Add vendoring for unicode:
govendor fetch golang.org/x/text/encoding/unicode
This commit is contained in:
parent
c2d1f6b617
commit
d56d683bd1
|
@ -0,0 +1,22 @@
|
|||
Copyright (c) 2012 - 2013 Mat Ryer and Tyler Bunnell
|
||||
|
||||
Please consider promoting this project if you find it useful.
|
||||
|
||||
Permission is hereby granted, free of charge, to any person
|
||||
obtaining a copy of this software and associated documentation
|
||||
files (the "Software"), to deal in the Software without restriction,
|
||||
including without limitation the rights to use, copy, modify, merge,
|
||||
publish, distribute, sublicense, and/or sell copies of the Software,
|
||||
and to permit persons to whom the Software is furnished to do so,
|
||||
subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included
|
||||
in all copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
|
||||
OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
||||
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
|
||||
DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT
|
||||
OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE
|
||||
OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
|
@ -0,0 +1,27 @@
|
|||
Copyright (c) 2009 The Go Authors. All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
* Neither the name of Google Inc. nor the names of its
|
||||
contributors may be used to endorse or promote products derived from
|
||||
this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
@ -0,0 +1,22 @@
|
|||
Additional IP Rights Grant (Patents)
|
||||
|
||||
"This implementation" means the copyrightable works distributed by
|
||||
Google as part of the Go project.
|
||||
|
||||
Google hereby grants to You a perpetual, worldwide, non-exclusive,
|
||||
no-charge, royalty-free, irrevocable (except as stated in this section)
|
||||
patent license to make, have made, use, offer to sell, sell, import,
|
||||
transfer and otherwise run, modify and propagate the contents of this
|
||||
implementation of Go, where such license applies only to those patent
|
||||
claims, both currently owned or controlled by Google and acquired in
|
||||
the future, licensable by Google that are necessarily infringed by this
|
||||
implementation of Go. This grant does not include claims that would be
|
||||
infringed only as a consequence of further modification of this
|
||||
implementation. If you or your agent or exclusive licensee institute or
|
||||
order or agree to the institution of patent litigation against any
|
||||
entity (including a cross-claim or counterclaim in a lawsuit) alleging
|
||||
that this implementation of Go or any code incorporated within this
|
||||
implementation of Go constitutes direct or contributory patent
|
||||
infringement, or inducement of patent infringement, then any patent
|
||||
rights granted to you under this License for this implementation of Go
|
||||
shall terminate as of the date such litigation is filed.
|
|
@ -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 "golang.org/x/text/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 nil, 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 "", 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 nil, 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
|
||||
// "", 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 "golang.org/x/text/encoding/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 +1,339 @@
|
|||
// 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 gen
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/gob"
|
||||
"fmt"
|
||||
"hash"
|
||||
"hash/fnv"
|
||||
"io"
|
||||
"log"
|
||||
"os"
|
||||
"reflect"
|
||||
"strings"
|
||||
"unicode"
|
||||
"unicode/utf8"
|
||||
)
|
||||
|
||||
// This file contains utilities for generating code.
|
||||
|
||||
// TODO: other write methods like:
|
||||
// - slices, maps, types, etc.
|
||||
|
||||
// CodeWriter is a utility for writing structured code. It computes the content
|
||||
// hash and size of written content. It ensures there are newlines between
|
||||
// written code blocks.
|
||||
type CodeWriter struct {
|
||||
buf bytes.Buffer
|
||||
Size int
|
||||
Hash hash.Hash32 // content hash
|
||||
gob *gob.Encoder
|
||||
// For comments we skip the usual one-line separator if they are followed by
|
||||
// a code block.
|
||||
skipSep bool
|
||||
}
|
||||
|
||||
func (w *CodeWriter) Write(p []byte) (n int, err error) {
|
||||
return w.buf.Write(p)
|
||||
}
|
||||
|
||||
// NewCodeWriter returns a new CodeWriter.
|
||||
func NewCodeWriter() *CodeWriter {
|
||||
h := fnv.New32()
|
||||
return &CodeWriter{Hash: h, gob: gob.NewEncoder(h)}
|
||||
}
|
||||
|
||||
// WriteGoFile appends the buffer with the total size of all created structures
|
||||
// and writes it as a Go file to the the given file with the given package name.
|
||||
func (w *CodeWriter) WriteGoFile(filename, pkg string) {
|
||||
f, err := os.Create(filename)
|
||||
if err != nil {
|
||||
log.Fatalf("Could not create file %s: %v", filename, err)
|
||||
}
|
||||
defer f.Close()
|
||||
if _, err = w.WriteGo(f, pkg); err != nil {
|
||||
log.Fatalf("Error writing file %s: %v", filename, err)
|
||||
}
|
||||
}
|
||||
|
||||
// WriteGo appends the buffer with the total size of all created structures and
|
||||
// writes it as a Go file to the the given writer with the given package name.
|
||||
func (w *CodeWriter) WriteGo(out io.Writer, pkg string) (n int, err error) {
|
||||
sz := w.Size
|
||||
w.WriteComment("Total table size %d bytes (%dKiB); checksum: %X\n", sz, sz/1024, w.Hash.Sum32())
|
||||
defer w.buf.Reset()
|
||||
return WriteGo(out, pkg, w.buf.Bytes())
|
||||
}
|
||||
|
||||
func (w *CodeWriter) printf(f string, x ...interface{}) {
|
||||
fmt.Fprintf(w, f, x...)
|
||||
}
|
||||
|
||||
func (w *CodeWriter) insertSep() {
|
||||
if w.skipSep {
|
||||
w.skipSep = false
|
||||
return
|
||||
}
|
||||
// Use at least two newlines to ensure a blank space between the previous
|
||||
// block. WriteGoFile will remove extraneous newlines.
|
||||
w.printf("\n\n")
|
||||
}
|
||||
|
||||
// WriteComment writes a comment block. All line starts are prefixed with "//".
|
||||
// Initial empty lines are gobbled. The indentation for the first line is
|
||||
// stripped from consecutive lines.
|
||||
func (w *CodeWriter) WriteComment(comment string, args ...interface{}) {
|
||||
s := fmt.Sprintf(comment, args...)
|
||||
s = strings.Trim(s, "\n")
|
||||
|
||||
// Use at least two newlines to ensure a blank space between the previous
|
||||
// block. WriteGoFile will remove extraneous newlines.
|
||||
w.printf("\n\n// ")
|
||||
w.skipSep = true
|
||||
|
||||
// strip first indent level.
|
||||
sep := "\n"
|
||||
for ; len(s) > 0 && (s[0] == '\t' || s[0] == ' '); s = s[1:] {
|
||||
sep += s[:1]
|
||||
}
|
||||
|
||||
strings.NewReplacer(sep, "\n// ", "\n", "\n// ").WriteString(w, s)
|
||||
|
||||
w.printf("\n")
|
||||
}
|
||||
|
||||
func (w *CodeWriter) writeSizeInfo(size int) {
|
||||
w.printf("// Size: %d bytes\n", size)
|
||||
}
|
||||
|
||||
// WriteConst writes a constant of the given name and value.
|
||||
func (w *CodeWriter) WriteConst(name string, x interface{}) {
|
||||
w.insertSep()
|
||||
v := reflect.ValueOf(x)
|
||||
|
||||
switch v.Type().Kind() {
|
||||
case reflect.String:
|
||||
// See golang.org/issue/13145.
|
||||
const arbitraryCutoff = 16
|
||||
if v.Len() > arbitraryCutoff {
|
||||
w.printf("var %s %s = ", name, typeName(x))
|
||||
} else {
|
||||
w.printf("const %s %s = ", name, typeName(x))
|
||||
}
|
||||
w.WriteString(v.String())
|
||||
w.printf("\n")
|
||||
default:
|
||||
w.printf("const %s = %#v\n", name, x)
|
||||
}
|
||||
}
|
||||
|
||||
// WriteVar writes a variable of the given name and value.
|
||||
func (w *CodeWriter) WriteVar(name string, x interface{}) {
|
||||
w.insertSep()
|
||||
v := reflect.ValueOf(x)
|
||||
oldSize := w.Size
|
||||
sz := int(v.Type().Size())
|
||||
w.Size += sz
|
||||
|
||||
switch v.Type().Kind() {
|
||||
case reflect.String:
|
||||
w.printf("var %s %s = ", name, typeName(x))
|
||||
w.WriteString(v.String())
|
||||
case reflect.Struct:
|
||||
w.gob.Encode(x)
|
||||
fallthrough
|
||||
case reflect.Slice, reflect.Array:
|
||||
w.printf("var %s = ", name)
|
||||
w.writeValue(v)
|
||||
w.writeSizeInfo(w.Size - oldSize)
|
||||
default:
|
||||
w.printf("var %s %s = ", name, typeName(x))
|
||||
w.gob.Encode(x)
|
||||
w.writeValue(v)
|
||||
w.writeSizeInfo(w.Size - oldSize)
|
||||
}
|
||||
w.printf("\n")
|
||||
}
|
||||
|
||||
func (w *CodeWriter) writeValue(v reflect.Value) {
|
||||
x := v.Interface()
|
||||
switch v.Kind() {
|
||||
case reflect.String:
|
||||
w.WriteString(v.String())
|
||||
case reflect.Array:
|
||||
// Don't double count: callers of WriteArray count on the size being
|
||||
// added, so we need to discount it here.
|
||||
w.Size -= int(v.Type().Size())
|
||||
w.writeSlice(x, true)
|
||||
case reflect.Slice:
|
||||
w.writeSlice(x, false)
|
||||
case reflect.Struct:
|
||||
w.printf("%s{\n", typeName(v.Interface()))
|
||||
t := v.Type()
|
||||
for i := 0; i < v.NumField(); i++ {
|
||||
w.printf("%s: ", t.Field(i).Name)
|
||||
w.writeValue(v.Field(i))
|
||||
w.printf(",\n")
|
||||
}
|
||||
w.printf("}")
|
||||
default:
|
||||
w.printf("%#v", x)
|
||||
}
|
||||
}
|
||||
|
||||
// WriteString writes a string literal.
|
||||
func (w *CodeWriter) WriteString(s string) {
|
||||
s = strings.Replace(s, `\`, `\\`, -1)
|
||||
io.WriteString(w.Hash, s) // content hash
|
||||
w.Size += len(s)
|
||||
|
||||
const maxInline = 40
|
||||
if len(s) <= maxInline {
|
||||
w.printf("%q", s)
|
||||
return
|
||||
}
|
||||
|
||||
// We will render the string as a multi-line string.
|
||||
const maxWidth = 80 - 4 - len(`"`) - len(`" +`)
|
||||
|
||||
// When starting on its own line, go fmt indents line 2+ an extra level.
|
||||
n, max := maxWidth, maxWidth-4
|
||||
|
||||
// Print "" +\n, if a string does not start on its own line.
|
||||
b := w.buf.Bytes()
|
||||
if p := len(bytes.TrimRight(b, " \t")); p > 0 && b[p-1] != '\n' {
|
||||
w.printf("\"\" + // Size: %d bytes\n", len(s))
|
||||
n, max = maxWidth, maxWidth
|
||||
}
|
||||
|
||||
w.printf(`"`)
|
||||
|
||||
for sz, p := 0, 0; p < len(s); {
|
||||
var r rune
|
||||
r, sz = utf8.DecodeRuneInString(s[p:])
|
||||
out := s[p : p+sz]
|
||||
chars := 1
|
||||
if !unicode.IsPrint(r) || r == utf8.RuneError || r == '"' {
|
||||
switch sz {
|
||||
case 1:
|
||||
out = fmt.Sprintf("\\x%02x", s[p])
|
||||
case 2, 3:
|
||||
out = fmt.Sprintf("\\u%04x", r)
|
||||
case 4:
|
||||
out = fmt.Sprintf("\\U%08x", r)
|
||||
}
|
||||
chars = len(out)
|
||||
}
|
||||
if n -= chars; n < 0 {
|
||||
w.printf("\" +\n\"")
|
||||
n = max - len(out)
|
||||
}
|
||||
w.printf("%s", out)
|
||||
p += sz
|
||||
}
|
||||
w.printf(`"`)
|
||||
}
|
||||
|
||||
// WriteSlice writes a slice value.
|
||||
func (w *CodeWriter) WriteSlice(x interface{}) {
|
||||
w.writeSlice(x, false)
|
||||
}
|
||||
|
||||
// WriteArray writes an array value.
|
||||
func (w *CodeWriter) WriteArray(x interface{}) {
|
||||
w.writeSlice(x, true)
|
||||
}
|
||||
|
||||
func (w *CodeWriter) writeSlice(x interface{}, isArray bool) {
|
||||
v := reflect.ValueOf(x)
|
||||
w.gob.Encode(v.Len())
|
||||
w.Size += v.Len() * int(v.Type().Elem().Size())
|
||||
name := typeName(x)
|
||||
if isArray {
|
||||
name = fmt.Sprintf("[%d]%s", v.Len(), name[strings.Index(name, "]")+1:])
|
||||
}
|
||||
if isArray {
|
||||
w.printf("%s{\n", name)
|
||||
} else {
|
||||
w.printf("%s{ // %d elements\n", name, v.Len())
|
||||
}
|
||||
|
||||
switch kind := v.Type().Elem().Kind(); kind {
|
||||
case reflect.String:
|
||||
for _, s := range x.([]string) {
|
||||
w.WriteString(s)
|
||||
w.printf(",\n")
|
||||
}
|
||||
case reflect.Int, reflect.Int8, reflect.Int16, reflect.Int32, reflect.Int64,
|
||||
reflect.Uint, reflect.Uint8, reflect.Uint16, reflect.Uint32, reflect.Uint64:
|
||||
// nLine and nBlock are the number of elements per line and block.
|
||||
nLine, nBlock, format := 8, 64, "%d,"
|
||||
switch kind {
|
||||
case reflect.Uint8:
|
||||
format = "%#02x,"
|
||||
case reflect.Uint16:
|
||||
format = "%#04x,"
|
||||
case reflect.Uint32:
|
||||
nLine, nBlock, format = 4, 32, "%#08x,"
|
||||
case reflect.Uint, reflect.Uint64:
|
||||
nLine, nBlock, format = 4, 32, "%#016x,"
|
||||
case reflect.Int8:
|
||||
nLine = 16
|
||||
}
|
||||
n := nLine
|
||||
for i := 0; i < v.Len(); i++ {
|
||||
if i%nBlock == 0 && v.Len() > nBlock {
|
||||
w.printf("// Entry %X - %X\n", i, i+nBlock-1)
|
||||
}
|
||||
x := v.Index(i).Interface()
|
||||
w.gob.Encode(x)
|
||||
w.printf(format, x)
|
||||
if n--; n == 0 {
|
||||
n = nLine
|
||||
w.printf("\n")
|
||||
}
|
||||
}
|
||||
w.printf("\n")
|
||||
case reflect.Struct:
|
||||
zero := reflect.Zero(v.Type().Elem()).Interface()
|
||||
for i := 0; i < v.Len(); i++ {
|
||||
x := v.Index(i).Interface()
|
||||
w.gob.EncodeValue(v)
|
||||
if !reflect.DeepEqual(zero, x) {
|
||||
line := fmt.Sprintf("%#v,\n", x)
|
||||
line = line[strings.IndexByte(line, '{'):]
|
||||
w.printf("%d: ", i)
|
||||
w.printf(line)
|
||||
}
|
||||
}
|
||||
case reflect.Array:
|
||||
for i := 0; i < v.Len(); i++ {
|
||||
w.printf("%d: %#v,\n", i, v.Index(i).Interface())
|
||||
}
|
||||
default:
|
||||
panic("gen: slice elem type not supported")
|
||||
}
|
||||
w.printf("}")
|
||||
}
|
||||
|
||||
// WriteType writes a definition of the type of the given value and returns the
|
||||
// type name.
|
||||
func (w *CodeWriter) WriteType(x interface{}) string {
|
||||
t := reflect.TypeOf(x)
|
||||
w.printf("type %s struct {\n", t.Name())
|
||||
for i := 0; i < t.NumField(); i++ {
|
||||
w.printf("\t%s %s\n", t.Field(i).Name, t.Field(i).Type)
|
||||
}
|
||||
w.printf("}\n")
|
||||
return t.Name()
|
||||
}
|
||||
|
||||
// typeName returns the name of the go type of x.
|
||||
func typeName(x interface{}) string {
|
||||
t := reflect.ValueOf(x).Type()
|
||||
return strings.Replace(fmt.Sprint(t), "main.", "", 1)
|
||||
}
|
|
@ -0,0 +1,281 @@
|
|||
// 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 gen contains common code for the various code generation tools in the
|
||||
// text repository. Its usage ensures consistency between tools.
|
||||
//
|
||||
// This package defines command line flags that are common to most generation
|
||||
// tools. The flags allow for specifying specific Unicode and CLDR versions
|
||||
// in the public Unicode data repository (http://www.unicode.org/Public).
|
||||
//
|
||||
// A local Unicode data mirror can be set through the flag -local or the
|
||||
// environment variable UNICODE_DIR. The former takes precedence. The local
|
||||
// directory should follow the same structure as the public repository.
|
||||
//
|
||||
// IANA data can also optionally be mirrored by putting it in the iana directory
|
||||
// rooted at the top of the local mirror. Beware, though, that IANA data is not
|
||||
// versioned. So it is up to the developer to use the right version.
|
||||
package gen // import "golang.org/x/text/internal/gen"
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"flag"
|
||||
"fmt"
|
||||
"go/build"
|
||||
"go/format"
|
||||
"io"
|
||||
"io/ioutil"
|
||||
"log"
|
||||
"net/http"
|
||||
"os"
|
||||
"path"
|
||||
"path/filepath"
|
||||
"sync"
|
||||
"unicode"
|
||||
|
||||
"golang.org/x/text/unicode/cldr"
|
||||
)
|
||||
|
||||
var (
|
||||
url = flag.String("url",
|
||||
"http://www.unicode.org/Public",
|
||||
"URL of Unicode database directory")
|
||||
iana = flag.String("iana",
|
||||
"http://www.iana.org",
|
||||
"URL of the IANA repository")
|
||||
unicodeVersion = flag.String("unicode",
|
||||
getEnv("UNICODE_VERSION", unicode.Version),
|
||||
"unicode version to use")
|
||||
cldrVersion = flag.String("cldr",
|
||||
getEnv("CLDR_VERSION", cldr.Version),
|
||||
"cldr version to use")
|
||||
)
|
||||
|
||||
func getEnv(name, def string) string {
|
||||
if v := os.Getenv(name); v != "" {
|
||||
return v
|
||||
}
|
||||
return def
|
||||
}
|
||||
|
||||
// Init performs common initialization for a gen command. It parses the flags
|
||||
// and sets up the standard logging parameters.
|
||||
func Init() {
|
||||
log.SetPrefix("")
|
||||
log.SetFlags(log.Lshortfile)
|
||||
flag.Parse()
|
||||
}
|
||||
|
||||
const header = `// This file was generated by go generate; DO NOT EDIT
|
||||
|
||||
package %s
|
||||
|
||||
`
|
||||
|
||||
// UnicodeVersion reports the requested Unicode version.
|
||||
func UnicodeVersion() string {
|
||||
return *unicodeVersion
|
||||
}
|
||||
|
||||
// UnicodeVersion reports the requested CLDR version.
|
||||
func CLDRVersion() string {
|
||||
return *cldrVersion
|
||||
}
|
||||
|
||||
// IsLocal reports whether data files are available locally.
