mirror of
https://github.com/TECHNOFAB11/zfs-localpv.git
synced 2025-12-12 06:20:11 +01:00
test(zfspv): vendor for ginkgo test code
Signed-off-by: Pawan <pawan@mayadata.io>
This commit is contained in:
parent
d933b47c75
commit
c3c5eb1794
305 changed files with 194450 additions and 1812 deletions
78
vendor/golang.org/x/net/html/atom/atom.go
generated
vendored
Normal file
78
vendor/golang.org/x/net/html/atom/atom.go
generated
vendored
Normal file
|
|
@ -0,0 +1,78 @@
|
|||
// Copyright 2012 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 atom provides integer codes (also known as atoms) for a fixed set of
|
||||
// frequently occurring HTML strings: tag names and attribute keys such as "p"
|
||||
// and "id".
|
||||
//
|
||||
// Sharing an atom's name between all elements with the same tag can result in
|
||||
// fewer string allocations when tokenizing and parsing HTML. Integer
|
||||
// comparisons are also generally faster than string comparisons.
|
||||
//
|
||||
// The value of an atom's particular code is not guaranteed to stay the same
|
||||
// between versions of this package. Neither is any ordering guaranteed:
|
||||
// whether atom.H1 < atom.H2 may also change. The codes are not guaranteed to
|
||||
// be dense. The only guarantees are that e.g. looking up "div" will yield
|
||||
// atom.Div, calling atom.Div.String will return "div", and atom.Div != 0.
|
||||
package atom // import "golang.org/x/net/html/atom"
|
||||
|
||||
// Atom is an integer code for a string. The zero value maps to "".
|
||||
type Atom uint32
|
||||
|
||||
// String returns the atom's name.
|
||||
func (a Atom) String() string {
|
||||
start := uint32(a >> 8)
|
||||
n := uint32(a & 0xff)
|
||||
if start+n > uint32(len(atomText)) {
|
||||
return ""
|
||||
}
|
||||
return atomText[start : start+n]
|
||||
}
|
||||
|
||||
func (a Atom) string() string {
|
||||
return atomText[a>>8 : a>>8+a&0xff]
|
||||
}
|
||||
|
||||
// fnv computes the FNV hash with an arbitrary starting value h.
|
||||
func fnv(h uint32, s []byte) uint32 {
|
||||
for i := range s {
|
||||
h ^= uint32(s[i])
|
||||
h *= 16777619
|
||||
}
|
||||
return h
|
||||
}
|
||||
|
||||
func match(s string, t []byte) bool {
|
||||
for i, c := range t {
|
||||
if s[i] != c {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// Lookup returns the atom whose name is s. It returns zero if there is no
|
||||
// such atom. The lookup is case sensitive.
|
||||
func Lookup(s []byte) Atom {
|
||||
if len(s) == 0 || len(s) > maxAtomLen {
|
||||
return 0
|
||||
}
|
||||
h := fnv(hash0, s)
|
||||
if a := table[h&uint32(len(table)-1)]; int(a&0xff) == len(s) && match(a.string(), s) {
|
||||
return a
|
||||
}
|
||||
if a := table[(h>>16)&uint32(len(table)-1)]; int(a&0xff) == len(s) && match(a.string(), s) {
|
||||
return a
|
||||
}
|
||||
return 0
|
||||
}
|
||||
|
||||
// String returns a string whose contents are equal to s. In that sense, it is
|
||||
// equivalent to string(s) but may be more efficient.
|
||||
func String(s []byte) string {
|
||||
if a := Lookup(s); a != 0 {
|
||||
return a.String()
|
||||
}
|
||||
return string(s)
|
||||
}
|
||||
712
vendor/golang.org/x/net/html/atom/gen.go
generated
vendored
Normal file
712
vendor/golang.org/x/net/html/atom/gen.go
generated
vendored
Normal file
|
|
@ -0,0 +1,712 @@
|
|||
// Copyright 2012 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
|
||||
|
||||
//go:generate go run gen.go
|
||||
//go:generate go run gen.go -test
|
||||
|
||||
package main
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"flag"
|
||||
"fmt"
|
||||
"go/format"
|
||||
"io/ioutil"
|
||||
"math/rand"
|
||||
"os"
|
||||
"sort"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// identifier converts s to a Go exported identifier.
|
||||
// It converts "div" to "Div" and "accept-charset" to "AcceptCharset".
|
||||
func identifier(s string) string {
|
||||
b := make([]byte, 0, len(s))
|
||||
cap := true
|
||||
for _, c := range s {
|
||||
if c == '-' {
|
||||
cap = true
|
||||
continue
|
||||
}
|
||||
if cap && 'a' <= c && c <= 'z' {
|
||||
c -= 'a' - 'A'
|
||||
}
|
||||
cap = false
|
||||
b = append(b, byte(c))
|
||||
}
|
||||
return string(b)
|
||||
}
|
||||
|
||||
var test = flag.Bool("test", false, "generate table_test.go")
|
||||
|
||||
func genFile(name string, buf *bytes.Buffer) {
|
||||
b, err := format.Source(buf.Bytes())
|
||||
if err != nil {
|
||||
fmt.Fprintln(os.Stderr, err)
|
||||
os.Exit(1)
|
||||
}
|
||||
if err := ioutil.WriteFile(name, b, 0644); err != nil {
|
||||
fmt.Fprintln(os.Stderr, err)
|
||||
os.Exit(1)
|
||||
}
|
||||
}
|
||||
|
||||
func main() {
|
||||
flag.Parse()
|
||||
|
||||
var all []string
|
||||
all = append(all, elements...)
|
||||
all = append(all, attributes...)
|
||||
all = append(all, eventHandlers...)
|
||||
all = append(all, extra...)
|
||||
sort.Strings(all)
|
||||
|
||||
// uniq - lists have dups
|
||||
w := 0
|
||||
for _, s := range all {
|
||||
if w == 0 || all[w-1] != s {
|
||||
all[w] = s
|
||||
w++
|
||||
}
|
||||
}
|
||||
all = all[:w]
|
||||
|
||||
if *test {
|
||||
var buf bytes.Buffer
|
||||
fmt.Fprintln(&buf, "// Code generated by go generate gen.go; DO NOT EDIT.\n")
|
||||
fmt.Fprintln(&buf, "//go:generate go run gen.go -test\n")
|
||||
fmt.Fprintln(&buf, "package atom\n")
|
||||
fmt.Fprintln(&buf, "var testAtomList = []string{")
|
||||
for _, s := range all {
|
||||
fmt.Fprintf(&buf, "\t%q,\n", s)
|
||||
}
|
||||
fmt.Fprintln(&buf, "}")
|
||||
|
||||
genFile("table_test.go", &buf)
|
||||
return
|
||||
}
|
||||
|
||||
// Find hash that minimizes table size.
|
||||
var best *table
|
||||
for i := 0; i < 1000000; i++ {
|
||||
if best != nil && 1<<(best.k-1) < len(all) {
|
||||
break
|
||||
}
|
||||
h := rand.Uint32()
|
||||
for k := uint(0); k <= 16; k++ {
|
||||
if best != nil && k >= best.k {
|
||||
break
|
||||
}
|
||||
var t table
|
||||
if t.init(h, k, all) {
|
||||
best = &t
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
if best == nil {
|
||||
fmt.Fprintf(os.Stderr, "failed to construct string table\n")
|
||||
os.Exit(1)
|
||||
}
|
||||
|
||||
// Lay out strings, using overlaps when possible.
|
||||
layout := append([]string{}, all...)
|
||||
|
||||
// Remove strings that are substrings of other strings
|
||||
for changed := true; changed; {
|
||||
changed = false
|
||||
for i, s := range layout {
|
||||
if s == "" {
|
||||
continue
|
||||
}
|
||||
for j, t := range layout {
|
||||
if i != j && t != "" && strings.Contains(s, t) {
|
||||
changed = true
|
||||
layout[j] = ""
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Join strings where one suffix matches another prefix.
|
||||
for {
|
||||
// Find best i, j, k such that layout[i][len-k:] == layout[j][:k],
|
||||
// maximizing overlap length k.
|
||||
besti := -1
|
||||
bestj := -1
|
||||
bestk := 0
|
||||
for i, s := range layout {
|
||||
if s == "" {
|
||||
continue
|
||||
}
|
||||
for j, t := range layout {
|
||||
if i == j {
|
||||
continue
|
||||
}
|
||||
for k := bestk + 1; k <= len(s) && k <= len(t); k++ {
|
||||
if s[len(s)-k:] == t[:k] {
|
||||
besti = i
|
||||
bestj = j
|
||||
bestk = k
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
if bestk > 0 {
|
||||
layout[besti] += layout[bestj][bestk:]
|
||||
layout[bestj] = ""
|
||||
continue
|
||||
}
|
||||
break
|
||||
}
|
||||
|
||||
text := strings.Join(layout, "")
|
||||
|
||||
atom := map[string]uint32{}
|
||||
for _, s := range all {
|
||||
off := strings.Index(text, s)
|
||||
if off < 0 {
|
||||
panic("lost string " + s)
|
||||
}
|
||||
atom[s] = uint32(off<<8 | len(s))
|
||||
}
|
||||
|
||||
var buf bytes.Buffer
|
||||
// Generate the Go code.
|
||||
fmt.Fprintln(&buf, "// Code generated by go generate gen.go; DO NOT EDIT.\n")
|
||||
fmt.Fprintln(&buf, "//go:generate go run gen.go\n")
|
||||
fmt.Fprintln(&buf, "package atom\n\nconst (")
|
||||
|
||||
// compute max len
|
||||
maxLen := 0
|
||||
for _, s := range all {
|
||||
if maxLen < len(s) {
|
||||
maxLen = len(s)
|
||||
}
|
||||
fmt.Fprintf(&buf, "\t%s Atom = %#x\n", identifier(s), atom[s])
|
||||
}
|
||||
fmt.Fprintln(&buf, ")\n")
|
||||
|
||||
fmt.Fprintf(&buf, "const hash0 = %#x\n\n", best.h0)
|
||||
fmt.Fprintf(&buf, "const maxAtomLen = %d\n\n", maxLen)
|
||||
|
||||
fmt.Fprintf(&buf, "var table = [1<<%d]Atom{\n", best.k)
|
||||
for i, s := range best.tab {
|
||||
if s == "" {
|
||||
continue
|
||||
}
|
||||
fmt.Fprintf(&buf, "\t%#x: %#x, // %s\n", i, atom[s], s)
|
||||
}
|
||||
fmt.Fprintf(&buf, "}\n")
|
||||
datasize := (1 << best.k) * 4
|
||||
|
||||
fmt.Fprintln(&buf, "const atomText =")
|
||||
textsize := len(text)
|
||||
for len(text) > 60 {
|
||||
fmt.Fprintf(&buf, "\t%q +\n", text[:60])
|
||||
text = text[60:]
|
||||
}
|
||||
fmt.Fprintf(&buf, "\t%q\n\n", text)
|
||||
|
||||
genFile("table.go", &buf)
|
||||
|
||||
fmt.Fprintf(os.Stdout, "%d atoms; %d string bytes + %d tables = %d total data\n", len(all), textsize, datasize, textsize+datasize)
|
||||
}
|
||||
|
||||
type byLen []string
|
||||
|
||||
func (x byLen) Less(i, j int) bool { return len(x[i]) > len(x[j]) }
|
||||
func (x byLen) Swap(i, j int) { x[i], x[j] = x[j], x[i] }
|
||||
func (x byLen) Len() int { return len(x) }
|
||||
|
||||
// fnv computes the FNV hash with an arbitrary starting value h.
|
||||
func fnv(h uint32, s string) uint32 {
|
||||
for i := 0; i < len(s); i++ {
|
||||
h ^= uint32(s[i])
|
||||
h *= 16777619
|
||||
}
|
||||
return h
|
||||
}
|
||||
|
||||
// A table represents an attempt at constructing the lookup table.
|
||||
// The lookup table uses cuckoo hashing, meaning that each string
|
||||
// can be found in one of two positions.
|
||||
type table struct {
|
||||
h0 uint32
|
||||
k uint
|
||||
mask uint32
|
||||
tab []string
|
||||
}
|
||||
|
||||
// hash returns the two hashes for s.
|
||||
func (t *table) hash(s string) (h1, h2 uint32) {
|
||||
h := fnv(t.h0, s)
|
||||
h1 = h & t.mask
|
||||
h2 = (h >> 16) & t.mask
|
||||
return
|
||||
}
|
||||
|
||||
// init initializes the table with the given parameters.
|
||||
// h0 is the initial hash value,
|
||||
// k is the number of bits of hash value to use, and
|
||||
// x is the list of strings to store in the table.
|
||||
// init returns false if the table cannot be constructed.
|
||||
func (t *table) init(h0 uint32, k uint, x []string) bool {
|
||||
t.h0 = h0
|
||||
t.k = k
|
||||
t.tab = make([]string, 1<<k)
|
||||
t.mask = 1<<k - 1
|
||||
for _, s := range x {
|
||||
if !t.insert(s) {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// insert inserts s in the table.
|
||||
func (t *table) insert(s string) bool {
|
||||
h1, h2 := t.hash(s)
|
||||
if t.tab[h1] == "" {
|
||||
t.tab[h1] = s
|
||||
return true
|
||||
}
|
||||
if t.tab[h2] == "" {
|
||||
t.tab[h2] = s
|
||||
return true
|
||||
}
|
||||
if t.push(h1, 0) {
|
||||
t.tab[h1] = s
|
||||
return true
|
||||
}
|
||||
if t.push(h2, 0) {
|
||||
t.tab[h2] = s
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// push attempts to push aside the entry in slot i.
|
||||
func (t *table) push(i uint32, depth int) bool {
|
||||
if depth > len(t.tab) {
|
||||
return false
|
||||
}
|
||||
s := t.tab[i]
|
||||
h1, h2 := t.hash(s)
|
||||
j := h1 + h2 - i
|
||||
if t.tab[j] != "" && !t.push(j, depth+1) {
|
||||
return false
|
||||
}
|
||||
t.tab[j] = s
|
||||
return true
|
||||
}
|
||||
|
||||
// The lists of element names and attribute keys were taken from
|
||||
// https://html.spec.whatwg.org/multipage/indices.html#index
|
||||
// as of the "HTML Living Standard - Last Updated 16 April 2018" version.
|
||||
|
||||
// "command", "keygen" and "menuitem" have been removed from the spec,
|
||||
// but are kept here for backwards compatibility.
|
||||
var elements = []string{
|
||||
"a",
|
||||
"abbr",
|
||||
"address",
|
||||
"area",
|
||||
"article",
|
||||
"aside",
|
||||
"audio",
|
||||
"b",
|
||||
"base",
|
||||
"bdi",
|
||||
"bdo",
|
||||
"blockquote",
|
||||
"body",
|
||||
"br",
|
||||
"button",
|
||||
"canvas",
|
||||
"caption",
|
||||
"cite",
|
||||
"code",
|
||||
"col",
|
||||
"colgroup",
|
||||
"command",
|
||||
"data",
|
||||
"datalist",
|
||||
"dd",
|
||||
"del",
|
||||
"details",
|
||||
"dfn",
|
||||
"dialog",
|
||||
"div",
|
||||
"dl",
|
||||
"dt",
|
||||
"em",
|
||||
"embed",
|
||||
"fieldset",
|
||||
"figcaption",
|
||||
"figure",
|
||||
"footer",
|
||||
"form",
|
||||
"h1",
|
||||
"h2",
|
||||
"h3",
|
||||
"h4",
|
||||
"h5",
|
||||
"h6",
|
||||
"head",
|
||||
"header",
|
||||
"hgroup",
|
||||
"hr",
|
||||
"html",
|
||||
"i",
|
||||
"iframe",
|
||||
"img",
|
||||
"input",
|
||||
"ins",
|
||||
"kbd",
|
||||
"keygen",
|
||||
"label",
|
||||
"legend",
|
||||
"li",
|
||||
"link",
|
||||
"main",
|
||||
"map",
|
||||
"mark",
|
||||
"menu",
|
||||
"menuitem",
|
||||
"meta",
|
||||
"meter",
|
||||
"nav",
|
||||
"noscript",
|
||||
"object",
|
||||
"ol",
|
||||
"optgroup",
|
||||
"option",
|
||||
"output",
|
||||
"p",
|
||||
"param",
|
||||
"picture",
|
||||
"pre",
|
||||
"progress",
|
||||
"q",
|
||||
"rp",
|
||||
"rt",
|
||||
"ruby",
|
||||
"s",
|
||||
"samp",
|
||||
"script",
|
||||
"section",
|
||||
"select",
|
||||
"slot",
|
||||
"small",
|
||||
"source",
|
||||
"span",
|
||||
"strong",
|
||||
"style",
|
||||
"sub",
|
||||
"summary",
|
||||
"sup",
|
||||
"table",
|
||||
"tbody",
|
||||
"td",
|
||||
"template",
|
||||
"textarea",
|
||||
"tfoot",
|
||||
"th",
|
||||
"thead",
|
||||
"time",
|
||||
"title",
|
||||
"tr",
|
||||
"track",
|
||||
"u",
|
||||
"ul",
|
||||
"var",
|
||||
"video",
|
||||
"wbr",
|
||||
}
|
||||
|
||||
// https://html.spec.whatwg.org/multipage/indices.html#attributes-3
|
||||
//
|
||||
// "challenge", "command", "contextmenu", "dropzone", "icon", "keytype", "mediagroup",
|
||||
// "radiogroup", "spellcheck", "scoped", "seamless", "sortable" and "sorted" have been removed from the spec,
|
||||
// but are kept here for backwards compatibility.
|
||||
var attributes = []string{
|
||||
"abbr",
|
||||
"accept",
|
||||
"accept-charset",
|
||||
"accesskey",
|
||||
"action",
|
||||
"allowfullscreen",
|
||||
"allowpaymentrequest",
|
||||
"allowusermedia",
|
||||
"alt",
|
||||
"as",
|
||||
"async",
|
||||
"autocomplete",
|
||||
"autofocus",
|
||||
"autoplay",
|
||||
"challenge",
|
||||
"charset",
|
||||
"checked",
|
||||
"cite",
|
||||
"class",
|
||||
"color",
|
||||
"cols",
|
||||
"colspan",
|
||||
"command",
|
||||
"content",
|
||||
"contenteditable",
|
||||
"contextmenu",
|
||||
"controls",
|
||||
"coords",
|
||||
"crossorigin",
|
||||
"data",
|
||||
"datetime",
|
||||
"default",
|
||||
"defer",
|
||||
"dir",
|
||||
"dirname",
|
||||
"disabled",
|
||||
"download",
|
||||
"draggable",
|
||||
"dropzone",
|
||||
"enctype",
|
||||
"for",
|
||||
"form",
|
||||
"formaction",
|
||||
"formenctype",
|
||||
"formmethod",
|
||||
"formnovalidate",
|
||||
"formtarget",
|
||||
"headers",
|
||||
"height",
|
||||
"hidden",
|
||||
"high",
|
||||
"href",
|
||||
"hreflang",
|
||||
"http-equiv",
|
||||
"icon",
|
||||
"id",
|
||||
"inputmode",
|
||||
"integrity",
|
||||
"is",
|
||||
"ismap",
|
||||
"itemid",
|
||||
"itemprop",
|
||||
"itemref",
|
||||
"itemscope",
|
||||
"itemtype",
|
||||
"keytype",
|
||||
"kind",
|
||||
"label",
|
||||
"lang",
|
||||
"list",
|
||||
"loop",
|
||||
"low",
|
||||
"manifest",
|
||||
"max",
|
||||
"maxlength",
|
||||
"media",
|
||||
"mediagroup",
|
||||
"method",
|
||||
"min",
|
||||
"minlength",
|
||||
"multiple",
|
||||
"muted",
|
||||
"name",
|
||||
"nomodule",
|
||||
"nonce",
|
||||
"novalidate",
|
||||
"open",
|
||||
"optimum",
|
||||
"pattern",
|
||||
"ping",
|
||||
"placeholder",
|
||||
"playsinline",
|
||||
"poster",
|
||||
"preload",
|
||||
"radiogroup",
|
||||
"readonly",
|
||||
"referrerpolicy",
|
||||
"rel",
|
||||
"required",
|
||||
"reversed",
|
||||
"rows",
|
||||
"rowspan",
|
||||
"sandbox",
|
||||
"spellcheck",
|
||||
"scope",
|
||||
"scoped",
|
||||
"seamless",
|
||||
"selected",
|
||||
"shape",
|
||||
"size",
|
||||
"sizes",
|
||||
"sortable",
|
||||
"sorted",
|
||||
"slot",
|
||||
"span",
|
||||
"spellcheck",
|
||||
"src",
|
||||
"srcdoc",
|
||||
"srclang",
|
||||
"srcset",
|
||||
"start",
|
||||
"step",
|
||||
"style",
|
||||
"tabindex",
|
||||
"target",
|
||||
"title",
|
||||
"translate",
|
||||
"type",
|
||||
"typemustmatch",
|
||||
"updateviacache",
|
||||
"usemap",
|
||||
"value",
|
||||
"width",
|
||||
"workertype",
|
||||
"wrap",
|
||||
}
|
||||
|
||||
// "onautocomplete", "onautocompleteerror", "onmousewheel",
|
||||
// "onshow" and "onsort" have been removed from the spec,
|
||||
// but are kept here for backwards compatibility.
|
||||
var eventHandlers = []string{
|
||||
"onabort",
|
||||
"onautocomplete",
|
||||
"onautocompleteerror",
|
||||
"onauxclick",
|
||||
"onafterprint",
|
||||
"onbeforeprint",
|
||||
"onbeforeunload",
|
||||
"onblur",
|
||||
"oncancel",
|
||||
"oncanplay",
|
||||
"oncanplaythrough",
|
||||
"onchange",
|
||||
"onclick",
|
||||
"onclose",
|
||||
"oncontextmenu",
|
||||
"oncopy",
|
||||
"oncuechange",
|
||||
"oncut",
|
||||
"ondblclick",
|
||||
"ondrag",
|
||||
"ondragend",
|
||||
"ondragenter",
|
||||
"ondragexit",
|
||||
"ondragleave",
|
||||
"ondragover",
|
||||
"ondragstart",
|
||||
"ondrop",
|
||||
"ondurationchange",
|
||||
"onemptied",
|
||||
"onended",
|
||||
"onerror",
|
||||
"onfocus",
|
||||
"onhashchange",
|
||||
"oninput",
|
||||
"oninvalid",
|
||||
"onkeydown",
|
||||
"onkeypress",
|
||||
"onkeyup",
|
||||
"onlanguagechange",
|
||||
"onload",
|
||||
"onloadeddata",
|
||||
"onloadedmetadata",
|
||||
"onloadend",
|
||||
"onloadstart",
|
||||
"onmessage",
|
||||
"onmessageerror",
|
||||
"onmousedown",
|
||||
"onmouseenter",
|
||||
"onmouseleave",
|
||||
"onmousemove",
|
||||
"onmouseout",
|
||||
"onmouseover",
|
||||
"onmouseup",
|
||||
"onmousewheel",
|
||||
"onwheel",
|
||||
"onoffline",
|
||||
"ononline",
|
||||
"onpagehide",
|
||||
"onpageshow",
|
||||
"onpaste",
|
||||
"onpause",
|
||||
"onplay",
|
||||
"onplaying",
|
||||
"onpopstate",
|
||||
"onprogress",
|
||||
"onratechange",
|
||||
"onreset",
|
||||
"onresize",
|
||||
"onrejectionhandled",
|
||||
"onscroll",
|
||||
"onsecuritypolicyviolation",
|
||||
"onseeked",
|
||||
"onseeking",
|
||||
"onselect",
|
||||
"onshow",
|
||||
"onsort",
|
||||
"onstalled",
|
||||
"onstorage",
|
||||
"onsubmit",
|
||||
"onsuspend",
|
||||
"ontimeupdate",
|
||||
"ontoggle",
|
||||
"onunhandledrejection",
|
||||
"onunload",
|
||||
"onvolumechange",
|
||||
"onwaiting",
|
||||
}
|
||||
|
||||
// extra are ad-hoc values not covered by any of the lists above.
|
||||
var extra = []string{
|
||||
"acronym",
|
||||
"align",
|
||||
"annotation",
|
||||
"annotation-xml",
|
||||
"applet",
|
||||
"basefont",
|
||||
"bgsound",
|
||||
"big",
|
||||
"blink",
|
||||
"center",
|
||||
"color",
|
||||
"desc",
|
||||
"face",
|
||||
"font",
|
||||
"foreignObject", // HTML is case-insensitive, but SVG-embedded-in-HTML is case-sensitive.
|
||||
"foreignobject",
|
||||
"frame",
|
||||
"frameset",
|
||||
"image",
|
||||
"isindex",
|
||||
"listing",
|
||||
"malignmark",
|
||||
"marquee",
|
||||
"math",
|
||||
"mglyph",
|
||||
"mi",
|
||||
"mn",
|
||||
"mo",
|
||||
"ms",
|
||||
"mtext",
|
||||
"nobr",
|
||||
"noembed",
|
||||
"noframes",
|
||||
"plaintext",
|
||||
"prompt",
|
||||
"public",
|
||||
"rb",
|
||||
"rtc",
|
||||
"spacer",
|
||||
"strike",
|
||||
"svg",
|
||||
"system",
|
||||
"tt",
|
||||
"xmp",
|
||||
}
|
||||
783
vendor/golang.org/x/net/html/atom/table.go
generated
vendored
Normal file
783
vendor/golang.org/x/net/html/atom/table.go
generated
vendored
Normal file
|
|
@ -0,0 +1,783 @@
|
|||
// Code generated by go generate gen.go; DO NOT EDIT.
