1
0
Fork 0
mirror of https://github.com/miniflux/v2.git synced 2025-08-11 17:51:01 +00:00

Update dependencies

This commit is contained in:
Frédéric Guillot 2019-09-05 21:39:32 -07:00 committed by Frédéric Guillot
parent 456ebaf423
commit b94160df72
350 changed files with 119448 additions and 25865 deletions

View file

@ -1,556 +0,0 @@
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build ignore
package main
import (
"bufio"
"fmt"
"log"
"net/http"
"sort"
"strings"
"unicode/utf8"
"golang.org/x/text/encoding"
"golang.org/x/text/internal/gen"
)
const ascii = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f" +
"\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f" +
` !"#$%&'()*+,-./0123456789:;<=>?` +
`@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_` +
"`abcdefghijklmnopqrstuvwxyz{|}~\u007f"
var encodings = []struct {
name string
mib string
comment string
varName string
replacement byte
mapping string
}{
{
"IBM Code Page 037",
"IBM037",
"",
"CodePage037",
0x3f,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/glibc-IBM037-2.1.2.ucm",
},
{
"IBM Code Page 437",
"PC8CodePage437",
"",
"CodePage437",
encoding.ASCIISub,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/glibc-IBM437-2.1.2.ucm",
},
{
"IBM Code Page 850",
"PC850Multilingual",
"",
"CodePage850",
encoding.ASCIISub,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/glibc-IBM850-2.1.2.ucm",
},
{
"IBM Code Page 852",
"PCp852",
"",
"CodePage852",
encoding.ASCIISub,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/glibc-IBM852-2.1.2.ucm",
},
{
"IBM Code Page 855",
"IBM855",
"",
"CodePage855",
encoding.ASCIISub,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/glibc-IBM855-2.1.2.ucm",
},
{
"Windows Code Page 858", // PC latin1 with Euro
"IBM00858",
"",
"CodePage858",
encoding.ASCIISub,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/windows-858-2000.ucm",
},
{
"IBM Code Page 860",
"IBM860",
"",
"CodePage860",
encoding.ASCIISub,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/glibc-IBM860-2.1.2.ucm",
},
{
"IBM Code Page 862",
"PC862LatinHebrew",
"",
"CodePage862",
encoding.ASCIISub,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/glibc-IBM862-2.1.2.ucm",
},
{
"IBM Code Page 863",
"IBM863",
"",
"CodePage863",
encoding.ASCIISub,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/glibc-IBM863-2.1.2.ucm",
},
{
"IBM Code Page 865",
"IBM865",
"",
"CodePage865",
encoding.ASCIISub,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/glibc-IBM865-2.1.2.ucm",
},
{
"IBM Code Page 866",
"IBM866",
"",
"CodePage866",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-ibm866.txt",
},
{
"IBM Code Page 1047",
"IBM1047",
"",
"CodePage1047",
0x3f,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/glibc-IBM1047-2.1.2.ucm",
},
{
"IBM Code Page 1140",
"IBM01140",
"",
"CodePage1140",
0x3f,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/ibm-1140_P100-1997.ucm",
},
{
"ISO 8859-1",
"ISOLatin1",
"",
"ISO8859_1",
encoding.ASCIISub,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/iso-8859_1-1998.ucm",
},
{
"ISO 8859-2",
"ISOLatin2",
"",
"ISO8859_2",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-iso-8859-2.txt",
},
{
"ISO 8859-3",
"ISOLatin3",
"",
"ISO8859_3",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-iso-8859-3.txt",
},
{
"ISO 8859-4",
"ISOLatin4",
"",
"ISO8859_4",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-iso-8859-4.txt",
},
{
"ISO 8859-5",
"ISOLatinCyrillic",
"",
"ISO8859_5",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-iso-8859-5.txt",
},
{
"ISO 8859-6",
"ISOLatinArabic",
"",
"ISO8859_6,ISO8859_6E,ISO8859_6I",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-iso-8859-6.txt",
},
{
"ISO 8859-7",
"ISOLatinGreek",
"",
"ISO8859_7",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-iso-8859-7.txt",
},
{
"ISO 8859-8",
"ISOLatinHebrew",
"",
"ISO8859_8,ISO8859_8E,ISO8859_8I",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-iso-8859-8.txt",
},
{
"ISO 8859-9",
"ISOLatin5",
"",
"ISO8859_9",
encoding.ASCIISub,
"http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/iso-8859_9-1999.ucm",
},
{
"ISO 8859-10",
"ISOLatin6",
"",
"ISO8859_10",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-iso-8859-10.txt",
},
{
"ISO 8859-13",
"ISO885913",
"",
"ISO8859_13",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-iso-8859-13.txt",
},
{
"ISO 8859-14",
"ISO885914",
"",
"ISO8859_14",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-iso-8859-14.txt",
},
{
"ISO 8859-15",
"ISO885915",
"",
"ISO8859_15",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-iso-8859-15.txt",
},
{
"ISO 8859-16",
"ISO885916",
"",
"ISO8859_16",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-iso-8859-16.txt",
},
{
"KOI8-R",
"KOI8R",
"",
"KOI8R",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-koi8-r.txt",
},
{
"KOI8-U",
"KOI8U",
"",
"KOI8U",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-koi8-u.txt",
},
{
"Macintosh",
"Macintosh",
"",
"Macintosh",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-macintosh.txt",
},
{
"Macintosh Cyrillic",
"MacintoshCyrillic",
"",
"MacintoshCyrillic",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-x-mac-cyrillic.txt",
},
{
"Windows 874",
"Windows874",
"",
"Windows874",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-windows-874.txt",
},
{
"Windows 1250",
"Windows1250",
"",
"Windows1250",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-windows-1250.txt",
},
{
"Windows 1251",
"Windows1251",
"",
"Windows1251",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-windows-1251.txt",
},
{
"Windows 1252",
"Windows1252",
"",
"Windows1252",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-windows-1252.txt",
},
{
"Windows 1253",
"Windows1253",
"",
"Windows1253",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-windows-1253.txt",