|
||||
func IsLocal() bool {
|
||||
dir, err := localReadmeFile()
|
||||
if err != nil {
|
||||
return false
|
||||
}
|
||||
if _, err = os.Stat(dir); err != nil {
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// OpenUCDFile opens the requested UCD file. The file is specified relative to
|
||||
// the public Unicode root directory. It will call log.Fatal if there are any
|
||||
// errors.
|
||||
func OpenUCDFile(file string) io.ReadCloser {
|
||||
return openUnicode(path.Join(*unicodeVersion, "ucd", file))
|
||||
}
|
||||
|
||||
// OpenCLDRCoreZip opens the CLDR core zip file. It will call log.Fatal if there
|
||||
// are any errors.
|
||||
func OpenCLDRCoreZip() io.ReadCloser {
|
||||
return OpenUnicodeFile("cldr", *cldrVersion, "core.zip")
|
||||
}
|
||||
|
||||
// OpenUnicodeFile opens the requested file of the requested category from the
|
||||
// root of the Unicode data archive. The file is specified relative to the
|
||||
// public Unicode root directory. If version is "", it will use the default
|
||||
// Unicode version. It will call log.Fatal if there are any errors.
|
||||
func OpenUnicodeFile(category, version, file string) io.ReadCloser {
|
||||
if version == "" {
|
||||
version = UnicodeVersion()
|
||||
}
|
||||
return openUnicode(path.Join(category, version, file))
|
||||
}
|
||||
|
||||
// OpenIANAFile opens the requested IANA file. The file is specified relative
|
||||
// to the IANA root, which is typically either http://www.iana.org or the
|
||||
// iana directory in the local mirror. It will call log.Fatal if there are any
|
||||
// errors.
|
||||
func OpenIANAFile(path string) io.ReadCloser {
|
||||
return Open(*iana, "iana", path)
|
||||
}
|
||||
|
||||
var (
|
||||
dirMutex sync.Mutex
|
||||
localDir string
|
||||
)
|
||||
|
||||
const permissions = 0755
|
||||
|
||||
func localReadmeFile() (string, error) {
|
||||
p, err := build.Import("golang.org/x/text", "", build.FindOnly)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("Could not locate package: %v", err)
|
||||
}
|
||||
return filepath.Join(p.Dir, "DATA", "README"), nil
|
||||
}
|
||||
|
||||
func getLocalDir() string {
|
||||
dirMutex.Lock()
|
||||
defer dirMutex.Unlock()
|
||||
|
||||
readme, err := localReadmeFile()
|
||||
if err != nil {
|
||||
log.Fatal(err)
|
||||
}
|
||||
dir := filepath.Dir(readme)
|
||||
if _, err := os.Stat(readme); err != nil {
|
||||
if err := os.MkdirAll(dir, permissions); err != nil {
|
||||
log.Fatalf("Could not create directory: %v", err)
|
||||
}
|
||||
ioutil.WriteFile(readme, []byte(readmeTxt), permissions)
|
||||
}
|
||||
return dir
|
||||
}
|
||||
|
||||
const readmeTxt = `Generated by golang.org/x/text/internal/gen. DO NOT EDIT.
|
||||
|
||||
This directory contains downloaded files used to generate the various tables
|
||||
in the golang.org/x/text subrepo.
|
||||
|
||||
Note that the language subtag repo (iana/assignments/language-subtag-registry)
|
||||
and all other times in the iana subdirectory are not versioned and will need
|
||||
to be periodically manually updated. The easiest way to do this is to remove
|
||||
the entire iana directory. This is mostly of concern when updating the language
|
||||
package.
|
||||
`
|
||||
|
||||
// Open opens subdir/path if a local directory is specified and the file exists,
|
||||
// where subdir is a directory relative to the local root, or fetches it from
|
||||
// urlRoot/path otherwise. It will call log.Fatal if there are any errors.
|
||||
func Open(urlRoot, subdir, path string) io.ReadCloser {
|
||||
file := filepath.Join(getLocalDir(), subdir, filepath.FromSlash(path))
|
||||
return open(file, urlRoot, path)
|
||||
}
|
||||
|
||||
func openUnicode(path string) io.ReadCloser {
|
||||
file := filepath.Join(getLocalDir(), filepath.FromSlash(path))
|
||||
return open(file, *url, path)
|
||||
}
|
||||
|
||||
// TODO: automatically periodically update non-versioned files.
|
||||
|
||||
func open(file, urlRoot, path string) io.ReadCloser {
|
||||
if f, err := os.Open(file); err == nil {
|
||||
return f
|
||||
}
|
||||
r := get(urlRoot, path)
|
||||
defer r.Close()
|
||||
b, err := ioutil.ReadAll(r)
|
||||
if err != nil {
|
||||
log.Fatalf("Could not download file: %v", err)
|
||||
}
|
||||
os.MkdirAll(filepath.Dir(file), permissions)
|
||||
if err := ioutil.WriteFile(file, b, permissions); err != nil {
|
||||
log.Fatalf("Could not create file: %v", err)
|
||||
}
|
||||
return ioutil.NopCloser(bytes.NewReader(b))
|
||||
}
|
||||
|
||||
func get(root, path string) io.ReadCloser {
|
||||
url := root + "/" + path
|
||||
fmt.Printf("Fetching %s...", url)
|
||||
defer fmt.Println(" done.")
|
||||
resp, err := http.Get(url)
|
||||
if err != nil {
|
||||
log.Fatalf("HTTP GET: %v", err)
|
||||
}
|
||||
if resp.StatusCode != 200 {
|
||||
log.Fatalf("Bad GET status for %q: %q", url, resp.Status)
|
||||
}
|
||||
return resp.Body
|
||||
}
|
||||
|
||||
// TODO: use Write*Version in all applicable packages.
|
||||
|
||||
// WriteUnicodeVersion writes a constant for the Unicode version from which the
|
||||
// tables are generated.
|
||||
func WriteUnicodeVersion(w io.Writer) {
|
||||
fmt.Fprintf(w, "// UnicodeVersion is the Unicode version from which the tables in this package are derived.\n")
|
||||
fmt.Fprintf(w, "const UnicodeVersion = %q\n\n", UnicodeVersion())
|
||||
}
|
||||
|
||||
// WriteCLDRVersion writes a constant for the CLDR version from which the
|
||||
// tables are generated.
|
||||
func WriteCLDRVersion(w io.Writer) {
|
||||
fmt.Fprintf(w, "// CLDRVersion is the CLDR version from which the tables in this package are derived.\n")
|
||||
fmt.Fprintf(w, "const CLDRVersion = %q\n\n", CLDRVersion())
|
||||
}
|
||||
|
||||
// WriteGoFile prepends a standard file comment and package statement to the
|
||||
// given bytes, applies gofmt, and writes them to a file with the given name.
|
||||
// It will call log.Fatal if there are any errors.
|
||||
func WriteGoFile(filename, pkg string, b []byte) {
|
||||
w, err := os.Create(filename)
|
||||
if err != nil {
|
||||
log.Fatalf("Could not create file %s: %v", filename, err)
|
||||
}
|
||||
defer w.Close()
|
||||
if _, err = WriteGo(w, pkg, b); err != nil {
|
||||
log.Fatalf("Error writing file %s: %v", filename, err)
|
||||
}
|
||||
}
|
||||
|
||||
// WriteGo prepends a standard file comment and package statement to the given
|
||||
// bytes, applies gofmt, and writes them to w.
|
||||
func WriteGo(w io.Writer, pkg string, b []byte) (n int, err error) {
|
||||
src := []byte(fmt.Sprintf(header, pkg))
|
||||
src = append(src, b...)
|
||||
formatted, err := format.Source(src)
|
||||
if err != nil {
|
||||
// Print the generated code even in case of an error so that the
|
||||
// returned error can be meaningfully interpreted.
|
||||
n, _ = w.Write(src)
|
||||
return n, err
|
||||
}
|
||||
return w.Write(formatted)
|
||||
}
|
||||
|
||||
// Repackage rewrites a Go file from belonging to package main to belonging to
|
||||
// the given package.
|
||||
func Repackage(inFile, outFile, pkg string) {
|
||||
src, err := ioutil.ReadFile(inFile)
|
||||
if err != nil {
|
||||
log.Fatalf("reading %s: %v", inFile, err)
|
||||
}
|
||||
const toDelete = "package main\n\n"
|
||||
i := bytes.Index(src, []byte(toDelete))
|
||||
if i < 0 {
|
||||
log.Fatalf("Could not find %q in %s.", toDelete, inFile)
|
||||
}
|
||||
w := &bytes.Buffer{}
|
||||
w.Write(src[i+len(toDelete):])
|
||||
WriteGoFile(outFile, pkg, w.Bytes())
|
||||
}
|
|
@ -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},
|
||||
}
|
|
@ -0,0 +1,187 @@
|
|||
// 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 runes
|
||||
|
||||
import (
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// Note: below we pass invalid UTF-8 to the tIn and tNotIn transformers as is.
|
||||
// This is done for various reasons:
|
||||
// - To retain the semantics of the Nop transformer: if input is passed to a Nop
|
||||
// one would expect it to be unchanged.
|
||||
// - It would be very expensive to pass a converted RuneError to a transformer:
|
||||
// a transformer might need more source bytes after RuneError, meaning that
|
||||
// the only way to pass it safely is to create a new buffer and manage the
|
||||
// intermingling of RuneErrors and normal input.
|
||||
// - Many transformers leave ill-formed UTF-8 as is, so this is not
|
||||
// inconsistent. Generally ill-formed UTF-8 is only replaced if it is a
|
||||
// logical consequence of the operation (as for Map) or if it otherwise would
|
||||
// pose security concerns (as for Remove).
|
||||
// - An alternative would be to return an error on ill-formed UTF-8, but this
|
||||
// would be inconsistent with other operations.
|
||||
|
||||
// If returns a transformer that applies tIn to consecutive runes for which
|
||||
// s.Contains(r) and tNotIn to consecutive runes for which !s.Contains(r). Reset
|
||||
// is called on tIn and tNotIn at the start of each run. A Nop transformer will
|
||||
// substitute a nil value passed to tIn or tNotIn. Invalid UTF-8 is translated
|
||||
// to RuneError to determine which transformer to apply, but is passed as is to
|
||||
// the respective transformer.
|
||||
func If(s Set, tIn, tNotIn transform.Transformer) Transformer {
|
||||
if tIn == nil && tNotIn == nil {
|
||||
return Transformer{transform.Nop}
|
||||
}
|
||||
if tIn == nil {
|
||||
tIn = transform.Nop
|
||||
}
|
||||
if tNotIn == nil {
|
||||
tNotIn = transform.Nop
|
||||
}
|
||||
sIn, ok := tIn.(transform.SpanningTransformer)
|
||||
if !ok {
|
||||
sIn = dummySpan{tIn}
|
||||
}
|
||||
sNotIn, ok := tNotIn.(transform.SpanningTransformer)
|
||||
if !ok {
|
||||
sNotIn = dummySpan{tNotIn}
|
||||
}
|
||||
|
||||
a := &cond{
|
||||
tIn: sIn,
|
||||
tNotIn: sNotIn,
|
||||
f: s.Contains,
|
||||
}
|
||||
a.Reset()
|
||||
return Transformer{a}
|
||||
}
|
||||
|
||||
type dummySpan struct{ transform.Transformer }
|
||||
|
||||
func (d dummySpan) Span(src []byte, atEOF bool) (n int, err error) {
|
||||
return 0, transform.ErrEndOfSpan
|
||||
}
|
||||
|
||||
type cond struct {
|
||||
tIn, tNotIn transform.SpanningTransformer
|
||||
f func(rune) bool
|
||||
check func(rune) bool // current check to perform
|
||||
t transform.SpanningTransformer // current transformer to use
|
||||
}
|
||||
|
||||
// Reset implements transform.Transformer.
|
||||
func (t *cond) Reset() {
|
||||
t.check = t.is
|
||||
t.t = t.tIn
|
||||
t.t.Reset() // notIn will be reset on first usage.
|
||||
}
|
||||
|
||||
func (t *cond) is(r rune) bool {
|
||||
if t.f(r) {
|
||||
return true
|
||||
}
|
||||
t.check = t.isNot
|
||||
t.t = t.tNotIn
|
||||
t.tNotIn.Reset()
|
||||
return false
|
||||
}
|
||||
|
||||
func (t *cond) isNot(r rune) bool {
|
||||
if !t.f(r) {
|
||||
return true
|
||||
}
|
||||
t.check = t.is
|
||||
t.t = t.tIn
|
||||
t.tIn.Reset()
|
||||
return false
|
||||
}
|
||||
|
||||
// This implementation of Span doesn't help all too much, but it needs to be
|
||||
// there to satisfy this package's Transformer interface.
|
||||
// TODO: there are certainly room for improvements, though. For example, if
|
||||
// t.t == transform.Nop (which will a common occurrence) it will save a bundle
|
||||
// to special-case that loop.
|
||||
func (t *cond) Span(src []byte, atEOF bool) (n int, err error) {
|
||||
p := 0
|
||||
for n < len(src) && err == nil {
|
||||
// Don't process too much at a time as the Spanner that will be
|
||||
// called on this block may terminate early.
|
||||
const maxChunk = 4096
|
||||
max := len(src)
|
||||
if v := n + maxChunk; v < max {
|
||||
max = v
|
||||
}
|
||||
atEnd := false
|
||||
size := 0
|
||||
current := t.t
|
||||
for ; p < max; p += size {
|
||||
r := rune(src[p])
|
||||
if r < utf8.RuneSelf {
|
||||
size = 1
|
||||
} else if r, size = utf8.DecodeRune(src[p:]); size == 1 {
|
||||
if !atEOF && !utf8.FullRune(src[p:]) {
|
||||
err = transform.ErrShortSrc
|
||||
break
|
||||
}
|
||||
}
|
||||
if !t.check(r) {
|
||||
// The next rune will be the start of a new run.
|
||||
atEnd = true
|
||||
break
|
||||
}
|
||||
}
|
||||
n2, err2 := current.Span(src[n:p], atEnd || (atEOF && p == len(src)))
|
||||
n += n2
|
||||
if err2 != nil {
|
||||
return n, err2
|
||||
}
|
||||
// At this point either err != nil or t.check will pass for the rune at p.
|
||||
p = n + size
|
||||
}
|
||||
return n, err
|
||||
}
|
||||
|
||||
func (t *cond) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
p := 0
|
||||
for nSrc < len(src) && err == nil {
|
||||
// Don't process too much at a time, as the work might be wasted if the
|
||||
// destination buffer isn't large enough to hold the result or a
|
||||
// transform returns an error early.
|
||||
const maxChunk = 4096
|
||||
max := len(src)
|
||||
if n := nSrc + maxChunk; n < len(src) {
|
||||
max = n
|
||||
}
|
||||
atEnd := false
|
||||
size := 0
|
||||
current := t.t
|
||||
for ; p < max; p += size {
|
||||
r := rune(src[p])
|
||||
if r < utf8.RuneSelf {
|
||||
size = 1
|
||||
} else if r, size = utf8.DecodeRune(src[p:]); size == 1 {
|
||||
if !atEOF && !utf8.FullRune(src[p:]) {
|
||||
err = transform.ErrShortSrc
|
||||
break
|
||||
}
|
||||
}
|
||||
if !t.check(r) {
|
||||
// The next rune will be the start of a new run.
|
||||
atEnd = true
|
||||
break
|
||||
}
|
||||
}
|
||||
nDst2, nSrc2, err2 := current.Transform(dst[nDst:], src[nSrc:p], atEnd || (atEOF && p == len(src)))
|
||||
nDst += nDst2
|
||||
nSrc += nSrc2
|
||||
if err2 != nil {
|
||||
return nDst, nSrc, err2
|
||||
}
|
||||
// At this point either err != nil or t.check will pass for the rune at p.
|
||||
p = nSrc + size
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
|
@ -0,0 +1,355 @@
|
|||
// 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 runes provide transforms for UTF-8 encoded text.
|
||||
package runes // import "golang.org/x/text/runes"
|
||||
|
||||
import (
|
||||
"unicode"
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// A Set is a collection of runes.
|
||||
type Set interface {
|
||||
// Contains returns true if r is contained in the set.
|
||||
Contains(r rune) bool
|
||||
}
|
||||
|
||||
type setFunc func(rune) bool
|
||||
|
||||
func (s setFunc) Contains(r rune) bool {
|
||||
return s(r)
|
||||
}
|
||||
|
||||
// Note: using funcs here instead of wrapping types result in cleaner
|
||||
// documentation and a smaller API.
|
||||
|
||||
// In creates a Set with a Contains method that returns true for all runes in
|
||||
// the given RangeTable.
|
||||
func In(rt *unicode.RangeTable) Set {
|
||||
return setFunc(func(r rune) bool { return unicode.Is(rt, r) })
|
||||
}
|
||||
|
||||
// In creates a Set with a Contains method that returns true for all runes not
|
||||
// in the given RangeTable.
|
||||
func NotIn(rt *unicode.RangeTable) Set {
|
||||
return setFunc(func(r rune) bool { return !unicode.Is(rt, r) })
|
||||
}
|
||||
|
||||
// Predicate creates a Set with a Contains method that returns f(r).
|
||||
func Predicate(f func(rune) bool) Set {
|
||||
return setFunc(f)
|
||||
}
|
||||
|
||||
// Transformer implements the transform.Transformer interface.
|
||||
type Transformer struct {
|
||||
t transform.SpanningTransformer
|
||||
}
|
||||
|
||||
func (t Transformer) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
return t.t.Transform(dst, src, atEOF)
|
||||
}
|
||||
|
||||
func (t Transformer) Span(b []byte, atEOF bool) (n int, err error) {
|
||||
return t.t.Span(b, atEOF)
|
||||
}
|
||||
|
||||
func (t Transformer) Reset() { t.t.Reset() }
|
||||
|
||||
// Bytes returns a new byte slice with the result of converting b using t. It
|
||||
// calls Reset on t. It returns nil if any error was found. This can only happen
|
||||
// if an error-producing Transformer is passed to If.
|
||||
func (t Transformer) Bytes(b []byte) []byte {
|
||||
b, _, err := transform.Bytes(t, b)
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
return b
|
||||
}
|
||||
|
||||
// String returns a string with the result of converting s using t. It calls
|
||||
// Reset on t. It returns the empty string if any error was found. This can only
|
||||
// happen if an error-producing Transformer is passed to If.
|
||||
func (t Transformer) String(s string) string {
|
||||
s, _, err := transform.String(t, s)
|
||||
if err != nil {
|
||||
return ""
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
// TODO:
|
||||
// - Copy: copying strings and bytes in whole-rune units.
|
||||
// - Validation (maybe)
|
||||
// - Well-formed-ness (maybe)
|
||||
|
||||
const runeErrorString = string(utf8.RuneError)
|
||||
|
||||
// Remove returns a Transformer that removes runes r for which s.Contains(r).
|
||||
// Illegal input bytes are replaced by RuneError before being passed to f.
|
||||
func Remove(s Set) Transformer {
|
||||
if f, ok := s.(setFunc); ok {
|
||||
// This little trick cuts the running time of BenchmarkRemove for sets
|
||||
// created by Predicate roughly in half.
|
||||
// TODO: special-case RangeTables as well.
|
||||
return Transformer{remove(f)}
|
||||
}
|
||||
return Transformer{remove(s.Contains)}
|
||||
}
|
||||
|
||||
// TODO: remove transform.RemoveFunc.
|
||||
|
||||
type remove func(r rune) bool
|
||||
|
||||
func (remove) Reset() {}
|
||||
|
||||
// Span implements transform.Spanner.
