vendor x/net/html
This commit is contained in:
James Bardin
Martin Atkins
parent
55d5e8a689
commit
190d5fae76
|
|
@ -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)
|
||||
}
|
||||
|
|
@ -0,0 +1,648 @@
|
|||
// 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
|
||||
|
||||
package main
|
||||
|
||||
// This program generates table.go and table_test.go.
|
||||
// Invoke as
|
||||
//
|
||||
// go run gen.go |gofmt >table.go
|
||||
// go run gen.go -test |gofmt >table_test.go
|
||||
|
||||
import (
|
||||
"flag"
|
||||
"fmt"
|
||||
"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 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)
|
||||
|
||||
if *test {
|
||||
fmt.Printf("// generated by go run gen.go -test; DO NOT EDIT\n\n")
|
||||
fmt.Printf("package atom\n\n")
|
||||
fmt.Printf("var testAtomList = []string{\n")
|
||||
for _, s := range all {
|
||||
fmt.Printf("\t%q,\n", s)
|
||||
}
|
||||
fmt.Printf("}\n")
|
||||
return
|
||||
}
|
||||
|
||||
// uniq - lists have dups
|
||||
// compute max len too
|
||||
maxLen := 0
|
||||
w := 0
|
||||
for _, s := range all {
|
||||
if w == 0 || all[w-1] != s {
|
||||
if maxLen < len(s) {
|
||||
maxLen = len(s)
|
||||
}
|
||||
all[w] = s
|
||||
w++
|
||||
}
|
||||
}
|
||||
all = all[:w]
|
||||
|
||||
// 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))
|
||||
}
|
||||
|
||||
// Generate the Go code.
|
||||
fmt.Printf("// generated by go run gen.go; DO NOT EDIT\n\n")
|
||||
fmt.Printf("package atom\n\nconst (\n")
|
||||
for _, s := range all {
|
||||
fmt.Printf("\t%s Atom = %#x\n", identifier(s), atom[s])
|
||||
}
|
||||
fmt.Printf(")\n\n")
|
||||
|
||||
fmt.Printf("const hash0 = %#x\n\n", best.h0)
|
||||
fmt.Printf("const maxAtomLen = %d\n\n", maxLen)
|
||||
|
||||
fmt.Printf("var table = [1<<%d]Atom{\n", best.k)
|
||||
for i, s := range best.tab {
|
||||
if s == "" {
|
||||
continue
|
||||
}
|
||||
fmt.Printf("\t%#x: %#x, // %s\n", i, atom[s], s)
|
||||
}
|
||||
fmt.Printf("}\n")
|
||||
datasize := (1 << best.k) * 4
|
||||
|
||||
fmt.Printf("const atomText =\n")
|
||||
textsize := len(text)
|
||||
for len(text) > 60 {
|
||||
fmt.Printf("\t%q +\n", text[:60])
|
||||
text = text[60:]
|
||||
}
|
||||
fmt.Printf("\t%q\n\n", text)
|
||||
|
||||
fmt.Fprintf(os.Stderr, "%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 21 February 2015" version.
|
||||
|
||||
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",
|
||||
"map",
|
||||
"mark",
|
||||
"menu",
|
||||
"menuitem",
|
||||
"meta",
|
||||
"meter",
|
||||
"nav",
|
||||
"noscript",
|
||||
"object",
|
||||
"ol",
|
||||
"optgroup",
|
||||
"option",
|
||||
"output",
|
||||
"p",
|
||||
"param",
|
||||
"pre",
|
||||
"progress",
|
||||
"q",
|
||||
"rp",
|
||||
"rt",
|
||||
"ruby",
|
||||
"s",
|
||||
"samp",
|
||||
"script",
|
||||
"section",
|
||||
"select",
|
||||
"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
|
||||
|
||||
var attributes = []string{
|
||||
"abbr",
|
||||
"accept",
|
||||
"accept-charset",
|
||||
"accesskey",
|
||||
"action",
|
||||
"alt",
|
||||
"async",
|
||||
"autocomplete",
|
||||
"autofocus",
|
||||
"autoplay",
|
||||
"challenge",
|
||||
"charset",
|
||||
"checked",
|
||||
"cite",
|
||||
"class",
|
||||
"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",
|
||||
"ismap",
|
||||
"itemid",
|
||||
"itemprop",
|
||||
"itemref",
|
||||
"itemscope",
|
||||
"itemtype",
|
||||
"keytype",
|
||||
"kind",
|
||||
"label",
|
||||
"lang",
|
||||
"list",
|
||||
"loop",
|
||||
"low",
|
||||
"manifest",
|
||||
"max",
|
||||
"maxlength",
|
||||
"media",
|
||||
"mediagroup",
|
||||
"method",
|
||||
"min",
|
||||
"minlength",
|
||||
"multiple",
|
||||
"muted",
|
||||
"name",
|
||||
"novalidate",
|
||||
"open",
|
||||
"optimum",
|
||||
"pattern",
|
||||
"ping",
|
||||
"placeholder",
|
||||
"poster",
|
||||
"preload",
|
||||
"radiogroup",
|
||||
"readonly",
|
||||
"rel",
|
||||
"required",
|
||||
"reversed",
|
||||
"rows",
|
||||
"rowspan",
|
||||
"sandbox",
|
||||
"spellcheck",
|
||||
"scope",