},
{
"Windows 1254",
"Windows1254",
"",
"Windows1254",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-windows-1254.txt",
},
{
"Windows 1255",
"Windows1255",
"",
"Windows1255",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-windows-1255.txt",
},
{
"Windows 1256",
"Windows1256",
"",
"Windows1256",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-windows-1256.txt",
},
{
"Windows 1257",
"Windows1257",
"",
"Windows1257",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-windows-1257.txt",
},
{
"Windows 1258",
"Windows1258",
"",
"Windows1258",
encoding.ASCIISub,
"http://encoding.spec.whatwg.org/index-windows-1258.txt",
},
{
"X-User-Defined",
"XUserDefined",
"It is defined at http://encoding.spec.whatwg.org/#x-user-defined",
"XUserDefined",
encoding.ASCIISub,
ascii +
"\uf780\uf781\uf782\uf783\uf784\uf785\uf786\uf787" +
"\uf788\uf789\uf78a\uf78b\uf78c\uf78d\uf78e\uf78f" +
"\uf790\uf791\uf792\uf793\uf794\uf795\uf796\uf797" +
"\uf798\uf799\uf79a\uf79b\uf79c\uf79d\uf79e\uf79f" +
"\uf7a0\uf7a1\uf7a2\uf7a3\uf7a4\uf7a5\uf7a6\uf7a7" +
"\uf7a8\uf7a9\uf7aa\uf7ab\uf7ac\uf7ad\uf7ae\uf7af" +
"\uf7b0\uf7b1\uf7b2\uf7b3\uf7b4\uf7b5\uf7b6\uf7b7" +
"\uf7b8\uf7b9\uf7ba\uf7bb\uf7bc\uf7bd\uf7be\uf7bf" +
"\uf7c0\uf7c1\uf7c2\uf7c3\uf7c4\uf7c5\uf7c6\uf7c7" +
"\uf7c8\uf7c9\uf7ca\uf7cb\uf7cc\uf7cd\uf7ce\uf7cf" +
"\uf7d0\uf7d1\uf7d2\uf7d3\uf7d4\uf7d5\uf7d6\uf7d7" +
"\uf7d8\uf7d9\uf7da\uf7db\uf7dc\uf7dd\uf7de\uf7df" +
"\uf7e0\uf7e1\uf7e2\uf7e3\uf7e4\uf7e5\uf7e6\uf7e7" +
"\uf7e8\uf7e9\uf7ea\uf7eb\uf7ec\uf7ed\uf7ee\uf7ef" +
"\uf7f0\uf7f1\uf7f2\uf7f3\uf7f4\uf7f5\uf7f6\uf7f7" +
"\uf7f8\uf7f9\uf7fa\uf7fb\uf7fc\uf7fd\uf7fe\uf7ff",
},
}
func getWHATWG(url string) string {
res, err := http.Get(url)
if err != nil {
log.Fatalf("%q: Get: %v", url, err)
}
defer res.Body.Close()
mapping := make([]rune, 128)
for i := range mapping {
mapping[i] = '\ufffd'
}
scanner := bufio.NewScanner(res.Body)
for scanner.Scan() {
s := strings.TrimSpace(scanner.Text())
if s == "" || s[0] == '#' {
continue
}
x, y := 0, 0
if _, err := fmt.Sscanf(s, "%d\t0x%x", &x, &y); err != nil {
log.Fatalf("could not parse %q", s)
}
if x < 0 || 128 <= x {
log.Fatalf("code %d is out of range", x)
}
if 0x80 <= y && y < 0xa0 {
// We diverge from the WHATWG spec by mapping control characters
// in the range [0x80, 0xa0) to U+FFFD.
continue
}
mapping[x] = rune(y)
}
return ascii + string(mapping)
}
func getUCM(url string) string {
res, err := http.Get(url)
if err != nil {
log.Fatalf("%q: Get: %v", url, err)
}
defer res.Body.Close()
mapping := make([]rune, 256)
for i := range mapping {
mapping[i] = '\ufffd'
}
charsFound := 0
scanner := bufio.NewScanner(res.Body)
for scanner.Scan() {
s := strings.TrimSpace(scanner.Text())
if s == "" || s[0] == '#' {
continue
}
var c byte
var r rune
if _, err := fmt.Sscanf(s, `<U%x> \x%x |0`, &r, &c); err != nil {
continue
}
mapping[c] = r
charsFound++
}
if charsFound < 200 {
log.Fatalf("%q: only %d characters found (wrong page format?)", url, charsFound)
}
return string(mapping)
}
func main() {
mibs := map[string]bool{}
all := []string{}
w := gen.NewCodeWriter()
defer w.WriteGoFile("tables.go", "charmap")
printf := func(s string, a ...interface{}) { fmt.Fprintf(w, s, a...) }
printf("import (\n")
printf("\t\"golang.org/x/text/encoding\"\n")
printf("\t\"golang.org/x/text/encoding/internal/identifier\"\n")
printf(")\n\n")
for _, e := range encodings {
varNames := strings.Split(e.varName, ",")
all = append(all, varNames...)
varName := varNames[0]
switch {
case strings.HasPrefix(e.mapping, "http://encoding.spec.whatwg.org/"):
e.mapping = getWHATWG(e.mapping)
case strings.HasPrefix(e.mapping, "http://source.icu-project.org/repos/icu/data/trunk/charset/data/ucm/"):
e.mapping = getUCM(e.mapping)
}
asciiSuperset, low := strings.HasPrefix(e.mapping, ascii), 0x00
if asciiSuperset {
low = 0x80
}
lvn := 1
if strings.HasPrefix(varName, "ISO") || strings.HasPrefix(varName, "KOI") {
lvn = 3
}
lowerVarName := strings.ToLower(varName[:lvn]) + varName[lvn:]
printf("// %s is the %s encoding.\n", varName, e.name)
if e.comment != "" {
printf("//\n// %s\n", e.comment)
}
printf("var %s *Charmap = &%s\n\nvar %s = Charmap{\nname: %q,\n",
varName, lowerVarName, lowerVarName, e.name)
if mibs[e.mib] {
log.Fatalf("MIB type %q declared multiple times.", e.mib)
}
printf("mib: identifier.%s,\n", e.mib)
printf("asciiSuperset: %t,\n", asciiSuperset)
printf("low: 0x%02x,\n", low)
printf("replacement: 0x%02x,\n", e.replacement)
printf("decode: [256]utf8Enc{\n")
i, backMapping := 0, map[rune]byte{}
for _, c := range e.mapping {
if _, ok := backMapping[c]; !ok && c != utf8.RuneError {
backMapping[c] = byte(i)
}
var buf [8]byte
n := utf8.EncodeRune(buf[:], c)
if n > 3 {
panic(fmt.Sprintf("rune %q (%U) is too long", c, c))
}
printf("{%d,[3]byte{0x%02x,0x%02x,0x%02x}},", n, buf[0], buf[1], buf[2])
if i%2 == 1 {
printf("\n")
}
i++
}
printf("},\n")
printf("encode: [256]uint32{\n")
encode := make([]uint32, 0, 256)
for c, i := range backMapping {
encode = append(encode, uint32(i)<<24|uint32(c))
}
sort.Sort(byRune(encode))
for len(encode) < cap(encode) {
encode = append(encode, encode[len(encode)-1])
}
for i, enc := range encode {
printf("0x%08x,", enc)
if i%8 == 7 {
printf("\n")
}
}
printf("},\n}\n")
// Add an estimate of the size of a single Charmap{} struct value, which
// includes two 256 elem arrays of 4 bytes and some extra fields, which
// align to 3 uint64s on 64-bit architectures.
w.Size += 2*4*256 + 3*8
}
// TODO: add proper line breaking.
printf("var listAll = []encoding.Encoding{\n%s,\n}\n\n", strings.Join(all, ",\n"))
}
type byRune []uint32
func (b byRune) Len() int { return len(b) }
func (b byRune) Less(i, j int) bool { return b[i]&0xffffff < b[j]&0xffffff }
func (b byRune) Swap(i, j int) { b[i], b[j] = b[j], b[i] }