|
||||
func (t remove) Span(src []byte, atEOF bool) (n int, err error) {
|
||||
for r, size := rune(0), 0; n < len(src); {
|
||||
if r = rune(src[n]); r < utf8.RuneSelf {
|
||||
size = 1
|
||||
} else if r, size = utf8.DecodeRune(src[n:]); size == 1 {
|
||||
// Invalid rune.
|
||||
if !atEOF && !utf8.FullRune(src[n:]) {
|
||||
err = transform.ErrShortSrc
|
||||
} else {
|
||||
err = transform.ErrEndOfSpan
|
||||
}
|
||||
break
|
||||
}
|
||||
if t(r) {
|
||||
err = transform.ErrEndOfSpan
|
||||
break
|
||||
}
|
||||
n += size
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
// Transform implements transform.Transformer.
|
||||
func (t remove) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
for r, size := rune(0), 0; nSrc < len(src); {
|
||||
if r = rune(src[nSrc]); r < utf8.RuneSelf {
|
||||
size = 1
|
||||
} else if r, size = utf8.DecodeRune(src[nSrc:]); size == 1 {
|
||||
// Invalid rune.
|
||||
if !atEOF && !utf8.FullRune(src[nSrc:]) {
|
||||
err = transform.ErrShortSrc
|
||||
break
|
||||
}
|
||||
// We replace illegal bytes with RuneError. Not doing so might
|
||||
// otherwise turn a sequence of invalid UTF-8 into valid UTF-8.
|
||||
// The resulting byte sequence may subsequently contain runes
|
||||
// for which t(r) is true that were passed unnoticed.
|
||||
if !t(utf8.RuneError) {
|
||||
if nDst+3 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst+0] = runeErrorString[0]
|
||||
dst[nDst+1] = runeErrorString[1]
|
||||
dst[nDst+2] = runeErrorString[2]
|
||||
nDst += 3
|
||||
}
|
||||
nSrc++
|
||||
continue
|
||||
}
|
||||
if t(r) {
|
||||
nSrc += size
|
||||
continue
|
||||
}
|
||||
if nDst+size > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
for i := 0; i < size; i++ {
|
||||
dst[nDst] = src[nSrc]
|
||||
nDst++
|
||||
nSrc++
|
||||
}
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
// Map returns a Transformer that maps the runes in the input using the given
|
||||
// mapping. Illegal bytes in the input are converted to utf8.RuneError before
|
||||
// being passed to the mapping func.
|
||||
func Map(mapping func(rune) rune) Transformer {
|
||||
return Transformer{mapper(mapping)}
|
||||
}
|
||||
|
||||
type mapper func(rune) rune
|
||||
|
||||
func (mapper) Reset() {}
|
||||
|
||||
// Span implements transform.Spanner.
|
||||
func (t mapper) Span(src []byte, atEOF bool) (n int, err error) {
|
||||
for r, size := rune(0), 0; n < len(src); n += size {
|
||||
if r = rune(src[n]); r < utf8.RuneSelf {
|
||||
size = 1
|
||||
} else if r, size = utf8.DecodeRune(src[n:]); size == 1 {
|
||||
// Invalid rune.
|
||||
if !atEOF && !utf8.FullRune(src[n:]) {
|
||||
err = transform.ErrShortSrc
|
||||
} else {
|
||||
err = transform.ErrEndOfSpan
|
||||
}
|
||||
break
|
||||
}
|
||||
if t(r) != r {
|
||||
err = transform.ErrEndOfSpan
|
||||
break
|
||||
}
|
||||
}
|
||||
return n, err
|
||||
}
|
||||
|
||||
// Transform implements transform.Transformer.
|
||||
func (t mapper) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
var replacement rune
|
||||
var b [utf8.UTFMax]byte
|
||||
|
||||
for r, size := rune(0), 0; nSrc < len(src); {
|
||||
if r = rune(src[nSrc]); r < utf8.RuneSelf {
|
||||
if replacement = t(r); replacement < utf8.RuneSelf {
|
||||
if nDst == len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst] = byte(replacement)
|
||||
nDst++
|
||||
nSrc++
|
||||
continue
|
||||
}
|
||||
size = 1
|
||||
} else if r, size = utf8.DecodeRune(src[nSrc:]); size == 1 {
|
||||
// Invalid rune.
|
||||
if !atEOF && !utf8.FullRune(src[nSrc:]) {
|
||||
err = transform.ErrShortSrc
|
||||
break
|
||||
}
|
||||
|
||||
if replacement = t(utf8.RuneError); replacement == utf8.RuneError {
|
||||
if nDst+3 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst+0] = runeErrorString[0]
|
||||
dst[nDst+1] = runeErrorString[1]
|
||||
dst[nDst+2] = runeErrorString[2]
|
||||
nDst += 3
|
||||
nSrc++
|
||||
continue
|
||||
}
|
||||
} else if replacement = t(r); replacement == r {
|
||||
if nDst+size > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
for i := 0; i < size; i++ {
|
||||
dst[nDst] = src[nSrc]
|
||||
nDst++
|
||||
nSrc++
|
||||
}
|
||||
continue
|
||||
}
|
||||
|
||||
n := utf8.EncodeRune(b[:], replacement)
|
||||
|
||||
if nDst+n > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
for i := 0; i < n; i++ {
|
||||
dst[nDst] = b[i]
|
||||
nDst++
|
||||
}
|
||||
nSrc += size
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
// ReplaceIllFormed returns a transformer that replaces all input bytes that are
|
||||
// not part of a well-formed UTF-8 code sequence with utf8.RuneError.
|
||||
func ReplaceIllFormed() Transformer {
|
||||
return Transformer{&replaceIllFormed{}}
|
||||
}
|
||||
|
||||
type replaceIllFormed struct{ transform.NopResetter }
|
||||
|
||||
func (t replaceIllFormed) Span(src []byte, atEOF bool) (n int, err error) {
|
||||
for n < len(src) {
|
||||
// ASCII fast path.
|
||||
if src[n] < utf8.RuneSelf {
|
||||
n++
|
||||
continue
|
||||
}
|
||||
|
||||
r, size := utf8.DecodeRune(src[n:])
|
||||
|
||||
// Look for a valid non-ASCII rune.
|
||||
if r != utf8.RuneError || size != 1 {
|
||||
n += size
|
||||
continue
|
||||
}
|
||||
|
||||
// Look for short source data.
|
||||
if !atEOF && !utf8.FullRune(src[n:]) {
|
||||
err = transform.ErrShortSrc
|
||||
break
|
||||
}
|
||||
|
||||
// We have an invalid rune.
|
||||
err = transform.ErrEndOfSpan
|
||||
break
|
||||
}
|
||||
return n, err
|
||||
}
|
||||
|
||||
func (t replaceIllFormed) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
for nSrc < len(src) {
|
||||
// ASCII fast path.
|
||||
if r := src[nSrc]; r < utf8.RuneSelf {
|
||||
if nDst == len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst] = r
|
||||
nDst++
|
||||
nSrc++
|
||||
continue
|
||||
}
|
||||
|
||||
// Look for a valid non-ASCII rune.
|
||||
if _, size := utf8.DecodeRune(src[nSrc:]); size != 1 {
|
||||
if size != copy(dst[nDst:], src[nSrc:nSrc+size]) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
nDst += size
|
||||
nSrc += size
|
||||
continue
|
||||
}
|
||||
|
||||
// Look for short source data.
|
||||
if !atEOF && !utf8.FullRune(src[nSrc:]) {
|
||||
err = transform.ErrShortSrc
|
||||
break
|
||||
}
|
||||
|
||||
// We have an invalid rune.
|
||||
if nDst+3 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst+0] = runeErrorString[0]
|
||||
dst[nDst+1] = runeErrorString[1]
|
||||
dst[nDst+2] = runeErrorString[2]
|
||||
nDst += 3
|
||||
nSrc++
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
|
@ -0,0 +1,705 @@
|
|||
// 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 transform provides reader and writer wrappers that transform the
|
||||
// bytes passing through as well as various transformations. Example
|
||||
// transformations provided by other packages include normalization and
|
||||
// conversion between character sets.
|
||||
package transform // import "golang.org/x/text/transform"
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"errors"
|
||||
"io"
|
||||
"unicode/utf8"
|
||||
)
|
||||
|
||||
var (
|
||||
// ErrShortDst means that the destination buffer was too short to
|
||||
// receive all of the transformed bytes.
|
||||
ErrShortDst = errors.New("transform: short destination buffer")
|
||||
|
||||
// ErrShortSrc means that the source buffer has insufficient data to
|
||||
// complete the transformation.
|
||||
ErrShortSrc = errors.New("transform: short source buffer")
|
||||
|
||||
// ErrEndOfSpan means that the input and output (the transformed input)
|
||||
// are not identical.
|
||||
ErrEndOfSpan = errors.New("transform: input and output are not identical")
|
||||
|
||||
// errInconsistentByteCount means that Transform returned success (nil
|
||||
// error) but also returned nSrc inconsistent with the src argument.
|
||||
errInconsistentByteCount = errors.New("transform: inconsistent byte count returned")
|
||||
|
||||
// errShortInternal means that an internal buffer is not large enough
|
||||
// to make progress and the Transform operation must be aborted.
|
||||
errShortInternal = errors.New("transform: short internal buffer")
|
||||
)
|
||||
|
||||
// Transformer transforms bytes.
|
||||
type Transformer interface {
|
||||
// Transform writes to dst the transformed bytes read from src, and
|
||||
// returns the number of dst bytes written and src bytes read. The
|
||||
// atEOF argument tells whether src represents the last bytes of the
|
||||
// input.
|
||||
//
|
||||
// Callers should always process the nDst bytes produced and account
|
||||
// for the nSrc bytes consumed before considering the error err.
|
||||
//
|
||||
// A nil error means that all of the transformed bytes (whether freshly
|
||||
// transformed from src or left over from previous Transform calls)
|
||||
// were written to dst. A nil error can be returned regardless of
|
||||
// whether atEOF is true. If err is nil then nSrc must equal len(src);
|
||||
// the converse is not necessarily true.
|
||||
//
|
||||
// ErrShortDst means that dst was too short to receive all of the
|
||||
// transformed bytes. ErrShortSrc means that src had insufficient data
|
||||
// to complete the transformation. If both conditions apply, then
|
||||
// either error may be returned. Other than the error conditions listed
|
||||
// here, implementations are free to report other errors that arise.
|
||||
Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error)
|
||||
|
||||
// Reset resets the state and allows a Transformer to be reused.
|
||||
Reset()
|
||||
}
|
||||
|
||||
// SpanningTransformer extends the Transformer interface with a Span method
|
||||
// that determines how much of the input already conforms to the Transformer.
|
||||
type SpanningTransformer interface {
|
||||
Transformer
|
||||
|
||||
// Span returns a position in src such that transforming src[:n] results in
|
||||
// identical output src[:n] for these bytes. It does not necessarily return
|
||||
// the largest such n. The atEOF argument tells whether src represents the
|
||||
// last bytes of the input.
|
||||
//
|
||||
// Callers should always account for the n bytes consumed before
|
||||
// considering the error err.
|
||||
//
|
||||
// A nil error means that all input bytes are known to be identical to the
|
||||
// output produced by the Transformer. A nil error can be be returned
|
||||
// regardless of whether atEOF is true. If err is nil, then then n must
|
||||
// equal len(src); the converse is not necessarily true.
|
||||
//
|
||||
// ErrEndOfSpan means that the Transformer output may differ from the
|
||||
// input after n bytes. Note that n may be len(src), meaning that the output
|
||||
// would contain additional bytes after otherwise identical output.
|
||||
// ErrShortSrc means that src had insufficient data to determine whether the
|
||||
// remaining bytes would change. Other than the error conditions listed
|
||||
// here, implementations are free to report other errors that arise.
|
||||
//
|
||||
// Calling Span can modify the Transformer state as a side effect. In
|
||||
// effect, it does the transformation just as calling Transform would, only
|
||||
// without copying to a destination buffer and only up to a point it can
|
||||
// determine the input and output bytes are the same. This is obviously more
|
||||
// limited than calling Transform, but can be more efficient in terms of
|
||||
// copying and allocating buffers. Calls to Span and Transform may be
|
||||
// interleaved.
|
||||
Span(src []byte, atEOF bool) (n int, err error)
|
||||
}
|
||||
|
||||
// NopResetter can be embedded by implementations of Transformer to add a nop
|
||||
// Reset method.
|
||||
type NopResetter struct{}
|
||||
|
||||
// Reset implements the Reset method of the Transformer interface.
|
||||
func (NopResetter) Reset() {}
|
||||
|
||||
// Reader wraps another io.Reader by transforming the bytes read.
|
||||
type Reader struct {
|
||||
r io.Reader
|
||||
t Transformer
|
||||
err error
|
||||
|
||||
// dst[dst0:dst1] contains bytes that have been transformed by t but
|
||||
// not yet copied out via Read.
|
||||
dst []byte
|
||||
dst0, dst1 int
|
||||
|
||||
// src[src0:src1] contains bytes that have been read from r but not
|
||||
// yet transformed through t.
|
||||
src []byte
|
||||
src0, src1 int
|
||||
|
||||
// transformComplete is whether the transformation is complete,
|
||||
// regardless of whether or not it was successful.
|
||||
transformComplete bool
|
||||
}
|
||||
|
||||
const defaultBufSize = 4096
|
||||
|
||||
// NewReader returns a new Reader that wraps r by transforming the bytes read
|
||||
// via t. It calls Reset on t.
|
||||
func NewReader(r io.Reader, t Transformer) *Reader {
|
||||
t.Reset()
|
||||
return &Reader{
|
||||
r: r,
|
||||
t: t,
|
||||
dst: make([]byte, defaultBufSize),
|
||||
src: make([]byte, defaultBufSize),
|
||||
}
|
||||
}
|
||||
|
||||
// Read implements the io.Reader interface.
|
||||
func (r *Reader) Read(p []byte) (int, error) {
|
||||
n, err := 0, error(nil)
|
||||
for {
|
||||
// Copy out any transformed bytes and return the final error if we are done.
|
||||
if r.dst0 != r.dst1 {
|
||||
n = copy(p, r.dst[r.dst0:r.dst1])
|
||||
r.dst0 += n
|
||||
if r.dst0 == r.dst1 && r.transformComplete {
|
||||
return n, r.err
|
||||
}
|
||||
return n, nil
|
||||
} else if r.transformComplete {
|
||||
return 0, r.err
|
||||
}
|
||||
|
||||
// Try to transform some source bytes, or to flush the transformer if we
|
||||
// are out of source bytes. We do this even if r.r.Read returned an error.
|
||||
// As the io.Reader documentation says, "process the n > 0 bytes returned
|
||||
// before considering the error".
|
||||
if r.src0 != r.src1 || r.err != nil {
|
||||
r.dst0 = 0
|
||||
r.dst1, n, err = r.t.Transform(r.dst, r.src[r.src0:r.src1], r.err == io.EOF)
|
||||
r.src0 += n
|
||||
|
||||
switch {
|
||||
case err == nil:
|
||||
if r.src0 != r.src1 {
|
||||
r.err = errInconsistentByteCount
|
||||
}
|
||||
// The Transform call was successful; we are complete if we
|
||||
// cannot read more bytes into src.
|
||||
r.transformComplete = r.err != nil
|
||||
continue
|
||||
case err == ErrShortDst && (r.dst1 != 0 || n != 0):
|
||||
// Make room in dst by copying out, and try again.
|
||||
continue
|
||||
case err == ErrShortSrc && r.src1-r.src0 != len(r.src) && r.err == nil:
|
||||
// Read more bytes into src via the code below, and try again.
|
||||
default:
|
||||
r.transformComplete = true
|
||||
// The reader error (r.err) takes precedence over the
|
||||
// transformer error (err) unless r.err is nil or io.EOF.
|
||||
if r.err == nil || r.err == io.EOF {
|
||||
r.err = err
|
||||
}
|
||||
continue
|
||||
}
|
||||
}
|
||||
|
||||
// Move any untransformed source bytes to the start of the buffer
|
||||
// and read more bytes.
|
||||
if r.src0 != 0 {
|
||||
r.src0, r.src1 = 0, copy(r.src, r.src[r.src0:r.src1])
|
||||
}
|
||||
n, r.err = r.r.Read(r.src[r.src1:])
|
||||
r.src1 += n
|
||||
}
|
||||
}
|
||||
|
||||
// TODO: implement ReadByte (and ReadRune??).
|
||||
|
||||
// Writer wraps another io.Writer by transforming the bytes read.
|
||||
// The user needs to call Close to flush unwritten bytes that may
|
||||
// be buffered.
|
||||
type Writer struct {
|
||||
w io.Writer
|
||||
t Transformer
|
||||
dst []byte
|
||||
|
||||
// src[:n] contains bytes that have not yet passed through t.
|
||||
src []byte
|
||||
n int
|
||||
}
|
||||
|
||||
// NewWriter returns a new Writer that wraps w by transforming the bytes written
|
||||
// via t. It calls Reset on t.
|
||||
func NewWriter(w io.Writer, t Transformer) *Writer {
|
||||
t.Reset()
|
||||
return &Writer{
|
||||
w: w,
|
||||
t: t,
|
||||
dst: make([]byte, defaultBufSize),
|
||||
src: make([]byte, defaultBufSize),
|
||||
}
|
||||
}
|
||||
|
||||
// Write implements the io.Writer interface. If there are not enough
|
||||
// bytes available to complete a Transform, the bytes will be buffered
|
||||
// for the next write. Call Close to convert the remaining bytes.
|
||||
func (w *Writer) Write(data []byte) (n int, err error) {
|
||||
src := data
|
||||
if w.n > 0 {
|
||||
// Append bytes from data to the last remainder.
|
||||
// TODO: limit the amount copied on first try.
|
||||
n = copy(w.src[w.n:], data)
|
||||
w.n += n
|
||||
src = w.src[:w.n]
|
||||
}
|
||||
for {
|
||||
nDst, nSrc, err := w.t.Transform(w.dst, src, false)
|
||||
if _, werr := w.w.Write(w.dst[:nDst]); werr != nil {
|
||||
return n, werr
|
||||
}
|
||||
src = src[nSrc:]
|
||||
if w.n == 0 {
|
||||
n += nSrc
|
||||
} else if len(src) <= n {
|
||||
// Enough bytes from w.src have been consumed. We make src point
|
||||
// to data instead to reduce the copying.
|
||||
w.n = 0
|
||||
n -= len(src)
|
||||
src = data[n:]
|
||||
if n < len(data) && (err == nil || err == ErrShortSrc) {
|
||||
continue
|
||||
}
|
||||
}
|
||||
switch err {
|
||||
case ErrShortDst:
|
||||
// This error is okay as long as we are making progress.
|
||||
if nDst > 0 || nSrc > 0 {
|
||||
continue
|
||||
}
|
||||
case ErrShortSrc:
|
||||
if len(src) < len(w.src) {
|
||||
m := copy(w.src, src)
|
||||
// If w.n > 0, bytes from data were already copied to w.src and n
|
||||
// was already set to the number of bytes consumed.
|
||||
if w.n == 0 {
|
||||
n += m
|
||||
}
|
||||
w.n = m
|
||||
err = nil
|
||||
} else if nDst > 0 || nSrc > 0 {
|
||||
// Not enough buffer to store the remainder. Keep processing as
|
||||
// long as there is progress. Without this case, transforms that
|
||||
// require a lookahead larger than the buffer may result in an
|
||||
// error. This is not something one may expect to be common in
|
||||
// practice, but it may occur when buffers are set to small
|
||||
// sizes during testing.
