
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"io"
|
||||
"strconv"
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/text/encoding/internal/identifier"
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// TODO:
|
||||
// - There seems to be some inconsistency in when decoders return errors
|
||||
// and when not. Also documentation seems to suggest they shouldn't return
|
||||
// errors at all (except for UTF-16).
|
||||
// - Encoders seem to rely on or at least benefit from the input being in NFC
|
||||
// normal form. Perhaps add an example how users could prepare their output.
|
||||
|
||||
// Encoding is a character set encoding that can be transformed to and from
|
||||
// UTF-8.
|
||||
type Encoding interface {
|
||||
// NewDecoder returns a Decoder.
|
||||
NewDecoder() *Decoder
|
||||
|
||||
// NewEncoder returns an Encoder.
|
||||
NewEncoder() *Encoder
|
||||
}
|
||||
|
||||
// A Decoder converts bytes to UTF-8. It implements transform.Transformer.
|
||||
//
|
||||
// Transforming source bytes that are not of that encoding will not result in an
|
||||
// error per se. Each byte that cannot be transcoded will be represented in the
|
||||
// output by the UTF-8 encoding of '\uFFFD', the replacement rune.
|
||||
type Decoder struct {
|
||||
transform.Transformer
|
||||
|
||||
// This forces external creators of Decoders to use names in struct
|
||||
// initializers, allowing for future extendibility without having to break
|
||||
// code.
|
||||
_ struct{}
|
||||
}
|
||||
|
||||
// Bytes converts the given encoded bytes to UTF-8. It returns the converted
|
||||
// bytes or 0, err if any error occurred.
|
||||
func (d *Decoder) Bytes(b []byte) ([]byte, error) {
|
||||
b, _, err := transform.Bytes(d, b)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return b, nil
|
||||
}
|
||||
|
||||
// String converts the given encoded string to UTF-8. It returns the converted
|
||||
// string or 0, err if any error occurred.
|
||||
func (d *Decoder) String(s string) (string, error) {
|
||||
s, _, err := transform.String(d, s)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
return s, nil
|
||||
}
|
||||
|
||||
// Reader wraps another Reader to decode its bytes.
|
||||
//
|
||||
// The Decoder may not be used for any other operation as long as the returned
|
||||
// Reader is in use.
|
||||
func (d *Decoder) Reader(r io.Reader) io.Reader {
|
||||
return transform.NewReader(r, d)
|
||||
}
|
||||
|
||||
// An Encoder converts bytes from UTF-8. It implements transform.Transformer.
|
||||
//
|
||||
// Each rune that cannot be transcoded will result in an error. In this case,
|
||||
// the transform will consume all source byte up to, not including the offending
|
||||
// rune. Transforming source bytes that are not valid UTF-8 will be replaced by
|
||||
// `\uFFFD`. To return early with an error instead, use transform.Chain to
|
||||
// preprocess the data with a UTF8Validator.
|
||||
type Encoder struct {
|
||||
transform.Transformer
|
||||
|
||||
// This forces external creators of Encoders to use names in struct
|
||||
// initializers, allowing for future extendibility without having to break
|
||||
// code.
|
||||
_ struct{}
|
||||
}
|
||||
|
||||
// Bytes converts bytes from UTF-8. It returns the converted bytes or 0, err if
|
||||
// any error occurred.
|
||||
func (e *Encoder) Bytes(b []byte) ([]byte, error) {
|
||||
b, _, err := transform.Bytes(e, b)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return b, nil
|
||||
}
|
||||
|
||||
// String converts a string from UTF-8. It returns the converted string or
|
||||
// 0, err if any error occurred.
|
||||
func (e *Encoder) String(s string) (string, error) {
|
||||
s, _, err := transform.String(e, s)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
return s, nil
|
||||
}
|
||||
|
||||
// Writer wraps another Writer to encode its UTF-8 output.
|
||||
//
|
||||
// The Encoder may not be used for any other operation as long as the returned
|
||||
// Writer is in use.
|
||||
func (e *Encoder) Writer(w io.Writer) io.Writer {
|
||||
return transform.NewWriter(w, e)
|
||||
}
|
||||
|
||||
// ASCIISub is the ASCII substitute character, as recommended by
|
||||
// http://unicode.org/reports/tr36/#Text_Comparison
|
||||
const ASCIISub = '\x1a'
|
||||
|
||||
// Nop is the nop encoding. Its transformed bytes are the same as the source
|
||||
// bytes; it does not replace invalid UTF-8 sequences.
|
||||
var Nop Encoding = nop{}
|
||||
|
||||
type nop struct{}
|
||||
|
||||
func (nop) NewDecoder() *Decoder {
|
||||
return &Decoder{Transformer: transform.Nop}
|
||||
}
|
||||
func (nop) NewEncoder() *Encoder {
|
||||
return &Encoder{Transformer: transform.Nop}
|
||||
}
|
||||
|
||||
// Replacement is the replacement encoding. Decoding from the replacement
|
||||
// encoding yields a single '\uFFFD' replacement rune. Encoding from UTF-8 to
|
||||
// the replacement encoding yields the same as the source bytes except that
|
||||
// invalid UTF-8 is converted to '\uFFFD'.
|
||||
//
|
||||
// It is defined at http://encoding.spec.whatwg.org/#replacement
|
||||
var Replacement Encoding = replacement{}
|
||||
|
||||
type replacement struct{}
|
||||
|
||||
func (replacement) NewDecoder() *Decoder {
|
||||
return &Decoder{Transformer: replacementDecoder{}}
|
||||
}
|
||||
|
||||
func (replacement) NewEncoder() *Encoder {
|
||||
return &Encoder{Transformer: replacementEncoder{}}
|
||||
}
|
||||
|
||||
func (replacement) ID() (mib identifier.MIB, other string) {
|
||||
return identifier.Replacement, ""
|
||||
}
|
||||
|
||||
type replacementDecoder struct{ transform.NopResetter }
|
||||
|
||||
func (replacementDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
if len(dst) < 3 {
|
||||
return 0, 0, transform.ErrShortDst
|
||||
}
|
||||
if atEOF {
|
||||
const fffd = "\ufffd"
|
||||
dst[0] = fffd[0]
|
||||
dst[1] = fffd[1]
|
||||
dst[2] = fffd[2]
|
||||
nDst = 3
|
||||
}
|
||||
return nDst, len(src), nil
|
||||
}
|
||||
|
||||
type replacementEncoder struct{ transform.NopResetter }
|
||||
|
||||
func (replacementEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
r, size := rune(0), 0
|
||||
|
||||
for ; nSrc < len(src); nSrc += size {
|
||||
r = rune(src[nSrc])
|
||||
|
||||
// Decode a 1-byte rune.