|
||||
|
||||
//go:generate go run gen.go
|
||||
|
||||
package atom
|
||||
|
||||
const (
|
||||
A Atom = 0x1
|
||||
Abbr Atom = 0x4
|
||||
Accept Atom = 0x1a06
|
||||
AcceptCharset Atom = 0x1a0e
|
||||
Accesskey Atom = 0x2c09
|
||||
Acronym Atom = 0xaa07
|
||||
Action Atom = 0x27206
|
||||
Address Atom = 0x6f307
|
||||
Align Atom = 0xb105
|
||||
Allowfullscreen Atom = 0x2080f
|
||||
Allowpaymentrequest Atom = 0xc113
|
||||
Allowusermedia Atom = 0xdd0e
|
||||
Alt Atom = 0xf303
|
||||
Annotation Atom = 0x1c90a
|
||||
AnnotationXml Atom = 0x1c90e
|
||||
Applet Atom = 0x31906
|
||||
Area Atom = 0x35604
|
||||
Article Atom = 0x3fc07
|
||||
As Atom = 0x3c02
|
||||
Aside Atom = 0x10705
|
||||
Async Atom = 0xff05
|
||||
Audio Atom = 0x11505
|
||||
Autocomplete Atom = 0x2780c
|
||||
Autofocus Atom = 0x12109
|
||||
Autoplay Atom = 0x13c08
|
||||
B Atom = 0x101
|
||||
Base Atom = 0x3b04
|
||||
Basefont Atom = 0x3b08
|
||||
Bdi Atom = 0xba03
|
||||
Bdo Atom = 0x14b03
|
||||
Bgsound Atom = 0x15e07
|
||||
Big Atom = 0x17003
|
||||
Blink Atom = 0x17305
|
||||
Blockquote Atom = 0x1870a
|
||||
Body Atom = 0x2804
|
||||
Br Atom = 0x202
|
||||
Button Atom = 0x19106
|
||||
Canvas Atom = 0x10306
|
||||
Caption Atom = 0x23107
|
||||
Center Atom = 0x22006
|
||||
Challenge Atom = 0x29b09
|
||||
Charset Atom = 0x2107
|
||||
Checked Atom = 0x47907
|
||||
Cite Atom = 0x19c04
|
||||
Class Atom = 0x56405
|
||||
Code Atom = 0x5c504
|
||||
Col Atom = 0x1ab03
|
||||
Colgroup Atom = 0x1ab08
|
||||
Color Atom = 0x1bf05
|
||||
Cols Atom = 0x1c404
|
||||
Colspan Atom = 0x1c407
|
||||
Command Atom = 0x1d707
|
||||
Content Atom = 0x58b07
|
||||
Contenteditable Atom = 0x58b0f
|
||||
Contextmenu Atom = 0x3800b
|
||||
Controls Atom = 0x1de08
|
||||
Coords Atom = 0x1ea06
|
||||
Crossorigin Atom = 0x1fb0b
|
||||
Data Atom = 0x4a504
|
||||
Datalist Atom = 0x4a508
|
||||
Datetime Atom = 0x2b808
|
||||
Dd Atom = 0x2d702
|
||||
Default Atom = 0x10a07
|
||||
Defer Atom = 0x5c705
|
||||
Del Atom = 0x45203
|
||||
Desc Atom = 0x56104
|
||||
Details Atom = 0x7207
|
||||
Dfn Atom = 0x8703
|
||||
Dialog Atom = 0xbb06
|
||||
Dir Atom = 0x9303
|
||||
Dirname Atom = 0x9307
|
||||
Disabled Atom = 0x16408
|
||||
Div Atom = 0x16b03
|
||||
Dl Atom = 0x5e602
|
||||
Download Atom = 0x46308
|
||||
Draggable Atom = 0x17a09
|
||||
Dropzone Atom = 0x40508
|
||||
Dt Atom = 0x64b02
|
||||
Em Atom = 0x6e02
|
||||
Embed Atom = 0x6e05
|
||||
Enctype Atom = 0x28d07
|
||||
Face Atom = 0x21e04
|
||||
Fieldset Atom = 0x22608
|
||||
Figcaption Atom = 0x22e0a
|
||||
Figure Atom = 0x24806
|
||||
Font Atom = 0x3f04
|
||||
Footer Atom = 0xf606
|
||||
For Atom = 0x25403
|
||||
ForeignObject Atom = 0x2540d
|
||||
Foreignobject Atom = 0x2610d
|
||||
Form Atom = 0x26e04
|
||||
Formaction Atom = 0x26e0a
|
||||
Formenctype Atom = 0x2890b
|
||||
Formmethod Atom = 0x2a40a
|
||||
Formnovalidate Atom = 0x2ae0e
|
||||
Formtarget Atom = 0x2c00a
|
||||
Frame Atom = 0x8b05
|
||||
Frameset Atom = 0x8b08
|
||||
H1 Atom = 0x15c02
|
||||
H2 Atom = 0x2de02
|
||||
H3 Atom = 0x30d02
|
||||
H4 Atom = 0x34502
|
||||
H5 Atom = 0x34f02
|
||||
H6 Atom = 0x64d02
|
||||
Head Atom = 0x33104
|
||||
Header Atom = 0x33106
|
||||
Headers Atom = 0x33107
|
||||
Height Atom = 0x5206
|
||||
Hgroup Atom = 0x2ca06
|
||||
Hidden Atom = 0x2d506
|
||||
High Atom = 0x2db04
|
||||
Hr Atom = 0x15702
|
||||
Href Atom = 0x2e004
|
||||
Hreflang Atom = 0x2e008
|
||||
Html Atom = 0x5604
|
||||
HttpEquiv Atom = 0x2e80a
|
||||
I Atom = 0x601
|
||||
Icon Atom = 0x58a04
|
||||
Id Atom = 0x10902
|
||||
Iframe Atom = 0x2fc06
|
||||
Image Atom = 0x30205
|
||||
Img Atom = 0x30703
|
||||
Input Atom = 0x44b05
|
||||
Inputmode Atom = 0x44b09
|
||||
Ins Atom = 0x20403
|
||||
Integrity Atom = 0x23f09
|
||||
Is Atom = 0x16502
|
||||
Isindex Atom = 0x30f07
|
||||
Ismap Atom = 0x31605
|
||||
Itemid Atom = 0x38b06
|
||||
Itemprop Atom = 0x19d08
|
||||
Itemref Atom = 0x3cd07
|
||||
Itemscope Atom = 0x67109
|
||||
Itemtype Atom = 0x31f08
|
||||
Kbd Atom = 0xb903
|
||||
Keygen Atom = 0x3206
|
||||
Keytype Atom = 0xd607
|
||||
Kind Atom = 0x17704
|
||||
Label Atom = 0x5905
|
||||
Lang Atom = 0x2e404
|
||||
Legend Atom = 0x18106
|
||||
Li Atom = 0xb202
|
||||
Link Atom = 0x17404
|
||||
List Atom = 0x4a904
|
||||
Listing Atom = 0x4a907
|
||||
Loop Atom = 0x5d04
|
||||
Low Atom = 0xc303
|
||||
Main Atom = 0x1004
|
||||
Malignmark Atom = 0xb00a
|
||||
Manifest Atom = 0x6d708
|
||||
Map Atom = 0x31803
|
||||
Mark Atom = 0xb604
|
||||
Marquee Atom = 0x32707
|
||||
Math Atom = 0x32e04
|
||||
Max Atom = 0x33d03
|
||||
Maxlength Atom = 0x33d09
|
||||
Media Atom = 0xe605
|
||||
Mediagroup Atom = 0xe60a
|
||||
Menu Atom = 0x38704
|
||||
Menuitem Atom = 0x38708
|
||||
Meta Atom = 0x4b804
|
||||
Meter Atom = 0x9805
|
||||
Method Atom = 0x2a806
|
||||
Mglyph Atom = 0x30806
|
||||
Mi Atom = 0x34702
|
||||
Min Atom = 0x34703
|
||||
Minlength Atom = 0x34709
|
||||
Mn Atom = 0x2b102
|
||||
Mo Atom = 0xa402
|
||||
Ms Atom = 0x67402
|
||||
Mtext Atom = 0x35105
|
||||
Multiple Atom = 0x35f08
|
||||
Muted Atom = 0x36705
|
||||
Name Atom = 0x9604
|
||||
Nav Atom = 0x1303
|
||||
Nobr Atom = 0x3704
|
||||
Noembed Atom = 0x6c07
|
||||
Noframes Atom = 0x8908
|
||||
Nomodule Atom = 0xa208
|
||||
Nonce Atom = 0x1a605
|
||||
Noscript Atom = 0x21608
|
||||
Novalidate Atom = 0x2b20a
|
||||
Object Atom = 0x26806
|
||||
Ol Atom = 0x13702
|
||||
Onabort Atom = 0x19507
|
||||
Onafterprint Atom = 0x2360c
|
||||
Onautocomplete Atom = 0x2760e
|
||||
Onautocompleteerror Atom = 0x27613
|
||||
Onauxclick Atom = 0x61f0a
|
||||
Onbeforeprint Atom = 0x69e0d
|
||||
Onbeforeunload Atom = 0x6e70e
|
||||
Onblur Atom = 0x56d06
|
||||
Oncancel Atom = 0x11908
|
||||
Oncanplay Atom = 0x14d09
|
||||
Oncanplaythrough Atom = 0x14d10
|
||||
Onchange Atom = 0x41b08
|
||||
Onclick Atom = 0x2f507
|
||||
Onclose Atom = 0x36c07
|
||||
Oncontextmenu Atom = 0x37e0d
|
||||
Oncopy Atom = 0x39106
|
||||
Oncuechange Atom = 0x3970b
|
||||
Oncut Atom = 0x3a205
|
||||
Ondblclick Atom = 0x3a70a
|
||||
Ondrag Atom = 0x3b106
|
||||
Ondragend Atom = 0x3b109
|
||||
Ondragenter Atom = 0x3ba0b
|
||||
Ondragexit Atom = 0x3c50a
|
||||
Ondragleave Atom = 0x3df0b
|
||||
Ondragover Atom = 0x3ea0a
|
||||
Ondragstart Atom = 0x3f40b
|
||||
Ondrop Atom = 0x40306
|
||||
Ondurationchange Atom = 0x41310
|
||||
Onemptied Atom = 0x40a09
|
||||
Onended Atom = 0x42307
|
||||
Onerror Atom = 0x42a07
|
||||
Onfocus Atom = 0x43107
|
||||
Onhashchange Atom = 0x43d0c
|
||||
Oninput Atom = 0x44907
|
||||
Oninvalid Atom = 0x45509
|
||||
Onkeydown Atom = 0x45e09
|
||||
Onkeypress Atom = 0x46b0a
|
||||
Onkeyup Atom = 0x48007
|
||||
Onlanguagechange Atom = 0x48d10
|
||||
Onload Atom = 0x49d06
|
||||
Onloadeddata Atom = 0x49d0c
|
||||
Onloadedmetadata Atom = 0x4b010
|
||||
Onloadend Atom = 0x4c609
|
||||
Onloadstart Atom = 0x4cf0b
|
||||
Onmessage Atom = 0x4da09
|
||||
Onmessageerror Atom = 0x4da0e
|
||||
Onmousedown Atom = 0x4e80b
|
||||
Onmouseenter Atom = 0x4f30c
|
||||
Onmouseleave Atom = 0x4ff0c
|
||||
Onmousemove Atom = 0x50b0b
|
||||
Onmouseout Atom = 0x5160a
|
||||
Onmouseover Atom = 0x5230b
|
||||
Onmouseup Atom = 0x52e09
|
||||
Onmousewheel Atom = 0x53c0c
|
||||
Onoffline Atom = 0x54809
|
||||
Ononline Atom = 0x55108
|
||||
Onpagehide Atom = 0x5590a
|
||||
Onpageshow Atom = 0x5730a
|
||||
Onpaste Atom = 0x57f07
|
||||
Onpause Atom = 0x59a07
|
||||
Onplay Atom = 0x5a406
|
||||
Onplaying Atom = 0x5a409
|
||||
Onpopstate Atom = 0x5ad0a
|
||||
Onprogress Atom = 0x5b70a
|
||||
Onratechange Atom = 0x5cc0c
|
||||
Onrejectionhandled Atom = 0x5d812
|
||||
Onreset Atom = 0x5ea07
|
||||
Onresize Atom = 0x5f108
|
||||
Onscroll Atom = 0x60008
|
||||
Onsecuritypolicyviolation Atom = 0x60819
|
||||
Onseeked Atom = 0x62908
|
||||
Onseeking Atom = 0x63109
|
||||
Onselect Atom = 0x63a08
|
||||
Onshow Atom = 0x64406
|
||||
Onsort Atom = 0x64f06
|
||||
Onstalled Atom = 0x65909
|
||||
Onstorage Atom = 0x66209
|
||||
Onsubmit Atom = 0x66b08
|
||||
Onsuspend Atom = 0x67b09
|
||||
Ontimeupdate Atom = 0x400c
|
||||
Ontoggle Atom = 0x68408
|
||||
Onunhandledrejection Atom = 0x68c14
|
||||
Onunload Atom = 0x6ab08
|
||||
Onvolumechange Atom = 0x6b30e
|
||||
Onwaiting Atom = 0x6c109
|
||||
Onwheel Atom = 0x6ca07
|
||||
Open Atom = 0x1a304
|
||||
Optgroup Atom = 0x5f08
|
||||
Optimum Atom = 0x6d107
|
||||
Option Atom = 0x6e306
|
||||
Output Atom = 0x51d06
|
||||
P Atom = 0xc01
|
||||
Param Atom = 0xc05
|
||||
Pattern Atom = 0x6607
|
||||
Picture Atom = 0x7b07
|
||||
Ping Atom = 0xef04
|
||||
Placeholder Atom = 0x1310b
|
||||
Plaintext Atom = 0x1b209
|
||||
Playsinline Atom = 0x1400b
|
||||
Poster Atom = 0x2cf06
|
||||
Pre Atom = 0x47003
|
||||
Preload Atom = 0x48607
|
||||
Progress Atom = 0x5b908
|
||||
Prompt Atom = 0x53606
|
||||
Public Atom = 0x58606
|
||||
Q Atom = 0xcf01
|
||||
Radiogroup Atom = 0x30a
|
||||
Rb Atom = 0x3a02
|
||||
Readonly Atom = 0x35708
|
||||
Referrerpolicy Atom = 0x3d10e
|
||||
Rel Atom = 0x48703
|
||||
Required Atom = 0x24c08
|
||||
Reversed Atom = 0x8008
|
||||
Rows Atom = 0x9c04
|
||||
Rowspan Atom = 0x9c07
|
||||
Rp Atom = 0x23c02
|
||||
Rt Atom = 0x19a02
|
||||
Rtc Atom = 0x19a03
|
||||
Ruby Atom = 0xfb04
|
||||
S Atom = 0x2501
|
||||
Samp Atom = 0x7804
|
||||
Sandbox Atom = 0x12907
|
||||
Scope Atom = 0x67505
|
||||
Scoped Atom = 0x67506
|
||||
Script Atom = 0x21806
|
||||
Seamless Atom = 0x37108
|
||||
Section Atom = 0x56807
|
||||
Select Atom = 0x63c06
|
||||
Selected Atom = 0x63c08
|
||||
Shape Atom = 0x1e505
|
||||
Size Atom = 0x5f504
|
||||
Sizes Atom = 0x5f505
|
||||
Slot Atom = 0x1ef04
|
||||
Small Atom = 0x20605
|
||||
Sortable Atom = 0x65108
|
||||
Sorted Atom = 0x33706
|
||||
Source Atom = 0x37806
|
||||
Spacer Atom = 0x43706
|
||||
Span Atom = 0x9f04
|
||||
Spellcheck Atom = 0x4740a
|
||||
Src Atom = 0x5c003
|
||||
Srcdoc Atom = 0x5c006
|
||||
Srclang Atom = 0x5f907
|
||||
Srcset Atom = 0x6f906
|
||||
Start Atom = 0x3fa05
|
||||
Step Atom = 0x58304
|
||||
Strike Atom = 0xd206
|
||||
Strong Atom = 0x6dd06
|
||||
Style Atom = 0x6ff05
|
||||
Sub Atom = 0x66d03
|
||||
Summary Atom = 0x70407
|
||||
Sup Atom = 0x70b03
|
||||
Svg Atom = 0x70e03
|
||||
System Atom = 0x71106
|
||||
Tabindex Atom = 0x4be08
|
||||
Table Atom = 0x59505
|
||||
Target Atom = 0x2c406
|
||||
Tbody Atom = 0x2705
|
||||
Td Atom = 0x9202
|
||||
Template Atom = 0x71408
|
||||
Textarea Atom = 0x35208
|
||||
Tfoot Atom = 0xf505
|
||||
Th Atom = 0x15602
|
||||
Thead Atom = 0x33005
|
||||
Time Atom = 0x4204
|
||||
Title Atom = 0x11005
|
||||
Tr Atom = 0xcc02
|
||||
Track Atom = 0x1ba05
|
||||
Translate Atom = 0x1f209
|
||||
Tt Atom = 0x6802
|
||||
Type Atom = 0xd904
|
||||
Typemustmatch Atom = 0x2900d
|
||||
U Atom = 0xb01
|
||||
Ul Atom = 0xa702
|
||||
Updateviacache Atom = 0x460e
|
||||
Usemap Atom = 0x59e06
|
||||
Value Atom = 0x1505
|
||||
Var Atom = 0x16d03
|
||||
Video Atom = 0x2f105
|
||||
Wbr Atom = 0x57c03
|
||||
Width Atom = 0x64905
|
||||
Workertype Atom = 0x71c0a
|
||||
Wrap Atom = 0x72604
|
||||
Xmp Atom = 0x12f03
|
||||
)
|
||||
|
||||
const hash0 = 0x81cdf10e
|
||||
|
||||
const maxAtomLen = 25
|
||||
|
||||
var table = [1 << 9]Atom{
|
||||
0x1: 0xe60a, // mediagroup
|
||||
0x2: 0x2e404, // lang
|
||||
0x4: 0x2c09, // accesskey
|
||||
0x5: 0x8b08, // frameset
|
||||
0x7: 0x63a08, // onselect
|
||||
0x8: 0x71106, // system
|
||||
0xa: 0x64905, // width
|
||||
0xc: 0x2890b, // formenctype
|
||||
0xd: 0x13702, // ol
|
||||
0xe: 0x3970b, // oncuechange
|
||||
0x10: 0x14b03, // bdo
|
||||
0x11: 0x11505, // audio
|
||||
0x12: 0x17a09, // draggable
|
||||
0x14: 0x2f105, // video
|
||||
0x15: 0x2b102, // mn
|
||||
0x16: 0x38704, // menu
|
||||
0x17: 0x2cf06, // poster
|
||||
0x19: 0xf606, // footer
|
||||
0x1a: 0x2a806, // method
|
||||
0x1b: 0x2b808, // datetime
|
||||
0x1c: 0x19507, // onabort
|
||||
0x1d: 0x460e, // updateviacache
|
||||
0x1e: 0xff05, // async
|
||||
0x1f: 0x49d06, // onload
|
||||
0x21: 0x11908, // oncancel
|
||||
0x22: 0x62908, // onseeked
|
||||
0x23: 0x30205, // image
|
||||
0x24: 0x5d812, // onrejectionhandled
|
||||
0x26: 0x17404, // link
|
||||
0x27: 0x51d06, // output
|
||||
0x28: 0x33104, // head
|
||||
0x29: 0x4ff0c, // onmouseleave
|
||||
0x2a: 0x57f07, // onpaste
|
||||
0x2b: 0x5a409, // onplaying
|
||||
0x2c: 0x1c407, // colspan
|
||||
0x2f: 0x1bf05, // color
|
||||
0x30: 0x5f504, // size
|
||||
0x31: 0x2e80a, // http-equiv
|
||||
0x33: 0x601, // i
|
||||
0x34: 0x5590a, // onpagehide
|
||||
0x35: 0x68c14, // onunhandledrejection
|
||||
0x37: 0x42a07, // onerror
|
||||
0x3a: 0x3b08, // basefont
|
||||
0x3f: 0x1303, // nav
|
||||
0x40: 0x17704, // kind
|
||||
0x41: 0x35708, // readonly
|
||||
0x42: 0x30806, // mglyph
|
||||
0x44: 0xb202, // li
|
||||
0x46: 0x2d506, // hidden
|
||||
0x47: 0x70e03, // svg
|
||||
0x48: 0x58304, // step
|
||||
0x49: 0x23f09, // integrity
|
||||
0x4a: 0x58606, // public
|
||||
0x4c: 0x1ab03, // col
|
||||
0x4d: 0x1870a, // blockquote
|
||||
0x4e: 0x34f02, // h5
|
||||
0x50: 0x5b908, // progress
|
||||
0x51: 0x5f505, // sizes
|
||||
0x52: 0x34502, // h4
|
||||
0x56: 0x33005, // thead
|
||||
0x57: 0xd607, // keytype
|
||||
0x58: 0x5b70a, // onprogress
|
||||
0x59: 0x44b09, // inputmode
|
||||
0x5a: 0x3b109, // ondragend
|
||||
0x5d: 0x3a205, // oncut
|
||||
0x5e: 0x43706, // spacer
|
||||
0x5f: 0x1ab08, // colgroup
|
||||
0x62: 0x16502, // is
|
||||
0x65: 0x3c02, // as
|
||||
0x66: 0x54809, // onoffline
|
||||
0x67: 0x33706, // sorted
|
||||
0x69: 0x48d10, // onlanguagechange
|
||||
0x6c: 0x43d0c, // onhashchange
|
||||
0x6d: 0x9604, // name
|
||||
0x6e: 0xf505, // tfoot
|
||||
0x6f: 0x56104, // desc
|
||||
0x70: 0x33d03, // max
|
||||
0x72: 0x1ea06, // coords
|
||||
0x73: 0x30d02, // h3
|
||||
0x74: 0x6e70e, // onbeforeunload
|
||||
0x75: 0x9c04, // rows
|
||||
0x76: 0x63c06, // select
|
||||
0x77: 0x9805, // meter
|
||||
0x78: 0x38b06, // itemid
|
||||
0x79: 0x53c0c, // onmousewheel
|
||||
0x7a: 0x5c006, // srcdoc
|
||||
0x7d: 0x1ba05, // track
|
||||
0x7f: 0x31f08, // itemtype
|
||||
0x82: 0xa402, // mo
|
||||
0x83: 0x41b08, // onchange
|
||||
0x84: 0x33107, // headers
|
||||
0x85: 0x5cc0c, // onratechange
|
||||
0x86: 0x60819, // onsecuritypolicyviolation
|
||||
0x88: 0x4a508, // datalist
|
||||
0x89: 0x4e80b, // onmousedown
|
||||
0x8a: 0x1ef04, // slot
|
||||
0x8b: 0x4b010, // onloadedmetadata
|
||||
0x8c: 0x1a06, // accept
|
||||
0x8d: 0x26806, // object
|
||||
0x91: 0x6b30e, // onvolumechange
|
||||
0x92: 0x2107, // charset
|
||||
0x93: 0x27613, // onautocompleteerror
|
||||
0x94: 0xc113, // allowpaymentrequest
|
||||
0x95: 0x2804, // body
|
||||
0x96: 0x10a07, // default
|
||||
0x97: 0x63c08, // selected
|
||||
0x98: 0x21e04, // face
|
||||
0x99: 0x1e505, // shape
|
||||
0x9b: 0x68408, // ontoggle
|
||||
0x9e: 0x64b02, // dt
|
||||
0x9f: 0xb604, // mark
|
||||
0xa1: 0xb01, // u
|
||||
0xa4: 0x6ab08, // onunload
|
||||
0xa5: 0x5d04, // loop
|
||||
0xa6: 0x16408, // disabled
|
||||
0xaa: 0x42307, // onended
|
||||
0xab: 0xb00a, // malignmark
|
||||
0xad: 0x67b09, // onsuspend
|
||||
0xae: 0x35105, // mtext
|
||||
0xaf: 0x64f06, // onsort
|
||||
0xb0: 0x19d08, // itemprop
|
||||
0xb3: 0x67109, // itemscope
|
||||
0xb4: 0x17305, // blink
|
||||
0xb6: 0x3b106, // ondrag
|
||||
0xb7: 0xa702, // ul
|
||||
0xb8: 0x26e04, // form
|
||||
0xb9: 0x12907, // sandbox
|
||||
0xba: 0x8b05, // frame
|
||||
0xbb: 0x1505, // value
|
||||
0xbc: 0x66209, // onstorage
|
||||
0xbf: 0xaa07, // acronym
|
||||
0xc0: 0x19a02, // rt
|
||||
0xc2: 0x202, // br
|
||||
0xc3: 0x22608, // fieldset
|
||||
0xc4: 0x2900d, // typemustmatch
|
||||
0xc5: 0xa208, // nomodule
|
||||
0xc6: 0x6c07, // noembed
|
||||
0xc7: 0x69e0d, // onbeforeprint
|
||||
0xc8: 0x19106, // button
|
||||
0xc9: 0x2f507, // onclick
|
||||
0xca: 0x70407, // summary
|
||||
0xcd: 0xfb04, // ruby
|
||||
0xce: 0x56405, // class
|
||||
0xcf: 0x3f40b, // ondragstart
|
||||
0xd0: 0x23107, // caption
|
||||
0xd4: 0xdd0e, // allowusermedia
|
||||
0xd5: 0x4cf0b, // onloadstart
|
||||
0xd9: 0x16b03, // div
|
||||
0xda: 0x4a904, // list
|
||||
0xdb: 0x32e04, // math
|
||||
0xdc: 0x44b05, // input
|
||||
0xdf: 0x3ea0a, // ondragover
|
||||
0xe0: 0x2de02, // h2
|
||||
0xe2: 0x1b209, // plaintext
|
||||
0xe4: 0x4f30c, // onmouseenter
|
||||
0xe7: 0x47907, // checked
|
||||
0xe8: 0x47003, // pre
|
||||
0xea: 0x35f08, // multiple
|
||||
0xeb: 0xba03, // bdi
|
||||
0xec: 0x33d09, // maxlength
|
||||
0xed: 0xcf01, // q
|
||||
0xee: 0x61f0a, // onauxclick
|
||||
0xf0: 0x57c03, // wbr
|
||||
0xf2: 0x3b04, // base
|
||||
0xf3: 0x6e306, // option
|
||||
0xf5: 0x41310, // ondurationchange
|
||||
0xf7: 0x8908, // noframes
|
||||
0xf9: 0x40508, // dropzone
|
||||
0xfb: 0x67505, // scope
|
||||
0xfc: 0x8008, // reversed
|
||||
0xfd: 0x3ba0b, // ondragenter
|
||||
0xfe: 0x3fa05, // start
|
||||
0xff: 0x12f03, // xmp
|
||||
0x100: 0x5f907, // srclang
|
||||
0x101: 0x30703, // img
|
||||
0x104: 0x101, // b
|
||||
0x105: 0x25403, // for
|
||||
0x106: 0x10705, // aside
|
||||
0x107: 0x44907, // oninput
|
||||
0x108: 0x35604, // area
|
||||
0x109: 0x2a40a, // formmethod
|
||||
0x10a: 0x72604, // wrap
|
||||
0x10c: 0x23c02, // rp
|
||||
0x10d: 0x46b0a, // onkeypress
|
||||
0x10e: 0x6802, // tt
|
||||
0x110: 0x34702, // mi
|
||||
0x111: 0x36705, // muted
|
||||
0x112: 0xf303, // alt
|
||||
0x113: 0x5c504, // code
|
||||
0x114: 0x6e02, // em
|
||||
0x115: 0x3c50a, // ondragexit
|
||||
0x117: 0x9f04, // span
|
||||
0x119: 0x6d708, // manifest
|
||||
0x11a: 0x38708, // menuitem
|
||||
0x11b: 0x58b07, // content
|
||||
0x11d: 0x6c109, // onwaiting
|
||||
0x11f: 0x4c609, // onloadend
|
||||
0x121: 0x37e0d, // oncontextmenu
|
||||
0x123: 0x56d06, // onblur
|
||||
0x124: 0x3fc07, // article
|
||||
0x125: 0x9303, // dir
|
||||
0x126: 0xef04, // ping
|
||||
0x127: 0x24c08, // required
|
||||
0x128: 0x45509, // oninvalid
|
||||
0x129: 0xb105, // align
|
||||
0x12b: 0x58a04, // icon
|
||||
0x12c: 0x64d02, // h6
|
||||
0x12d: 0x1c404, // cols
|
||||
0x12e: 0x22e0a, // figcaption
|
||||
0x12f: 0x45e09, // onkeydown
|
||||
0x130: 0x66b08, // onsubmit
|
||||
0x131: 0x14d09, // oncanplay
|
||||
0x132: 0x70b03, // sup
|
||||
0x133: 0xc01, // p
|
||||
0x135: 0x40a09, // onemptied
|
||||
0x136: 0x39106, // oncopy
|
||||
0x137: 0x19c04, // cite
|
||||
0x138: 0x3a70a, // ondblclick
|
||||
0x13a: 0x50b0b, // onmousemove
|
||||
0x13c: 0x66d03, // sub
|
||||
0x13d: 0x48703, // rel
|
||||
0x13e: 0x5f08, // optgroup
|
||||
0x142: 0x9c07, // rowspan
|
||||
0x143: 0x37806, // source
|
||||
0x144: 0x21608, // noscript
|
||||
0x145: 0x1a304, // open
|
||||
0x146: 0x20403, // ins
|
||||
0x147: 0x2540d, // foreignObject
|
||||
0x148: 0x5ad0a, // onpopstate
|
||||
0x14a: 0x28d07, // enctype
|
||||
0x14b: 0x2760e, // onautocomplete
|
||||
0x14c: 0x35208, // textarea
|
||||
0x14e: 0x2780c, // autocomplete
|
||||
0x14f: 0x15702, // hr
|
||||
0x150: 0x1de08, // controls
|
||||
0x151: 0x10902, // id
|
||||
0x153: 0x2360c, // onafterprint
|
||||
0x155: 0x2610d, // foreignobject
|
||||
0x156: 0x32707, // marquee
|
||||
0x157: 0x59a07, // onpause
|
||||
0x158: 0x5e602, // dl
|
||||
0x159: 0x5206, // height
|
||||
0x15a: 0x34703, // min
|
||||
0x15b: 0x9307, // dirname
|
||||
0x15c: 0x1f209, // translate
|
||||
0x15d: 0x5604, // html
|
||||
0x15e: 0x34709, // minlength
|
||||
0x15f: 0x48607, // preload
|
||||
0x160: 0x71408, // template
|
||||
0x161: 0x3df0b, // ondragleave
|
||||
0x162: 0x3a02, // rb
|
||||
0x164: 0x5c003, // src
|
||||
0x165: 0x6dd06, // strong
|
||||
0x167: 0x7804, // samp
|
||||
0x168: 0x6f307, // address
|
||||
0x169: 0x55108, // ononline
|
||||
0x16b: 0x1310b, // placeholder
|
||||
0x16c: 0x2c406, // target
|
||||
0x16d: 0x20605, // small
|
||||
0x16e: 0x6ca07, // onwheel
|
||||
0x16f: 0x1c90a, // annotation
|
||||
0x170: 0x4740a, // spellcheck
|
||||
0x171: 0x7207, // details
|
||||
0x172: 0x10306, // canvas
|
||||
0x173: 0x12109, // autofocus
|
||||
0x174: 0xc05, // param
|
||||
0x176: 0x46308, // download
|
||||
0x177: 0x45203, // del
|
||||
0x178: 0x36c07, // onclose
|
||||
0x179: 0xb903, // kbd
|
||||
0x17a: 0x31906, // applet
|
||||
0x17b: 0x2e004, // href
|
||||
0x17c: 0x5f108, // onresize
|
||||
0x17e: 0x49d0c, // onloadeddata
|
||||
0x180: 0xcc02, // tr
|
||||
0x181: 0x2c00a, // formtarget
|
||||
0x182: 0x11005, // title
|
||||
0x183: 0x6ff05, // style
|
||||
0x184: 0xd206, // strike
|
||||
0x185: 0x59e06, // usemap
|
||||
0x186: 0x2fc06, // iframe
|
||||
0x187: 0x1004, // main
|
||||
0x189: 0x7b07, // picture
|
||||
0x18c: 0x31605, // ismap
|
||||
0x18e: 0x4a504, // data
|
||||
0x18f: 0x5905, // label
|
||||
0x191: 0x3d10e, // referrerpolicy
|
||||
0x192: 0x15602, // th
|
||||
0x194: 0x53606, // prompt
|
||||
0x195: 0x56807, // section
|
||||
0x197: 0x6d107, // optimum
|
||||
0x198: 0x2db04, // high
|
||||
0x199: 0x15c02, // h1
|
||||
0x19a: 0x65909, // onstalled
|
||||
0x19b: 0x16d03, // var
|
||||
0x19c: 0x4204, // time
|
||||
0x19e: 0x67402, // ms
|
||||
0x19f: 0x33106, // header
|
||||
0x1a0: 0x4da09, // onmessage
|
||||
0x1a1: 0x1a605, // nonce
|
||||
0x1a2: 0x26e0a, // formaction
|
||||
0x1a3: 0x22006, // center
|
||||
0x1a4: 0x3704, // nobr
|
||||
0x1a5: 0x59505, // table
|
||||
0x1a6: 0x4a907, // listing
|
||||
0x1a7: 0x18106, // legend
|
||||
0x1a9: 0x29b09, // challenge
|
||||
0x1aa: 0x24806, // figure
|
||||
0x1ab: 0xe605, // media
|
||||
0x1ae: 0xd904, // type
|
||||
0x1af: 0x3f04, // font
|
||||
0x1b0: 0x4da0e, // onmessageerror
|
||||
0x1b1: 0x37108, // seamless
|
||||
0x1b2: 0x8703, // dfn
|
||||
0x1b3: 0x5c705, // defer
|
||||
0x1b4: 0xc303, // low
|
||||
0x1b5: 0x19a03, // rtc
|
||||
0x1b6: 0x5230b, // onmouseover
|
||||
0x1b7: 0x2b20a, // novalidate
|
||||
0x1b8: 0x71c0a, // workertype
|
||||
0x1ba: 0x3cd07, // itemref
|
||||
0x1bd: 0x1, // a
|
||||
0x1be: 0x31803, // map
|
||||
0x1bf: 0x400c, // ontimeupdate
|
||||
0x1c0: 0x15e07, // bgsound
|
||||
0x1c1: 0x3206, // keygen
|
||||
0x1c2: 0x2705, // tbody
|
||||
0x1c5: 0x64406, // onshow
|
||||
0x1c7: 0x2501, // s
|
||||
0x1c8: 0x6607, // pattern
|
||||
0x1cc: 0x14d10, // oncanplaythrough
|
||||
0x1ce: 0x2d702, // dd
|
||||
0x1cf: 0x6f906, // srcset
|
||||
0x1d0: 0x17003, // big
|
||||
0x1d2: 0x65108, // sortable
|
||||
0x1d3: 0x48007, // onkeyup
|
||||
0x1d5: 0x5a406, // onplay
|
||||
0x1d7: 0x4b804, // meta
|
||||
0x1d8: 0x40306, // ondrop
|
||||
0x1da: 0x60008, // onscroll
|
||||
0x1db: 0x1fb0b, // crossorigin
|
||||
0x1dc: 0x5730a, // onpageshow
|
||||
0x1dd: 0x4, // abbr
|
||||
0x1de: 0x9202, // td
|
||||
0x1df: 0x58b0f, // contenteditable
|
||||
0x1e0: 0x27206, // action
|
||||
0x1e1: 0x1400b, // playsinline
|
||||
0x1e2: 0x43107, // onfocus
|
||||
0x1e3: 0x2e008, // hreflang
|
||||
0x1e5: 0x5160a, // onmouseout
|
||||
0x1e6: 0x5ea07, // onreset
|
||||
0x1e7: 0x13c08, // autoplay
|
||||
0x1e8: 0x63109, // onseeking
|
||||
0x1ea: 0x67506, // scoped
|
||||
0x1ec: 0x30a, // radiogroup
|
||||
0x1ee: 0x3800b, // contextmenu
|
||||
0x1ef: 0x52e09, // onmouseup
|
||||
0x1f1: 0x2ca06, // hgroup
|
||||
0x1f2: 0x2080f, // allowfullscreen
|
||||
0x1f3: 0x4be08, // tabindex
|
||||
0x1f6: 0x30f07, // isindex
|
||||
0x1f7: 0x1a0e, // accept-charset
|
||||
0x1f8: 0x2ae0e, // formnovalidate
|
||||
0x1fb: 0x1c90e, // annotation-xml
|
||||
0x1fc: 0x6e05, // embed
|
||||
0x1fd: 0x21806, // script
|
||||
0x1fe: 0xbb06, // dialog
|
||||
0x1ff: 0x1d707, // command
|
||||
}
|
||||
|
||||
const atomText = "abbradiogrouparamainavalueaccept-charsetbodyaccesskeygenobrb" +
|
||||
"asefontimeupdateviacacheightmlabelooptgroupatternoembedetail" +
|
||||
"sampictureversedfnoframesetdirnameterowspanomoduleacronymali" +
|
||||
"gnmarkbdialogallowpaymentrequestrikeytypeallowusermediagroup" +
|
||||
"ingaltfooterubyasyncanvasidefaultitleaudioncancelautofocusan" +
|
||||
"dboxmplaceholderautoplaysinlinebdoncanplaythrough1bgsoundisa" +
|
||||
"bledivarbigblinkindraggablegendblockquotebuttonabortcitempro" +
|
||||
"penoncecolgrouplaintextrackcolorcolspannotation-xmlcommandco" +
|
||||
"ntrolshapecoordslotranslatecrossoriginsmallowfullscreenoscri" +
|
||||
"ptfacenterfieldsetfigcaptionafterprintegrityfigurequiredfore" +
|
||||
"ignObjectforeignobjectformactionautocompleteerrorformenctype" +
|
||||
"mustmatchallengeformmethodformnovalidatetimeformtargethgroup" +
|
||||
"osterhiddenhigh2hreflanghttp-equivideonclickiframeimageimgly" +
|
||||
"ph3isindexismappletitemtypemarqueematheadersortedmaxlength4m" +
|
||||
"inlength5mtextareadonlymultiplemutedoncloseamlessourceoncont" +
|
||||
"extmenuitemidoncopyoncuechangeoncutondblclickondragendondrag" +
|
||||
"enterondragexitemreferrerpolicyondragleaveondragoverondragst" +
|
||||
"articleondropzonemptiedondurationchangeonendedonerroronfocus" +
|
||||
"paceronhashchangeoninputmodeloninvalidonkeydownloadonkeypres" +
|
||||
"spellcheckedonkeyupreloadonlanguagechangeonloadeddatalisting" +
|
||||
"onloadedmetadatabindexonloadendonloadstartonmessageerroronmo" +
|
||||
"usedownonmouseenteronmouseleaveonmousemoveonmouseoutputonmou" +
|
||||
"seoveronmouseupromptonmousewheelonofflineononlineonpagehides" +
|
||||
"classectionbluronpageshowbronpastepublicontenteditableonpaus" +
|
||||
"emaponplayingonpopstateonprogressrcdocodeferonratechangeonre" +
|
||||
"jectionhandledonresetonresizesrclangonscrollonsecuritypolicy" +
|
||||
"violationauxclickonseekedonseekingonselectedonshowidth6onsor" +
|
||||
"tableonstalledonstorageonsubmitemscopedonsuspendontoggleonun" +
|
||||
"handledrejectionbeforeprintonunloadonvolumechangeonwaitingon" +
|
||||
"wheeloptimumanifestrongoptionbeforeunloaddressrcsetstylesumm" +
|
||||
"arysupsvgsystemplateworkertypewrap"
|
||||
257
vendor/golang.org/x/net/html/charset/charset.go
generated
vendored
Normal file
257
vendor/golang.org/x/net/html/charset/charset.go
generated
vendored
Normal file
|
|
@ -0,0 +1,257 @@
|
|||
// 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 charset provides common text encodings for HTML documents.