View file

@ -124,7 +124,7 @@ func (e *Encoder) Writer(w io.Writer) io.Writer {
}
// ASCIISub is the ASCII substitute character, as recommended by
// http://unicode.org/reports/tr36/#Text_Comparison
// https://unicode.org/reports/tr36/#Text_Comparison
const ASCIISub = '\x1a'
// Nop is the nop encoding. Its transformed bytes are the same as the source

View file

@ -1,173 +0,0 @@
// 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/json"
"fmt"
"log"
"strings"
"golang.org/x/text/internal/gen"
)
type group struct {
Encodings []struct {
Labels []string
Name string
}
}
func main() {
gen.Init()
r := gen.Open("https://encoding.spec.whatwg.org", "whatwg", "encodings.json")
var groups []group
if err := json.NewDecoder(r).Decode(&groups); err != nil {
log.Fatalf("Error reading encodings.json: %v", err)
}
w := &bytes.Buffer{}
fmt.Fprintln(w, "type htmlEncoding byte")
fmt.Fprintln(w, "const (")
for i, g := range groups {
for _, e := range g.Encodings {
key := strings.ToLower(e.Name)
name := consts[key]
if name == "" {
log.Fatalf("No const defined for %s.", key)
}
if i == 0 {
fmt.Fprintf(w, "%s htmlEncoding = iota\n", name)
} else {
fmt.Fprintf(w, "%s\n", name)
}
}
}
fmt.Fprintln(w, "numEncodings")
fmt.Fprint(w, ")\n\n")
fmt.Fprintln(w, "var canonical = [numEncodings]string{")
for _, g := range groups {
for _, e := range g.Encodings {
fmt.Fprintf(w, "%q,\n", strings.ToLower(e.Name))
}
}
fmt.Fprint(w, "}\n\n")
fmt.Fprintln(w, "var nameMap = map[string]htmlEncoding{")
for _, g := range groups {
for _, e := range g.Encodings {
for _, l := range e.Labels {
key := strings.ToLower(e.Name)
name := consts[key]
fmt.Fprintf(w, "%q: %s,\n", l, name)
}
}
}
fmt.Fprint(w, "}\n\n")
var tags []string
fmt.Fprintln(w, "var localeMap = []htmlEncoding{")
for _, loc := range locales {
tags = append(tags, loc.tag)
fmt.Fprintf(w, "%s, // %s \n", consts[loc.name], loc.tag)
}
fmt.Fprint(w, "}\n\n")
fmt.Fprintf(w, "const locales = %q\n", strings.Join(tags, " "))
gen.WriteGoFile("tables.go", "htmlindex", w.Bytes())
}
// consts maps canonical encoding name to internal constant.
var consts = map[string]string{
"utf-8": "utf8",
"ibm866": "ibm866",
"iso-8859-2": "iso8859_2",
"iso-8859-3": "iso8859_3",
"iso-8859-4": "iso8859_4",
"iso-8859-5": "iso8859_5",
"iso-8859-6": "iso8859_6",
"iso-8859-7": "iso8859_7",
"iso-8859-8": "iso8859_8",
"iso-8859-8-i": "iso8859_8I",
"iso-8859-10": "iso8859_10",
"iso-8859-13": "iso8859_13",
"iso-8859-14": "iso8859_14",
"iso-8859-15": "iso8859_15",
"iso-8859-16": "iso8859_16",
"koi8-r": "koi8r",
"koi8-u": "koi8u",
"macintosh": "macintosh",
"windows-874": "windows874",
"windows-1250": "windows1250",
"windows-1251": "windows1251",
"windows-1252": "windows1252",
"windows-1253": "windows1253",
"windows-1254": "windows1254",
"windows-1255": "windows1255",
"windows-1256": "windows1256",
"windows-1257": "windows1257",
"windows-1258": "windows1258",
"x-mac-cyrillic": "macintoshCyrillic",
"gbk": "gbk",
"gb18030": "gb18030",
// "hz-gb-2312": "hzgb2312", // Was removed from WhatWG
"big5": "big5",
"euc-jp": "eucjp",
"iso-2022-jp": "iso2022jp",
"shift_jis": "shiftJIS",
"euc-kr": "euckr",
"replacement": "replacement",
"utf-16be": "utf16be",
"utf-16le": "utf16le",
"x-user-defined": "xUserDefined",
}
// locales is taken from
// https://html.spec.whatwg.org/multipage/syntax.html#encoding-sniffing-algorithm.
var locales = []struct{ tag, name string }{
// The default value. Explicitly state latin to benefit from the exact
// script option, while still making 1252 the default encoding for languages
// written in Latin script.
{"und_Latn", "windows-1252"},
{"ar", "windows-1256"},
{"ba", "windows-1251"},
{"be", "windows-1251"},
{"bg", "windows-1251"},
{"cs", "windows-1250"},
{"el", "iso-8859-7"},
{"et", "windows-1257"},
{"fa", "windows-1256"},
{"he", "windows-1255"},
{"hr", "windows-1250"},
{"hu", "iso-8859-2"},
{"ja", "shift_jis"},
{"kk", "windows-1251"},
{"ko", "euc-kr"},
{"ku", "windows-1254"},
{"ky", "windows-1251"},
{"lt", "windows-1257"},
{"lv", "windows-1257"},
{"mk", "windows-1251"},
{"pl", "iso-8859-2"},
{"ru", "windows-1251"},
{"sah", "windows-1251"},
{"sk", "windows-1250"},
{"sl", "iso-8859-2"},
{"sr", "windows-1251"},
{"tg", "windows-1251"},
{"th", "windows-874"},
{"tr", "windows-1254"},
{"tt", "windows-1251"},
{"uk", "windows-1251"},
{"vi", "windows-1258"},
{"zh-hans", "gb18030"},
{"zh-hant", "big5"},
}