|
||||
continue
|
||||
}
|
||||
case nil:
|
||||
if w.n > 0 {
|
||||
err = errInconsistentByteCount
|
||||
}
|
||||
}
|
||||
return n, err
|
||||
}
|
||||
}
|
||||
|
||||
// Close implements the io.Closer interface.
|
||||
func (w *Writer) Close() error {
|
||||
src := w.src[:w.n]
|
||||
for {
|
||||
nDst, nSrc, err := w.t.Transform(w.dst, src, true)
|
||||
if _, werr := w.w.Write(w.dst[:nDst]); werr != nil {
|
||||
return werr
|
||||
}
|
||||
if err != ErrShortDst {
|
||||
return err
|
||||
}
|
||||
src = src[nSrc:]
|
||||
}
|
||||
}
|
||||
|
||||
type nop struct{ NopResetter }
|
||||
|
||||
func (nop) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
n := copy(dst, src)
|
||||
if n < len(src) {
|
||||
err = ErrShortDst
|
||||
}
|
||||
return n, n, err
|
||||
}
|
||||
|
||||
func (nop) Span(src []byte, atEOF bool) (n int, err error) {
|
||||
return len(src), nil
|
||||
}
|
||||
|
||||
type discard struct{ NopResetter }
|
||||
|
||||
func (discard) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
return 0, len(src), nil
|
||||
}
|
||||
|
||||
var (
|
||||
// Discard is a Transformer for which all Transform calls succeed
|
||||
// by consuming all bytes and writing nothing.
|
||||
Discard Transformer = discard{}
|
||||
|
||||
// Nop is a SpanningTransformer that copies src to dst.
|
||||
Nop SpanningTransformer = nop{}
|
||||
)
|
||||
|
||||
// chain is a sequence of links. A chain with N Transformers has N+1 links and
|
||||
// N+1 buffers. Of those N+1 buffers, the first and last are the src and dst
|
||||
// buffers given to chain.Transform and the middle N-1 buffers are intermediate
|
||||
// buffers owned by the chain. The i'th link transforms bytes from the i'th
|
||||
// buffer chain.link[i].b at read offset chain.link[i].p to the i+1'th buffer
|
||||
// chain.link[i+1].b at write offset chain.link[i+1].n, for i in [0, N).
|
||||
type chain struct {
|
||||
link []link
|
||||
err error
|
||||
// errStart is the index at which the error occurred plus 1. Processing
|
||||
// errStart at this level at the next call to Transform. As long as
|
||||
// errStart > 0, chain will not consume any more source bytes.
|
||||
errStart int
|
||||
}
|
||||
|
||||
func (c *chain) fatalError(errIndex int, err error) {
|
||||
if i := errIndex + 1; i > c.errStart {
|
||||
c.errStart = i
|
||||
c.err = err
|
||||
}
|
||||
}
|
||||
|
||||
type link struct {
|
||||
t Transformer
|
||||
// b[p:n] holds the bytes to be transformed by t.
|
||||
b []byte
|
||||
p int
|
||||
n int
|
||||
}
|
||||
|
||||
func (l *link) src() []byte {
|
||||
return l.b[l.p:l.n]
|
||||
}
|
||||
|
||||
func (l *link) dst() []byte {
|
||||
return l.b[l.n:]
|
||||
}
|
||||
|
||||
// Chain returns a Transformer that applies t in sequence.
|
||||
func Chain(t ...Transformer) Transformer {
|
||||
if len(t) == 0 {
|
||||
return nop{}
|
||||
}
|
||||
c := &chain{link: make([]link, len(t)+1)}
|
||||
for i, tt := range t {
|
||||
c.link[i].t = tt
|
||||
}
|
||||
// Allocate intermediate buffers.
|
||||
b := make([][defaultBufSize]byte, len(t)-1)
|
||||
for i := range b {
|
||||
c.link[i+1].b = b[i][:]
|
||||
}
|
||||
return c
|
||||
}
|
||||
|
||||
// Reset resets the state of Chain. It calls Reset on all the Transformers.
|
||||
func (c *chain) Reset() {
|
||||
for i, l := range c.link {
|
||||
if l.t != nil {
|
||||
l.t.Reset()
|
||||
}
|
||||
c.link[i].p, c.link[i].n = 0, 0
|
||||
}
|
||||
}
|
||||
|
||||
// TODO: make chain use Span (is going to be fun to implement!)
|
||||
|
||||
// Transform applies the transformers of c in sequence.
|
||||
func (c *chain) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
// Set up src and dst in the chain.
|
||||
srcL := &c.link[0]
|
||||
dstL := &c.link[len(c.link)-1]
|
||||
srcL.b, srcL.p, srcL.n = src, 0, len(src)
|
||||
dstL.b, dstL.n = dst, 0
|
||||
var lastFull, needProgress bool // for detecting progress
|
||||
|
||||
// i is the index of the next Transformer to apply, for i in [low, high].
|
||||
// low is the lowest index for which c.link[low] may still produce bytes.
|
||||
// high is the highest index for which c.link[high] has a Transformer.
|
||||
// The error returned by Transform determines whether to increase or
|
||||
// decrease i. We try to completely fill a buffer before converting it.
|
||||
for low, i, high := c.errStart, c.errStart, len(c.link)-2; low <= i && i <= high; {
|
||||
in, out := &c.link[i], &c.link[i+1]
|
||||
nDst, nSrc, err0 := in.t.Transform(out.dst(), in.src(), atEOF && low == i)
|
||||
out.n += nDst
|
||||
in.p += nSrc
|
||||
if i > 0 && in.p == in.n {
|
||||
in.p, in.n = 0, 0
|
||||
}
|
||||
needProgress, lastFull = lastFull, false
|
||||
switch err0 {
|
||||
case ErrShortDst:
|
||||
// Process the destination buffer next. Return if we are already
|
||||
// at the high index.
|
||||
if i == high {
|
||||
return dstL.n, srcL.p, ErrShortDst
|
||||
}
|
||||
if out.n != 0 {
|
||||
i++
|
||||
// If the Transformer at the next index is not able to process any
|
||||
// source bytes there is nothing that can be done to make progress
|
||||
// and the bytes will remain unprocessed. lastFull is used to
|
||||
// detect this and break out of the loop with a fatal error.
|
||||
lastFull = true
|
||||
continue
|
||||
}
|
||||
// The destination buffer was too small, but is completely empty.
|
||||
// Return a fatal error as this transformation can never complete.
|
||||
c.fatalError(i, errShortInternal)
|
||||
case ErrShortSrc:
|
||||
if i == 0 {
|
||||
// Save ErrShortSrc in err. All other errors take precedence.
|
||||
err = ErrShortSrc
|
||||
break
|
||||
}
|
||||
// Source bytes were depleted before filling up the destination buffer.
|
||||
// Verify we made some progress, move the remaining bytes to the errStart
|
||||
// and try to get more source bytes.
|
||||
if needProgress && nSrc == 0 || in.n-in.p == len(in.b) {
|
||||
// There were not enough source bytes to proceed while the source
|
||||
// buffer cannot hold any more bytes. Return a fatal error as this
|
||||
// transformation can never complete.
|
||||
c.fatalError(i, errShortInternal)
|
||||
break
|
||||
}
|
||||
// in.b is an internal buffer and we can make progress.
|
||||
in.p, in.n = 0, copy(in.b, in.src())
|
||||
fallthrough
|
||||
case nil:
|
||||
// if i == low, we have depleted the bytes at index i or any lower levels.
|
||||
// In that case we increase low and i. In all other cases we decrease i to
|
||||
// fetch more bytes before proceeding to the next index.
|
||||
if i > low {
|
||||
i--
|
||||
continue
|
||||
}
|
||||
default:
|
||||
c.fatalError(i, err0)
|
||||
}
|
||||
// Exhausted level low or fatal error: increase low and continue
|
||||
// to process the bytes accepted so far.
|
||||
i++
|
||||
low = i
|
||||
}
|
||||
|
||||
// If c.errStart > 0, this means we found a fatal error. We will clear
|
||||
// all upstream buffers. At this point, no more progress can be made
|
||||
// downstream, as Transform would have bailed while handling ErrShortDst.
|
||||
if c.errStart > 0 {
|
||||
for i := 1; i < c.errStart; i++ {
|
||||
c.link[i].p, c.link[i].n = 0, 0
|
||||
}
|
||||
err, c.errStart, c.err = c.err, 0, nil
|
||||
}
|
||||
return dstL.n, srcL.p, err
|
||||
}
|
||||
|
||||
// Deprecated: use runes.Remove instead.
|
||||
func RemoveFunc(f func(r rune) bool) Transformer {
|
||||
return removeF(f)
|
||||
}
|
||||
|
||||
type removeF func(r rune) bool
|
||||
|
||||
func (removeF) Reset() {}
|
||||
|
||||
// Transform implements the Transformer interface.
|
||||
func (t removeF) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
for r, sz := rune(0), 0; len(src) > 0; src = src[sz:] {
|
||||
|
||||
if r = rune(src[0]); r < utf8.RuneSelf {
|
||||
sz = 1
|
||||
} else {
|
||||
r, sz = utf8.DecodeRune(src)
|
||||
|
||||
if sz == 1 {
|
||||
// Invalid rune.
|
||||
if !atEOF && !utf8.FullRune(src) {
|
||||
err = ErrShortSrc
|
||||
break
|
||||
}
|
||||
// We replace illegal bytes with RuneError. Not doing so might
|
||||
// otherwise turn a sequence of invalid UTF-8 into valid UTF-8.
|
||||
// The resulting byte sequence may subsequently contain runes
|
||||
// for which t(r) is true that were passed unnoticed.
|
||||
if !t(r) {
|
||||
if nDst+3 > len(dst) {
|
||||
err = ErrShortDst
|
||||
break
|
||||
}
|
||||
nDst += copy(dst[nDst:], "\uFFFD")
|
||||
}
|
||||
nSrc++
|
||||
continue
|
||||
}
|
||||
}
|
||||
|
||||
if !t(r) {
|
||||
if nDst+sz > len(dst) {
|
||||
err = ErrShortDst
|
||||
break
|
||||
}
|
||||
nDst += copy(dst[nDst:], src[:sz])
|
||||
}
|
||||
nSrc += sz
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
// grow returns a new []byte that is longer than b, and copies the first n bytes
|
||||
// of b to the start of the new slice.
|
||||
func grow(b []byte, n int) []byte {
|
||||
m := len(b)
|
||||
if m <= 32 {
|
||||
m = 64
|
||||
} else if m <= 256 {
|
||||
m *= 2
|
||||
} else {
|
||||
m += m >> 1
|
||||
}
|
||||
buf := make([]byte, m)
|
||||
copy(buf, b[:n])
|
||||
return buf
|
||||
}
|
||||
|
||||
const initialBufSize = 128
|
||||
|
||||
// String returns a string with the result of converting s[:n] using t, where
|
||||
// n <= len(s). If err == nil, n will be len(s). It calls Reset on t.
|
||||
func String(t Transformer, s string) (result string, n int, err error) {
|
||||
t.Reset()
|
||||
if s == "" {
|
||||
// Fast path for the common case for empty input. Results in about a
|
||||
// 86% reduction of running time for BenchmarkStringLowerEmpty.
|
||||
if _, _, err := t.Transform(nil, nil, true); err == nil {
|
||||
return "", 0, nil
|
||||
}
|
||||
}
|
||||
|
||||
// Allocate only once. Note that both dst and src escape when passed to
|
||||
// Transform.
|
||||
buf := [2 * initialBufSize]byte{}
|
||||
dst := buf[:initialBufSize:initialBufSize]
|
||||
src := buf[initialBufSize : 2*initialBufSize]
|
||||
|
||||
// The input string s is transformed in multiple chunks (starting with a
|
||||
// chunk size of initialBufSize). nDst and nSrc are per-chunk (or
|
||||
// per-Transform-call) indexes, pDst and pSrc are overall indexes.
|
||||
nDst, nSrc := 0, 0
|
||||
pDst, pSrc := 0, 0
|
||||
|
||||
// pPrefix is the length of a common prefix: the first pPrefix bytes of the
|
||||
// result will equal the first pPrefix bytes of s. It is not guaranteed to
|
||||
// be the largest such value, but if pPrefix, len(result) and len(s) are
|
||||
// all equal after the final transform (i.e. calling Transform with atEOF
|
||||
// being true returned nil error) then we don't need to allocate a new
|
||||
// result string.
|
||||
pPrefix := 0
|
||||
for {
|
||||
// Invariant: pDst == pPrefix && pSrc == pPrefix.
|
||||
|
||||
n := copy(src, s[pSrc:])
|
||||
nDst, nSrc, err = t.Transform(dst, src[:n], pSrc+n == len(s))
|
||||
pDst += nDst
|
||||
pSrc += nSrc
|
||||
|
||||
// TODO: let transformers implement an optional Spanner interface, akin
|
||||
// to norm's QuickSpan. This would even allow us to avoid any allocation.
|
||||
if !bytes.Equal(dst[:nDst], src[:nSrc]) {
|
||||
break
|
||||
}
|
||||
pPrefix = pSrc
|
||||
if err == ErrShortDst {
|
||||
// A buffer can only be short if a transformer modifies its input.
|
||||
break
|
||||
} else if err == ErrShortSrc {
|
||||
if nSrc == 0 {
|
||||
// No progress was made.
|
||||
break
|
||||
}
|
||||
// Equal so far and !atEOF, so continue checking.
|
||||
} else if err != nil || pPrefix == len(s) {
|
||||
return string(s[:pPrefix]), pPrefix, err
|
||||
}
|
||||
}
|
||||
// Post-condition: pDst == pPrefix + nDst && pSrc == pPrefix + nSrc.
|
||||
|
||||
// We have transformed the first pSrc bytes of the input s to become pDst
|
||||
// transformed bytes. Those transformed bytes are discontiguous: the first
|
||||
// pPrefix of them equal s[:pPrefix] and the last nDst of them equal
|
||||
// dst[:nDst]. We copy them around, into a new dst buffer if necessary, so
|
||||
// that they become one contiguous slice: dst[:pDst].
|
||||
if pPrefix != 0 {
|
||||
newDst := dst
|
||||
if pDst > len(newDst) {
|
||||
newDst = make([]byte, len(s)+nDst-nSrc)
|
||||
}
|
||||
copy(newDst[pPrefix:pDst], dst[:nDst])
|
||||
copy(newDst[:pPrefix], s[:pPrefix])
|
||||
dst = newDst
|
||||
}
|
||||
|
||||
// Prevent duplicate Transform calls with atEOF being true at the end of
|
||||
// the input. Also return if we have an unrecoverable error.
|
||||
if (err == nil && pSrc == len(s)) ||
|
||||
(err != nil && err != ErrShortDst && err != ErrShortSrc) {
|
||||
return string(dst[:pDst]), pSrc, err
|
||||
}
|
||||
|
||||
// Transform the remaining input, growing dst and src buffers as necessary.
|
||||
for {
|
||||
n := copy(src, s[pSrc:])
|
||||
nDst, nSrc, err := t.Transform(dst[pDst:], src[:n], pSrc+n == len(s))
|
||||
pDst += nDst
|
||||
pSrc += nSrc
|
||||
|
||||
// If we got ErrShortDst or ErrShortSrc, do not grow as long as we can
|
||||
// make progress. This may avoid excessive allocations.
|
||||
if err == ErrShortDst {
|
||||
if nDst == 0 {
|
||||
dst = grow(dst, pDst)
|
||||
}
|
||||
} else if err == ErrShortSrc {
|
||||
if nSrc == 0 {
|
||||
src = grow(src, 0)
|
||||
}
|
||||
} else if err != nil || pSrc == len(s) {
|
||||
return string(dst[:pDst]), pSrc, err
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Bytes returns a new byte slice with the result of converting b[:n] using t,
|
||||
// where n <= len(b). If err == nil, n will be len(b). It calls Reset on t.
|
||||
func Bytes(t Transformer, b []byte) (result []byte, n int, err error) {
|
||||
return doAppend(t, 0, make([]byte, len(b)), b)
|
||||
}
|
||||
|
||||
// Append appends the result of converting src[:n] using t to dst, where
|
||||
// n <= len(src), If err == nil, n will be len(src). It calls Reset on t.
|
||||
func Append(t Transformer, dst, src []byte) (result []byte, n int, err error) {
|
||||
if len(dst) == cap(dst) {
|
||||
n := len(src) + len(dst) // It is okay for this to be 0.
|
||||
b := make([]byte, n)
|
||||
dst = b[:copy(b, dst)]
|
||||
}
|
||||
return doAppend(t, len(dst), dst[:cap(dst)], src)
|
||||
}
|
||||
|
||||
func doAppend(t Transformer, pDst int, dst, src []byte) (result []byte, n int, err error) {
|
||||
t.Reset()
|
||||
pSrc := 0
|
||||
for {
|
||||
nDst, nSrc, err := t.Transform(dst[pDst:], src[pSrc:], true)
|
||||
pDst += nDst
|
||||
pSrc += nSrc
|
||||
if err != ErrShortDst {
|
||||
return dst[:pDst], pSrc, err
|
||||
}
|
||||
|
||||
// Grow the destination buffer, but do not grow as long as we can make
|
||||
// progress. This may avoid excessive allocations.
|
||||
if nDst == 0 {
|
||||
dst = grow(dst, pDst)
|
||||
}
|
||||
}
|
||||
}
|
|
@ -0,0 +1,100 @@
|
|||
// 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 cldr
|
||||
|
||||
import (
|
||||
"encoding/xml"
|
||||
"regexp"
|
||||
"strconv"
|
||||
)
|
||||
|
||||
// Elem is implemented by every XML element.
|
||||
type Elem interface {
|
||||
setEnclosing(Elem)
|
||||
setName(string)
|
||||
enclosing() Elem
|
||||
|
||||
GetCommon() *Common
|
||||
}
|
||||
|
||||
type hidden struct {
|
||||
CharData string `xml:",chardata"`
|
||||
Alias *struct {
|
||||
Common
|
||||
Source string `xml:"source,attr"`
|
||||
Path string `xml:"path,attr"`
|
||||
} `xml:"alias"`
|
||||
Def *struct {
|
||||
Common
|
||||
Choice string `xml:"choice,attr,omitempty"`
|
||||
Type string `xml:"type,attr,omitempty"`
|
||||
} `xml:"default"`
|
||||
}
|
||||
|
||||
// Common holds several of the most common attributes and sub elements
|
||||
// of an XML element.
|
||||
type Common struct {
|
||||
XMLName xml.Name
|
||||
name string
|
||||
enclElem Elem
|
||||
Type string `xml:"type,attr,omitempty"`
|
||||
Reference string `xml:"reference,attr,omitempty"`
|
||||
Alt string `xml:"alt,attr,omitempty"`
|
||||
ValidSubLocales string `xml:"validSubLocales,attr,omitempty"`
|
||||
Draft string `xml:"draft,attr,omitempty"`
|
||||
hidden
|
||||
}
|
||||
|
||||
// Default returns the default type to select from the enclosed list
|
||||
// or "" if no default value is specified.
|
||||
func (e *Common) Default() string {
|
||||
if e.Def == nil {
|
||||
return ""
|
||||
}
|
||||
if e.Def.Choice != "" {
|
||||
return e.Def.Choice
|
||||
} else if e.Def.Type != "" {
|
||||
// Type is still used by the default element in collation.
|
||||
return e.Def.Type
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// GetCommon returns e. It is provided such that Common implements Elem.