|
||||
//
|
||||
// The mapping from encoding labels to encodings is defined at
|
||||
// https://encoding.spec.whatwg.org/.
|
||||
package charset // import "golang.org/x/net/html/charset"
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"io"
|
||||
"mime"
|
||||
"strings"
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/net/html"
|
||||
"golang.org/x/text/encoding"
|
||||
"golang.org/x/text/encoding/charmap"
|
||||
"golang.org/x/text/encoding/htmlindex"
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// Lookup returns the encoding with the specified label, and its canonical
|
||||
// name. It returns nil and the empty string if label is not one of the
|
||||
// standard encodings for HTML. Matching is case-insensitive and ignores
|
||||
// leading and trailing whitespace. Encoders will use HTML escape sequences for
|
||||
// runes that are not supported by the character set.
|
||||
func Lookup(label string) (e encoding.Encoding, name string) {
|
||||
e, err := htmlindex.Get(label)
|
||||
if err != nil {
|
||||
return nil, ""
|
||||
}
|
||||
name, _ = htmlindex.Name(e)
|
||||
return &htmlEncoding{e}, name
|
||||
}
|
||||
|
||||
type htmlEncoding struct{ encoding.Encoding }
|
||||
|
||||
func (h *htmlEncoding) NewEncoder() *encoding.Encoder {
|
||||
// HTML requires a non-terminating legacy encoder. We use HTML escapes to
|
||||
// substitute unsupported code points.
|
||||
return encoding.HTMLEscapeUnsupported(h.Encoding.NewEncoder())
|
||||
}
|
||||
|
||||
// DetermineEncoding determines the encoding of an HTML document by examining
|
||||
// up to the first 1024 bytes of content and the declared Content-Type.
|
||||
//
|
||||
// See http://www.whatwg.org/specs/web-apps/current-work/multipage/parsing.html#determining-the-character-encoding
|
||||
func DetermineEncoding(content []byte, contentType string) (e encoding.Encoding, name string, certain bool) {
|
||||
if len(content) > 1024 {
|
||||
content = content[:1024]
|
||||
}
|
||||
|
||||
for _, b := range boms {
|
||||
if bytes.HasPrefix(content, b.bom) {
|
||||
e, name = Lookup(b.enc)
|
||||
return e, name, true
|
||||
}
|
||||
}
|
||||
|
||||
if _, params, err := mime.ParseMediaType(contentType); err == nil {
|
||||
if cs, ok := params["charset"]; ok {
|
||||
if e, name = Lookup(cs); e != nil {
|
||||
return e, name, true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if len(content) > 0 {
|
||||
e, name = prescan(content)
|
||||
if e != nil {
|
||||
return e, name, false
|
||||
}
|
||||
}
|
||||
|
||||
// Try to detect UTF-8.
|
||||
// First eliminate any partial rune at the end.
|
||||
for i := len(content) - 1; i >= 0 && i > len(content)-4; i-- {
|
||||
b := content[i]
|
||||
if b < 0x80 {
|
||||
break
|
||||
}
|
||||
if utf8.RuneStart(b) {
|
||||
content = content[:i]
|
||||
break
|
||||
}
|
||||
}
|
||||
hasHighBit := false
|
||||
for _, c := range content {
|
||||
if c >= 0x80 {
|
||||
hasHighBit = true
|
||||
break
|
||||
}
|
||||
}
|
||||
if hasHighBit && utf8.Valid(content) {
|
||||
return encoding.Nop, "utf-8", false
|
||||
}
|
||||
|
||||
// TODO: change default depending on user's locale?
|
||||
return charmap.Windows1252, "windows-1252", false
|
||||
}
|
||||
|
||||
// NewReader returns an io.Reader that converts the content of r to UTF-8.
|
||||
// It calls DetermineEncoding to find out what r's encoding is.
|
||||
func NewReader(r io.Reader, contentType string) (io.Reader, error) {
|
||||
preview := make([]byte, 1024)
|
||||
n, err := io.ReadFull(r, preview)
|
||||
switch {
|
||||
case err == io.ErrUnexpectedEOF:
|
||||
preview = preview[:n]
|
||||
r = bytes.NewReader(preview)
|
||||
case err != nil:
|
||||
return nil, err
|
||||
default:
|
||||
r = io.MultiReader(bytes.NewReader(preview), r)
|
||||
}
|
||||
|
||||
if e, _, _ := DetermineEncoding(preview, contentType); e != encoding.Nop {
|
||||
r = transform.NewReader(r, e.NewDecoder())
|
||||
}
|
||||
return r, nil
|
||||
}
|
||||
|
||||
// NewReaderLabel returns a reader that converts from the specified charset to
|
||||
// UTF-8. It uses Lookup to find the encoding that corresponds to label, and
|
||||
// returns an error if Lookup returns nil. It is suitable for use as
|
||||
// encoding/xml.Decoder's CharsetReader function.
|
||||
func NewReaderLabel(label string, input io.Reader) (io.Reader, error) {
|
||||
e, _ := Lookup(label)
|
||||
if e == nil {
|
||||
return nil, fmt.Errorf("unsupported charset: %q", label)
|
||||
}
|
||||
return transform.NewReader(input, e.NewDecoder()), nil
|
||||
}
|
||||
|
||||
func prescan(content []byte) (e encoding.Encoding, name string) {
|
||||
z := html.NewTokenizer(bytes.NewReader(content))
|
||||
for {
|
||||
switch z.Next() {
|
||||
case html.ErrorToken:
|
||||
return nil, ""
|
||||
|
||||
case html.StartTagToken, html.SelfClosingTagToken:
|
||||
tagName, hasAttr := z.TagName()
|
||||
if !bytes.Equal(tagName, []byte("meta")) {
|
||||
continue
|
||||
}
|
||||
attrList := make(map[string]bool)
|
||||
gotPragma := false
|
||||
|
||||
const (
|
||||
dontKnow = iota
|
||||
doNeedPragma
|
||||
doNotNeedPragma
|
||||
)
|
||||
needPragma := dontKnow
|
||||
|
||||
name = ""
|
||||
e = nil
|
||||
for hasAttr {
|
||||
var key, val []byte
|
||||
key, val, hasAttr = z.TagAttr()
|
||||
ks := string(key)
|
||||
if attrList[ks] {
|
||||
continue
|
||||
}
|
||||
attrList[ks] = true
|
||||
for i, c := range val {
|
||||
if 'A' <= c && c <= 'Z' {
|
||||
val[i] = c + 0x20
|
||||
}
|
||||
}
|
||||
|
||||
switch ks {
|
||||
case "http-equiv":
|
||||
if bytes.Equal(val, []byte("content-type")) {
|
||||
gotPragma = true
|
||||
}
|
||||
|
||||
case "content":
|
||||
if e == nil {
|
||||
name = fromMetaElement(string(val))
|
||||
if name != "" {
|
||||
e, name = Lookup(name)
|
||||
if e != nil {
|
||||
needPragma = doNeedPragma
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
case "charset":
|
||||
e, name = Lookup(string(val))
|
||||
needPragma = doNotNeedPragma
|
||||
}
|
||||
}
|
||||
|
||||
if needPragma == dontKnow || needPragma == doNeedPragma && !gotPragma {
|
||||
continue
|
||||
}
|
||||
|
||||
if strings.HasPrefix(name, "utf-16") {
|
||||
name = "utf-8"
|
||||
e = encoding.Nop
|
||||
}
|
||||
|
||||
if e != nil {
|
||||
return e, name
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func fromMetaElement(s string) string {
|
||||
for s != "" {
|
||||
csLoc := strings.Index(s, "charset")
|
||||
if csLoc == -1 {
|
||||
return ""
|
||||
}
|
||||
s = s[csLoc+len("charset"):]
|
||||
s = strings.TrimLeft(s, " \t\n\f\r")
|
||||
if !strings.HasPrefix(s, "=") {
|
||||
continue
|
||||
}
|
||||
s = s[1:]
|
||||
s = strings.TrimLeft(s, " \t\n\f\r")
|
||||
if s == "" {
|
||||
return ""
|
||||
}
|
||||
if q := s[0]; q == '"' || q == '\'' {
|
||||
s = s[1:]
|
||||
closeQuote := strings.IndexRune(s, rune(q))
|
||||
if closeQuote == -1 {
|
||||
return ""
|
||||
}
|
||||
return s[:closeQuote]
|
||||
}
|
||||
|
||||
end := strings.IndexAny(s, "; \t\n\f\r")
|
||||
if end == -1 {
|
||||
end = len(s)
|
||||
}
|
||||
return s[:end]
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
var boms = []struct {
|
||||
bom []byte
|
||||
enc string
|
||||
}{
|
||||
{[]byte{0xfe, 0xff}, "utf-16be"},
|
||||
{[]byte{0xff, 0xfe}, "utf-16le"},
|
||||
{[]byte{0xef, 0xbb, 0xbf}, "utf-8"},
|
||||
}
|
||||
112
vendor/golang.org/x/net/html/const.go
generated
vendored
Normal file
112
vendor/golang.org/x/net/html/const.go
generated
vendored
Normal file
|
|
@ -0,0 +1,112 @@
|
|||
// Copyright 2011 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 html
|
||||
|
||||
// Section 12.2.4.2 of the HTML5 specification says "The following elements
|
||||
// have varying levels of special parsing rules".
|
||||
// https://html.spec.whatwg.org/multipage/syntax.html#the-stack-of-open-elements
|
||||
var isSpecialElementMap = map[string]bool{
|
||||
"address": true,
|
||||
"applet": true,
|
||||
"area": true,
|
||||
"article": true,
|
||||
"aside": true,
|
||||
"base": true,
|
||||
"basefont": true,
|
||||
"bgsound": true,
|
||||
"blockquote": true,
|
||||
"body": true,
|
||||
"br": true,
|
||||
"button": true,
|
||||
"caption": true,
|
||||
"center": true,
|
||||
"col": true,
|
||||
"colgroup": true,
|
||||
"dd": true,
|
||||
"details": true,
|
||||
"dir": true,
|
||||
"div": true,
|
||||
"dl": true,
|
||||
"dt": true,
|
||||
"embed": true,
|
||||
"fieldset": true,
|
||||
"figcaption": true,
|
||||
"figure": true,
|
||||
"footer": true,
|
||||
"form": true,
|
||||
"frame": true,
|
||||
"frameset": true,
|
||||
"h1": true,
|
||||
"h2": true,
|
||||
"h3": true,
|
||||
"h4": true,
|
||||
"h5": true,
|
||||
"h6": true,
|
||||
"head": true,
|
||||
"header": true,
|
||||
"hgroup": true,
|
||||
"hr": true,
|
||||
"html": true,
|
||||
"iframe": true,
|
||||
"img": true,
|
||||
"input": true,
|
||||
"isindex": true, // The 'isindex' element has been removed, but keep it for backwards compatibility.
|
||||
"keygen": true,
|
||||
"li": true,
|
||||
"link": true,
|
||||
"listing": true,
|
||||
"main": true,
|
||||
"marquee": true,
|
||||
"menu": true,
|
||||
"meta": true,
|
||||
"nav": true,
|
||||
"noembed": true,
|
||||
"noframes": true,
|
||||
"noscript": true,
|
||||
"object": true,
|
||||
"ol": true,
|
||||
"p": true,
|
||||
"param": true,
|
||||
"plaintext": true,
|
||||
"pre": true,
|
||||
"script": true,
|
||||
"section": true,
|
||||
"select": true,
|
||||
"source": true,
|
||||
"style": true,
|
||||
"summary": true,
|
||||
"table": true,
|
||||
"tbody": true,
|
||||
"td": true,
|
||||
"template": true,
|
||||
"textarea": true,
|
||||
"tfoot": true,
|
||||
"th": true,
|
||||
"thead": true,
|
||||
"title": true,
|
||||
"tr": true,
|
||||
"track": true,
|
||||
"ul": true,
|
||||
"wbr": true,
|
||||
"xmp": true,
|
||||
}
|
||||
|
||||
func isSpecialElement(element *Node) bool {
|
||||
switch element.Namespace {
|
||||
case "", "html":
|
||||
return isSpecialElementMap[element.Data]
|
||||
case "math":
|
||||
switch element.Data {
|
||||
case "mi", "mo", "mn", "ms", "mtext", "annotation-xml":
|
||||
return true
|
||||
}
|
||||
case "svg":
|
||||
switch element.Data {
|
||||
case "foreignObject", "desc", "title":
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
106
vendor/golang.org/x/net/html/doc.go
generated
vendored
Normal file
106
vendor/golang.org/x/net/html/doc.go
generated
vendored
Normal file
|
|
@ -0,0 +1,106 @@
|
|||
// Copyright 2010 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 html implements an HTML5-compliant tokenizer and parser.
|
||||
|
||||
Tokenization is done by creating a Tokenizer for an io.Reader r. It is the
|
||||
caller's responsibility to ensure that r provides UTF-8 encoded HTML.
|
||||
|
||||
z := html.NewTokenizer(r)
|
||||
|
||||
Given a Tokenizer z, the HTML is tokenized by repeatedly calling z.Next(),
|
||||
which parses the next token and returns its type, or an error:
|
||||
|
||||
for {
|
||||
tt := z.Next()
|
||||
if tt == html.ErrorToken {
|
||||
// ...
|
||||
return ...
|
||||
}
|
||||
// Process the current token.
|
||||
}
|
||||
|
||||
There are two APIs for retrieving the current token. The high-level API is to
|
||||
call Token; the low-level API is to call Text or TagName / TagAttr. Both APIs
|
||||
allow optionally calling Raw after Next but before Token, Text, TagName, or
|
||||
TagAttr. In EBNF notation, the valid call sequence per token is:
|
||||
|
||||
Next {Raw} [ Token | Text | TagName {TagAttr} ]
|
||||
|
||||
Token returns an independent data structure that completely describes a token.
|
||||
Entities (such as "<") are unescaped, tag names and attribute keys are
|
||||
lower-cased, and attributes are collected into a []Attribute. For example:
|
||||
|
||||
for {
|
||||
if z.Next() == html.ErrorToken {
|
||||
// Returning io.EOF indicates success.
|
||||
return z.Err()
|
||||
}
|
||||
emitToken(z.Token())
|
||||
}
|
||||
|
||||
The low-level API performs fewer allocations and copies, but the contents of
|
||||
the []byte values returned by Text, TagName and TagAttr may change on the next
|
||||
call to Next. For example, to extract an HTML page's anchor text:
|
||||
|
||||
depth := 0
|
||||
for {
|
||||
tt := z.Next()
|
||||
switch tt {
|
||||
case html.ErrorToken:
|
||||
return z.Err()
|
||||
case html.TextToken:
|
||||
if depth > 0 {
|
||||
// emitBytes should copy the []byte it receives,
|
||||
// if it doesn't process it immediately.
|
||||
emitBytes(z.Text())
|
||||
}
|
||||
case html.StartTagToken, html.EndTagToken:
|
||||
tn, _ := z.TagName()
|
||||
if len(tn) == 1 && tn[0] == 'a' {
|
||||
if tt == html.StartTagToken {
|
||||
depth++
|
||||
} else {
|
||||
depth--
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Parsing is done by calling Parse with an io.Reader, which returns the root of
|
||||
the parse tree (the document element) as a *Node. It is the caller's
|
||||
responsibility to ensure that the Reader provides UTF-8 encoded HTML. For
|
||||
example, to process each anchor node in depth-first order:
|
||||
|
||||
doc, err := html.Parse(r)
|
||||
if err != nil {
|
||||
// ...
|
||||
}
|
||||
var f func(*html.Node)
|
||||
f = func(n *html.Node) {
|
||||
if n.Type == html.ElementNode && n.Data == "a" {
|
||||
// Do something with n...
|
||||
}
|
||||
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
||||
f(c)
|
||||
}
|
||||
}
|
||||
f(doc)
|
||||
|
||||
The relevant specifications include:
|
||||
https://html.spec.whatwg.org/multipage/syntax.html and
|
||||
https://html.spec.whatwg.org/multipage/syntax.html#tokenization
|
||||
*/
|
||||
package html // import "golang.org/x/net/html"
|
||||
|
||||
// The tokenization algorithm implemented by this package is not a line-by-line
|
||||
// transliteration of the relatively verbose state-machine in the WHATWG
|
||||
// specification. A more direct approach is used instead, where the program
|
||||
// counter implies the state, such as whether it is tokenizing a tag or a text
|
||||
// node. Specification compliance is verified by checking expected and actual
|
||||
// outputs over a test suite rather than aiming for algorithmic fidelity.
|
||||
|
||||
// TODO(nigeltao): Does a DOM API belong in this package or a separate one?
|
||||
// TODO(nigeltao): How does parsing interact with a JavaScript engine?
|
||||
156
vendor/golang.org/x/net/html/doctype.go
generated
vendored
Normal file
156
vendor/golang.org/x/net/html/doctype.go
generated
vendored
Normal file
|
|
@ -0,0 +1,156 @@
|
|||
// Copyright 2011 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 html
|
||||
|
||||
import (
|
||||
"strings"
|
||||
)
|
||||
|
||||
// parseDoctype parses the data from a DoctypeToken into a name,
|
||||
// public identifier, and system identifier. It returns a Node whose Type
|
||||
// is DoctypeNode, whose Data is the name, and which has attributes
|
||||
// named "system" and "public" for the two identifiers if they were present.
|
||||
// quirks is whether the document should be parsed in "quirks mode".
|
||||
func parseDoctype(s string) (n *Node, quirks bool) {
|
||||
n = &Node{Type: DoctypeNode}
|
||||
|
||||
// Find the name.
|
||||
space := strings.IndexAny(s, whitespace)
|
||||
if space == -1 {
|
||||
space = len(s)
|
||||
}
|
||||
n.Data = s[:space]
|
||||
// The comparison to "html" is case-sensitive.
|
||||
if n.Data != "html" {
|
||||
quirks = true
|
||||
}
|
||||
n.Data = strings.ToLower(n.Data)
|
||||
s = strings.TrimLeft(s[space:], whitespace)
|
||||
|
||||
if len(s) < 6 {
|
||||
// It can't start with "PUBLIC" or "SYSTEM".
|
||||
// Ignore the rest of the string.
|
||||
return n, quirks || s != ""
|
||||
}
|
||||
|
||||
key := strings.ToLower(s[:6])
|
||||
s = s[6:]
|
||||
for key == "public" || key == "system" {
|
||||
s = strings.TrimLeft(s, whitespace)
|
||||
if s == "" {
|
||||
break
|
||||
}
|
||||
quote := s[0]
|
||||
if quote != '"' && quote != '\'' {
|
||||
break
|
||||
}
|
||||
s = s[1:]
|
||||
q := strings.IndexRune(s, rune(quote))
|
||||
var id string
|
||||
if q == -1 {
|
||||
id = s
|
||||
s = ""
|
||||
} else {
|
||||
id = s[:q]
|
||||
s = s[q+1:]
|
||||
}
|
||||
n.Attr = append(n.Attr, Attribute{Key: key, Val: id})
|
||||
if key == "public" {
|
||||
key = "system"
|
||||
} else {
|
||||
key = ""
|
||||
}
|
||||
}
|
||||
|
||||
if key != "" || s != "" {
|
||||
quirks = true
|
||||
} else if len(n.Attr) > 0 {
|
||||
if n.Attr[0].Key == "public" {
|
||||
public := strings.ToLower(n.Attr[0].Val)
|
||||
switch public {
|
||||
case "-//w3o//dtd w3 html strict 3.0//en//", "-/w3d/dtd html 4.0 transitional/en", "html":
|
||||
quirks = true
|
||||
default:
|
||||
for _, q := range quirkyIDs {
|
||||
if strings.HasPrefix(public, q) {
|
||||
quirks = true
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
// The following two public IDs only cause quirks mode if there is no system ID.
|
||||
if len(n.Attr) == 1 && (strings.HasPrefix(public, "-//w3c//dtd html 4.01 frameset//") ||
|
||||
strings.HasPrefix(public, "-//w3c//dtd html 4.01 transitional//")) {
|
||||
quirks = true
|
||||
}
|
||||
}
|
||||
if lastAttr := n.Attr[len(n.Attr)-1]; lastAttr.Key == "system" &&
|
||||
strings.ToLower(lastAttr.Val) == "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd" {
|
||||
quirks = true
|
||||
}
|
||||
}
|
||||
|
||||
return n, quirks
|
||||
}
|
||||
|
||||
// quirkyIDs is a list of public doctype identifiers that cause a document
|
||||
// to be interpreted in quirks mode. The identifiers should be in lower case.
|
||||
var quirkyIDs = []string{
|
||||
"+//silmaril//dtd html pro v0r11 19970101//",
|
||||
"-//advasoft ltd//dtd html 3.0 aswedit + extensions//",
|
||||
"-//as//dtd html 3.0 aswedit + extensions//",
|
||||
"-//ietf//dtd html 2.0 level 1//",
|
||||
"-//ietf//dtd html 2.0 level 2//",
|
||||
"-//ietf//dtd html 2.0 strict level 1//",
|
||||
"-//ietf//dtd html 2.0 strict level 2//",
|
||||
"-//ietf//dtd html 2.0 strict//",
|
||||
"-//ietf//dtd html 2.0//",
|
||||
"-//ietf//dtd html 2.1e//",
|
||||
"-//ietf//dtd html 3.0//",
|
||||
"-//ietf//dtd html 3.2 final//",
|
||||
"-//ietf//dtd html 3.2//",
|
||||
"-//ietf//dtd html 3//",
|
||||
"-//ietf//dtd html level 0//",
|
||||
"-//ietf//dtd html level 1//",
|
||||
"-//ietf//dtd html level 2//",
|
||||
"-//ietf//dtd html level 3//",
|
||||
"-//ietf//dtd html strict level 0//",
|
||||
"-//ietf//dtd html strict level 1//",
|
||||
"-//ietf//dtd html strict level 2//",
|
||||
"-//ietf//dtd html strict level 3//",
|
||||
"-//ietf//dtd html strict//",
|
||||
"-//ietf//dtd html//",
|
||||
"-//metrius//dtd metrius presentational//",
|
||||
"-//microsoft//dtd internet explorer 2.0 html strict//",
|
||||
"-//microsoft//dtd internet explorer 2.0 html//",
|
||||
"-//microsoft//dtd internet explorer 2.0 tables//",
|
||||
"-//microsoft//dtd internet explorer 3.0 html strict//",
|
||||
"-//microsoft//dtd internet explorer 3.0 html//",
|
||||
"-//microsoft//dtd internet explorer 3.0 tables//",
|
||||
"-//netscape comm. corp.//dtd html//",
|
||||
"-//netscape comm. corp.//dtd strict html//",
|
||||
"-//o'reilly and associates//dtd html 2.0//",
|
||||
"-//o'reilly and associates//dtd html extended 1.0//",
|
||||
"-//o'reilly and associates//dtd html extended relaxed 1.0//",
|
||||
"-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//",
|
||||
"-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//",
|
||||
"-//spyglass//dtd html 2.0 extended//",
|
||||
"-//sq//dtd html 2.0 hotmetal + extensions//",
|
||||
"-//sun microsystems corp.//dtd hotjava html//",
|
||||
"-//sun microsystems corp.//dtd hotjava strict html//",
|
||||
"-//w3c//dtd html 3 1995-03-24//",
|
||||
"-//w3c//dtd html 3.2 draft//",
|
||||
"-//w3c//dtd html 3.2 final//",
|
||||
"-//w3c//dtd html 3.2//",
|
||||
"-//w3c//dtd html 3.2s draft//",
|
||||
"-//w3c//dtd html 4.0 frameset//",
|
||||
"-//w3c//dtd html 4.0 transitional//",
|
||||
"-//w3c//dtd html experimental 19960712//",
|
||||
"-//w3c//dtd html experimental 970421//",
|
||||
"-//w3c//dtd w3 html//",
|
||||
"-//w3o//dtd w3 html 3.0//",
|
||||
"-//webtechs//dtd mozilla html 2.0//",
|
||||
"-//webtechs//dtd mozilla html//",
|
||||
}
|
||||
2253
vendor/golang.org/x/net/html/entity.go
generated
vendored
Normal file
2253
vendor/golang.org/x/net/html/entity.go
generated
vendored
Normal file
File diff suppressed because it is too large
Load diff
258
vendor/golang.org/x/net/html/escape.go
generated
vendored
Normal file
258
vendor/golang.org/x/net/html/escape.go
generated
vendored
Normal file
|
|
@ -0,0 +1,258 @@
|
|||
// Copyright 2010 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 html
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"strings"
|
||||
"unicode/utf8"
|
||||
)
|
||||
|
||||
// These replacements permit compatibility with old numeric entities that
|
||||
// assumed Windows-1252 encoding.
|
||||
// https://html.spec.whatwg.org/multipage/syntax.html#consume-a-character-reference
|
||||
var replacementTable = [...]rune{
|
||||
'\u20AC', // First entry is what 0x80 should be replaced with.
|
||||
'\u0081',
|
||||
'\u201A',
|
||||
'\u0192',
|
||||
'\u201E',
|
||||
'\u2026',
|
||||
'\u2020',
|
||||
'\u2021',
|
||||
'\u02C6',
|
||||
'\u2030',
|
||||
'\u0160',
|
||||
'\u2039',
|
||||
'\u0152',
|
||||
'\u008D',
|
||||
'\u017D',
|
||||
'\u008F',
|
||||
'\u0090',
|
||||
'\u2018',
|
||||
'\u2019',
|
||||
'\u201C',
|
||||
'\u201D',
|
||||
'\u2022',
|
||||
'\u2013',
|
||||
'\u2014',
|
||||
'\u02DC',
|
||||
'\u2122',
|
||||
'\u0161',
|
||||
'\u203A',
|
||||
'\u0153',
|
||||
'\u009D',
|
||||
'\u017E',
|
||||
'\u0178', // Last entry is 0x9F.
|
||||
// 0x00->'\uFFFD' is handled programmatically.
|
||||
// 0x0D->'\u000D' is a no-op.
|
||||
}
|
||||
|
||||
// unescapeEntity reads an entity like "<" from b[src:] and writes the
|
||||
// corresponding "<" to b[dst:], returning the incremented dst and src cursors.
|
||||
// Precondition: b[src] == '&' && dst <= src.
|
||||
// attribute should be true if parsing an attribute value.
|
||||
func unescapeEntity(b []byte, dst, src int, attribute bool) (dst1, src1 int) {
|
||||
// https://html.spec.whatwg.org/multipage/syntax.html#consume-a-character-reference
|
||||
|
||||
// i starts at 1 because we already know that s[0] == '&'.
|
||||
i, s := 1, b[src:]
|
||||
|
||||
if len(s) <= 1 {
|
||||
b[dst] = b[src]
|
||||
return dst + 1, src + 1
|
||||
}
|
||||
|
||||
if s[i] == '#' {
|
||||
if len(s) <= 3 { // We need to have at least "&#.".
|
||||
b[dst] = b[src]
|
||||
return dst + 1, src + 1
|
||||
}
|
||||
i++
|
||||
c := s[i]
|
||||
hex := false
|
||||
if c == 'x' || c == 'X' {
|
||||
hex = true
|
||||
i++
|
||||
}
|
||||
|
||||
x := '\x00'
|
||||
for i < len(s) {
|
||||
c = s[i]
|
||||
i++
|
||||
if hex {
|
||||
if '0' <= c && c <= '9' {
|
||||
x = 16*x + rune(c) - '0'
|
||||
continue
|
||||
} else if 'a' <= c && c <= 'f' {
|
||||
x = 16*x + rune(c) - 'a' + 10
|
||||
continue
|
||||
} else if 'A' <= c && c <= 'F' {
|
||||
x = 16*x + rune(c) - 'A' + 10
|
||||
continue
|
||||
}
|
||||
} else if '0' <= c && c <= '9' {
|
||||
x = 10*x + rune(c) - '0'
|
||||
continue
|
||||
}
|
||||
if c != ';' {
|
||||
i--
|
||||
}
|
||||
break
|
||||
}
|
||||
|
||||
if i <= 3 { // No characters matched.
|
||||
b[dst] = b[src]
|
||||
return dst + 1, src + 1
|
||||
}
|
||||
|
||||
if 0x80 <= x && x <= 0x9F {
|
||||
// Replace characters from Windows-1252 with UTF-8 equivalents.
|
||||
x = replacementTable[x-0x80]
|
||||
} else if x == 0 || (0xD800 <= x && x <= 0xDFFF) || x > 0x10FFFF {
|
||||
// Replace invalid characters with the replacement character.
|
||||
x = '\uFFFD'
|
||||
}
|
||||
|
||||
return dst + utf8.EncodeRune(b[dst:], x), src + i
|
||||
}
|
||||
|
||||
// Consume the maximum number of characters possible, with the
|
||||
// consumed characters matching one of the named references.
|
||||
|
||||
for i < len(s) {
|
||||
c := s[i]
|
||||
i++
|
||||
// Lower-cased characters are more common in entities, so we check for them first.
|
||||
if 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' || '0' <= c && c <= '9' {
|
||||
continue
|
||||
}
|
||||
if c != ';' {
|
||||
i--
|
||||
}
|
||||
break
|
||||
}
|
||||
|
||||
entityName := string(s[1:i])
|
||||
if entityName == "" {
|
||||
// No-op.
|
||||
} else if attribute && entityName[len(entityName)-1] != ';' && len(s) > i && s[i] == '=' {
|
||||
// No-op.
|
||||
} else if x := entity[entityName]; x != 0 {
|
||||
return dst + utf8.EncodeRune(b[dst:], x), src + i
|
||||
} else if x := entity2[entityName]; x[0] != 0 {
|
||||
dst1 := dst + utf8.EncodeRune(b[dst:], x[0])
|
||||
return dst1 + utf8.EncodeRune(b[dst1:], x[1]), src + i
|
||||
} else if !attribute {
|
||||
maxLen := len(entityName) - 1
|
||||
if maxLen > longestEntityWithoutSemicolon {
|
||||
maxLen = longestEntityWithoutSemicolon
|
||||
}
|
||||
for j := maxLen; j > 1; j-- {
|
||||
if x := entity[entityName[:j]]; x != 0 {
|
||||
return dst + utf8.EncodeRune(b[dst:], x), src + j + 1
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
dst1, src1 = dst+i, src+i
|
||||
copy(b[dst:dst1], b[src:src1])
|
||||
return dst1, src1
|
||||
}
|
||||
|
||||
// unescape unescapes b's entities in-place, so that "a<b" becomes "a<b".
|
||||
// attribute should be true if parsing an attribute value.
|
||||
func unescape(b []byte, attribute bool) []byte {
|
||||
for i, c := range b {
|
||||
if c == '&' {
|
||||
dst, src := unescapeEntity(b, i, i, attribute)
|
||||
for src < len(b) {
|
||||
c := b[src]
|
||||
if c == '&' {
|
||||
dst, src = unescapeEntity(b, dst, src, attribute)
|
||||
} else {
|
||||
b[dst] = c
|
||||
dst, src = dst+1, src+1
|
||||
}
|
||||
}
|
||||
return b[0:dst]
|
||||
}
|
||||
}
|
||||
return b
|
||||
}
|
||||
|
||||
// lower lower-cases the A-Z bytes in b in-place, so that "aBc" becomes "abc".
|
||||
func lower(b []byte) []byte {
|
||||
for i, c := range b {
|
||||
if 'A' <= c && c <= 'Z' {
|
||||
b[i] = c + 'a' - 'A'
|
||||
}
|
||||
}
|
||||
return b
|
||||
}
|
||||
|
||||
const escapedChars = "&'<>\"\r"
|
||||
|
||||
func escape(w writer, s string) error {
|
||||
i := strings.IndexAny(s, escapedChars)
|
||||
for i != -1 {
|
||||
if _, err := w.WriteString(s[:i]); err != nil {
|
||||
return err
|
||||
}
|
||||
var esc string
|
||||
switch s[i] {
|
||||
case '&':
|
||||
esc = "&"
|
||||
case '\'':
|
||||
// "'" is shorter than "'" and apos was not in HTML until HTML5.
|
||||
esc = "'"
|
||||
case '<':
|
||||
esc = "<"
|
||||
case '>':
|
||||
esc = ">"
|
||||
case '"':
|
||||
// """ is shorter than """.
|
||||
esc = """
|
||||
case '\r':
|
||||
esc = " "
|
||||
default:
|
||||
panic("unrecognized escape character")
|
||||
}
|
||||
s = s[i+1:]
|
||||
if _, err := w.WriteString(esc); err != nil {
|
||||
return err
|
||||
}
|
||||
i = strings.IndexAny(s, escapedChars)
|
||||
}
|
||||
_, err := w.WriteString(s)
|
||||
return err
|
||||
}
|
||||
|
||||
// EscapeString escapes special characters like "<" to become "<". It
|
||||
// escapes only five such characters: <, >, &, ' and ".
|
||||
// UnescapeString(EscapeString(s)) == s always holds, but the converse isn't
|
||||
// always true.