View file

@ -306,6 +306,7 @@ var nameMap = map[string]htmlEncoding{
"iso-2022-cn": replacement,
"iso-2022-cn-ext": replacement,
"iso-2022-kr": replacement,
"replacement": replacement,
"utf-16be": utf16be,
"utf-16": utf16le,
"utf-16le": utf16le,

View file

@ -1,137 +0,0 @@
// 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 := &registry{}
if err := xml.NewDecoder(r).Decode(&reg); 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())
}

View file

@ -34,7 +34,7 @@ package identifier
// - 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/
// - https://www.unicode.org/reports/tr22/
// - http://www.w3.org/TR/encoding/
// - https://encoding.spec.whatwg.org/
// - https://encoding.spec.whatwg.org/encodings.json

View file

@ -538,8 +538,6 @@ const (
// ISO111ECMACyrillic is the MIB identifier with IANA name ECMA-cyrillic.
//
// ISO registry
// (formerly ECMA
// registry )
ISO111ECMACyrillic MIB = 77
// ISO121Canadian1 is the MIB identifier with IANA name CSA_Z243.4-1985-1.
@ -732,18 +730,18 @@ const (
// ISO885913 is the MIB identifier with IANA name ISO-8859-13.
//
// ISO See http://www.iana.org/assignments/charset-reg/ISO-8859-13 http://www.iana.org/assignments/charset-reg/ISO-8859-13
// ISO See https://www.iana.org/assignments/charset-reg/ISO-8859-13 https://www.iana.org/assignments/charset-reg/ISO-8859-13
ISO885913 MIB = 109
// ISO885914 is the MIB identifier with IANA name ISO-8859-14.
//
// ISO See http://www.iana.org/assignments/charset-reg/ISO-8859-14
// ISO See https://www.iana.org/assignments/charset-reg/ISO-8859-14
ISO885914 MIB = 110
// ISO885915 is the MIB identifier with IANA name ISO-8859-15.
//
// ISO
// Please see: http://www.iana.org/assignments/charset-reg/ISO-8859-15
// Please see: https://www.iana.org/assignments/charset-reg/ISO-8859-15
ISO885915 MIB = 111
// ISO885916 is the MIB identifier with IANA name ISO-8859-16.
@ -754,41 +752,41 @@ const (
// GBK is the MIB identifier with IANA name GBK.
//
// Chinese IT Standardization Technical Committee
// Please see: http://www.iana.org/assignments/charset-reg/GBK
// Please see: https://www.iana.org/assignments/charset-reg/GBK
GBK MIB = 113
// GB18030 is the MIB identifier with IANA name GB18030.
//
// Chinese IT Standardization Technical Committee
// Please see: http://www.iana.org/assignments/charset-reg/GB18030
// Please see: https://www.iana.org/assignments/charset-reg/GB18030
GB18030 MIB = 114
// OSDEBCDICDF0415 is the MIB identifier with IANA name OSD_EBCDIC_DF04_15.
//
// Fujitsu-Siemens standard mainframe EBCDIC encoding
// Please see: http://www.iana.org/assignments/charset-reg/OSD-EBCDIC-DF04-15
// Please see: https://www.iana.org/assignments/charset-reg/OSD-EBCDIC-DF04-15
OSDEBCDICDF0415 MIB = 115
// OSDEBCDICDF03IRV is the MIB identifier with IANA name OSD_EBCDIC_DF03_IRV.
//
// Fujitsu-Siemens standard mainframe EBCDIC encoding
// Please see: http://www.iana.org/assignments/charset-reg/OSD-EBCDIC-DF03-IRV
// Please see: https://www.iana.org/assignments/charset-reg/OSD-EBCDIC-DF03-IRV
OSDEBCDICDF03IRV MIB = 116
// OSDEBCDICDF041 is the MIB identifier with IANA name OSD_EBCDIC_DF04_1.
//
// Fujitsu-Siemens standard mainframe EBCDIC encoding
// Please see: http://www.iana.org/assignments/charset-reg/OSD-EBCDIC-DF04-1
// Please see: https://www.iana.org/assignments/charset-reg/OSD-EBCDIC-DF04-1
OSDEBCDICDF041 MIB = 117
// ISO115481 is the MIB identifier with IANA name ISO-11548-1.
//
// See http://www.iana.org/assignments/charset-reg/ISO-11548-1
// See https://www.iana.org/assignments/charset-reg/ISO-11548-1
ISO115481 MIB = 118
// KZ1048 is the MIB identifier with IANA name KZ-1048.
//
// See http://www.iana.org/assignments/charset-reg/KZ-1048
// See https://www.iana.org/assignments/charset-reg/KZ-1048
KZ1048 MIB = 119
// Unicode is the MIB identifier with IANA name ISO-10646-UCS-2.
@ -855,7 +853,7 @@ const (
// SCSU is the MIB identifier with IANA name SCSU.
//
// SCSU See http://www.iana.org/assignments/charset-reg/SCSU
// SCSU See https://www.iana.org/assignments/charset-reg/SCSU
SCSU MIB = 1011
// UTF7 is the MIB identifier with IANA name UTF-7.
@ -884,27 +882,27 @@ const (
// CESU8 is the MIB identifier with IANA name CESU-8.
//
// http://www.unicode.org/unicode/reports/tr26
// https://www.unicode.org/reports/tr26
CESU8 MIB = 1016
// UTF32 is the MIB identifier with IANA name UTF-32.
//
// http://www.unicode.org/unicode/reports/tr19/
// https://www.unicode.org/reports/tr19/
UTF32 MIB = 1017
// UTF32BE is the MIB identifier with IANA name UTF-32BE.
//
// http://www.unicode.org/unicode/reports/tr19/
// https://www.unicode.org/reports/tr19/
UTF32BE MIB = 1018
// UTF32LE is the MIB identifier with IANA name UTF-32LE.
//
// http://www.unicode.org/unicode/reports/tr19/
// https://www.unicode.org/reports/tr19/
UTF32LE MIB = 1019
// BOCU1 is the MIB identifier with IANA name BOCU-1.
//
// http://www.unicode.org/notes/tn6/
// https://www.unicode.org/notes/tn6/
BOCU1 MIB = 1020
// Windows30Latin1 is the MIB identifier with IANA name ISO-8859-1-Windows-3.0-Latin-1.
@ -1461,152 +1459,152 @@ const (
// IBM00858 is the MIB identifier with IANA name IBM00858.
//
// IBM See http://www.iana.org/assignments/charset-reg/IBM00858
// IBM See https://www.iana.org/assignments/charset-reg/IBM00858
IBM00858 MIB = 2089
// IBM00924 is the MIB identifier with IANA name IBM00924.
//
// IBM See http://www.iana.org/assignments/charset-reg/IBM00924
// IBM See https://www.iana.org/assignments/charset-reg/IBM00924
IBM00924 MIB = 2090
// IBM01140 is the MIB identifier with IANA name IBM01140.
//
// IBM See http://www.iana.org/assignments/charset-reg/IBM01140
// IBM See https://www.iana.org/assignments/charset-reg/IBM01140
IBM01140 MIB = 2091
// IBM01141 is the MIB identifier with IANA name IBM01141.
//
// IBM See http://www.iana.org/assignments/charset-reg/IBM01141
// IBM See https://www.iana.org/assignments/charset-reg/IBM01141
IBM01141 MIB = 2092
// IBM01142 is the MIB identifier with IANA name IBM01142.