|
||||
func (e *Common) GetCommon() *Common {
|
||||
return e
|
||||
}
|
||||
|
||||
// Data returns the character data accumulated for this element.
|
||||
func (e *Common) Data() string {
|
||||
e.CharData = charRe.ReplaceAllStringFunc(e.CharData, replaceUnicode)
|
||||
return e.CharData
|
||||
}
|
||||
|
||||
func (e *Common) setName(s string) {
|
||||
e.name = s
|
||||
}
|
||||
|
||||
func (e *Common) enclosing() Elem {
|
||||
return e.enclElem
|
||||
}
|
||||
|
||||
func (e *Common) setEnclosing(en Elem) {
|
||||
e.enclElem = en
|
||||
}
|
||||
|
||||
// Escape characters that can be escaped without further escaping the string.
|
||||
var charRe = regexp.MustCompile(`&#x[0-9a-fA-F]*;|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}|\\x[0-9a-fA-F]{2}|\\[0-7]{3}|\\[abtnvfr]`)
|
||||
|
||||
// replaceUnicode converts hexadecimal Unicode codepoint notations to a one-rune string.
|
||||
// It assumes the input string is correctly formatted.
|
||||
func replaceUnicode(s string) string {
|
||||
if s[1] == '#' {
|
||||
r, _ := strconv.ParseInt(s[3:len(s)-1], 16, 32)
|
||||
return string(r)
|
||||
}
|
||||
r, _, _, _ := strconv.UnquoteChar(s, 0)
|
||||
return string(r)
|
||||
}
|
|
@ -0,0 +1,130 @@
|
|||
// Copyright 2013 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
//go:generate go run makexml.go -output xml.go
|
||||
|
||||
// Package cldr provides a parser for LDML and related XML formats.
|
||||
// This package is intended to be used by the table generation tools
|
||||
// for the various internationalization-related packages.
|
||||
// As the XML types are generated from the CLDR DTD, and as the CLDR standard
|
||||
// is periodically amended, this package may change considerably over time.
|
||||
// This mostly means that data may appear and disappear between versions.
|
||||
// That is, old code should keep compiling for newer versions, but data
|
||||
// may have moved or changed.
|
||||
// CLDR version 22 is the first version supported by this package.
|
||||
// Older versions may not work.
|
||||
package cldr // import "golang.org/x/text/unicode/cldr"
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"sort"
|
||||
)
|
||||
|
||||
// CLDR provides access to parsed data of the Unicode Common Locale Data Repository.
|
||||
type CLDR struct {
|
||||
parent map[string][]string
|
||||
locale map[string]*LDML
|
||||
resolved map[string]*LDML
|
||||
bcp47 *LDMLBCP47
|
||||
supp *SupplementalData
|
||||
}
|
||||
|
||||
func makeCLDR() *CLDR {
|
||||
return &CLDR{
|
||||
parent: make(map[string][]string),
|
||||
locale: make(map[string]*LDML),
|
||||
resolved: make(map[string]*LDML),
|
||||
bcp47: &LDMLBCP47{},
|
||||
supp: &SupplementalData{},
|
||||
}
|
||||
}
|
||||
|
||||
// BCP47 returns the parsed BCP47 LDML data. If no such data was parsed, nil is returned.
|
||||
func (cldr *CLDR) BCP47() *LDMLBCP47 {
|
||||
return nil
|
||||
}
|
||||
|
||||
// Draft indicates the draft level of an element.
|
||||
type Draft int
|
||||
|
||||
const (
|
||||
Approved Draft = iota
|
||||
Contributed
|
||||
Provisional
|
||||
Unconfirmed
|
||||
)
|
||||
|
||||
var drafts = []string{"unconfirmed", "provisional", "contributed", "approved", ""}
|
||||
|
||||
// ParseDraft returns the Draft value corresponding to the given string. The
|
||||
// empty string corresponds to Approved.
|
||||
func ParseDraft(level string) (Draft, error) {
|
||||
if level == "" {
|
||||
return Approved, nil
|
||||
}
|
||||
for i, s := range drafts {
|
||||
if level == s {
|
||||
return Unconfirmed - Draft(i), nil
|
||||
}
|
||||
}
|
||||
return Approved, fmt.Errorf("cldr: unknown draft level %q", level)
|
||||
}
|
||||
|
||||
func (d Draft) String() string {
|
||||
return drafts[len(drafts)-1-int(d)]
|
||||
}
|
||||
|
||||
// SetDraftLevel sets which draft levels to include in the evaluated LDML.
|
||||
// Any draft element for which the draft level is higher than lev will be excluded.
|
||||
// If multiple draft levels are available for a single element, the one with the
|
||||
// lowest draft level will be selected, unless preferDraft is true, in which case
|
||||
// the highest draft will be chosen.
|
||||
// It is assumed that the underlying LDML is canonicalized.
|
||||
func (cldr *CLDR) SetDraftLevel(lev Draft, preferDraft bool) {
|
||||
// TODO: implement
|
||||
cldr.resolved = make(map[string]*LDML)
|
||||
}
|
||||
|
||||
// RawLDML returns the LDML XML for id in unresolved form.
|
||||
// id must be one of the strings returned by Locales.
|
||||
func (cldr *CLDR) RawLDML(loc string) *LDML {
|
||||
return cldr.locale[loc]
|
||||
}
|
||||
|
||||
// LDML returns the fully resolved LDML XML for loc, which must be one of
|
||||
// the strings returned by Locales.
|
||||
func (cldr *CLDR) LDML(loc string) (*LDML, error) {
|
||||
return cldr.resolve(loc)
|
||||
}
|
||||
|
||||
// Supplemental returns the parsed supplemental data. If no such data was parsed,
|
||||
// nil is returned.
|
||||
func (cldr *CLDR) Supplemental() *SupplementalData {
|
||||
return cldr.supp
|
||||
}
|
||||
|
||||
// Locales returns the locales for which there exist files.
|
||||
// Valid sublocales for which there is no file are not included.
|
||||
// The root locale is always sorted first.
|
||||
func (cldr *CLDR) Locales() []string {
|
||||
loc := []string{"root"}
|
||||
hasRoot := false
|
||||
for l, _ := range cldr.locale {
|
||||
if l == "root" {
|
||||
hasRoot = true
|
||||
continue
|
||||
}
|
||||
loc = append(loc, l)
|
||||
}
|
||||
sort.Strings(loc[1:])
|
||||
if !hasRoot {
|
||||
return loc[1:]
|
||||
}
|
||||
return loc
|
||||
}
|
||||
|
||||
// Get fills in the fields of x based on the XPath path.
|
||||
func Get(e Elem, path string) (res Elem, err error) {
|
||||
return walkXPath(e, path)
|
||||
}
|
|
@ -0,0 +1,359 @@
|
|||
// 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 cldr
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"encoding/xml"
|
||||
"errors"
|
||||
"fmt"
|
||||
"strconv"
|
||||
"strings"
|
||||
"unicode"
|
||||
"unicode/utf8"
|
||||
)
|
||||
|
||||
// RuleProcessor can be passed to Collator's Process method, which
|
||||
// parses the rules and calls the respective method for each rule found.
|
||||
type RuleProcessor interface {
|
||||
Reset(anchor string, before int) error
|
||||
Insert(level int, str, context, extend string) error
|
||||
Index(id string)
|
||||
}
|
||||
|
||||
const (
|
||||
// cldrIndex is a Unicode-reserved sentinel value used to mark the start
|
||||
// of a grouping within an index.
|
||||
// We ignore any rule that starts with this rune.
|
||||
// See http://unicode.org/reports/tr35/#Collation_Elements for details.
|
||||
cldrIndex = "\uFDD0"
|
||||
|
||||
// specialAnchor is the format in which to represent logical reset positions,
|
||||
// such as "first tertiary ignorable".
|
||||
specialAnchor = "<%s/>"
|
||||
)
|
||||
|
||||
// Process parses the rules for the tailorings of this collation
|
||||
// and calls the respective methods of p for each rule found.
|
||||
func (c Collation) Process(p RuleProcessor) (err error) {
|
||||
if len(c.Cr) > 0 {
|
||||
if len(c.Cr) > 1 {
|
||||
return fmt.Errorf("multiple cr elements, want 0 or 1")
|
||||
}
|
||||
return processRules(p, c.Cr[0].Data())
|
||||
}
|
||||
if c.Rules.Any != nil {
|
||||
return c.processXML(p)
|
||||
}
|
||||
return errors.New("no tailoring data")
|
||||
}
|
||||
|
||||
// processRules parses rules in the Collation Rule Syntax defined in
|
||||
// http://www.unicode.org/reports/tr35/tr35-collation.html#Collation_Tailorings.
|
||||
func processRules(p RuleProcessor, s string) (err error) {
|
||||
chk := func(s string, e error) string {
|
||||
if err == nil {
|
||||
err = e
|
||||
}
|
||||
return s
|
||||
}
|
||||
i := 0 // Save the line number for use after the loop.
|
||||
scanner := bufio.NewScanner(strings.NewReader(s))
|
||||
for ; scanner.Scan() && err == nil; i++ {
|
||||
for s := skipSpace(scanner.Text()); s != "" && s[0] != '#'; s = skipSpace(s) {
|
||||
level := 5
|
||||
var ch byte
|
||||
switch ch, s = s[0], s[1:]; ch {
|
||||
case '&': // followed by <anchor> or '[' <key> ']'
|
||||
if s = skipSpace(s); consume(&s, '[') {
|
||||
s = chk(parseSpecialAnchor(p, s))
|
||||
} else {
|
||||
s = chk(parseAnchor(p, 0, s))
|
||||
}
|
||||
case '<': // sort relation '<'{1,4}, optionally followed by '*'.
|
||||
for level = 1; consume(&s, '<'); level++ {
|
||||
}
|
||||
if level > 4 {
|
||||
err = fmt.Errorf("level %d > 4", level)
|
||||
}
|
||||
fallthrough
|
||||
case '=': // identity relation, optionally followed by *.
|
||||
if consume(&s, '*') {
|
||||
s = chk(parseSequence(p, level, s))
|
||||
} else {
|
||||
s = chk(parseOrder(p, level, s))
|
||||
}
|
||||
default:
|
||||
chk("", fmt.Errorf("illegal operator %q", ch))
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
if chk("", scanner.Err()); err != nil {
|
||||
return fmt.Errorf("%d: %v", i, err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// parseSpecialAnchor parses the anchor syntax which is either of the form
|
||||
// ['before' <level>] <anchor>
|
||||
// or
|
||||
// [<label>]
|
||||
// The starting should already be consumed.
|
||||
func parseSpecialAnchor(p RuleProcessor, s string) (tail string, err error) {
|
||||
i := strings.IndexByte(s, ']')
|
||||
if i == -1 {
|
||||
return "", errors.New("unmatched bracket")
|
||||
}
|
||||
a := strings.TrimSpace(s[:i])
|
||||
s = s[i+1:]
|
||||
if strings.HasPrefix(a, "before ") {
|
||||
l, err := strconv.ParseUint(skipSpace(a[len("before "):]), 10, 3)
|
||||
if err != nil {
|
||||
return s, err
|
||||
}
|
||||
return parseAnchor(p, int(l), s)
|
||||
}
|
||||
return s, p.Reset(fmt.Sprintf(specialAnchor, a), 0)
|
||||
}
|
||||
|
||||
func parseAnchor(p RuleProcessor, level int, s string) (tail string, err error) {
|
||||
anchor, s, err := scanString(s)
|
||||
if err != nil {
|
||||
return s, err
|
||||
}
|
||||
return s, p.Reset(anchor, level)
|
||||
}
|
||||
|
||||
func parseOrder(p RuleProcessor, level int, s string) (tail string, err error) {
|
||||
var value, context, extend string
|
||||
if value, s, err = scanString(s); err != nil {
|
||||
return s, err
|
||||
}
|
||||
if strings.HasPrefix(value, cldrIndex) {
|
||||
p.Index(value[len(cldrIndex):])
|
||||
return
|
||||
}
|
||||
if consume(&s, '|') {
|
||||
if context, s, err = scanString(s); err != nil {
|
||||
return s, errors.New("missing string after context")
|
||||
}
|
||||
}
|
||||
if consume(&s, '/') {
|
||||
if extend, s, err = scanString(s); err != nil {
|
||||
return s, errors.New("missing string after extension")
|
||||
}
|
||||
}
|
||||
return s, p.Insert(level, value, context, extend)
|
||||
}
|
||||
|
||||
// scanString scans a single input string.
|
||||
func scanString(s string) (str, tail string, err error) {
|
||||
if s = skipSpace(s); s == "" {
|
||||
return s, s, errors.New("missing string")
|
||||
}
|
||||
buf := [16]byte{} // small but enough to hold most cases.
|
||||
value := buf[:0]
|
||||
for s != "" {
|
||||
if consume(&s, '\'') {
|
||||
i := strings.IndexByte(s, '\'')
|
||||
if i == -1 {
|
||||
return "", "", errors.New(`unmatched single quote`)
|
||||
}
|
||||
if i == 0 {
|
||||
value = append(value, '\'')
|
||||
} else {
|
||||
value = append(value, s[:i]...)
|
||||
}
|
||||
s = s[i+1:]
|
||||
continue
|
||||
}
|
||||
r, sz := utf8.DecodeRuneInString(s)
|
||||
if unicode.IsSpace(r) || strings.ContainsRune("&<=#", r) {
|
||||
break
|
||||
}
|
||||
value = append(value, s[:sz]...)
|
||||
s = s[sz:]
|
||||
}
|
||||
return string(value), skipSpace(s), nil
|
||||
}
|
||||
|
||||
func parseSequence(p RuleProcessor, level int, s string) (tail string, err error) {
|
||||
if s = skipSpace(s); s == "" {
|
||||
return s, errors.New("empty sequence")
|
||||
}
|
||||
last := rune(0)
|
||||
for s != "" {
|
||||
r, sz := utf8.DecodeRuneInString(s)
|
||||
s = s[sz:]
|
||||
|
||||
if r == '-' {
|
||||
// We have a range. The first element was already written.
|
||||
if last == 0 {
|
||||
return s, errors.New("range without starter value")
|
||||
}
|
||||
r, sz = utf8.DecodeRuneInString(s)
|
||||
s = s[sz:]
|
||||
if r == utf8.RuneError || r < last {
|
||||
return s, fmt.Errorf("invalid range %q-%q", last, r)
|
||||
}
|
||||
for i := last + 1; i <= r; i++ {
|
||||
if err := p.Insert(level, string(i), "", ""); err != nil {
|
||||
return s, err
|
||||
}
|
||||
}
|
||||
last = 0
|
||||
continue
|
||||
}
|
||||
|
||||
if unicode.IsSpace(r) || unicode.IsPunct(r) {
|
||||
break
|
||||
}
|
||||
|
||||
// normal case
|
||||
if err := p.Insert(level, string(r), "", ""); err != nil {
|
||||
return s, err
|
||||
}
|
||||
last = r
|
||||
}
|
||||
return s, nil
|
||||
}
|
||||
|
||||
func skipSpace(s string) string {
|
||||
return strings.TrimLeftFunc(s, unicode.IsSpace)
|
||||
}
|
||||
|
||||
// consumes returns whether the next byte is ch. If so, it gobbles it by
|
||||
// updating s.
|
||||
func consume(s *string, ch byte) (ok bool) {
|
||||
if *s == "" || (*s)[0] != ch {
|
||||
return false
|
||||
}
|
||||
*s = (*s)[1:]
|
||||
return true
|
||||
}
|
||||
|
||||
// The following code parses Collation rules of CLDR version 24 and before.
|
||||
|
||||
var lmap = map[byte]int{
|
||||
'p': 1,
|
||||
's': 2,
|
||||
't': 3,
|
||||
'i': 5,
|
||||
}
|
||||
|
||||
type rulesElem struct {
|
||||
Rules struct {
|
||||
Common
|
||||
Any []*struct {
|
||||
XMLName xml.Name
|
||||
rule
|
||||
} `xml:",any"`
|
||||
} `xml:"rules"`
|
||||
}
|
||||
|
||||
type rule struct {
|
||||
Value string `xml:",chardata"`
|
||||
Before string `xml:"before,attr"`
|
||||
Any []*struct {
|
||||
XMLName xml.Name
|
||||
rule
|
||||
} `xml:",any"`
|
||||
}
|
||||
|
||||
var emptyValueError = errors.New("cldr: empty rule value")
|
||||
|
||||
func (r *rule) value() (string, error) {
|
||||
// Convert hexadecimal Unicode codepoint notation to a string.
|
||||
s := charRe.ReplaceAllStringFunc(r.Value, replaceUnicode)
|
||||
r.Value = s
|
||||
if s == "" {
|
||||
if len(r.Any) != 1 {
|
||||
return "", emptyValueError
|
||||
}
|
||||
r.Value = fmt.Sprintf(specialAnchor, r.Any[0].XMLName.Local)
|
||||
r.Any = nil
|
||||
} else if len(r.Any) != 0 {
|
||||
return "", fmt.Errorf("cldr: XML elements found in collation rule: %v", r.Any)
|
||||
}
|
||||
return r.Value, nil
|
||||
}
|
||||
|
||||
func (r rule) process(p RuleProcessor, name, context, extend string) error {
|
||||
v, err := r.value()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
switch name {
|
||||
case "p", "s", "t", "i":
|
||||
if strings.HasPrefix(v, cldrIndex) {
|
||||
p.Index(v[len(cldrIndex):])
|
||||
return nil
|
||||
}
|
||||
if err := p.Insert(lmap[name[0]], v, context, extend); err != nil {
|
||||
return err
|
||||
}
|
||||
case "pc", "sc", "tc", "ic":
|
||||
level := lmap[name[0]]
|
||||
for _, s := range v {
|
||||
if err := p.Insert(level, string(s), context, extend); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
default:
|
||||
return fmt.Errorf("cldr: unsupported tag: %q", name)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// processXML parses the format of CLDR versions 24 and older.
|
||||
func (c Collation) processXML(p RuleProcessor) (err error) {
|
||||
// Collation is generated and defined in xml.go.
|
||||
var v string
|
||||
for _, r := range c.Rules.Any {
|
||||
switch r.XMLName.Local {
|
||||
case "reset":
|
||||
level := 0
|
||||
switch r.Before {
|
||||
case "primary", "1":
|
||||
level = 1
|
||||
case "secondary", "2":
|
||||
level = 2
|
||||
case "tertiary", "3":
|
||||
level = 3
|
||||
case "":
|
||||
default:
|
||||
return fmt.Errorf("cldr: unknown level %q", r.Before)
|
||||
}
|
||||
v, err = r.value()
|
||||
if err == nil {
|
||||
err = p.Reset(v, level)
|
||||
}
|
||||
case "x":
|
||||
var context, extend string
|
||||
for _, r1 := range r.Any {
|
||||
v, err = r1.value()
|
||||
switch r1.XMLName.Local {
|
||||
case "context":
|
||||
context = v
|
||||
case "extend":
|
||||
extend = v
|
||||
}
|
||||
}
|
||||
for _, r1 := range r.Any {
|
||||
if t := r1.XMLName.Local; t == "context" || t == "extend" {
|
||||
continue
|
||||
}
|
||||
r1.rule.process(p, r1.XMLName.Local, context, extend)
|
||||
}
|
||||
default:
|
||||
err = r.rule.process(p, r.XMLName.Local, "", "")
|
||||
}
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
|
@ -0,0 +1,171 @@
|
|||
// 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 cldr
|
||||
|
||||
import (
|
||||
"archive/zip"
|
||||
"bytes"
|
||||
"encoding/xml"
|
||||
"fmt"
|
||||
"io"
|
||||
"io/ioutil"
|
||||
"log"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"regexp"
|
||||
)
|
||||
|
||||
// A Decoder loads an archive of CLDR data.