|
||||
func EscapeString(s string) string {
|
||||
if strings.IndexAny(s, escapedChars) == -1 {
|
||||
return s
|
||||
}
|
||||
var buf bytes.Buffer
|
||||
escape(&buf, s)
|
||||
return buf.String()
|
||||
}
|
||||
|
||||
// UnescapeString unescapes entities like "<" to become "<". It unescapes a
|
||||
// larger range of entities than EscapeString escapes. For example, "á"
|
||||
// unescapes to "á", as does "á" and "&xE1;".
|
||||
// UnescapeString(EscapeString(s)) == s always holds, but the converse isn't
|
||||
// always true.
|
||||
func UnescapeString(s string) string {
|
||||
for _, c := range s {
|
||||
if c == '&' {
|
||||
return string(unescape([]byte(s), false))
|
||||
}
|
||||
}
|
||||
return s
|
||||
}
|
||||
226
vendor/golang.org/x/net/html/foreign.go
generated
vendored
Normal file
226
vendor/golang.org/x/net/html/foreign.go
generated
vendored
Normal file
|
|
@ -0,0 +1,226 @@
|
|||
// Copyright 2011 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 html
|
||||
|
||||
import (
|
||||
"strings"
|
||||
)
|
||||
|
||||
func adjustAttributeNames(aa []Attribute, nameMap map[string]string) {
|
||||
for i := range aa {
|
||||
if newName, ok := nameMap[aa[i].Key]; ok {
|
||||
aa[i].Key = newName
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func adjustForeignAttributes(aa []Attribute) {
|
||||
for i, a := range aa {
|
||||
if a.Key == "" || a.Key[0] != 'x' {
|
||||
continue
|
||||
}
|
||||
switch a.Key {
|
||||
case "xlink:actuate", "xlink:arcrole", "xlink:href", "xlink:role", "xlink:show",
|
||||
"xlink:title", "xlink:type", "xml:base", "xml:lang", "xml:space", "xmlns:xlink":
|
||||
j := strings.Index(a.Key, ":")
|
||||
aa[i].Namespace = a.Key[:j]
|
||||
aa[i].Key = a.Key[j+1:]
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func htmlIntegrationPoint(n *Node) bool {
|
||||
if n.Type != ElementNode {
|
||||
return false
|
||||
}
|
||||
switch n.Namespace {
|
||||
case "math":
|
||||
if n.Data == "annotation-xml" {
|
||||
for _, a := range n.Attr {
|
||||
if a.Key == "encoding" {
|
||||
val := strings.ToLower(a.Val)
|
||||
if val == "text/html" || val == "application/xhtml+xml" {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
case "svg":
|
||||
switch n.Data {
|
||||
case "desc", "foreignObject", "title":
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
func mathMLTextIntegrationPoint(n *Node) bool {
|
||||
if n.Namespace != "math" {
|
||||
return false
|
||||
}
|
||||
switch n.Data {
|
||||
case "mi", "mo", "mn", "ms", "mtext":
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// Section 12.2.6.5.
|
||||
var breakout = map[string]bool{
|
||||
"b": true,
|
||||
"big": true,
|
||||
"blockquote": true,
|
||||
"body": true,
|
||||
"br": true,
|
||||
"center": true,
|
||||
"code": true,
|
||||
"dd": true,
|
||||
"div": true,
|
||||
"dl": true,
|
||||
"dt": true,
|
||||
"em": true,
|
||||
"embed": true,
|
||||
"h1": true,
|
||||
"h2": true,
|
||||
"h3": true,
|
||||
"h4": true,
|
||||
"h5": true,
|
||||
"h6": true,
|
||||
"head": true,
|
||||
"hr": true,
|
||||
"i": true,
|
||||
"img": true,
|
||||
"li": true,
|
||||
"listing": true,
|
||||
"menu": true,
|
||||
"meta": true,
|
||||
"nobr": true,
|
||||
"ol": true,
|
||||
"p": true,
|
||||
"pre": true,
|
||||
"ruby": true,
|
||||
"s": true,
|
||||
"small": true,
|
||||
"span": true,
|
||||
"strong": true,
|
||||
"strike": true,
|
||||
"sub": true,
|
||||
"sup": true,
|
||||
"table": true,
|
||||
"tt": true,
|
||||
"u": true,
|
||||
"ul": true,
|
||||
"var": true,
|
||||
}
|
||||
|
||||
// Section 12.2.6.5.
|
||||
var svgTagNameAdjustments = map[string]string{
|
||||
"altglyph": "altGlyph",
|
||||
"altglyphdef": "altGlyphDef",
|
||||
"altglyphitem": "altGlyphItem",
|
||||
"animatecolor": "animateColor",
|
||||
"animatemotion": "animateMotion",
|
||||
"animatetransform": "animateTransform",
|
||||
"clippath": "clipPath",
|
||||
"feblend": "feBlend",
|
||||
"fecolormatrix": "feColorMatrix",
|
||||
"fecomponenttransfer": "feComponentTransfer",
|
||||
"fecomposite": "feComposite",
|
||||
"feconvolvematrix": "feConvolveMatrix",
|
||||
"fediffuselighting": "feDiffuseLighting",
|
||||
"fedisplacementmap": "feDisplacementMap",
|
||||
"fedistantlight": "feDistantLight",
|
||||
"feflood": "feFlood",
|
||||
"fefunca": "feFuncA",
|
||||
"fefuncb": "feFuncB",
|
||||
"fefuncg": "feFuncG",
|
||||
"fefuncr": "feFuncR",
|
||||
"fegaussianblur": "feGaussianBlur",
|
||||
"feimage": "feImage",
|
||||
"femerge": "feMerge",
|
||||
"femergenode": "feMergeNode",
|
||||
"femorphology": "feMorphology",
|
||||
"feoffset": "feOffset",
|
||||
"fepointlight": "fePointLight",
|
||||
"fespecularlighting": "feSpecularLighting",
|
||||
"fespotlight": "feSpotLight",
|
||||
"fetile": "feTile",
|
||||
"feturbulence": "feTurbulence",
|
||||
"foreignobject": "foreignObject",
|
||||
"glyphref": "glyphRef",
|
||||
"lineargradient": "linearGradient",
|
||||
"radialgradient": "radialGradient",
|
||||
"textpath": "textPath",
|
||||
}
|
||||
|
||||
// Section 12.2.6.1
|
||||
var mathMLAttributeAdjustments = map[string]string{
|
||||
"definitionurl": "definitionURL",
|
||||
}
|
||||
|
||||
var svgAttributeAdjustments = map[string]string{
|
||||
"attributename": "attributeName",
|
||||
"attributetype": "attributeType",
|
||||
"basefrequency": "baseFrequency",
|
||||
"baseprofile": "baseProfile",
|
||||
"calcmode": "calcMode",
|
||||
"clippathunits": "clipPathUnits",
|
||||
"contentscripttype": "contentScriptType",
|
||||
"contentstyletype": "contentStyleType",
|
||||
"diffuseconstant": "diffuseConstant",
|
||||
"edgemode": "edgeMode",
|
||||
"externalresourcesrequired": "externalResourcesRequired",
|
||||
"filterres": "filterRes",
|
||||
"filterunits": "filterUnits",
|
||||
"glyphref": "glyphRef",
|
||||
"gradienttransform": "gradientTransform",
|
||||
"gradientunits": "gradientUnits",
|
||||
"kernelmatrix": "kernelMatrix",
|
||||
"kernelunitlength": "kernelUnitLength",
|
||||
"keypoints": "keyPoints",
|
||||
"keysplines": "keySplines",
|
||||
"keytimes": "keyTimes",
|
||||
"lengthadjust": "lengthAdjust",
|
||||
"limitingconeangle": "limitingConeAngle",
|
||||
"markerheight": "markerHeight",
|
||||
"markerunits": "markerUnits",
|
||||
"markerwidth": "markerWidth",
|
||||
"maskcontentunits": "maskContentUnits",
|
||||
"maskunits": "maskUnits",
|
||||
"numoctaves": "numOctaves",
|
||||
"pathlength": "pathLength",
|
||||
"patterncontentunits": "patternContentUnits",
|
||||
"patterntransform": "patternTransform",
|
||||
"patternunits": "patternUnits",
|
||||
"pointsatx": "pointsAtX",
|
||||
"pointsaty": "pointsAtY",
|
||||
"pointsatz": "pointsAtZ",
|
||||
"preservealpha": "preserveAlpha",
|
||||
"preserveaspectratio": "preserveAspectRatio",
|
||||
"primitiveunits": "primitiveUnits",
|
||||
"refx": "refX",
|
||||
"refy": "refY",
|
||||
"repeatcount": "repeatCount",
|
||||
"repeatdur": "repeatDur",
|
||||
"requiredextensions": "requiredExtensions",
|
||||
"requiredfeatures": "requiredFeatures",
|
||||
"specularconstant": "specularConstant",
|
||||
"specularexponent": "specularExponent",
|
||||
"spreadmethod": "spreadMethod",
|
||||
"startoffset": "startOffset",
|
||||
"stddeviation": "stdDeviation",
|
||||
"stitchtiles": "stitchTiles",
|
||||
"surfacescale": "surfaceScale",
|
||||
"systemlanguage": "systemLanguage",
|
||||
"tablevalues": "tableValues",
|
||||
"targetx": "targetX",
|
||||
"targety": "targetY",
|
||||
"textlength": "textLength",
|
||||
"viewbox": "viewBox",
|
||||
"viewtarget": "viewTarget",
|
||||
"xchannelselector": "xChannelSelector",
|
||||
"ychannelselector": "yChannelSelector",
|
||||
"zoomandpan": "zoomAndPan",
|
||||
}
|
||||
220
vendor/golang.org/x/net/html/node.go
generated
vendored
Normal file
220
vendor/golang.org/x/net/html/node.go
generated
vendored
Normal file
|
|
@ -0,0 +1,220 @@
|
|||
// Copyright 2011 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 html
|
||||
|
||||
import (
|
||||
"golang.org/x/net/html/atom"
|
||||
)
|
||||
|
||||
// A NodeType is the type of a Node.
|
||||
type NodeType uint32
|
||||
|
||||
const (
|
||||
ErrorNode NodeType = iota
|
||||
TextNode
|
||||
DocumentNode
|
||||
ElementNode
|
||||
CommentNode
|
||||
DoctypeNode
|
||||
scopeMarkerNode
|
||||
)
|
||||
|
||||
// Section 12.2.4.3 says "The markers are inserted when entering applet,
|
||||
// object, marquee, template, td, th, and caption elements, and are used
|
||||
// to prevent formatting from "leaking" into applet, object, marquee,
|
||||
// template, td, th, and caption elements".
|
||||
var scopeMarker = Node{Type: scopeMarkerNode}
|
||||
|
||||
// A Node consists of a NodeType and some Data (tag name for element nodes,
|
||||
// content for text) and are part of a tree of Nodes. Element nodes may also
|
||||
// have a Namespace and contain a slice of Attributes. Data is unescaped, so
|
||||
// that it looks like "a<b" rather than "a<b". For element nodes, DataAtom
|
||||
// is the atom for Data, or zero if Data is not a known tag name.
|
||||
//
|
||||
// An empty Namespace implies a "http://www.w3.org/1999/xhtml" namespace.
|
||||
// Similarly, "math" is short for "http://www.w3.org/1998/Math/MathML", and
|
||||
// "svg" is short for "http://www.w3.org/2000/svg".
|
||||
type Node struct {
|
||||
Parent, FirstChild, LastChild, PrevSibling, NextSibling *Node
|
||||
|
||||
Type NodeType
|
||||
DataAtom atom.Atom
|
||||
Data string
|
||||
Namespace string
|
||||
Attr []Attribute
|
||||
}
|
||||
|
||||
// InsertBefore inserts newChild as a child of n, immediately before oldChild
|
||||
// in the sequence of n's children. oldChild may be nil, in which case newChild
|
||||
// is appended to the end of n's children.
|
||||
//
|
||||
// It will panic if newChild already has a parent or siblings.
|
||||
func (n *Node) InsertBefore(newChild, oldChild *Node) {
|
||||
if newChild.Parent != nil || newChild.PrevSibling != nil || newChild.NextSibling != nil {
|
||||
panic("html: InsertBefore called for an attached child Node")
|
||||
}
|
||||
var prev, next *Node
|
||||
if oldChild != nil {
|
||||
prev, next = oldChild.PrevSibling, oldChild
|
||||
} else {
|
||||
prev = n.LastChild
|
||||
}
|
||||
if prev != nil {
|
||||
prev.NextSibling = newChild
|
||||
} else {
|
||||
n.FirstChild = newChild
|
||||
}
|
||||
if next != nil {
|
||||
next.PrevSibling = newChild
|
||||
} else {
|
||||
n.LastChild = newChild
|
||||
}
|
||||
newChild.Parent = n
|
||||
newChild.PrevSibling = prev
|
||||
newChild.NextSibling = next
|
||||
}
|
||||
|
||||
// AppendChild adds a node c as a child of n.
|
||||
//
|
||||
// It will panic if c already has a parent or siblings.
|
||||
func (n *Node) AppendChild(c *Node) {
|
||||
if c.Parent != nil || c.PrevSibling != nil || c.NextSibling != nil {
|
||||
panic("html: AppendChild called for an attached child Node")
|
||||
}
|
||||
last := n.LastChild
|
||||
if last != nil {
|
||||
last.NextSibling = c
|
||||
} else {
|
||||
n.FirstChild = c
|
||||
}
|
||||
n.LastChild = c
|
||||
c.Parent = n
|
||||
c.PrevSibling = last
|
||||
}
|
||||
|
||||
// RemoveChild removes a node c that is a child of n. Afterwards, c will have
|
||||
// no parent and no siblings.
|
||||
//
|
||||
// It will panic if c's parent is not n.
|
||||
func (n *Node) RemoveChild(c *Node) {
|
||||
if c.Parent != n {
|
||||
panic("html: RemoveChild called for a non-child Node")
|
||||
}
|
||||
if n.FirstChild == c {
|
||||
n.FirstChild = c.NextSibling
|
||||
}
|
||||
if c.NextSibling != nil {
|
||||
c.NextSibling.PrevSibling = c.PrevSibling
|
||||
}
|
||||
if n.LastChild == c {
|
||||
n.LastChild = c.PrevSibling
|
||||
}
|
||||
if c.PrevSibling != nil {
|
||||
c.PrevSibling.NextSibling = c.NextSibling
|
||||
}
|
||||
c.Parent = nil
|
||||
c.PrevSibling = nil
|
||||
c.NextSibling = nil
|
||||
}
|
||||
|
||||
// reparentChildren reparents all of src's child nodes to dst.
|
||||
func reparentChildren(dst, src *Node) {
|
||||
for {
|
||||
child := src.FirstChild
|
||||
if child == nil {
|
||||
break
|
||||
}
|
||||
src.RemoveChild(child)
|
||||
dst.AppendChild(child)
|
||||
}
|
||||
}
|
||||
|
||||
// clone returns a new node with the same type, data and attributes.
|
||||
// The clone has no parent, no siblings and no children.
|
||||
func (n *Node) clone() *Node {
|
||||
m := &Node{
|
||||
Type: n.Type,
|
||||
DataAtom: n.DataAtom,
|
||||
Data: n.Data,
|
||||
Attr: make([]Attribute, len(n.Attr)),
|
||||
}
|
||||
copy(m.Attr, n.Attr)
|
||||
return m
|
||||
}
|
||||
|
||||
// nodeStack is a stack of nodes.
|
||||
type nodeStack []*Node
|
||||
|
||||
// pop pops the stack. It will panic if s is empty.
|
||||
func (s *nodeStack) pop() *Node {
|
||||
i := len(*s)
|
||||
n := (*s)[i-1]
|
||||
*s = (*s)[:i-1]
|
||||
return n
|
||||
}
|
||||
|
||||
// top returns the most recently pushed node, or nil if s is empty.
|
||||
func (s *nodeStack) top() *Node {
|
||||
if i := len(*s); i > 0 {
|
||||
return (*s)[i-1]
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// index returns the index of the top-most occurrence of n in the stack, or -1
|
||||
// if n is not present.
|
||||
func (s *nodeStack) index(n *Node) int {
|
||||
for i := len(*s) - 1; i >= 0; i-- {
|
||||
if (*s)[i] == n {
|
||||
return i
|
||||
}
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
||||
// contains returns whether a is within s.
|
||||
func (s *nodeStack) contains(a atom.Atom) bool {
|
||||
for _, n := range *s {
|
||||
if n.DataAtom == a && n.Namespace == "" {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// insert inserts a node at the given index.
|
||||
func (s *nodeStack) insert(i int, n *Node) {
|
||||
(*s) = append(*s, nil)
|
||||
copy((*s)[i+1:], (*s)[i:])
|
||||
(*s)[i] = n
|
||||
}
|
||||
|
||||
// remove removes a node from the stack. It is a no-op if n is not present.
|
||||
func (s *nodeStack) remove(n *Node) {
|
||||
i := s.index(n)
|
||||
if i == -1 {
|
||||
return
|
||||
}
|
||||
copy((*s)[i:], (*s)[i+1:])
|
||||
j := len(*s) - 1
|
||||
(*s)[j] = nil
|
||||
*s = (*s)[:j]
|
||||
}
|
||||
|
||||
type insertionModeStack []insertionMode
|
||||
|
||||
func (s *insertionModeStack) pop() (im insertionMode) {
|
||||
i := len(*s)
|
||||
im = (*s)[i-1]
|
||||
*s = (*s)[:i-1]
|
||||
return im
|
||||
}
|
||||
|
||||
func (s *insertionModeStack) top() insertionMode {
|
||||
if i := len(*s); i > 0 {
|
||||
return (*s)[i-1]
|
||||
}
|
||||
return nil
|
||||
}
|
||||
2417
vendor/golang.org/x/net/html/parse.go
generated
vendored
Normal file
2417
vendor/golang.org/x/net/html/parse.go
generated
vendored
Normal file
File diff suppressed because it is too large
Load diff
271
vendor/golang.org/x/net/html/render.go
generated
vendored
Normal file
271
vendor/golang.org/x/net/html/render.go
generated
vendored
Normal file
|
|
@ -0,0 +1,271 @@
|
|||
// Copyright 2011 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 html
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"strings"
|
||||
)
|
||||
|
||||
type writer interface {
|
||||
io.Writer
|
||||
io.ByteWriter
|
||||
WriteString(string) (int, error)
|
||||
}
|
||||
|
||||
// Render renders the parse tree n to the given writer.
|
||||
//
|
||||
// Rendering is done on a 'best effort' basis: calling Parse on the output of
|
||||
// Render will always result in something similar to the original tree, but it
|
||||
// is not necessarily an exact clone unless the original tree was 'well-formed'.
|
||||
// 'Well-formed' is not easily specified; the HTML5 specification is
|
||||
// complicated.
|
||||
//
|
||||
// Calling Parse on arbitrary input typically results in a 'well-formed' parse
|
||||
// tree. However, it is possible for Parse to yield a 'badly-formed' parse tree.
|
||||
// For example, in a 'well-formed' parse tree, no <a> element is a child of
|
||||
// another <a> element: parsing "<a><a>" results in two sibling elements.
|
||||
// Similarly, in a 'well-formed' parse tree, no <a> element is a child of a
|
||||
// <table> element: parsing "<p><table><a>" results in a <p> with two sibling
|
||||
// children; the <a> is reparented to the <table>'s parent. However, calling
|
||||
// Parse on "<a><table><a>" does not return an error, but the result has an <a>
|
||||
// element with an <a> child, and is therefore not 'well-formed'.
|
||||
//
|
||||
// Programmatically constructed trees are typically also 'well-formed', but it
|
||||
// is possible to construct a tree that looks innocuous but, when rendered and
|
||||
// re-parsed, results in a different tree. A simple example is that a solitary
|
||||
// text node would become a tree containing <html>, <head> and <body> elements.
|
||||
// Another example is that the programmatic equivalent of "a<head>b</head>c"
|
||||
// becomes "<html><head><head/><body>abc</body></html>".
|
||||
func Render(w io.Writer, n *Node) error {
|
||||
if x, ok := w.(writer); ok {
|
||||
return render(x, n)
|
||||
}
|
||||
buf := bufio.NewWriter(w)
|
||||
if err := render(buf, n); err != nil {
|
||||
return err
|
||||
}
|
||||
return buf.Flush()
|
||||
}
|
||||
|
||||
// plaintextAbort is returned from render1 when a <plaintext> element
|
||||
// has been rendered. No more end tags should be rendered after that.
|
||||
var plaintextAbort = errors.New("html: internal error (plaintext abort)")
|
||||
|
||||
func render(w writer, n *Node) error {
|
||||
err := render1(w, n)
|
||||
if err == plaintextAbort {
|
||||
err = nil
|
||||
}
|
||||
return err
|
||||
}
|
||||
|
||||
func render1(w writer, n *Node) error {
|
||||
// Render non-element nodes; these are the easy cases.
|
||||
switch n.Type {
|
||||
case ErrorNode:
|
||||
return errors.New("html: cannot render an ErrorNode node")
|
||||
case TextNode:
|
||||
return escape(w, n.Data)
|
||||
case DocumentNode:
|
||||
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
||||
if err := render1(w, c); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
return nil
|
||||
case ElementNode:
|
||||
// No-op.
|
||||
case CommentNode:
|
||||
if _, err := w.WriteString("<!--"); err != nil {
|
||||
return err
|
||||
}
|
||||
if _, err := w.WriteString(n.Data); err != nil {
|
||||
return err
|
||||
}
|
||||
if _, err := w.WriteString("-->"); err != nil {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
case DoctypeNode:
|
||||
if _, err := w.WriteString("<!DOCTYPE "); err != nil {
|
||||
return err
|
||||
}
|
||||
if _, err := w.WriteString(n.Data); err != nil {
|
||||
return err
|
||||
}
|
||||
if n.Attr != nil {
|
||||
var p, s string
|
||||
for _, a := range n.Attr {
|
||||
switch a.Key {
|
||||
case "public":
|
||||
p = a.Val
|
||||
case "system":
|
||||
s = a.Val
|
||||
}
|
||||
}
|
||||
if p != "" {
|
||||
if _, err := w.WriteString(" PUBLIC "); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := writeQuoted(w, p); err != nil {
|
||||
return err
|
||||
}
|
||||
if s != "" {
|
||||
if err := w.WriteByte(' '); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := writeQuoted(w, s); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
} else if s != "" {
|
||||
if _, err := w.WriteString(" SYSTEM "); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := writeQuoted(w, s); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
}
|
||||
return w.WriteByte('>')
|
||||
default:
|
||||
return errors.New("html: unknown node type")
|
||||
}
|
||||
|
||||
// Render the <xxx> opening tag.
|
||||
if err := w.WriteByte('<'); err != nil {
|
||||
return err
|
||||
}
|
||||
if _, err := w.WriteString(n.Data); err != nil {
|
||||
return err
|
||||
}
|
||||
for _, a := range n.Attr {
|
||||
if err := w.WriteByte(' '); err != nil {
|
||||
return err
|
||||
}
|
||||
if a.Namespace != "" {
|
||||
if _, err := w.WriteString(a.Namespace); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := w.WriteByte(':'); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
if _, err := w.WriteString(a.Key); err != nil {
|
||||
return err
|
||||
}
|
||||
if _, err := w.WriteString(`="`); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := escape(w, a.Val); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := w.WriteByte('"'); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
if voidElements[n.Data] {
|
||||
if n.FirstChild != nil {
|
||||
return fmt.Errorf("html: void element <%s> has child nodes", n.Data)
|
||||
}
|
||||
_, err := w.WriteString("/>")
|
||||
return err
|
||||
}
|
||||
if err := w.WriteByte('>'); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
// Add initial newline where there is danger of a newline beging ignored.
|
||||
if c := n.FirstChild; c != nil && c.Type == TextNode && strings.HasPrefix(c.Data, "\n") {
|
||||
switch n.Data {
|
||||
case "pre", "listing", "textarea":
|
||||
if err := w.WriteByte('\n'); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Render any child nodes.
|
||||
switch n.Data {
|
||||
case "iframe", "noembed", "noframes", "noscript", "plaintext", "script", "style", "xmp":
|
||||
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
||||
if c.Type == TextNode {
|
||||
if _, err := w.WriteString(c.Data); err != nil {
|
||||
return err
|
||||
}
|
||||
} else {
|
||||
if err := render1(w, c); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
}
|
||||
if n.Data == "plaintext" {
|
||||
// Don't render anything else. <plaintext> must be the
|
||||
// last element in the file, with no closing tag.
|
||||
return plaintextAbort
|
||||
}
|
||||
default:
|
||||
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
||||
if err := render1(w, c); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Render the </xxx> closing tag.
|
||||
if _, err := w.WriteString("</"); err != nil {
|
||||
return err
|
||||
}
|
||||
if _, err := w.WriteString(n.Data); err != nil {
|
||||
return err
|
||||
}
|
||||
return w.WriteByte('>')
|
||||
}
|
||||
|
||||
// writeQuoted writes s to w surrounded by quotes. Normally it will use double
|
||||
// quotes, but if s contains a double quote, it will use single quotes.
|
||||
// It is used for writing the identifiers in a doctype declaration.
|
||||
// In valid HTML, they can't contain both types of quotes.
|
||||
func writeQuoted(w writer, s string) error {
|
||||
var q byte = '"'
|
||||
if strings.Contains(s, `"`) {
|
||||
q = '\''
|
||||
}
|
||||
if err := w.WriteByte(q); err != nil {
|
||||
return err
|
||||
}
|
||||
if _, err := w.WriteString(s); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := w.WriteByte(q); err != nil {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Section 12.1.2, "Elements", gives this list of void elements. Void elements
|
||||
// are those that can't have any contents.
|
||||
var voidElements = map[string]bool{
|
||||
"area": true,
|
||||
"base": true,
|
||||
"br": true,
|
||||
"col": true,
|
||||
"command": true,
|
||||
"embed": true,
|
||||
"hr": true,
|
||||
"img": true,
|
||||
"input": true,
|
||||
"keygen": true,
|
||||
"link": true,
|
||||
"meta": true,
|
||||
"param": true,
|
||||
"source": true,
|
||||
"track": true,
|
||||
"wbr": true,
|
||||
}
|
||||
1219
vendor/golang.org/x/net/html/token.go
generated
vendored
Normal file
1219
vendor/golang.org/x/net/html/token.go
generated
vendored
Normal file
File diff suppressed because it is too large
Load diff
38
vendor/golang.org/x/oauth2/google/appengine.go
generated
vendored
Normal file
38
vendor/golang.org/x/oauth2/google/appengine.go
generated
vendored
Normal file
|
|
@ -0,0 +1,38 @@
|
|||
// 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 google
|
||||
|
||||
import (
|
||||
"context"
|
||||
"time"
|
||||
|
||||
"golang.org/x/oauth2"
|
||||
)
|
||||
|
||||
// Set at init time by appengine_gen1.go. If nil, we're not on App Engine standard first generation (<= Go 1.9) or App Engine flexible.
|
||||
var appengineTokenFunc func(c context.Context, scopes ...string) (token string, expiry time.Time, err error)
|
||||
|
||||
// Set at init time by appengine_gen1.go. If nil, we're not on App Engine standard first generation (<= Go 1.9) or App Engine flexible.
|
||||
var appengineAppIDFunc func(c context.Context) string
|
||||
|
||||
// AppEngineTokenSource returns a token source that fetches tokens from either
|
||||
// the current application's service account or from the metadata server,
|
||||
// depending on the App Engine environment. See below for environment-specific
|
||||
// details. If you are implementing a 3-legged OAuth 2.0 flow on App Engine that
|
||||
// involves user accounts, see oauth2.Config instead.
|
||||
//
|
||||
// First generation App Engine runtimes (<= Go 1.9):
|
||||
// AppEngineTokenSource returns a token source that fetches tokens issued to the
|
||||
// current App Engine application's service account. The provided context must have
|
||||
// come from appengine.NewContext.
|
||||
//
|
||||
// Second generation App Engine runtimes (>= Go 1.11) and App Engine flexible:
|
||||
// AppEngineTokenSource is DEPRECATED on second generation runtimes and on the
|
||||
// flexible environment. It delegates to ComputeTokenSource, and the provided
|
||||
// context and scopes are not used. Please use DefaultTokenSource (or ComputeTokenSource,
|
||||
// which DefaultTokenSource will use in this case) instead.
|
||||
func AppEngineTokenSource(ctx context.Context, scope ...string) oauth2.TokenSource {
|
||||
return appEngineTokenSource(ctx, scope...)
|
||||
}
|
||||
77
vendor/golang.org/x/oauth2/google/appengine_gen1.go
generated
vendored
Normal file
77
vendor/golang.org/x/oauth2/google/appengine_gen1.go
generated
vendored
Normal file
|
|
@ -0,0 +1,77 @@
|
|||
// Copyright 2018 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build appengine
|
||||
|
||||
// This file applies to App Engine first generation runtimes (<= Go 1.9).
|
||||
|
||||
package google
|
||||
|
||||
import (
|
||||
"context"
|
||||
"sort"
|
||||
"strings"
|
||||
"sync"
|
||||
|
||||
"golang.org/x/oauth2"
|
||||
"google.golang.org/appengine"
|
||||
)
|
||||
|
||||
func init() {
|
||||
appengineTokenFunc = appengine.AccessToken
|
||||
appengineAppIDFunc = appengine.AppID
|
||||
}
|
||||
|
||||
// See comment on AppEngineTokenSource in appengine.go.
|
||||
func appEngineTokenSource(ctx context.Context, scope ...string) oauth2.TokenSource {
|
||||
scopes := append([]string{}, scope...)
|
||||
sort.Strings(scopes)
|
||||
return &gaeTokenSource{
|
||||
ctx: ctx,
|
||||
scopes: scopes,
|
||||
key: strings.Join(scopes, " "),
|
||||
}
|
||||
}
|
||||
|
||||
// aeTokens helps the fetched tokens to be reused until their expiration.
|
||||
var (
|
||||
aeTokensMu sync.Mutex
|
||||
aeTokens = make(map[string]*tokenLock) // key is space-separated scopes
|
||||
)
|
||||
|
||||
type tokenLock struct {
|
||||
mu sync.Mutex // guards t; held while fetching or updating t
|
||||
t *oauth2.Token
|
||||
}
|
||||
|
||||
type gaeTokenSource struct {
|
||||
ctx context.Context
|
||||
scopes []string
|
||||
key string // to aeTokens map; space-separated scopes
|
||||
}
|
||||
|
||||
func (ts *gaeTokenSource) Token() (*oauth2.Token, error) {
|
||||
aeTokensMu.Lock()
|
||||
tok, ok := aeTokens[ts.key]
|
||||
if !ok {
|
||||
tok = &tokenLock{}
|
||||
aeTokens[ts.key] = tok
|
||||
}
|
||||
aeTokensMu.Unlock()
|
||||
|
||||
tok.mu.Lock()
|
||||
defer tok.mu.Unlock()
|
||||
if tok.t.Valid() {
|
||||
return tok.t, nil
|
||||
}
|
||||
access, exp, err := appengineTokenFunc(ts.ctx, ts.scopes...)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
tok.t = &oauth2.Token{
|
||||
AccessToken: access,
|
||||
Expiry: exp,
|
||||
}
|
||||
return tok.t, nil
|
||||
}
|
||||
27
vendor/golang.org/x/oauth2/google/appengine_gen2_flex.go
generated
vendored
Normal file
27
vendor/golang.org/x/oauth2/google/appengine_gen2_flex.go
generated
vendored
Normal file
|
|
@ -0,0 +1,27 @@
|
|||
// Copyright 2018 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build !appengine
|
||||
|
||||
// This file applies to App Engine second generation runtimes (>= Go 1.11) and App Engine flexible.
|
||||
|
||||
package google
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log"
|
||||
"sync"
|
||||
|
||||
"golang.org/x/oauth2"
|
||||
)
|
||||
|
||||
var logOnce sync.Once // only spam about deprecation once
|
||||
|
||||
// See comment on AppEngineTokenSource in appengine.go.
|
||||
func appEngineTokenSource(ctx context.Context, scope ...string) oauth2.TokenSource {
|
||||
logOnce.Do(func() {
|
||||
log.Print("google: AppEngineTokenSource is deprecated on App Engine standard second generation runtimes (>= Go 1.11) and App Engine flexible. Please use DefaultTokenSource or ComputeTokenSource.")
|
||||
})
|
||||
return ComputeTokenSource("")
|
||||
}
|
||||
154
vendor/golang.org/x/oauth2/google/default.go
generated
vendored
Normal file
154
vendor/golang.org/x/oauth2/google/default.go
generated
vendored
Normal file
|
|
@ -0,0 +1,154 @@
|
|||
// 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 google
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"io/ioutil"
|
||||
"net/http"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
|
||||
"cloud.google.com/go/compute/metadata"
|
||||
"golang.org/x/oauth2"
|
||||
)
|
||||
|
||||
// Credentials holds Google credentials, including "Application Default Credentials".