|
||||
if r < utf8.RuneSelf {
|
||||
size = 1
|
||||
|
||||
} else {
|
||||
// Decode a multi-byte rune.
|
||||
r, size = utf8.DecodeRune(src[nSrc:])
|
||||
if size == 1 {
|
||||
// All valid runes of size 1 (those below utf8.RuneSelf) were
|
||||
// handled above. We have invalid UTF-8 or we haven't seen the
|
||||
// full character yet.
|
||||
if !atEOF && !utf8.FullRune(src[nSrc:]) {
|
||||
err = transform.ErrShortSrc
|
||||
break
|
||||
}
|
||||
r = '\ufffd'
|
||||
}
|
||||
}
|
||||
|
||||
if nDst+utf8.RuneLen(r) > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
nDst += utf8.EncodeRune(dst[nDst:], r)
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
// HTMLEscapeUnsupported wraps encoders to replace source runes outside the
|
||||
// repertoire of the destination encoding with HTML escape sequences.
|
||||
//
|
||||
// This wrapper exists to comply to URL and HTML forms requiring a
|
||||
// non-terminating legacy encoder. The produced sequences may lead to data
|
||||
// loss as they are indistinguishable from legitimate input. To avoid this
|
||||
// issue, use UTF-8 encodings whenever possible.
|
||||
func HTMLEscapeUnsupported(e *Encoder) *Encoder {
|
||||
return &Encoder{Transformer: &errorHandler{e, errorToHTML}}
|
||||
}
|
||||
|
||||
// ReplaceUnsupported wraps encoders to replace source runes outside the
|
||||
// repertoire of the destination encoding with an encoding-specific
|
||||
// replacement.
|
||||
//
|
||||
// This wrapper is only provided for backwards compatibility and legacy
|
||||
// handling. Its use is strongly discouraged. Use UTF-8 whenever possible.
|
||||
func ReplaceUnsupported(e *Encoder) *Encoder {
|
||||
return &Encoder{Transformer: &errorHandler{e, errorToReplacement}}
|
||||
}
|
||||
|
||||
type errorHandler struct {
|
||||
*Encoder
|
||||
handler func(dst []byte, r rune, err repertoireError) (n int, ok bool)
|
||||
}
|
||||
|
||||
// TODO: consider making this error public in some form.
|
||||
type repertoireError interface {
|
||||
Replacement() byte
|
||||
}
|
||||
|
||||
func (h errorHandler) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
nDst, nSrc, err = h.Transformer.Transform(dst, src, atEOF)
|
||||
for err != nil {
|
||||
rerr, ok := err.(repertoireError)
|
||||
if !ok {
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
r, sz := utf8.DecodeRune(src[nSrc:])
|
||||
n, ok := h.handler(dst[nDst:], r, rerr)
|
||||
if !ok {
|
||||
return nDst, nSrc, transform.ErrShortDst
|
||||
}
|
||||
err = nil
|
||||
nDst += n
|
||||
if nSrc += sz; nSrc < len(src) {
|
||||
var dn, sn int
|
||||
dn, sn, err = h.Transformer.Transform(dst[nDst:], src[nSrc:], atEOF)
|
||||
nDst += dn
|
||||
nSrc += sn
|
||||
}
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
func errorToHTML(dst []byte, r rune, err repertoireError) (n int, ok bool) {
|
||||
buf := [8]byte{}
|
||||
b := strconv.AppendUint(buf[:0], uint64(r), 10)
|
||||
if n = len(b) + len("&#;"); n >= len(dst) {
|
||||
return 0, false
|
||||
}
|
||||
dst[0] = '&'
|
||||
dst[1] = '#'
|
||||
dst[copy(dst[2:], b)+2] = ';'
|
||||
return n, true
|
||||
}
|
||||
|
||||
func errorToReplacement(dst []byte, r rune, err repertoireError) (n int, ok bool) {
|
||||
if len(dst) == 0 {
|
||||
return 0, false
|
||||
}
|
||||
dst[0] = err.Replacement()
|
||||
return 1, true
|
||||
}
|
||||
|
||||
// ErrInvalidUTF8 means that a transformer encountered invalid UTF-8.
|
||||
var ErrInvalidUTF8 = errors.New("encoding: invalid UTF-8")
|
||||
|
||||
// UTF8Validator is a transformer that returns ErrInvalidUTF8 on the first
|
||||
// input byte that is not valid UTF-8.
|
||||
var UTF8Validator transform.Transformer = utf8Validator{}
|
||||
|
||||
type utf8Validator struct{ transform.NopResetter }
|
||||
|
||||
func (utf8Validator) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
n := len(src)
|
||||
if n > len(dst) {
|
||||
n = len(dst)
|
||||
}
|
||||
for i := 0; i < n; {
|
||||
if c := src[i]; c < utf8.RuneSelf {
|
||||
dst[i] = c
|
||||
i++
|
||||
continue
|
||||
}
|
||||
_, size := utf8.DecodeRune(src[i:])
|
||||
if size == 1 {
|
||||
// All valid runes of size 1 (those below utf8.RuneSelf) were
|
||||
// handled above. We have invalid UTF-8 or we haven't seen the
|
||||
// full character yet.
|
||||
err = ErrInvalidUTF8
|
||||
if !atEOF && !utf8.FullRune(src[i:]) {
|
||||
err = transform.ErrShortSrc
|
||||
}
|
||||
return i, i, err
|
||||
}
|
||||
if i+size > len(dst) {
|
||||
return i, i, transform.ErrShortDst
|
||||
}
|
||||
for ; size > 0; size-- {
|
||||
dst[i] = src[i]
|
||||
i++
|
||||
}
|
||||
}
|
||||
if len(src) > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
}
|
||||
return n, n, err
|
||||
}
|
||||
|
|
@ -0,0 +1,137 @@
|
|||
// 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.