//
// IBM See http://www.iana.org/assignments/charset-reg/IBM01142
// IBM See https://www.iana.org/assignments/charset-reg/IBM01142
IBM01142 MIB = 2093
// IBM01143 is the MIB identifier with IANA name IBM01143.
//
// IBM See http://www.iana.org/assignments/charset-reg/IBM01143
// IBM See https://www.iana.org/assignments/charset-reg/IBM01143
IBM01143 MIB = 2094
// IBM01144 is the MIB identifier with IANA name IBM01144.
//
// IBM See http://www.iana.org/assignments/charset-reg/IBM01144
// IBM See https://www.iana.org/assignments/charset-reg/IBM01144
IBM01144 MIB = 2095
// IBM01145 is the MIB identifier with IANA name IBM01145.
//
// IBM See http://www.iana.org/assignments/charset-reg/IBM01145
// IBM See https://www.iana.org/assignments/charset-reg/IBM01145
IBM01145 MIB = 2096
// IBM01146 is the MIB identifier with IANA name IBM01146.
//
// IBM See http://www.iana.org/assignments/charset-reg/IBM01146
// IBM See https://www.iana.org/assignments/charset-reg/IBM01146
IBM01146 MIB = 2097
// IBM01147 is the MIB identifier with IANA name IBM01147.
//
// IBM See http://www.iana.org/assignments/charset-reg/IBM01147
// IBM See https://www.iana.org/assignments/charset-reg/IBM01147
IBM01147 MIB = 2098
// IBM01148 is the MIB identifier with IANA name IBM01148.
//
// IBM See http://www.iana.org/assignments/charset-reg/IBM01148
// IBM See https://www.iana.org/assignments/charset-reg/IBM01148
IBM01148 MIB = 2099
// IBM01149 is the MIB identifier with IANA name IBM01149.
//
// IBM See http://www.iana.org/assignments/charset-reg/IBM01149
// IBM See https://www.iana.org/assignments/charset-reg/IBM01149
IBM01149 MIB = 2100
// Big5HKSCS is the MIB identifier with IANA name Big5-HKSCS.
//
// See http://www.iana.org/assignments/charset-reg/Big5-HKSCS
// See https://www.iana.org/assignments/charset-reg/Big5-HKSCS
Big5HKSCS MIB = 2101
// IBM1047 is the MIB identifier with IANA name IBM1047.
//
// IBM1047 (EBCDIC Latin 1/Open Systems) http://www-1.ibm.com/servers/eserver/iseries/software/globalization/pdf/cp01047z.pdf
// IBM1047 (EBCDIC Latin 1/Open Systems) https://www-1.ibm.com/servers/eserver/iseries/software/globalization/pdf/cp01047z.pdf
IBM1047 MIB = 2102
// PTCP154 is the MIB identifier with IANA name PTCP154.
//
// See http://www.iana.org/assignments/charset-reg/PTCP154
// See https://www.iana.org/assignments/charset-reg/PTCP154
PTCP154 MIB = 2103
// Amiga1251 is the MIB identifier with IANA name Amiga-1251.
//
// See http://www.amiga.ultranet.ru/Amiga-1251.html
// See https://www.amiga.ultranet.ru/Amiga-1251.html
Amiga1251 MIB = 2104
// KOI7switched is the MIB identifier with IANA name KOI7-switched.
//
// See http://www.iana.org/assignments/charset-reg/KOI7-switched
// See https://www.iana.org/assignments/charset-reg/KOI7-switched
KOI7switched MIB = 2105
// BRF is the MIB identifier with IANA name BRF.
//
// See http://www.iana.org/assignments/charset-reg/BRF
// See https://www.iana.org/assignments/charset-reg/BRF
BRF MIB = 2106
// TSCII is the MIB identifier with IANA name TSCII.
//
// See http://www.iana.org/assignments/charset-reg/TSCII
// See https://www.iana.org/assignments/charset-reg/TSCII
TSCII MIB = 2107
// CP51932 is the MIB identifier with IANA name CP51932.
//
// See http://www.iana.org/assignments/charset-reg/CP51932
// See https://www.iana.org/assignments/charset-reg/CP51932
CP51932 MIB = 2108
// Windows874 is the MIB identifier with IANA name windows-874.
//
// See http://www.iana.org/assignments/charset-reg/windows-874
// See https://www.iana.org/assignments/charset-reg/windows-874
Windows874 MIB = 2109
// Windows1250 is the MIB identifier with IANA name windows-1250.
//
// Microsoft http://www.iana.org/assignments/charset-reg/windows-1250
// Microsoft https://www.iana.org/assignments/charset-reg/windows-1250
Windows1250 MIB = 2250
// Windows1251 is the MIB identifier with IANA name windows-1251.
//
// Microsoft http://www.iana.org/assignments/charset-reg/windows-1251
// Microsoft https://www.iana.org/assignments/charset-reg/windows-1251
Windows1251 MIB = 2251
// Windows1252 is the MIB identifier with IANA name windows-1252.
//
// Microsoft http://www.iana.org/assignments/charset-reg/windows-1252
// Microsoft https://www.iana.org/assignments/charset-reg/windows-1252
Windows1252 MIB = 2252
// Windows1253 is the MIB identifier with IANA name windows-1253.
//
// Microsoft http://www.iana.org/assignments/charset-reg/windows-1253
// Microsoft https://www.iana.org/assignments/charset-reg/windows-1253
Windows1253 MIB = 2253
// Windows1254 is the MIB identifier with IANA name windows-1254.
//
// Microsoft http://www.iana.org/assignments/charset-reg/windows-1254
// Microsoft https://www.iana.org/assignments/charset-reg/windows-1254
Windows1254 MIB = 2254
// Windows1255 is the MIB identifier with IANA name windows-1255.
//
// Microsoft http://www.iana.org/assignments/charset-reg/windows-1255
// Microsoft https://www.iana.org/assignments/charset-reg/windows-1255
Windows1255 MIB = 2255
// Windows1256 is the MIB identifier with IANA name windows-1256.
//
// Microsoft http://www.iana.org/assignments/charset-reg/windows-1256
// Microsoft https://www.iana.org/assignments/charset-reg/windows-1256
Windows1256 MIB = 2256
// Windows1257 is the MIB identifier with IANA name windows-1257.
//
// Microsoft http://www.iana.org/assignments/charset-reg/windows-1257
// Microsoft https://www.iana.org/assignments/charset-reg/windows-1257
Windows1257 MIB = 2257
// Windows1258 is the MIB identifier with IANA name windows-1258.
//
// Microsoft http://www.iana.org/assignments/charset-reg/windows-1258
// Microsoft https://www.iana.org/assignments/charset-reg/windows-1258
Windows1258 MIB = 2258
// TIS620 is the MIB identifier with IANA name TIS-620.
@ -1616,6 +1614,6 @@ const (
// CP50220 is the MIB identifier with IANA name CP50220.
//
// See http://www.iana.org/assignments/charset-reg/CP50220
// See https://www.iana.org/assignments/charset-reg/CP50220
CP50220 MIB = 2260
)