|
||||
type Decoder struct {
|
||||
dirFilter []string
|
||||
sectionFilter []string
|
||||
loader Loader
|
||||
cldr *CLDR
|
||||
curLocale string
|
||||
}
|
||||
|
||||
// SetSectionFilter takes a list top-level LDML element names to which
|
||||
// evaluation of LDML should be limited. It automatically calls SetDirFilter.
|
||||
func (d *Decoder) SetSectionFilter(filter ...string) {
|
||||
d.sectionFilter = filter
|
||||
// TODO: automatically set dir filter
|
||||
}
|
||||
|
||||
// SetDirFilter limits the loading of LDML XML files of the specied directories.
|
||||
// Note that sections may be split across directories differently for different CLDR versions.
|
||||
// For more robust code, use SetSectionFilter.
|
||||
func (d *Decoder) SetDirFilter(dir ...string) {
|
||||
d.dirFilter = dir
|
||||
}
|
||||
|
||||
// A Loader provides access to the files of a CLDR archive.
|
||||
type Loader interface {
|
||||
Len() int
|
||||
Path(i int) string
|
||||
Reader(i int) (io.ReadCloser, error)
|
||||
}
|
||||
|
||||
var fileRe = regexp.MustCompile(".*/(.*)/(.*)\\.xml")
|
||||
|
||||
// Decode loads and decodes the files represented by l.
|
||||
func (d *Decoder) Decode(l Loader) (cldr *CLDR, err error) {
|
||||
d.cldr = makeCLDR()
|
||||
for i := 0; i < l.Len(); i++ {
|
||||
fname := l.Path(i)
|
||||
if m := fileRe.FindStringSubmatch(fname); m != nil {
|
||||
if len(d.dirFilter) > 0 && !in(d.dirFilter, m[1]) {
|
||||
continue
|
||||
}
|
||||
var r io.Reader
|
||||
if r, err = l.Reader(i); err == nil {
|
||||
err = d.decode(m[1], m[2], r)
|
||||
}
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
}
|
||||
d.cldr.finalize(d.sectionFilter)
|
||||
return d.cldr, nil
|
||||
}
|
||||
|
||||
func (d *Decoder) decode(dir, id string, r io.Reader) error {
|
||||
var v interface{}
|
||||
var l *LDML
|
||||
cldr := d.cldr
|
||||
switch {
|
||||
case dir == "supplemental":
|
||||
v = cldr.supp
|
||||
case dir == "transforms":
|
||||
return nil
|
||||
case dir == "bcp47":
|
||||
v = cldr.bcp47
|
||||
case dir == "validity":
|
||||
return nil
|
||||
default:
|
||||
ok := false
|
||||
if v, ok = cldr.locale[id]; !ok {
|
||||
l = &LDML{}
|
||||
v, cldr.locale[id] = l, l
|
||||
}
|
||||
}
|
||||
x := xml.NewDecoder(r)
|
||||
if err := x.Decode(v); err != nil {
|
||||
log.Printf("%s/%s: %v", dir, id, err)
|
||||
return err
|
||||
}
|
||||
if l != nil {
|
||||
if l.Identity == nil {
|
||||
return fmt.Errorf("%s/%s: missing identity element", dir, id)
|
||||
}
|
||||
// TODO: verify when CLDR bug http://unicode.org/cldr/trac/ticket/8970
|
||||
// is resolved.
|
||||
// path := strings.Split(id, "_")
|
||||
// if lang := l.Identity.Language.Type; lang != path[0] {
|
||||
// return fmt.Errorf("%s/%s: language was %s; want %s", dir, id, lang, path[0])
|
||||
// }
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type pathLoader []string
|
||||
|
||||
func makePathLoader(path string) (pl pathLoader, err error) {
|
||||
err = filepath.Walk(path, func(path string, _ os.FileInfo, err error) error {
|
||||
pl = append(pl, path)
|
||||
return err
|
||||
})
|
||||
return pl, err
|
||||
}
|
||||
|
||||
func (pl pathLoader) Len() int {
|
||||
return len(pl)
|
||||
}
|
||||
|
||||
func (pl pathLoader) Path(i int) string {
|
||||
return pl[i]
|
||||
}
|
||||
|
||||
func (pl pathLoader) Reader(i int) (io.ReadCloser, error) {
|
||||
return os.Open(pl[i])
|
||||
}
|
||||
|
||||
// DecodePath loads CLDR data from the given path.
|
||||
func (d *Decoder) DecodePath(path string) (cldr *CLDR, err error) {
|
||||
loader, err := makePathLoader(path)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return d.Decode(loader)
|
||||
}
|
||||
|
||||
type zipLoader struct {
|
||||
r *zip.Reader
|
||||
}
|
||||
|
||||
func (zl zipLoader) Len() int {
|
||||
return len(zl.r.File)
|
||||
}
|
||||
|
||||
func (zl zipLoader) Path(i int) string {
|
||||
return zl.r.File[i].Name
|
||||
}
|
||||
|
||||
func (zl zipLoader) Reader(i int) (io.ReadCloser, error) {
|
||||
return zl.r.File[i].Open()
|
||||
}
|
||||
|
||||
// DecodeZip loads CLDR data from the zip archive for which r is the source.
|
||||
func (d *Decoder) DecodeZip(r io.Reader) (cldr *CLDR, err error) {
|
||||
buffer, err := ioutil.ReadAll(r)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
archive, err := zip.NewReader(bytes.NewReader(buffer), int64(len(buffer)))
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return d.Decode(zipLoader{archive})
|
||||
}
|
|
@ -0,0 +1,400 @@
|
|||
// 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.
|
||||
|
||||
// +build ignore
|
||||
|
||||
// This tool generates types for the various XML formats of CLDR.
|
||||
package main
|
||||
|
||||
import (
|
||||
"archive/zip"
|
||||
"bytes"
|
||||
"encoding/xml"
|
||||
"flag"
|
||||
"fmt"
|
||||
"io"
|
||||
"io/ioutil"
|
||||
"log"
|
||||
"os"
|
||||
"regexp"
|
||||
"strings"
|
||||
|
||||
"golang.org/x/text/internal/gen"
|
||||
)
|
||||
|
||||
var outputFile = flag.String("output", "xml.go", "output file name")
|
||||
|
||||
func main() {
|
||||
flag.Parse()
|
||||
|
||||
r := gen.OpenCLDRCoreZip()
|
||||
buffer, err := ioutil.ReadAll(r)
|
||||
if err != nil {
|
||||
log.Fatal("Could not read zip file")
|
||||
}
|
||||
r.Close()
|
||||
z, err := zip.NewReader(bytes.NewReader(buffer), int64(len(buffer)))
|
||||
if err != nil {
|
||||
log.Fatalf("Could not read zip archive: %v", err)
|
||||
}
|
||||
|
||||
var buf bytes.Buffer
|
||||
|
||||
version := gen.CLDRVersion()
|
||||
|
||||
for _, dtd := range files {
|
||||
for _, f := range z.File {
|
||||
if strings.HasSuffix(f.Name, dtd.file+".dtd") {
|
||||
r, err := f.Open()
|
||||
failOnError(err)
|
||||
|
||||
b := makeBuilder(&buf, dtd)
|
||||
b.parseDTD(r)
|
||||
b.resolve(b.index[dtd.top[0]])
|
||||
b.write()
|
||||
if b.version != "" && version != b.version {
|
||||
println(f.Name)
|
||||
log.Fatalf("main: inconsistent versions: found %s; want %s", b.version, version)
|
||||
}
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
fmt.Fprintln(&buf, "// Version is the version of CLDR from which the XML definitions are generated.")
|
||||
fmt.Fprintf(&buf, "const Version = %q\n", version)
|
||||
|
||||
gen.WriteGoFile(*outputFile, "cldr", buf.Bytes())
|
||||
}
|
||||
|
||||
func failOnError(err error) {
|
||||
if err != nil {
|
||||
log.New(os.Stderr, "", log.Lshortfile).Output(2, err.Error())
|
||||
os.Exit(1)
|
||||
}
|
||||
}
|
||||
|
||||
// configuration data per DTD type
|
||||
type dtd struct {
|
||||
file string // base file name
|
||||
root string // Go name of the root XML element
|
||||
top []string // create a different type for this section
|
||||
|
||||
skipElem []string // hard-coded or deprecated elements
|
||||
skipAttr []string // attributes to exclude
|
||||
predefined []string // hard-coded elements exist of the form <name>Elem
|
||||
forceRepeat []string // elements to make slices despite DTD
|
||||
}
|
||||
|
||||
var files = []dtd{
|
||||
{
|
||||
file: "ldmlBCP47",
|
||||
root: "LDMLBCP47",
|
||||
top: []string{"ldmlBCP47"},
|
||||
skipElem: []string{
|
||||
"cldrVersion", // deprecated, not used
|
||||
},
|
||||
},
|
||||
{
|
||||
file: "ldmlSupplemental",
|
||||
root: "SupplementalData",
|
||||
top: []string{"supplementalData"},
|
||||
skipElem: []string{
|
||||
"cldrVersion", // deprecated, not used
|
||||
},
|
||||
forceRepeat: []string{
|
||||
"plurals", // data defined in plurals.xml and ordinals.xml
|
||||
},
|
||||
},
|
||||
{
|
||||
file: "ldml",
|
||||
root: "LDML",
|
||||
top: []string{
|
||||
"ldml", "collation", "calendar", "timeZoneNames", "localeDisplayNames", "numbers",
|
||||
},
|
||||
skipElem: []string{
|
||||
"cp", // not used anywhere
|
||||
"special", // not used anywhere
|
||||
"fallback", // deprecated, not used
|
||||
"alias", // in Common
|
||||
"default", // in Common
|
||||
},
|
||||
skipAttr: []string{
|
||||
"hiraganaQuarternary", // typo in DTD, correct version included as well
|
||||
},
|
||||
predefined: []string{"rules"},
|
||||
},
|
||||
}
|
||||
|
||||
var comments = map[string]string{
|
||||
"ldmlBCP47": `
|
||||
// LDMLBCP47 holds information on allowable values for various variables in LDML.
|
||||
`,
|
||||
"supplementalData": `
|
||||
// SupplementalData holds information relevant for internationalization
|
||||
// and proper use of CLDR, but that is not contained in the locale hierarchy.
|
||||
`,
|
||||
"ldml": `
|
||||
// LDML is the top-level type for locale-specific data.
|
||||
`,
|
||||
"collation": `
|
||||
// Collation contains rules that specify a certain sort-order,
|
||||
// as a tailoring of the root order.
|
||||
// The parsed rules are obtained by passing a RuleProcessor to Collation's
|
||||
// Process method.
|
||||
`,
|
||||
"calendar": `
|
||||
// Calendar specifies the fields used for formatting and parsing dates and times.
|
||||
// The month and quarter names are identified numerically, starting at 1.
|
||||
// The day (of the week) names are identified with short strings, since there is
|
||||
// no universally-accepted numeric designation.
|
||||
`,
|
||||
"dates": `
|
||||
// Dates contains information regarding the format and parsing of dates and times.
|
||||
`,
|
||||
"localeDisplayNames": `
|
||||
// LocaleDisplayNames specifies localized display names for for scripts, languages,
|
||||
// countries, currencies, and variants.
|
||||
`,
|
||||
"numbers": `
|
||||
// Numbers supplies information for formatting and parsing numbers and currencies.
|
||||
`,
|
||||
}
|
||||
|
||||
type element struct {
|
||||
name string // XML element name
|
||||
category string // elements contained by this element
|
||||
signature string // category + attrKey*
|
||||
|
||||
attr []*attribute // attributes supported by this element.
|
||||
sub []struct { // parsed and evaluated sub elements of this element.
|
||||
e *element
|
||||
repeat bool // true if the element needs to be a slice
|
||||
}
|
||||
|
||||
resolved bool // prevent multiple resolutions of this element.
|
||||
}
|
||||
|
||||
type attribute struct {
|
||||
name string
|
||||
key string
|
||||
list []string
|
||||
|
||||
tag string // Go tag
|
||||
}
|
||||
|
||||
var (
|
||||
reHead = regexp.MustCompile(` *(\w+) +([\w\-]+)`)
|
||||
reAttr = regexp.MustCompile(` *(\w+) *(?:(\w+)|\(([\w\- \|]+)\)) *(?:#([A-Z]*) *(?:\"([\.\d+])\")?)? *("[\w\-:]*")?`)
|
||||
reElem = regexp.MustCompile(`^ *(EMPTY|ANY|\(.*\)[\*\+\?]?) *$`)
|
||||
reToken = regexp.MustCompile(`\w\-`)
|
||||
)
|
||||
|
||||
// builder is used to read in the DTD files from CLDR and generate Go code
|
||||
// to be used with the encoding/xml package.
|
||||
type builder struct {
|
||||
w io.Writer
|
||||
index map[string]*element
|
||||
elem []*element
|
||||
info dtd
|
||||
version string
|
||||
}
|
||||
|
||||
func makeBuilder(w io.Writer, d dtd) builder {
|
||||
return builder{
|
||||
w: w,
|
||||
index: make(map[string]*element),
|
||||
elem: []*element{},
|
||||
info: d,
|
||||
}
|
||||
}
|
||||
|
||||
// parseDTD parses a DTD file.
|
||||
func (b *builder) parseDTD(r io.Reader) {
|
||||
for d := xml.NewDecoder(r); ; {
|
||||
t, err := d.Token()
|
||||
if t == nil {
|
||||
break
|
||||
}
|
||||
failOnError(err)
|
||||
dir, ok := t.(xml.Directive)
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
m := reHead.FindSubmatch(dir)
|
||||
dir = dir[len(m[0]):]
|
||||
ename := string(m[2])
|
||||
el, elementFound := b.index[ename]
|
||||
switch string(m[1]) {
|
||||
case "ELEMENT":
|
||||
if elementFound {
|
||||
log.Fatal("parseDTD: duplicate entry for element %q", ename)
|
||||
}
|
||||
m := reElem.FindSubmatch(dir)
|
||||
if m == nil {
|
||||
log.Fatalf("parseDTD: invalid element %q", string(dir))
|
||||
}
|
||||
if len(m[0]) != len(dir) {
|
||||
log.Fatal("parseDTD: invalid element %q", string(dir), len(dir), len(m[0]), string(m[0]))
|
||||
}
|
||||
s := string(m[1])
|
||||
el = &element{
|
||||
name: ename,
|
||||
category: s,
|
||||
}
|
||||
b.index[ename] = el
|
||||
case "ATTLIST":
|
||||
if !elementFound {
|
||||
log.Fatalf("parseDTD: unknown element %q", ename)
|
||||
}
|
||||
s := string(dir)
|
||||
m := reAttr.FindStringSubmatch(s)
|
||||
if m == nil {
|
||||
log.Fatal(fmt.Errorf("parseDTD: invalid attribute %q", string(dir)))
|
||||
}
|
||||
if m[4] == "FIXED" {
|
||||
b.version = m[5]
|
||||
} else {
|
||||
switch m[1] {
|
||||
case "draft", "references", "alt", "validSubLocales", "standard" /* in Common */ :
|
||||
case "type", "choice":
|
||||
default:
|
||||
el.attr = append(el.attr, &attribute{
|
||||
name: m[1],
|
||||
key: s,
|
||||
list: reToken.FindAllString(m[3], -1),
|
||||
})
|
||||
el.signature = fmt.Sprintf("%s=%s+%s", el.signature, m[1], m[2])
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
var reCat = regexp.MustCompile(`[ ,\|]*(?:(\(|\)|\#?[\w_-]+)([\*\+\?]?))?`)
|
||||
|
||||
// resolve takes a parsed element and converts it into structured data
|
||||
// that can be used to generate the XML code.
|
||||
func (b *builder) resolve(e *element) {
|
||||
if e.resolved {
|
||||
return
|
||||
}
|
||||
b.elem = append(b.elem, e)
|
||||
e.resolved = true
|
||||
s := e.category
|
||||
found := make(map[string]bool)
|
||||
sequenceStart := []int{}
|
||||
for len(s) > 0 {
|
||||
m := reCat.FindStringSubmatch(s)
|
||||
if m == nil {
|
||||
log.Fatalf("%s: invalid category string %q", e.name, s)
|
||||
}
|
||||
repeat := m[2] == "*" || m[2] == "+" || in(b.info.forceRepeat, m[1])
|
||||
switch m[1] {
|
||||
case "":
|
||||
case "(":
|
||||
sequenceStart = append(sequenceStart, len(e.sub))
|
||||
case ")":
|
||||
if len(sequenceStart) == 0 {
|
||||
log.Fatalf("%s: unmatched closing parenthesis", e.name)
|
||||
}
|
||||
for i := sequenceStart[len(sequenceStart)-1]; i < len(e.sub); i++ {
|
||||
e.sub[i].repeat = e.sub[i].repeat || repeat
|
||||
}
|
||||
sequenceStart = sequenceStart[:len(sequenceStart)-1]
|
||||
default:
|
||||
if in(b.info.skipElem, m[1]) {
|
||||
} else if sub, ok := b.index[m[1]]; ok {
|
||||
if !found[sub.name] {
|
||||
e.sub = append(e.sub, struct {
|
||||
e *element
|
||||
repeat bool
|
||||
}{sub, repeat})
|
||||
found[sub.name] = true
|
||||
b.resolve(sub)
|
||||
}
|
||||
} else if m[1] == "#PCDATA" || m[1] == "ANY" {
|
||||
} else if m[1] != "EMPTY" {
|
||||
log.Fatalf("resolve:%s: element %q not found", e.name, m[1])
|
||||
}
|
||||
}
|
||||
s = s[len(m[0]):]
|
||||
}
|
||||
}
|
||||
|
||||
// return true if s is contained in set.
|
||||
func in(set []string, s string) bool {
|
||||
for _, v := range set {
|
||||
if v == s {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
var repl = strings.NewReplacer("-", " ", "_", " ")
|
||||
|
||||
// title puts the first character or each character following '_' in title case and
|
||||
// removes all occurrences of '_'.
|
||||
func title(s string) string {
|
||||
return strings.Replace(strings.Title(repl.Replace(s)), " ", "", -1)
|
||||
}
|
||||
|
||||
// writeElem generates Go code for a single element, recursively.
|
||||
func (b *builder) writeElem(tab int, e *element) {
|
||||
p := func(f string, x ...interface{}) {
|
||||
f = strings.Replace(f, "\n", "\n"+strings.Repeat("\t", tab), -1)
|
||||
fmt.Fprintf(b.w, f, x...)
|
||||
}
|
||||
if len(e.sub) == 0 && len(e.attr) == 0 {
|
||||
p("Common")
|
||||
return
|
||||
}
|
||||
p("struct {")
|
||||
tab++
|
||||
p("\nCommon")
|
||||
for _, attr := range e.attr {
|
||||
if !in(b.info.skipAttr, attr.name) {
|
||||
p("\n%s string `xml:\"%s,attr\"`", title(attr.name), attr.name)
|
||||
}
|
||||
}
|
||||
for _, sub := range e.sub {
|
||||
if in(b.info.predefined, sub.e.name) {
|
||||
p("\n%sElem", sub.e.name)
|
||||
continue
|
||||
}
|
||||
if in(b.info.skipElem, sub.e.name) {
|
||||
continue
|
||||
}
|
||||
p("\n%s ", title(sub.e.name))
|
||||
if sub.repeat {
|
||||
p("[]")
|
||||
}
|
||||
p("*")
|
||||
if in(b.info.top, sub.e.name) {
|
||||
p(title(sub.e.name))
|
||||
} else {
|
||||
b.writeElem(tab, sub.e)
|
||||
}
|
||||
p(" `xml:\"%s\"`", sub.e.name)
|
||||
}
|
||||
tab--
|
||||
p("\n}")
|
||||
}
|
||||
|
||||
// write generates the Go XML code.
|
||||
func (b *builder) write() {
|
||||
for i, name := range b.info.top {
|
||||
e := b.index[name]
|
||||
if e != nil {
|
||||
fmt.Fprintf(b.w, comments[name])
|
||||
name := title(e.name)
|
||||
if i == 0 {
|
||||
name = b.info.root
|
||||
}
|
||||
fmt.Fprintf(b.w, "type %s ", name)
|
||||
b.writeElem(0, e)
|
||||
fmt.Fprint(b.w, "\n")
|
||||
}
|
||||
}
|
||||
}
|
|
@ -0,0 +1,602 @@
|
|||
// 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 cldr
|
||||
|
||||
// This file implements the various inheritance constructs defined by LDML.
|
||||
// See http://www.unicode.org/reports/tr35/#Inheritance_and_Validity
|
||||
// for more details.