|
||||
|
||||
// +build ignore
|
||||
|
||||
package main
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/xml"
|
||||
"fmt"
|
||||
"io"
|
||||
"log"
|
||||
"strings"
|
||||
|
||||
"golang.org/x/text/internal/gen"
|
||||
)
|
||||
|
||||
type registry struct {
|
||||
XMLName xml.Name `xml:"registry"`
|
||||
Updated string `xml:"updated"`
|
||||
Registry []struct {
|
||||
ID string `xml:"id,attr"`
|
||||
Record []struct {
|
||||
Name string `xml:"name"`
|
||||
Xref []struct {
|
||||
Type string `xml:"type,attr"`
|
||||
Data string `xml:"data,attr"`
|
||||
} `xml:"xref"`
|
||||
Desc struct {
|
||||
Data string `xml:",innerxml"`
|
||||
// Any []struct {
|
||||
// Data string `xml:",chardata"`
|
||||
// } `xml:",any"`
|
||||
// Data string `xml:",chardata"`
|
||||
} `xml:"description,"`
|
||||
MIB string `xml:"value"`
|
||||
Alias []string `xml:"alias"`
|
||||
MIME string `xml:"preferred_alias"`
|
||||
} `xml:"record"`
|
||||
} `xml:"registry"`
|
||||
}
|
||||
|
||||
func main() {
|
||||
r := gen.OpenIANAFile("assignments/character-sets/character-sets.xml")
|
||||
reg := ®istry{}
|
||||
if err := xml.NewDecoder(r).Decode(®); err != nil && err != io.EOF {
|
||||
log.Fatalf("Error decoding charset registry: %v", err)
|
||||
}
|
||||
if len(reg.Registry) == 0 || reg.Registry[0].ID != "character-sets-1" {
|
||||
log.Fatalf("Unexpected ID %s", reg.Registry[0].ID)
|
||||
}
|
||||
|
||||
w := &bytes.Buffer{}
|
||||
fmt.Fprintf(w, "const (\n")
|
||||
for _, rec := range reg.Registry[0].Record {
|
||||
constName := ""
|
||||
for _, a := range rec.Alias {
|
||||
if strings.HasPrefix(a, "cs") && strings.IndexByte(a, '-') == -1 {
|
||||
// Some of the constant definitions have comments in them. Strip those.
|
||||
constName = strings.Title(strings.SplitN(a[2:], "\n", 2)[0])
|
||||
}
|
||||
}
|
||||
if constName == "" {
|
||||
switch rec.MIB {
|
||||
case "2085":
|
||||
constName = "HZGB2312" // Not listed as alias for some reason.
|
||||
default:
|
||||
log.Fatalf("No cs alias defined for %s.", rec.MIB)
|
||||
}
|
||||
}
|
||||
if rec.MIME != "" {
|
||||
rec.MIME = fmt.Sprintf(" (MIME: %s)", rec.MIME)
|
||||
}
|
||||
fmt.Fprintf(w, "// %s is the MIB identifier with IANA name %s%s.\n//\n", constName, rec.Name, rec.MIME)
|
||||
if len(rec.Desc.Data) > 0 {
|
||||
fmt.Fprint(w, "// ")
|
||||
d := xml.NewDecoder(strings.NewReader(rec.Desc.Data))
|
||||
inElem := true
|
||||
attr := ""
|
||||
for {
|
||||
t, err := d.Token()
|
||||
if err != nil {
|
||||
if err != io.EOF {
|
||||
log.Fatal(err)
|
||||
}
|
||||
break
|
||||
}
|
||||
switch x := t.(type) {
|
||||
case xml.CharData:
|
||||
attr = "" // Don't need attribute info.
|
||||
a := bytes.Split([]byte(x), []byte("\n"))
|
||||
for i, b := range a {
|
||||
if b = bytes.TrimSpace(b); len(b) != 0 {
|
||||
if !inElem && i > 0 {
|
||||
fmt.Fprint(w, "\n// ")
|
||||
}
|
||||
inElem = false
|
||||
fmt.Fprintf(w, "%s ", string(b))
|
||||
}
|
||||
}
|
||||
case xml.StartElement:
|
||||
if x.Name.Local == "xref" {
|
||||
inElem = true
|
||||
use := false
|
||||
for _, a := range x.Attr {
|
||||
if a.Name.Local == "type" {
|
||||
use = use || a.Value != "person"
|
||||
}
|
||||
if a.Name.Local == "data" && use {
|
||||
attr = a.Value + " "
|
||||
}
|
||||
}
|
||||
}
|
||||
case xml.EndElement:
|
||||
inElem = false
|
||||
fmt.Fprint(w, attr)
|
||||
}
|
||||
}
|
||||
fmt.Fprint(w, "\n")
|
||||
}
|
||||
for _, x := range rec.Xref {
|
||||
switch x.Type {
|
||||
case "rfc":
|
||||
fmt.Fprintf(w, "// Reference: %s\n", strings.ToUpper(x.Data))
|
||||
case "uri":
|
||||
fmt.Fprintf(w, "// Reference: %s\n", x.Data)
|
||||
}
|
||||
}
|
||||
fmt.Fprintf(w, "%s MIB = %s\n", constName, rec.MIB)
|
||||
fmt.Fprintln(w)
|
||||
}
|
||||
fmt.Fprintln(w, ")")
|
||||
|
||||
gen.WriteGoFile("mib.go", "identifier", w.Bytes())
|
||||
}
|
||||
81
vendor/golang.org/x/text/encoding/internal/identifier/identifier.go
generated
vendored
Normal file
81
vendor/golang.org/x/text/encoding/internal/identifier/identifier.go
generated
vendored
Normal file
|
|
@ -0,0 +1,81 @@
|
|||
// Copyright 2015 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
//go:generate go run gen.go
|
||||
|
||||
// Package identifier defines the contract between implementations of Encoding
|
||||
// and Index by defining identifiers that uniquely identify standardized coded
|
||||
// character sets (CCS) and character encoding schemes (CES), which we will
|
||||
// together refer to as encodings, for which Encoding implementations provide
|
||||
// converters to and from UTF-8. This package is typically only of concern to
|
||||
// implementers of Indexes and Encodings.
|
||||
//
|
||||
// One part of the identifier is the MIB code, which is defined by IANA and
|
||||
// uniquely identifies a CCS or CES. Each code is associated with data that
|
||||
// references authorities, official documentation as well as aliases and MIME
|
||||
// names.
|
||||
//
|
||||
// Not all CESs are covered by the IANA registry. The "other" string that is
|
||||
// returned by ID can be used to identify other character sets or versions of
|
||||
// existing ones.
|
||||
//
|
||||
// It is recommended that each package that provides a set of Encodings provide
|
||||
// the All and Common variables to reference all supported encodings and
|
||||
// commonly used subset. This allows Index implementations to include all
|
||||
// available encodings without explicitly referencing or knowing about them.