|
||||
"scoped",
|
||||
"seamless",
|
||||
"selected",
|
||||
"shape",
|
||||
"size",
|
||||
"sizes",
|
||||
"sortable",
|
||||
"sorted",
|
||||
"span",
|
||||
"src",
|
||||
"srcdoc",
|
||||
"srclang",
|
||||
"start",
|
||||
"step",
|
||||
"style",
|
||||
"tabindex",
|
||||
"target",
|
||||
"title",
|
||||
"translate",
|
||||
"type",
|
||||
"typemustmatch",
|
||||
"usemap",
|
||||
"value",
|
||||
"width",
|
||||
"wrap",
|
||||
}
|
||||
|
||||
var eventHandlers = []string{
|
||||
"onabort",
|
||||
"onautocomplete",
|
||||
"onautocompleteerror",
|
||||
"onafterprint",
|
||||
"onbeforeprint",
|
||||
"onbeforeunload",
|
||||
"onblur",
|
||||
"oncancel",
|
||||
"oncanplay",
|
||||
"oncanplaythrough",
|
||||
"onchange",
|
||||
"onclick",
|
||||
"onclose",
|
||||
"oncontextmenu",
|
||||
"oncuechange",
|
||||
"ondblclick",
|
||||
"ondrag",
|
||||
"ondragend",
|
||||
"ondragenter",
|
||||
"ondragleave",
|
||||
"ondragover",
|
||||
"ondragstart",
|
||||
"ondrop",
|
||||
"ondurationchange",
|
||||
"onemptied",
|
||||
"onended",
|
||||
"onerror",
|
||||
"onfocus",
|
||||
"onhashchange",
|
||||
"oninput",
|
||||
"oninvalid",
|
||||
"onkeydown",
|
||||
"onkeypress",
|
||||
"onkeyup",
|
||||
"onlanguagechange",
|
||||
"onload",
|
||||
"onloadeddata",
|
||||
"onloadedmetadata",
|
||||
"onloadstart",
|
||||
"onmessage",
|
||||
"onmousedown",
|
||||
"onmousemove",
|
||||
"onmouseout",
|
||||
"onmouseover",
|
||||
"onmouseup",
|
||||
"onmousewheel",
|
||||
"onoffline",
|
||||
"ononline",
|
||||
"onpagehide",
|
||||
"onpageshow",
|
||||
"onpause",
|
||||
"onplay",
|
||||
"onplaying",
|
||||
"onpopstate",
|
||||
"onprogress",
|
||||
"onratechange",
|
||||
"onreset",
|
||||
"onresize",
|
||||
"onscroll",
|
||||
"onseeked",
|
||||
"onseeking",
|
||||
"onselect",
|
||||
"onshow",
|
||||
"onsort",
|
||||
"onstalled",
|
||||
"onstorage",
|
||||
"onsubmit",
|
||||
"onsuspend",
|
||||
"ontimeupdate",
|
||||
"ontoggle",
|
||||
"onunload",
|
||||
"onvolumechange",
|
||||
"onwaiting",
|
||||
}
|
||||
|
||||
// extra are ad-hoc values not covered by any of the lists above.
|
||||
var extra = []string{
|
||||
"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",
|
||||
"spacer",
|
||||
"strike",
|
||||
"svg",
|
||||
"system",
|
||||
"tt",
|
||||
"xmp",
|
||||
}
|
||||
|
|
@ -0,0 +1,713 @@
|
|||
// generated by go run gen.go; DO NOT EDIT
|
||||
|
||||
package atom
|
||||
|
||||
const (
|
||||
A Atom = 0x1
|
||||
Abbr Atom = 0x4
|
||||
Accept Atom = 0x2106
|
||||
AcceptCharset Atom = 0x210e
|
||||
Accesskey Atom = 0x3309
|
||||
Action Atom = 0x1f606
|
||||
Address Atom = 0x4f307
|
||||
Align Atom = 0x1105
|
||||
Alt Atom = 0x4503
|
||||
Annotation Atom = 0x1670a
|
||||
AnnotationXml Atom = 0x1670e
|
||||
Applet Atom = 0x2b306
|
||||
Area Atom = 0x2fa04
|
||||
Article Atom = 0x38807
|
||||
Aside Atom = 0x8305
|
||||
Async Atom = 0x7b05
|
||||
Audio Atom = 0xa605
|
||||
Autocomplete Atom = 0x1fc0c
|
||||
Autofocus Atom = 0xb309
|
||||
Autoplay Atom = 0xce08
|
||||
B Atom = 0x101
|
||||
Base Atom = 0xd604
|
||||
Basefont Atom = 0xd608
|
||||
Bdi Atom = 0x1a03
|
||||
Bdo Atom = 0xe703
|
||||
Bgsound Atom = 0x11807
|
||||
Big Atom = 0x12403
|
||||
Blink Atom = 0x12705
|
||||
Blockquote Atom = 0x12c0a
|
||||
Body Atom = 0x2f04
|
||||
Br Atom = 0x202
|
||||
Button Atom = 0x13606
|
||||
Canvas Atom = 0x7f06
|
||||
Caption Atom = 0x1bb07
|
||||
Center Atom = 0x5b506
|
||||
Challenge Atom = 0x21f09
|
||||
Charset Atom = 0x2807
|
||||
Checked Atom = 0x32807
|
||||
Cite Atom = 0x3c804
|
||||
Class Atom = 0x4de05
|
||||
Code Atom = 0x14904
|
||||
Col Atom = 0x15003
|
||||
Colgroup Atom = 0x15008
|
||||
Color Atom = 0x15d05
|
||||
Cols Atom = 0x16204
|
||||
Colspan Atom = 0x16207
|
||||
Command Atom = 0x17507
|
||||
Content Atom = 0x42307
|
||||
Contenteditable Atom = 0x4230f
|
||||
Contextmenu Atom = 0x3310b
|
||||
Controls Atom = 0x18808
|
||||
Coords Atom = 0x19406
|
||||
Crossorigin Atom = 0x19f0b
|
||||
Data Atom = 0x44a04
|
||||
Datalist Atom = 0x44a08
|
||||
Datetime Atom = 0x23c08
|
||||
Dd Atom = 0x26702
|
||||
Default Atom = 0x8607
|
||||
Defer Atom = 0x14b05
|
||||
Del Atom = 0x3ef03
|
||||
Desc Atom = 0x4db04
|
||||
Details Atom = 0x4807
|
||||
Dfn Atom = 0x6103
|
||||
Dialog Atom = 0x1b06
|
||||
Dir Atom = 0x6903
|
||||
Dirname Atom = 0x6907
|
||||
Disabled Atom = 0x10c08
|
||||
Div Atom = 0x11303
|
||||
Dl Atom = 0x11e02
|
||||
Download Atom = 0x40008
|
||||
Draggable Atom = 0x17b09
|
||||
Dropzone Atom = 0x39108
|
||||
Dt Atom = 0x50902
|
||||
Em Atom = 0x6502
|
||||
Embed Atom = 0x6505
|
||||
Enctype Atom = 0x21107
|
||||
Face Atom = 0x5b304
|
||||
Fieldset Atom = 0x1b008
|
||||
Figcaption Atom = 0x1b80a
|
||||
Figure Atom = 0x1cc06
|
||||
Font Atom = 0xda04
|
||||
Footer Atom = 0x8d06
|
||||
For Atom = 0x1d803
|
||||
ForeignObject Atom = 0x1d80d
|
||||
Foreignobject Atom = 0x1e50d
|
||||
Form Atom = 0x1f204
|
||||
Formaction Atom = 0x1f20a
|
||||
Formenctype Atom = 0x20d0b
|
||||
Formmethod Atom = 0x2280a
|
||||
Formnovalidate Atom = 0x2320e
|
||||
Formtarget Atom = 0x2470a
|
||||
Frame Atom = 0x9a05
|
||||
Frameset Atom = 0x9a08
|
||||
H1 Atom = 0x26e02
|
||||
H2 Atom = 0x29402
|
||||
H3 Atom = 0x2a702
|
||||
H4 Atom = 0x2e902
|
||||
H5 Atom = 0x2f302
|
||||
H6 Atom = 0x50b02
|
||||
Head Atom = 0x2d504
|
||||
Header Atom = 0x2d506
|
||||
Headers Atom = 0x2d507
|
||||
Height Atom = 0x25106
|
||||
Hgroup Atom = 0x25906
|
||||
Hidden Atom = 0x26506
|
||||
High Atom = 0x26b04
|
||||
Hr Atom = 0x27002
|
||||
Href Atom = 0x27004
|
||||
Hreflang Atom = 0x27008
|
||||
Html Atom = 0x25504
|
||||
HttpEquiv Atom = 0x2780a
|
||||
I Atom = 0x601
|
||||
Icon Atom = 0x42204
|
||||
Id Atom = 0x8502
|
||||
Iframe Atom = 0x29606
|
||||
Image Atom = 0x29c05
|
||||
Img Atom = 0x2a103
|
||||
Input Atom = 0x3e805
|
||||
Inputmode Atom = 0x3e809
|
||||
Ins Atom = 0x1a803
|
||||
Isindex Atom = 0x2a907
|
||||
Ismap Atom = 0x2b005
|
||||
Itemid Atom = 0x33c06
|
||||
Itemprop Atom = 0x3c908
|
||||
Itemref Atom = 0x5ad07
|
||||
Itemscope Atom = 0x2b909
|
||||
Itemtype Atom = 0x2c308
|
||||
Kbd Atom = 0x1903
|
||||
Keygen Atom = 0x3906
|
||||
Keytype Atom = 0x53707
|
||||
Kind Atom = 0x10904
|
||||
Label Atom = 0xf005
|
||||
Lang Atom = 0x27404
|
||||
Legend Atom = 0x18206
|
||||
Li Atom = 0x1202
|
||||
Link Atom = 0x12804
|
||||
List Atom = 0x44e04
|
||||
Listing Atom = 0x44e07
|
||||
Loop Atom = 0xf404
|
||||
Low Atom = 0x11f03
|
||||
Malignmark Atom = 0x100a
|
||||
Manifest Atom = 0x5f108
|
||||
Map Atom = 0x2b203
|
||||
Mark Atom = 0x1604
|
||||
Marquee Atom = 0x2cb07
|
||||
Math Atom = 0x2d204
|
||||
Max Atom = 0x2e103
|
||||
Maxlength Atom = 0x2e109
|
||||
Media Atom = 0x6e05
|
||||
Mediagroup Atom = 0x6e0a
|
||||
Menu Atom = 0x33804
|
||||
Menuitem Atom = 0x33808
|
||||
Meta Atom = 0x45d04
|
||||
Meter Atom = 0x24205
|
||||
Method Atom = 0x22c06
|
||||
Mglyph Atom = 0x2a206
|
||||
Mi Atom = 0x2eb02
|
||||
Min Atom = 0x2eb03
|
||||
Minlength Atom = 0x2eb09
|
||||
Mn Atom = 0x23502
|
||||
Mo Atom = 0x3ed02
|
||||
Ms Atom = 0x2bc02
|
||||
Mtext Atom = 0x2f505
|
||||
Multiple Atom = 0x30308
|
||||
Muted Atom = 0x30b05
|
||||
Name Atom = 0x6c04
|
||||
Nav Atom = 0x3e03
|
||||
Nobr Atom = 0x5704
|
||||
Noembed Atom = 0x6307
|
||||
Noframes Atom = 0x9808
|
||||
Noscript Atom = 0x3d208
|
||||
Novalidate Atom = 0x2360a
|
||||
Object Atom = 0x1ec06
|
||||
Ol Atom = 0xc902
|
||||
Onabort Atom = 0x13a07
|
||||
Onafterprint Atom = 0x1c00c
|
||||
Onautocomplete Atom = 0x1fa0e
|
||||
Onautocompleteerror Atom = 0x1fa13
|
||||
Onbeforeprint Atom = 0x6040d
|
||||
Onbeforeunload Atom = 0x4e70e
|
||||
Onblur Atom = 0xaa06
|
||||
Oncancel Atom = 0xe908
|
||||
Oncanplay Atom = 0x28509
|
||||
Oncanplaythrough Atom = 0x28510
|
||||
Onchange Atom = 0x3a708
|
||||
Onclick Atom = 0x31007
|
||||
Onclose Atom = 0x31707
|
||||
Oncontextmenu Atom = 0x32f0d
|
||||
Oncuechange Atom = 0x3420b
|
||||
Ondblclick Atom = 0x34d0a
|
||||
Ondrag Atom = 0x35706
|
||||
Ondragend Atom = 0x35709
|
||||
Ondragenter Atom = 0x3600b
|
||||
Ondragleave Atom = 0x36b0b
|
||||
Ondragover Atom = 0x3760a
|
||||
Ondragstart Atom = 0x3800b
|
||||
Ondrop Atom = 0x38f06
|
||||
Ondurationchange Atom = 0x39f10
|
||||
Onemptied Atom = 0x39609
|
||||
Onended Atom = 0x3af07
|
||||
Onerror Atom = 0x3b607
|
||||
Onfocus Atom = 0x3bd07
|
||||
Onhashchange Atom = 0x3da0c
|
||||
Oninput Atom = 0x3e607
|
||||
Oninvalid Atom = 0x3f209
|
||||
Onkeydown Atom = 0x3fb09
|
||||
Onkeypress Atom = 0x4080a
|
||||
Onkeyup Atom = 0x41807
|
||||
Onlanguagechange Atom = 0x43210
|
||||
Onload Atom = 0x44206
|
||||
Onloadeddata Atom = 0x4420c
|
||||
Onloadedmetadata Atom = 0x45510
|
||||
Onloadstart Atom = 0x46b0b
|
||||
Onmessage Atom = 0x47609
|
||||
Onmousedown Atom = 0x47f0b
|
||||
Onmousemove Atom = 0x48a0b
|
||||
Onmouseout Atom = 0x4950a
|
||||
Onmouseover Atom = 0x4a20b
|
||||
Onmouseup Atom = 0x4ad09
|
||||
Onmousewheel Atom = 0x4b60c
|
||||
Onoffline Atom = 0x4c209
|
||||
Ononline Atom = 0x4cb08
|
||||
Onpagehide Atom = 0x4d30a
|
||||
Onpageshow Atom = 0x4fe0a
|
||||
Onpause Atom = 0x50d07
|
||||
Onplay Atom = 0x51706
|
||||
Onplaying Atom = 0x51709
|
||||
Onpopstate Atom = 0x5200a
|
||||
Onprogress Atom = 0x52a0a
|
||||
Onratechange Atom = 0x53e0c
|
||||
Onreset Atom = 0x54a07
|
||||
Onresize Atom = 0x55108
|
||||
Onscroll Atom = 0x55f08
|
||||
Onseeked Atom = 0x56708
|
||||
Onseeking Atom = 0x56f09
|
||||
Onselect Atom = 0x57808
|
||||
Onshow Atom = 0x58206
|
||||
Onsort Atom = 0x58b06
|
||||
Onstalled Atom = 0x59509
|
||||
Onstorage Atom = 0x59e09
|
||||
Onsubmit Atom = 0x5a708
|
||||
Onsuspend Atom = 0x5bb09
|
||||
Ontimeupdate Atom = 0xdb0c
|
||||
Ontoggle Atom = 0x5c408
|
||||
Onunload Atom = 0x5cc08
|
||||
Onvolumechange Atom = 0x5d40e
|
||||
Onwaiting Atom = 0x5e209
|
||||
Open Atom = 0x3cf04
|
||||
Optgroup Atom = 0xf608
|
||||
Optimum Atom = 0x5eb07
|
||||
Option Atom = 0x60006
|
||||
Output Atom = 0x49c06
|
||||
P Atom = 0xc01
|
||||
Param Atom = 0xc05
|
||||
Pattern Atom = 0x5107
|
||||
Ping Atom = 0x7704
|
||||
Placeholder Atom = 0xc30b
|
||||
Plaintext Atom = 0xfd09
|
||||
Poster Atom = 0x15706
|
||||
Pre Atom = 0x25e03
|
||||
Preload Atom = 0x25e07
|
||||
Progress Atom = 0x52c08
|
||||
Prompt Atom = 0x5fa06
|
||||
Public Atom = 0x41e06
|
||||
Q Atom = 0x13101
|
||||
Radiogroup Atom = 0x30a
|
||||
Readonly Atom = 0x2fb08
|
||||
Rel Atom = 0x25f03
|
||||
Required Atom = 0x1d008
|
||||
Reversed Atom = 0x5a08
|
||||
Rows Atom = 0x9204
|
||||
Rowspan Atom = 0x9207
|
||||
Rp Atom = 0x1c602
|
||||
Rt Atom = 0x13f02
|
||||
Ruby Atom = 0xaf04
|
||||
S Atom = 0x2c01
|
||||
Samp Atom = 0x4e04
|
||||
Sandbox Atom = 0xbb07
|
||||
Scope Atom = 0x2bd05
|
||||
Scoped Atom = 0x2bd06
|
||||
Script Atom = 0x3d406
|
||||
Seamless Atom = 0x31c08
|
||||
Section Atom = 0x4e207
|
||||
Select Atom = 0x57a06
|
||||
Selected Atom = 0x57a08
|
||||
Shape Atom = 0x4f905
|
||||
Size Atom = 0x55504
|
||||
Sizes Atom = 0x55505
|
||||
Small Atom = 0x18f05
|
||||
Sortable Atom = 0x58d08
|
||||
Sorted Atom = 0x19906
|
||||
Source Atom = 0x1aa06
|
||||
Spacer Atom = 0x2db06
|
||||
Span Atom = 0x9504
|
||||
Spellcheck Atom = 0x3230a
|
||||
Src Atom = 0x3c303
|
||||
Srcdoc Atom = 0x3c306
|
||||
Srclang Atom = 0x41107
|
||||
Start Atom = 0x38605
|
||||
Step Atom = 0x5f704
|
||||
Strike Atom = 0x53306
|
||||
Strong Atom = 0x55906
|
||||
Style Atom = 0x61105
|
||||
Sub Atom = 0x5a903
|
||||
Summary Atom = 0x61607
|
||||
Sup Atom = 0x61d03
|
||||
Svg Atom = 0x62003
|
||||
System Atom = 0x62306
|
||||
Tabindex Atom = 0x46308
|
||||
Table Atom = 0x42d05
|
||||
Target Atom = 0x24b06
|
||||
Tbody Atom = 0x2e05
|
||||
Td Atom = 0x4702
|
||||
Template Atom = 0x62608
|
||||
Textarea Atom = 0x2f608
|
||||
Tfoot Atom = 0x8c05
|
||||
Th Atom = 0x22e02
|
||||
Thead Atom = 0x2d405
|
||||
Time Atom = 0xdd04
|
||||
Title Atom = 0xa105
|
||||
Tr Atom = 0x10502
|
||||
Track Atom = 0x10505
|
||||
Translate Atom = 0x14009
|
||||
Tt Atom = 0x5302
|
||||
Type Atom = 0x21404
|
||||
Typemustmatch Atom = 0x2140d
|
||||
U Atom = 0xb01
|
||||
Ul Atom = 0x8a02
|
||||
Usemap Atom = 0x51106
|
||||
Value Atom = 0x4005
|
||||
Var Atom = 0x11503
|
||||
Video Atom = 0x28105
|
||||
Wbr Atom = 0x12103
|
||||
Width Atom = 0x50705
|
||||
Wrap Atom = 0x58704
|
||||
Xmp Atom = 0xc103
|
||||
)
|
||||
|
||||
const hash0 = 0xc17da63e
|
||||
|
||||
const maxAtomLen = 19
|
||||
|
||||
var table = [1 << 9]Atom{
|
||||
0x1: 0x48a0b, // onmousemove
|
||||
0x2: 0x5e209, // onwaiting
|
||||
0x3: 0x1fa13, // onautocompleteerror
|
||||
0x4: 0x5fa06, // prompt
|
||||
0x7: 0x5eb07, // optimum
|
||||
0x8: 0x1604, // mark
|
||||
0xa: 0x5ad07, // itemref
|
||||
0xb: 0x4fe0a, // onpageshow
|
||||
0xc: 0x57a06, // select
|
||||
0xd: 0x17b09, // draggable
|
||||
0xe: 0x3e03, // nav
|
||||
0xf: 0x17507, // command
|
||||
0x11: 0xb01, // u
|
||||
0x14: 0x2d507, // headers
|
||||
0x15: 0x44a08, // datalist
|
||||
0x17: 0x4e04, // samp
|
||||
0x1a: 0x3fb09, // onkeydown
|
||||
0x1b: 0x55f08, // onscroll
|
||||
0x1c: 0x15003, // col
|
||||
0x20: 0x3c908, // itemprop
|
||||
0x21: 0x2780a, // http-equiv
|
||||
0x22: 0x61d03, // sup
|
||||
0x24: 0x1d008, // required
|
||||
0x2b: 0x25e07, // preload
|
||||
0x2c: 0x6040d, // onbeforeprint
|
||||
0x2d: 0x3600b, // ondragenter
|
||||
0x2e: 0x50902, // dt
|
||||
0x2f: 0x5a708, // onsubmit
|
||||
0x30: 0x27002, // hr
|
||||
0x31: 0x32f0d, // oncontextmenu
|
||||
0x33: 0x29c05, // image
|
||||
0x34: 0x50d07, // onpause
|
||||
0x35: 0x25906, // hgroup
|
||||
0x36: 0x7704, // ping
|
||||
0x37: 0x57808, // onselect
|
||||
0x3a: 0x11303, // div
|
||||
0x3b: 0x1fa0e, // onautocomplete
|
||||
0x40: 0x2eb02, // mi
|
||||
0x41: 0x31c08, // seamless
|
||||
0x42: 0x2807, // charset
|
||||
0x43: 0x8502, // id
|
||||
0x44: 0x5200a, // onpopstate
|
||||
0x45: 0x3ef03, // del
|
||||
0x46: 0x2cb07, // marquee
|
||||
0x47: 0x3309, // accesskey
|
||||
0x49: 0x8d06, // footer
|
||||
0x4a: 0x44e04, // list
|
||||
0x4b: 0x2b005, // ismap
|
||||
0x51: 0x33804, // menu
|
||||
0x52: 0x2f04, // body
|
||||
0x55: 0x9a08, // frameset
|
||||
0x56: 0x54a07, // onreset
|
||||
0x57: 0x12705, // blink
|
||||
0x58: 0xa105, // title
|
||||
0x59: 0x38807, // article
|
||||
0x5b: 0x22e02, // th
|
||||
0x5d: 0x13101, // q
|
||||
0x5e: 0x3cf04, // open
|
||||
0x5f: 0x2fa04, // area
|
||||
0x61: 0x44206, // onload
|
||||
0x62: 0xda04, // font
|
||||
0x63: 0xd604, // base
|
||||
0x64: 0x16207, // colspan
|
||||
0x65: 0x53707, // keytype
|
||||
0x66: 0x11e02, // dl
|
||||
0x68: 0x1b008, // fieldset
|
||||
0x6a: 0x2eb03, // min
|
||||
0x6b: 0x11503, // var
|
||||
0x6f: 0x2d506, // header
|
||||
0x70: 0x13f02, // rt
|
||||
0x71: 0x15008, // colgroup
|
||||
0x72: 0x23502, // mn
|
||||
0x74: 0x13a07, // onabort
|
||||
0x75: 0x3906, // keygen
|
||||
0x76: 0x4c209, // onoffline
|
||||
0x77: 0x21f09, // challenge
|
||||
0x78: 0x2b203, // map
|
||||
0x7a: 0x2e902, // h4
|
||||
0x7b: 0x3b607, // onerror
|
||||
0x7c: 0x2e109, // maxlength
|
||||
0x7d: 0x2f505, // mtext
|
||||
0x7e: 0xbb07, // sandbox
|
||||
0x7f: 0x58b06, // onsort
|
||||
0x80: 0x100a, // malignmark
|
||||
0x81: 0x45d04, // meta
|
||||
0x82: 0x7b05, // async
|
||||
0x83: 0x2a702, // h3
|
||||
0x84: 0x26702, // dd
|
||||
0x85: 0x27004, // href
|
||||
0x86: 0x6e0a, // mediagroup
|
||||
0x87: 0x19406, // coords
|
||||
0x88: 0x41107, // srclang
|
||||
0x89: 0x34d0a, // ondblclick
|
||||
0x8a: 0x4005, // value
|
||||
0x8c: 0xe908, // oncancel
|
||||
0x8e: 0x3230a, // spellcheck
|
||||
0x8f: 0x9a05, // frame
|
||||
0x91: 0x12403, // big
|
||||
0x94: 0x1f606, // action
|
||||
0x95: 0x6903, // dir
|
||||
0x97: 0x2fb08, // readonly
|
||||
0x99: 0x42d05, // table
|
||||
0x9a: 0x61607, // summary
|
||||
0x9b: 0x12103, // wbr
|
||||
0x9c: 0x30a, // radiogroup
|
||||
0x9d: 0x6c04, // name
|
||||
0x9f: 0x62306, // system
|
||||
0xa1: 0x15d05, // color
|
||||
0xa2: 0x7f06, // canvas
|
||||
0xa3: 0x25504, // html
|
||||
0xa5: 0x56f09, // onseeking
|
||||
0xac: 0x4f905, // shape
|
||||
0xad: 0x25f03, // rel
|
||||
0xae: 0x28510, // oncanplaythrough
|
||||
0xaf: 0x3760a, // ondragover
|
||||
0xb0: 0x62608, // template
|
||||
0xb1: 0x1d80d, // foreignObject
|
||||
0xb3: 0x9204, // rows
|
||||
0xb6: 0x44e07, // listing
|
||||
0xb7: 0x49c06, // output
|
||||
0xb9: 0x3310b, // contextmenu
|
||||
0xbb: 0x11f03, // low
|
||||
0xbc: 0x1c602, // rp
|
||||
0xbd: 0x5bb09, // onsuspend
|
||||
0xbe: 0x13606, // button
|
||||
0xbf: 0x4db04, // desc
|
||||
0xc1: 0x4e207, // section
|
||||
0xc2: 0x52a0a, // onprogress
|
||||
0xc3: 0x59e09, // onstorage
|
||||
0xc4: 0x2d204, // math
|
||||
0xc5: 0x4503, // alt
|
||||
0xc7: 0x8a02, // ul
|
||||
0xc8: 0x5107, // pattern
|
||||
0xc9: 0x4b60c, // onmousewheel
|
||||
0xca: 0x35709, // ondragend
|
||||
0xcb: 0xaf04, // ruby
|
||||
0xcc: 0xc01, // p
|
||||
0xcd: 0x31707, // onclose
|
||||
0xce: 0x24205, // meter
|
||||
0xcf: 0x11807, // bgsound
|
||||
0xd2: 0x25106, // height
|
||||
0xd4: 0x101, // b
|
||||
0xd5: 0x2c308, // itemtype
|
||||
0xd8: 0x1bb07, // caption
|
||||
0xd9: 0x10c08, // disabled
|
||||
0xdb: 0x33808, // menuitem
|
||||
0xdc: 0x62003, // svg
|
||||
0xdd: 0x18f05, // small
|
||||
0xde: 0x44a04, // data
|
||||
0xe0: 0x4cb08, // ononline
|
||||
0xe1: 0x2a206, // mglyph
|
||||
0xe3: 0x6505, // embed
|
||||
0xe4: 0x10502, // tr
|
||||
0xe5: 0x46b0b, // onloadstart
|
||||
0xe7: 0x3c306, // srcdoc
|
||||
0xeb: 0x5c408, // ontoggle
|
||||
0xed: 0xe703, // bdo
|
||||
0xee: 0x4702, // td
|
||||
0xef: 0x8305, // aside
|
||||
0xf0: 0x29402, // h2
|
||||
0xf1: 0x52c08, // progress
|
||||
0xf2: 0x12c0a, // blockquote
|
||||
0xf4: 0xf005, // label
|
||||
0xf5: 0x601, // i
|
||||
0xf7: 0x9207, // rowspan
|
||||
0xfb: 0x51709, // onplaying
|
||||
0xfd: 0x2a103, // img
|
||||
0xfe: 0xf608, // optgroup
|
||||
0xff: 0x42307, // content
|
||||
0x101: 0x53e0c, // onratechange
|
||||
0x103: 0x3da0c, // onhashchange
|
||||
0x104: 0x4807, // details
|
||||
0x106: 0x40008, // download
|
||||
0x109: 0x14009, // translate
|
||||
0x10b: 0x4230f, // contenteditable
|
||||
0x10d: 0x36b0b, // ondragleave
|
||||
0x10e: 0x2106, // accept
|
||||
0x10f: 0x57a08, // selected
|
||||
0x112: 0x1f20a, // formaction
|
||||
0x113: 0x5b506, // center
|
||||
0x115: 0x45510, // onloadedmetadata
|
||||
0x116: 0x12804, // link
|
||||
0x117: 0xdd04, // time
|
||||
0x118: 0x19f0b, // crossorigin
|
||||
0x119: 0x3bd07, // onfocus
|
||||
0x11a: 0x58704, // wrap
|
||||
0x11b: 0x42204, // icon
|
||||
0x11d: 0x28105, // video
|
||||
0x11e: 0x4de05, // class
|
||||
0x121: 0x5d40e, // onvolumechange
|
||||
0x122: 0xaa06, // onblur
|
||||
0x123: 0x2b909, // itemscope
|
||||
0x124: 0x61105, // style
|
||||
0x127: 0x41e06, // public
|
||||
0x129: 0x2320e, // formnovalidate
|
||||
0x12a: 0x58206, // onshow
|
||||
0x12c: 0x51706, // onplay
|
||||
0x12d: 0x3c804, // cite
|
||||
0x12e: 0x2bc02, // ms
|
||||
0x12f: 0xdb0c, // ontimeupdate
|
||||
0x130: 0x10904, // kind
|
||||
0x131: 0x2470a, // formtarget
|
||||
0x135: 0x3af07, // onended
|
||||
0x136: 0x26506, // hidden
|
||||
0x137: 0x2c01, // s
|
||||
0x139: 0x2280a, // formmethod
|
||||
0x13a: 0x3e805, // input
|
||||
0x13c: 0x50b02, // h6
|
||||
0x13d: 0xc902, // ol
|
||||
0x13e: 0x3420b, // oncuechange
|
||||
0x13f: 0x1e50d, // foreignobject
|
||||
0x143: 0x4e70e, // onbeforeunload
|
||||
0x144: 0x2bd05, // scope
|
||||
0x145: 0x39609, // onemptied
|
||||
0x146: 0x14b05, // defer
|
||||
0x147: 0xc103, // xmp
|
||||
0x148: 0x39f10, // ondurationchange
|
||||
0x149: 0x1903, // kbd
|
||||
0x14c: 0x47609, // onmessage
|
||||
0x14d: 0x60006, // option
|
||||
0x14e: 0x2eb09, // minlength
|
||||
0x14f: 0x32807, // checked
|
||||
0x150: 0xce08, // autoplay
|
||||
0x152: 0x202, // br
|
||||
0x153: 0x2360a, // novalidate
|
||||
0x156: 0x6307, // noembed
|
||||
0x159: 0x31007, // onclick
|
||||
0x15a: 0x47f0b, // onmousedown
|
||||
0x15b: 0x3a708, // onchange
|
||||
0x15e: 0x3f209, // oninvalid
|
||||
0x15f: 0x2bd06, // scoped
|
||||
0x160: 0x18808, // controls
|
||||
0x161: 0x30b05, // muted
|
||||
0x162: 0x58d08, // sortable
|
||||
0x163: 0x51106, // usemap
|
||||
0x164: 0x1b80a, // figcaption
|
||||
0x165: 0x35706, // ondrag
|
||||
0x166: 0x26b04, // high
|
||||
0x168: 0x3c303, // src
|
||||
0x169: 0x15706, // poster
|
||||
0x16b: 0x1670e, // annotation-xml
|
||||
0x16c: 0x5f704, // step
|
||||
0x16d: 0x4, // abbr
|
||||
0x16e: 0x1b06, // dialog
|
||||
0x170: 0x1202, // li
|
||||
0x172: 0x3ed02, // mo
|
||||
0x175: 0x1d803, // for
|
||||
0x176: 0x1a803, // ins
|
||||
0x178: 0x55504, // size
|
||||
0x179: 0x43210, // onlanguagechange
|
||||
0x17a: 0x8607, // default
|
||||
0x17b: 0x1a03, // bdi
|
||||
0x17c: 0x4d30a, // onpagehide
|
||||
0x17d: 0x6907, // dirname
|
||||
0x17e: 0x21404, // type
|
||||
0x17f: 0x1f204, // form
|
||||
0x181: 0x28509, // oncanplay
|
||||
0x182: 0x6103, // dfn
|
||||
0x183: 0x46308, // tabindex
|
||||
0x186: 0x6502, // em
|
||||
0x187: 0x27404, // lang
|
||||
0x189: 0x39108, // dropzone
|
||||
0x18a: 0x4080a, // onkeypress
|
||||
0x18b: 0x23c08, // datetime
|
||||
0x18c: 0x16204, // cols
|
||||
0x18d: 0x1, // a
|
||||
0x18e: 0x4420c, // onloadeddata
|
||||
0x190: 0xa605, // audio
|
||||
0x192: 0x2e05, // tbody
|
||||
0x193: 0x22c06, // method
|
||||
0x195: 0xf404, // loop
|
||||
0x196: 0x29606, // iframe
|
||||
0x198: 0x2d504, // head
|
||||
0x19e: 0x5f108, // manifest
|
||||
0x19f: 0xb309, // autofocus
|
||||
0x1a0: 0x14904, // code
|
||||
0x1a1: 0x55906, // strong
|
||||
0x1a2: 0x30308, // multiple
|
||||
0x1a3: 0xc05, // param
|
||||
0x1a6: 0x21107, // enctype
|
||||
0x1a7: 0x5b304, // face
|
||||
0x1a8: 0xfd09, // plaintext
|
||||
0x1a9: 0x26e02, // h1
|
||||
0x1aa: 0x59509, // onstalled
|
||||
0x1ad: 0x3d406, // script
|
||||
0x1ae: 0x2db06, // spacer
|
||||
0x1af: 0x55108, // onresize
|
||||
0x1b0: 0x4a20b, // onmouseover
|
||||
0x1b1: 0x5cc08, // onunload
|
||||
0x1b2: 0x56708, // onseeked
|
||||
0x1b4: 0x2140d, // typemustmatch
|
||||
0x1b5: 0x1cc06, // figure
|
||||
0x1b6: 0x4950a, // onmouseout
|
||||
0x1b7: 0x25e03, // pre
|
||||
0x1b8: 0x50705, // width
|
||||
0x1b9: 0x19906, // sorted
|
||||
0x1bb: 0x5704, // nobr
|
||||
0x1be: 0x5302, // tt
|
||||
0x1bf: 0x1105, // align
|
||||
0x1c0: 0x3e607, // oninput
|
||||
0x1c3: 0x41807, // onkeyup
|
||||
0x1c6: 0x1c00c, // onafterprint
|
||||
0x1c7: 0x210e, // accept-charset
|
||||
0x1c8: 0x33c06, // itemid
|
||||
0x1c9: 0x3e809, // inputmode
|
||||
0x1cb: 0x53306, // strike
|
||||
0x1cc: 0x5a903, // sub
|
||||
0x1cd: 0x10505, // track
|
||||
0x1ce: 0x38605, // start
|
||||
0x1d0: 0xd608, // basefont
|
||||
0x1d6: 0x1aa06, // source
|
||||
0x1d7: 0x18206, // legend
|
||||
0x1d8: 0x2d405, // thead
|
||||
0x1da: 0x8c05, // tfoot
|
||||
0x1dd: 0x1ec06, // object
|
||||
0x1de: 0x6e05, // media
|
||||
0x1df: 0x1670a, // annotation
|
||||
0x1e0: 0x20d0b, // formenctype
|
||||
0x1e2: 0x3d208, // noscript
|
||||
0x1e4: 0x55505, // sizes
|
||||
0x1e5: 0x1fc0c, // autocomplete
|
||||
0x1e6: 0x9504, // span
|
||||
0x1e7: 0x9808, // noframes
|
||||
0x1e8: 0x24b06, // target
|
||||
0x1e9: 0x38f06, // ondrop
|
||||
0x1ea: 0x2b306, // applet
|
||||
0x1ec: 0x5a08, // reversed
|
||||
0x1f0: 0x2a907, // isindex
|
||||
0x1f3: 0x27008, // hreflang
|
||||
0x1f5: 0x2f302, // h5
|
||||
0x1f6: 0x4f307, // address
|
||||
0x1fa: 0x2e103, // max
|
||||
0x1fb: 0xc30b, // placeholder
|
||||
0x1fc: 0x2f608, // textarea
|
||||
0x1fe: 0x4ad09, // onmouseup
|
||||
0x1ff: 0x3800b, // ondragstart
|
||||
}
|
||||
|
||||
const atomText = "abbradiogrouparamalignmarkbdialogaccept-charsetbodyaccesskey" +
|
||||
"genavaluealtdetailsampatternobreversedfnoembedirnamediagroup" +
|
||||
"ingasyncanvasidefaultfooterowspanoframesetitleaudionblurubya" +
|
||||
"utofocusandboxmplaceholderautoplaybasefontimeupdatebdoncance" +
|
||||
"labelooptgrouplaintextrackindisabledivarbgsoundlowbrbigblink" +
|
||||
"blockquotebuttonabortranslatecodefercolgroupostercolorcolspa" +
|
||||
"nnotation-xmlcommandraggablegendcontrolsmallcoordsortedcross" +
|
||||
"originsourcefieldsetfigcaptionafterprintfigurequiredforeignO" +
|
||||
"bjectforeignobjectformactionautocompleteerrorformenctypemust" +
|
||||
"matchallengeformmethodformnovalidatetimeterformtargetheightm" +
|
||||
"lhgroupreloadhiddenhigh1hreflanghttp-equivideoncanplaythroug" +
|
||||
"h2iframeimageimglyph3isindexismappletitemscopeditemtypemarqu" +
|
||||
"eematheaderspacermaxlength4minlength5mtextareadonlymultiplem" +
|
||||
"utedonclickoncloseamlesspellcheckedoncontextmenuitemidoncuec" +
|
||||
"hangeondblclickondragendondragenterondragleaveondragoverondr" +
|
||||
"agstarticleondropzonemptiedondurationchangeonendedonerroronf" +
|
||||
"ocusrcdocitempropenoscriptonhashchangeoninputmodeloninvalido" +
|
||||
"nkeydownloadonkeypressrclangonkeyupublicontenteditableonlang" +
|
||||
"uagechangeonloadeddatalistingonloadedmetadatabindexonloadsta" +
|
||||
"rtonmessageonmousedownonmousemoveonmouseoutputonmouseoveronm" +
|
||||
"ouseuponmousewheelonofflineononlineonpagehidesclassectionbef" +
|
||||
"oreunloaddresshapeonpageshowidth6onpausemaponplayingonpopsta" +
|
||||
"teonprogresstrikeytypeonratechangeonresetonresizestrongonscr" +
|
||||
"ollonseekedonseekingonselectedonshowraponsortableonstalledon" +
|
||||
"storageonsubmitemrefacenteronsuspendontoggleonunloadonvolume" +
|
||||
"changeonwaitingoptimumanifestepromptoptionbeforeprintstylesu" +
|
||||
"mmarysupsvgsystemplate"
|
||||
|
|
@ -0,0 +1,102 @@
|
|||
// 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 12.2.3.2 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,
|
||||
"li": true,
|
||||
"link": true,
|
||||
"listing": 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 "svg":
|
||||
return element.Data == "foreignObject"
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
|
@ -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 ErrorToken:
|
||||
return z.Err()
|
||||
case TextToken:
|
||||
if depth > 0 {
|
||||
// emitBytes should copy the []byte it receives,
|
||||
// if it doesn't process it immediately.
|
||||
emitBytes(z.Text())
|
||||
}
|
||||
case StartTagToken, EndTagToken:
|
||||
tn, _ := z.TagName()
|
||||
if len(tn) == 1 && tn[0] == 'a' {
|
||||
if tt == 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?
|
||||
|
|
@ -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//",
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -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
|
||||
}
|
||||
|
|
@ -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 12.2.5.5.
|
||||
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 12.2.5.5.
|
||||
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 12.2.5.1
|
||||
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",
|
||||
}
|
||||
|
|
@ -0,0 +1,193 @@
|
|||
// 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 12.2.3.3 says "scope markers are inserted when entering applet
|
||||
// elements, buttons, object elements, marquees, table cells, and table
|
||||
// captions, and are used to prevent formatting from 'leaking'".
|
||||
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
|
||||
}
|
||||
|
||||
// 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]
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -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,
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -3294,6 +3294,18 @@
|
|||
"revision": "f2499483f923065a842d38eb4c7f1927e6fc6e6d",
|
||||
"revisionTime": "2017-01-14T04:22:49Z"
|
||||
},
|
||||
{
|
||||
"checksumSHA1": "vqc3a+oTUGX8PmD0TS+qQ7gmN8I=",
|
||||
"path": "golang.org/x/net/html",
|
||||
"revision": "59a0b19b5533c7977ddeb86b017bf507ed407b12",
|
||||
"revisionTime": "2017-06-03T08:13:02Z"
|
||||
},
|
||||
{
|
||||
"checksumSHA1": "00eQaGynDYrv3tL+C7l9xH0IDZg=",
|
||||
"path": "golang.org/x/net/html/atom",
|
||||
"revision": "59a0b19b5533c7977ddeb86b017bf507ed407b12",
|
||||
"revisionTime": "2017-06-03T08:13:02Z"
|
||||
},
|
||||
{
|
||||
"checksumSHA1": "N1akwAdrHVfPPrsFOhG2ouP21VA=",
|
||||
"path": "golang.org/x/net/http2",
|
||||
|
|
|
|||
Loading…
Reference in New Issue