View file

@ -1,161 +0,0 @@
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build ignore
package main
// This program generates tables.go:
// go run maketables.go | gofmt > tables.go
// TODO: Emoji extensions?
// http://www.unicode.org/faq/emoji_dingbats.html
// http://www.unicode.org/Public/UNIDATA/EmojiSources.txt
import (
"bufio"
"fmt"
"log"
"net/http"
"sort"
"strings"
)
type entry struct {
jisCode, table int
}
func main() {
fmt.Printf("// generated by go run maketables.go; DO NOT EDIT\n\n")
fmt.Printf("// Package japanese provides Japanese encodings such as EUC-JP and Shift JIS.\n")
fmt.Printf(`package japanese // import "golang.org/x/text/encoding/japanese"` + "\n\n")
reverse := [65536]entry{}
for i := range reverse {
reverse[i].table = -1
}
tables := []struct {
url string
name string
}{
{"http://encoding.spec.whatwg.org/index-jis0208.txt", "0208"},
{"http://encoding.spec.whatwg.org/index-jis0212.txt", "0212"},
}
for i, table := range tables {
res, err := http.Get(table.url)
if err != nil {
log.Fatalf("%q: Get: %v", table.url, err)
}
defer res.Body.Close()
mapping := [65536]uint16{}
scanner := bufio.NewScanner(res.Body)
for scanner.Scan() {
s := strings.TrimSpace(scanner.Text())
if s == "" || s[0] == '#' {
continue
}
x, y := 0, uint16(0)
if _, err := fmt.Sscanf(s, "%d 0x%x", &x, &y); err != nil {
log.Fatalf("%q: could not parse %q", table.url, s)
}
if x < 0 || 120*94 <= x {
log.Fatalf("%q: JIS code %d is out of range", table.url, x)
}
mapping[x] = y
if reverse[y].table == -1 {
reverse[y] = entry{jisCode: x, table: i}
}
}
if err := scanner.Err(); err != nil {
log.Fatalf("%q: scanner error: %v", table.url, err)
}
fmt.Printf("// jis%sDecode is the decoding table from JIS %s code to Unicode.\n// It is defined at %s\n",
table.name, table.name, table.url)
fmt.Printf("var jis%sDecode = [...]uint16{\n", table.name)
for i, m := range mapping {
if m != 0 {
fmt.Printf("\t%d: 0x%04X,\n", i, m)
}
}
fmt.Printf("}\n\n")
}
// Any run of at least separation continuous zero entries in the reverse map will
// be a separate encode table.
const separation = 1024
intervals := []interval(nil)
low, high := -1, -1
for i, v := range reverse {
if v.table == -1 {
continue
}
if low < 0 {
low = i
} else if i-high >= separation {
if high >= 0 {
intervals = append(intervals, interval{low, high})
}
low = i
}
high = i + 1
}
if high >= 0 {
intervals = append(intervals, interval{low, high})
}
sort.Sort(byDecreasingLength(intervals))
fmt.Printf("const (\n")
fmt.Printf("\tjis0208 = 1\n")
fmt.Printf("\tjis0212 = 2\n")
fmt.Printf("\tcodeMask = 0x7f\n")
fmt.Printf("\tcodeShift = 7\n")
fmt.Printf("\ttableShift = 14\n")
fmt.Printf(")\n\n")
fmt.Printf("const numEncodeTables = %d\n\n", len(intervals))
fmt.Printf("// encodeX are the encoding tables from Unicode to JIS code,\n")
fmt.Printf("// sorted by decreasing length.\n")
for i, v := range intervals {
fmt.Printf("// encode%d: %5d entries for runes in [%5d, %5d).\n", i, v.len(), v.low, v.high)
}
fmt.Printf("//\n")
fmt.Printf("// The high two bits of the value record whether the JIS code comes from the\n")
fmt.Printf("// JIS0208 table (high bits == 1) or the JIS0212 table (high bits == 2).\n")
fmt.Printf("// The low 14 bits are two 7-bit unsigned integers j1 and j2 that form the\n")
fmt.Printf("// JIS code (94*j1 + j2) within that table.\n")
fmt.Printf("\n")
for i, v := range intervals {
fmt.Printf("const encode%dLow, encode%dHigh = %d, %d\n\n", i, i, v.low, v.high)
fmt.Printf("var encode%d = [...]uint16{\n", i)
for j := v.low; j < v.high; j++ {
x := reverse[j]
if x.table == -1 {
continue
}
fmt.Printf("\t%d - %d: jis%s<<14 | 0x%02X<<7 | 0x%02X,\n",
j, v.low, tables[x.table].name, x.jisCode/94, x.jisCode%94)
}
fmt.Printf("}\n\n")
}
}
// interval is a half-open interval [low, high).
type interval struct {
low, high int
}
func (i interval) len() int { return i.high - i.low }
// byDecreasingLength sorts intervals by decreasing length.
type byDecreasingLength []interval
func (b byDecreasingLength) Len() int { return len(b) }
func (b byDecreasingLength) Less(i, j int) bool { return b[i].len() > b[j].len() }
func (b byDecreasingLength) Swap(i, j int) { b[i], b[j] = b[j], b[i] }