|
||||
package identifier
|
||||
|
||||
// Note: this package is internal, but could be made public if there is a need
|
||||
// for writing third-party Indexes and Encodings.
|
||||
|
||||
// References:
|
||||
// - http://source.icu-project.org/repos/icu/icu/trunk/source/data/mappings/convrtrs.txt
|
||||
// - http://www.iana.org/assignments/character-sets/character-sets.xhtml
|
||||
// - http://www.iana.org/assignments/ianacharset-mib/ianacharset-mib
|
||||
// - http://www.ietf.org/rfc/rfc2978.txt
|
||||
// - http://www.unicode.org/reports/tr22/
|
||||
// - http://www.w3.org/TR/encoding/
|
||||
// - http://www.w3.org/TR/encoding/indexes/encodings.json
|
||||
// - https://encoding.spec.whatwg.org/
|
||||
// - https://tools.ietf.org/html/rfc6657#section-5
|
||||
|
||||
// Interface can be implemented by Encodings to define the CCS or CES for which
|
||||
// it implements conversions.
|
||||
type Interface interface {
|
||||
// ID returns an encoding identifier. Exactly one of the mib and other
|
||||
// values should be non-zero.
|
||||
//
|
||||
// In the usual case it is only necessary to indicate the MIB code. The
|
||||
// other string can be used to specify encodings for which there is no MIB,
|
||||
// such as "x-mac-dingbat".
|
||||
//
|
||||
// The other string may only contain the characters a-z, A-Z, 0-9, - and _.
|
||||
ID() (mib MIB, other string)
|
||||
|
||||
// NOTE: the restrictions on the encoding are to allow extending the syntax
|
||||
// with additional information such as versions, vendors and other variants.
|
||||
}
|
||||
|
||||
// A MIB identifies an encoding. It is derived from the IANA MIB codes and adds
|
||||
// some identifiers for some encodings that are not covered by the IANA
|
||||
// standard.
|
||||
//
|
||||
// See http://www.iana.org/assignments/ianacharset-mib.
|
||||
type MIB uint16
|
||||
|
||||
// These additional MIB types are not defined in IANA. They are added because
|
||||
// they are common and defined within the text repo.
|
||||
const (
|
||||
// Unofficial marks the start of encodings not registered by IANA.
|
||||
Unofficial MIB = 10000 + iota
|
||||
|
||||
// Replacement is the WhatWG replacement encoding.
|
||||
Replacement
|
||||
|
||||
// XUserDefined is the code for x-user-defined.
|
||||
XUserDefined
|
||||
|
||||
// MacintoshCyrillic is the code for x-mac-cyrillic.
|
||||
MacintoshCyrillic
|
||||
)
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,75 @@
|
|||
// 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 code that is shared among encoding implementations.
|
||||
package internal
|
||||
|
||||
import (
|
||||
"golang.org/x/text/encoding"
|
||||
"golang.org/x/text/encoding/internal/identifier"
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// Encoding is an implementation of the Encoding interface that adds the String
|
||||
// and ID methods to an existing encoding.
|
||||
type Encoding struct {
|
||||
encoding.Encoding
|
||||
Name string
|
||||
MIB identifier.MIB
|
||||
}
|
||||
|
||||
// _ verifies that Encoding implements identifier.Interface.
|
||||
var _ identifier.Interface = (*Encoding)(nil)
|
||||
|
||||
func (e *Encoding) String() string {
|
||||
return e.Name
|
||||
}
|
||||
|
||||
func (e *Encoding) ID() (mib identifier.MIB, other string) {
|
||||
return e.MIB, ""
|
||||
}
|
||||
|
||||
// SimpleEncoding is an Encoding that combines two Transformers.
|
||||
type SimpleEncoding struct {
|
||||
Decoder transform.Transformer
|
||||
Encoder transform.Transformer
|
||||
}
|
||||
|
||||
func (e *SimpleEncoding) NewDecoder() *encoding.Decoder {
|
||||
return &encoding.Decoder{Transformer: e.Decoder}
|
||||
}
|
||||
|
||||
func (e *SimpleEncoding) NewEncoder() *encoding.Encoder {
|
||||
return &encoding.Encoder{Transformer: e.Encoder}
|
||||
}
|
||||
|
||||
// FuncEncoding is an Encoding that combines two functions returning a new
|
||||
// Transformer.
|
||||
type FuncEncoding struct {
|
||||
Decoder func() transform.Transformer
|
||||
Encoder func() transform.Transformer
|
||||
}
|
||||
|
||||
func (e FuncEncoding) NewDecoder() *encoding.Decoder {
|
||||
return &encoding.Decoder{Transformer: e.Decoder()}
|
||||
}
|
||||
|
||||
func (e FuncEncoding) NewEncoder() *encoding.Encoder {
|
||||
return &encoding.Encoder{Transformer: e.Encoder()}
|
||||
}
|
||||
|
||||
// A RepertoireError indicates a rune is not in the repertoire of a destination
|
||||
// encoding. It is associated with an encoding-specific suggested replacement
|
||||
// byte.
|
||||
type RepertoireError byte
|
||||
|
||||
// Error implements the error interrface.
|
||||
func (r RepertoireError) Error() string {
|
||||
return "encoding: rune not supported by encoding."
|
||||
}
|
||||
|
||||
// Replacement returns the replacement string associated with this error.
|
||||
func (r RepertoireError) Replacement() byte { return byte(r) }
|
||||
|
||||
var ErrASCIIReplacement = RepertoireError(encoding.ASCIISub)
|
||||
|
|
@ -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 unicode
|
||||
|
||||
import (
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// BOMOverride returns a new decoder transformer that is identical to fallback,
|
||||
// except that the presence of a Byte Order Mark at the start of the input
|
||||
// causes it to switch to the corresponding Unicode decoding. It will only
|
||||
// consider BOMs for UTF-8, UTF-16BE, and UTF-16LE.
|
||||
//
|
||||
// This differs from using ExpectBOM by allowing a BOM to switch to UTF-8, not
|
||||
// just UTF-16 variants, and allowing falling back to any encoding scheme.
|
||||
//
|
||||
// This technique is recommended by the W3C for use in HTML 5: "For
|
||||
// compatibility with deployed content, the byte order mark (also known as BOM)
|
||||
// is considered more authoritative than anything else."