|
||||
// For more details, see:
|
||||
// https://developers.google.com/accounts/docs/application-default-credentials
|
||||
type Credentials struct {
|
||||
ProjectID string // may be empty
|
||||
TokenSource oauth2.TokenSource
|
||||
|
||||
// JSON contains the raw bytes from a JSON credentials file.
|
||||
// This field may be nil if authentication is provided by the
|
||||
// environment and not with a credentials file, e.g. when code is
|
||||
// running on Google Cloud Platform.
|
||||
JSON []byte
|
||||
}
|
||||
|
||||
// DefaultCredentials is the old name of Credentials.
|
||||
//
|
||||
// Deprecated: use Credentials instead.
|
||||
type DefaultCredentials = Credentials
|
||||
|
||||
// DefaultClient returns an HTTP Client that uses the
|
||||
// DefaultTokenSource to obtain authentication credentials.
|
||||
func DefaultClient(ctx context.Context, scope ...string) (*http.Client, error) {
|
||||
ts, err := DefaultTokenSource(ctx, scope...)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return oauth2.NewClient(ctx, ts), nil
|
||||
}
|
||||
|
||||
// DefaultTokenSource returns the token source for
|
||||
// "Application Default Credentials".
|
||||
// It is a shortcut for FindDefaultCredentials(ctx, scope).TokenSource.
|
||||
func DefaultTokenSource(ctx context.Context, scope ...string) (oauth2.TokenSource, error) {
|
||||
creds, err := FindDefaultCredentials(ctx, scope...)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return creds.TokenSource, nil
|
||||
}
|
||||
|
||||
// FindDefaultCredentials searches for "Application Default Credentials".
|
||||
//
|
||||
// It looks for credentials in the following places,
|
||||
// preferring the first location found:
|
||||
//
|
||||
// 1. A JSON file whose path is specified by the
|
||||
// GOOGLE_APPLICATION_CREDENTIALS environment variable.
|
||||
// 2. A JSON file in a location known to the gcloud command-line tool.
|
||||
// On Windows, this is %APPDATA%/gcloud/application_default_credentials.json.
|
||||
// On other systems, $HOME/.config/gcloud/application_default_credentials.json.
|
||||
// 3. On Google App Engine standard first generation runtimes (<= Go 1.9) it uses
|
||||
// the appengine.AccessToken function.
|
||||
// 4. On Google Compute Engine, Google App Engine standard second generation runtimes
|
||||
// (>= Go 1.11), and Google App Engine flexible environment, it fetches
|
||||
// credentials from the metadata server.
|
||||
func FindDefaultCredentials(ctx context.Context, scopes ...string) (*Credentials, error) {
|
||||
// First, try the environment variable.
|
||||
const envVar = "GOOGLE_APPLICATION_CREDENTIALS"
|
||||
if filename := os.Getenv(envVar); filename != "" {
|
||||
creds, err := readCredentialsFile(ctx, filename, scopes)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("google: error getting credentials using %v environment variable: %v", envVar, err)
|
||||
}
|
||||
return creds, nil
|
||||
}
|
||||
|
||||
// Second, try a well-known file.
|
||||
filename := wellKnownFile()
|
||||
if creds, err := readCredentialsFile(ctx, filename, scopes); err == nil {
|
||||
return creds, nil
|
||||
} else if !os.IsNotExist(err) {
|
||||
return nil, fmt.Errorf("google: error getting credentials using well-known file (%v): %v", filename, err)
|
||||
}
|
||||
|
||||
// Third, if we're on a Google App Engine standard first generation runtime (<= Go 1.9)
|
||||
// use those credentials. App Engine standard second generation runtimes (>= Go 1.11)
|
||||
// and App Engine flexible use ComputeTokenSource and the metadata server.
|
||||
if appengineTokenFunc != nil {
|
||||
return &DefaultCredentials{
|
||||
ProjectID: appengineAppIDFunc(ctx),
|
||||
TokenSource: AppEngineTokenSource(ctx, scopes...),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Fourth, if we're on Google Compute Engine, an App Engine standard second generation runtime,
|
||||
// or App Engine flexible, use the metadata server.
|
||||
if metadata.OnGCE() {
|
||||
id, _ := metadata.ProjectID()
|
||||
return &DefaultCredentials{
|
||||
ProjectID: id,
|
||||
TokenSource: ComputeTokenSource("", scopes...),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// None are found; return helpful error.
|
||||
const url = "https://developers.google.com/accounts/docs/application-default-credentials"
|
||||
return nil, fmt.Errorf("google: could not find default credentials. See %v for more information.", url)
|
||||
}
|
||||
|
||||
// CredentialsFromJSON obtains Google credentials from a JSON value. The JSON can
|
||||
// represent either a Google Developers Console client_credentials.json file (as in
|
||||
// ConfigFromJSON) or a Google Developers service account key file (as in
|
||||
// JWTConfigFromJSON).
|
||||
func CredentialsFromJSON(ctx context.Context, jsonData []byte, scopes ...string) (*Credentials, error) {
|
||||
var f credentialsFile
|
||||
if err := json.Unmarshal(jsonData, &f); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
ts, err := f.tokenSource(ctx, append([]string(nil), scopes...))
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &DefaultCredentials{
|
||||
ProjectID: f.ProjectID,
|
||||
TokenSource: ts,
|
||||
JSON: jsonData,
|
||||
}, nil
|
||||
}
|
||||
|
||||
func wellKnownFile() string {
|
||||
const f = "application_default_credentials.json"
|
||||
if runtime.GOOS == "windows" {
|
||||
return filepath.Join(os.Getenv("APPDATA"), "gcloud", f)
|
||||
}
|
||||
return filepath.Join(guessUnixHomeDir(), ".config", "gcloud", f)
|
||||
}
|
||||
|
||||
func readCredentialsFile(ctx context.Context, filename string, scopes []string) (*DefaultCredentials, error) {
|
||||
b, err := ioutil.ReadFile(filename)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return CredentialsFromJSON(ctx, b, scopes...)
|
||||
}
|
||||
40
vendor/golang.org/x/oauth2/google/doc.go
generated
vendored
Normal file
40
vendor/golang.org/x/oauth2/google/doc.go
generated
vendored
Normal file
|
|
@ -0,0 +1,40 @@
|
|||
// Copyright 2018 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// Package google provides support for making OAuth2 authorized and authenticated
|
||||
// HTTP requests to Google APIs. It supports the Web server flow, client-side
|
||||
// credentials, service accounts, Google Compute Engine service accounts, and Google
|
||||
// App Engine service accounts.
|
||||
//
|
||||
// A brief overview of the package follows. For more information, please read
|
||||
// https://developers.google.com/accounts/docs/OAuth2
|
||||
// and
|
||||
// https://developers.google.com/accounts/docs/application-default-credentials.
|
||||
//
|
||||
// OAuth2 Configs
|
||||
//
|
||||
// Two functions in this package return golang.org/x/oauth2.Config values from Google credential
|
||||
// data. Google supports two JSON formats for OAuth2 credentials: one is handled by ConfigFromJSON,
|
||||
// the other by JWTConfigFromJSON. The returned Config can be used to obtain a TokenSource or
|
||||
// create an http.Client.
|
||||
//
|
||||
//
|
||||
// Credentials
|
||||
//
|
||||
// The Credentials type represents Google credentials, including Application Default
|
||||
// Credentials.
|
||||
//
|
||||
// Use FindDefaultCredentials to obtain Application Default Credentials.
|
||||
// FindDefaultCredentials looks in some well-known places for a credentials file, and
|
||||
// will call AppEngineTokenSource or ComputeTokenSource as needed.
|
||||
//
|
||||
// DefaultClient and DefaultTokenSource are convenience methods. They first call FindDefaultCredentials,
|
||||
// then use the credentials to construct an http.Client or an oauth2.TokenSource.
|
||||
//
|
||||
// Use CredentialsFromJSON to obtain credentials from either of the two JSON formats
|
||||
// described in OAuth2 Configs, above. The TokenSource in the returned value is the
|
||||
// same as the one obtained from the oauth2.Config returned from ConfigFromJSON or
|
||||
// JWTConfigFromJSON, but the Credentials may contain additional information
|
||||
// that is useful is some circumstances.
|
||||
package google // import "golang.org/x/oauth2/google"
|
||||
209
vendor/golang.org/x/oauth2/google/google.go
generated
vendored
Normal file
209
vendor/golang.org/x/oauth2/google/google.go
generated
vendored
Normal file
|
|
@ -0,0 +1,209 @@
|
|||
// 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 google
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"net/url"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"cloud.google.com/go/compute/metadata"
|
||||
"golang.org/x/oauth2"
|
||||
"golang.org/x/oauth2/jwt"
|
||||
)
|
||||
|
||||
// Endpoint is Google's OAuth 2.0 endpoint.
|
||||
var Endpoint = oauth2.Endpoint{
|
||||
AuthURL: "https://accounts.google.com/o/oauth2/auth",
|
||||
TokenURL: "https://oauth2.googleapis.com/token",
|
||||
AuthStyle: oauth2.AuthStyleInParams,
|
||||
}
|
||||
|
||||
// JWTTokenURL is Google's OAuth 2.0 token URL to use with the JWT flow.
|
||||
const JWTTokenURL = "https://oauth2.googleapis.com/token"
|
||||
|
||||
// ConfigFromJSON uses a Google Developers Console client_credentials.json
|
||||
// file to construct a config.
|
||||
// client_credentials.json can be downloaded from
|
||||
// https://console.developers.google.com, under "Credentials". Download the Web
|
||||
// application credentials in the JSON format and provide the contents of the
|
||||
// file as jsonKey.
|
||||
func ConfigFromJSON(jsonKey []byte, scope ...string) (*oauth2.Config, error) {
|
||||
type cred struct {
|
||||
ClientID string `json:"client_id"`
|
||||
ClientSecret string `json:"client_secret"`
|
||||
RedirectURIs []string `json:"redirect_uris"`
|
||||
AuthURI string `json:"auth_uri"`
|
||||
TokenURI string `json:"token_uri"`
|
||||
}
|
||||
var j struct {
|
||||
Web *cred `json:"web"`
|
||||
Installed *cred `json:"installed"`
|
||||
}
|
||||
if err := json.Unmarshal(jsonKey, &j); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
var c *cred
|
||||
switch {
|
||||
case j.Web != nil:
|
||||
c = j.Web
|
||||
case j.Installed != nil:
|
||||
c = j.Installed
|
||||
default:
|
||||
return nil, fmt.Errorf("oauth2/google: no credentials found")
|
||||
}
|
||||
if len(c.RedirectURIs) < 1 {
|
||||
return nil, errors.New("oauth2/google: missing redirect URL in the client_credentials.json")
|
||||
}
|
||||
return &oauth2.Config{
|
||||
ClientID: c.ClientID,
|
||||
ClientSecret: c.ClientSecret,
|
||||
RedirectURL: c.RedirectURIs[0],
|
||||
Scopes: scope,
|
||||
Endpoint: oauth2.Endpoint{
|
||||
AuthURL: c.AuthURI,
|
||||
TokenURL: c.TokenURI,
|
||||
},
|
||||
}, nil
|
||||
}
|
||||
|
||||
// JWTConfigFromJSON uses a Google Developers service account JSON key file to read
|
||||
// the credentials that authorize and authenticate the requests.
|
||||
// Create a service account on "Credentials" for your project at
|
||||
// https://console.developers.google.com to download a JSON key file.
|
||||
func JWTConfigFromJSON(jsonKey []byte, scope ...string) (*jwt.Config, error) {
|
||||
var f credentialsFile
|
||||
if err := json.Unmarshal(jsonKey, &f); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if f.Type != serviceAccountKey {
|
||||
return nil, fmt.Errorf("google: read JWT from JSON credentials: 'type' field is %q (expected %q)", f.Type, serviceAccountKey)
|
||||
}
|
||||
scope = append([]string(nil), scope...) // copy
|
||||
return f.jwtConfig(scope), nil
|
||||
}
|
||||
|
||||
// JSON key file types.
|
||||
const (
|
||||
serviceAccountKey = "service_account"
|
||||
userCredentialsKey = "authorized_user"
|
||||
)
|
||||
|
||||
// credentialsFile is the unmarshalled representation of a credentials file.
|
||||
type credentialsFile struct {
|
||||
Type string `json:"type"` // serviceAccountKey or userCredentialsKey
|
||||
|
||||
// Service Account fields
|
||||
ClientEmail string `json:"client_email"`
|
||||
PrivateKeyID string `json:"private_key_id"`
|
||||
PrivateKey string `json:"private_key"`
|
||||
TokenURL string `json:"token_uri"`
|
||||
ProjectID string `json:"project_id"`
|
||||
|
||||
// User Credential fields
|
||||
// (These typically come from gcloud auth.)
|
||||
ClientSecret string `json:"client_secret"`
|
||||
ClientID string `json:"client_id"`
|
||||
RefreshToken string `json:"refresh_token"`
|
||||
}
|
||||
|
||||
func (f *credentialsFile) jwtConfig(scopes []string) *jwt.Config {
|
||||
cfg := &jwt.Config{
|
||||
Email: f.ClientEmail,
|
||||
PrivateKey: []byte(f.PrivateKey),
|
||||
PrivateKeyID: f.PrivateKeyID,
|
||||
Scopes: scopes,
|
||||
TokenURL: f.TokenURL,
|
||||
}
|
||||
if cfg.TokenURL == "" {
|
||||
cfg.TokenURL = JWTTokenURL
|
||||
}
|
||||
return cfg
|
||||
}
|
||||
|
||||
func (f *credentialsFile) tokenSource(ctx context.Context, scopes []string) (oauth2.TokenSource, error) {
|
||||
switch f.Type {
|
||||
case serviceAccountKey:
|
||||
cfg := f.jwtConfig(scopes)
|
||||
return cfg.TokenSource(ctx), nil
|
||||
case userCredentialsKey:
|
||||
cfg := &oauth2.Config{
|
||||
ClientID: f.ClientID,
|
||||
ClientSecret: f.ClientSecret,
|
||||
Scopes: scopes,
|
||||
Endpoint: Endpoint,
|
||||
}
|
||||
tok := &oauth2.Token{RefreshToken: f.RefreshToken}
|
||||
return cfg.TokenSource(ctx, tok), nil
|
||||
case "":
|
||||
return nil, errors.New("missing 'type' field in credentials")
|
||||
default:
|
||||
return nil, fmt.Errorf("unknown credential type: %q", f.Type)
|
||||
}
|
||||
}
|
||||
|
||||
// ComputeTokenSource returns a token source that fetches access tokens
|
||||
// from Google Compute Engine (GCE)'s metadata server. It's only valid to use
|
||||
// this token source if your program is running on a GCE instance.
|
||||
// If no account is specified, "default" is used.
|
||||
// If no scopes are specified, a set of default scopes are automatically granted.
|
||||
// Further information about retrieving access tokens from the GCE metadata
|
||||
// server can be found at https://cloud.google.com/compute/docs/authentication.
|
||||
func ComputeTokenSource(account string, scope ...string) oauth2.TokenSource {
|
||||
return oauth2.ReuseTokenSource(nil, computeSource{account: account, scopes: scope})
|
||||
}
|
||||
|
||||
type computeSource struct {
|
||||
account string
|
||||
scopes []string
|
||||
}
|
||||
|
||||
func (cs computeSource) Token() (*oauth2.Token, error) {
|
||||
if !metadata.OnGCE() {
|
||||
return nil, errors.New("oauth2/google: can't get a token from the metadata service; not running on GCE")
|
||||
}
|
||||
acct := cs.account
|
||||
if acct == "" {
|
||||
acct = "default"
|
||||
}
|
||||
tokenURI := "instance/service-accounts/" + acct + "/token"
|
||||
if len(cs.scopes) > 0 {
|
||||
v := url.Values{}
|
||||
v.Set("scopes", strings.Join(cs.scopes, ","))
|
||||
tokenURI = tokenURI + "?" + v.Encode()
|
||||
}
|
||||
tokenJSON, err := metadata.Get(tokenURI)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
var res struct {
|
||||
AccessToken string `json:"access_token"`
|
||||
ExpiresInSec int `json:"expires_in"`
|
||||
TokenType string `json:"token_type"`
|
||||
}
|
||||
err = json.NewDecoder(strings.NewReader(tokenJSON)).Decode(&res)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("oauth2/google: invalid token JSON from metadata: %v", err)
|
||||
}
|
||||
if res.ExpiresInSec == 0 || res.AccessToken == "" {
|
||||
return nil, fmt.Errorf("oauth2/google: incomplete token received from metadata")
|
||||
}
|
||||
tok := &oauth2.Token{
|
||||
AccessToken: res.AccessToken,
|
||||
TokenType: res.TokenType,
|
||||
Expiry: time.Now().Add(time.Duration(res.ExpiresInSec) * time.Second),
|
||||
}
|
||||
// NOTE(cbro): add hidden metadata about where the token is from.
|
||||
// This is needed for detection by client libraries to know that credentials come from the metadata server.
|
||||
// This may be removed in a future version of this library.
|
||||
return tok.WithExtra(map[string]interface{}{
|
||||
"oauth2.google.tokenSource": "compute-metadata",
|
||||
"oauth2.google.serviceAccount": acct,
|
||||
}), nil
|
||||
}
|
||||
74
vendor/golang.org/x/oauth2/google/jwt.go
generated
vendored
Normal file
74
vendor/golang.org/x/oauth2/google/jwt.go
generated
vendored
Normal file
|
|
@ -0,0 +1,74 @@
|
|||
// 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 google
|
||||
|
||||
import (
|
||||
"crypto/rsa"
|
||||
"fmt"
|
||||
"time"
|
||||
|
||||
"golang.org/x/oauth2"
|
||||
"golang.org/x/oauth2/internal"
|
||||
"golang.org/x/oauth2/jws"
|
||||
)
|
||||
|
||||
// JWTAccessTokenSourceFromJSON uses a Google Developers service account JSON
|
||||
// key file to read the credentials that authorize and authenticate the
|
||||
// requests, and returns a TokenSource that does not use any OAuth2 flow but
|
||||
// instead creates a JWT and sends that as the access token.
|
||||
// The audience is typically a URL that specifies the scope of the credentials.
|
||||
//
|
||||
// Note that this is not a standard OAuth flow, but rather an
|
||||
// optimization supported by a few Google services.
|
||||
// Unless you know otherwise, you should use JWTConfigFromJSON instead.
|
||||
func JWTAccessTokenSourceFromJSON(jsonKey []byte, audience string) (oauth2.TokenSource, error) {
|
||||
cfg, err := JWTConfigFromJSON(jsonKey)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("google: could not parse JSON key: %v", err)
|
||||
}
|
||||
pk, err := internal.ParseKey(cfg.PrivateKey)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("google: could not parse key: %v", err)
|
||||
}
|
||||
ts := &jwtAccessTokenSource{
|
||||
email: cfg.Email,
|
||||
audience: audience,
|
||||
pk: pk,
|
||||
pkID: cfg.PrivateKeyID,
|
||||
}
|
||||
tok, err := ts.Token()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return oauth2.ReuseTokenSource(tok, ts), nil
|
||||
}
|
||||
|
||||
type jwtAccessTokenSource struct {
|
||||
email, audience string
|
||||
pk *rsa.PrivateKey
|
||||
pkID string
|
||||
}
|
||||
|
||||
func (ts *jwtAccessTokenSource) Token() (*oauth2.Token, error) {
|
||||
iat := time.Now()
|
||||
exp := iat.Add(time.Hour)
|
||||
cs := &jws.ClaimSet{
|
||||
Iss: ts.email,
|
||||
Sub: ts.email,
|
||||
Aud: ts.audience,
|
||||
Iat: iat.Unix(),
|
||||
Exp: exp.Unix(),
|
||||
}
|
||||
hdr := &jws.Header{
|
||||
Algorithm: "RS256",
|
||||
Typ: "JWT",
|
||||
KeyID: string(ts.pkID),
|
||||
}
|
||||
msg, err := jws.Encode(hdr, cs, ts.pk)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("google: could not encode JWT: %v", err)
|
||||
}
|
||||
return &oauth2.Token{AccessToken: msg, TokenType: "Bearer", Expiry: exp}, nil
|
||||
}
|
||||
201
vendor/golang.org/x/oauth2/google/sdk.go
generated
vendored
Normal file
201
vendor/golang.org/x/oauth2/google/sdk.go
generated
vendored
Normal file
|
|
@ -0,0 +1,201 @@
|
|||
// 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 google
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"net/http"
|
||||
"os"
|
||||
"os/user"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"golang.org/x/oauth2"
|
||||
)
|
||||
|
||||
type sdkCredentials struct {
|
||||
Data []struct {
|
||||
Credential struct {
|
||||
ClientID string `json:"client_id"`
|
||||
ClientSecret string `json:"client_secret"`
|
||||
AccessToken string `json:"access_token"`
|
||||
RefreshToken string `json:"refresh_token"`
|
||||
TokenExpiry *time.Time `json:"token_expiry"`
|
||||
} `json:"credential"`
|
||||
Key struct {
|
||||
Account string `json:"account"`
|
||||
Scope string `json:"scope"`
|
||||
} `json:"key"`
|
||||
}
|
||||
}
|
||||
|
||||
// An SDKConfig provides access to tokens from an account already
|
||||
// authorized via the Google Cloud SDK.
|
||||
type SDKConfig struct {
|
||||
conf oauth2.Config
|
||||
initialToken *oauth2.Token
|
||||
}
|
||||
|
||||
// NewSDKConfig creates an SDKConfig for the given Google Cloud SDK
|
||||
// account. If account is empty, the account currently active in
|
||||
// Google Cloud SDK properties is used.
|
||||
// Google Cloud SDK credentials must be created by running `gcloud auth`
|
||||
// before using this function.
|
||||
// The Google Cloud SDK is available at https://cloud.google.com/sdk/.
|
||||
func NewSDKConfig(account string) (*SDKConfig, error) {
|
||||
configPath, err := sdkConfigPath()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("oauth2/google: error getting SDK config path: %v", err)
|
||||
}
|
||||
credentialsPath := filepath.Join(configPath, "credentials")
|
||||
f, err := os.Open(credentialsPath)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("oauth2/google: failed to load SDK credentials: %v", err)
|
||||
}
|
||||
defer f.Close()
|
||||
|
||||
var c sdkCredentials
|
||||
if err := json.NewDecoder(f).Decode(&c); err != nil {
|
||||
return nil, fmt.Errorf("oauth2/google: failed to decode SDK credentials from %q: %v", credentialsPath, err)
|
||||
}
|
||||
if len(c.Data) == 0 {
|
||||
return nil, fmt.Errorf("oauth2/google: no credentials found in %q, run `gcloud auth login` to create one", credentialsPath)
|
||||
}
|
||||
if account == "" {
|
||||
propertiesPath := filepath.Join(configPath, "properties")
|
||||
f, err := os.Open(propertiesPath)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("oauth2/google: failed to load SDK properties: %v", err)
|
||||
}
|
||||
defer f.Close()
|
||||
ini, err := parseINI(f)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("oauth2/google: failed to parse SDK properties %q: %v", propertiesPath, err)
|
||||
}
|
||||
core, ok := ini["core"]
|
||||
if !ok {
|
||||
return nil, fmt.Errorf("oauth2/google: failed to find [core] section in %v", ini)
|
||||
}
|
||||
active, ok := core["account"]
|
||||
if !ok {
|
||||
return nil, fmt.Errorf("oauth2/google: failed to find %q attribute in %v", "account", core)
|
||||
}
|
||||
account = active
|
||||
}
|
||||
|
||||
for _, d := range c.Data {
|
||||
if account == "" || d.Key.Account == account {
|
||||
if d.Credential.AccessToken == "" && d.Credential.RefreshToken == "" {
|
||||
return nil, fmt.Errorf("oauth2/google: no token available for account %q", account)
|
||||
}
|
||||
var expiry time.Time
|
||||
if d.Credential.TokenExpiry != nil {
|
||||
expiry = *d.Credential.TokenExpiry
|
||||
}
|
||||
return &SDKConfig{
|
||||
conf: oauth2.Config{
|
||||
ClientID: d.Credential.ClientID,
|
||||
ClientSecret: d.Credential.ClientSecret,
|
||||
Scopes: strings.Split(d.Key.Scope, " "),
|
||||
Endpoint: Endpoint,
|
||||
RedirectURL: "oob",
|
||||
},
|
||||
initialToken: &oauth2.Token{
|
||||
AccessToken: d.Credential.AccessToken,
|
||||
RefreshToken: d.Credential.RefreshToken,
|
||||
Expiry: expiry,
|
||||
},
|
||||
}, nil
|
||||
}
|
||||
}
|
||||
return nil, fmt.Errorf("oauth2/google: no such credentials for account %q", account)
|
||||
}
|
||||
|
||||
// Client returns an HTTP client using Google Cloud SDK credentials to
|
||||
// authorize requests. The token will auto-refresh as necessary. The
|
||||
// underlying http.RoundTripper will be obtained using the provided
|
||||
// context. The returned client and its Transport should not be
|
||||
// modified.
|
||||
func (c *SDKConfig) Client(ctx context.Context) *http.Client {
|
||||
return &http.Client{
|
||||
Transport: &oauth2.Transport{
|
||||
Source: c.TokenSource(ctx),
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
// TokenSource returns an oauth2.TokenSource that retrieve tokens from
|
||||
// Google Cloud SDK credentials using the provided context.
|
||||
// It will returns the current access token stored in the credentials,
|
||||
// and refresh it when it expires, but it won't update the credentials
|
||||
// with the new access token.
|
||||
func (c *SDKConfig) TokenSource(ctx context.Context) oauth2.TokenSource {
|
||||
return c.conf.TokenSource(ctx, c.initialToken)
|
||||
}
|
||||
|
||||
// Scopes are the OAuth 2.0 scopes the current account is authorized for.
|
||||
func (c *SDKConfig) Scopes() []string {
|
||||
return c.conf.Scopes
|
||||
}
|
||||
|
||||
func parseINI(ini io.Reader) (map[string]map[string]string, error) {
|
||||
result := map[string]map[string]string{
|
||||
"": {}, // root section
|
||||
}
|
||||
scanner := bufio.NewScanner(ini)
|
||||
currentSection := ""
|
||||
for scanner.Scan() {
|
||||
line := strings.TrimSpace(scanner.Text())
|
||||
if strings.HasPrefix(line, ";") {
|
||||
// comment.
|
||||
continue
|
||||
}
|
||||
if strings.HasPrefix(line, "[") && strings.HasSuffix(line, "]") {
|
||||
currentSection = strings.TrimSpace(line[1 : len(line)-1])
|
||||
result[currentSection] = map[string]string{}
|
||||
continue
|
||||
}
|
||||
parts := strings.SplitN(line, "=", 2)
|
||||
if len(parts) == 2 && parts[0] != "" {
|
||||
result[currentSection][strings.TrimSpace(parts[0])] = strings.TrimSpace(parts[1])
|
||||
}
|
||||
}
|
||||
if err := scanner.Err(); err != nil {
|
||||
return nil, fmt.Errorf("error scanning ini: %v", err)
|
||||
}
|
||||
return result, nil
|
||||
}
|
||||
|
||||
// sdkConfigPath tries to guess where the gcloud config is located.
|
||||
// It can be overridden during tests.
|
||||
var sdkConfigPath = func() (string, error) {
|
||||
if runtime.GOOS == "windows" {
|
||||
return filepath.Join(os.Getenv("APPDATA"), "gcloud"), nil
|
||||
}
|
||||
homeDir := guessUnixHomeDir()
|
||||
if homeDir == "" {
|
||||
return "", errors.New("unable to get current user home directory: os/user lookup failed; $HOME is empty")
|
||||
}
|
||||
return filepath.Join(homeDir, ".config", "gcloud"), nil
|
||||
}
|
||||
|
||||
func guessUnixHomeDir() string {
|
||||
// Prefer $HOME over user.Current due to glibc bug: golang.org/issue/13470
|
||||
if v := os.Getenv("HOME"); v != "" {
|
||||
return v
|
||||
}
|
||||
// Else, fall back to user.Current:
|
||||
if u, err := user.Current(); err == nil {
|
||||
return u.HomeDir
|
||||
}
|
||||
return ""
|
||||
}
|
||||
182
vendor/golang.org/x/oauth2/jws/jws.go
generated
vendored
Normal file
182
vendor/golang.org/x/oauth2/jws/jws.go
generated
vendored
Normal file
|
|
@ -0,0 +1,182 @@
|
|||
// 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 jws provides a partial implementation
|
||||
// of JSON Web Signature encoding and decoding.
|
||||
// It exists to support the golang.org/x/oauth2 package.
|
||||
//
|
||||
// See RFC 7515.
|
||||
//
|
||||
// Deprecated: this package is not intended for public use and might be
|
||||
// removed in the future. It exists for internal use only.
|
||||
// Please switch to another JWS package or copy this package into your own
|
||||
// source tree.
|
||||
package jws // import "golang.org/x/oauth2/jws"
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"crypto"
|
||||
"crypto/rand"
|
||||
"crypto/rsa"
|
||||
"crypto/sha256"
|
||||
"encoding/base64"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
|
||||
// ClaimSet contains information about the JWT signature including the
|
||||
// permissions being requested (scopes), the target of the token, the issuer,
|
||||
// the time the token was issued, and the lifetime of the token.
|
||||
type ClaimSet struct {
|
||||
Iss string `json:"iss"` // email address of the client_id of the application making the access token request
|
||||
Scope string `json:"scope,omitempty"` // space-delimited list of the permissions the application requests
|
||||
Aud string `json:"aud"` // descriptor of the intended target of the assertion (Optional).
|
||||
Exp int64 `json:"exp"` // the expiration time of the assertion (seconds since Unix epoch)
|
||||
Iat int64 `json:"iat"` // the time the assertion was issued (seconds since Unix epoch)
|
||||
Typ string `json:"typ,omitempty"` // token type (Optional).
|
||||
|
||||
// Email for which the application is requesting delegated access (Optional).
|
||||
Sub string `json:"sub,omitempty"`
|
||||
|
||||
// The old name of Sub. Client keeps setting Prn to be
|
||||
// complaint with legacy OAuth 2.0 providers. (Optional)
|
||||
Prn string `json:"prn,omitempty"`
|
||||
|
||||
// See http://tools.ietf.org/html/draft-jones-json-web-token-10#section-4.3
|
||||
// This array is marshalled using custom code (see (c *ClaimSet) encode()).
|
||||
PrivateClaims map[string]interface{} `json:"-"`
|
||||
}
|
||||
|
||||
func (c *ClaimSet) encode() (string, error) {
|
||||
// Reverting time back for machines whose time is not perfectly in sync.
|
||||
// If client machine's time is in the future according
|
||||
// to Google servers, an access token will not be issued.
|
||||
now := time.Now().Add(-10 * time.Second)
|
||||
if c.Iat == 0 {
|
||||
c.Iat = now.Unix()
|
||||
}
|
||||
if c.Exp == 0 {
|
||||
c.Exp = now.Add(time.Hour).Unix()
|
||||
}
|
||||
if c.Exp < c.Iat {
|
||||
return "", fmt.Errorf("jws: invalid Exp = %v; must be later than Iat = %v", c.Exp, c.Iat)
|
||||
}
|
||||
|
||||
b, err := json.Marshal(c)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
|
||||
if len(c.PrivateClaims) == 0 {
|
||||
return base64.RawURLEncoding.EncodeToString(b), nil
|
||||
}
|
||||
|
||||
// Marshal private claim set and then append it to b.
|
||||
prv, err := json.Marshal(c.PrivateClaims)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("jws: invalid map of private claims %v", c.PrivateClaims)
|
||||
}
|
||||
|
||||
// Concatenate public and private claim JSON objects.
|
||||
if !bytes.HasSuffix(b, []byte{'}'}) {
|
||||
return "", fmt.Errorf("jws: invalid JSON %s", b)
|
||||
}
|
||||
if !bytes.HasPrefix(prv, []byte{'{'}) {
|
||||
return "", fmt.Errorf("jws: invalid JSON %s", prv)
|
||||
}
|
||||
b[len(b)-1] = ',' // Replace closing curly brace with a comma.
|
||||
b = append(b, prv[1:]...) // Append private claims.
|
||||
return base64.RawURLEncoding.EncodeToString(b), nil
|
||||
}
|
||||
|
||||
// Header represents the header for the signed JWS payloads.
|
||||
type Header struct {
|
||||
// The algorithm used for signature.
|
||||
Algorithm string `json:"alg"`
|
||||
|
||||
// Represents the token type.
|
||||
Typ string `json:"typ"`
|
||||
|
||||
// The optional hint of which key is being used.