View file

@ -1,143 +0,0 @@
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build ignore
package main
// This program generates tables.go:
// go run maketables.go | gofmt > tables.go
import (
"bufio"
"fmt"
"log"
"net/http"
"sort"
"strings"
)
func main() {
fmt.Printf("// generated by go run maketables.go; DO NOT EDIT\n\n")
fmt.Printf("// Package korean provides Korean encodings such as EUC-KR.\n")
fmt.Printf(`package korean // import "golang.org/x/text/encoding/korean"` + "\n\n")
res, err := http.Get("http://encoding.spec.whatwg.org/index-euc-kr.txt")
if err != nil {
log.Fatalf("Get: %v", err)
}
defer res.Body.Close()
mapping := [65536]uint16{}
reverse := [65536]uint16{}
scanner := bufio.NewScanner(res.Body)
for scanner.Scan() {
s := strings.TrimSpace(scanner.Text())
if s == "" || s[0] == '#' {
continue
}
x, y := uint16(0), uint16(0)
if _, err := fmt.Sscanf(s, "%d 0x%x", &x, &y); err != nil {
log.Fatalf("could not parse %q", s)
}
if x < 0 || 178*(0xc7-0x81)+(0xfe-0xc7)*94+(0xff-0xa1) <= x {
log.Fatalf("EUC-KR code %d is out of range", x)
}
mapping[x] = y
if reverse[y] == 0 {
c0, c1 := uint16(0), uint16(0)
if x < 178*(0xc7-0x81) {
c0 = uint16(x/178) + 0x81
c1 = uint16(x % 178)
switch {
case c1 < 1*26:
c1 += 0x41
case c1 < 2*26:
c1 += 0x47
default:
c1 += 0x4d
}
} else {
x -= 178 * (0xc7 - 0x81)
c0 = uint16(x/94) + 0xc7
c1 = uint16(x%94) + 0xa1
}
reverse[y] = c0<<8 | c1
}
}
if err := scanner.Err(); err != nil {
log.Fatalf("scanner error: %v", err)
}
fmt.Printf("// decode is the decoding table from EUC-KR code to Unicode.\n")
fmt.Printf("// It is defined at http://encoding.spec.whatwg.org/index-euc-kr.txt\n")
fmt.Printf("var decode = [...]uint16{\n")
for i, v := range mapping {
if v != 0 {
fmt.Printf("\t%d: 0x%04X,\n", i, v)
}
}
fmt.Printf("}\n\n")
// Any run of at least separation continuous zero entries in the reverse map will
// be a separate encode table.
const separation = 1024
intervals := []interval(nil)
low, high := -1, -1
for i, v := range reverse {
if v == 0 {
continue
}
if low < 0 {
low = i
} else if i-high >= separation {
if high >= 0 {
intervals = append(intervals, interval{low, high})
}
low = i
}
high = i + 1
}
if high >= 0 {
intervals = append(intervals, interval{low, high})
}
sort.Sort(byDecreasingLength(intervals))
fmt.Printf("const numEncodeTables = %d\n\n", len(intervals))
fmt.Printf("// encodeX are the encoding tables from Unicode to EUC-KR code,\n")
fmt.Printf("// sorted by decreasing length.\n")
for i, v := range intervals {
fmt.Printf("// encode%d: %5d entries for runes in [%5d, %5d).\n", i, v.len(), v.low, v.high)
}
fmt.Printf("\n")
for i, v := range intervals {
fmt.Printf("const encode%dLow, encode%dHigh = %d, %d\n\n", i, i, v.low, v.high)
fmt.Printf("var encode%d = [...]uint16{\n", i)
for j := v.low; j < v.high; j++ {
x := reverse[j]
if x == 0 {
continue
}
fmt.Printf("\t%d-%d: 0x%04X,\n", j, v.low, x)
}
fmt.Printf("}\n\n")
}
}
// interval is a half-open interval [low, high).
type interval struct {
low, high int
}
func (i interval) len() int { return i.high - i.low }
// byDecreasingLength sorts intervals by decreasing length.
type byDecreasingLength []interval
func (b byDecreasingLength) Len() int { return len(b) }
func (b byDecreasingLength) Less(i, j int) bool { return b[i].len() > b[j].len() }
func (b byDecreasingLength) Swap(i, j int) { b[i], b[j] = b[j], b[i] }

View file

@ -1,161 +0,0 @@
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build ignore
package main
// This program generates tables.go:
// go run maketables.go | gofmt > tables.go
import (
"bufio"
"fmt"
"log"
"net/http"
"sort"
"strings"
)
func main() {
fmt.Printf("// generated by go run maketables.go; DO NOT EDIT\n\n")
fmt.Printf("// Package simplifiedchinese provides Simplified Chinese encodings such as GBK.\n")
fmt.Printf(`package simplifiedchinese // import "golang.org/x/text/encoding/simplifiedchinese"` + "\n\n")
printGB18030()
printGBK()
}
func printGB18030() {
res, err := http.Get("http://encoding.spec.whatwg.org/index-gb18030.txt")
if err != nil {
log.Fatalf("Get: %v", err)
}
defer res.Body.Close()
fmt.Printf("// gb18030 is the table from http://encoding.spec.whatwg.org/index-gb18030.txt\n")
fmt.Printf("var gb18030 = [...][2]uint16{\n")
scanner := bufio.NewScanner(res.Body)
for scanner.Scan() {
s := strings.TrimSpace(scanner.Text())
if s == "" || s[0] == '#' {
continue
}
x, y := uint32(0), uint32(0)
if _, err := fmt.Sscanf(s, "%d 0x%x", &x, &y); err != nil {
log.Fatalf("could not parse %q", s)
}
if x < 0x10000 && y < 0x10000 {
fmt.Printf("\t{0x%04x, 0x%04x},\n", x, y)
}
}
fmt.Printf("}\n\n")
}
func printGBK() {
res, err := http.Get("http://encoding.spec.whatwg.org/index-gbk.txt")
if err != nil {
log.Fatalf("Get: %v", err)
}
defer res.Body.Close()
mapping := [65536]uint16{}
reverse := [65536]uint16{}
scanner := bufio.NewScanner(res.Body)
for scanner.Scan() {
s := strings.TrimSpace(scanner.Text())
if s == "" || s[0] == '#' {
continue
}
x, y := uint16(0), uint16(0)
if _, err := fmt.Sscanf(s, "%d 0x%x", &x, &y); err != nil {
log.Fatalf("could not parse %q", s)
}
if x < 0 || 126*190 <= x {
log.Fatalf("GBK code %d is out of range", x)
}
mapping[x] = y
if reverse[y] == 0 {
c0, c1 := x/190, x%190
if c1 >= 0x3f {
c1++
}
reverse[y] = (0x81+c0)<<8 | (0x40 + c1)
}
}
if err := scanner.Err(); err != nil {
log.Fatalf("scanner error: %v", err)
}
fmt.Printf("// decode is the decoding table from GBK code to Unicode.\n")
fmt.Printf("// It is defined at http://encoding.spec.whatwg.org/index-gbk.txt\n")
fmt.Printf("var decode = [...]uint16{\n")
for i, v := range mapping {
if v != 0 {
fmt.Printf("\t%d: 0x%04X,\n", i, v)
}
}
fmt.Printf("}\n\n")
// Any run of at least separation continuous zero entries in the reverse map will
// be a separate encode table.
const separation = 1024
intervals := []interval(nil)
low, high := -1, -1
for i, v := range reverse {
if v == 0 {
continue
}
if low < 0 {
low = i
} else if i-high >= separation {
if high >= 0 {
intervals = append(intervals, interval{low, high})
}
low = i
}
high = i + 1
}
if high >= 0 {
intervals = append(intervals, interval{low, high})
}
sort.Sort(byDecreasingLength(intervals))
fmt.Printf("const numEncodeTables = %d\n\n", len(intervals))
fmt.Printf("// encodeX are the encoding tables from Unicode to GBK code,\n")
fmt.Printf("// sorted by decreasing length.\n")
for i, v := range intervals {
fmt.Printf("// encode%d: %5d entries for runes in [%5d, %5d).\n", i, v.len(), v.low, v.high)
}
fmt.Printf("\n")
for i, v := range intervals {
fmt.Printf("const encode%dLow, encode%dHigh = %d, %d\n\n", i, i, v.low, v.high)
fmt.Printf("var encode%d = [...]uint16{\n", i)
for j := v.low; j < v.high; j++ {
x := reverse[j]
if x == 0 {
continue
}
fmt.Printf("\t%d-%d: 0x%04X,\n", j, v.low, x)
}
fmt.Printf("}\n\n")
}
}
// interval is a half-open interval [low, high).
type interval struct {
low, high int
}
func (i interval) len() int { return i.high - i.low }
// byDecreasingLength sorts intervals by decreasing length.
type byDecreasingLength []interval
func (b byDecreasingLength) Len() int { return len(b) }
func (b byDecreasingLength) Less(i, j int) bool { return b[i].len() > b[j].len() }
func (b byDecreasingLength) Swap(i, j int) { b[i], b[j] = b[j], b[i] }