|
||||
// http://www.w3.org/TR/encoding/#specification-hooks
|
||||
//
|
||||
// Using BOMOverride is mostly intended for use cases where the first characters
|
||||
// of a fallback encoding are known to not be a BOM, for example, for valid HTML
|
||||
// and most encodings.
|
||||
func BOMOverride(fallback transform.Transformer) transform.Transformer {
|
||||
// TODO: possibly allow a variadic argument of unicode encodings to allow
|
||||
// specifying details of which fallbacks are supported as well as
|
||||
// specifying the details of the implementations. This would also allow for
|
||||
// support for UTF-32, which should not be supported by default.
|
||||
return &bomOverride{fallback: fallback}
|
||||
}
|
||||
|
||||
type bomOverride struct {
|
||||
fallback transform.Transformer
|
||||
current transform.Transformer
|
||||
}
|
||||
|
||||
func (d *bomOverride) Reset() {
|
||||
d.current = nil
|
||||
d.fallback.Reset()
|
||||
}
|
||||
|
||||
var (
|
||||
// TODO: we could use decode functions here, instead of allocating a new
|
||||
// decoder on every NewDecoder as IgnoreBOM decoders can be stateless.
|
||||
utf16le = UTF16(LittleEndian, IgnoreBOM)
|
||||
utf16be = UTF16(BigEndian, IgnoreBOM)
|
||||
)
|
||||
|
||||
const utf8BOM = "\ufeff"
|
||||
|
||||
func (d *bomOverride) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
if d.current != nil {
|
||||
return d.current.Transform(dst, src, atEOF)
|
||||
}
|
||||
if len(src) < 3 && !atEOF {
|
||||
return 0, 0, transform.ErrShortSrc
|
||||
}
|
||||
d.current = d.fallback
|
||||
bomSize := 0
|
||||
if len(src) >= 2 {
|
||||
if src[0] == 0xFF && src[1] == 0xFE {
|
||||
d.current = utf16le.NewDecoder()
|
||||
bomSize = 2
|
||||
} else if src[0] == 0xFE && src[1] == 0xFF {
|
||||
d.current = utf16be.NewDecoder()
|
||||
bomSize = 2
|
||||
} else if len(src) >= 3 &&
|
||||
src[0] == utf8BOM[0] &&
|
||||
src[1] == utf8BOM[1] &&
|
||||
src[2] == utf8BOM[2] {
|
||||
d.current = transform.Nop
|
||||
bomSize = 3
|
||||
}
|
||||
}
|
||||
if bomSize < len(src) {
|
||||
nDst, nSrc, err = d.current.Transform(dst, src[bomSize:], atEOF)
|
||||
}
|
||||
return nDst, nSrc + bomSize, err
|
||||
}
|
||||
|
|
@ -0,0 +1,434 @@
|
|||
// Copyright 2013 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// Package unicode provides Unicode encodings such as UTF-16.
|
||||
package unicode
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"unicode/utf16"
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/text/encoding"
|
||||
"golang.org/x/text/encoding/internal"
|
||||
"golang.org/x/text/encoding/internal/identifier"
|
||||
"golang.org/x/text/internal/utf8internal"
|
||||
"golang.org/x/text/runes"
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// TODO: I think the Transformers really should return errors on unmatched
|
||||
// surrogate pairs and odd numbers of bytes. This is not required by RFC 2781,
|
||||
// which leaves it open, but is suggested by WhatWG. It will allow for all error
|
||||
// modes as defined by WhatWG: fatal, HTML and Replacement. This would require
|
||||
// the introduction of some kind of error type for conveying the erroneous code
|
||||
// point.
|
||||
|
||||
// UTF8 is the UTF-8 encoding.
|
||||
var UTF8 encoding.Encoding = utf8enc
|
||||
|
||||
var utf8enc = &internal.Encoding{
|
||||
&internal.SimpleEncoding{utf8Decoder{}, runes.ReplaceIllFormed()},
|
||||
"UTF-8",
|
||||
identifier.UTF8,
|
||||
}
|
||||
|
||||
type utf8Decoder struct{ transform.NopResetter }
|
||||
|
||||
func (utf8Decoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
var pSrc int // point from which to start copy in src
|
||||
var accept utf8internal.AcceptRange
|
||||
|
||||
// The decoder can only make the input larger, not smaller.
|
||||
n := len(src)
|
||||
if len(dst) < n {
|
||||
err = transform.ErrShortDst
|
||||
n = len(dst)
|
||||
atEOF = false
|
||||
}
|
||||
for nSrc < n {
|
||||
c := src[nSrc]
|
||||
if c < utf8.RuneSelf {
|
||||
nSrc++
|
||||
continue
|
||||
}
|
||||
first := utf8internal.First[c]
|
||||
size := int(first & utf8internal.SizeMask)
|
||||
if first == utf8internal.FirstInvalid {
|
||||
goto handleInvalid // invalid starter byte
|
||||
}
|
||||
accept = utf8internal.AcceptRanges[first>>utf8internal.AcceptShift]
|
||||
if nSrc+size > n {
|
||||
if !atEOF {
|
||||
// We may stop earlier than necessary here if the short sequence
|
||||
// has invalid bytes. Not checking for this simplifies the code
|
||||
// and may avoid duplicate computations in certain conditions.
|
||||
if err == nil {
|
||||
err = transform.ErrShortSrc
|
||||
}
|
||||
break
|
||||
}
|
||||
// Determine the maximal subpart of an ill-formed subsequence.
|
||||
switch {
|
||||
case nSrc+1 >= n || src[nSrc+1] < accept.Lo || accept.Hi < src[nSrc+1]:
|
||||
size = 1
|
||||
case nSrc+2 >= n || src[nSrc+2] < utf8internal.LoCB || utf8internal.HiCB < src[nSrc+2]:
|
||||
size = 2
|
||||
default:
|
||||
size = 3 // As we are short, the maximum is 3.
|
||||
}
|
||||
goto handleInvalid
|
||||
}
|
||||
if c = src[nSrc+1]; c < accept.Lo || accept.Hi < c {
|
||||
size = 1
|
||||
goto handleInvalid // invalid continuation byte
|
||||
} else if size == 2 {
|
||||
} else if c = src[nSrc+2]; c < utf8internal.LoCB || utf8internal.HiCB < c {
|
||||
size = 2
|
||||
goto handleInvalid // invalid continuation byte
|
||||
} else if size == 3 {
|
||||
} else if c = src[nSrc+3]; c < utf8internal.LoCB || utf8internal.HiCB < c {
|
||||
size = 3
|
||||
goto handleInvalid // invalid continuation byte
|
||||
}
|
||||
nSrc += size
|
||||
continue
|
||||
|
||||
handleInvalid:
|
||||
// Copy the scanned input so far.