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"log"
|
||||
"reflect"
|
||||
"regexp"
|
||||
"sort"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// fieldIter iterates over fields in a struct. It includes
|
||||
// fields of embedded structs.
|
||||
type fieldIter struct {
|
||||
v reflect.Value
|
||||
index, n []int
|
||||
}
|
||||
|
||||
func iter(v reflect.Value) fieldIter {
|
||||
if v.Kind() != reflect.Struct {
|
||||
log.Panicf("value %v must be a struct", v)
|
||||
}
|
||||
i := fieldIter{
|
||||
v: v,
|
||||
index: []int{0},
|
||||
n: []int{v.NumField()},
|
||||
}
|
||||
i.descent()
|
||||
return i
|
||||
}
|
||||
|
||||
func (i *fieldIter) descent() {
|
||||
for f := i.field(); f.Anonymous && f.Type.NumField() > 0; f = i.field() {
|
||||
i.index = append(i.index, 0)
|
||||
i.n = append(i.n, f.Type.NumField())
|
||||
}
|
||||
}
|
||||
|
||||
func (i *fieldIter) done() bool {
|
||||
return len(i.index) == 1 && i.index[0] >= i.n[0]
|
||||
}
|
||||
|
||||
func skip(f reflect.StructField) bool {
|
||||
return !f.Anonymous && (f.Name[0] < 'A' || f.Name[0] > 'Z')
|
||||
}
|
||||
|
||||
func (i *fieldIter) next() {
|
||||
for {
|
||||
k := len(i.index) - 1
|
||||
i.index[k]++
|
||||
if i.index[k] < i.n[k] {
|
||||
if !skip(i.field()) {
|
||||
break
|
||||
}
|
||||
} else {
|
||||
if k == 0 {
|
||||
return
|
||||
}
|
||||
i.index = i.index[:k]
|
||||
i.n = i.n[:k]
|
||||
}
|
||||
}
|
||||
i.descent()
|
||||
}
|
||||
|
||||
func (i *fieldIter) value() reflect.Value {
|
||||
return i.v.FieldByIndex(i.index)
|
||||
}
|
||||
|
||||
func (i *fieldIter) field() reflect.StructField {
|
||||
return i.v.Type().FieldByIndex(i.index)
|
||||
}
|
||||
|
||||
type visitor func(v reflect.Value) error
|
||||
|
||||
var stopDescent = fmt.Errorf("do not recurse")
|
||||
|
||||
func (f visitor) visit(x interface{}) error {
|
||||
return f.visitRec(reflect.ValueOf(x))
|
||||
}
|
||||
|
||||
// visit recursively calls f on all nodes in v.
|
||||
func (f visitor) visitRec(v reflect.Value) error {
|
||||
if v.Kind() == reflect.Ptr {
|
||||
if v.IsNil() {
|
||||
return nil
|
||||
}
|
||||
return f.visitRec(v.Elem())
|
||||
}
|
||||
if err := f(v); err != nil {
|
||||
if err == stopDescent {
|
||||
return nil
|
||||
}
|
||||
return err
|
||||
}
|
||||
switch v.Kind() {
|
||||
case reflect.Struct:
|
||||
for i := iter(v); !i.done(); i.next() {
|
||||
if err := f.visitRec(i.value()); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
case reflect.Slice:
|
||||
for i := 0; i < v.Len(); i++ {
|
||||
if err := f.visitRec(v.Index(i)); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// getPath is used for error reporting purposes only.
|
||||
func getPath(e Elem) string {
|
||||
if e == nil {
|
||||
return "<nil>"
|
||||
}
|
||||
if e.enclosing() == nil {
|
||||
return e.GetCommon().name
|
||||
}
|
||||
if e.GetCommon().Type == "" {
|
||||
return fmt.Sprintf("%s.%s", getPath(e.enclosing()), e.GetCommon().name)
|
||||
}
|
||||
return fmt.Sprintf("%s.%s[type=%s]", getPath(e.enclosing()), e.GetCommon().name, e.GetCommon().Type)
|
||||
}
|
||||
|
||||
// xmlName returns the xml name of the element or attribute
|
||||
func xmlName(f reflect.StructField) (name string, attr bool) {
|
||||
tags := strings.Split(f.Tag.Get("xml"), ",")
|
||||
for _, s := range tags {
|
||||
attr = attr || s == "attr"
|
||||
}
|
||||
return tags[0], attr
|
||||
}
|
||||
|
||||
func findField(v reflect.Value, key string) (reflect.Value, error) {
|
||||
v = reflect.Indirect(v)
|
||||
for i := iter(v); !i.done(); i.next() {
|
||||
if n, _ := xmlName(i.field()); n == key {
|
||||
return i.value(), nil
|
||||
}
|
||||
}
|
||||
return reflect.Value{}, fmt.Errorf("cldr: no field %q in element %#v", key, v.Interface())
|
||||
}
|
||||
|
||||
var xpathPart = regexp.MustCompile(`(\pL+)(?:\[@(\pL+)='([\w-]+)'\])?`)
|
||||
|
||||
func walkXPath(e Elem, path string) (res Elem, err error) {
|
||||
for _, c := range strings.Split(path, "/") {
|
||||
if c == ".." {
|
||||
if e = e.enclosing(); e == nil {
|
||||
panic("path ..")
|
||||
return nil, fmt.Errorf(`cldr: ".." moves past root in path %q`, path)
|
||||
}
|
||||
continue
|
||||
} else if c == "" {
|
||||
continue
|
||||
}
|
||||
m := xpathPart.FindStringSubmatch(c)
|
||||
if len(m) == 0 || len(m[0]) != len(c) {
|
||||
return nil, fmt.Errorf("cldr: syntax error in path component %q", c)
|
||||
}
|
||||
v, err := findField(reflect.ValueOf(e), m[1])
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
switch v.Kind() {
|
||||
case reflect.Slice:
|
||||
i := 0
|
||||
if m[2] != "" || v.Len() > 1 {
|
||||
if m[2] == "" {
|
||||
m[2] = "type"
|
||||
if m[3] = e.GetCommon().Default(); m[3] == "" {
|
||||
return nil, fmt.Errorf("cldr: type selector or default value needed for element %s", m[1])
|
||||
}
|
||||
}
|
||||
for ; i < v.Len(); i++ {
|
||||
vi := v.Index(i)
|
||||
key, err := findField(vi.Elem(), m[2])
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
key = reflect.Indirect(key)
|
||||
if key.Kind() == reflect.String && key.String() == m[3] {
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
if i == v.Len() || v.Index(i).IsNil() {
|
||||
return nil, fmt.Errorf("no %s found with %s==%s", m[1], m[2], m[3])
|
||||
}
|
||||
e = v.Index(i).Interface().(Elem)
|
||||
case reflect.Ptr:
|
||||
if v.IsNil() {
|
||||
return nil, fmt.Errorf("cldr: element %q not found within element %q", m[1], e.GetCommon().name)
|
||||
}
|
||||
var ok bool
|
||||
if e, ok = v.Interface().(Elem); !ok {
|
||||
return nil, fmt.Errorf("cldr: %q is not an XML element", m[1])
|
||||
} else if m[2] != "" || m[3] != "" {
|
||||
return nil, fmt.Errorf("cldr: no type selector allowed for element %s", m[1])
|
||||
}
|
||||
default:
|
||||
return nil, fmt.Errorf("cldr: %q is not an XML element", m[1])
|
||||
}
|
||||
}
|
||||
return e, nil
|
||||
}
|
||||
|
||||
const absPrefix = "//ldml/"
|
||||
|
||||
func (cldr *CLDR) resolveAlias(e Elem, src, path string) (res Elem, err error) {
|
||||
if src != "locale" {
|
||||
if !strings.HasPrefix(path, absPrefix) {
|
||||
return nil, fmt.Errorf("cldr: expected absolute path, found %q", path)
|
||||
}
|
||||
path = path[len(absPrefix):]
|
||||
if e, err = cldr.resolve(src); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
return walkXPath(e, path)
|
||||
}
|
||||
|
||||
func (cldr *CLDR) resolveAndMergeAlias(e Elem) error {
|
||||
alias := e.GetCommon().Alias
|
||||
if alias == nil {
|
||||
return nil
|
||||
}
|
||||
a, err := cldr.resolveAlias(e, alias.Source, alias.Path)
|
||||
if err != nil {
|
||||
return fmt.Errorf("%v: error evaluating path %q: %v", getPath(e), alias.Path, err)
|
||||
}
|
||||
// Ensure alias node was already evaluated. TODO: avoid double evaluation.
|
||||
err = cldr.resolveAndMergeAlias(a)
|
||||
v := reflect.ValueOf(e).Elem()
|
||||
for i := iter(reflect.ValueOf(a).Elem()); !i.done(); i.next() {
|
||||
if vv := i.value(); vv.Kind() != reflect.Ptr || !vv.IsNil() {
|
||||
if _, attr := xmlName(i.field()); !attr {
|
||||
v.FieldByIndex(i.index).Set(vv)
|
||||
}
|
||||
}
|
||||
}
|
||||
return err
|
||||
}
|
||||
|
||||
func (cldr *CLDR) aliasResolver() visitor {
|
||||
return func(v reflect.Value) (err error) {
|
||||
if e, ok := v.Addr().Interface().(Elem); ok {
|
||||
err = cldr.resolveAndMergeAlias(e)
|
||||
if err == nil && blocking[e.GetCommon().name] {
|
||||
return stopDescent
|
||||
}
|
||||
}
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
// elements within blocking elements do not inherit.
|
||||
// Taken from CLDR's supplementalMetaData.xml.
|
||||
var blocking = map[string]bool{
|
||||
"identity": true,
|
||||
"supplementalData": true,
|
||||
"cldrTest": true,
|
||||
"collation": true,
|
||||
"transform": true,
|
||||
}
|
||||
|
||||
// Distinguishing attributes affect inheritance; two elements with different
|
||||
// distinguishing attributes are treated as different for purposes of inheritance,
|
||||
// except when such attributes occur in the indicated elements.
|
||||
// Taken from CLDR's supplementalMetaData.xml.
|
||||
var distinguishing = map[string][]string{
|
||||
"key": nil,
|
||||
"request_id": nil,
|
||||
"id": nil,
|
||||
"registry": nil,
|
||||
"alt": nil,
|
||||
"iso4217": nil,
|
||||
"iso3166": nil,
|
||||
"mzone": nil,
|
||||
"from": nil,
|
||||
"to": nil,
|
||||
"type": []string{
|
||||
"abbreviationFallback",
|
||||
"default",
|
||||
"mapping",
|
||||
"measurementSystem",
|
||||
"preferenceOrdering",
|
||||
},
|
||||
"numberSystem": nil,
|
||||
}
|
||||
|
||||
func in(set []string, s string) bool {
|
||||
for _, v := range set {
|
||||
if v == s {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// attrKey computes a key based on the distinguishable attributes of
|
||||
// an element and it's values.
|
||||
func attrKey(v reflect.Value, exclude ...string) string {
|
||||
parts := []string{}
|
||||
ename := v.Interface().(Elem).GetCommon().name
|
||||
v = v.Elem()
|
||||
for i := iter(v); !i.done(); i.next() {
|
||||
if name, attr := xmlName(i.field()); attr {
|
||||
if except, ok := distinguishing[name]; ok && !in(exclude, name) && !in(except, ename) {
|
||||
v := i.value()
|
||||
if v.Kind() == reflect.Ptr {
|
||||
v = v.Elem()
|
||||
}
|
||||
if v.IsValid() {
|
||||
parts = append(parts, fmt.Sprintf("%s=%s", name, v.String()))
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
sort.Strings(parts)
|
||||
return strings.Join(parts, ";")
|
||||
}
|
||||
|
||||
// Key returns a key for e derived from all distinguishing attributes
|
||||
// except those specified by exclude.
|
||||
func Key(e Elem, exclude ...string) string {
|
||||
return attrKey(reflect.ValueOf(e), exclude...)
|
||||
}
|
||||
|
||||
// linkEnclosing sets the enclosing element as well as the name
|
||||
// for all sub-elements of child, recursively.
|
||||
func linkEnclosing(parent, child Elem) {
|
||||
child.setEnclosing(parent)
|
||||
v := reflect.ValueOf(child).Elem()
|
||||
for i := iter(v); !i.done(); i.next() {
|
||||
vf := i.value()
|
||||
if vf.Kind() == reflect.Slice {
|
||||
for j := 0; j < vf.Len(); j++ {
|
||||
linkEnclosing(child, vf.Index(j).Interface().(Elem))
|
||||
}
|
||||
} else if vf.Kind() == reflect.Ptr && !vf.IsNil() && vf.Elem().Kind() == reflect.Struct {
|
||||
linkEnclosing(child, vf.Interface().(Elem))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func setNames(e Elem, name string) {
|
||||
e.setName(name)
|
||||
v := reflect.ValueOf(e).Elem()
|
||||
for i := iter(v); !i.done(); i.next() {
|
||||
vf := i.value()
|
||||
name, _ = xmlName(i.field())
|
||||
if vf.Kind() == reflect.Slice {
|
||||
for j := 0; j < vf.Len(); j++ {
|
||||
setNames(vf.Index(j).Interface().(Elem), name)
|
||||
}
|
||||
} else if vf.Kind() == reflect.Ptr && !vf.IsNil() && vf.Elem().Kind() == reflect.Struct {
|
||||
setNames(vf.Interface().(Elem), name)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// deepCopy copies elements of v recursively. All elements of v that may
|
||||
// be modified by inheritance are explicitly copied.
|
||||
func deepCopy(v reflect.Value) reflect.Value {
|
||||
switch v.Kind() {
|
||||
case reflect.Ptr:
|
||||
if v.IsNil() || v.Elem().Kind() != reflect.Struct {
|
||||
return v
|
||||
}
|
||||
nv := reflect.New(v.Elem().Type())
|
||||
nv.Elem().Set(v.Elem())
|
||||
deepCopyRec(nv.Elem(), v.Elem())
|
||||
return nv
|
||||
case reflect.Slice:
|
||||
nv := reflect.MakeSlice(v.Type(), v.Len(), v.Len())
|
||||
for i := 0; i < v.Len(); i++ {
|
||||
deepCopyRec(nv.Index(i), v.Index(i))
|
||||
}
|
||||
return nv
|
||||
}
|
||||
panic("deepCopy: must be called with pointer or slice")
|
||||
}
|
||||
|
||||
// deepCopyRec is only called by deepCopy.
|
||||
func deepCopyRec(nv, v reflect.Value) {
|
||||
if v.Kind() == reflect.Struct {
|
||||
t := v.Type()
|
||||
for i := 0; i < v.NumField(); i++ {
|
||||
if name, attr := xmlName(t.Field(i)); name != "" && !attr {
|
||||
deepCopyRec(nv.Field(i), v.Field(i))
|
||||
}
|
||||
}
|
||||
} else {
|
||||
nv.Set(deepCopy(v))
|
||||
}
|
||||
}
|
||||
|
||||
// newNode is used to insert a missing node during inheritance.
|
||||
func (cldr *CLDR) newNode(v, enc reflect.Value) reflect.Value {
|
||||
n := reflect.New(v.Type())
|
||||
for i := iter(v); !i.done(); i.next() {
|
||||
if name, attr := xmlName(i.field()); name == "" || attr {
|
||||
n.Elem().FieldByIndex(i.index).Set(i.value())
|
||||
}
|
||||
}
|
||||
n.Interface().(Elem).GetCommon().setEnclosing(enc.Addr().Interface().(Elem))
|
||||
return n
|
||||
}
|
||||
|
||||
// v, parent must be pointers to struct
|
||||
func (cldr *CLDR) inheritFields(v, parent reflect.Value) (res reflect.Value, err error) {
|
||||
t := v.Type()
|
||||
nv := reflect.New(t)
|
||||
nv.Elem().Set(v)
|
||||
for i := iter(v); !i.done(); i.next() {
|
||||
vf := i.value()
|
||||
f := i.field()
|
||||
name, attr := xmlName(f)
|
||||
if name == "" || attr {
|
||||
continue
|
||||
}
|
||||
pf := parent.FieldByIndex(i.index)
|
||||
if blocking[name] {
|
||||
if vf.IsNil() {
|
||||
vf = pf
|
||||
}
|
||||
nv.Elem().FieldByIndex(i.index).Set(deepCopy(vf))
|
||||
continue
|
||||
}
|
||||
switch f.Type.Kind() {
|
||||
case reflect.Ptr:
|
||||
if f.Type.Elem().Kind() == reflect.Struct {
|
||||
if !vf.IsNil() {
|
||||
if vf, err = cldr.inheritStructPtr(vf, pf); err != nil {
|
||||
return reflect.Value{}, err
|
||||
}
|
||||
vf.Interface().(Elem).setEnclosing(nv.Interface().(Elem))
|
||||
nv.Elem().FieldByIndex(i.index).Set(vf)
|
||||
} else if !pf.IsNil() {
|
||||
n := cldr.newNode(pf.Elem(), v)
|
||||
if vf, err = cldr.inheritStructPtr(n, pf); err != nil {
|
||||
return reflect.Value{}, err
|
||||
}
|
||||
vf.Interface().(Elem).setEnclosing(nv.Interface().(Elem))
|
||||
nv.Elem().FieldByIndex(i.index).Set(vf)
|
||||
}
|
||||
}
|
||||
case reflect.Slice:
|
||||
vf, err := cldr.inheritSlice(nv.Elem(), vf, pf)
|
||||
if err != nil {
|
||||
return reflect.Zero(t), err
|
||||
}
|
||||
nv.Elem().FieldByIndex(i.index).Set(vf)
|
||||
}
|
||||
}
|
||||
return nv, nil
|
||||
}
|
||||
|
||||
func root(e Elem) *LDML {
|
||||
for ; e.enclosing() != nil; e = e.enclosing() {
|
||||
}
|
||||
return e.(*LDML)
|
||||
}
|
||||
|
||||
// inheritStructPtr first merges possible aliases in with v and then inherits
|
||||
// any underspecified elements from parent.