View file

@ -1,140 +0,0 @@
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build ignore
package main
// This program generates tables.go:
// go run maketables.go | gofmt > tables.go
import (
"bufio"
"fmt"
"log"
"net/http"
"sort"
"strings"
)
func main() {
fmt.Printf("// generated by go run maketables.go; DO NOT EDIT\n\n")
fmt.Printf("// Package traditionalchinese provides Traditional Chinese encodings such as Big5.\n")
fmt.Printf(`package traditionalchinese // import "golang.org/x/text/encoding/traditionalchinese"` + "\n\n")
res, err := http.Get("http://encoding.spec.whatwg.org/index-big5.txt")
if err != nil {
log.Fatalf("Get: %v", err)
}
defer res.Body.Close()
mapping := [65536]uint32{}
reverse := [65536 * 4]uint16{}
scanner := bufio.NewScanner(res.Body)
for scanner.Scan() {
s := strings.TrimSpace(scanner.Text())
if s == "" || s[0] == '#' {
continue
}
x, y := uint16(0), uint32(0)
if _, err := fmt.Sscanf(s, "%d 0x%x", &x, &y); err != nil {
log.Fatalf("could not parse %q", s)
}
if x < 0 || 126*157 <= x {
log.Fatalf("Big5 code %d is out of range", x)
}
mapping[x] = y
// The WHATWG spec http://encoding.spec.whatwg.org/#indexes says that
// "The index pointer for code point in index is the first pointer
// corresponding to code point in index", which would normally mean
// that the code below should be guarded by "if reverse[y] == 0", but
// last instead of first seems to match the behavior of
// "iconv -f UTF-8 -t BIG5". For example, U+8005 者 occurs twice in
// http://encoding.spec.whatwg.org/index-big5.txt, as index 2148
// (encoded as "\x8e\xcd") and index 6543 (encoded as "\xaa\xcc")
// and "echo 者 | iconv -f UTF-8 -t BIG5 | xxd" gives "\xaa\xcc".
c0, c1 := x/157, x%157
if c1 < 0x3f {
c1 += 0x40
} else {
c1 += 0x62
}
reverse[y] = (0x81+c0)<<8 | c1
}
if err := scanner.Err(); err != nil {
log.Fatalf("scanner error: %v", err)
}
fmt.Printf("// decode is the decoding table from Big5 code to Unicode.\n")
fmt.Printf("// It is defined at http://encoding.spec.whatwg.org/index-big5.txt\n")
fmt.Printf("var decode = [...]uint32{\n")
for i, v := range mapping {
if v != 0 {
fmt.Printf("\t%d: 0x%08X,\n", i, v)
}
}
fmt.Printf("}\n\n")
// Any run of at least separation continuous zero entries in the reverse map will
// be a separate encode table.
const separation = 1024
intervals := []interval(nil)
low, high := -1, -1
for i, v := range reverse {
if v == 0 {
continue
}
if low < 0 {
low = i
} else if i-high >= separation {
if high >= 0 {
intervals = append(intervals, interval{low, high})
}
low = i
}
high = i + 1
}
if high >= 0 {
intervals = append(intervals, interval{low, high})
}
sort.Sort(byDecreasingLength(intervals))
fmt.Printf("const numEncodeTables = %d\n\n", len(intervals))
fmt.Printf("// encodeX are the encoding tables from Unicode to Big5 code,\n")
fmt.Printf("// sorted by decreasing length.\n")
for i, v := range intervals {
fmt.Printf("// encode%d: %5d entries for runes in [%6d, %6d).\n", i, v.len(), v.low, v.high)
}
fmt.Printf("\n")
for i, v := range intervals {
fmt.Printf("const encode%dLow, encode%dHigh = %d, %d\n\n", i, i, v.low, v.high)
fmt.Printf("var encode%d = [...]uint16{\n", i)
for j := v.low; j < v.high; j++ {
x := reverse[j]
if x == 0 {
continue
}
fmt.Printf("\t%d-%d: 0x%04X,\n", j, v.low, x)
}
fmt.Printf("}\n\n")
}
}
// interval is a half-open interval [low, high).
type interval struct {
low, high int
}
func (i interval) len() int { return i.high - i.low }
// byDecreasingLength sorts intervals by decreasing length.
type byDecreasingLength []interval
func (b byDecreasingLength) Len() int { return len(b) }
func (b byDecreasingLength) Less(i, j int) bool { return b[i].len() > b[j].len() }
func (b byDecreasingLength) Swap(i, j int) { b[i], b[j] = b[j], b[i] }

View file

@ -145,7 +145,7 @@ func (utf8Decoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err e
// 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
// In the language of https://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".