|
||||
nDst += copy(dst[nDst:], src[pSrc:nSrc])
|
||||
|
||||
// Append RuneError to the destination.
|
||||
const runeError = "\ufffd"
|
||||
if nDst+len(runeError) > len(dst) {
|
||||
return nDst, nSrc, transform.ErrShortDst
|
||||
}
|
||||
nDst += copy(dst[nDst:], runeError)
|
||||
|
||||
// Skip the maximal subpart of an ill-formed subsequence according to
|
||||
// the W3C standard way instead of the Go way. This Transform is
|
||||
// probably the only place in the text repo where it is warranted.
|
||||
nSrc += size
|
||||
pSrc = nSrc
|
||||
|
||||
// Recompute the maximum source length.
|
||||
if sz := len(dst) - nDst; sz < len(src)-nSrc {
|
||||
err = transform.ErrShortDst
|
||||
n = nSrc + sz
|
||||
atEOF = false
|
||||
}
|
||||
}
|
||||
return nDst + copy(dst[nDst:], src[pSrc:nSrc]), nSrc, err
|
||||
}
|
||||
|
||||
// UTF16 returns a UTF-16 Encoding for the given default endianness and byte
|
||||
// order mark (BOM) policy.
|
||||
//
|
||||
// When decoding from UTF-16 to UTF-8, if the BOMPolicy is IgnoreBOM then
|
||||
// neither BOMs U+FEFF nor noncharacters U+FFFE in the input stream will affect
|
||||
// the endianness used for decoding, and will instead be output as their
|
||||
// standard UTF-8 encodings: "\xef\xbb\xbf" and "\xef\xbf\xbe". If the BOMPolicy
|
||||
// is UseBOM or ExpectBOM a staring BOM is not written to the UTF-8 output.
|
||||
// Instead, it overrides the default endianness e for the remainder of the
|
||||
// transformation. Any subsequent BOMs U+FEFF or noncharacters U+FFFE will not
|
||||
// affect the endianness used, and will instead be output as their standard
|
||||
// UTF-8 encodings. For UseBOM, if there is no starting BOM, it will proceed
|
||||
// with the default Endianness. For ExpectBOM, in that case, the transformation
|
||||
// will return early with an ErrMissingBOM error.
|
||||
//
|
||||
// When encoding from UTF-8 to UTF-16, a BOM will be inserted at the start of
|
||||
// the output if the BOMPolicy is UseBOM or ExpectBOM. Otherwise, a BOM will not
|
||||
// be inserted. The UTF-8 input does not need to contain a BOM.
|
||||
//
|
||||
// There is no concept of a 'native' endianness. If the UTF-16 data is produced
|
||||
// and consumed in a greater context that implies a certain endianness, use
|
||||
// IgnoreBOM. Otherwise, use ExpectBOM and always produce and consume a BOM.
|
||||
//
|
||||
// In the language of http://www.unicode.org/faq/utf_bom.html#bom10, IgnoreBOM
|
||||
// corresponds to "Where the precise type of the data stream is known... the
|
||||
// BOM should not be used" and ExpectBOM corresponds to "A particular
|
||||
// protocol... may require use of the BOM".
|
||||
func UTF16(e Endianness, b BOMPolicy) encoding.Encoding {
|
||||
return utf16Encoding{config{e, b}, mibValue[e][b&bomMask]}
|
||||
}
|
||||
|
||||
// mibValue maps Endianness and BOMPolicy settings to MIB constants. Note that
|
||||
// some configurations map to the same MIB identifier. RFC 2781 has requirements
|
||||
// and recommendations. Some of the "configurations" are merely recommendations,
|
||||
// so multiple configurations could match.
|
||||
var mibValue = map[Endianness][numBOMValues]identifier.MIB{
|
||||
BigEndian: [numBOMValues]identifier.MIB{
|
||||
IgnoreBOM: identifier.UTF16BE,
|
||||
UseBOM: identifier.UTF16, // BigEnding default is preferred by RFC 2781.
|
||||
// TODO: acceptBOM | strictBOM would map to UTF16BE as well.
|
||||
},
|
||||
LittleEndian: [numBOMValues]identifier.MIB{
|
||||
IgnoreBOM: identifier.UTF16LE,
|
||||
UseBOM: identifier.UTF16, // LittleEndian default is allowed and preferred on Windows.
|
||||
// TODO: acceptBOM | strictBOM would map to UTF16LE as well.
|
||||
},
|
||||
// ExpectBOM is not widely used and has no valid MIB identifier.
|
||||
}
|
||||
|
||||
// All lists a configuration for each IANA-defined UTF-16 variant.
|
||||
var All = []encoding.Encoding{
|
||||
UTF8,
|
||||
UTF16(BigEndian, UseBOM),
|
||||
UTF16(BigEndian, IgnoreBOM),
|
||||
UTF16(LittleEndian, IgnoreBOM),
|
||||
}
|
||||
|
||||
// BOMPolicy is a UTF-16 encoding's byte order mark policy.
|
||||
type BOMPolicy uint8
|
||||
|
||||
const (
|
||||
writeBOM BOMPolicy = 0x01
|
||||
acceptBOM BOMPolicy = 0x02
|
||||
requireBOM BOMPolicy = 0x04
|
||||
bomMask BOMPolicy = 0x07
|
||||
|
||||
// HACK: numBOMValues == 8 triggers a bug in the 1.4 compiler (cannot have a
|
||||
// map of an array of length 8 of a type that is also used as a key or value
|
||||
// in another map). See golang.org/issue/11354.
|
||||
// TODO: consider changing this value back to 8 if the use of 1.4.* has
|
||||
// been minimized.
|
||||
numBOMValues = 8 + 1
|
||||
|
||||
// IgnoreBOM means to ignore any byte order marks.
|
||||
IgnoreBOM BOMPolicy = 0
|
||||
// Common and RFC 2781-compliant interpretation for UTF-16BE/LE.
|
||||
|
||||
// UseBOM means that the UTF-16 form may start with a byte order mark, which
|
||||
// will be used to override the default encoding.
|
||||
UseBOM BOMPolicy = writeBOM | acceptBOM
|
||||
// Common and RFC 2781-compliant interpretation for UTF-16.