|
||||
KeyID string `json:"kid,omitempty"`
|
||||
}
|
||||
|
||||
func (h *Header) encode() (string, error) {
|
||||
b, err := json.Marshal(h)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
return base64.RawURLEncoding.EncodeToString(b), nil
|
||||
}
|
||||
|
||||
// Decode decodes a claim set from a JWS payload.
|
||||
func Decode(payload string) (*ClaimSet, error) {
|
||||
// decode returned id token to get expiry
|
||||
s := strings.Split(payload, ".")
|
||||
if len(s) < 2 {
|
||||
// TODO(jbd): Provide more context about the error.
|
||||
return nil, errors.New("jws: invalid token received")
|
||||
}
|
||||
decoded, err := base64.RawURLEncoding.DecodeString(s[1])
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
c := &ClaimSet{}
|
||||
err = json.NewDecoder(bytes.NewBuffer(decoded)).Decode(c)
|
||||
return c, err
|
||||
}
|
||||
|
||||
// Signer returns a signature for the given data.
|
||||
type Signer func(data []byte) (sig []byte, err error)
|
||||
|
||||
// EncodeWithSigner encodes a header and claim set with the provided signer.
|
||||
func EncodeWithSigner(header *Header, c *ClaimSet, sg Signer) (string, error) {
|
||||
head, err := header.encode()
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
cs, err := c.encode()
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
ss := fmt.Sprintf("%s.%s", head, cs)
|
||||
sig, err := sg([]byte(ss))
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
return fmt.Sprintf("%s.%s", ss, base64.RawURLEncoding.EncodeToString(sig)), nil
|
||||
}
|
||||
|
||||
// Encode encodes a signed JWS with provided header and claim set.
|
||||
// This invokes EncodeWithSigner using crypto/rsa.SignPKCS1v15 with the given RSA private key.
|
||||
func Encode(header *Header, c *ClaimSet, key *rsa.PrivateKey) (string, error) {
|
||||
sg := func(data []byte) (sig []byte, err error) {
|
||||
h := sha256.New()
|
||||
h.Write(data)
|
||||
return rsa.SignPKCS1v15(rand.Reader, key, crypto.SHA256, h.Sum(nil))
|
||||
}
|
||||
return EncodeWithSigner(header, c, sg)
|
||||
}
|
||||
|
||||
// Verify tests whether the provided JWT token's signature was produced by the private key
|
||||
// associated with the supplied public key.
|
||||
func Verify(token string, key *rsa.PublicKey) error {
|
||||
parts := strings.Split(token, ".")
|
||||
if len(parts) != 3 {
|
||||
return errors.New("jws: invalid token received, token must have 3 parts")
|
||||
}
|
||||
|
||||
signedContent := parts[0] + "." + parts[1]
|
||||
signatureString, err := base64.RawURLEncoding.DecodeString(parts[2])
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
h := sha256.New()
|
||||
h.Write([]byte(signedContent))
|
||||
return rsa.VerifyPKCS1v15(key, crypto.SHA256, h.Sum(nil), []byte(signatureString))
|
||||
}
|
||||
185
vendor/golang.org/x/oauth2/jwt/jwt.go
generated
vendored
Normal file
185
vendor/golang.org/x/oauth2/jwt/jwt.go
generated
vendored
Normal file
|
|
@ -0,0 +1,185 @@
|
|||
// 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 jwt implements the OAuth 2.0 JSON Web Token flow, commonly
|
||||
// known as "two-legged OAuth 2.0".
|
||||
//
|
||||
// See: https://tools.ietf.org/html/draft-ietf-oauth-jwt-bearer-12
|
||||
package jwt
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"io"
|
||||
"io/ioutil"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"golang.org/x/oauth2"
|
||||
"golang.org/x/oauth2/internal"
|
||||
"golang.org/x/oauth2/jws"
|
||||
)
|
||||
|
||||
var (
|
||||
defaultGrantType = "urn:ietf:params:oauth:grant-type:jwt-bearer"
|
||||
defaultHeader = &jws.Header{Algorithm: "RS256", Typ: "JWT"}
|
||||
)
|
||||
|
||||
// Config is the configuration for using JWT to fetch tokens,
|
||||
// commonly known as "two-legged OAuth 2.0".
|
||||
type Config struct {
|
||||
// Email is the OAuth client identifier used when communicating with
|
||||
// the configured OAuth provider.
|
||||
Email string
|
||||
|
||||
// PrivateKey contains the contents of an RSA private key or the
|
||||
// contents of a PEM file that contains a private key. The provided
|
||||
// private key is used to sign JWT payloads.
|
||||
// PEM containers with a passphrase are not supported.
|
||||
// Use the following command to convert a PKCS 12 file into a PEM.
|
||||
//
|
||||
// $ openssl pkcs12 -in key.p12 -out key.pem -nodes
|
||||
//
|
||||
PrivateKey []byte
|
||||
|
||||
// PrivateKeyID contains an optional hint indicating which key is being
|
||||
// used.
|
||||
PrivateKeyID string
|
||||
|
||||
// Subject is the optional user to impersonate.
|
||||
Subject string
|
||||
|
||||
// Scopes optionally specifies a list of requested permission scopes.
|
||||
Scopes []string
|
||||
|
||||
// TokenURL is the endpoint required to complete the 2-legged JWT flow.
|
||||
TokenURL string
|
||||
|
||||
// Expires optionally specifies how long the token is valid for.
|
||||
Expires time.Duration
|
||||
|
||||
// Audience optionally specifies the intended audience of the
|
||||
// request. If empty, the value of TokenURL is used as the
|
||||
// intended audience.
|
||||
Audience string
|
||||
|
||||
// PrivateClaims optionally specifies custom private claims in the JWT.
|
||||
// See http://tools.ietf.org/html/draft-jones-json-web-token-10#section-4.3
|
||||
PrivateClaims map[string]interface{}
|
||||
|
||||
// UseIDToken optionally specifies whether ID token should be used instead
|
||||
// of access token when the server returns both.
|
||||
UseIDToken bool
|
||||
}
|
||||
|
||||
// TokenSource returns a JWT TokenSource using the configuration
|
||||
// in c and the HTTP client from the provided context.
|
||||
func (c *Config) TokenSource(ctx context.Context) oauth2.TokenSource {
|
||||
return oauth2.ReuseTokenSource(nil, jwtSource{ctx, c})
|
||||
}
|
||||
|
||||
// Client returns an HTTP client wrapping the context's
|
||||
// HTTP transport and adding Authorization headers with tokens
|
||||
// obtained from c.
|
||||
//
|
||||
// The returned client and its Transport should not be modified.
|
||||
func (c *Config) Client(ctx context.Context) *http.Client {
|
||||
return oauth2.NewClient(ctx, c.TokenSource(ctx))
|
||||
}
|
||||
|
||||
// jwtSource is a source that always does a signed JWT request for a token.
|
||||
// It should typically be wrapped with a reuseTokenSource.
|
||||
type jwtSource struct {
|
||||
ctx context.Context
|
||||
conf *Config
|
||||
}
|
||||
|
||||
func (js jwtSource) Token() (*oauth2.Token, error) {
|
||||
pk, err := internal.ParseKey(js.conf.PrivateKey)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
hc := oauth2.NewClient(js.ctx, nil)
|
||||
claimSet := &jws.ClaimSet{
|
||||
Iss: js.conf.Email,
|
||||
Scope: strings.Join(js.conf.Scopes, " "),
|
||||
Aud: js.conf.TokenURL,
|
||||
PrivateClaims: js.conf.PrivateClaims,
|
||||
}
|
||||
if subject := js.conf.Subject; subject != "" {
|
||||
claimSet.Sub = subject
|
||||
// prn is the old name of sub. Keep setting it
|
||||
// to be compatible with legacy OAuth 2.0 providers.
|
||||
claimSet.Prn = subject
|
||||
}
|
||||
if t := js.conf.Expires; t > 0 {
|
||||
claimSet.Exp = time.Now().Add(t).Unix()
|
||||
}
|
||||
if aud := js.conf.Audience; aud != "" {
|
||||
claimSet.Aud = aud
|
||||
}
|
||||
h := *defaultHeader
|
||||
h.KeyID = js.conf.PrivateKeyID
|
||||
payload, err := jws.Encode(&h, claimSet, pk)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
v := url.Values{}
|
||||
v.Set("grant_type", defaultGrantType)
|
||||
v.Set("assertion", payload)
|
||||
resp, err := hc.PostForm(js.conf.TokenURL, v)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("oauth2: cannot fetch token: %v", err)
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
body, err := ioutil.ReadAll(io.LimitReader(resp.Body, 1<<20))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("oauth2: cannot fetch token: %v", err)
|
||||
}
|
||||
if c := resp.StatusCode; c < 200 || c > 299 {
|
||||
return nil, &oauth2.RetrieveError{
|
||||
Response: resp,
|
||||
Body: body,
|
||||
}
|
||||
}
|
||||
// tokenRes is the JSON response body.
|
||||
var tokenRes struct {
|
||||
AccessToken string `json:"access_token"`
|
||||
TokenType string `json:"token_type"`
|
||||
IDToken string `json:"id_token"`
|
||||
ExpiresIn int64 `json:"expires_in"` // relative seconds from now
|
||||
}
|
||||
if err := json.Unmarshal(body, &tokenRes); err != nil {
|
||||
return nil, fmt.Errorf("oauth2: cannot fetch token: %v", err)
|
||||
}
|
||||
token := &oauth2.Token{
|
||||
AccessToken: tokenRes.AccessToken,
|
||||
TokenType: tokenRes.TokenType,
|
||||
}
|
||||
raw := make(map[string]interface{})
|
||||
json.Unmarshal(body, &raw) // no error checks for optional fields
|
||||
token = token.WithExtra(raw)
|
||||
|
||||
if secs := tokenRes.ExpiresIn; secs > 0 {
|
||||
token.Expiry = time.Now().Add(time.Duration(secs) * time.Second)
|
||||
}
|
||||
if v := tokenRes.IDToken; v != "" {
|
||||
// decode returned id token to get expiry
|
||||
claimSet, err := jws.Decode(v)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("oauth2: error decoding JWT token: %v", err)
|
||||
}
|
||||
token.Expiry = time.Unix(claimSet.Exp, 0)
|
||||
}
|
||||
if js.conf.UseIDToken {
|
||||
if tokenRes.IDToken == "" {
|
||||
return nil, fmt.Errorf("oauth2: response doesn't have JWT token")
|
||||
}
|
||||
token.AccessToken = tokenRes.IDToken
|
||||
}
|
||||
return token, nil
|
||||
}
|
||||
249
vendor/golang.org/x/text/encoding/charmap/charmap.go
generated
vendored
Normal file
249
vendor/golang.org/x/text/encoding/charmap/charmap.go
generated
vendored
Normal file
|
|
@ -0,0 +1,249 @@
|
|||
// 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 maketables.go
|
||||
|
||||
// Package charmap provides simple character encodings such as IBM Code Page 437
|
||||
// and Windows 1252.
|
||||
package charmap // import "golang.org/x/text/encoding/charmap"
|
||||
|
||||
import (
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/text/encoding"
|
||||
"golang.org/x/text/encoding/internal"
|
||||
"golang.org/x/text/encoding/internal/identifier"
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// These encodings vary only in the way clients should interpret them. Their
|
||||
// coded character set is identical and a single implementation can be shared.
|
||||
var (
|
||||
// ISO8859_6E is the ISO 8859-6E encoding.
|
||||
ISO8859_6E encoding.Encoding = &iso8859_6E
|
||||
|
||||
// ISO8859_6I is the ISO 8859-6I encoding.
|
||||
ISO8859_6I encoding.Encoding = &iso8859_6I
|
||||
|
||||
// ISO8859_8E is the ISO 8859-8E encoding.
|
||||
ISO8859_8E encoding.Encoding = &iso8859_8E
|
||||
|
||||
// ISO8859_8I is the ISO 8859-8I encoding.
|
||||
ISO8859_8I encoding.Encoding = &iso8859_8I
|
||||
|
||||
iso8859_6E = internal.Encoding{
|
||||
Encoding: ISO8859_6,
|
||||
Name: "ISO-8859-6E",
|
||||
MIB: identifier.ISO88596E,
|
||||
}
|
||||
|
||||
iso8859_6I = internal.Encoding{
|
||||
Encoding: ISO8859_6,
|
||||
Name: "ISO-8859-6I",
|
||||
MIB: identifier.ISO88596I,
|
||||
}
|
||||
|
||||
iso8859_8E = internal.Encoding{
|
||||
Encoding: ISO8859_8,
|
||||
Name: "ISO-8859-8E",
|
||||
MIB: identifier.ISO88598E,
|
||||
}
|
||||
|
||||
iso8859_8I = internal.Encoding{
|
||||
Encoding: ISO8859_8,
|
||||
Name: "ISO-8859-8I",
|
||||
MIB: identifier.ISO88598I,
|
||||
}
|
||||
)
|
||||
|
||||
// All is a list of all defined encodings in this package.
|
||||
var All []encoding.Encoding = listAll
|
||||
|
||||
// TODO: implement these encodings, in order of importance.
|
||||
// ASCII, ISO8859_1: Rather common. Close to Windows 1252.
|
||||
// ISO8859_9: Close to Windows 1254.
|
||||
|
||||
// utf8Enc holds a rune's UTF-8 encoding in data[:len].
|
||||
type utf8Enc struct {
|
||||
len uint8
|
||||
data [3]byte
|
||||
}
|
||||
|
||||
// Charmap is an 8-bit character set encoding.
|
||||
type Charmap struct {
|
||||
// name is the encoding's name.
|
||||
name string
|
||||
// mib is the encoding type of this encoder.
|
||||
mib identifier.MIB
|
||||
// asciiSuperset states whether the encoding is a superset of ASCII.
|
||||
asciiSuperset bool
|
||||
// low is the lower bound of the encoded byte for a non-ASCII rune. If
|
||||
// Charmap.asciiSuperset is true then this will be 0x80, otherwise 0x00.
|
||||
low uint8
|
||||
// replacement is the encoded replacement character.
|
||||
replacement byte
|
||||
// decode is the map from encoded byte to UTF-8.
|
||||
decode [256]utf8Enc
|
||||
// encoding is the map from runes to encoded bytes. Each entry is a
|
||||
// uint32: the high 8 bits are the encoded byte and the low 24 bits are
|
||||
// the rune. The table entries are sorted by ascending rune.
|
||||
encode [256]uint32
|
||||
}
|
||||
|
||||
// NewDecoder implements the encoding.Encoding interface.
|
||||
func (m *Charmap) NewDecoder() *encoding.Decoder {
|
||||
return &encoding.Decoder{Transformer: charmapDecoder{charmap: m}}
|
||||
}
|
||||
|
||||
// NewEncoder implements the encoding.Encoding interface.
|
||||
func (m *Charmap) NewEncoder() *encoding.Encoder {
|
||||
return &encoding.Encoder{Transformer: charmapEncoder{charmap: m}}
|
||||
}
|
||||
|
||||
// String returns the Charmap's name.
|
||||
func (m *Charmap) String() string {
|
||||
return m.name
|
||||
}
|
||||
|
||||
// ID implements an internal interface.
|
||||
func (m *Charmap) ID() (mib identifier.MIB, other string) {
|
||||
return m.mib, ""
|
||||
}
|
||||
|
||||
// charmapDecoder implements transform.Transformer by decoding to UTF-8.
|
||||
type charmapDecoder struct {
|
||||
transform.NopResetter
|
||||
charmap *Charmap
|
||||
}
|
||||
|
||||
func (m charmapDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
for i, c := range src {
|
||||
if m.charmap.asciiSuperset && c < utf8.RuneSelf {
|
||||
if nDst >= len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst] = c
|
||||
nDst++
|
||||
nSrc = i + 1
|
||||
continue
|
||||
}
|
||||
|
||||
decode := &m.charmap.decode[c]
|
||||
n := int(decode.len)
|
||||
if nDst+n > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
// It's 15% faster to avoid calling copy for these tiny slices.
|
||||
for j := 0; j < n; j++ {
|
||||
dst[nDst] = decode.data[j]
|
||||
nDst++
|
||||
}
|
||||
nSrc = i + 1
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
// DecodeByte returns the Charmap's rune decoding of the byte b.
|
||||
func (m *Charmap) DecodeByte(b byte) rune {
|
||||
switch x := &m.decode[b]; x.len {
|
||||
case 1:
|
||||
return rune(x.data[0])
|
||||
case 2:
|
||||
return rune(x.data[0]&0x1f)<<6 | rune(x.data[1]&0x3f)
|
||||
default:
|
||||
return rune(x.data[0]&0x0f)<<12 | rune(x.data[1]&0x3f)<<6 | rune(x.data[2]&0x3f)
|
||||
}
|
||||
}
|
||||
|
||||
// charmapEncoder implements transform.Transformer by encoding from UTF-8.
|
||||
type charmapEncoder struct {
|
||||
transform.NopResetter
|
||||
charmap *Charmap
|
||||
}
|
||||
|
||||
func (m charmapEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
r, size := rune(0), 0
|
||||
loop:
|
||||
for nSrc < len(src) {
|
||||
if nDst >= len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
r = rune(src[nSrc])
|
||||
|
||||
// Decode a 1-byte rune.
|
||||
if r < utf8.RuneSelf {
|
||||
if m.charmap.asciiSuperset {
|
||||
nSrc++
|
||||
dst[nDst] = uint8(r)
|
||||
nDst++
|
||||
continue
|
||||
}
|
||||
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
|
||||
} else {
|
||||
err = internal.RepertoireError(m.charmap.replacement)
|
||||
}
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
// Binary search in [low, high) for that rune in the m.charmap.encode table.
|
||||
for low, high := int(m.charmap.low), 0x100; ; {
|
||||
if low >= high {
|
||||
err = internal.RepertoireError(m.charmap.replacement)
|
||||
break loop
|
||||
}
|
||||
mid := (low + high) / 2
|
||||
got := m.charmap.encode[mid]
|
||||
gotRune := rune(got & (1<<24 - 1))
|
||||
if gotRune < r {
|
||||
low = mid + 1
|
||||
} else if gotRune > r {
|
||||
high = mid
|
||||
} else {
|
||||
dst[nDst] = byte(got >> 24)
|
||||
nDst++
|
||||
break
|
||||
}
|
||||
}
|
||||
nSrc += size
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
// EncodeRune returns the Charmap's byte encoding of the rune r. ok is whether
|
||||
// r is in the Charmap's repertoire. If not, b is set to the Charmap's
|
||||
// replacement byte. This is often the ASCII substitute character '\x1a'.
|
||||
func (m *Charmap) EncodeRune(r rune) (b byte, ok bool) {
|
||||
if r < utf8.RuneSelf && m.asciiSuperset {
|
||||
return byte(r), true
|
||||
}
|
||||
for low, high := int(m.low), 0x100; ; {
|
||||
if low >= high {
|
||||
return m.replacement, false
|
||||
}
|
||||
mid := (low + high) / 2
|
||||
got := m.encode[mid]
|
||||
gotRune := rune(got & (1<<24 - 1))
|
||||
if gotRune < r {
|
||||
low = mid + 1
|
||||
} else if gotRune > r {
|
||||
high = mid
|
||||
} else {
|
||||
return byte(got >> 24), true
|
||||
}
|
||||
}
|
||||
}
|
||||
556
vendor/golang.org/x/text/encoding/charmap/maketables.go
generated
vendored
Normal file
556
vendor/golang.org/x/text/encoding/charmap/maketables.go
generated
vendored
Normal file
|
|
@ -0,0 +1,556 @@
|
|||
// 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] }
|
||||
7410
vendor/golang.org/x/text/encoding/charmap/tables.go
generated
vendored
Normal file
7410
vendor/golang.org/x/text/encoding/charmap/tables.go
generated
vendored
Normal file
File diff suppressed because it is too large
Load diff
335
vendor/golang.org/x/text/encoding/encoding.go
generated
vendored
Normal file
335
vendor/golang.org/x/text/encoding/encoding.go
generated
vendored
Normal file
|
|
@ -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
|
||||
// https://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
|
||||
}
|
||||
173
vendor/golang.org/x/text/encoding/htmlindex/gen.go
generated
vendored
Normal file
173
vendor/golang.org/x/text/encoding/htmlindex/gen.go
generated
vendored
Normal file
|
|
@ -0,0 +1,173 @@
|
|||
// 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"},
|
||||
}
|
||||
86
vendor/golang.org/x/text/encoding/htmlindex/htmlindex.go
generated
vendored
Normal file
86
vendor/golang.org/x/text/encoding/htmlindex/htmlindex.go
generated
vendored
Normal file
|
|
@ -0,0 +1,86 @@
|
|||
// 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 htmlindex maps character set encoding names to Encodings as
|
||||
// recommended by the W3C for use in HTML 5. See http://www.w3.org/TR/encoding.
|
||||
package htmlindex
|
||||
|
||||
// TODO: perhaps have a "bare" version of the index (used by this package) that
|
||||
// is not pre-loaded with all encodings. Global variables in encodings prevent
|
||||
// the linker from being able to purge unneeded tables. This means that
|
||||
// referencing all encodings, as this package does for the default index, links
|
||||
// in all encodings unconditionally.
|
||||
//
|
||||
// This issue can be solved by either solving the linking issue (see
|
||||
// https://github.com/golang/go/issues/6330) or refactoring the encoding tables
|
||||
// (e.g. moving the tables to internal packages that do not use global
|
||||
// variables).
|
||||
|
||||
// TODO: allow canonicalizing names
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"strings"
|
||||
"sync"
|
||||
|
||||
"golang.org/x/text/encoding"
|
||||
"golang.org/x/text/encoding/internal/identifier"
|
||||
"golang.org/x/text/language"
|
||||
)
|
||||
|
||||
var (
|
||||
errInvalidName = errors.New("htmlindex: invalid encoding name")
|
||||
errUnknown = errors.New("htmlindex: unknown Encoding")
|
||||
errUnsupported = errors.New("htmlindex: this encoding is not supported")
|
||||
)
|
||||
|
||||
var (
|
||||
matcherOnce sync.Once
|
||||
matcher language.Matcher
|
||||
)
|
||||
|
||||
// LanguageDefault returns the canonical name of the default encoding for a
|
||||
// given language.
|
||||
func LanguageDefault(tag language.Tag) string {
|
||||
matcherOnce.Do(func() {
|
||||
tags := []language.Tag{}
|
||||
for _, t := range strings.Split(locales, " ") {
|
||||
tags = append(tags, language.MustParse(t))
|
||||
}
|
||||
matcher = language.NewMatcher(tags, language.PreferSameScript(true))
|
||||
})
|
||||
_, i, _ := matcher.Match(tag)
|
||||
return canonical[localeMap[i]] // Default is Windows-1252.
|
||||
}
|
||||
|
||||
// Get returns an Encoding for one of the names listed in
|
||||
// http://www.w3.org/TR/encoding using the Default Index. Matching is case-
|
||||
// insensitive.
|
||||
func Get(name string) (encoding.Encoding, error) {
|
||||
x, ok := nameMap[strings.ToLower(strings.TrimSpace(name))]
|
||||
if !ok {
|
||||
return nil, errInvalidName
|
||||
}
|
||||
return encodings[x], nil
|
||||
}
|
||||
|
||||
// Name reports the canonical name of the given Encoding. It will return
|
||||
// an error if e is not associated with a supported encoding scheme.
|
||||
func Name(e encoding.Encoding) (string, error) {
|
||||
id, ok := e.(identifier.Interface)
|
||||
if !ok {
|
||||
return "", errUnknown
|
||||
}
|
||||
mib, _ := id.ID()
|
||||
if mib == 0 {
|
||||
return "", errUnknown
|
||||
}
|
||||
v, ok := mibMap[mib]
|
||||
if !ok {
|
||||
return "", errUnsupported
|
||||
}
|
||||
return canonical[v], nil
|
||||
}
|
||||
105
vendor/golang.org/x/text/encoding/htmlindex/map.go
generated
vendored
Normal file
105
vendor/golang.org/x/text/encoding/htmlindex/map.go
generated
vendored
Normal file
|
|
@ -0,0 +1,105 @@
|
|||
// 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 htmlindex
|
||||
|
||||
import (
|
||||
"golang.org/x/text/encoding"
|
||||
"golang.org/x/text/encoding/charmap"
|
||||
"golang.org/x/text/encoding/internal/identifier"
|
||||
"golang.org/x/text/encoding/japanese"
|
||||
"golang.org/x/text/encoding/korean"
|
||||
"golang.org/x/text/encoding/simplifiedchinese"
|
||||
"golang.org/x/text/encoding/traditionalchinese"
|
||||
"golang.org/x/text/encoding/unicode"
|
||||
)
|
||||
|
||||
// mibMap maps a MIB identifier to an htmlEncoding index.
|
||||
var mibMap = map[identifier.MIB]htmlEncoding{
|
||||
identifier.UTF8: utf8,
|
||||
identifier.UTF16BE: utf16be,
|
||||
identifier.UTF16LE: utf16le,
|
||||
identifier.IBM866: ibm866,
|
||||
identifier.ISOLatin2: iso8859_2,
|
||||
identifier.ISOLatin3: iso8859_3,
|
||||
identifier.ISOLatin4: iso8859_4,
|
||||
identifier.ISOLatinCyrillic: iso8859_5,
|
||||
identifier.ISOLatinArabic: iso8859_6,
|
||||
identifier.ISOLatinGreek: iso8859_7,
|
||||
identifier.ISOLatinHebrew: iso8859_8,
|
||||
identifier.ISO88598I: iso8859_8I,
|
||||
identifier.ISOLatin6: iso8859_10,
|
||||
identifier.ISO885913: iso8859_13,
|
||||
identifier.ISO885914: iso8859_14,
|
||||
identifier.ISO885915: iso8859_15,
|
||||
identifier.ISO885916: iso8859_16,
|
||||
identifier.KOI8R: koi8r,
|
||||
identifier.KOI8U: koi8u,
|
||||
identifier.Macintosh: macintosh,
|
||||
identifier.MacintoshCyrillic: macintoshCyrillic,
|
||||
identifier.Windows874: windows874,
|
||||
identifier.Windows1250: windows1250,
|
||||
identifier.Windows1251: windows1251,
|
||||
identifier.Windows1252: windows1252,
|
||||
identifier.Windows1253: windows1253,
|
||||
identifier.Windows1254: windows1254,
|
||||
identifier.Windows1255: windows1255,
|
||||
identifier.Windows1256: windows1256,
|
||||
identifier.Windows1257: windows1257,
|
||||
identifier.Windows1258: windows1258,
|
||||
identifier.XUserDefined: xUserDefined,
|
||||
identifier.GBK: gbk,
|
||||
identifier.GB18030: gb18030,
|
||||
identifier.Big5: big5,
|
||||
identifier.EUCPkdFmtJapanese: eucjp,
|
||||
identifier.ISO2022JP: iso2022jp,
|
||||
identifier.ShiftJIS: shiftJIS,
|
||||
identifier.EUCKR: euckr,
|
||||
identifier.Replacement: replacement,
|
||||
}
|
||||
|
||||
// encodings maps the internal htmlEncoding to an Encoding.
|
||||
// TODO: consider using a reusable index in encoding/internal.
|
||||
var encodings = [numEncodings]encoding.Encoding{
|
||||
utf8: unicode.UTF8,
|
||||
ibm866: charmap.CodePage866,
|
||||
iso8859_2: charmap.ISO8859_2,
|
||||
iso8859_3: charmap.ISO8859_3,
|
||||
iso8859_4: charmap.ISO8859_4,
|
||||
iso8859_5: charmap.ISO8859_5,
|
||||
iso8859_6: charmap.ISO8859_6,
|
||||
iso8859_7: charmap.ISO8859_7,
|
||||
iso8859_8: charmap.ISO8859_8,
|
||||
iso8859_8I: charmap.ISO8859_8I,
|
||||
iso8859_10: charmap.ISO8859_10,
|
||||
iso8859_13: charmap.ISO8859_13,
|
||||
iso8859_14: charmap.ISO8859_14,
|
||||
iso8859_15: charmap.ISO8859_15,
|
||||
iso8859_16: charmap.ISO8859_16,
|
||||
koi8r: charmap.KOI8R,
|
||||
koi8u: charmap.KOI8U,
|
||||
macintosh: charmap.Macintosh,
|
||||
windows874: charmap.Windows874,
|
||||
windows1250: charmap.Windows1250,
|
||||
windows1251: charmap.Windows1251,
|
||||
windows1252: charmap.Windows1252,
|
||||
windows1253: charmap.Windows1253,
|
||||
windows1254: charmap.Windows1254,
|
||||
windows1255: charmap.Windows1255,
|
||||
windows1256: charmap.Windows1256,
|
||||
windows1257: charmap.Windows1257,
|
||||
windows1258: charmap.Windows1258,
|
||||
macintoshCyrillic: charmap.MacintoshCyrillic,
|
||||
gbk: simplifiedchinese.GBK,
|
||||
gb18030: simplifiedchinese.GB18030,
|
||||
big5: traditionalchinese.Big5,
|
||||
eucjp: japanese.EUCJP,
|
||||
iso2022jp: japanese.ISO2022JP,
|
||||
shiftJIS: japanese.ShiftJIS,
|
||||
euckr: korean.EUCKR,
|
||||
replacement: encoding.Replacement,
|
||||
utf16be: unicode.UTF16(unicode.BigEndian, unicode.IgnoreBOM),
|
||||
utf16le: unicode.UTF16(unicode.LittleEndian, unicode.IgnoreBOM),
|
||||
xUserDefined: charmap.XUserDefined,
|
||||
}
|
||||
353
vendor/golang.org/x/text/encoding/htmlindex/tables.go
generated
vendored
Normal file
353
vendor/golang.org/x/text/encoding/htmlindex/tables.go
generated
vendored
Normal file
|
|
@ -0,0 +1,353 @@
|
|||
// Code generated by running "go generate" in golang.org/x/text. DO NOT EDIT.