|
||||
func (cldr *CLDR) inheritStructPtr(v, parent reflect.Value) (r reflect.Value, err error) {
|
||||
if !v.IsNil() {
|
||||
e := v.Interface().(Elem).GetCommon()
|
||||
alias := e.Alias
|
||||
if alias == nil && !parent.IsNil() {
|
||||
alias = parent.Interface().(Elem).GetCommon().Alias
|
||||
}
|
||||
if alias != nil {
|
||||
a, err := cldr.resolveAlias(v.Interface().(Elem), alias.Source, alias.Path)
|
||||
if a != nil {
|
||||
if v, err = cldr.inheritFields(v.Elem(), reflect.ValueOf(a).Elem()); err != nil {
|
||||
return reflect.Value{}, err
|
||||
}
|
||||
}
|
||||
}
|
||||
if !parent.IsNil() {
|
||||
return cldr.inheritFields(v.Elem(), parent.Elem())
|
||||
}
|
||||
} else if parent.IsNil() {
|
||||
panic("should not reach here")
|
||||
}
|
||||
return v, nil
|
||||
}
|
||||
|
||||
// Must be slice of struct pointers.
|
||||
func (cldr *CLDR) inheritSlice(enc, v, parent reflect.Value) (res reflect.Value, err error) {
|
||||
t := v.Type()
|
||||
index := make(map[string]reflect.Value)
|
||||
if !v.IsNil() {
|
||||
for i := 0; i < v.Len(); i++ {
|
||||
vi := v.Index(i)
|
||||
key := attrKey(vi)
|
||||
index[key] = vi
|
||||
}
|
||||
}
|
||||
if !parent.IsNil() {
|
||||
for i := 0; i < parent.Len(); i++ {
|
||||
vi := parent.Index(i)
|
||||
key := attrKey(vi)
|
||||
if w, ok := index[key]; ok {
|
||||
index[key], err = cldr.inheritStructPtr(w, vi)
|
||||
} else {
|
||||
n := cldr.newNode(vi.Elem(), enc)
|
||||
index[key], err = cldr.inheritStructPtr(n, vi)
|
||||
}
|
||||
index[key].Interface().(Elem).setEnclosing(enc.Addr().Interface().(Elem))
|
||||
if err != nil {
|
||||
return v, err
|
||||
}
|
||||
}
|
||||
}
|
||||
keys := make([]string, 0, len(index))
|
||||
for k, _ := range index {
|
||||
keys = append(keys, k)
|
||||
}
|
||||
sort.Strings(keys)
|
||||
sl := reflect.MakeSlice(t, len(index), len(index))
|
||||
for i, k := range keys {
|
||||
sl.Index(i).Set(index[k])
|
||||
}
|
||||
return sl, nil
|
||||
}
|
||||
|
||||
func parentLocale(loc string) string {
|
||||
parts := strings.Split(loc, "_")
|
||||
if len(parts) == 1 {
|
||||
return "root"
|
||||
}
|
||||
parts = parts[:len(parts)-1]
|
||||
key := strings.Join(parts, "_")
|
||||
return key
|
||||
}
|
||||
|
||||
func (cldr *CLDR) resolve(loc string) (res *LDML, err error) {
|
||||
if r := cldr.resolved[loc]; r != nil {
|
||||
return r, nil
|
||||
}
|
||||
x := cldr.RawLDML(loc)
|
||||
if x == nil {
|
||||
return nil, fmt.Errorf("cldr: unknown locale %q", loc)
|
||||
}
|
||||
var v reflect.Value
|
||||
if loc == "root" {
|
||||
x = deepCopy(reflect.ValueOf(x)).Interface().(*LDML)
|
||||
linkEnclosing(nil, x)
|
||||
err = cldr.aliasResolver().visit(x)
|
||||
} else {
|
||||
key := parentLocale(loc)
|
||||
var parent *LDML
|
||||
for ; cldr.locale[key] == nil; key = parentLocale(key) {
|
||||
}
|
||||
if parent, err = cldr.resolve(key); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
v, err = cldr.inheritFields(reflect.ValueOf(x).Elem(), reflect.ValueOf(parent).Elem())
|
||||
x = v.Interface().(*LDML)
|
||||
linkEnclosing(nil, x)
|
||||
}
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
cldr.resolved[loc] = x
|
||||
return x, err
|
||||
}
|
||||
|
||||
// finalize finalizes the initialization of the raw LDML structs. It also
|
||||
// removed unwanted fields, as specified by filter, so that they will not
|
||||
// be unnecessarily evaluated.
|
||||
func (cldr *CLDR) finalize(filter []string) {
|
||||
for _, x := range cldr.locale {
|
||||
if filter != nil {
|
||||
v := reflect.ValueOf(x).Elem()
|
||||
t := v.Type()
|
||||
for i := 0; i < v.NumField(); i++ {
|
||||
f := t.Field(i)
|
||||
name, _ := xmlName(f)
|
||||
if name != "" && name != "identity" && !in(filter, name) {
|
||||
v.Field(i).Set(reflect.Zero(f.Type))
|
||||
}
|
||||
}
|
||||
}
|
||||
linkEnclosing(nil, x) // for resolving aliases and paths
|
||||
setNames(x, "ldml")
|
||||
}
|
||||
}
|
|
@ -0,0 +1,144 @@
|
|||
// 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 cldr
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"reflect"
|
||||
"sort"
|
||||
)
|
||||
|
||||
// Slice provides utilities for modifying slices of elements.
|
||||
// It can be wrapped around any slice of which the element type implements
|
||||
// interface Elem.
|
||||
type Slice struct {
|
||||
ptr reflect.Value
|
||||
typ reflect.Type
|
||||
}
|
||||
|
||||
// Value returns the reflect.Value of the underlying slice.
|
||||
func (s *Slice) Value() reflect.Value {
|
||||
return s.ptr.Elem()
|
||||
}
|
||||
|
||||
// MakeSlice wraps a pointer to a slice of Elems.
|
||||
// It replaces the array pointed to by the slice so that subsequent modifications
|
||||
// do not alter the data in a CLDR type.
|
||||
// It panics if an incorrect type is passed.
|
||||
func MakeSlice(slicePtr interface{}) Slice {
|
||||
ptr := reflect.ValueOf(slicePtr)
|
||||
if ptr.Kind() != reflect.Ptr {
|
||||
panic(fmt.Sprintf("MakeSlice: argument must be pointer to slice, found %v", ptr.Type()))
|
||||
}
|
||||
sl := ptr.Elem()
|
||||
if sl.Kind() != reflect.Slice {
|
||||
panic(fmt.Sprintf("MakeSlice: argument must point to a slice, found %v", sl.Type()))
|
||||
}
|
||||
intf := reflect.TypeOf((*Elem)(nil)).Elem()
|
||||
if !sl.Type().Elem().Implements(intf) {
|
||||
panic(fmt.Sprintf("MakeSlice: element type of slice (%v) does not implement Elem", sl.Type().Elem()))
|
||||
}
|
||||
nsl := reflect.MakeSlice(sl.Type(), sl.Len(), sl.Len())
|
||||
reflect.Copy(nsl, sl)
|
||||
sl.Set(nsl)
|
||||
return Slice{
|
||||
ptr: ptr,
|
||||
typ: sl.Type().Elem().Elem(),
|
||||
}
|
||||
}
|
||||
|
||||
func (s Slice) indexForAttr(a string) []int {
|
||||
for i := iter(reflect.Zero(s.typ)); !i.done(); i.next() {
|
||||
if n, _ := xmlName(i.field()); n == a {
|
||||
return i.index
|
||||
}
|
||||
}
|
||||
panic(fmt.Sprintf("MakeSlice: no attribute %q for type %v", a, s.typ))
|
||||
}
|
||||
|
||||
// Filter filters s to only include elements for which fn returns true.
|
||||
func (s Slice) Filter(fn func(e Elem) bool) {
|
||||
k := 0
|
||||
sl := s.Value()
|
||||
for i := 0; i < sl.Len(); i++ {
|
||||
vi := sl.Index(i)
|
||||
if fn(vi.Interface().(Elem)) {
|
||||
sl.Index(k).Set(vi)
|
||||
k++
|
||||
}
|
||||
}
|
||||
sl.Set(sl.Slice(0, k))
|
||||
}
|
||||
|
||||
// Group finds elements in s for which fn returns the same value and groups
|
||||
// them in a new Slice.
|
||||
func (s Slice) Group(fn func(e Elem) string) []Slice {
|
||||
m := make(map[string][]reflect.Value)
|
||||
sl := s.Value()
|
||||
for i := 0; i < sl.Len(); i++ {
|
||||
vi := sl.Index(i)
|
||||
key := fn(vi.Interface().(Elem))
|
||||
m[key] = append(m[key], vi)
|
||||
}
|
||||
keys := []string{}
|
||||
for k, _ := range m {
|
||||
keys = append(keys, k)
|
||||
}
|
||||
sort.Strings(keys)
|
||||
res := []Slice{}
|
||||
for _, k := range keys {
|
||||
nsl := reflect.New(sl.Type())
|
||||
nsl.Elem().Set(reflect.Append(nsl.Elem(), m[k]...))
|
||||
res = append(res, MakeSlice(nsl.Interface()))
|
||||
}
|
||||
return res
|
||||
}
|
||||
|
||||
// SelectAnyOf filters s to contain only elements for which attr matches
|
||||
// any of the values.
|
||||
func (s Slice) SelectAnyOf(attr string, values ...string) {
|
||||
index := s.indexForAttr(attr)
|
||||
s.Filter(func(e Elem) bool {
|
||||
vf := reflect.ValueOf(e).Elem().FieldByIndex(index)
|
||||
return in(values, vf.String())
|
||||
})
|
||||
}
|
||||
|
||||
// SelectOnePerGroup filters s to include at most one element e per group of
|
||||
// elements matching Key(attr), where e has an attribute a that matches any
|
||||
// the values in v.
|
||||
// If more than one element in a group matches a value in v preference
|
||||
// is given to the element that matches the first value in v.
|
||||
func (s Slice) SelectOnePerGroup(a string, v []string) {
|
||||
index := s.indexForAttr(a)
|
||||
grouped := s.Group(func(e Elem) string { return Key(e, a) })
|
||||
sl := s.Value()
|
||||
sl.Set(sl.Slice(0, 0))
|
||||
for _, g := range grouped {
|
||||
e := reflect.Value{}
|
||||
found := len(v)
|
||||
gsl := g.Value()
|
||||
for i := 0; i < gsl.Len(); i++ {
|
||||
vi := gsl.Index(i).Elem().FieldByIndex(index)
|
||||
j := 0
|
||||
for ; j < len(v) && v[j] != vi.String(); j++ {
|
||||
}
|
||||
if j < found {
|
||||
found = j
|
||||
e = gsl.Index(i)
|
||||
}
|
||||
}
|
||||
if found < len(v) {
|
||||
sl.Set(reflect.Append(sl, e))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// SelectDraft drops all elements from the list with a draft level smaller than d
|
||||
// and selects the highest draft level of the remaining.
|
||||
// This method assumes that the input CLDR is canonicalized.
|
||||
func (s Slice) SelectDraft(d Draft) {
|
||||
s.SelectOnePerGroup("draft", drafts[len(drafts)-2-int(d):])
|
||||
}
|
File diff suppressed because it is too large
Load Diff
|
@ -0,0 +1,202 @@
|
|||
|
||||
Apache License
|
||||
Version 2.0, January 2004
|
||||
http://www.apache.org/licenses/
|
||||
|
||||
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||
|
||||
1. Definitions.
|
||||
|
||||
"License" shall mean the terms and conditions for use, reproduction,
|
||||
and distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
"Licensor" shall mean the copyright owner or entity authorized by
|
||||
the copyright owner that is granting the License.
|
||||
|
||||
"Legal Entity" shall mean the union of the acting entity and all
|
||||
other entities that control, are controlled by, or are under common
|
||||
control with that entity. For the purposes of this definition,
|
||||
"control" means (i) the power, direct or indirect, to cause the
|
||||
direction or management of such entity, whether by contract or
|
||||
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||
|
||||
"You" (or "Your") shall mean an individual or Legal Entity
|
||||
exercising permissions granted by this License.
|
||||
|
||||
"Source" form shall mean the preferred form for making modifications,
|
||||
including but not limited to software source code, documentation
|
||||
source, and configuration files.
|
||||
|
||||
"Object" form shall mean any form resulting from mechanical
|
||||
transformation or translation of a Source form, including but
|
||||
not limited to compiled object code, generated documentation,
|
||||
and conversions to other media types.
|
||||
|
||||
"Work" shall mean the work of authorship, whether in Source or
|
||||
Object form, made available under the License, as indicated by a
|
||||
copyright notice that is included in or attached to the work
|
||||
(an example is provided in the Appendix below).
|
||||
|
||||
"Derivative Works" shall mean any work, whether in Source or Object
|
||||
form, that is based on (or derived from) the Work and for which the
|
||||
editorial revisions, annotations, elaborations, or other modifications
|
||||
represent, as a whole, an original work of authorship. For the purposes
|
||||
of this License, Derivative Works shall not include works that remain
|
||||
separable from, or merely link (or bind by name) to the interfaces of,
|
||||
the Work and Derivative Works thereof.
|
||||
|
||||
"Contribution" shall mean any work of authorship, including
|
||||
the original version of the Work and any modifications or additions
|
||||
to that Work or Derivative Works thereof, that is intentionally
|
||||
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||
or by an individual or Legal Entity authorized to submit on behalf of
|
||||
the copyright owner. For the purposes of this definition, "submitted"
|
||||
means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems,
|
||||
and issue tracking systems that are managed by, or on behalf of, the
|
||||
Licensor for the purpose of discussing and improving the Work, but
|
||||
excluding communication that is conspicuously marked or otherwise
|
||||
designated in writing by the copyright owner as "Not a Contribution."
|
||||
|
||||
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||
on behalf of whom a Contribution has been received by Licensor and
|
||||
subsequently incorporated within the Work.
|
||||
|
||||
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the
|
||||
Work and such Derivative Works in Source or Object form.
|
||||
|
||||
3. Grant of Patent License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
(except as stated in this section) patent license to make, have made,
|
||||
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||
where such license applies only to those patent claims licensable
|
||||
by such Contributor that are necessarily infringed by their
|
||||
Contribution(s) alone or by combination of their Contribution(s)
|
||||
with the Work to which such Contribution(s) was submitted. If You
|
||||
institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||
or a Contribution incorporated within the Work constitutes direct
|
||||
or contributory patent infringement, then any patent licenses
|
||||
granted to You under this License for that Work shall terminate
|
||||
as of the date such litigation is filed.
|
||||
|
||||
4. Redistribution. You may reproduce and distribute copies of the
|
||||
Work or Derivative Works thereof in any medium, with or without
|
||||
modifications, and in Source or Object form, provided that You
|
||||
meet the following conditions:
|
||||
|
||||
(a) You must give any other recipients of the Work or
|
||||
Derivative Works a copy of this License; and
|
||||
|
||||
(b) You must cause any modified files to carry prominent notices
|
||||
stating that You changed the files; and
|
||||
|
||||
(c) You must retain, in the Source form of any Derivative Works
|
||||
that You distribute, all copyright, patent, trademark, and
|
||||
attribution notices from the Source form of the Work,
|
||||
excluding those notices that do not pertain to any part of
|
||||
the Derivative Works; and
|
||||
|
||||
(d) If the Work includes a "NOTICE" text file as part of its
|
||||
distribution, then any Derivative Works that You distribute must
|
||||
include a readable copy of the attribution notices contained
|
||||
within such NOTICE file, excluding those notices that do not
|
||||
pertain to any part of the Derivative Works, in at least one
|
||||
of the following places: within a NOTICE text file distributed
|
||||
as part of the Derivative Works; within the Source form or
|
||||
documentation, if provided along with the Derivative Works; or,
|
||||
within a display generated by the Derivative Works, if and
|
||||
wherever such third-party notices normally appear. The contents
|
||||
of the NOTICE file are for informational purposes only and
|
||||
do not modify the License. You may add Your own attribution
|
||||
notices within Derivative Works that You distribute, alongside
|
||||
or as an addendum to the NOTICE text from the Work, provided
|
||||
that such additional attribution notices cannot be construed
|
||||
as modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and
|
||||
may provide additional or different license terms and conditions
|
||||
for use, reproduction, or distribution of Your modifications, or
|
||||
for any such Derivative Works as a whole, provided Your use,
|
||||
reproduction, and distribution of the Work otherwise complies with
|
||||
the conditions stated in this License.
|
||||
|
||||
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||
any Contribution intentionally submitted for inclusion in the Work
|
||||
by You to the Licensor shall be under the terms and conditions of
|
||||
this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify
|
||||
the terms of any separate license agreement you may have executed
|
||||
with Licensor regarding such Contributions.
|
||||
|
||||
6. Trademarks. This License does not grant permission to use the trade
|
||||
names, trademarks, service marks, or product names of the Licensor,
|
||||
except as required for reasonable and customary use in describing the
|
||||
origin of the Work and reproducing the content of the NOTICE file.
|
||||
|
||||
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||
agreed to in writing, Licensor provides the Work (and each
|
||||
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
implied, including, without limitation, any warranties or conditions
|
||||
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||
appropriateness of using or redistributing the Work and assume any
|
||||
risks associated with Your exercise of permissions under this License.
|
||||
|
||||
8. Limitation of Liability. In no event and under no legal theory,
|
||||
whether in tort (including negligence), contract, or otherwise,
|
||||
unless required by applicable law (such as deliberate and grossly
|
||||
negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special,
|
||||
incidental, or consequential damages of any character arising as a
|
||||
result of this License or out of the use or inability to use the
|
||||
Work (including but not limited to damages for loss of goodwill,
|
||||
work stoppage, computer failure or malfunction, or any and all
|
||||
other commercial damages or losses), even if such Contributor
|
||||
has been advised of the possibility of such damages.
|
||||
|
||||
9. Accepting Warranty or Additional Liability. While redistributing
|
||||
the Work or Derivative Works thereof, You may choose to offer,
|
||||
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||
or other liability obligations and/or rights consistent with this
|
||||
License. However, in accepting such obligations, You may act only
|
||||
on Your own behalf and on Your sole responsibility, not on behalf
|
||||
of any other Contributor, and only if You agree to indemnify,
|
||||
defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason
|
||||
of your accepting any such warranty or additional liability.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
APPENDIX: How to apply the Apache License to your work.
|
||||
|
||||
To apply the Apache License to your work, attach the following
|
||||
boilerplate notice, with the fields enclosed by brackets "[]"
|
||||
replaced with your own identifying information. (Don't include
|
||||
the brackets!) The text should be enclosed in the appropriate
|
||||
comment syntax for the file format. We also recommend that a
|
||||
file or class name and description of purpose be included on the
|
||||
same "printed page" as the copyright notice for easier
|
||||
identification within third-party archives.
|
||||
|
||||
Copyright 2014 Google Inc.
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
|
@ -807,6 +807,12 @@
|
|||
"path": "golang.org/x/sys/unix",
|
||||
"revision": "50c6bc5e4292a1d4e65c6e9be5f53be28bcbe28e"
|
||||
},
|
||||
{
|
||||
"checksumSHA1": "G9LfJI9gySazd+MyyC6QbTHx4to=",
|
||||
"path": "golang.org/x/text/encoding/unicode",
|
||||
"revision": "16e1d1f27f7aba51c74c0aeb7a7ee31a75c5c63c",
|
||||
"revisionTime": "2016-10-12T14:34:48Z"
|
||||
},
|
||||
{
|
||||
"checksumSHA1": "hrUTmck0J+LE+lBtCvHvemNDY8U=",
|
||||
"path": "google.golang.org/api/compute/v1",
|
||||
|
|
Loading…
Reference in New Issue