|
||||
|
||||
// ExpectBOM means that the UTF-16 form must start with a byte order mark,
|
||||
// which will be used to override the default encoding.
|
||||
ExpectBOM BOMPolicy = writeBOM | acceptBOM | requireBOM
|
||||
// Used in Java as Unicode (not to be confused with Java's UTF-16) and
|
||||
// ICU's UTF-16,version=1. Not compliant with RFC 2781.
|
||||
|
||||
// TODO (maybe): strictBOM: BOM must match Endianness. This would allow:
|
||||
// - UTF-16(B|L)E,version=1: writeBOM | acceptBOM | requireBOM | strictBOM
|
||||
// (UnicodeBig and UnicodeLittle in Java)
|
||||
// - RFC 2781-compliant, but less common interpretation for UTF-16(B|L)E:
|
||||
// acceptBOM | strictBOM (e.g. assigned to CheckBOM).
|
||||
// This addition would be consistent with supporting ExpectBOM.
|
||||
)
|
||||
|
||||
// Endianness is a UTF-16 encoding's default endianness.
|
||||
type Endianness bool
|
||||
|
||||
const (
|
||||
// BigEndian is UTF-16BE.
|
||||
BigEndian Endianness = false
|
||||
// LittleEndian is UTF-16LE.
|
||||
LittleEndian Endianness = true
|
||||
)
|
||||
|
||||
// ErrMissingBOM means that decoding UTF-16 input with ExpectBOM did not find a
|
||||
// starting byte order mark.
|
||||
var ErrMissingBOM = errors.New("encoding: missing byte order mark")
|
||||
|
||||
type utf16Encoding struct {
|
||||
config
|
||||
mib identifier.MIB
|
||||
}
|
||||
|
||||
type config struct {
|
||||
endianness Endianness
|
||||
bomPolicy BOMPolicy
|
||||
}
|
||||
|
||||
func (u utf16Encoding) NewDecoder() *encoding.Decoder {
|
||||
return &encoding.Decoder{Transformer: &utf16Decoder{
|
||||
initial: u.config,
|
||||
current: u.config,
|
||||
}}
|
||||
}
|
||||
|
||||
func (u utf16Encoding) NewEncoder() *encoding.Encoder {
|
||||
return &encoding.Encoder{Transformer: &utf16Encoder{
|
||||
endianness: u.endianness,
|
||||
initialBOMPolicy: u.bomPolicy,
|
||||
currentBOMPolicy: u.bomPolicy,
|
||||
}}
|
||||
}
|
||||
|
||||
func (u utf16Encoding) ID() (mib identifier.MIB, other string) {
|
||||
return u.mib, ""
|
||||
}
|
||||
|
||||
func (u utf16Encoding) String() string {
|
||||
e, b := "B", ""
|
||||
if u.endianness == LittleEndian {
|
||||
e = "L"
|
||||
}
|
||||
switch u.bomPolicy {
|
||||
case ExpectBOM:
|
||||
b = "Expect"
|
||||
case UseBOM:
|
||||
b = "Use"
|
||||
case IgnoreBOM:
|
||||
b = "Ignore"
|
||||
}
|
||||
return "UTF-16" + e + "E (" + b + " BOM)"
|
||||
}
|
||||
|
||||
type utf16Decoder struct {
|
||||
initial config
|
||||
current config
|
||||
}
|
||||
|
||||
func (u *utf16Decoder) Reset() {
|
||||
u.current = u.initial
|
||||
}
|
||||
|
||||
func (u *utf16Decoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
if len(src) == 0 {
|
||||
if atEOF && u.current.bomPolicy&requireBOM != 0 {
|
||||
return 0, 0, ErrMissingBOM
|
||||
}
|
||||
return 0, 0, nil
|
||||
}
|
||||
if u.current.bomPolicy&acceptBOM != 0 {
|
||||
if len(src) < 2 {
|
||||
return 0, 0, transform.ErrShortSrc
|
||||
}
|
||||
switch {
|
||||
case src[0] == 0xfe && src[1] == 0xff:
|
||||
u.current.endianness = BigEndian
|
||||
nSrc = 2
|
||||
case src[0] == 0xff && src[1] == 0xfe:
|
||||
u.current.endianness = LittleEndian
|
||||
nSrc = 2
|
||||
default:
|
||||
if u.current.bomPolicy&requireBOM != 0 {
|
||||
return 0, 0, ErrMissingBOM
|
||||
}
|
||||
}
|
||||
u.current.bomPolicy = IgnoreBOM
|
||||
}
|
||||
|
||||
var r rune
|
||||
var dSize, sSize int
|
||||
for nSrc < len(src) {
|
||||
if nSrc+1 < len(src) {
|
||||
x := uint16(src[nSrc+0])<<8 | uint16(src[nSrc+1])
|
||||
if u.current.endianness == LittleEndian {
|
||||
x = x>>8 | x<<8
|
||||
}
|
||||
r, sSize = rune(x), 2
|
||||
if utf16.IsSurrogate(r) {
|
||||
if nSrc+3 < len(src) {
|
||||
x = uint16(src[nSrc+2])<<8 | uint16(src[nSrc+3])
|
||||
if u.current.endianness == LittleEndian {
|
||||
x = x>>8 | x<<8
|
||||
}
|
||||
// Save for next iteration if it is not a high surrogate.
|
||||
if isHighSurrogate(rune(x)) {
|
||||
r, sSize = utf16.DecodeRune(r, rune(x)), 4
|
||||
}
|
||||
} else if !atEOF {
|
||||
err = transform.ErrShortSrc
|
||||
break
|
||||
}
|
||||
}
|
||||
if dSize = utf8.RuneLen(r); dSize < 0 {
|
||||
r, dSize = utf8.RuneError, 3
|
||||
}
|
||||
} else if atEOF {
|
||||
// Single trailing byte.