|
||||
|
||||
package htmlindex
|
||||
|
||||
type htmlEncoding byte
|
||||
|
||||
const (
|
||||
utf8 htmlEncoding = iota
|
||||
ibm866
|
||||
iso8859_2
|
||||
iso8859_3
|
||||
iso8859_4
|
||||
iso8859_5
|
||||
iso8859_6
|
||||
iso8859_7
|
||||
iso8859_8
|
||||
iso8859_8I
|
||||
iso8859_10
|
||||
iso8859_13
|
||||
iso8859_14
|
||||
iso8859_15
|
||||
iso8859_16
|
||||
koi8r
|
||||
koi8u
|
||||
macintosh
|
||||
windows874
|
||||
windows1250
|
||||
windows1251
|
||||
windows1252
|
||||
windows1253
|
||||
windows1254
|
||||
windows1255
|
||||
windows1256
|
||||
windows1257
|
||||
windows1258
|
||||
macintoshCyrillic
|
||||
gbk
|
||||
gb18030
|
||||
big5
|
||||
eucjp
|
||||
iso2022jp
|
||||
shiftJIS
|
||||
euckr
|
||||
replacement
|
||||
utf16be
|
||||
utf16le
|
||||
xUserDefined
|
||||
numEncodings
|
||||
)
|
||||
|
||||
var canonical = [numEncodings]string{
|
||||
"utf-8",
|
||||
"ibm866",
|
||||
"iso-8859-2",
|
||||
"iso-8859-3",
|
||||
"iso-8859-4",
|
||||
"iso-8859-5",
|
||||
"iso-8859-6",
|
||||
"iso-8859-7",
|
||||
"iso-8859-8",
|
||||
"iso-8859-8-i",
|
||||
"iso-8859-10",
|
||||
"iso-8859-13",
|
||||
"iso-8859-14",
|
||||
"iso-8859-15",
|
||||
"iso-8859-16",
|
||||
"koi8-r",
|
||||
"koi8-u",
|
||||
"macintosh",
|
||||
"windows-874",
|
||||
"windows-1250",
|
||||
"windows-1251",
|
||||
"windows-1252",
|
||||
"windows-1253",
|
||||
"windows-1254",
|
||||
"windows-1255",
|
||||
"windows-1256",
|
||||
"windows-1257",
|
||||
"windows-1258",
|
||||
"x-mac-cyrillic",
|
||||
"gbk",
|
||||
"gb18030",
|
||||
"big5",
|
||||
"euc-jp",
|
||||
"iso-2022-jp",
|
||||
"shift_jis",
|
||||
"euc-kr",
|
||||
"replacement",
|
||||
"utf-16be",
|
||||
"utf-16le",
|
||||
"x-user-defined",
|
||||
}
|
||||
|
||||
var nameMap = map[string]htmlEncoding{
|
||||
"unicode-1-1-utf-8": utf8,
|
||||
"utf-8": utf8,
|
||||
"utf8": utf8,
|
||||
"866": ibm866,
|
||||
"cp866": ibm866,
|
||||
"csibm866": ibm866,
|
||||
"ibm866": ibm866,
|
||||
"csisolatin2": iso8859_2,
|
||||
"iso-8859-2": iso8859_2,
|
||||
"iso-ir-101": iso8859_2,
|
||||
"iso8859-2": iso8859_2,
|
||||
"iso88592": iso8859_2,
|
||||
"iso_8859-2": iso8859_2,
|
||||
"iso_8859-2:1987": iso8859_2,
|
||||
"l2": iso8859_2,
|
||||
"latin2": iso8859_2,
|
||||
"csisolatin3": iso8859_3,
|
||||
"iso-8859-3": iso8859_3,
|
||||
"iso-ir-109": iso8859_3,
|
||||
"iso8859-3": iso8859_3,
|
||||
"iso88593": iso8859_3,
|
||||
"iso_8859-3": iso8859_3,
|
||||
"iso_8859-3:1988": iso8859_3,
|
||||
"l3": iso8859_3,
|
||||
"latin3": iso8859_3,
|
||||
"csisolatin4": iso8859_4,
|
||||
"iso-8859-4": iso8859_4,
|
||||
"iso-ir-110": iso8859_4,
|
||||
"iso8859-4": iso8859_4,
|
||||
"iso88594": iso8859_4,
|
||||
"iso_8859-4": iso8859_4,
|
||||
"iso_8859-4:1988": iso8859_4,
|
||||
"l4": iso8859_4,
|
||||
"latin4": iso8859_4,
|
||||
"csisolatincyrillic": iso8859_5,
|
||||
"cyrillic": iso8859_5,
|
||||
"iso-8859-5": iso8859_5,
|
||||
"iso-ir-144": iso8859_5,
|
||||
"iso8859-5": iso8859_5,
|
||||
"iso88595": iso8859_5,
|
||||
"iso_8859-5": iso8859_5,
|
||||
"iso_8859-5:1988": iso8859_5,
|
||||
"arabic": iso8859_6,
|
||||
"asmo-708": iso8859_6,
|
||||
"csiso88596e": iso8859_6,
|
||||
"csiso88596i": iso8859_6,
|
||||
"csisolatinarabic": iso8859_6,
|
||||
"ecma-114": iso8859_6,
|
||||
"iso-8859-6": iso8859_6,
|
||||
"iso-8859-6-e": iso8859_6,
|
||||
"iso-8859-6-i": iso8859_6,
|
||||
"iso-ir-127": iso8859_6,
|
||||
"iso8859-6": iso8859_6,
|
||||
"iso88596": iso8859_6,
|
||||
"iso_8859-6": iso8859_6,
|
||||
"iso_8859-6:1987": iso8859_6,
|
||||
"csisolatingreek": iso8859_7,
|
||||
"ecma-118": iso8859_7,
|
||||
"elot_928": iso8859_7,
|
||||
"greek": iso8859_7,
|
||||
"greek8": iso8859_7,
|
||||
"iso-8859-7": iso8859_7,
|
||||
"iso-ir-126": iso8859_7,
|
||||
"iso8859-7": iso8859_7,
|
||||
"iso88597": iso8859_7,
|
||||
"iso_8859-7": iso8859_7,
|
||||
"iso_8859-7:1987": iso8859_7,
|
||||
"sun_eu_greek": iso8859_7,
|
||||
"csiso88598e": iso8859_8,
|
||||
"csisolatinhebrew": iso8859_8,
|
||||
"hebrew": iso8859_8,
|
||||
"iso-8859-8": iso8859_8,
|
||||
"iso-8859-8-e": iso8859_8,
|
||||
"iso-ir-138": iso8859_8,
|
||||
"iso8859-8": iso8859_8,
|
||||
"iso88598": iso8859_8,
|
||||
"iso_8859-8": iso8859_8,
|
||||
"iso_8859-8:1988": iso8859_8,
|
||||
"visual": iso8859_8,
|
||||
"csiso88598i": iso8859_8I,
|
||||
"iso-8859-8-i": iso8859_8I,
|
||||
"logical": iso8859_8I,
|
||||
"csisolatin6": iso8859_10,
|
||||
"iso-8859-10": iso8859_10,
|
||||
"iso-ir-157": iso8859_10,
|
||||
"iso8859-10": iso8859_10,
|
||||
"iso885910": iso8859_10,
|
||||
"l6": iso8859_10,
|
||||
"latin6": iso8859_10,
|
||||
"iso-8859-13": iso8859_13,
|
||||
"iso8859-13": iso8859_13,
|
||||
"iso885913": iso8859_13,
|
||||
"iso-8859-14": iso8859_14,
|
||||
"iso8859-14": iso8859_14,
|
||||
"iso885914": iso8859_14,
|
||||
"csisolatin9": iso8859_15,
|
||||
"iso-8859-15": iso8859_15,
|
||||
"iso8859-15": iso8859_15,
|
||||
"iso885915": iso8859_15,
|
||||
"iso_8859-15": iso8859_15,
|
||||
"l9": iso8859_15,
|
||||
"iso-8859-16": iso8859_16,
|
||||
"cskoi8r": koi8r,
|
||||
"koi": koi8r,
|
||||
"koi8": koi8r,
|
||||
"koi8-r": koi8r,
|
||||
"koi8_r": koi8r,
|
||||
"koi8-ru": koi8u,
|
||||
"koi8-u": koi8u,
|
||||
"csmacintosh": macintosh,
|
||||
"mac": macintosh,
|
||||
"macintosh": macintosh,
|
||||
"x-mac-roman": macintosh,
|
||||
"dos-874": windows874,
|
||||
"iso-8859-11": windows874,
|
||||
"iso8859-11": windows874,
|
||||
"iso885911": windows874,
|
||||
"tis-620": windows874,
|
||||
"windows-874": windows874,
|
||||
"cp1250": windows1250,
|
||||
"windows-1250": windows1250,
|
||||
"x-cp1250": windows1250,
|
||||
"cp1251": windows1251,
|
||||
"windows-1251": windows1251,
|
||||
"x-cp1251": windows1251,
|
||||
"ansi_x3.4-1968": windows1252,
|
||||
"ascii": windows1252,
|
||||
"cp1252": windows1252,
|
||||
"cp819": windows1252,
|
||||
"csisolatin1": windows1252,
|
||||
"ibm819": windows1252,
|
||||
"iso-8859-1": windows1252,
|
||||
"iso-ir-100": windows1252,
|
||||
"iso8859-1": windows1252,
|
||||
"iso88591": windows1252,
|
||||
"iso_8859-1": windows1252,
|
||||
"iso_8859-1:1987": windows1252,
|
||||
"l1": windows1252,
|
||||
"latin1": windows1252,
|
||||
"us-ascii": windows1252,
|
||||
"windows-1252": windows1252,
|
||||
"x-cp1252": windows1252,
|
||||
"cp1253": windows1253,
|
||||
"windows-1253": windows1253,
|
||||
"x-cp1253": windows1253,
|
||||
"cp1254": windows1254,
|
||||
"csisolatin5": windows1254,
|
||||
"iso-8859-9": windows1254,
|
||||
"iso-ir-148": windows1254,
|
||||
"iso8859-9": windows1254,
|
||||
"iso88599": windows1254,
|
||||
"iso_8859-9": windows1254,
|
||||
"iso_8859-9:1989": windows1254,
|
||||
"l5": windows1254,
|
||||
"latin5": windows1254,
|
||||
"windows-1254": windows1254,
|
||||
"x-cp1254": windows1254,
|
||||
"cp1255": windows1255,
|
||||
"windows-1255": windows1255,
|
||||
"x-cp1255": windows1255,
|
||||
"cp1256": windows1256,
|
||||
"windows-1256": windows1256,
|
||||
"x-cp1256": windows1256,
|
||||
"cp1257": windows1257,
|
||||
"windows-1257": windows1257,
|
||||
"x-cp1257": windows1257,
|
||||
"cp1258": windows1258,
|
||||
"windows-1258": windows1258,
|
||||
"x-cp1258": windows1258,
|
||||
"x-mac-cyrillic": macintoshCyrillic,
|
||||
"x-mac-ukrainian": macintoshCyrillic,
|
||||
"chinese": gbk,
|
||||
"csgb2312": gbk,
|
||||
"csiso58gb231280": gbk,
|
||||
"gb2312": gbk,
|
||||
"gb_2312": gbk,
|
||||
"gb_2312-80": gbk,
|
||||
"gbk": gbk,
|
||||
"iso-ir-58": gbk,
|
||||
"x-gbk": gbk,
|
||||
"gb18030": gb18030,
|
||||
"big5": big5,
|
||||
"big5-hkscs": big5,
|
||||
"cn-big5": big5,
|
||||
"csbig5": big5,
|
||||
"x-x-big5": big5,
|
||||
"cseucpkdfmtjapanese": eucjp,
|
||||
"euc-jp": eucjp,
|
||||
"x-euc-jp": eucjp,
|
||||
"csiso2022jp": iso2022jp,
|
||||
"iso-2022-jp": iso2022jp,
|
||||
"csshiftjis": shiftJIS,
|
||||
"ms932": shiftJIS,
|
||||
"ms_kanji": shiftJIS,
|
||||
"shift-jis": shiftJIS,
|
||||
"shift_jis": shiftJIS,
|
||||
"sjis": shiftJIS,
|
||||
"windows-31j": shiftJIS,
|
||||
"x-sjis": shiftJIS,
|
||||
"cseuckr": euckr,
|
||||
"csksc56011987": euckr,
|
||||
"euc-kr": euckr,
|
||||
"iso-ir-149": euckr,
|
||||
"korean": euckr,
|
||||
"ks_c_5601-1987": euckr,
|
||||
"ks_c_5601-1989": euckr,
|
||||
"ksc5601": euckr,
|
||||
"ksc_5601": euckr,
|
||||
"windows-949": euckr,
|
||||
"csiso2022kr": replacement,
|
||||
"hz-gb-2312": replacement,
|
||||
"iso-2022-cn": replacement,
|
||||
"iso-2022-cn-ext": replacement,
|
||||
"iso-2022-kr": replacement,
|
||||
"replacement": replacement,
|
||||
"utf-16be": utf16be,
|
||||
"utf-16": utf16le,
|
||||
"utf-16le": utf16le,
|
||||
"x-user-defined": xUserDefined,
|
||||
}
|
||||
|
||||
var localeMap = []htmlEncoding{
|
||||
windows1252, // und_Latn
|
||||
windows1256, // ar
|
||||
windows1251, // ba
|
||||
windows1251, // be
|
||||
windows1251, // bg
|
||||
windows1250, // cs
|
||||
iso8859_7, // el
|
||||
windows1257, // et
|
||||
windows1256, // fa
|
||||
windows1255, // he
|
||||
windows1250, // hr
|
||||
iso8859_2, // hu
|
||||
shiftJIS, // ja
|
||||
windows1251, // kk
|
||||
euckr, // ko
|
||||
windows1254, // ku
|
||||
windows1251, // ky
|
||||
windows1257, // lt
|
||||
windows1257, // lv
|
||||
windows1251, // mk
|
||||
iso8859_2, // pl
|
||||
windows1251, // ru
|
||||
windows1251, // sah
|
||||
windows1250, // sk
|
||||
iso8859_2, // sl
|
||||
windows1251, // sr
|
||||
windows1251, // tg
|
||||
windows874, // th
|
||||
windows1254, // tr
|
||||
windows1251, // tt
|
||||
windows1251, // uk
|
||||
windows1258, // vi
|
||||
gb18030, // zh-hans
|
||||
big5, // zh-hant
|
||||
}
|
||||
|
||||
const locales = "und_Latn ar ba be bg cs el et fa he hr hu ja kk ko ku ky lt lv mk pl ru sah sk sl sr tg th tr tt uk vi zh-hans zh-hant"
|
||||
142
vendor/golang.org/x/text/encoding/internal/identifier/gen.go
generated
vendored
Normal file
142
vendor/golang.org/x/text/encoding/internal/identifier/gen.go
generated
vendored
Normal file
|
|
@ -0,0 +1,142 @@
|
|||
// 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 {
|
||||
// Patch up URLs to use https. From some links, the
|
||||
// https version is different from the http one.
|
||||
s := a.Value
|
||||
s = strings.Replace(s, "http://", "https://", -1)
|
||||
s = strings.Replace(s, "/unicode/", "/", -1)
|
||||
attr = s + " "
|
||||
}
|
||||
}
|
||||
}
|
||||
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
|
||||
// - https://www.unicode.org/reports/tr22/
|
||||
// - http://www.w3.org/TR/encoding/
|
||||
// - https://encoding.spec.whatwg.org/
|
||||
// - https://encoding.spec.whatwg.org/encodings.json
|
||||
// - 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
|
||||
)
|
||||
1619
vendor/golang.org/x/text/encoding/internal/identifier/mib.go
generated
vendored
Normal file
1619
vendor/golang.org/x/text/encoding/internal/identifier/mib.go
generated
vendored
Normal file
File diff suppressed because it is too large
Load diff
75
vendor/golang.org/x/text/encoding/internal/internal.go
generated
vendored
Normal file
75
vendor/golang.org/x/text/encoding/internal/internal.go
generated
vendored
Normal file
|
|
@ -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)
|
||||
12
vendor/golang.org/x/text/encoding/japanese/all.go
generated
vendored
Normal file
12
vendor/golang.org/x/text/encoding/japanese/all.go
generated
vendored
Normal file
|
|
@ -0,0 +1,12 @@
|
|||
// 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 japanese
|
||||
|
||||
import (
|
||||
"golang.org/x/text/encoding"
|
||||
)
|
||||
|
||||
// All is a list of all defined encodings in this package.
|
||||
var All = []encoding.Encoding{EUCJP, ISO2022JP, ShiftJIS}
|
||||
225
vendor/golang.org/x/text/encoding/japanese/eucjp.go
generated
vendored
Normal file
225
vendor/golang.org/x/text/encoding/japanese/eucjp.go
generated
vendored
Normal file
|
|
@ -0,0 +1,225 @@
|
|||
// 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 japanese
|
||||
|
||||
import (
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/text/encoding"
|
||||
"golang.org/x/text/encoding/internal"
|
||||
"golang.org/x/text/encoding/internal/identifier"
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// EUCJP is the EUC-JP encoding.
|
||||
var EUCJP encoding.Encoding = &eucJP
|
||||
|
||||
var eucJP = internal.Encoding{
|
||||
&internal.SimpleEncoding{eucJPDecoder{}, eucJPEncoder{}},
|
||||
"EUC-JP",
|
||||
identifier.EUCPkdFmtJapanese,
|
||||
}
|
||||
|
||||
type eucJPDecoder struct{ transform.NopResetter }
|
||||
|
||||
// See https://encoding.spec.whatwg.org/#euc-jp-decoder.
|
||||
func (eucJPDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
r, size := rune(0), 0
|
||||
loop:
|
||||
for ; nSrc < len(src); nSrc += size {
|
||||
switch c0 := src[nSrc]; {
|
||||
case c0 < utf8.RuneSelf:
|
||||
r, size = rune(c0), 1
|
||||
|
||||
case c0 == 0x8e:
|
||||
if nSrc+1 >= len(src) {
|
||||
if !atEOF {
|
||||
err = transform.ErrShortSrc
|
||||
break loop
|
||||
}
|
||||
r, size = utf8.RuneError, 1
|
||||
break
|
||||
}
|
||||
c1 := src[nSrc+1]
|
||||
switch {
|
||||
case c1 < 0xa1:
|
||||
r, size = utf8.RuneError, 1
|
||||
case c1 > 0xdf:
|
||||
r, size = utf8.RuneError, 2
|
||||
if c1 == 0xff {
|
||||
size = 1
|
||||
}
|
||||
default:
|
||||
r, size = rune(c1)+(0xff61-0xa1), 2
|
||||
}
|
||||
case c0 == 0x8f:
|
||||
if nSrc+2 >= len(src) {
|
||||
if !atEOF {
|
||||
err = transform.ErrShortSrc
|
||||
break loop
|
||||
}
|
||||
r, size = utf8.RuneError, 1
|
||||
if p := nSrc + 1; p < len(src) && 0xa1 <= src[p] && src[p] < 0xfe {
|
||||
size = 2
|
||||
}
|
||||
break
|
||||
}
|
||||
c1 := src[nSrc+1]
|
||||
if c1 < 0xa1 || 0xfe < c1 {
|
||||
r, size = utf8.RuneError, 1
|
||||
break
|
||||
}
|
||||
c2 := src[nSrc+2]
|
||||
if c2 < 0xa1 || 0xfe < c2 {
|
||||
r, size = utf8.RuneError, 2
|
||||
break
|
||||
}
|
||||
r, size = utf8.RuneError, 3
|
||||
if i := int(c1-0xa1)*94 + int(c2-0xa1); i < len(jis0212Decode) {
|
||||
r = rune(jis0212Decode[i])
|
||||
if r == 0 {
|
||||
r = utf8.RuneError
|
||||
}
|
||||
}
|
||||
|
||||
case 0xa1 <= c0 && c0 <= 0xfe:
|
||||
if nSrc+1 >= len(src) {
|
||||
if !atEOF {
|
||||
err = transform.ErrShortSrc
|
||||
break loop
|
||||
}
|
||||
r, size = utf8.RuneError, 1
|
||||
break
|
||||
}
|
||||
c1 := src[nSrc+1]
|
||||
if c1 < 0xa1 || 0xfe < c1 {
|
||||
r, size = utf8.RuneError, 1
|
||||
break
|
||||
}
|
||||
r, size = utf8.RuneError, 2
|
||||
if i := int(c0-0xa1)*94 + int(c1-0xa1); i < len(jis0208Decode) {
|
||||
r = rune(jis0208Decode[i])
|
||||
if r == 0 {
|
||||
r = utf8.RuneError
|
||||
}
|
||||
}
|
||||
|
||||
default:
|
||||
r, size = utf8.RuneError, 1
|
||||
}
|
||||
|
||||
if nDst+utf8.RuneLen(r) > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break loop
|
||||
}
|
||||
nDst += utf8.EncodeRune(dst[nDst:], r)
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
type eucJPEncoder struct{ transform.NopResetter }
|
||||
|
||||
func (eucJPEncoder) 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
|
||||
}
|
||||
}
|
||||
|
||||
// func init checks that the switch covers all tables.
|
||||
switch {
|
||||
case encode0Low <= r && r < encode0High:
|
||||
if r = rune(encode0[r-encode0Low]); r != 0 {
|
||||
goto write2or3
|
||||
}
|
||||
case encode1Low <= r && r < encode1High:
|
||||
if r = rune(encode1[r-encode1Low]); r != 0 {
|
||||
goto write2or3
|
||||
}
|
||||
case encode2Low <= r && r < encode2High:
|
||||
if r = rune(encode2[r-encode2Low]); r != 0 {
|
||||
goto write2or3
|
||||
}
|
||||
case encode3Low <= r && r < encode3High:
|
||||
if r = rune(encode3[r-encode3Low]); r != 0 {
|
||||
goto write2or3
|
||||
}
|
||||
case encode4Low <= r && r < encode4High:
|
||||
if r = rune(encode4[r-encode4Low]); r != 0 {
|
||||
goto write2or3
|
||||
}
|
||||
case encode5Low <= r && r < encode5High:
|
||||
if 0xff61 <= r && r < 0xffa0 {
|
||||
goto write2
|
||||
}
|
||||
if r = rune(encode5[r-encode5Low]); r != 0 {
|
||||
goto write2or3
|
||||
}
|
||||
}
|
||||
err = internal.ErrASCIIReplacement
|
||||
break
|
||||
}
|
||||
|
||||
if nDst >= len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst] = uint8(r)
|
||||
nDst++
|
||||
continue
|
||||
|
||||
write2or3:
|
||||
if r>>tableShift == jis0208 {
|
||||
if nDst+2 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
} else {
|
||||
if nDst+3 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst] = 0x8f
|
||||
nDst++
|
||||
}
|
||||
dst[nDst+0] = 0xa1 + uint8(r>>codeShift)&codeMask
|
||||
dst[nDst+1] = 0xa1 + uint8(r)&codeMask
|
||||
nDst += 2
|
||||
continue
|
||||
|
||||
write2:
|
||||
if nDst+2 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst+0] = 0x8e
|
||||
dst[nDst+1] = uint8(r - (0xff61 - 0xa1))
|
||||
nDst += 2
|
||||
continue
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
func init() {
|
||||
// Check that the hard-coded encode switch covers all tables.
|
||||
if numEncodeTables != 6 {
|
||||
panic("bad numEncodeTables")
|
||||
}
|
||||
}
|
||||
299
vendor/golang.org/x/text/encoding/japanese/iso2022jp.go
generated
vendored
Normal file
299
vendor/golang.org/x/text/encoding/japanese/iso2022jp.go
generated
vendored
Normal file
|
|
@ -0,0 +1,299 @@
|
|||
// 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 japanese
|
||||
|
||||
import (
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/text/encoding"
|
||||
"golang.org/x/text/encoding/internal"
|
||||
"golang.org/x/text/encoding/internal/identifier"
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// ISO2022JP is the ISO-2022-JP encoding.
|
||||
var ISO2022JP encoding.Encoding = &iso2022JP
|
||||
|
||||
var iso2022JP = internal.Encoding{
|
||||
internal.FuncEncoding{iso2022JPNewDecoder, iso2022JPNewEncoder},
|
||||
"ISO-2022-JP",
|
||||
identifier.ISO2022JP,
|
||||
}
|
||||
|
||||
func iso2022JPNewDecoder() transform.Transformer {
|
||||
return new(iso2022JPDecoder)
|
||||
}
|
||||
|
||||
func iso2022JPNewEncoder() transform.Transformer {
|
||||
return new(iso2022JPEncoder)
|
||||
}
|
||||
|
||||
const (
|
||||
asciiState = iota
|
||||
katakanaState
|
||||
jis0208State
|
||||
jis0212State
|
||||
)
|
||||
|
||||
const asciiEsc = 0x1b
|
||||
|
||||
type iso2022JPDecoder int
|
||||
|
||||
func (d *iso2022JPDecoder) Reset() {
|
||||
*d = asciiState
|
||||
}
|
||||
|
||||
func (d *iso2022JPDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
r, size := rune(0), 0
|
||||
for ; nSrc < len(src); nSrc += size {
|
||||
c0 := src[nSrc]
|
||||
if c0 >= utf8.RuneSelf {
|
||||
r, size = '\ufffd', 1
|
||||
goto write
|
||||
}
|
||||
|
||||
if c0 == asciiEsc {
|
||||
if nSrc+2 >= len(src) {
|
||||
if !atEOF {
|
||||
return nDst, nSrc, transform.ErrShortSrc
|
||||
}
|
||||
// TODO: is it correct to only skip 1??
|
||||
r, size = '\ufffd', 1
|
||||
goto write
|
||||
}
|
||||
size = 3
|
||||
c1 := src[nSrc+1]
|
||||
c2 := src[nSrc+2]
|
||||
switch {
|
||||
case c1 == '$' && (c2 == '@' || c2 == 'B'): // 0x24 {0x40, 0x42}
|
||||
*d = jis0208State
|
||||
continue
|
||||
case c1 == '$' && c2 == '(': // 0x24 0x28
|
||||
if nSrc+3 >= len(src) {
|
||||
if !atEOF {
|
||||
return nDst, nSrc, transform.ErrShortSrc
|
||||
}
|
||||
r, size = '\ufffd', 1
|
||||
goto write
|
||||
}
|
||||
size = 4
|
||||
if src[nSrc+3] == 'D' {
|
||||
*d = jis0212State
|
||||
continue
|
||||
}
|
||||
case c1 == '(' && (c2 == 'B' || c2 == 'J'): // 0x28 {0x42, 0x4A}
|
||||
*d = asciiState
|
||||
continue
|
||||
case c1 == '(' && c2 == 'I': // 0x28 0x49
|
||||
*d = katakanaState
|
||||
continue
|
||||
}
|
||||
r, size = '\ufffd', 1
|
||||
goto write
|
||||
}
|
||||
|
||||
switch *d {
|
||||
case asciiState:
|
||||
r, size = rune(c0), 1
|
||||
|
||||
case katakanaState:
|
||||
if c0 < 0x21 || 0x60 <= c0 {
|
||||
r, size = '\ufffd', 1
|
||||
goto write
|
||||
}
|
||||
r, size = rune(c0)+(0xff61-0x21), 1
|
||||
|
||||
default:
|
||||
if c0 == 0x0a {
|
||||
*d = asciiState
|
||||
r, size = rune(c0), 1
|
||||
goto write
|
||||
}
|
||||
if nSrc+1 >= len(src) {
|
||||
if !atEOF {
|
||||
return nDst, nSrc, transform.ErrShortSrc
|
||||
}
|
||||
r, size = '\ufffd', 1
|
||||
goto write
|
||||
}
|
||||
size = 2
|
||||
c1 := src[nSrc+1]
|
||||
i := int(c0-0x21)*94 + int(c1-0x21)
|
||||
if *d == jis0208State && i < len(jis0208Decode) {
|
||||
r = rune(jis0208Decode[i])
|
||||
} else if *d == jis0212State && i < len(jis0212Decode) {
|
||||
r = rune(jis0212Decode[i])
|
||||
} else {
|
||||
r = '\ufffd'
|
||||
goto write
|
||||
}
|
||||
if r == 0 {
|
||||
r = '\ufffd'
|
||||
}
|
||||
}
|
||||
|
||||
write:
|
||||
if nDst+utf8.RuneLen(r) > len(dst) {
|
||||
return nDst, nSrc, transform.ErrShortDst
|
||||
}
|
||||
nDst += utf8.EncodeRune(dst[nDst:], r)
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
type iso2022JPEncoder int
|
||||
|
||||
func (e *iso2022JPEncoder) Reset() {
|
||||
*e = asciiState
|
||||
}
|
||||
|
||||
func (e *iso2022JPEncoder) 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
|
||||
}
|
||||
}
|
||||
|
||||
// func init checks that the switch covers all tables.
|
||||
//
|
||||
// http://encoding.spec.whatwg.org/#iso-2022-jp says that "the index jis0212
|
||||
// is not used by the iso-2022-jp encoder due to lack of widespread support".
|
||||
//
|
||||
// TODO: do we have to special-case U+00A5 and U+203E, as per
|
||||
// http://encoding.spec.whatwg.org/#iso-2022-jp
|
||||
// Doing so would mean that "\u00a5" would not be preserved
|
||||
// after an encode-decode round trip.
|
||||
switch {
|
||||
case encode0Low <= r && r < encode0High:
|
||||
if r = rune(encode0[r-encode0Low]); r>>tableShift == jis0208 {
|
||||
goto writeJIS
|
||||
}
|
||||
case encode1Low <= r && r < encode1High:
|
||||
if r = rune(encode1[r-encode1Low]); r>>tableShift == jis0208 {
|
||||
goto writeJIS
|
||||
}
|
||||
case encode2Low <= r && r < encode2High:
|
||||
if r = rune(encode2[r-encode2Low]); r>>tableShift == jis0208 {
|
||||
goto writeJIS
|
||||
}
|
||||
case encode3Low <= r && r < encode3High:
|
||||
if r = rune(encode3[r-encode3Low]); r>>tableShift == jis0208 {
|
||||
goto writeJIS
|
||||
}
|
||||
case encode4Low <= r && r < encode4High:
|
||||
if r = rune(encode4[r-encode4Low]); r>>tableShift == jis0208 {
|
||||
goto writeJIS
|
||||
}
|
||||
case encode5Low <= r && r < encode5High:
|
||||
if 0xff61 <= r && r < 0xffa0 {
|
||||
goto writeKatakana
|
||||
}
|
||||
if r = rune(encode5[r-encode5Low]); r>>tableShift == jis0208 {
|
||||
goto writeJIS
|
||||
}
|
||||
}
|
||||
|
||||
// Switch back to ASCII state in case of error so that an ASCII
|
||||
// replacement character can be written in the correct state.
|
||||
if *e != asciiState {
|
||||
if nDst+3 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
*e = asciiState
|
||||
dst[nDst+0] = asciiEsc
|
||||
dst[nDst+1] = '('
|
||||
dst[nDst+2] = 'B'
|
||||
nDst += 3
|
||||
}
|
||||
err = internal.ErrASCIIReplacement
|
||||
break
|
||||
}
|
||||
|
||||
if *e != asciiState {
|
||||
if nDst+4 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
*e = asciiState
|
||||
dst[nDst+0] = asciiEsc
|
||||
dst[nDst+1] = '('
|
||||
dst[nDst+2] = 'B'
|
||||
nDst += 3
|
||||
} else if nDst >= len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst] = uint8(r)
|
||||
nDst++
|
||||
continue
|
||||
|
||||
writeJIS:
|
||||
if *e != jis0208State {
|
||||
if nDst+5 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
*e = jis0208State
|
||||
dst[nDst+0] = asciiEsc
|
||||
dst[nDst+1] = '$'
|
||||
dst[nDst+2] = 'B'
|
||||
nDst += 3
|
||||
} else if nDst+2 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst+0] = 0x21 + uint8(r>>codeShift)&codeMask
|
||||
dst[nDst+1] = 0x21 + uint8(r)&codeMask
|
||||
nDst += 2
|
||||
continue
|
||||
|
||||
writeKatakana:
|
||||
if *e != katakanaState {
|
||||
if nDst+4 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
*e = katakanaState
|
||||
dst[nDst+0] = asciiEsc
|
||||
dst[nDst+1] = '('
|
||||
dst[nDst+2] = 'I'
|
||||
nDst += 3
|
||||
} else if nDst >= len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst] = uint8(r - (0xff61 - 0x21))
|
||||
nDst++
|
||||
continue
|
||||
}
|
||||
if atEOF && err == nil && *e != asciiState {
|
||||
if nDst+3 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
} else {
|
||||
*e = asciiState
|
||||
dst[nDst+0] = asciiEsc
|
||||
dst[nDst+1] = '('
|
||||
dst[nDst+2] = 'B'
|
||||
nDst += 3
|
||||
}
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
161
vendor/golang.org/x/text/encoding/japanese/maketables.go
generated
vendored
Normal file
161
vendor/golang.org/x/text/encoding/japanese/maketables.go
generated
vendored
Normal file
|
|
@ -0,0 +1,161 @@
|
|||
// Copyright 2013 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build ignore
|
||||
|
||||
package main
|
||||
|
||||
// This program generates tables.go:
|
||||
// go run maketables.go | gofmt > tables.go
|
||||
|
||||
// TODO: Emoji extensions?
|
||||
// https://www.unicode.org/faq/emoji_dingbats.html
|
||||
// https://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] }
|
||||
189
vendor/golang.org/x/text/encoding/japanese/shiftjis.go
generated
vendored
Normal file
189
vendor/golang.org/x/text/encoding/japanese/shiftjis.go
generated
vendored
Normal file
|
|
@ -0,0 +1,189 @@
|
|||
// 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 japanese
|
||||
|
||||
import (
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/text/encoding"
|
||||
"golang.org/x/text/encoding/internal"
|
||||
"golang.org/x/text/encoding/internal/identifier"
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// ShiftJIS is the Shift JIS encoding, also known as Code Page 932 and
|
||||
// Windows-31J.
|
||||
var ShiftJIS encoding.Encoding = &shiftJIS
|
||||
|
||||
var shiftJIS = internal.Encoding{
|
||||
&internal.SimpleEncoding{shiftJISDecoder{}, shiftJISEncoder{}},
|
||||
"Shift JIS",
|
||||
identifier.ShiftJIS,
|
||||
}
|
||||
|
||||
type shiftJISDecoder struct{ transform.NopResetter }
|
||||
|
||||
func (shiftJISDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
r, size := rune(0), 0
|
||||
loop:
|
||||
for ; nSrc < len(src); nSrc += size {
|
||||
switch c0 := src[nSrc]; {
|
||||
case c0 < utf8.RuneSelf:
|
||||
r, size = rune(c0), 1
|
||||
|
||||
case 0xa1 <= c0 && c0 < 0xe0:
|
||||
r, size = rune(c0)+(0xff61-0xa1), 1
|
||||
|
||||
case (0x81 <= c0 && c0 < 0xa0) || (0xe0 <= c0 && c0 < 0xfd):
|
||||
if c0 <= 0x9f {
|
||||
c0 -= 0x70
|
||||
} else {
|
||||
c0 -= 0xb0
|
||||
}
|
||||
c0 = 2*c0 - 0x21
|
||||
|
||||
if nSrc+1 >= len(src) {
|
||||
if !atEOF {
|
||||
err = transform.ErrShortSrc
|
||||
break loop
|
||||
}
|
||||
r, size = '\ufffd', 1
|
||||
goto write
|
||||
}
|
||||
c1 := src[nSrc+1]
|
||||
switch {
|
||||
case c1 < 0x40:
|
||||
r, size = '\ufffd', 1 // c1 is ASCII so output on next round
|
||||
goto write
|
||||
case c1 < 0x7f:
|
||||
c0--
|
||||
c1 -= 0x40
|
||||
case c1 == 0x7f:
|
||||
r, size = '\ufffd', 1 // c1 is ASCII so output on next round
|
||||
goto write
|
||||
case c1 < 0x9f:
|
||||
c0--
|
||||
c1 -= 0x41
|
||||
case c1 < 0xfd:
|
||||
c1 -= 0x9f
|
||||
default:
|
||||
r, size = '\ufffd', 2
|
||||
goto write
|
||||
}
|
||||
r, size = '\ufffd', 2
|
||||
if i := int(c0)*94 + int(c1); i < len(jis0208Decode) {
|
||||
r = rune(jis0208Decode[i])
|
||||
if r == 0 {
|
||||
r = '\ufffd'
|
||||
}
|
||||
}
|
||||
|
||||
case c0 == 0x80:
|
||||
r, size = 0x80, 1
|
||||
|
||||
default:
|
||||
r, size = '\ufffd', 1
|
||||
}
|
||||
write:
|
||||
if nDst+utf8.RuneLen(r) > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break loop
|
||||
}
|
||||
nDst += utf8.EncodeRune(dst[nDst:], r)
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
type shiftJISEncoder struct{ transform.NopResetter }
|
||||
|
||||
func (shiftJISEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
r, size := rune(0), 0
|
||||
loop:
|
||||
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 loop
|
||||
}
|
||||
}
|
||||
|
||||
// func init checks that the switch covers all tables.