|
||||
r, dSize, sSize = utf8.RuneError, 3, 1
|
||||
} else {
|
||||
err = transform.ErrShortSrc
|
||||
break
|
||||
}
|
||||
if nDst+dSize > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
nDst += utf8.EncodeRune(dst[nDst:], r)
|
||||
nSrc += sSize
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
func isHighSurrogate(r rune) bool {
|
||||
return 0xDC00 <= r && r <= 0xDFFF
|
||||
}
|
||||
|
||||
type utf16Encoder struct {
|
||||
endianness Endianness
|
||||
initialBOMPolicy BOMPolicy
|
||||
currentBOMPolicy BOMPolicy
|
||||
}
|
||||
|
||||
func (u *utf16Encoder) Reset() {
|
||||
u.currentBOMPolicy = u.initialBOMPolicy
|
||||
}
|
||||
|
||||
func (u *utf16Encoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
if u.currentBOMPolicy&writeBOM != 0 {
|
||||
if len(dst) < 2 {
|
||||
return 0, 0, transform.ErrShortDst
|
||||
}
|
||||
dst[0], dst[1] = 0xfe, 0xff
|
||||
u.currentBOMPolicy = IgnoreBOM
|
||||
nDst = 2
|
||||
}
|
||||
|
||||
r, size := rune(0), 0
|
||||
for nSrc < len(src) {
|
||||
r = rune(src[nSrc])
|
||||
|
||||
// Decode a 1-byte rune.
|
||||
if r < utf8.RuneSelf {
|
||||
size = 1
|
||||
|
||||
} else {
|
||||
// Decode a multi-byte rune.
|
||||
r, size = utf8.DecodeRune(src[nSrc:])
|
||||
if size == 1 {
|
||||
// All valid runes of size 1 (those below utf8.RuneSelf) were
|
||||
// handled above. We have invalid UTF-8 or we haven't seen the
|
||||
// full character yet.
|
||||
if !atEOF && !utf8.FullRune(src[nSrc:]) {
|
||||
err = transform.ErrShortSrc
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if r <= 0xffff {
|
||||
if nDst+2 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst+0] = uint8(r >> 8)
|
||||
dst[nDst+1] = uint8(r)
|
||||
nDst += 2
|
||||
} else {
|
||||
if nDst+4 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
r1, r2 := utf16.EncodeRune(r)
|
||||
dst[nDst+0] = uint8(r1 >> 8)
|
||||
dst[nDst+1] = uint8(r1)
|
||||
dst[nDst+2] = uint8(r2 >> 8)
|
||||
dst[nDst+3] = uint8(r2)
|
||||
nDst += 4
|
||||
}
|
||||
nSrc += size
|
||||
}
|
||||
|
||||
if u.endianness == LittleEndian {
|
||||
for i := 0; i < nDst; i += 2 {
|
||||
dst[i], dst[i+1] = dst[i+1], dst[i]
|
||||
}
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
|
@ -0,0 +1,87 @@
|
|||
// 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 utf8internal contains low-level utf8-related constants, tables, etc.
|
||||
// that are used internally by the text package.
|
||||
package utf8internal
|
||||
|
||||
// The default lowest and highest continuation byte.
|
||||
const (
|
||||
LoCB = 0x80 // 1000 0000
|
||||
HiCB = 0xBF // 1011 1111
|
||||
)
|
||||
|
||||
// Constants related to getting information of first bytes of UTF-8 sequences.
|
||||
const (
|
||||
// ASCII identifies a UTF-8 byte as ASCII.
|
||||
ASCII = as
|
||||
|
||||
// FirstInvalid indicates a byte is invalid as a first byte of a UTF-8
|
||||
// sequence.
|
||||
FirstInvalid = xx
|
||||
|
||||
// SizeMask is a mask for the size bits. Use use x&SizeMask to get the size.
|
||||
SizeMask = 7
|
||||
|
||||
// AcceptShift is the right-shift count for the first byte info byte to get
|
||||
// the index into the AcceptRanges table. See AcceptRanges.
|
||||
AcceptShift = 4
|
||||
|
||||
// The names of these constants are chosen to give nice alignment in the
|
||||
// table below. The first nibble is an index into acceptRanges or F for
|
||||
// special one-byte cases. The second nibble is the Rune length or the
|
||||
// Status for the special one-byte case.
|
||||
xx = 0xF1 // invalid: size 1
|
||||
as = 0xF0 // ASCII: size 1
|
||||
s1 = 0x02 // accept 0, size 2
|
||||
s2 = 0x13 // accept 1, size 3
|
||||
s3 = 0x03 // accept 0, size 3
|
||||
s4 = 0x23 // accept 2, size 3
|
||||
s5 = 0x34 // accept 3, size 4
|
||||
s6 = 0x04 // accept 0, size 4
|
||||
s7 = 0x44 // accept 4, size 4
|
||||
)
|
||||
|
||||
// First is information about the first byte in a UTF-8 sequence.
|
||||
var First = [256]uint8{
|
||||
// 1 2 3 4 5 6 7 8 9 A B C D E F
|
||||
as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x00-0x0F
|
||||
as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x10-0x1F
|
||||
as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x20-0x2F
|
||||
as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x30-0x3F
|
||||
as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x40-0x4F
|
||||
as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x50-0x5F
|
||||
as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x60-0x6F
|
||||
as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x70-0x7F
|
||||
// 1 2 3 4 5 6 7 8 9 A B C D E F
|
||||
xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, // 0x80-0x8F
|
||||
xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, // 0x90-0x9F
|
||||
xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, // 0xA0-0xAF
|
||||
xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, // 0xB0-0xBF
|
||||
xx, xx, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, // 0xC0-0xCF
|
||||
s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, // 0xD0-0xDF
|
||||
s2, s3, s3, s3, s3, s3, s3, s3, s3, s3, s3, s3, s3, s4, s3, s3, // 0xE0-0xEF
|
||||
s5, s6, s6, s6, s7, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, // 0xF0-0xFF
|
||||
}
|
||||
|
||||
// AcceptRange gives the range of valid values for the second byte in a UTF-8
|
||||
// sequence for any value for First that is not ASCII or FirstInvalid.
|
||||
type AcceptRange struct {
|
||||
Lo uint8 // lowest value for second byte.
|
||||
Hi uint8 // highest value for second byte.
|
||||
}
|
||||
|
||||
// AcceptRanges is a slice of AcceptRange values. For a given byte sequence b
|
||||
//
|
||||
// AcceptRanges[First[b[0]]>>AcceptShift]
|
||||
//
|
||||
// will give the value of AcceptRange for the multi-byte UTF-8 sequence starting
|
||||
// at b[0].
|
||||
var AcceptRanges = [...]AcceptRange{
|
||||
0: {LoCB, HiCB},
|
||||
1: {0xA0, HiCB},
|
||||
2: {LoCB, 0x9F},
|
||||
3: {0x90, HiCB},
|
||||
4: {LoCB, 0x8F},
|
||||
}
|
||||
Loading…
Reference in New Issue