|
||||
switch {
|
||||
case encode0Low <= r && r < encode0High:
|
||||
if r = rune(encode0[r-encode0Low]); r>>tableShift == jis0208 {
|
||||
goto write2
|
||||
}
|
||||
case encode1Low <= r && r < encode1High:
|
||||
if r = rune(encode1[r-encode1Low]); r>>tableShift == jis0208 {
|
||||
goto write2
|
||||
}
|
||||
case encode2Low <= r && r < encode2High:
|
||||
if r = rune(encode2[r-encode2Low]); r>>tableShift == jis0208 {
|
||||
goto write2
|
||||
}
|
||||
case encode3Low <= r && r < encode3High:
|
||||
if r = rune(encode3[r-encode3Low]); r>>tableShift == jis0208 {
|
||||
goto write2
|
||||
}
|
||||
case encode4Low <= r && r < encode4High:
|
||||
if r = rune(encode4[r-encode4Low]); r>>tableShift == jis0208 {
|
||||
goto write2
|
||||
}
|
||||
case encode5Low <= r && r < encode5High:
|
||||
if 0xff61 <= r && r < 0xffa0 {
|
||||
r -= 0xff61 - 0xa1
|
||||
goto write1
|
||||
}
|
||||
if r = rune(encode5[r-encode5Low]); r>>tableShift == jis0208 {
|
||||
goto write2
|
||||
}
|
||||
}
|
||||
err = internal.ErrASCIIReplacement
|
||||
break
|
||||
}
|
||||
|
||||
write1:
|
||||
if nDst >= len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst] = uint8(r)
|
||||
nDst++
|
||||
continue
|
||||
|
||||
write2:
|
||||
j1 := uint8(r>>codeShift) & codeMask
|
||||
j2 := uint8(r) & codeMask
|
||||
if nDst+2 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break loop
|
||||
}
|
||||
if j1 <= 61 {
|
||||
dst[nDst+0] = 129 + j1/2
|
||||
} else {
|
||||
dst[nDst+0] = 193 + j1/2
|
||||
}
|
||||
if j1&1 == 0 {
|
||||
dst[nDst+1] = j2 + j2/63 + 64
|
||||
} else {
|
||||
dst[nDst+1] = j2 + 159
|
||||
}
|
||||
nDst += 2
|
||||
continue
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
26971
vendor/golang.org/x/text/encoding/japanese/tables.go
generated
vendored
Normal file
26971
vendor/golang.org/x/text/encoding/japanese/tables.go
generated
vendored
Normal file
File diff suppressed because it is too large
Load diff
177
vendor/golang.org/x/text/encoding/korean/euckr.go
generated
vendored
Normal file
177
vendor/golang.org/x/text/encoding/korean/euckr.go
generated
vendored
Normal file
|
|
@ -0,0 +1,177 @@
|
|||
// 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 korean
|
||||
|
||||
import (
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/text/encoding"
|
||||
"golang.org/x/text/encoding/internal"
|
||||
"golang.org/x/text/encoding/internal/identifier"
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// All is a list of all defined encodings in this package.
|
||||
var All = []encoding.Encoding{EUCKR}
|
||||
|
||||
// EUCKR is the EUC-KR encoding, also known as Code Page 949.
|
||||
var EUCKR encoding.Encoding = &eucKR
|
||||
|
||||
var eucKR = internal.Encoding{
|
||||
&internal.SimpleEncoding{eucKRDecoder{}, eucKREncoder{}},
|
||||
"EUC-KR",
|
||||
identifier.EUCKR,
|
||||
}
|
||||
|
||||
type eucKRDecoder struct{ transform.NopResetter }
|
||||
|
||||
func (eucKRDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
r, size := rune(0), 0
|
||||
loop:
|
||||
for ; nSrc < len(src); nSrc += size {
|
||||
switch c0 := src[nSrc]; {
|
||||
case c0 < utf8.RuneSelf:
|
||||
r, size = rune(c0), 1
|
||||
|
||||
case 0x81 <= c0 && c0 < 0xff:
|
||||
if nSrc+1 >= len(src) {
|
||||
if !atEOF {
|
||||
err = transform.ErrShortSrc
|
||||
break loop
|
||||
}
|
||||
r, size = utf8.RuneError, 1
|
||||
break
|
||||
}
|
||||
c1 := src[nSrc+1]
|
||||
size = 2
|
||||
if c0 < 0xc7 {
|
||||
r = 178 * rune(c0-0x81)
|
||||
switch {
|
||||
case 0x41 <= c1 && c1 < 0x5b:
|
||||
r += rune(c1) - (0x41 - 0*26)
|
||||
case 0x61 <= c1 && c1 < 0x7b:
|
||||
r += rune(c1) - (0x61 - 1*26)
|
||||
case 0x81 <= c1 && c1 < 0xff:
|
||||
r += rune(c1) - (0x81 - 2*26)
|
||||
default:
|
||||
goto decError
|
||||
}
|
||||
} else if 0xa1 <= c1 && c1 < 0xff {
|
||||
r = 178*(0xc7-0x81) + rune(c0-0xc7)*94 + rune(c1-0xa1)
|
||||
} else {
|
||||
goto decError
|
||||
}
|
||||
if int(r) < len(decode) {
|
||||
r = rune(decode[r])
|
||||
if r != 0 {
|
||||
break
|
||||
}
|
||||
}
|
||||
decError:
|
||||
r = utf8.RuneError
|
||||
if c1 < utf8.RuneSelf {
|
||||
size = 1
|
||||
}
|
||||
|
||||
default:
|
||||
r, size = utf8.RuneError, 1
|
||||
break
|
||||
}
|
||||
|
||||
if nDst+utf8.RuneLen(r) > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
nDst += utf8.EncodeRune(dst[nDst:], r)
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
type eucKREncoder struct{ transform.NopResetter }
|
||||
|
||||
func (eucKREncoder) 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
|
||||
|
||||
if nDst >= len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst] = uint8(r)
|
||||
nDst++
|
||||
continue
|
||||
|
||||
} 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
|
||||
}
|
||||
}
|
||||
|
||||
// func init checks that the switch covers all tables.
|
||||
switch {
|
||||
case encode0Low <= r && r < encode0High:
|
||||
if r = rune(encode0[r-encode0Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode1Low <= r && r < encode1High:
|
||||
if r = rune(encode1[r-encode1Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode2Low <= r && r < encode2High:
|
||||
if r = rune(encode2[r-encode2Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode3Low <= r && r < encode3High:
|
||||
if r = rune(encode3[r-encode3Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode4Low <= r && r < encode4High:
|
||||
if r = rune(encode4[r-encode4Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode5Low <= r && r < encode5High:
|
||||
if r = rune(encode5[r-encode5Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode6Low <= r && r < encode6High:
|
||||
if r = rune(encode6[r-encode6Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
}
|
||||
err = internal.ErrASCIIReplacement
|
||||
break
|
||||
}
|
||||
|
||||
write2:
|
||||
if nDst+2 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst+0] = uint8(r >> 8)
|
||||
dst[nDst+1] = uint8(r)
|
||||
nDst += 2
|
||||
continue
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
func init() {
|
||||
// Check that the hard-coded encode switch covers all tables.
|
||||
if numEncodeTables != 7 {
|
||||
panic("bad numEncodeTables")
|
||||
}
|
||||
}
|
||||
143
vendor/golang.org/x/text/encoding/korean/maketables.go
generated
vendored
Normal file
143
vendor/golang.org/x/text/encoding/korean/maketables.go
generated
vendored
Normal file
|
|
@ -0,0 +1,143 @@
|
|||
// 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] }
|
||||
34152
vendor/golang.org/x/text/encoding/korean/tables.go
generated
vendored
Normal file
34152
vendor/golang.org/x/text/encoding/korean/tables.go
generated
vendored
Normal file
File diff suppressed because it is too large
Load diff
12
vendor/golang.org/x/text/encoding/simplifiedchinese/all.go
generated
vendored
Normal file
12
vendor/golang.org/x/text/encoding/simplifiedchinese/all.go
generated
vendored
Normal file
|
|
@ -0,0 +1,12 @@
|
|||
// 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 simplifiedchinese
|
||||
|
||||
import (
|
||||
"golang.org/x/text/encoding"
|
||||
)
|
||||
|
||||
// All is a list of all defined encodings in this package.
|
||||
var All = []encoding.Encoding{GB18030, GBK, HZGB2312}
|
||||
269
vendor/golang.org/x/text/encoding/simplifiedchinese/gbk.go
generated
vendored
Normal file
269
vendor/golang.org/x/text/encoding/simplifiedchinese/gbk.go
generated
vendored
Normal file
|
|
@ -0,0 +1,269 @@
|
|||
// 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 simplifiedchinese
|
||||
|
||||
import (
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/text/encoding"
|
||||
"golang.org/x/text/encoding/internal"
|
||||
"golang.org/x/text/encoding/internal/identifier"
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
var (
|
||||
// GB18030 is the GB18030 encoding.
|
||||
GB18030 encoding.Encoding = &gbk18030
|
||||
// GBK is the GBK encoding. It encodes an extension of the GB2312 character set
|
||||
// and is also known as Code Page 936.
|
||||
GBK encoding.Encoding = &gbk
|
||||
)
|
||||
|
||||
var gbk = internal.Encoding{
|
||||
&internal.SimpleEncoding{
|
||||
gbkDecoder{gb18030: false},
|
||||
gbkEncoder{gb18030: false},
|
||||
},
|
||||
"GBK",
|
||||
identifier.GBK,
|
||||
}
|
||||
|
||||
var gbk18030 = internal.Encoding{
|
||||
&internal.SimpleEncoding{
|
||||
gbkDecoder{gb18030: true},
|
||||
gbkEncoder{gb18030: true},
|
||||
},
|
||||
"GB18030",
|
||||
identifier.GB18030,
|
||||
}
|
||||
|
||||
type gbkDecoder struct {
|
||||
transform.NopResetter
|
||||
gb18030 bool
|
||||
}
|
||||
|
||||
func (d gbkDecoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
r, size := rune(0), 0
|
||||
loop:
|
||||
for ; nSrc < len(src); nSrc += size {
|
||||
switch c0 := src[nSrc]; {
|
||||
case c0 < utf8.RuneSelf:
|
||||
r, size = rune(c0), 1
|
||||
|
||||
// Microsoft's Code Page 936 extends GBK 1.0 to encode the euro sign U+20AC
|
||||
// as 0x80. The HTML5 specification at http://encoding.spec.whatwg.org/#gbk
|
||||
// says to treat "gbk" as Code Page 936.
|
||||
case c0 == 0x80:
|
||||
r, size = '€', 1
|
||||
|
||||
case c0 < 0xff:
|
||||
if nSrc+1 >= len(src) {
|
||||
if !atEOF {
|
||||
err = transform.ErrShortSrc
|
||||
break loop
|
||||
}
|
||||
r, size = utf8.RuneError, 1
|
||||
goto write
|
||||
}
|
||||
c1 := src[nSrc+1]
|
||||
switch {
|
||||
case 0x40 <= c1 && c1 < 0x7f:
|
||||
c1 -= 0x40
|
||||
case 0x80 <= c1 && c1 < 0xff:
|
||||
c1 -= 0x41
|
||||
case d.gb18030 && 0x30 <= c1 && c1 < 0x40:
|
||||
if nSrc+3 >= len(src) {
|
||||
if !atEOF {
|
||||
err = transform.ErrShortSrc
|
||||
break loop
|
||||
}
|
||||
// The second byte here is always ASCII, so we can set size
|
||||
// to 1 in all cases.
|
||||
r, size = utf8.RuneError, 1
|
||||
goto write
|
||||
}
|
||||
c2 := src[nSrc+2]
|
||||
if c2 < 0x81 || 0xff <= c2 {
|
||||
r, size = utf8.RuneError, 1
|
||||
goto write
|
||||
}
|
||||
c3 := src[nSrc+3]
|
||||
if c3 < 0x30 || 0x3a <= c3 {
|
||||
r, size = utf8.RuneError, 1
|
||||
goto write
|
||||
}
|
||||
size = 4
|
||||
r = ((rune(c0-0x81)*10+rune(c1-0x30))*126+rune(c2-0x81))*10 + rune(c3-0x30)
|
||||
if r < 39420 {
|
||||
i, j := 0, len(gb18030)
|
||||
for i < j {
|
||||
h := i + (j-i)/2
|
||||
if r >= rune(gb18030[h][0]) {
|
||||
i = h + 1
|
||||
} else {
|
||||
j = h
|
||||
}
|
||||
}
|
||||
dec := &gb18030[i-1]
|
||||
r += rune(dec[1]) - rune(dec[0])
|
||||
goto write
|
||||
}
|
||||
r -= 189000
|
||||
if 0 <= r && r < 0x100000 {
|
||||
r += 0x10000
|
||||
} else {
|
||||
r, size = utf8.RuneError, 1
|
||||
}
|
||||
goto write
|
||||
default:
|
||||
r, size = utf8.RuneError, 1
|
||||
goto write
|
||||
}
|
||||
r, size = '\ufffd', 2
|
||||
if i := int(c0-0x81)*190 + int(c1); i < len(decode) {
|
||||
r = rune(decode[i])
|
||||
if r == 0 {
|
||||
r = '\ufffd'
|
||||
}
|
||||
}
|
||||
|
||||
default:
|
||||
r, size = utf8.RuneError, 1
|
||||
}
|
||||
|
||||
write:
|
||||
if nDst+utf8.RuneLen(r) > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break loop
|
||||
}
|
||||
nDst += utf8.EncodeRune(dst[nDst:], r)
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
type gbkEncoder struct {
|
||||
transform.NopResetter
|
||||
gb18030 bool
|
||||
}
|
||||
|
||||
func (e gbkEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
r, r2, size := rune(0), 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
|
||||
}
|
||||
}
|
||||
|
||||
// func init checks that the switch covers all tables.
|
||||
switch {
|
||||
case encode0Low <= r && r < encode0High:
|
||||
if r2 = rune(encode0[r-encode0Low]); r2 != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode1Low <= r && r < encode1High:
|
||||
// Microsoft's Code Page 936 extends GBK 1.0 to encode the euro sign U+20AC
|
||||
// as 0x80. The HTML5 specification at http://encoding.spec.whatwg.org/#gbk
|
||||
// says to treat "gbk" as Code Page 936.
|
||||
if r == '€' {
|
||||
r = 0x80
|
||||
goto write1
|
||||
}
|
||||
if r2 = rune(encode1[r-encode1Low]); r2 != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode2Low <= r && r < encode2High:
|
||||
if r2 = rune(encode2[r-encode2Low]); r2 != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode3Low <= r && r < encode3High:
|
||||
if r2 = rune(encode3[r-encode3Low]); r2 != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode4Low <= r && r < encode4High:
|
||||
if r2 = rune(encode4[r-encode4Low]); r2 != 0 {
|
||||
goto write2
|
||||
}
|
||||
}
|
||||
|
||||
if e.gb18030 {
|
||||
if r < 0x10000 {
|
||||
i, j := 0, len(gb18030)
|
||||
for i < j {
|
||||
h := i + (j-i)/2
|
||||
if r >= rune(gb18030[h][1]) {
|
||||
i = h + 1
|
||||
} else {
|
||||
j = h
|
||||
}
|
||||
}
|
||||
dec := &gb18030[i-1]
|
||||
r += rune(dec[0]) - rune(dec[1])
|
||||
goto write4
|
||||
} else if r < 0x110000 {
|
||||
r += 189000 - 0x10000
|
||||
goto write4
|
||||
}
|
||||
}
|
||||
err = internal.ErrASCIIReplacement
|
||||
break
|
||||
}
|
||||
|
||||
write1:
|
||||
if nDst >= len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst] = uint8(r)
|
||||
nDst++
|
||||
continue
|
||||
|
||||
write2:
|
||||
if nDst+2 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst+0] = uint8(r2 >> 8)
|
||||
dst[nDst+1] = uint8(r2)
|
||||
nDst += 2
|
||||
continue
|
||||
|
||||
write4:
|
||||
if nDst+4 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst+3] = uint8(r%10 + 0x30)
|
||||
r /= 10
|
||||
dst[nDst+2] = uint8(r%126 + 0x81)
|
||||
r /= 126
|
||||
dst[nDst+1] = uint8(r%10 + 0x30)
|
||||
r /= 10
|
||||
dst[nDst+0] = uint8(r + 0x81)
|
||||
nDst += 4
|
||||
continue
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
func init() {
|
||||
// Check that the hard-coded encode switch covers all tables.
|
||||
if numEncodeTables != 5 {
|
||||
panic("bad numEncodeTables")
|
||||
}
|
||||
}
|
||||
245
vendor/golang.org/x/text/encoding/simplifiedchinese/hzgb2312.go
generated
vendored
Normal file
245
vendor/golang.org/x/text/encoding/simplifiedchinese/hzgb2312.go
generated
vendored
Normal file
|
|
@ -0,0 +1,245 @@
|
|||
// 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 simplifiedchinese
|
||||
|
||||
import (
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/text/encoding"
|
||||
"golang.org/x/text/encoding/internal"
|
||||
"golang.org/x/text/encoding/internal/identifier"
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// HZGB2312 is the HZ-GB2312 encoding.
|
||||
var HZGB2312 encoding.Encoding = &hzGB2312
|
||||
|
||||
var hzGB2312 = internal.Encoding{
|
||||
internal.FuncEncoding{hzGB2312NewDecoder, hzGB2312NewEncoder},
|
||||
"HZ-GB2312",
|
||||
identifier.HZGB2312,
|
||||
}
|
||||
|
||||
func hzGB2312NewDecoder() transform.Transformer {
|
||||
return new(hzGB2312Decoder)
|
||||
}
|
||||
|
||||
func hzGB2312NewEncoder() transform.Transformer {
|
||||
return new(hzGB2312Encoder)
|
||||
}
|
||||
|
||||
const (
|
||||
asciiState = iota
|
||||
gbState
|
||||
)
|
||||
|
||||
type hzGB2312Decoder int
|
||||
|
||||
func (d *hzGB2312Decoder) Reset() {
|
||||
*d = asciiState
|
||||
}
|
||||
|
||||
func (d *hzGB2312Decoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
r, size := rune(0), 0
|
||||
loop:
|
||||
for ; nSrc < len(src); nSrc += size {
|
||||
c0 := src[nSrc]
|
||||
if c0 >= utf8.RuneSelf {
|
||||
r, size = utf8.RuneError, 1
|
||||
goto write
|
||||
}
|
||||
|
||||
if c0 == '~' {
|
||||
if nSrc+1 >= len(src) {
|
||||
if !atEOF {
|
||||
err = transform.ErrShortSrc
|
||||
break loop
|
||||
}
|
||||
r = utf8.RuneError
|
||||
goto write
|
||||
}
|
||||
size = 2
|
||||
switch src[nSrc+1] {
|
||||
case '{':
|
||||
*d = gbState
|
||||
continue
|
||||
case '}':
|
||||
*d = asciiState
|
||||
continue
|
||||
case '~':
|
||||
if nDst >= len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break loop
|
||||
}
|
||||
dst[nDst] = '~'
|
||||
nDst++
|
||||
continue
|
||||
case '\n':
|
||||
continue
|
||||
default:
|
||||
r = utf8.RuneError
|
||||
goto write
|
||||
}
|
||||
}
|
||||
|
||||
if *d == asciiState {
|
||||
r, size = rune(c0), 1
|
||||
} else {
|
||||
if nSrc+1 >= len(src) {
|
||||
if !atEOF {
|
||||
err = transform.ErrShortSrc
|
||||
break loop
|
||||
}
|
||||
r, size = utf8.RuneError, 1
|
||||
goto write
|
||||
}
|
||||
size = 2
|
||||
c1 := src[nSrc+1]
|
||||
if c0 < 0x21 || 0x7e <= c0 || c1 < 0x21 || 0x7f <= c1 {
|
||||
// error
|
||||
} else if i := int(c0-0x01)*190 + int(c1+0x3f); i < len(decode) {
|
||||
r = rune(decode[i])
|
||||
if r != 0 {
|
||||
goto write
|
||||
}
|
||||
}
|
||||
if c1 > utf8.RuneSelf {
|
||||
// Be consistent and always treat non-ASCII as a single error.
|
||||
size = 1
|
||||
}
|
||||
r = utf8.RuneError
|
||||
}
|
||||
|
||||
write:
|
||||
if nDst+utf8.RuneLen(r) > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break loop
|
||||
}
|
||||
nDst += utf8.EncodeRune(dst[nDst:], r)
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
type hzGB2312Encoder int
|
||||
|
||||
func (d *hzGB2312Encoder) Reset() {
|
||||
*d = asciiState
|
||||
}
|
||||
|
||||
func (e *hzGB2312Encoder) 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
|
||||
if r == '~' {
|
||||
if nDst+2 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst+0] = '~'
|
||||
dst[nDst+1] = '~'
|
||||
nDst += 2
|
||||
continue
|
||||
} else if *e != asciiState {
|
||||
if nDst+3 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
*e = asciiState
|
||||
dst[nDst+0] = '~'
|
||||
dst[nDst+1] = '}'
|
||||
nDst += 2
|
||||
} else if nDst >= len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst] = uint8(r)
|
||||
nDst += 1
|
||||
continue
|
||||
|
||||
}
|
||||
|
||||
// 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
|
||||
}
|
||||
}
|
||||
|
||||
// func init checks that the switch covers all tables.
|
||||
switch {
|
||||
case encode0Low <= r && r < encode0High:
|
||||
if r = rune(encode0[r-encode0Low]); r != 0 {
|
||||
goto writeGB
|
||||
}
|
||||
case encode1Low <= r && r < encode1High:
|
||||
if r = rune(encode1[r-encode1Low]); r != 0 {
|
||||
goto writeGB
|
||||
}
|
||||
case encode2Low <= r && r < encode2High:
|
||||
if r = rune(encode2[r-encode2Low]); r != 0 {
|
||||
goto writeGB
|
||||
}
|
||||
case encode3Low <= r && r < encode3High:
|
||||
if r = rune(encode3[r-encode3Low]); r != 0 {
|
||||
goto writeGB
|
||||
}
|
||||
case encode4Low <= r && r < encode4High:
|
||||
if r = rune(encode4[r-encode4Low]); r != 0 {
|
||||
goto writeGB
|
||||
}
|
||||
}
|
||||
|
||||
terminateInASCIIState:
|
||||
// Switch back to ASCII state in case of error so that an ASCII
|
||||
// replacement character can be written in the correct state.
|
||||
if *e != asciiState {
|
||||
if nDst+2 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst+0] = '~'
|
||||
dst[nDst+1] = '}'
|
||||
nDst += 2
|
||||
}
|
||||
err = internal.ErrASCIIReplacement
|
||||
break
|
||||
|
||||
writeGB:
|
||||
c0 := uint8(r>>8) - 0x80
|
||||
c1 := uint8(r) - 0x80
|
||||
if c0 < 0x21 || 0x7e <= c0 || c1 < 0x21 || 0x7f <= c1 {
|
||||
goto terminateInASCIIState
|
||||
}
|
||||
if *e == asciiState {
|
||||
if nDst+4 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
*e = gbState
|
||||
dst[nDst+0] = '~'
|
||||
dst[nDst+1] = '{'
|
||||
nDst += 2
|
||||
} else if nDst+2 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst+0] = c0
|
||||
dst[nDst+1] = c1
|
||||
nDst += 2
|
||||
continue
|
||||
}
|
||||
// TODO: should one always terminate in ASCII state to make it safe to
|
||||
// concatenate two HZ-GB2312-encoded strings?
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
161
vendor/golang.org/x/text/encoding/simplifiedchinese/maketables.go
generated
vendored
Normal file
161
vendor/golang.org/x/text/encoding/simplifiedchinese/maketables.go
generated
vendored
Normal file
|
|
@ -0,0 +1,161 @@
|
|||
// Copyright 2013 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +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] }
|
||||
43999
vendor/golang.org/x/text/encoding/simplifiedchinese/tables.go
generated
vendored
Normal file
43999
vendor/golang.org/x/text/encoding/simplifiedchinese/tables.go
generated
vendored
Normal file
File diff suppressed because it is too large
Load diff
199
vendor/golang.org/x/text/encoding/traditionalchinese/big5.go
generated
vendored
Normal file
199
vendor/golang.org/x/text/encoding/traditionalchinese/big5.go
generated
vendored
Normal file
|
|
@ -0,0 +1,199 @@
|
|||
// 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 traditionalchinese
|
||||
|
||||
import (
|
||||
"unicode/utf8"
|
||||
|
||||
"golang.org/x/text/encoding"
|
||||
"golang.org/x/text/encoding/internal"
|
||||
"golang.org/x/text/encoding/internal/identifier"
|
||||
"golang.org/x/text/transform"
|
||||
)
|
||||
|
||||
// All is a list of all defined encodings in this package.
|
||||
var All = []encoding.Encoding{Big5}
|
||||
|
||||
// Big5 is the Big5 encoding, also known as Code Page 950.
|
||||
var Big5 encoding.Encoding = &big5
|
||||
|
||||
var big5 = internal.Encoding{
|
||||
&internal.SimpleEncoding{big5Decoder{}, big5Encoder{}},
|
||||
"Big5",
|
||||
identifier.Big5,
|
||||
}
|
||||
|
||||
type big5Decoder struct{ transform.NopResetter }
|
||||
|
||||
func (big5Decoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
|
||||
r, size, s := rune(0), 0, ""
|
||||
loop:
|
||||
for ; nSrc < len(src); nSrc += size {
|
||||
switch c0 := src[nSrc]; {
|
||||
case c0 < utf8.RuneSelf:
|
||||
r, size = rune(c0), 1
|
||||
|
||||
case 0x81 <= c0 && c0 < 0xff:
|
||||
if nSrc+1 >= len(src) {
|
||||
if !atEOF {
|
||||
err = transform.ErrShortSrc
|
||||
break loop
|
||||
}
|
||||
r, size = utf8.RuneError, 1
|
||||
goto write
|
||||
}
|
||||
c1 := src[nSrc+1]
|
||||
switch {
|
||||
case 0x40 <= c1 && c1 < 0x7f:
|
||||
c1 -= 0x40
|
||||
case 0xa1 <= c1 && c1 < 0xff:
|
||||
c1 -= 0x62
|
||||
case c1 < 0x40:
|
||||
r, size = utf8.RuneError, 1
|
||||
goto write
|
||||
default:
|
||||
r, size = utf8.RuneError, 2
|
||||
goto write
|
||||
}
|
||||
r, size = '\ufffd', 2
|
||||
if i := int(c0-0x81)*157 + int(c1); i < len(decode) {
|
||||
if 1133 <= i && i < 1167 {
|
||||
// The two-rune special cases for LATIN CAPITAL / SMALL E WITH CIRCUMFLEX
|
||||
// AND MACRON / CARON are from http://encoding.spec.whatwg.org/#big5
|
||||
switch i {
|
||||
case 1133:
|
||||
s = "\u00CA\u0304"
|
||||
goto writeStr
|
||||
case 1135:
|
||||
s = "\u00CA\u030C"
|
||||
goto writeStr
|
||||
case 1164:
|
||||
s = "\u00EA\u0304"
|
||||
goto writeStr
|
||||
case 1166:
|
||||
s = "\u00EA\u030C"
|
||||
goto writeStr
|
||||
}
|
||||
}
|
||||
r = rune(decode[i])
|
||||
if r == 0 {
|
||||
r = '\ufffd'
|
||||
}
|
||||
}
|
||||
|
||||
default:
|
||||
r, size = utf8.RuneError, 1
|
||||
}
|
||||
|
||||
write:
|
||||
if nDst+utf8.RuneLen(r) > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break loop
|
||||
}
|
||||
nDst += utf8.EncodeRune(dst[nDst:], r)
|
||||
continue loop
|
||||
|
||||
writeStr:
|
||||
if nDst+len(s) > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break loop
|
||||
}
|
||||
nDst += copy(dst[nDst:], s)
|
||||
continue loop
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
type big5Encoder struct{ transform.NopResetter }
|
||||
|
||||
func (big5Encoder) 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
|
||||
if nDst >= len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst] = uint8(r)
|
||||
nDst++
|
||||
continue
|
||||
|
||||
} 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 >= utf8.RuneSelf {
|
||||
// func init checks that the switch covers all tables.
|
||||
switch {
|
||||
case encode0Low <= r && r < encode0High:
|
||||
if r = rune(encode0[r-encode0Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode1Low <= r && r < encode1High:
|
||||
if r = rune(encode1[r-encode1Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode2Low <= r && r < encode2High:
|
||||
if r = rune(encode2[r-encode2Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode3Low <= r && r < encode3High:
|
||||
if r = rune(encode3[r-encode3Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode4Low <= r && r < encode4High:
|
||||
if r = rune(encode4[r-encode4Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode5Low <= r && r < encode5High:
|
||||
if r = rune(encode5[r-encode5Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode6Low <= r && r < encode6High:
|
||||
if r = rune(encode6[r-encode6Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
case encode7Low <= r && r < encode7High:
|
||||
if r = rune(encode7[r-encode7Low]); r != 0 {
|
||||
goto write2
|
||||
}
|
||||
}
|
||||
err = internal.ErrASCIIReplacement
|
||||
break
|
||||
}
|
||||
|
||||
write2:
|
||||
if nDst+2 > len(dst) {
|
||||
err = transform.ErrShortDst
|
||||
break
|
||||
}
|
||||
dst[nDst+0] = uint8(r >> 8)
|
||||
dst[nDst+1] = uint8(r)
|
||||
nDst += 2
|
||||
continue
|
||||
}
|
||||
return nDst, nSrc, err
|
||||
}
|
||||
|
||||
func init() {
|
||||
// Check that the hard-coded encode switch covers all tables.
|
||||
if numEncodeTables != 8 {
|
||||
panic("bad numEncodeTables")
|
||||
}
|
||||
}
|
||||
140
vendor/golang.org/x/text/encoding/traditionalchinese/maketables.go
generated
vendored
Normal file
140
vendor/golang.org/x/text/encoding/traditionalchinese/maketables.go
generated
vendored
Normal file
|
|
@ -0,0 +1,140 @@
|
|||
// 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] }
|
||||
37142
vendor/golang.org/x/text/encoding/traditionalchinese/tables.go
generated
vendored
Normal file
37142
vendor/golang.org/x/text/encoding/traditionalchinese/tables.go
generated
vendored
Normal file
File diff suppressed because it is too large
Load diff
82
vendor/golang.org/x/text/encoding/unicode/override.go
generated
vendored
Normal file
82
vendor/golang.org/x/text/encoding/unicode/override.go
generated
vendored
Normal file
|
|
@ -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
|
||||
}
|
||||
434
vendor/golang.org/x/text/encoding/unicode/unicode.go
generated
vendored
Normal file
434
vendor/golang.org/x/text/encoding/unicode/unicode.go
generated
vendored
Normal file
|
|
@ -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 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".
|
||||
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
|
||||
}
|
||||
87
vendor/golang.org/x/text/internal/utf8internal/utf8internal.go
generated
vendored
Normal file
87
vendor/golang.org/x/text/internal/utf8internal/utf8internal.go
generated
vendored
Normal file
|
|
@ -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},
|
||||
}
|
||||
187
vendor/golang.org/x/text/runes/cond.go
generated
vendored
Normal file
187
vendor/golang.org/x/text/runes/cond.go
generated
vendored
Normal file
|
|
@ -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
|
||||
}
|
||||
355
vendor/golang.org/x/text/runes/runes.go
generated
vendored
Normal file
355
vendor/golang.org/x/text/runes/runes.go
generated
vendored
Normal file
|
|
@ -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
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue