diff options
Diffstat (limited to 'vendor/golang.org/x/net/html')
-rw-r--r-- | vendor/golang.org/x/net/html/atom/atom.go | 78 | ||||
-rw-r--r-- | vendor/golang.org/x/net/html/atom/gen.go | 648 | ||||
-rw-r--r-- | vendor/golang.org/x/net/html/atom/table.go | 713 | ||||
-rw-r--r-- | vendor/golang.org/x/net/html/charset/charset.go | 257 | ||||
-rw-r--r-- | vendor/golang.org/x/net/html/const.go | 102 | ||||
-rw-r--r-- | vendor/golang.org/x/net/html/doc.go | 106 | ||||
-rw-r--r-- | vendor/golang.org/x/net/html/doctype.go | 156 | ||||
-rw-r--r-- | vendor/golang.org/x/net/html/entity.go | 2253 | ||||
-rw-r--r-- | vendor/golang.org/x/net/html/escape.go | 258 | ||||
-rw-r--r-- | vendor/golang.org/x/net/html/foreign.go | 226 | ||||
-rw-r--r-- | vendor/golang.org/x/net/html/node.go | 193 | ||||
-rw-r--r-- | vendor/golang.org/x/net/html/parse.go | 2094 | ||||
-rw-r--r-- | vendor/golang.org/x/net/html/render.go | 271 | ||||
-rw-r--r-- | vendor/golang.org/x/net/html/token.go | 1219 |
14 files changed, 8574 insertions, 0 deletions
diff --git a/vendor/golang.org/x/net/html/atom/atom.go b/vendor/golang.org/x/net/html/atom/atom.go new file mode 100644 index 000000000..cd0a8ac15 --- /dev/null +++ b/vendor/golang.org/x/net/html/atom/atom.go @@ -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) +} diff --git a/vendor/golang.org/x/net/html/atom/gen.go b/vendor/golang.org/x/net/html/atom/gen.go new file mode 100644 index 000000000..6bfa86601 --- /dev/null +++ b/vendor/golang.org/x/net/html/atom/gen.go @@ -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", +} diff --git a/vendor/golang.org/x/net/html/atom/table.go b/vendor/golang.org/x/net/html/atom/table.go new file mode 100644 index 000000000..2605ba310 --- /dev/null +++ b/vendor/golang.org/x/net/html/atom/table.go @@ -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" diff --git a/vendor/golang.org/x/net/html/charset/charset.go b/vendor/golang.org/x/net/html/charset/charset.go new file mode 100644 index 000000000..13bed1599 --- /dev/null +++ b/vendor/golang.org/x/net/html/charset/charset.go @@ -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"}, +} diff --git a/vendor/golang.org/x/net/html/const.go b/vendor/golang.org/x/net/html/const.go new file mode 100644 index 000000000..52f651ff6 --- /dev/null +++ b/vendor/golang.org/x/net/html/const.go @@ -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 +} diff --git a/vendor/golang.org/x/net/html/doc.go b/vendor/golang.org/x/net/html/doc.go new file mode 100644 index 000000000..94f496874 --- /dev/null +++ b/vendor/golang.org/x/net/html/doc.go @@ -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? diff --git a/vendor/golang.org/x/net/html/doctype.go b/vendor/golang.org/x/net/html/doctype.go new file mode 100644 index 000000000..c484e5a94 --- /dev/null +++ b/vendor/golang.org/x/net/html/doctype.go @@ -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//", +} diff --git a/vendor/golang.org/x/net/html/entity.go b/vendor/golang.org/x/net/html/entity.go new file mode 100644 index 000000000..a50c04c60 --- /dev/null +++ b/vendor/golang.org/x/net/html/entity.go @@ -0,0 +1,2253 @@ +// 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 + +// All entities that do not end with ';' are 6 or fewer bytes long. +const longestEntityWithoutSemicolon = 6 + +// entity is a map from HTML entity names to their values. The semicolon matters: +// https://html.spec.whatwg.org/multipage/syntax.html#named-character-references +// lists both "amp" and "amp;" as two separate entries. +// +// Note that the HTML5 list is larger than the HTML4 list at +// http://www.w3.org/TR/html4/sgml/entities.html +var entity = map[string]rune{ + "AElig;": '\U000000C6', + "AMP;": '\U00000026', + "Aacute;": '\U000000C1', + "Abreve;": '\U00000102', + "Acirc;": '\U000000C2', + "Acy;": '\U00000410', + "Afr;": '\U0001D504', + "Agrave;": '\U000000C0', + "Alpha;": '\U00000391', + "Amacr;": '\U00000100', + "And;": '\U00002A53', + "Aogon;": '\U00000104', + "Aopf;": '\U0001D538', + "ApplyFunction;": '\U00002061', + "Aring;": '\U000000C5', + "Ascr;": '\U0001D49C', + "Assign;": '\U00002254', + "Atilde;": '\U000000C3', + "Auml;": '\U000000C4', + "Backslash;": '\U00002216', + "Barv;": '\U00002AE7', + "Barwed;": '\U00002306', + "Bcy;": '\U00000411', + "Because;": '\U00002235', + "Bernoullis;": '\U0000212C', + "Beta;": '\U00000392', + "Bfr;": '\U0001D505', + "Bopf;": '\U0001D539', + "Breve;": '\U000002D8', + "Bscr;": '\U0000212C', + "Bumpeq;": '\U0000224E', + "CHcy;": '\U00000427', + "COPY;": '\U000000A9', + "Cacute;": '\U00000106', + "Cap;": '\U000022D2', + "CapitalDifferentialD;": '\U00002145', + "Cayleys;": '\U0000212D', + "Ccaron;": '\U0000010C', + "Ccedil;": '\U000000C7', + "Ccirc;": '\U00000108', + "Cconint;": '\U00002230', + "Cdot;": '\U0000010A', + "Cedilla;": '\U000000B8', + "CenterDot;": '\U000000B7', + "Cfr;": '\U0000212D', + "Chi;": '\U000003A7', + "CircleDot;": '\U00002299', + "CircleMinus;": '\U00002296', + "CirclePlus;": '\U00002295', + "CircleTimes;": '\U00002297', + "ClockwiseContourIntegral;": '\U00002232', + "CloseCurlyDoubleQuote;": '\U0000201D', + "CloseCurlyQuote;": '\U00002019', + "Colon;": '\U00002237', + "Colone;": '\U00002A74', + "Congruent;": '\U00002261', + "Conint;": '\U0000222F', + "ContourIntegral;": '\U0000222E', + "Copf;": '\U00002102', + "Coproduct;": '\U00002210', + "CounterClockwiseContourIntegral;": '\U00002233', + "Cross;": '\U00002A2F', + "Cscr;": '\U0001D49E', + "Cup;": '\U000022D3', + "CupCap;": '\U0000224D', + "DD;": '\U00002145', + "DDotrahd;": '\U00002911', + "DJcy;": '\U00000402', + "DScy;": '\U00000405', + "DZcy;": '\U0000040F', + "Dagger;": '\U00002021', + "Darr;": '\U000021A1', + "Dashv;": '\U00002AE4', + "Dcaron;": '\U0000010E', + "Dcy;": '\U00000414', + "Del;": '\U00002207', + "Delta;": '\U00000394', + "Dfr;": '\U0001D507', + "DiacriticalAcute;": '\U000000B4', + "DiacriticalDot;": '\U000002D9', + "DiacriticalDoubleAcute;": '\U000002DD', + "DiacriticalGrave;": '\U00000060', + "DiacriticalTilde;": '\U000002DC', + "Diamond;": '\U000022C4', + "DifferentialD;": '\U00002146', + "Dopf;": '\U0001D53B', + "Dot;": '\U000000A8', + "DotDot;": '\U000020DC', + "DotEqual;": '\U00002250', + "DoubleContourIntegral;": '\U0000222F', + "DoubleDot;": '\U000000A8', + "DoubleDownArrow;": '\U000021D3', + "DoubleLeftArrow;": '\U000021D0', + "DoubleLeftRightArrow;": '\U000021D4', + "DoubleLeftTee;": '\U00002AE4', + "DoubleLongLeftArrow;": '\U000027F8', + "DoubleLongLeftRightArrow;": '\U000027FA', + "DoubleLongRightArrow;": '\U000027F9', + "DoubleRightArrow;": '\U000021D2', + "DoubleRightTee;": '\U000022A8', + "DoubleUpArrow;": '\U000021D1', + "DoubleUpDownArrow;": '\U000021D5', + "DoubleVerticalBar;": '\U00002225', + "DownArrow;": '\U00002193', + "DownArrowBar;": '\U00002913', + "DownArrowUpArrow;": '\U000021F5', + "DownBreve;": '\U00000311', + "DownLeftRightVector;": '\U00002950', + "DownLeftTeeVector;": '\U0000295E', + "DownLeftVector;": '\U000021BD', + "DownLeftVectorBar;": '\U00002956', + "DownRightTeeVector;": '\U0000295F', + "DownRightVector;": '\U000021C1', + "DownRightVectorBar;": '\U00002957', + "DownTee;": '\U000022A4', + "DownTeeArrow;": '\U000021A7', + "Downarrow;": '\U000021D3', + "Dscr;": '\U0001D49F', + "Dstrok;": '\U00000110', + "ENG;": '\U0000014A', + "ETH;": '\U000000D0', + "Eacute;": '\U000000C9', + "Ecaron;": '\U0000011A', + "Ecirc;": '\U000000CA', + "Ecy;": '\U0000042D', + "Edot;": '\U00000116', + "Efr;": '\U0001D508', + "Egrave;": '\U000000C8', + "Element;": '\U00002208', + "Emacr;": '\U00000112', + "EmptySmallSquare;": '\U000025FB', + "EmptyVerySmallSquare;": '\U000025AB', + "Eogon;": '\U00000118', + "Eopf;": '\U0001D53C', + "Epsilon;": '\U00000395', + "Equal;": '\U00002A75', + "EqualTilde;": '\U00002242', + "Equilibrium;": '\U000021CC', + "Escr;": '\U00002130', + "Esim;": '\U00002A73', + "Eta;": '\U00000397', + "Euml;": '\U000000CB', + "Exists;": '\U00002203', + "ExponentialE;": '\U00002147', + "Fcy;": '\U00000424', + "Ffr;": '\U0001D509', + "FilledSmallSquare;": '\U000025FC', + "FilledVerySmallSquare;": '\U000025AA', + "Fopf;": '\U0001D53D', + "ForAll;": '\U00002200', + "Fouriertrf;": '\U00002131', + "Fscr;": '\U00002131', + "GJcy;": '\U00000403', + "GT;": '\U0000003E', + "Gamma;": '\U00000393', + "Gammad;": '\U000003DC', + "Gbreve;": '\U0000011E', + "Gcedil;": '\U00000122', + "Gcirc;": '\U0000011C', + "Gcy;": '\U00000413', + "Gdot;": '\U00000120', + "Gfr;": '\U0001D50A', + "Gg;": '\U000022D9', + "Gopf;": '\U0001D53E', + "GreaterEqual;": '\U00002265', + "GreaterEqualLess;": '\U000022DB', + "GreaterFullEqual;": '\U00002267', + "GreaterGreater;": '\U00002AA2', + "GreaterLess;": '\U00002277', + "GreaterSlantEqual;": '\U00002A7E', + "GreaterTilde;": '\U00002273', + "Gscr;": '\U0001D4A2', + "Gt;": '\U0000226B', + "HARDcy;": '\U0000042A', + "Hacek;": '\U000002C7', + "Hat;": '\U0000005E', + "Hcirc;": '\U00000124', + "Hfr;": '\U0000210C', + "HilbertSpace;": '\U0000210B', + "Hopf;": '\U0000210D', + "HorizontalLine;": '\U00002500', + "Hscr;": '\U0000210B', + "Hstrok;": '\U00000126', + "HumpDownHump;": '\U0000224E', + "HumpEqual;": '\U0000224F', + "IEcy;": '\U00000415', + "IJlig;": '\U00000132', + "IOcy;": '\U00000401', + "Iacute;": '\U000000CD', + "Icirc;": '\U000000CE', + "Icy;": '\U00000418', + "Idot;": '\U00000130', + "Ifr;": '\U00002111', + "Igrave;": '\U000000CC', + "Im;": '\U00002111', + "Imacr;": '\U0000012A', + "ImaginaryI;": '\U00002148', + "Implies;": '\U000021D2', + "Int;": '\U0000222C', + "Integral;": '\U0000222B', + "Intersection;": '\U000022C2', + "InvisibleComma;": '\U00002063', + "InvisibleTimes;": '\U00002062', + "Iogon;": '\U0000012E', + "Iopf;": '\U0001D540', + "Iota;": '\U00000399', + "Iscr;": '\U00002110', + "Itilde;": '\U00000128', + "Iukcy;": '\U00000406', + "Iuml;": '\U000000CF', + "Jcirc;": '\U00000134', + "Jcy;": '\U00000419', + "Jfr;": '\U0001D50D', + "Jopf;": '\U0001D541', + "Jscr;": '\U0001D4A5', + "Jsercy;": '\U00000408', + "Jukcy;": '\U00000404', + "KHcy;": '\U00000425', + "KJcy;": '\U0000040C', + "Kappa;": '\U0000039A', + "Kcedil;": '\U00000136', + "Kcy;": '\U0000041A', + "Kfr;": '\U0001D50E', + "Kopf;": '\U0001D542', + "Kscr;": '\U0001D4A6', + "LJcy;": '\U00000409', + "LT;": '\U0000003C', + "Lacute;": '\U00000139', + "Lambda;": '\U0000039B', + "Lang;": '\U000027EA', + "Laplacetrf;": '\U00002112', + "Larr;": '\U0000219E', + "Lcaron;": '\U0000013D', + "Lcedil;": '\U0000013B', + "Lcy;": '\U0000041B', + "LeftAngleBracket;": '\U000027E8', + "LeftArrow;": '\U00002190', + "LeftArrowBar;": '\U000021E4', + "LeftArrowRightArrow;": '\U000021C6', + "LeftCeiling;": '\U00002308', + "LeftDoubleBracket;": '\U000027E6', + "LeftDownTeeVector;": '\U00002961', + "LeftDownVector;": '\U000021C3', + "LeftDownVectorBar;": '\U00002959', + "LeftFloor;": '\U0000230A', + "LeftRightArrow;": '\U00002194', + "LeftRightVector;": '\U0000294E', + "LeftTee;": '\U000022A3', + "LeftTeeArrow;": '\U000021A4', + "LeftTeeVector;": '\U0000295A', + "LeftTriangle;": '\U000022B2', + "LeftTriangleBar;": '\U000029CF', + "LeftTriangleEqual;": '\U000022B4', + "LeftUpDownVector;": '\U00002951', + "LeftUpTeeVector;": '\U00002960', + "LeftUpVector;": '\U000021BF', + "LeftUpVectorBar;": '\U00002958', + "LeftVector;": '\U000021BC', + "LeftVectorBar;": '\U00002952', + "Leftarrow;": '\U000021D0', + "Leftrightarrow;": '\U000021D4', + "LessEqualGreater;": '\U000022DA', + "LessFullEqual;": '\U00002266', + "LessGreater;": '\U00002276', + "LessLess;": '\U00002AA1', + "LessSlantEqual;": '\U00002A7D', + "LessTilde;": '\U00002272', + "Lfr;": '\U0001D50F', + "Ll;": '\U000022D8', + "Lleftarrow;": '\U000021DA', + "Lmidot;": '\U0000013F', + "LongLeftArrow;": '\U000027F5', + "LongLeftRightArrow;": '\U000027F7', + "LongRightArrow;": '\U000027F6', + "Longleftarrow;": '\U000027F8', + "Longleftrightarrow;": '\U000027FA', + "Longrightarrow;": '\U000027F9', + "Lopf;": '\U0001D543', + "LowerLeftArrow;": '\U00002199', + "LowerRightArrow;": '\U00002198', + "Lscr;": '\U00002112', + "Lsh;": '\U000021B0', + "Lstrok;": '\U00000141', + "Lt;": '\U0000226A', + "Map;": '\U00002905', + "Mcy;": '\U0000041C', + "MediumSpace;": '\U0000205F', + "Mellintrf;": '\U00002133', + "Mfr;": '\U0001D510', + "MinusPlus;": '\U00002213', + "Mopf;": '\U0001D544', + "Mscr;": '\U00002133', + "Mu;": '\U0000039C', + "NJcy;": '\U0000040A', + "Nacute;": '\U00000143', + "Ncaron;": '\U00000147', + "Ncedil;": '\U00000145', + "Ncy;": '\U0000041D', + "NegativeMediumSpace;": '\U0000200B', + "NegativeThickSpace;": '\U0000200B', + "NegativeThinSpace;": '\U0000200B', + "NegativeVeryThinSpace;": '\U0000200B', + "NestedGreaterGreater;": '\U0000226B', + "NestedLessLess;": '\U0000226A', + "NewLine;": '\U0000000A', + "Nfr;": '\U0001D511', + "NoBreak;": '\U00002060', + "NonBreakingSpace;": '\U000000A0', + "Nopf;": '\U00002115', + "Not;": '\U00002AEC', + "NotCongruent;": '\U00002262', + "NotCupCap;": '\U0000226D', + "NotDoubleVerticalBar;": '\U00002226', + "NotElement;": '\U00002209', + "NotEqual;": '\U00002260', + "NotExists;": '\U00002204', + "NotGreater;": '\U0000226F', + "NotGreaterEqual;": '\U00002271', + "NotGreaterLess;": '\U00002279', + "NotGreaterTilde;": '\U00002275', + "NotLeftTriangle;": '\U000022EA', + "NotLeftTriangleEqual;": '\U000022EC', + "NotLess;": '\U0000226E', + "NotLessEqual;": '\U00002270', + "NotLessGreater;": '\U00002278', + "NotLessTilde;": '\U00002274', + "NotPrecedes;": '\U00002280', + "NotPrecedesSlantEqual;": '\U000022E0', + "NotReverseElement;": '\U0000220C', + "NotRightTriangle;": '\U000022EB', + "NotRightTriangleEqual;": '\U000022ED', + "NotSquareSubsetEqual;": '\U000022E2', + "NotSquareSupersetEqual;": '\U000022E3', + "NotSubsetEqual;": '\U00002288', + "NotSucceeds;": '\U00002281', + "NotSucceedsSlantEqual;": '\U000022E1', + "NotSupersetEqual;": '\U00002289', + "NotTilde;": '\U00002241', + "NotTildeEqual;": '\U00002244', + "NotTildeFullEqual;": '\U00002247', + "NotTildeTilde;": '\U00002249', + "NotVerticalBar;": '\U00002224', + "Nscr;": '\U0001D4A9', + "Ntilde;": '\U000000D1', + "Nu;": '\U0000039D', + "OElig;": '\U00000152', + "Oacute;": '\U000000D3', + "Ocirc;": '\U000000D4', + "Ocy;": '\U0000041E', + "Odblac;": '\U00000150', + "Ofr;": '\U0001D512', + "Ograve;": '\U000000D2', + "Omacr;": '\U0000014C', + "Omega;": '\U000003A9', + "Omicron;": '\U0000039F', + "Oopf;": '\U0001D546', + "OpenCurlyDoubleQuote;": '\U0000201C', + "OpenCurlyQuote;": '\U00002018', + "Or;": '\U00002A54', + "Oscr;": '\U0001D4AA', + "Oslash;": '\U000000D8', + "Otilde;": '\U000000D5', + "Otimes;": '\U00002A37', + "Ouml;": '\U000000D6', + "OverBar;": '\U0000203E', + "OverBrace;": '\U000023DE', + "OverBracket;": '\U000023B4', + "OverParenthesis;": '\U000023DC', + "PartialD;": '\U00002202', + "Pcy;": '\U0000041F', + "Pfr;": '\U0001D513', + "Phi;": '\U000003A6', + "Pi;": '\U000003A0', + "PlusMinus;": '\U000000B1', + "Poincareplane;": '\U0000210C', + "Popf;": '\U00002119', + "Pr;": '\U00002ABB', + "Precedes;": '\U0000227A', + "PrecedesEqual;": '\U00002AAF', + "PrecedesSlantEqual;": '\U0000227C', + "PrecedesTilde;": '\U0000227E', + "Prime;": '\U00002033', + "Product;": '\U0000220F', + "Proportion;": '\U00002237', + "Proportional;": '\U0000221D', + "Pscr;": '\U0001D4AB', + "Psi;": '\U000003A8', + "QUOT;": '\U00000022', + "Qfr;": '\U0001D514', + "Qopf;": '\U0000211A', + "Qscr;": '\U0001D4AC', + "RBarr;": '\U00002910', + "REG;": '\U000000AE', + "Racute;": '\U00000154', + "Rang;": '\U000027EB', + "Rarr;": '\U000021A0', + "Rarrtl;": '\U00002916', + "Rcaron;": '\U00000158', + "Rcedil;": '\U00000156', + "Rcy;": '\U00000420', + "Re;": '\U0000211C', + "ReverseElement;": '\U0000220B', + "ReverseEquilibrium;": '\U000021CB', + "ReverseUpEquilibrium;": '\U0000296F', + "Rfr;": '\U0000211C', + "Rho;": '\U000003A1', + "RightAngleBracket;": '\U000027E9', + "RightArrow;": '\U00002192', + "RightArrowBar;": '\U000021E5', + "RightArrowLeftArrow;": '\U000021C4', + "RightCeiling;": '\U00002309', + "RightDoubleBracket;": '\U000027E7', + "RightDownTeeVector;": '\U0000295D', + "RightDownVector;": '\U000021C2', + "RightDownVectorBar;": '\U00002955', + "RightFloor;": '\U0000230B', + "RightTee;": '\U000022A2', + "RightTeeArrow;": '\U000021A6', + "RightTeeVector;": '\U0000295B', + "RightTriangle;": '\U000022B3', + "RightTriangleBar;": '\U000029D0', + "RightTriangleEqual;": '\U000022B5', + "RightUpDownVector;": '\U0000294F', + "RightUpTeeVector;": '\U0000295C', + "RightUpVector;": '\U000021BE', + "RightUpVectorBar;": '\U00002954', + "RightVector;": '\U000021C0', + "RightVectorBar;": '\U00002953', + "Rightarrow;": '\U000021D2', + "Ropf;": '\U0000211D', + "RoundImplies;": '\U00002970', + "Rrightarrow;": '\U000021DB', + "Rscr;": '\U0000211B', + "Rsh;": '\U000021B1', + "RuleDelayed;": '\U000029F4', + "SHCHcy;": '\U00000429', + "SHcy;": '\U00000428', + "SOFTcy;": '\U0000042C', + "Sacute;": '\U0000015A', + "Sc;": '\U00002ABC', + "Scaron;": '\U00000160', + "Scedil;": '\U0000015E', + "Scirc;": '\U0000015C', + "Scy;": '\U00000421', + "Sfr;": '\U0001D516', + "ShortDownArrow;": '\U00002193', + "ShortLeftArrow;": '\U00002190', + "ShortRightArrow;": '\U00002192', + "ShortUpArrow;": '\U00002191', + "Sigma;": '\U000003A3', + "SmallCircle;": '\U00002218', + "Sopf;": '\U0001D54A', + "Sqrt;": '\U0000221A', + "Square;": '\U000025A1', + "SquareIntersection;": '\U00002293', + "SquareSubset;": '\U0000228F', + "SquareSubsetEqual;": '\U00002291', + "SquareSuperset;": '\U00002290', + "SquareSupersetEqual;": '\U00002292', + "SquareUnion;": '\U00002294', + "Sscr;": '\U0001D4AE', + "Star;": '\U000022C6', + "Sub;": '\U000022D0', + "Subset;": '\U000022D0', + "SubsetEqual;": '\U00002286', + "Succeeds;": '\U0000227B', + "SucceedsEqual;": '\U00002AB0', + "SucceedsSlantEqual;": '\U0000227D', + "SucceedsTilde;": '\U0000227F', + "SuchThat;": '\U0000220B', + "Sum;": '\U00002211', + "Sup;": '\U000022D1', + "Superset;": '\U00002283', + "SupersetEqual;": '\U00002287', + "Supset;": '\U000022D1', + "THORN;": '\U000000DE', + "TRADE;": '\U00002122', + "TSHcy;": '\U0000040B', + "TScy;": '\U00000426', + "Tab;": '\U00000009', + "Tau;": '\U000003A4', + "Tcaron;": '\U00000164', + "Tcedil;": '\U00000162', + "Tcy;": '\U00000422', + "Tfr;": '\U0001D517', + "Therefore;": '\U00002234', + "Theta;": '\U00000398', + "ThinSpace;": '\U00002009', + "Tilde;": '\U0000223C', + "TildeEqual;": '\U00002243', + "TildeFullEqual;": '\U00002245', + "TildeTilde;": '\U00002248', + "Topf;": '\U0001D54B', + "TripleDot;": '\U000020DB', + "Tscr;": '\U0001D4AF', + "Tstrok;": '\U00000166', + "Uacute;": '\U000000DA', + "Uarr;": '\U0000219F', + "Uarrocir;": '\U00002949', + "Ubrcy;": '\U0000040E', + "Ubreve;": '\U0000016C', + "Ucirc;": '\U000000DB', + "Ucy;": '\U00000423', + "Udblac;": '\U00000170', + "Ufr;": '\U0001D518', + "Ugrave;": '\U000000D9', + "Umacr;": '\U0000016A', + "UnderBar;": '\U0000005F', + "UnderBrace;": '\U000023DF', + "UnderBracket;": '\U000023B5', + "UnderParenthesis;": '\U000023DD', + "Union;": '\U000022C3', + "UnionPlus;": '\U0000228E', + "Uogon;": '\U00000172', + "Uopf;": '\U0001D54C', + "UpArrow;": '\U00002191', + "UpArrowBar;": '\U00002912', + "UpArrowDownArrow;": '\U000021C5', + "UpDownArrow;": '\U00002195', + "UpEquilibrium;": '\U0000296E', + "UpTee;": '\U000022A5', + "UpTeeArrow;": '\U000021A5', + "Uparrow;": '\U000021D1', + "Updownarrow;": '\U000021D5', + "UpperLeftArrow;": '\U00002196', + "UpperRightArrow;": '\U00002197', + "Upsi;": '\U000003D2', + "Upsilon;": '\U000003A5', + "Uring;": '\U0000016E', + "Uscr;": '\U0001D4B0', + "Utilde;": '\U00000168', + "Uuml;": '\U000000DC', + "VDash;": '\U000022AB', + "Vbar;": '\U00002AEB', + "Vcy;": '\U00000412', + "Vdash;": '\U000022A9', + "Vdashl;": '\U00002AE6', + "Vee;": '\U000022C1', + "Verbar;": '\U00002016', + "Vert;": '\U00002016', + "VerticalBar;": '\U00002223', + "VerticalLine;": '\U0000007C', + "VerticalSeparator;": '\U00002758', + "VerticalTilde;": '\U00002240', + "VeryThinSpace;": '\U0000200A', + "Vfr;": '\U0001D519', + "Vopf;": '\U0001D54D', + "Vscr;": '\U0001D4B1', + "Vvdash;": '\U000022AA', + "Wcirc;": '\U00000174', + "Wedge;": '\U000022C0', + "Wfr;": '\U0001D51A', + "Wopf;": '\U0001D54E', + "Wscr;": '\U0001D4B2', + "Xfr;": '\U0001D51B', + "Xi;": '\U0000039E', + "Xopf;": '\U0001D54F', + "Xscr;": '\U0001D4B3', + "YAcy;": '\U0000042F', + "YIcy;": '\U00000407', + "YUcy;": '\U0000042E', + "Yacute;": '\U000000DD', + "Ycirc;": '\U00000176', + "Ycy;": '\U0000042B', + "Yfr;": '\U0001D51C', + "Yopf;": '\U0001D550', + "Yscr;": '\U0001D4B4', + "Yuml;": '\U00000178', + "ZHcy;": '\U00000416', + "Zacute;": '\U00000179', + "Zcaron;": '\U0000017D', + "Zcy;": '\U00000417', + "Zdot;": '\U0000017B', + "ZeroWidthSpace;": '\U0000200B', + "Zeta;": '\U00000396', + "Zfr;": '\U00002128', + "Zopf;": '\U00002124', + "Zscr;": '\U0001D4B5', + "aacute;": '\U000000E1', + "abreve;": '\U00000103', + "ac;": '\U0000223E', + "acd;": '\U0000223F', + "acirc;": '\U000000E2', + "acute;": '\U000000B4', + "acy;": '\U00000430', + "aelig;": '\U000000E6', + "af;": '\U00002061', + "afr;": '\U0001D51E', + "agrave;": '\U000000E0', + "alefsym;": '\U00002135', + "aleph;": '\U00002135', + "alpha;": '\U000003B1', + "amacr;": '\U00000101', + "amalg;": '\U00002A3F', + "amp;": '\U00000026', + "and;": '\U00002227', + "andand;": '\U00002A55', + "andd;": '\U00002A5C', + "andslope;": '\U00002A58', + "andv;": '\U00002A5A', + "ang;": '\U00002220', + "ange;": '\U000029A4', + "angle;": '\U00002220', + "angmsd;": '\U00002221', + "angmsdaa;": '\U000029A8', + "angmsdab;": '\U000029A9', + "angmsdac;": '\U000029AA', + "angmsdad;": '\U000029AB', + "angmsdae;": '\U000029AC', + "angmsdaf;": '\U000029AD', + "angmsdag;": '\U000029AE', + "angmsdah;": '\U000029AF', + "angrt;": '\U0000221F', + "angrtvb;": '\U000022BE', + "angrtvbd;": '\U0000299D', + "angsph;": '\U00002222', + "angst;": '\U000000C5', + "angzarr;": '\U0000237C', + "aogon;": '\U00000105', + "aopf;": '\U0001D552', + "ap;": '\U00002248', + "apE;": '\U00002A70', + "apacir;": '\U00002A6F', + "ape;": '\U0000224A', + "apid;": '\U0000224B', + "apos;": '\U00000027', + "approx;": '\U00002248', + "approxeq;": '\U0000224A', + "aring;": '\U000000E5', + "ascr;": '\U0001D4B6', + "ast;": '\U0000002A', + "asymp;": '\U00002248', + "asympeq;": '\U0000224D', + "atilde;": '\U000000E3', + "auml;": '\U000000E4', + "awconint;": '\U00002233', + "awint;": '\U00002A11', + "bNot;": '\U00002AED', + "backcong;": '\U0000224C', + "backepsilon;": '\U000003F6', + "backprime;": '\U00002035', + "backsim;": '\U0000223D', + "backsimeq;": '\U000022CD', + "barvee;": '\U000022BD', + "barwed;": '\U00002305', + "barwedge;": '\U00002305', + "bbrk;": '\U000023B5', + "bbrktbrk;": '\U000023B6', + "bcong;": '\U0000224C', + "bcy;": '\U00000431', + "bdquo;": '\U0000201E', + "becaus;": '\U00002235', + "because;": '\U00002235', + "bemptyv;": '\U000029B0', + "bepsi;": '\U000003F6', + "bernou;": '\U0000212C', + "beta;": '\U000003B2', + "beth;": '\U00002136', + "between;": '\U0000226C', + "bfr;": '\U0001D51F', + "bigcap;": '\U000022C2', + "bigcirc;": '\U000025EF', + "bigcup;": '\U000022C3', + "bigodot;": '\U00002A00', + "bigoplus;": '\U00002A01', + "bigotimes;": '\U00002A02', + "bigsqcup;": '\U00002A06', + "bigstar;": '\U00002605', + "bigtriangledown;": '\U000025BD', + "bigtriangleup;": '\U000025B3', + "biguplus;": '\U00002A04', + "bigvee;": '\U000022C1', + "bigwedge;": '\U000022C0', + "bkarow;": '\U0000290D', + "blacklozenge;": '\U000029EB', + "blacksquare;": '\U000025AA', + "blacktriangle;": '\U000025B4', + "blacktriangledown;": '\U000025BE', + "blacktriangleleft;": '\U000025C2', + "blacktriangleright;": '\U000025B8', + "blank;": '\U00002423', + "blk12;": '\U00002592', + "blk14;": '\U00002591', + "blk34;": '\U00002593', + "block;": '\U00002588', + "bnot;": '\U00002310', + "bopf;": '\U0001D553', + "bot;": '\U000022A5', + "bottom;": '\U000022A5', + "bowtie;": '\U000022C8', + "boxDL;": '\U00002557', + "boxDR;": '\U00002554', + "boxDl;": '\U00002556', + "boxDr;": '\U00002553', + "boxH;": '\U00002550', + "boxHD;": '\U00002566', + "boxHU;": '\U00002569', + "boxHd;": '\U00002564', + "boxHu;": '\U00002567', + "boxUL;": '\U0000255D', + "boxUR;": '\U0000255A', + "boxUl;": '\U0000255C', + "boxUr;": '\U00002559', + "boxV;": '\U00002551', + "boxVH;": '\U0000256C', + "boxVL;": '\U00002563', + "boxVR;": '\U00002560', + "boxVh;": '\U0000256B', + "boxVl;": '\U00002562', + "boxVr;": '\U0000255F', + "boxbox;": '\U000029C9', + "boxdL;": '\U00002555', + "boxdR;": '\U00002552', + "boxdl;": '\U00002510', + "boxdr;": '\U0000250C', + "boxh;": '\U00002500', + "boxhD;": '\U00002565', + "boxhU;": '\U00002568', + "boxhd;": '\U0000252C', + "boxhu;": '\U00002534', + "boxminus;": '\U0000229F', + "boxplus;": '\U0000229E', + "boxtimes;": '\U000022A0', + "boxuL;": '\U0000255B', + "boxuR;": '\U00002558', + "boxul;": '\U00002518', + "boxur;": '\U00002514', + "boxv;": '\U00002502', + "boxvH;": '\U0000256A', + "boxvL;": '\U00002561', + "boxvR;": '\U0000255E', + "boxvh;": '\U0000253C', + "boxvl;": '\U00002524', + "boxvr;": '\U0000251C', + "bprime;": '\U00002035', + "breve;": '\U000002D8', + "brvbar;": '\U000000A6', + "bscr;": '\U0001D4B7', + "bsemi;": '\U0000204F', + "bsim;": '\U0000223D', + "bsime;": '\U000022CD', + "bsol;": '\U0000005C', + "bsolb;": '\U000029C5', + "bsolhsub;": '\U000027C8', + "bull;": '\U00002022', + "bullet;": '\U00002022', + "bump;": '\U0000224E', + "bumpE;": '\U00002AAE', + "bumpe;": '\U0000224F', + "bumpeq;": '\U0000224F', + "cacute;": '\U00000107', + "cap;": '\U00002229', + "capand;": '\U00002A44', + "capbrcup;": '\U00002A49', + "capcap;": '\U00002A4B', + "capcup;": '\U00002A47', + "capdot;": '\U00002A40', + "caret;": '\U00002041', + "caron;": '\U000002C7', + "ccaps;": '\U00002A4D', + "ccaron;": '\U0000010D', + "ccedil;": '\U000000E7', + "ccirc;": '\U00000109', + "ccups;": '\U00002A4C', + "ccupssm;": '\U00002A50', + "cdot;": '\U0000010B', + "cedil;": '\U000000B8', + "cemptyv;": '\U000029B2', + "cent;": '\U000000A2', + "centerdot;": '\U000000B7', + "cfr;": '\U0001D520', + "chcy;": '\U00000447', + "check;": '\U00002713', + "checkmark;": '\U00002713', + "chi;": '\U000003C7', + "cir;": '\U000025CB', + "cirE;": '\U000029C3', + "circ;": '\U000002C6', + "circeq;": '\U00002257', + "circlearrowleft;": '\U000021BA', + "circlearrowright;": '\U000021BB', + "circledR;": '\U000000AE', + "circledS;": '\U000024C8', + "circledast;": '\U0000229B', + "circledcirc;": '\U0000229A', + "circleddash;": '\U0000229D', + "cire;": '\U00002257', + "cirfnint;": '\U00002A10', + "cirmid;": '\U00002AEF', + "cirscir;": '\U000029C2', + "clubs;": '\U00002663', + "clubsuit;": '\U00002663', + "colon;": '\U0000003A', + "colone;": '\U00002254', + "coloneq;": '\U00002254', + "comma;": '\U0000002C', + "commat;": '\U00000040', + "comp;": '\U00002201', + "compfn;": '\U00002218', + "complement;": '\U00002201', + "complexes;": '\U00002102', + "cong;": '\U00002245', + "congdot;": '\U00002A6D', + "conint;": '\U0000222E', + "copf;": '\U0001D554', + "coprod;": '\U00002210', + "copy;": '\U000000A9', + "copysr;": '\U00002117', + "crarr;": '\U000021B5', + "cross;": '\U00002717', + "cscr;": '\U0001D4B8', + "csub;": '\U00002ACF', + "csube;": '\U00002AD1', + "csup;": '\U00002AD0', + "csupe;": '\U00002AD2', + "ctdot;": '\U000022EF', + "cudarrl;": '\U00002938', + "cudarrr;": '\U00002935', + "cuepr;": '\U000022DE', + "cuesc;": '\U000022DF', + "cularr;": '\U000021B6', + "cularrp;": '\U0000293D', + "cup;": '\U0000222A', + "cupbrcap;": '\U00002A48', + "cupcap;": '\U00002A46', + "cupcup;": '\U00002A4A', + "cupdot;": '\U0000228D', + "cupor;": '\U00002A45', + "curarr;": '\U000021B7', + "curarrm;": '\U0000293C', + "curlyeqprec;": '\U000022DE', + "curlyeqsucc;": '\U000022DF', + "curlyvee;": '\U000022CE', + "curlywedge;": '\U000022CF', + "curren;": '\U000000A4', + "curvearrowleft;": '\U000021B6', + "curvearrowright;": '\U000021B7', + "cuvee;": '\U000022CE', + "cuwed;": '\U000022CF', + "cwconint;": '\U00002232', + "cwint;": '\U00002231', + "cylcty;": '\U0000232D', + "dArr;": '\U000021D3', + "dHar;": '\U00002965', + "dagger;": '\U00002020', + "daleth;": '\U00002138', + "darr;": '\U00002193', + "dash;": '\U00002010', + "dashv;": '\U000022A3', + "dbkarow;": '\U0000290F', + "dblac;": '\U000002DD', + "dcaron;": '\U0000010F', + "dcy;": '\U00000434', + "dd;": '\U00002146', + "ddagger;": '\U00002021', + "ddarr;": '\U000021CA', + "ddotseq;": '\U00002A77', + "deg;": '\U000000B0', + "delta;": '\U000003B4', + "demptyv;": '\U000029B1', + "dfisht;": '\U0000297F', + "dfr;": '\U0001D521', + "dharl;": '\U000021C3', + "dharr;": '\U000021C2', + "diam;": '\U000022C4', + "diamond;": '\U000022C4', + "diamondsuit;": '\U00002666', + "diams;": '\U00002666', + "die;": '\U000000A8', + "digamma;": '\U000003DD', + "disin;": '\U000022F2', + "div;": '\U000000F7', + "divide;": '\U000000F7', + "divideontimes;": '\U000022C7', + "divonx;": '\U000022C7', + "djcy;": '\U00000452', + "dlcorn;": '\U0000231E', + "dlcrop;": '\U0000230D', + "dollar;": '\U00000024', + "dopf;": '\U0001D555', + "dot;": '\U000002D9', + "doteq;": '\U00002250', + "doteqdot;": '\U00002251', + "dotminus;": '\U00002238', + "dotplus;": '\U00002214', + "dotsquare;": '\U000022A1', + "doublebarwedge;": '\U00002306', + "downarrow;": '\U00002193', + "downdownarrows;": '\U000021CA', + "downharpoonleft;": '\U000021C3', + "downharpoonright;": '\U000021C2', + "drbkarow;": '\U00002910', + "drcorn;": '\U0000231F', + "drcrop;": '\U0000230C', + "dscr;": '\U0001D4B9', + "dscy;": '\U00000455', + "dsol;": '\U000029F6', + "dstrok;": '\U00000111', + "dtdot;": '\U000022F1', + "dtri;": '\U000025BF', + "dtrif;": '\U000025BE', + "duarr;": '\U000021F5', + "duhar;": '\U0000296F', + "dwangle;": '\U000029A6', + "dzcy;": '\U0000045F', + "dzigrarr;": '\U000027FF', + "eDDot;": '\U00002A77', + "eDot;": '\U00002251', + "eacute;": '\U000000E9', + "easter;": '\U00002A6E', + "ecaron;": '\U0000011B', + "ecir;": '\U00002256', + "ecirc;": '\U000000EA', + "ecolon;": '\U00002255', + "ecy;": '\U0000044D', + "edot;": '\U00000117', + "ee;": '\U00002147', + "efDot;": '\U00002252', + "efr;": '\U0001D522', + "eg;": '\U00002A9A', + "egrave;": '\U000000E8', + "egs;": '\U00002A96', + "egsdot;": '\U00002A98', + "el;": '\U00002A99', + "elinters;": '\U000023E7', + "ell;": '\U00002113', + "els;": '\U00002A95', + "elsdot;": '\U00002A97', + "emacr;": '\U00000113', + "empty;": '\U00002205', + "emptyset;": '\U00002205', + "emptyv;": '\U00002205', + "emsp;": '\U00002003', + "emsp13;": '\U00002004', + "emsp14;": '\U00002005', + "eng;": '\U0000014B', + "ensp;": '\U00002002', + "eogon;": '\U00000119', + "eopf;": '\U0001D556', + "epar;": '\U000022D5', + "eparsl;": '\U000029E3', + "eplus;": '\U00002A71', + "epsi;": '\U000003B5', + "epsilon;": '\U000003B5', + "epsiv;": '\U000003F5', + "eqcirc;": '\U00002256', + "eqcolon;": '\U00002255', + "eqsim;": '\U00002242', + "eqslantgtr;": '\U00002A96', + "eqslantless;": '\U00002A95', + "equals;": '\U0000003D', + "equest;": '\U0000225F', + "equiv;": '\U00002261', + "equivDD;": '\U00002A78', + "eqvparsl;": '\U000029E5', + "erDot;": '\U00002253', + "erarr;": '\U00002971', + "escr;": '\U0000212F', + "esdot;": '\U00002250', + "esim;": '\U00002242', + "eta;": '\U000003B7', + "eth;": '\U000000F0', + "euml;": '\U000000EB', + "euro;": '\U000020AC', + "excl;": '\U00000021', + "exist;": '\U00002203', + "expectation;": '\U00002130', + "exponentiale;": '\U00002147', + "fallingdotseq;": '\U00002252', + "fcy;": '\U00000444', + "female;": '\U00002640', + "ffilig;": '\U0000FB03', + "fflig;": '\U0000FB00', + "ffllig;": '\U0000FB04', + "ffr;": '\U0001D523', + "filig;": '\U0000FB01', + "flat;": '\U0000266D', + "fllig;": '\U0000FB02', + "fltns;": '\U000025B1', + "fnof;": '\U00000192', + "fopf;": '\U0001D557', + "forall;": '\U00002200', + "fork;": '\U000022D4', + "forkv;": '\U00002AD9', + "fpartint;": '\U00002A0D', + "frac12;": '\U000000BD', + "frac13;": '\U00002153', + "frac14;": '\U000000BC', + "frac15;": '\U00002155', + "frac16;": '\U00002159', + "frac18;": '\U0000215B', + "frac23;": '\U00002154', + "frac25;": '\U00002156', + "frac34;": '\U000000BE', + "frac35;": '\U00002157', + "frac38;": '\U0000215C', + "frac45;": '\U00002158', + "frac56;": '\U0000215A', + "frac58;": '\U0000215D', + "frac78;": '\U0000215E', + "frasl;": '\U00002044', + "frown;": '\U00002322', + "fscr;": '\U0001D4BB', + "gE;": '\U00002267', + "gEl;": '\U00002A8C', + "gacute;": '\U000001F5', + "gamma;": '\U000003B3', + "gammad;": '\U000003DD', + "gap;": '\U00002A86', + "gbreve;": '\U0000011F', + "gcirc;": '\U0000011D', + "gcy;": '\U00000433', + "gdot;": '\U00000121', + "ge;": '\U00002265', + "gel;": '\U000022DB', + "geq;": '\U00002265', + "geqq;": '\U00002267', + "geqslant;": '\U00002A7E', + "ges;": '\U00002A7E', + "gescc;": '\U00002AA9', + "gesdot;": '\U00002A80', + "gesdoto;": '\U00002A82', + "gesdotol;": '\U00002A84', + "gesles;": '\U00002A94', + "gfr;": '\U0001D524', + "gg;": '\U0000226B', + "ggg;": '\U000022D9', + "gimel;": '\U00002137', + "gjcy;": '\U00000453', + "gl;": '\U00002277', + "glE;": '\U00002A92', + "gla;": '\U00002AA5', + "glj;": '\U00002AA4', + "gnE;": '\U00002269', + "gnap;": '\U00002A8A', + "gnapprox;": '\U00002A8A', + "gne;": '\U00002A88', + "gneq;": '\U00002A88', + "gneqq;": '\U00002269', + "gnsim;": '\U000022E7', + "gopf;": '\U0001D558', + "grave;": '\U00000060', + "gscr;": '\U0000210A', + "gsim;": '\U00002273', + "gsime;": '\U00002A8E', + "gsiml;": '\U00002A90', + "gt;": '\U0000003E', + "gtcc;": '\U00002AA7', + "gtcir;": '\U00002A7A', + "gtdot;": '\U000022D7', + "gtlPar;": '\U00002995', + "gtquest;": '\U00002A7C', + "gtrapprox;": '\U00002A86', + "gtrarr;": '\U00002978', + "gtrdot;": '\U000022D7', + "gtreqless;": '\U000022DB', + "gtreqqless;": '\U00002A8C', + "gtrless;": '\U00002277', + "gtrsim;": '\U00002273', + "hArr;": '\U000021D4', + "hairsp;": '\U0000200A', + "half;": '\U000000BD', + "hamilt;": '\U0000210B', + "hardcy;": '\U0000044A', + "harr;": '\U00002194', + "harrcir;": '\U00002948', + "harrw;": '\U000021AD', + "hbar;": '\U0000210F', + "hcirc;": '\U00000125', + "hearts;": '\U00002665', + "heartsuit;": '\U00002665', + "hellip;": '\U00002026', + "hercon;": '\U000022B9', + "hfr;": '\U0001D525', + "hksearow;": '\U00002925', + "hkswarow;": '\U00002926', + "hoarr;": '\U000021FF', + "homtht;": '\U0000223B', + "hookleftarrow;": '\U000021A9', + "hookrightarrow;": '\U000021AA', + "hopf;": '\U0001D559', + "horbar;": '\U00002015', + "hscr;": '\U0001D4BD', + "hslash;": '\U0000210F', + "hstrok;": '\U00000127', + "hybull;": '\U00002043', + "hyphen;": '\U00002010', + "iacute;": '\U000000ED', + "ic;": '\U00002063', + "icirc;": '\U000000EE', + "icy;": '\U00000438', + "iecy;": '\U00000435', + "iexcl;": '\U000000A1', + "iff;": '\U000021D4', + "ifr;": '\U0001D526', + "igrave;": '\U000000EC', + "ii;": '\U00002148', + "iiiint;": '\U00002A0C', + "iiint;": '\U0000222D', + "iinfin;": '\U000029DC', + "iiota;": '\U00002129', + "ijlig;": '\U00000133', + "imacr;": '\U0000012B', + "image;": '\U00002111', + "imagline;": '\U00002110', + "imagpart;": '\U00002111', + "imath;": '\U00000131', + "imof;": '\U000022B7', + "imped;": '\U000001B5', + "in;": '\U00002208', + "incare;": '\U00002105', + "infin;": '\U0000221E', + "infintie;": '\U000029DD', + "inodot;": '\U00000131', + "int;": '\U0000222B', + "intcal;": '\U000022BA', + "integers;": '\U00002124', + "intercal;": '\U000022BA', + "intlarhk;": '\U00002A17', + "intprod;": '\U00002A3C', + "iocy;": '\U00000451', + "iogon;": '\U0000012F', + "iopf;": '\U0001D55A', + "iota;": '\U000003B9', + "iprod;": '\U00002A3C', + "iquest;": '\U000000BF', + "iscr;": '\U0001D4BE', + "isin;": '\U00002208', + "isinE;": '\U000022F9', + "isindot;": '\U000022F5', + "isins;": '\U000022F4', + "isinsv;": '\U000022F3', + "isinv;": '\U00002208', + "it;": '\U00002062', + "itilde;": '\U00000129', + "iukcy;": '\U00000456', + "iuml;": '\U000000EF', + "jcirc;": '\U00000135', + "jcy;": '\U00000439', + "jfr;": '\U0001D527', + "jmath;": '\U00000237', + "jopf;": '\U0001D55B', + "jscr;": '\U0001D4BF', + "jsercy;": '\U00000458', + "jukcy;": '\U00000454', + "kappa;": '\U000003BA', + "kappav;": '\U000003F0', + "kcedil;": '\U00000137', + "kcy;": '\U0000043A', + "kfr;": '\U0001D528', + "kgreen;": '\U00000138', + "khcy;": '\U00000445', + "kjcy;": '\U0000045C', + "kopf;": '\U0001D55C', + "kscr;": '\U0001D4C0', + "lAarr;": '\U000021DA', + "lArr;": '\U000021D0', + "lAtail;": '\U0000291B', + "lBarr;": '\U0000290E', + "lE;": '\U00002266', + "lEg;": '\U00002A8B', + "lHar;": '\U00002962', + "lacute;": '\U0000013A', + "laemptyv;": '\U000029B4', + "lagran;": '\U00002112', + "lambda;": '\U000003BB', + "lang;": '\U000027E8', + "langd;": '\U00002991', + "langle;": '\U000027E8', + "lap;": '\U00002A85', + "laquo;": '\U000000AB', + "larr;": '\U00002190', + "larrb;": '\U000021E4', + "larrbfs;": '\U0000291F', + "larrfs;": '\U0000291D', + "larrhk;": '\U000021A9', + "larrlp;": '\U000021AB', + "larrpl;": '\U00002939', + "larrsim;": '\U00002973', + "larrtl;": '\U000021A2', + "lat;": '\U00002AAB', + "latail;": '\U00002919', + "late;": '\U00002AAD', + "lbarr;": '\U0000290C', + "lbbrk;": '\U00002772', + "lbrace;": '\U0000007B', + "lbrack;": '\U0000005B', + "lbrke;": '\U0000298B', + "lbrksld;": '\U0000298F', + "lbrkslu;": '\U0000298D', + "lcaron;": '\U0000013E', + "lcedil;": '\U0000013C', + "lceil;": '\U00002308', + "lcub;": '\U0000007B', + "lcy;": '\U0000043B', + "ldca;": '\U00002936', + "ldquo;": '\U0000201C', + "ldquor;": '\U0000201E', + "ldrdhar;": '\U00002967', + "ldrushar;": '\U0000294B', + "ldsh;": '\U000021B2', + "le;": '\U00002264', + "leftarrow;": '\U00002190', + "leftarrowtail;": '\U000021A2', + "leftharpoondown;": '\U000021BD', + "leftharpoonup;": '\U000021BC', + "leftleftarrows;": '\U000021C7', + "leftrightarrow;": '\U00002194', + "leftrightarrows;": '\U000021C6', + "leftrightharpoons;": '\U000021CB', + "leftrightsquigarrow;": '\U000021AD', + "leftthreetimes;": '\U000022CB', + "leg;": '\U000022DA', + "leq;": '\U00002264', + "leqq;": '\U00002266', + "leqslant;": '\U00002A7D', + "les;": '\U00002A7D', + "lescc;": '\U00002AA8', + "lesdot;": '\U00002A7F', + "lesdoto;": '\U00002A81', + "lesdotor;": '\U00002A83', + "lesges;": '\U00002A93', + "lessapprox;": '\U00002A85', + "lessdot;": '\U000022D6', + "lesseqgtr;": '\U000022DA', + "lesseqqgtr;": '\U00002A8B', + "lessgtr;": '\U00002276', + "lesssim;": '\U00002272', + "lfisht;": '\U0000297C', + "lfloor;": '\U0000230A', + "lfr;": '\U0001D529', + "lg;": '\U00002276', + "lgE;": '\U00002A91', + "lhard;": '\U000021BD', + "lharu;": '\U000021BC', + "lharul;": '\U0000296A', + "lhblk;": '\U00002584', + "ljcy;": '\U00000459', + "ll;": '\U0000226A', + "llarr;": '\U000021C7', + "llcorner;": '\U0000231E', + "llhard;": '\U0000296B', + "lltri;": '\U000025FA', + "lmidot;": '\U00000140', + "lmoust;": '\U000023B0', + "lmoustache;": '\U000023B0', + "lnE;": '\U00002268', + "lnap;": '\U00002A89', + "lnapprox;": '\U00002A89', + "lne;": '\U00002A87', + "lneq;": '\U00002A87', + "lneqq;": '\U00002268', + "lnsim;": '\U000022E6', + "loang;": '\U000027EC', + "loarr;": '\U000021FD', + "lobrk;": '\U000027E6', + "longleftarrow;": '\U000027F5', + "longleftrightarrow;": '\U000027F7', + "longmapsto;": '\U000027FC', + "longrightarrow;": '\U000027F6', + "looparrowleft;": '\U000021AB', + "looparrowright;": '\U000021AC', + "lopar;": '\U00002985', + "lopf;": '\U0001D55D', + "loplus;": '\U00002A2D', + "lotimes;": '\U00002A34', + "lowast;": '\U00002217', + "lowbar;": '\U0000005F', + "loz;": '\U000025CA', + "lozenge;": '\U000025CA', + "lozf;": '\U000029EB', + "lpar;": '\U00000028', + "lparlt;": '\U00002993', + "lrarr;": '\U000021C6', + "lrcorner;": '\U0000231F', + "lrhar;": '\U000021CB', + "lrhard;": '\U0000296D', + "lrm;": '\U0000200E', + "lrtri;": '\U000022BF', + "lsaquo;": '\U00002039', + "lscr;": '\U0001D4C1', + "lsh;": '\U000021B0', + "lsim;": '\U00002272', + "lsime;": '\U00002A8D', + "lsimg;": '\U00002A8F', + "lsqb;": '\U0000005B', + "lsquo;": '\U00002018', + "lsquor;": '\U0000201A', + "lstrok;": '\U00000142', + "lt;": '\U0000003C', + "ltcc;": '\U00002AA6', + "ltcir;": '\U00002A79', + "ltdot;": '\U000022D6', + "lthree;": '\U000022CB', + "ltimes;": '\U000022C9', + "ltlarr;": '\U00002976', + "ltquest;": '\U00002A7B', + "ltrPar;": '\U00002996', + "ltri;": '\U000025C3', + "ltrie;": '\U000022B4', + "ltrif;": '\U000025C2', + "lurdshar;": '\U0000294A', + "luruhar;": '\U00002966', + "mDDot;": '\U0000223A', + "macr;": '\U000000AF', + "male;": '\U00002642', + "malt;": '\U00002720', + "maltese;": '\U00002720', + "map;": '\U000021A6', + "mapsto;": '\U000021A6', + "mapstodown;": '\U000021A7', + "mapstoleft;": '\U000021A4', + "mapstoup;": '\U000021A5', + "marker;": '\U000025AE', + "mcomma;": '\U00002A29', + "mcy;": '\U0000043C', + "mdash;": '\U00002014', + "measuredangle;": '\U00002221', + "mfr;": '\U0001D52A', + "mho;": '\U00002127', + "micro;": '\U000000B5', + "mid;": '\U00002223', + "midast;": '\U0000002A', + "midcir;": '\U00002AF0', + "middot;": '\U000000B7', + "minus;": '\U00002212', + "minusb;": '\U0000229F', + "minusd;": '\U00002238', + "minusdu;": '\U00002A2A', + "mlcp;": '\U00002ADB', + "mldr;": '\U00002026', + "mnplus;": '\U00002213', + "models;": '\U000022A7', + "mopf;": '\U0001D55E', + "mp;": '\U00002213', + "mscr;": '\U0001D4C2', + "mstpos;": '\U0000223E', + "mu;": '\U000003BC', + "multimap;": '\U000022B8', + "mumap;": '\U000022B8', + "nLeftarrow;": '\U000021CD', + "nLeftrightarrow;": '\U000021CE', + "nRightarrow;": '\U000021CF', + "nVDash;": '\U000022AF', + "nVdash;": '\U000022AE', + "nabla;": '\U00002207', + "nacute;": '\U00000144', + "nap;": '\U00002249', + "napos;": '\U00000149', + "napprox;": '\U00002249', + "natur;": '\U0000266E', + "natural;": '\U0000266E', + "naturals;": '\U00002115', + "nbsp;": '\U000000A0', + "ncap;": '\U00002A43', + "ncaron;": '\U00000148', + "ncedil;": '\U00000146', + "ncong;": '\U00002247', + "ncup;": '\U00002A42', + "ncy;": '\U0000043D', + "ndash;": '\U00002013', + "ne;": '\U00002260', + "neArr;": '\U000021D7', + "nearhk;": '\U00002924', + "nearr;": '\U00002197', + "nearrow;": '\U00002197', + "nequiv;": '\U00002262', + "nesear;": '\U00002928', + "nexist;": '\U00002204', + "nexists;": '\U00002204', + "nfr;": '\U0001D52B', + "nge;": '\U00002271', + "ngeq;": '\U00002271', + "ngsim;": '\U00002275', + "ngt;": '\U0000226F', + "ngtr;": '\U0000226F', + "nhArr;": '\U000021CE', + "nharr;": '\U000021AE', + "nhpar;": '\U00002AF2', + "ni;": '\U0000220B', + "nis;": '\U000022FC', + "nisd;": '\U000022FA', + "niv;": '\U0000220B', + "njcy;": '\U0000045A', + "nlArr;": '\U000021CD', + "nlarr;": '\U0000219A', + "nldr;": '\U00002025', + "nle;": '\U00002270', + "nleftarrow;": '\U0000219A', + "nleftrightarrow;": '\U000021AE', + "nleq;": '\U00002270', + "nless;": '\U0000226E', + "nlsim;": '\U00002274', + "nlt;": '\U0000226E', + "nltri;": '\U000022EA', + "nltrie;": '\U000022EC', + "nmid;": '\U00002224', + "nopf;": '\U0001D55F', + "not;": '\U000000AC', + "notin;": '\U00002209', + "notinva;": '\U00002209', + "notinvb;": '\U000022F7', + "notinvc;": '\U000022F6', + "notni;": '\U0000220C', + "notniva;": '\U0000220C', + "notnivb;": '\U000022FE', + "notnivc;": '\U000022FD', + "npar;": '\U00002226', + "nparallel;": '\U00002226', + "npolint;": '\U00002A14', + "npr;": '\U00002280', + "nprcue;": '\U000022E0', + "nprec;": '\U00002280', + "nrArr;": '\U000021CF', + "nrarr;": '\U0000219B', + "nrightarrow;": '\U0000219B', + "nrtri;": '\U000022EB', + "nrtrie;": '\U000022ED', + "nsc;": '\U00002281', + "nsccue;": '\U000022E1', + "nscr;": '\U0001D4C3', + "nshortmid;": '\U00002224', + "nshortparallel;": '\U00002226', + "nsim;": '\U00002241', + "nsime;": '\U00002244', + "nsimeq;": '\U00002244', + "nsmid;": '\U00002224', + "nspar;": '\U00002226', + "nsqsube;": '\U000022E2', + "nsqsupe;": '\U000022E3', + "nsub;": '\U00002284', + "nsube;": '\U00002288', + "nsubseteq;": '\U00002288', + "nsucc;": '\U00002281', + "nsup;": '\U00002285', + "nsupe;": '\U00002289', + "nsupseteq;": '\U00002289', + "ntgl;": '\U00002279', + "ntilde;": '\U000000F1', + "ntlg;": '\U00002278', + "ntriangleleft;": '\U000022EA', + "ntrianglelefteq;": '\U000022EC', + "ntriangleright;": '\U000022EB', + "ntrianglerighteq;": '\U000022ED', + "nu;": '\U000003BD', + "num;": '\U00000023', + "numero;": '\U00002116', + "numsp;": '\U00002007', + "nvDash;": '\U000022AD', + "nvHarr;": '\U00002904', + "nvdash;": '\U000022AC', + "nvinfin;": '\U000029DE', + "nvlArr;": '\U00002902', + "nvrArr;": '\U00002903', + "nwArr;": '\U000021D6', + "nwarhk;": '\U00002923', + "nwarr;": '\U00002196', + "nwarrow;": '\U00002196', + "nwnear;": '\U00002927', + "oS;": '\U000024C8', + "oacute;": '\U000000F3', + "oast;": '\U0000229B', + "ocir;": '\U0000229A', + "ocirc;": '\U000000F4', + "ocy;": '\U0000043E', + "odash;": '\U0000229D', + "odblac;": '\U00000151', + "odiv;": '\U00002A38', + "odot;": '\U00002299', + "odsold;": '\U000029BC', + "oelig;": '\U00000153', + "ofcir;": '\U000029BF', + "ofr;": '\U0001D52C', + "ogon;": '\U000002DB', + "ograve;": '\U000000F2', + "ogt;": '\U000029C1', + "ohbar;": '\U000029B5', + "ohm;": '\U000003A9', + "oint;": '\U0000222E', + "olarr;": '\U000021BA', + "olcir;": '\U000029BE', + "olcross;": '\U000029BB', + "oline;": '\U0000203E', + "olt;": '\U000029C0', + "omacr;": '\U0000014D', + "omega;": '\U000003C9', + "omicron;": '\U000003BF', + "omid;": '\U000029B6', + "ominus;": '\U00002296', + "oopf;": '\U0001D560', + "opar;": '\U000029B7', + "operp;": '\U000029B9', + "oplus;": '\U00002295', + "or;": '\U00002228', + "orarr;": '\U000021BB', + "ord;": '\U00002A5D', + "order;": '\U00002134', + "orderof;": '\U00002134', + "ordf;": '\U000000AA', + "ordm;": '\U000000BA', + "origof;": '\U000022B6', + "oror;": '\U00002A56', + "orslope;": '\U00002A57', + "orv;": '\U00002A5B', + "oscr;": '\U00002134', + "oslash;": '\U000000F8', + "osol;": '\U00002298', + "otilde;": '\U000000F5', + "otimes;": '\U00002297', + "otimesas;": '\U00002A36', + "ouml;": '\U000000F6', + "ovbar;": '\U0000233D', + "par;": '\U00002225', + "para;": '\U000000B6', + "parallel;": '\U00002225', + "parsim;": '\U00002AF3', + "parsl;": '\U00002AFD', + "part;": '\U00002202', + "pcy;": '\U0000043F', + "percnt;": '\U00000025', + "period;": '\U0000002E', + "permil;": '\U00002030', + "perp;": '\U000022A5', + "pertenk;": '\U00002031', + "pfr;": '\U0001D52D', + "phi;": '\U000003C6', + "phiv;": '\U000003D5', + "phmmat;": '\U00002133', + "phone;": '\U0000260E', + "pi;": '\U000003C0', + "pitchfork;": '\U000022D4', + "piv;": '\U000003D6', + "planck;": '\U0000210F', + "planckh;": '\U0000210E', + "plankv;": '\U0000210F', + "plus;": '\U0000002B', + "plusacir;": '\U00002A23', + "plusb;": '\U0000229E', + "pluscir;": '\U00002A22', + "plusdo;": '\U00002214', + "plusdu;": '\U00002A25', + "pluse;": '\U00002A72', + "plusmn;": '\U000000B1', + "plussim;": '\U00002A26', + "plustwo;": '\U00002A27', + "pm;": '\U000000B1', + "pointint;": '\U00002A15', + "popf;": '\U0001D561', + "pound;": '\U000000A3', + "pr;": '\U0000227A', + "prE;": '\U00002AB3', + "prap;": '\U00002AB7', + "prcue;": '\U0000227C', + "pre;": '\U00002AAF', + "prec;": '\U0000227A', + "precapprox;": '\U00002AB7', + "preccurlyeq;": '\U0000227C', + "preceq;": '\U00002AAF', + "precnapprox;": '\U00002AB9', + "precneqq;": '\U00002AB5', + "precnsim;": '\U000022E8', + "precsim;": '\U0000227E', + "prime;": '\U00002032', + "primes;": '\U00002119', + "prnE;": '\U00002AB5', + "prnap;": '\U00002AB9', + "prnsim;": '\U000022E8', + "prod;": '\U0000220F', + "profalar;": '\U0000232E', + "profline;": '\U00002312', + "profsurf;": '\U00002313', + "prop;": '\U0000221D', + "propto;": '\U0000221D', + "prsim;": '\U0000227E', + "prurel;": '\U000022B0', + "pscr;": '\U0001D4C5', + "psi;": '\U000003C8', + "puncsp;": '\U00002008', + "qfr;": '\U0001D52E', + "qint;": '\U00002A0C', + "qopf;": '\U0001D562', + "qprime;": '\U00002057', + "qscr;": '\U0001D4C6', + "quaternions;": '\U0000210D', + "quatint;": '\U00002A16', + "quest;": '\U0000003F', + "questeq;": '\U0000225F', + "quot;": '\U00000022', + "rAarr;": '\U000021DB', + "rArr;": '\U000021D2', + "rAtail;": '\U0000291C', + "rBarr;": '\U0000290F', + "rHar;": '\U00002964', + "racute;": '\U00000155', + "radic;": '\U0000221A', + "raemptyv;": '\U000029B3', + "rang;": '\U000027E9', + "rangd;": '\U00002992', + "range;": '\U000029A5', + "rangle;": '\U000027E9', + "raquo;": '\U000000BB', + "rarr;": '\U00002192', + "rarrap;": '\U00002975', + "rarrb;": '\U000021E5', + "rarrbfs;": '\U00002920', + "rarrc;": '\U00002933', + "rarrfs;": '\U0000291E', + "rarrhk;": '\U000021AA', + "rarrlp;": '\U000021AC', + "rarrpl;": '\U00002945', + "rarrsim;": '\U00002974', + "rarrtl;": '\U000021A3', + "rarrw;": '\U0000219D', + "ratail;": '\U0000291A', + "ratio;": '\U00002236', + "rationals;": '\U0000211A', + "rbarr;": '\U0000290D', + "rbbrk;": '\U00002773', + "rbrace;": '\U0000007D', + "rbrack;": '\U0000005D', + "rbrke;": '\U0000298C', + "rbrksld;": '\U0000298E', + "rbrkslu;": '\U00002990', + "rcaron;": '\U00000159', + "rcedil;": '\U00000157', + "rceil;": '\U00002309', + "rcub;": '\U0000007D', + "rcy;": '\U00000440', + "rdca;": '\U00002937', + "rdldhar;": '\U00002969', + "rdquo;": '\U0000201D', + "rdquor;": '\U0000201D', + "rdsh;": '\U000021B3', + "real;": '\U0000211C', + "realine;": '\U0000211B', + "realpart;": '\U0000211C', + "reals;": '\U0000211D', + "rect;": '\U000025AD', + "reg;": '\U000000AE', + "rfisht;": '\U0000297D', + "rfloor;": '\U0000230B', + "rfr;": '\U0001D52F', + "rhard;": '\U000021C1', + "rharu;": '\U000021C0', + "rharul;": '\U0000296C', + "rho;": '\U000003C1', + "rhov;": '\U000003F1', + "rightarrow;": '\U00002192', + "rightarrowtail;": '\U000021A3', + "rightharpoondown;": '\U000021C1', + "rightharpoonup;": '\U000021C0', + "rightleftarrows;": '\U000021C4', + "rightleftharpoons;": '\U000021CC', + "rightrightarrows;": '\U000021C9', + "rightsquigarrow;": '\U0000219D', + "rightthreetimes;": '\U000022CC', + "ring;": '\U000002DA', + "risingdotseq;": '\U00002253', + "rlarr;": '\U000021C4', + "rlhar;": '\U000021CC', + "rlm;": '\U0000200F', + "rmoust;": '\U000023B1', + "rmoustache;": '\U000023B1', + "rnmid;": '\U00002AEE', + "roang;": '\U000027ED', + "roarr;": '\U000021FE', + "robrk;": '\U000027E7', + "ropar;": '\U00002986', + "ropf;": '\U0001D563', + "roplus;": '\U00002A2E', + "rotimes;": '\U00002A35', + "rpar;": '\U00000029', + "rpargt;": '\U00002994', + "rppolint;": '\U00002A12', + "rrarr;": '\U000021C9', + "rsaquo;": '\U0000203A', + "rscr;": '\U0001D4C7', + "rsh;": '\U000021B1', + "rsqb;": '\U0000005D', + "rsquo;": '\U00002019', + "rsquor;": '\U00002019', + "rthree;": '\U000022CC', + "rtimes;": '\U000022CA', + "rtri;": '\U000025B9', + "rtrie;": '\U000022B5', + "rtrif;": '\U000025B8', + "rtriltri;": '\U000029CE', + "ruluhar;": '\U00002968', + "rx;": '\U0000211E', + "sacute;": '\U0000015B', + "sbquo;": '\U0000201A', + "sc;": '\U0000227B', + "scE;": '\U00002AB4', + "scap;": '\U00002AB8', + "scaron;": '\U00000161', + "sccue;": '\U0000227D', + "sce;": '\U00002AB0', + "scedil;": '\U0000015F', + "scirc;": '\U0000015D', + "scnE;": '\U00002AB6', + "scnap;": '\U00002ABA', + "scnsim;": '\U000022E9', + "scpolint;": '\U00002A13', + "scsim;": '\U0000227F', + "scy;": '\U00000441', + "sdot;": '\U000022C5', + "sdotb;": '\U000022A1', + "sdote;": '\U00002A66', + "seArr;": '\U000021D8', + "searhk;": '\U00002925', + "searr;": '\U00002198', + "searrow;": '\U00002198', + "sect;": '\U000000A7', + "semi;": '\U0000003B', + "seswar;": '\U00002929', + "setminus;": '\U00002216', + "setmn;": '\U00002216', + "sext;": '\U00002736', + "sfr;": '\U0001D530', + "sfrown;": '\U00002322', + "sharp;": '\U0000266F', + "shchcy;": '\U00000449', + "shcy;": '\U00000448', + "shortmid;": '\U00002223', + "shortparallel;": '\U00002225', + "shy;": '\U000000AD', + "sigma;": '\U000003C3', + "sigmaf;": '\U000003C2', + "sigmav;": '\U000003C2', + "sim;": '\U0000223C', + "simdot;": '\U00002A6A', + "sime;": '\U00002243', + "simeq;": '\U00002243', + "simg;": '\U00002A9E', + "simgE;": '\U00002AA0', + "siml;": '\U00002A9D', + "simlE;": '\U00002A9F', + "simne;": '\U00002246', + "simplus;": '\U00002A24', + "simrarr;": '\U00002972', + "slarr;": '\U00002190', + "smallsetminus;": '\U00002216', + "smashp;": '\U00002A33', + "smeparsl;": '\U000029E4', + "smid;": '\U00002223', + "smile;": '\U00002323', + "smt;": '\U00002AAA', + "smte;": '\U00002AAC', + "softcy;": '\U0000044C', + "sol;": '\U0000002F', + "solb;": '\U000029C4', + "solbar;": '\U0000233F', + "sopf;": '\U0001D564', + "spades;": '\U00002660', + "spadesuit;": '\U00002660', + "spar;": '\U00002225', + "sqcap;": '\U00002293', + "sqcup;": '\U00002294', + "sqsub;": '\U0000228F', + "sqsube;": '\U00002291', + "sqsubset;": '\U0000228F', + "sqsubseteq;": '\U00002291', + "sqsup;": '\U00002290', + "sqsupe;": '\U00002292', + "sqsupset;": '\U00002290', + "sqsupseteq;": '\U00002292', + "squ;": '\U000025A1', + "square;": '\U000025A1', + "squarf;": '\U000025AA', + "squf;": '\U000025AA', + "srarr;": '\U00002192', + "sscr;": '\U0001D4C8', + "ssetmn;": '\U00002216', + "ssmile;": '\U00002323', + "sstarf;": '\U000022C6', + "star;": '\U00002606', + "starf;": '\U00002605', + "straightepsilon;": '\U000003F5', + "straightphi;": '\U000003D5', + "strns;": '\U000000AF', + "sub;": '\U00002282', + "subE;": '\U00002AC5', + "subdot;": '\U00002ABD', + "sube;": '\U00002286', + "subedot;": '\U00002AC3', + "submult;": '\U00002AC1', + "subnE;": '\U00002ACB', + "subne;": '\U0000228A', + "subplus;": '\U00002ABF', + "subrarr;": '\U00002979', + "subset;": '\U00002282', + "subseteq;": '\U00002286', + "subseteqq;": '\U00002AC5', + "subsetneq;": '\U0000228A', + "subsetneqq;": '\U00002ACB', + "subsim;": '\U00002AC7', + "subsub;": '\U00002AD5', + "subsup;": '\U00002AD3', + "succ;": '\U0000227B', + "succapprox;": '\U00002AB8', + "succcurlyeq;": '\U0000227D', + "succeq;": '\U00002AB0', + "succnapprox;": '\U00002ABA', + "succneqq;": '\U00002AB6', + "succnsim;": '\U000022E9', + "succsim;": '\U0000227F', + "sum;": '\U00002211', + "sung;": '\U0000266A', + "sup;": '\U00002283', + "sup1;": '\U000000B9', + "sup2;": '\U000000B2', + "sup3;": '\U000000B3', + "supE;": '\U00002AC6', + "supdot;": '\U00002ABE', + "supdsub;": '\U00002AD8', + "supe;": '\U00002287', + "supedot;": '\U00002AC4', + "suphsol;": '\U000027C9', + "suphsub;": '\U00002AD7', + "suplarr;": '\U0000297B', + "supmult;": '\U00002AC2', + "supnE;": '\U00002ACC', + "supne;": '\U0000228B', + "supplus;": '\U00002AC0', + "supset;": '\U00002283', + "supseteq;": '\U00002287', + "supseteqq;": '\U00002AC6', + "supsetneq;": '\U0000228B', + "supsetneqq;": '\U00002ACC', + "supsim;": '\U00002AC8', + "supsub;": '\U00002AD4', + "supsup;": '\U00002AD6', + "swArr;": '\U000021D9', + "swarhk;": '\U00002926', + "swarr;": '\U00002199', + "swarrow;": '\U00002199', + "swnwar;": '\U0000292A', + "szlig;": '\U000000DF', + "target;": '\U00002316', + "tau;": '\U000003C4', + "tbrk;": '\U000023B4', + "tcaron;": '\U00000165', + "tcedil;": '\U00000163', + "tcy;": '\U00000442', + "tdot;": '\U000020DB', + "telrec;": '\U00002315', + "tfr;": '\U0001D531', + "there4;": '\U00002234', + "therefore;": '\U00002234', + "theta;": '\U000003B8', + "thetasym;": '\U000003D1', + "thetav;": '\U000003D1', + "thickapprox;": '\U00002248', + "thicksim;": '\U0000223C', + "thinsp;": '\U00002009', + "thkap;": '\U00002248', + "thksim;": '\U0000223C', + "thorn;": '\U000000FE', + "tilde;": '\U000002DC', + "times;": '\U000000D7', + "timesb;": '\U000022A0', + "timesbar;": '\U00002A31', + "timesd;": '\U00002A30', + "tint;": '\U0000222D', + "toea;": '\U00002928', + "top;": '\U000022A4', + "topbot;": '\U00002336', + "topcir;": '\U00002AF1', + "topf;": '\U0001D565', + "topfork;": '\U00002ADA', + "tosa;": '\U00002929', + "tprime;": '\U00002034', + "trade;": '\U00002122', + "triangle;": '\U000025B5', + "triangledown;": '\U000025BF', + "triangleleft;": '\U000025C3', + "trianglelefteq;": '\U000022B4', + "triangleq;": '\U0000225C', + "triangleright;": '\U000025B9', + "trianglerighteq;": '\U000022B5', + "tridot;": '\U000025EC', + "trie;": '\U0000225C', + "triminus;": '\U00002A3A', + "triplus;": '\U00002A39', + "trisb;": '\U000029CD', + "tritime;": '\U00002A3B', + "trpezium;": '\U000023E2', + "tscr;": '\U0001D4C9', + "tscy;": '\U00000446', + "tshcy;": '\U0000045B', + "tstrok;": '\U00000167', + "twixt;": '\U0000226C', + "twoheadleftarrow;": '\U0000219E', + "twoheadrightarrow;": '\U000021A0', + "uArr;": '\U000021D1', + "uHar;": '\U00002963', + "uacute;": '\U000000FA', + "uarr;": '\U00002191', + "ubrcy;": '\U0000045E', + "ubreve;": '\U0000016D', + "ucirc;": '\U000000FB', + "ucy;": '\U00000443', + "udarr;": '\U000021C5', + "udblac;": '\U00000171', + "udhar;": '\U0000296E', + "ufisht;": '\U0000297E', + "ufr;": '\U0001D532', + "ugrave;": '\U000000F9', + "uharl;": '\U000021BF', + "uharr;": '\U000021BE', + "uhblk;": '\U00002580', + "ulcorn;": '\U0000231C', + "ulcorner;": '\U0000231C', + "ulcrop;": '\U0000230F', + "ultri;": '\U000025F8', + "umacr;": '\U0000016B', + "uml;": '\U000000A8', + "uogon;": '\U00000173', + "uopf;": '\U0001D566', + "uparrow;": '\U00002191', + "updownarrow;": '\U00002195', + "upharpoonleft;": '\U000021BF', + "upharpoonright;": '\U000021BE', + "uplus;": '\U0000228E', + "upsi;": '\U000003C5', + "upsih;": '\U000003D2', + "upsilon;": '\U000003C5', + "upuparrows;": '\U000021C8', + "urcorn;": '\U0000231D', + "urcorner;": '\U0000231D', + "urcrop;": '\U0000230E', + "uring;": '\U0000016F', + "urtri;": '\U000025F9', + "uscr;": '\U0001D4CA', + "utdot;": '\U000022F0', + "utilde;": '\U00000169', + "utri;": '\U000025B5', + "utrif;": '\U000025B4', + "uuarr;": '\U000021C8', + "uuml;": '\U000000FC', + "uwangle;": '\U000029A7', + "vArr;": '\U000021D5', + "vBar;": '\U00002AE8', + "vBarv;": '\U00002AE9', + "vDash;": '\U000022A8', + "vangrt;": '\U0000299C', + "varepsilon;": '\U000003F5', + "varkappa;": '\U000003F0', + "varnothing;": '\U00002205', + "varphi;": '\U000003D5', + "varpi;": '\U000003D6', + "varpropto;": '\U0000221D', + "varr;": '\U00002195', + "varrho;": '\U000003F1', + "varsigma;": '\U000003C2', + "vartheta;": '\U000003D1', + "vartriangleleft;": '\U000022B2', + "vartriangleright;": '\U000022B3', + "vcy;": '\U00000432', + "vdash;": '\U000022A2', + "vee;": '\U00002228', + "veebar;": '\U000022BB', + "veeeq;": '\U0000225A', + "vellip;": '\U000022EE', + "verbar;": '\U0000007C', + "vert;": '\U0000007C', + "vfr;": '\U0001D533', + "vltri;": '\U000022B2', + "vopf;": '\U0001D567', + "vprop;": '\U0000221D', + "vrtri;": '\U000022B3', + "vscr;": '\U0001D4CB', + "vzigzag;": '\U0000299A', + "wcirc;": '\U00000175', + "wedbar;": '\U00002A5F', + "wedge;": '\U00002227', + "wedgeq;": '\U00002259', + "weierp;": '\U00002118', + "wfr;": '\U0001D534', + "wopf;": '\U0001D568', + "wp;": '\U00002118', + "wr;": '\U00002240', + "wreath;": '\U00002240', + "wscr;": '\U0001D4CC', + "xcap;": '\U000022C2', + "xcirc;": '\U000025EF', + "xcup;": '\U000022C3', + "xdtri;": '\U000025BD', + "xfr;": '\U0001D535', + "xhArr;": '\U000027FA', + "xharr;": '\U000027F7', + "xi;": '\U000003BE', + "xlArr;": '\U000027F8', + "xlarr;": '\U000027F5', + "xmap;": '\U000027FC', + "xnis;": '\U000022FB', + "xodot;": '\U00002A00', + "xopf;": '\U0001D569', + "xoplus;": '\U00002A01', + "xotime;": '\U00002A02', + "xrArr;": '\U000027F9', + "xrarr;": '\U000027F6', + "xscr;": '\U0001D4CD', + "xsqcup;": '\U00002A06', + "xuplus;": '\U00002A04', + "xutri;": '\U000025B3', + "xvee;": '\U000022C1', + "xwedge;": '\U000022C0', + "yacute;": '\U000000FD', + "yacy;": '\U0000044F', + "ycirc;": '\U00000177', + "ycy;": '\U0000044B', + "yen;": '\U000000A5', + "yfr;": '\U0001D536', + "yicy;": '\U00000457', + "yopf;": '\U0001D56A', + "yscr;": '\U0001D4CE', + "yucy;": '\U0000044E', + "yuml;": '\U000000FF', + "zacute;": '\U0000017A', + "zcaron;": '\U0000017E', + "zcy;": '\U00000437', + "zdot;": '\U0000017C', + "zeetrf;": '\U00002128', + "zeta;": '\U000003B6', + "zfr;": '\U0001D537', + "zhcy;": '\U00000436', + "zigrarr;": '\U000021DD', + "zopf;": '\U0001D56B', + "zscr;": '\U0001D4CF', + "zwj;": '\U0000200D', + "zwnj;": '\U0000200C', + "AElig": '\U000000C6', + "AMP": '\U00000026', + "Aacute": '\U000000C1', + "Acirc": '\U000000C2', + "Agrave": '\U000000C0', + "Aring": '\U000000C5', + "Atilde": '\U000000C3', + "Auml": '\U000000C4', + "COPY": '\U000000A9', + "Ccedil": '\U000000C7', + "ETH": '\U000000D0', + "Eacute": '\U000000C9', + "Ecirc": '\U000000CA', + "Egrave": '\U000000C8', + "Euml": '\U000000CB', + "GT": '\U0000003E', + "Iacute": '\U000000CD', + "Icirc": '\U000000CE', + "Igrave": '\U000000CC', + "Iuml": '\U000000CF', + "LT": '\U0000003C', + "Ntilde": '\U000000D1', + "Oacute": '\U000000D3', + "Ocirc": '\U000000D4', + "Ograve": '\U000000D2', + "Oslash": '\U000000D8', + "Otilde": '\U000000D5', + "Ouml": '\U000000D6', + "QUOT": '\U00000022', + "REG": '\U000000AE', + "THORN": '\U000000DE', + "Uacute": '\U000000DA', + "Ucirc": '\U000000DB', + "Ugrave": '\U000000D9', + "Uuml": '\U000000DC', + "Yacute": '\U000000DD', + "aacute": '\U000000E1', + "acirc": '\U000000E2', + "acute": '\U000000B4', + "aelig": '\U000000E6', + "agrave": '\U000000E0', + "amp": '\U00000026', + "aring": '\U000000E5', + "atilde": '\U000000E3', + "auml": '\U000000E4', + "brvbar": '\U000000A6', + "ccedil": '\U000000E7', + "cedil": '\U000000B8', + "cent": '\U000000A2', + "copy": '\U000000A9', + "curren": '\U000000A4', + "deg": '\U000000B0', + "divide": '\U000000F7', + "eacute": '\U000000E9', + "ecirc": '\U000000EA', + "egrave": '\U000000E8', + "eth": '\U000000F0', + "euml": '\U000000EB', + "frac12": '\U000000BD', + "frac14": '\U000000BC', + "frac34": '\U000000BE', + "gt": '\U0000003E', + "iacute": '\U000000ED', + "icirc": '\U000000EE', + "iexcl": '\U000000A1', + "igrave": '\U000000EC', + "iquest": '\U000000BF', + "iuml": '\U000000EF', + "laquo": '\U000000AB', + "lt": '\U0000003C', + "macr": '\U000000AF', + "micro": '\U000000B5', + "middot": '\U000000B7', + "nbsp": '\U000000A0', + "not": '\U000000AC', + "ntilde": '\U000000F1', + "oacute": '\U000000F3', + "ocirc": '\U000000F4', + "ograve": '\U000000F2', + "ordf": '\U000000AA', + "ordm": '\U000000BA', + "oslash": '\U000000F8', + "otilde": '\U000000F5', + "ouml": '\U000000F6', + "para": '\U000000B6', + "plusmn": '\U000000B1', + "pound": '\U000000A3', + "quot": '\U00000022', + "raquo": '\U000000BB', + "reg": '\U000000AE', + "sect": '\U000000A7', + "shy": '\U000000AD', + "sup1": '\U000000B9', + "sup2": '\U000000B2', + "sup3": '\U000000B3', + "szlig": '\U000000DF', + "thorn": '\U000000FE', + "times": '\U000000D7', + "uacute": '\U000000FA', + "ucirc": '\U000000FB', + "ugrave": '\U000000F9', + "uml": '\U000000A8', + "uuml": '\U000000FC', + "yacute": '\U000000FD', + "yen": '\U000000A5', + "yuml": '\U000000FF', +} + +// HTML entities that are two unicode codepoints. +var entity2 = map[string][2]rune{ + // TODO(nigeltao): Handle replacements that are wider than their names. + // "nLt;": {'\u226A', '\u20D2'}, + // "nGt;": {'\u226B', '\u20D2'}, + "NotEqualTilde;": {'\u2242', '\u0338'}, + "NotGreaterFullEqual;": {'\u2267', '\u0338'}, + "NotGreaterGreater;": {'\u226B', '\u0338'}, + "NotGreaterSlantEqual;": {'\u2A7E', '\u0338'}, + "NotHumpDownHump;": {'\u224E', '\u0338'}, + "NotHumpEqual;": {'\u224F', '\u0338'}, + "NotLeftTriangleBar;": {'\u29CF', '\u0338'}, + "NotLessLess;": {'\u226A', '\u0338'}, + "NotLessSlantEqual;": {'\u2A7D', '\u0338'}, + "NotNestedGreaterGreater;": {'\u2AA2', '\u0338'}, + "NotNestedLessLess;": {'\u2AA1', '\u0338'}, + "NotPrecedesEqual;": {'\u2AAF', '\u0338'}, + "NotRightTriangleBar;": {'\u29D0', '\u0338'}, + "NotSquareSubset;": {'\u228F', '\u0338'}, + "NotSquareSuperset;": {'\u2290', '\u0338'}, + "NotSubset;": {'\u2282', '\u20D2'}, + "NotSucceedsEqual;": {'\u2AB0', '\u0338'}, + "NotSucceedsTilde;": {'\u227F', '\u0338'}, + "NotSuperset;": {'\u2283', '\u20D2'}, + "ThickSpace;": {'\u205F', '\u200A'}, + "acE;": {'\u223E', '\u0333'}, + "bne;": {'\u003D', '\u20E5'}, + "bnequiv;": {'\u2261', '\u20E5'}, + "caps;": {'\u2229', '\uFE00'}, + "cups;": {'\u222A', '\uFE00'}, + "fjlig;": {'\u0066', '\u006A'}, + "gesl;": {'\u22DB', '\uFE00'}, + "gvertneqq;": {'\u2269', '\uFE00'}, + "gvnE;": {'\u2269', '\uFE00'}, + "lates;": {'\u2AAD', '\uFE00'}, + "lesg;": {'\u22DA', '\uFE00'}, + "lvertneqq;": {'\u2268', '\uFE00'}, + "lvnE;": {'\u2268', '\uFE00'}, + "nGg;": {'\u22D9', '\u0338'}, + "nGtv;": {'\u226B', '\u0338'}, + "nLl;": {'\u22D8', '\u0338'}, + "nLtv;": {'\u226A', '\u0338'}, + "nang;": {'\u2220', '\u20D2'}, + "napE;": {'\u2A70', '\u0338'}, + "napid;": {'\u224B', '\u0338'}, + "nbump;": {'\u224E', '\u0338'}, + "nbumpe;": {'\u224F', '\u0338'}, + "ncongdot;": {'\u2A6D', '\u0338'}, + "nedot;": {'\u2250', '\u0338'}, + "nesim;": {'\u2242', '\u0338'}, + "ngE;": {'\u2267', '\u0338'}, + "ngeqq;": {'\u2267', '\u0338'}, + "ngeqslant;": {'\u2A7E', '\u0338'}, + "nges;": {'\u2A7E', '\u0338'}, + "nlE;": {'\u2266', '\u0338'}, + "nleqq;": {'\u2266', '\u0338'}, + "nleqslant;": {'\u2A7D', '\u0338'}, + "nles;": {'\u2A7D', '\u0338'}, + "notinE;": {'\u22F9', '\u0338'}, + "notindot;": {'\u22F5', '\u0338'}, + "nparsl;": {'\u2AFD', '\u20E5'}, + "npart;": {'\u2202', '\u0338'}, + "npre;": {'\u2AAF', '\u0338'}, + "npreceq;": {'\u2AAF', '\u0338'}, + "nrarrc;": {'\u2933', '\u0338'}, + "nrarrw;": {'\u219D', '\u0338'}, + "nsce;": {'\u2AB0', '\u0338'}, + "nsubE;": {'\u2AC5', '\u0338'}, + "nsubset;": {'\u2282', '\u20D2'}, + "nsubseteqq;": {'\u2AC5', '\u0338'}, + "nsucceq;": {'\u2AB0', '\u0338'}, + "nsupE;": {'\u2AC6', '\u0338'}, + "nsupset;": {'\u2283', '\u20D2'}, + "nsupseteqq;": {'\u2AC6', '\u0338'}, + "nvap;": {'\u224D', '\u20D2'}, + "nvge;": {'\u2265', '\u20D2'}, + "nvgt;": {'\u003E', '\u20D2'}, + "nvle;": {'\u2264', '\u20D2'}, + "nvlt;": {'\u003C', '\u20D2'}, + "nvltrie;": {'\u22B4', '\u20D2'}, + "nvrtrie;": {'\u22B5', '\u20D2'}, + "nvsim;": {'\u223C', '\u20D2'}, + "race;": {'\u223D', '\u0331'}, + "smtes;": {'\u2AAC', '\uFE00'}, + "sqcaps;": {'\u2293', '\uFE00'}, + "sqcups;": {'\u2294', '\uFE00'}, + "varsubsetneq;": {'\u228A', '\uFE00'}, + "varsubsetneqq;": {'\u2ACB', '\uFE00'}, + "varsupsetneq;": {'\u228B', '\uFE00'}, + "varsupsetneqq;": {'\u2ACC', '\uFE00'}, + "vnsub;": {'\u2282', '\u20D2'}, + "vnsup;": {'\u2283', '\u20D2'}, + "vsubnE;": {'\u2ACB', '\uFE00'}, + "vsubne;": {'\u228A', '\uFE00'}, + "vsupnE;": {'\u2ACC', '\uFE00'}, + "vsupne;": {'\u228B', '\uFE00'}, +} diff --git a/vendor/golang.org/x/net/html/escape.go b/vendor/golang.org/x/net/html/escape.go new file mode 100644 index 000000000..d85613962 --- /dev/null +++ b/vendor/golang.org/x/net/html/escape.go @@ -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 +} diff --git a/vendor/golang.org/x/net/html/foreign.go b/vendor/golang.org/x/net/html/foreign.go new file mode 100644 index 000000000..d3b384409 --- /dev/null +++ b/vendor/golang.org/x/net/html/foreign.go @@ -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", +} diff --git a/vendor/golang.org/x/net/html/node.go b/vendor/golang.org/x/net/html/node.go new file mode 100644 index 000000000..26b657aec --- /dev/null +++ b/vendor/golang.org/x/net/html/node.go @@ -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] +} diff --git a/vendor/golang.org/x/net/html/parse.go b/vendor/golang.org/x/net/html/parse.go new file mode 100644 index 000000000..be4b2bf5a --- /dev/null +++ b/vendor/golang.org/x/net/html/parse.go @@ -0,0 +1,2094 @@ +// 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 ( + "errors" + "fmt" + "io" + "strings" + + a "golang.org/x/net/html/atom" +) + +// A parser implements the HTML5 parsing algorithm: +// https://html.spec.whatwg.org/multipage/syntax.html#tree-construction +type parser struct { + // tokenizer provides the tokens for the parser. + tokenizer *Tokenizer + // tok is the most recently read token. + tok Token + // Self-closing tags like <hr/> are treated as start tags, except that + // hasSelfClosingToken is set while they are being processed. + hasSelfClosingToken bool + // doc is the document root element. + doc *Node + // The stack of open elements (section 12.2.3.2) and active formatting + // elements (section 12.2.3.3). + oe, afe nodeStack + // Element pointers (section 12.2.3.4). + head, form *Node + // Other parsing state flags (section 12.2.3.5). + scripting, framesetOK bool + // im is the current insertion mode. + im insertionMode + // originalIM is the insertion mode to go back to after completing a text + // or inTableText insertion mode. + originalIM insertionMode + // fosterParenting is whether new elements should be inserted according to + // the foster parenting rules (section 12.2.5.3). + fosterParenting bool + // quirks is whether the parser is operating in "quirks mode." + quirks bool + // fragment is whether the parser is parsing an HTML fragment. + fragment bool + // context is the context element when parsing an HTML fragment + // (section 12.4). + context *Node +} + +func (p *parser) top() *Node { + if n := p.oe.top(); n != nil { + return n + } + return p.doc +} + +// Stop tags for use in popUntil. These come from section 12.2.3.2. +var ( + defaultScopeStopTags = map[string][]a.Atom{ + "": {a.Applet, a.Caption, a.Html, a.Table, a.Td, a.Th, a.Marquee, a.Object, a.Template}, + "math": {a.AnnotationXml, a.Mi, a.Mn, a.Mo, a.Ms, a.Mtext}, + "svg": {a.Desc, a.ForeignObject, a.Title}, + } +) + +type scope int + +const ( + defaultScope scope = iota + listItemScope + buttonScope + tableScope + tableRowScope + tableBodyScope + selectScope +) + +// popUntil pops the stack of open elements at the highest element whose tag +// is in matchTags, provided there is no higher element in the scope's stop +// tags (as defined in section 12.2.3.2). It returns whether or not there was +// such an element. If there was not, popUntil leaves the stack unchanged. +// +// For example, the set of stop tags for table scope is: "html", "table". If +// the stack was: +// ["html", "body", "font", "table", "b", "i", "u"] +// then popUntil(tableScope, "font") would return false, but +// popUntil(tableScope, "i") would return true and the stack would become: +// ["html", "body", "font", "table", "b"] +// +// If an element's tag is in both the stop tags and matchTags, then the stack +// will be popped and the function returns true (provided, of course, there was +// no higher element in the stack that was also in the stop tags). For example, +// popUntil(tableScope, "table") returns true and leaves: +// ["html", "body", "font"] +func (p *parser) popUntil(s scope, matchTags ...a.Atom) bool { + if i := p.indexOfElementInScope(s, matchTags...); i != -1 { + p.oe = p.oe[:i] + return true + } + return false +} + +// indexOfElementInScope returns the index in p.oe of the highest element whose +// tag is in matchTags that is in scope. If no matching element is in scope, it +// returns -1. +func (p *parser) indexOfElementInScope(s scope, matchTags ...a.Atom) int { + for i := len(p.oe) - 1; i >= 0; i-- { + tagAtom := p.oe[i].DataAtom + if p.oe[i].Namespace == "" { + for _, t := range matchTags { + if t == tagAtom { + return i + } + } + switch s { + case defaultScope: + // No-op. + case listItemScope: + if tagAtom == a.Ol || tagAtom == a.Ul { + return -1 + } + case buttonScope: + if tagAtom == a.Button { + return -1 + } + case tableScope: + if tagAtom == a.Html || tagAtom == a.Table { + return -1 + } + case selectScope: + if tagAtom != a.Optgroup && tagAtom != a.Option { + return -1 + } + default: + panic("unreachable") + } + } + switch s { + case defaultScope, listItemScope, buttonScope: + for _, t := range defaultScopeStopTags[p.oe[i].Namespace] { + if t == tagAtom { + return -1 + } + } + } + } + return -1 +} + +// elementInScope is like popUntil, except that it doesn't modify the stack of +// open elements. +func (p *parser) elementInScope(s scope, matchTags ...a.Atom) bool { + return p.indexOfElementInScope(s, matchTags...) != -1 +} + +// clearStackToContext pops elements off the stack of open elements until a +// scope-defined element is found. +func (p *parser) clearStackToContext(s scope) { + for i := len(p.oe) - 1; i >= 0; i-- { + tagAtom := p.oe[i].DataAtom + switch s { + case tableScope: + if tagAtom == a.Html || tagAtom == a.Table { + p.oe = p.oe[:i+1] + return + } + case tableRowScope: + if tagAtom == a.Html || tagAtom == a.Tr { + p.oe = p.oe[:i+1] + return + } + case tableBodyScope: + if tagAtom == a.Html || tagAtom == a.Tbody || tagAtom == a.Tfoot || tagAtom == a.Thead { + p.oe = p.oe[:i+1] + return + } + default: + panic("unreachable") + } + } +} + +// generateImpliedEndTags pops nodes off the stack of open elements as long as +// the top node has a tag name of dd, dt, li, option, optgroup, p, rp, or rt. +// If exceptions are specified, nodes with that name will not be popped off. +func (p *parser) generateImpliedEndTags(exceptions ...string) { + var i int +loop: + for i = len(p.oe) - 1; i >= 0; i-- { + n := p.oe[i] + if n.Type == ElementNode { + switch n.DataAtom { + case a.Dd, a.Dt, a.Li, a.Option, a.Optgroup, a.P, a.Rp, a.Rt: + for _, except := range exceptions { + if n.Data == except { + break loop + } + } + continue + } + } + break + } + + p.oe = p.oe[:i+1] +} + +// addChild adds a child node n to the top element, and pushes n onto the stack +// of open elements if it is an element node. +func (p *parser) addChild(n *Node) { + if p.shouldFosterParent() { + p.fosterParent(n) + } else { + p.top().AppendChild(n) + } + + if n.Type == ElementNode { + p.oe = append(p.oe, n) + } +} + +// shouldFosterParent returns whether the next node to be added should be +// foster parented. +func (p *parser) shouldFosterParent() bool { + if p.fosterParenting { + switch p.top().DataAtom { + case a.Table, a.Tbody, a.Tfoot, a.Thead, a.Tr: + return true + } + } + return false +} + +// fosterParent adds a child node according to the foster parenting rules. +// Section 12.2.5.3, "foster parenting". +func (p *parser) fosterParent(n *Node) { + var table, parent, prev *Node + var i int + for i = len(p.oe) - 1; i >= 0; i-- { + if p.oe[i].DataAtom == a.Table { + table = p.oe[i] + break + } + } + + if table == nil { + // The foster parent is the html element. + parent = p.oe[0] + } else { + parent = table.Parent + } + if parent == nil { + parent = p.oe[i-1] + } + + if table != nil { + prev = table.PrevSibling + } else { + prev = parent.LastChild + } + if prev != nil && prev.Type == TextNode && n.Type == TextNode { + prev.Data += n.Data + return + } + + parent.InsertBefore(n, table) +} + +// addText adds text to the preceding node if it is a text node, or else it +// calls addChild with a new text node. +func (p *parser) addText(text string) { + if text == "" { + return + } + + if p.shouldFosterParent() { + p.fosterParent(&Node{ + Type: TextNode, + Data: text, + }) + return + } + + t := p.top() + if n := t.LastChild; n != nil && n.Type == TextNode { + n.Data += text + return + } + p.addChild(&Node{ + Type: TextNode, + Data: text, + }) +} + +// addElement adds a child element based on the current token. +func (p *parser) addElement() { + p.addChild(&Node{ + Type: ElementNode, + DataAtom: p.tok.DataAtom, + Data: p.tok.Data, + Attr: p.tok.Attr, + }) +} + +// Section 12.2.3.3. +func (p *parser) addFormattingElement() { + tagAtom, attr := p.tok.DataAtom, p.tok.Attr + p.addElement() + + // Implement the Noah's Ark clause, but with three per family instead of two. + identicalElements := 0 +findIdenticalElements: + for i := len(p.afe) - 1; i >= 0; i-- { + n := p.afe[i] + if n.Type == scopeMarkerNode { + break + } + if n.Type != ElementNode { + continue + } + if n.Namespace != "" { + continue + } + if n.DataAtom != tagAtom { + continue + } + if len(n.Attr) != len(attr) { + continue + } + compareAttributes: + for _, t0 := range n.Attr { + for _, t1 := range attr { + if t0.Key == t1.Key && t0.Namespace == t1.Namespace && t0.Val == t1.Val { + // Found a match for this attribute, continue with the next attribute. + continue compareAttributes + } + } + // If we get here, there is no attribute that matches a. + // Therefore the element is not identical to the new one. + continue findIdenticalElements + } + + identicalElements++ + if identicalElements >= 3 { + p.afe.remove(n) + } + } + + p.afe = append(p.afe, p.top()) +} + +// Section 12.2.3.3. +func (p *parser) clearActiveFormattingElements() { + for { + n := p.afe.pop() + if len(p.afe) == 0 || n.Type == scopeMarkerNode { + return + } + } +} + +// Section 12.2.3.3. +func (p *parser) reconstructActiveFormattingElements() { + n := p.afe.top() + if n == nil { + return + } + if n.Type == scopeMarkerNode || p.oe.index(n) != -1 { + return + } + i := len(p.afe) - 1 + for n.Type != scopeMarkerNode && p.oe.index(n) == -1 { + if i == 0 { + i = -1 + break + } + i-- + n = p.afe[i] + } + for { + i++ + clone := p.afe[i].clone() + p.addChild(clone) + p.afe[i] = clone + if i == len(p.afe)-1 { + break + } + } +} + +// Section 12.2.4. +func (p *parser) acknowledgeSelfClosingTag() { + p.hasSelfClosingToken = false +} + +// An insertion mode (section 12.2.3.1) is the state transition function from +// a particular state in the HTML5 parser's state machine. It updates the +// parser's fields depending on parser.tok (where ErrorToken means EOF). +// It returns whether the token was consumed. +type insertionMode func(*parser) bool + +// setOriginalIM sets the insertion mode to return to after completing a text or +// inTableText insertion mode. +// Section 12.2.3.1, "using the rules for". +func (p *parser) setOriginalIM() { + if p.originalIM != nil { + panic("html: bad parser state: originalIM was set twice") + } + p.originalIM = p.im +} + +// Section 12.2.3.1, "reset the insertion mode". +func (p *parser) resetInsertionMode() { + for i := len(p.oe) - 1; i >= 0; i-- { + n := p.oe[i] + if i == 0 && p.context != nil { + n = p.context + } + + switch n.DataAtom { + case a.Select: + p.im = inSelectIM + case a.Td, a.Th: + p.im = inCellIM + case a.Tr: + p.im = inRowIM + case a.Tbody, a.Thead, a.Tfoot: + p.im = inTableBodyIM + case a.Caption: + p.im = inCaptionIM + case a.Colgroup: + p.im = inColumnGroupIM + case a.Table: + p.im = inTableIM + case a.Head: + p.im = inBodyIM + case a.Body: + p.im = inBodyIM + case a.Frameset: + p.im = inFramesetIM + case a.Html: + p.im = beforeHeadIM + default: + continue + } + return + } + p.im = inBodyIM +} + +const whitespace = " \t\r\n\f" + +// Section 12.2.5.4.1. +func initialIM(p *parser) bool { + switch p.tok.Type { + case TextToken: + p.tok.Data = strings.TrimLeft(p.tok.Data, whitespace) + if len(p.tok.Data) == 0 { + // It was all whitespace, so ignore it. + return true + } + case CommentToken: + p.doc.AppendChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + return true + case DoctypeToken: + n, quirks := parseDoctype(p.tok.Data) + p.doc.AppendChild(n) + p.quirks = quirks + p.im = beforeHTMLIM + return true + } + p.quirks = true + p.im = beforeHTMLIM + return false +} + +// Section 12.2.5.4.2. +func beforeHTMLIM(p *parser) bool { + switch p.tok.Type { + case DoctypeToken: + // Ignore the token. + return true + case TextToken: + p.tok.Data = strings.TrimLeft(p.tok.Data, whitespace) + if len(p.tok.Data) == 0 { + // It was all whitespace, so ignore it. + return true + } + case StartTagToken: + if p.tok.DataAtom == a.Html { + p.addElement() + p.im = beforeHeadIM + return true + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Head, a.Body, a.Html, a.Br: + p.parseImpliedToken(StartTagToken, a.Html, a.Html.String()) + return false + default: + // Ignore the token. + return true + } + case CommentToken: + p.doc.AppendChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + return true + } + p.parseImpliedToken(StartTagToken, a.Html, a.Html.String()) + return false +} + +// Section 12.2.5.4.3. +func beforeHeadIM(p *parser) bool { + switch p.tok.Type { + case TextToken: + p.tok.Data = strings.TrimLeft(p.tok.Data, whitespace) + if len(p.tok.Data) == 0 { + // It was all whitespace, so ignore it. + return true + } + case StartTagToken: + switch p.tok.DataAtom { + case a.Head: + p.addElement() + p.head = p.top() + p.im = inHeadIM + return true + case a.Html: + return inBodyIM(p) + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Head, a.Body, a.Html, a.Br: + p.parseImpliedToken(StartTagToken, a.Head, a.Head.String()) + return false + default: + // Ignore the token. + return true + } + case CommentToken: + p.addChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + return true + case DoctypeToken: + // Ignore the token. + return true + } + + p.parseImpliedToken(StartTagToken, a.Head, a.Head.String()) + return false +} + +// Section 12.2.5.4.4. +func inHeadIM(p *parser) bool { + switch p.tok.Type { + case TextToken: + s := strings.TrimLeft(p.tok.Data, whitespace) + if len(s) < len(p.tok.Data) { + // Add the initial whitespace to the current node. + p.addText(p.tok.Data[:len(p.tok.Data)-len(s)]) + if s == "" { + return true + } + p.tok.Data = s + } + case StartTagToken: + switch p.tok.DataAtom { + case a.Html: + return inBodyIM(p) + case a.Base, a.Basefont, a.Bgsound, a.Command, a.Link, a.Meta: + p.addElement() + p.oe.pop() + p.acknowledgeSelfClosingTag() + return true + case a.Script, a.Title, a.Noscript, a.Noframes, a.Style: + p.addElement() + p.setOriginalIM() + p.im = textIM + return true + case a.Head: + // Ignore the token. + return true + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Head: + n := p.oe.pop() + if n.DataAtom != a.Head { + panic("html: bad parser state: <head> element not found, in the in-head insertion mode") + } + p.im = afterHeadIM + return true + case a.Body, a.Html, a.Br: + p.parseImpliedToken(EndTagToken, a.Head, a.Head.String()) + return false + default: + // Ignore the token. + return true + } + case CommentToken: + p.addChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + return true + case DoctypeToken: + // Ignore the token. + return true + } + + p.parseImpliedToken(EndTagToken, a.Head, a.Head.String()) + return false +} + +// Section 12.2.5.4.6. +func afterHeadIM(p *parser) bool { + switch p.tok.Type { + case TextToken: + s := strings.TrimLeft(p.tok.Data, whitespace) + if len(s) < len(p.tok.Data) { + // Add the initial whitespace to the current node. + p.addText(p.tok.Data[:len(p.tok.Data)-len(s)]) + if s == "" { + return true + } + p.tok.Data = s + } + case StartTagToken: + switch p.tok.DataAtom { + case a.Html: + return inBodyIM(p) + case a.Body: + p.addElement() + p.framesetOK = false + p.im = inBodyIM + return true + case a.Frameset: + p.addElement() + p.im = inFramesetIM + return true + case a.Base, a.Basefont, a.Bgsound, a.Link, a.Meta, a.Noframes, a.Script, a.Style, a.Title: + p.oe = append(p.oe, p.head) + defer p.oe.remove(p.head) + return inHeadIM(p) + case a.Head: + // Ignore the token. + return true + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Body, a.Html, a.Br: + // Drop down to creating an implied <body> tag. + default: + // Ignore the token. + return true + } + case CommentToken: + p.addChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + return true + case DoctypeToken: + // Ignore the token. + return true + } + + p.parseImpliedToken(StartTagToken, a.Body, a.Body.String()) + p.framesetOK = true + return false +} + +// copyAttributes copies attributes of src not found on dst to dst. +func copyAttributes(dst *Node, src Token) { + if len(src.Attr) == 0 { + return + } + attr := map[string]string{} + for _, t := range dst.Attr { + attr[t.Key] = t.Val + } + for _, t := range src.Attr { + if _, ok := attr[t.Key]; !ok { + dst.Attr = append(dst.Attr, t) + attr[t.Key] = t.Val + } + } +} + +// Section 12.2.5.4.7. +func inBodyIM(p *parser) bool { + switch p.tok.Type { + case TextToken: + d := p.tok.Data + switch n := p.oe.top(); n.DataAtom { + case a.Pre, a.Listing: + if n.FirstChild == nil { + // Ignore a newline at the start of a <pre> block. + if d != "" && d[0] == '\r' { + d = d[1:] + } + if d != "" && d[0] == '\n' { + d = d[1:] + } + } + } + d = strings.Replace(d, "\x00", "", -1) + if d == "" { + return true + } + p.reconstructActiveFormattingElements() + p.addText(d) + if p.framesetOK && strings.TrimLeft(d, whitespace) != "" { + // There were non-whitespace characters inserted. + p.framesetOK = false + } + case StartTagToken: + switch p.tok.DataAtom { + case a.Html: + copyAttributes(p.oe[0], p.tok) + case a.Base, a.Basefont, a.Bgsound, a.Command, a.Link, a.Meta, a.Noframes, a.Script, a.Style, a.Title: + return inHeadIM(p) + case a.Body: + if len(p.oe) >= 2 { + body := p.oe[1] + if body.Type == ElementNode && body.DataAtom == a.Body { + p.framesetOK = false + copyAttributes(body, p.tok) + } + } + case a.Frameset: + if !p.framesetOK || len(p.oe) < 2 || p.oe[1].DataAtom != a.Body { + // Ignore the token. + return true + } + body := p.oe[1] + if body.Parent != nil { + body.Parent.RemoveChild(body) + } + p.oe = p.oe[:1] + p.addElement() + p.im = inFramesetIM + return true + case a.Address, a.Article, a.Aside, a.Blockquote, a.Center, a.Details, a.Dir, a.Div, a.Dl, a.Fieldset, a.Figcaption, a.Figure, a.Footer, a.Header, a.Hgroup, a.Menu, a.Nav, a.Ol, a.P, a.Section, a.Summary, a.Ul: + p.popUntil(buttonScope, a.P) + p.addElement() + case a.H1, a.H2, a.H3, a.H4, a.H5, a.H6: + p.popUntil(buttonScope, a.P) + switch n := p.top(); n.DataAtom { + case a.H1, a.H2, a.H3, a.H4, a.H5, a.H6: + p.oe.pop() + } + p.addElement() + case a.Pre, a.Listing: + p.popUntil(buttonScope, a.P) + p.addElement() + // The newline, if any, will be dealt with by the TextToken case. + p.framesetOK = false + case a.Form: + if p.form == nil { + p.popUntil(buttonScope, a.P) + p.addElement() + p.form = p.top() + } + case a.Li: + p.framesetOK = false + for i := len(p.oe) - 1; i >= 0; i-- { + node := p.oe[i] + switch node.DataAtom { + case a.Li: + p.oe = p.oe[:i] + case a.Address, a.Div, a.P: + continue + default: + if !isSpecialElement(node) { + continue + } + } + break + } + p.popUntil(buttonScope, a.P) + p.addElement() + case a.Dd, a.Dt: + p.framesetOK = false + for i := len(p.oe) - 1; i >= 0; i-- { + node := p.oe[i] + switch node.DataAtom { + case a.Dd, a.Dt: + p.oe = p.oe[:i] + case a.Address, a.Div, a.P: + continue + default: + if !isSpecialElement(node) { + continue + } + } + break + } + p.popUntil(buttonScope, a.P) + p.addElement() + case a.Plaintext: + p.popUntil(buttonScope, a.P) + p.addElement() + case a.Button: + p.popUntil(defaultScope, a.Button) + p.reconstructActiveFormattingElements() + p.addElement() + p.framesetOK = false + case a.A: + for i := len(p.afe) - 1; i >= 0 && p.afe[i].Type != scopeMarkerNode; i-- { + if n := p.afe[i]; n.Type == ElementNode && n.DataAtom == a.A { + p.inBodyEndTagFormatting(a.A) + p.oe.remove(n) + p.afe.remove(n) + break + } + } + p.reconstructActiveFormattingElements() + p.addFormattingElement() + case a.B, a.Big, a.Code, a.Em, a.Font, a.I, a.S, a.Small, a.Strike, a.Strong, a.Tt, a.U: + p.reconstructActiveFormattingElements() + p.addFormattingElement() + case a.Nobr: + p.reconstructActiveFormattingElements() + if p.elementInScope(defaultScope, a.Nobr) { + p.inBodyEndTagFormatting(a.Nobr) + p.reconstructActiveFormattingElements() + } + p.addFormattingElement() + case a.Applet, a.Marquee, a.Object: + p.reconstructActiveFormattingElements() + p.addElement() + p.afe = append(p.afe, &scopeMarker) + p.framesetOK = false + case a.Table: + if !p.quirks { + p.popUntil(buttonScope, a.P) + } + p.addElement() + p.framesetOK = false + p.im = inTableIM + return true + case a.Area, a.Br, a.Embed, a.Img, a.Input, a.Keygen, a.Wbr: + p.reconstructActiveFormattingElements() + p.addElement() + p.oe.pop() + p.acknowledgeSelfClosingTag() + if p.tok.DataAtom == a.Input { + for _, t := range p.tok.Attr { + if t.Key == "type" { + if strings.ToLower(t.Val) == "hidden" { + // Skip setting framesetOK = false + return true + } + } + } + } + p.framesetOK = false + case a.Param, a.Source, a.Track: + p.addElement() + p.oe.pop() + p.acknowledgeSelfClosingTag() + case a.Hr: + p.popUntil(buttonScope, a.P) + p.addElement() + p.oe.pop() + p.acknowledgeSelfClosingTag() + p.framesetOK = false + case a.Image: + p.tok.DataAtom = a.Img + p.tok.Data = a.Img.String() + return false + case a.Isindex: + if p.form != nil { + // Ignore the token. + return true + } + action := "" + prompt := "This is a searchable index. Enter search keywords: " + attr := []Attribute{{Key: "name", Val: "isindex"}} + for _, t := range p.tok.Attr { + switch t.Key { + case "action": + action = t.Val + case "name": + // Ignore the attribute. + case "prompt": + prompt = t.Val + default: + attr = append(attr, t) + } + } + p.acknowledgeSelfClosingTag() + p.popUntil(buttonScope, a.P) + p.parseImpliedToken(StartTagToken, a.Form, a.Form.String()) + if action != "" { + p.form.Attr = []Attribute{{Key: "action", Val: action}} + } + p.parseImpliedToken(StartTagToken, a.Hr, a.Hr.String()) + p.parseImpliedToken(StartTagToken, a.Label, a.Label.String()) + p.addText(prompt) + p.addChild(&Node{ + Type: ElementNode, + DataAtom: a.Input, + Data: a.Input.String(), + Attr: attr, + }) + p.oe.pop() + p.parseImpliedToken(EndTagToken, a.Label, a.Label.String()) + p.parseImpliedToken(StartTagToken, a.Hr, a.Hr.String()) + p.parseImpliedToken(EndTagToken, a.Form, a.Form.String()) + case a.Textarea: + p.addElement() + p.setOriginalIM() + p.framesetOK = false + p.im = textIM + case a.Xmp: + p.popUntil(buttonScope, a.P) + p.reconstructActiveFormattingElements() + p.framesetOK = false + p.addElement() + p.setOriginalIM() + p.im = textIM + case a.Iframe: + p.framesetOK = false + p.addElement() + p.setOriginalIM() + p.im = textIM + case a.Noembed, a.Noscript: + p.addElement() + p.setOriginalIM() + p.im = textIM + case a.Select: + p.reconstructActiveFormattingElements() + p.addElement() + p.framesetOK = false + p.im = inSelectIM + return true + case a.Optgroup, a.Option: + if p.top().DataAtom == a.Option { + p.oe.pop() + } + p.reconstructActiveFormattingElements() + p.addElement() + case a.Rp, a.Rt: + if p.elementInScope(defaultScope, a.Ruby) { + p.generateImpliedEndTags() + } + p.addElement() + case a.Math, a.Svg: + p.reconstructActiveFormattingElements() + if p.tok.DataAtom == a.Math { + adjustAttributeNames(p.tok.Attr, mathMLAttributeAdjustments) + } else { + adjustAttributeNames(p.tok.Attr, svgAttributeAdjustments) + } + adjustForeignAttributes(p.tok.Attr) + p.addElement() + p.top().Namespace = p.tok.Data + if p.hasSelfClosingToken { + p.oe.pop() + p.acknowledgeSelfClosingTag() + } + return true + case a.Caption, a.Col, a.Colgroup, a.Frame, a.Head, a.Tbody, a.Td, a.Tfoot, a.Th, a.Thead, a.Tr: + // Ignore the token. + default: + p.reconstructActiveFormattingElements() + p.addElement() + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Body: + if p.elementInScope(defaultScope, a.Body) { + p.im = afterBodyIM + } + case a.Html: + if p.elementInScope(defaultScope, a.Body) { + p.parseImpliedToken(EndTagToken, a.Body, a.Body.String()) + return false + } + return true + case a.Address, a.Article, a.Aside, a.Blockquote, a.Button, a.Center, a.Details, a.Dir, a.Div, a.Dl, a.Fieldset, a.Figcaption, a.Figure, a.Footer, a.Header, a.Hgroup, a.Listing, a.Menu, a.Nav, a.Ol, a.Pre, a.Section, a.Summary, a.Ul: + p.popUntil(defaultScope, p.tok.DataAtom) + case a.Form: + node := p.form + p.form = nil + i := p.indexOfElementInScope(defaultScope, a.Form) + if node == nil || i == -1 || p.oe[i] != node { + // Ignore the token. + return true + } + p.generateImpliedEndTags() + p.oe.remove(node) + case a.P: + if !p.elementInScope(buttonScope, a.P) { + p.parseImpliedToken(StartTagToken, a.P, a.P.String()) + } + p.popUntil(buttonScope, a.P) + case a.Li: + p.popUntil(listItemScope, a.Li) + case a.Dd, a.Dt: + p.popUntil(defaultScope, p.tok.DataAtom) + case a.H1, a.H2, a.H3, a.H4, a.H5, a.H6: + p.popUntil(defaultScope, a.H1, a.H2, a.H3, a.H4, a.H5, a.H6) + case a.A, a.B, a.Big, a.Code, a.Em, a.Font, a.I, a.Nobr, a.S, a.Small, a.Strike, a.Strong, a.Tt, a.U: + p.inBodyEndTagFormatting(p.tok.DataAtom) + case a.Applet, a.Marquee, a.Object: + if p.popUntil(defaultScope, p.tok.DataAtom) { + p.clearActiveFormattingElements() + } + case a.Br: + p.tok.Type = StartTagToken + return false + default: + p.inBodyEndTagOther(p.tok.DataAtom) + } + case CommentToken: + p.addChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + } + + return true +} + +func (p *parser) inBodyEndTagFormatting(tagAtom a.Atom) { + // This is the "adoption agency" algorithm, described at + // https://html.spec.whatwg.org/multipage/syntax.html#adoptionAgency + + // TODO: this is a fairly literal line-by-line translation of that algorithm. + // Once the code successfully parses the comprehensive test suite, we should + // refactor this code to be more idiomatic. + + // Steps 1-4. The outer loop. + for i := 0; i < 8; i++ { + // Step 5. Find the formatting element. + var formattingElement *Node + for j := len(p.afe) - 1; j >= 0; j-- { + if p.afe[j].Type == scopeMarkerNode { + break + } + if p.afe[j].DataAtom == tagAtom { + formattingElement = p.afe[j] + break + } + } + if formattingElement == nil { + p.inBodyEndTagOther(tagAtom) + return + } + feIndex := p.oe.index(formattingElement) + if feIndex == -1 { + p.afe.remove(formattingElement) + return + } + if !p.elementInScope(defaultScope, tagAtom) { + // Ignore the tag. + return + } + + // Steps 9-10. Find the furthest block. + var furthestBlock *Node + for _, e := range p.oe[feIndex:] { + if isSpecialElement(e) { + furthestBlock = e + break + } + } + if furthestBlock == nil { + e := p.oe.pop() + for e != formattingElement { + e = p.oe.pop() + } + p.afe.remove(e) + return + } + + // Steps 11-12. Find the common ancestor and bookmark node. + commonAncestor := p.oe[feIndex-1] + bookmark := p.afe.index(formattingElement) + + // Step 13. The inner loop. Find the lastNode to reparent. + lastNode := furthestBlock + node := furthestBlock + x := p.oe.index(node) + // Steps 13.1-13.2 + for j := 0; j < 3; j++ { + // Step 13.3. + x-- + node = p.oe[x] + // Step 13.4 - 13.5. + if p.afe.index(node) == -1 { + p.oe.remove(node) + continue + } + // Step 13.6. + if node == formattingElement { + break + } + // Step 13.7. + clone := node.clone() + p.afe[p.afe.index(node)] = clone + p.oe[p.oe.index(node)] = clone + node = clone + // Step 13.8. + if lastNode == furthestBlock { + bookmark = p.afe.index(node) + 1 + } + // Step 13.9. + if lastNode.Parent != nil { + lastNode.Parent.RemoveChild(lastNode) + } + node.AppendChild(lastNode) + // Step 13.10. + lastNode = node + } + + // Step 14. Reparent lastNode to the common ancestor, + // or for misnested table nodes, to the foster parent. + if lastNode.Parent != nil { + lastNode.Parent.RemoveChild(lastNode) + } + switch commonAncestor.DataAtom { + case a.Table, a.Tbody, a.Tfoot, a.Thead, a.Tr: + p.fosterParent(lastNode) + default: + commonAncestor.AppendChild(lastNode) + } + + // Steps 15-17. Reparent nodes from the furthest block's children + // to a clone of the formatting element. + clone := formattingElement.clone() + reparentChildren(clone, furthestBlock) + furthestBlock.AppendChild(clone) + + // Step 18. Fix up the list of active formatting elements. + if oldLoc := p.afe.index(formattingElement); oldLoc != -1 && oldLoc < bookmark { + // Move the bookmark with the rest of the list. + bookmark-- + } + p.afe.remove(formattingElement) + p.afe.insert(bookmark, clone) + + // Step 19. Fix up the stack of open elements. + p.oe.remove(formattingElement) + p.oe.insert(p.oe.index(furthestBlock)+1, clone) + } +} + +// inBodyEndTagOther performs the "any other end tag" algorithm for inBodyIM. +// "Any other end tag" handling from 12.2.5.5 The rules for parsing tokens in foreign content +// https://html.spec.whatwg.org/multipage/syntax.html#parsing-main-inforeign +func (p *parser) inBodyEndTagOther(tagAtom a.Atom) { + for i := len(p.oe) - 1; i >= 0; i-- { + if p.oe[i].DataAtom == tagAtom { + p.oe = p.oe[:i] + break + } + if isSpecialElement(p.oe[i]) { + break + } + } +} + +// Section 12.2.5.4.8. +func textIM(p *parser) bool { + switch p.tok.Type { + case ErrorToken: + p.oe.pop() + case TextToken: + d := p.tok.Data + if n := p.oe.top(); n.DataAtom == a.Textarea && n.FirstChild == nil { + // Ignore a newline at the start of a <textarea> block. + if d != "" && d[0] == '\r' { + d = d[1:] + } + if d != "" && d[0] == '\n' { + d = d[1:] + } + } + if d == "" { + return true + } + p.addText(d) + return true + case EndTagToken: + p.oe.pop() + } + p.im = p.originalIM + p.originalIM = nil + return p.tok.Type == EndTagToken +} + +// Section 12.2.5.4.9. +func inTableIM(p *parser) bool { + switch p.tok.Type { + case ErrorToken: + // Stop parsing. + return true + case TextToken: + p.tok.Data = strings.Replace(p.tok.Data, "\x00", "", -1) + switch p.oe.top().DataAtom { + case a.Table, a.Tbody, a.Tfoot, a.Thead, a.Tr: + if strings.Trim(p.tok.Data, whitespace) == "" { + p.addText(p.tok.Data) + return true + } + } + case StartTagToken: + switch p.tok.DataAtom { + case a.Caption: + p.clearStackToContext(tableScope) + p.afe = append(p.afe, &scopeMarker) + p.addElement() + p.im = inCaptionIM + return true + case a.Colgroup: + p.clearStackToContext(tableScope) + p.addElement() + p.im = inColumnGroupIM + return true + case a.Col: + p.parseImpliedToken(StartTagToken, a.Colgroup, a.Colgroup.String()) + return false + case a.Tbody, a.Tfoot, a.Thead: + p.clearStackToContext(tableScope) + p.addElement() + p.im = inTableBodyIM + return true + case a.Td, a.Th, a.Tr: + p.parseImpliedToken(StartTagToken, a.Tbody, a.Tbody.String()) + return false + case a.Table: + if p.popUntil(tableScope, a.Table) { + p.resetInsertionMode() + return false + } + // Ignore the token. + return true + case a.Style, a.Script: + return inHeadIM(p) + case a.Input: + for _, t := range p.tok.Attr { + if t.Key == "type" && strings.ToLower(t.Val) == "hidden" { + p.addElement() + p.oe.pop() + return true + } + } + // Otherwise drop down to the default action. + case a.Form: + if p.form != nil { + // Ignore the token. + return true + } + p.addElement() + p.form = p.oe.pop() + case a.Select: + p.reconstructActiveFormattingElements() + switch p.top().DataAtom { + case a.Table, a.Tbody, a.Tfoot, a.Thead, a.Tr: + p.fosterParenting = true + } + p.addElement() + p.fosterParenting = false + p.framesetOK = false + p.im = inSelectInTableIM + return true + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Table: + if p.popUntil(tableScope, a.Table) { + p.resetInsertionMode() + return true + } + // Ignore the token. + return true + case a.Body, a.Caption, a.Col, a.Colgroup, a.Html, a.Tbody, a.Td, a.Tfoot, a.Th, a.Thead, a.Tr: + // Ignore the token. + return true + } + case CommentToken: + p.addChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + return true + case DoctypeToken: + // Ignore the token. + return true + } + + p.fosterParenting = true + defer func() { p.fosterParenting = false }() + + return inBodyIM(p) +} + +// Section 12.2.5.4.11. +func inCaptionIM(p *parser) bool { + switch p.tok.Type { + case StartTagToken: + switch p.tok.DataAtom { + case a.Caption, a.Col, a.Colgroup, a.Tbody, a.Td, a.Tfoot, a.Thead, a.Tr: + if p.popUntil(tableScope, a.Caption) { + p.clearActiveFormattingElements() + p.im = inTableIM + return false + } else { + // Ignore the token. + return true + } + case a.Select: + p.reconstructActiveFormattingElements() + p.addElement() + p.framesetOK = false + p.im = inSelectInTableIM + return true + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Caption: + if p.popUntil(tableScope, a.Caption) { + p.clearActiveFormattingElements() + p.im = inTableIM + } + return true + case a.Table: + if p.popUntil(tableScope, a.Caption) { + p.clearActiveFormattingElements() + p.im = inTableIM + return false + } else { + // Ignore the token. + return true + } + case a.Body, a.Col, a.Colgroup, a.Html, a.Tbody, a.Td, a.Tfoot, a.Th, a.Thead, a.Tr: + // Ignore the token. + return true + } + } + return inBodyIM(p) +} + +// Section 12.2.5.4.12. +func inColumnGroupIM(p *parser) bool { + switch p.tok.Type { + case TextToken: + s := strings.TrimLeft(p.tok.Data, whitespace) + if len(s) < len(p.tok.Data) { + // Add the initial whitespace to the current node. + p.addText(p.tok.Data[:len(p.tok.Data)-len(s)]) + if s == "" { + return true + } + p.tok.Data = s + } + case CommentToken: + p.addChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + return true + case DoctypeToken: + // Ignore the token. + return true + case StartTagToken: + switch p.tok.DataAtom { + case a.Html: + return inBodyIM(p) + case a.Col: + p.addElement() + p.oe.pop() + p.acknowledgeSelfClosingTag() + return true + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Colgroup: + if p.oe.top().DataAtom != a.Html { + p.oe.pop() + p.im = inTableIM + } + return true + case a.Col: + // Ignore the token. + return true + } + } + if p.oe.top().DataAtom != a.Html { + p.oe.pop() + p.im = inTableIM + return false + } + return true +} + +// Section 12.2.5.4.13. +func inTableBodyIM(p *parser) bool { + switch p.tok.Type { + case StartTagToken: + switch p.tok.DataAtom { + case a.Tr: + p.clearStackToContext(tableBodyScope) + p.addElement() + p.im = inRowIM + return true + case a.Td, a.Th: + p.parseImpliedToken(StartTagToken, a.Tr, a.Tr.String()) + return false + case a.Caption, a.Col, a.Colgroup, a.Tbody, a.Tfoot, a.Thead: + if p.popUntil(tableScope, a.Tbody, a.Thead, a.Tfoot) { + p.im = inTableIM + return false + } + // Ignore the token. + return true + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Tbody, a.Tfoot, a.Thead: + if p.elementInScope(tableScope, p.tok.DataAtom) { + p.clearStackToContext(tableBodyScope) + p.oe.pop() + p.im = inTableIM + } + return true + case a.Table: + if p.popUntil(tableScope, a.Tbody, a.Thead, a.Tfoot) { + p.im = inTableIM + return false + } + // Ignore the token. + return true + case a.Body, a.Caption, a.Col, a.Colgroup, a.Html, a.Td, a.Th, a.Tr: + // Ignore the token. + return true + } + case CommentToken: + p.addChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + return true + } + + return inTableIM(p) +} + +// Section 12.2.5.4.14. +func inRowIM(p *parser) bool { + switch p.tok.Type { + case StartTagToken: + switch p.tok.DataAtom { + case a.Td, a.Th: + p.clearStackToContext(tableRowScope) + p.addElement() + p.afe = append(p.afe, &scopeMarker) + p.im = inCellIM + return true + case a.Caption, a.Col, a.Colgroup, a.Tbody, a.Tfoot, a.Thead, a.Tr: + if p.popUntil(tableScope, a.Tr) { + p.im = inTableBodyIM + return false + } + // Ignore the token. + return true + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Tr: + if p.popUntil(tableScope, a.Tr) { + p.im = inTableBodyIM + return true + } + // Ignore the token. + return true + case a.Table: + if p.popUntil(tableScope, a.Tr) { + p.im = inTableBodyIM + return false + } + // Ignore the token. + return true + case a.Tbody, a.Tfoot, a.Thead: + if p.elementInScope(tableScope, p.tok.DataAtom) { + p.parseImpliedToken(EndTagToken, a.Tr, a.Tr.String()) + return false + } + // Ignore the token. + return true + case a.Body, a.Caption, a.Col, a.Colgroup, a.Html, a.Td, a.Th: + // Ignore the token. + return true + } + } + + return inTableIM(p) +} + +// Section 12.2.5.4.15. +func inCellIM(p *parser) bool { + switch p.tok.Type { + case StartTagToken: + switch p.tok.DataAtom { + case a.Caption, a.Col, a.Colgroup, a.Tbody, a.Td, a.Tfoot, a.Th, a.Thead, a.Tr: + if p.popUntil(tableScope, a.Td, a.Th) { + // Close the cell and reprocess. + p.clearActiveFormattingElements() + p.im = inRowIM + return false + } + // Ignore the token. + return true + case a.Select: + p.reconstructActiveFormattingElements() + p.addElement() + p.framesetOK = false + p.im = inSelectInTableIM + return true + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Td, a.Th: + if !p.popUntil(tableScope, p.tok.DataAtom) { + // Ignore the token. + return true + } + p.clearActiveFormattingElements() + p.im = inRowIM + return true + case a.Body, a.Caption, a.Col, a.Colgroup, a.Html: + // Ignore the token. + return true + case a.Table, a.Tbody, a.Tfoot, a.Thead, a.Tr: + if !p.elementInScope(tableScope, p.tok.DataAtom) { + // Ignore the token. + return true + } + // Close the cell and reprocess. + p.popUntil(tableScope, a.Td, a.Th) + p.clearActiveFormattingElements() + p.im = inRowIM + return false + } + } + return inBodyIM(p) +} + +// Section 12.2.5.4.16. +func inSelectIM(p *parser) bool { + switch p.tok.Type { + case ErrorToken: + // Stop parsing. + return true + case TextToken: + p.addText(strings.Replace(p.tok.Data, "\x00", "", -1)) + case StartTagToken: + switch p.tok.DataAtom { + case a.Html: + return inBodyIM(p) + case a.Option: + if p.top().DataAtom == a.Option { + p.oe.pop() + } + p.addElement() + case a.Optgroup: + if p.top().DataAtom == a.Option { + p.oe.pop() + } + if p.top().DataAtom == a.Optgroup { + p.oe.pop() + } + p.addElement() + case a.Select: + p.tok.Type = EndTagToken + return false + case a.Input, a.Keygen, a.Textarea: + if p.elementInScope(selectScope, a.Select) { + p.parseImpliedToken(EndTagToken, a.Select, a.Select.String()) + return false + } + // In order to properly ignore <textarea>, we need to change the tokenizer mode. + p.tokenizer.NextIsNotRawText() + // Ignore the token. + return true + case a.Script: + return inHeadIM(p) + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Option: + if p.top().DataAtom == a.Option { + p.oe.pop() + } + case a.Optgroup: + i := len(p.oe) - 1 + if p.oe[i].DataAtom == a.Option { + i-- + } + if p.oe[i].DataAtom == a.Optgroup { + p.oe = p.oe[:i] + } + case a.Select: + if p.popUntil(selectScope, a.Select) { + p.resetInsertionMode() + } + } + case CommentToken: + p.addChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + case DoctypeToken: + // Ignore the token. + return true + } + + return true +} + +// Section 12.2.5.4.17. +func inSelectInTableIM(p *parser) bool { + switch p.tok.Type { + case StartTagToken, EndTagToken: + switch p.tok.DataAtom { + case a.Caption, a.Table, a.Tbody, a.Tfoot, a.Thead, a.Tr, a.Td, a.Th: + if p.tok.Type == StartTagToken || p.elementInScope(tableScope, p.tok.DataAtom) { + p.parseImpliedToken(EndTagToken, a.Select, a.Select.String()) + return false + } else { + // Ignore the token. + return true + } + } + } + return inSelectIM(p) +} + +// Section 12.2.5.4.18. +func afterBodyIM(p *parser) bool { + switch p.tok.Type { + case ErrorToken: + // Stop parsing. + return true + case TextToken: + s := strings.TrimLeft(p.tok.Data, whitespace) + if len(s) == 0 { + // It was all whitespace. + return inBodyIM(p) + } + case StartTagToken: + if p.tok.DataAtom == a.Html { + return inBodyIM(p) + } + case EndTagToken: + if p.tok.DataAtom == a.Html { + if !p.fragment { + p.im = afterAfterBodyIM + } + return true + } + case CommentToken: + // The comment is attached to the <html> element. + if len(p.oe) < 1 || p.oe[0].DataAtom != a.Html { + panic("html: bad parser state: <html> element not found, in the after-body insertion mode") + } + p.oe[0].AppendChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + return true + } + p.im = inBodyIM + return false +} + +// Section 12.2.5.4.19. +func inFramesetIM(p *parser) bool { + switch p.tok.Type { + case CommentToken: + p.addChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + case TextToken: + // Ignore all text but whitespace. + s := strings.Map(func(c rune) rune { + switch c { + case ' ', '\t', '\n', '\f', '\r': + return c + } + return -1 + }, p.tok.Data) + if s != "" { + p.addText(s) + } + case StartTagToken: + switch p.tok.DataAtom { + case a.Html: + return inBodyIM(p) + case a.Frameset: + p.addElement() + case a.Frame: + p.addElement() + p.oe.pop() + p.acknowledgeSelfClosingTag() + case a.Noframes: + return inHeadIM(p) + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Frameset: + if p.oe.top().DataAtom != a.Html { + p.oe.pop() + if p.oe.top().DataAtom != a.Frameset { + p.im = afterFramesetIM + return true + } + } + } + default: + // Ignore the token. + } + return true +} + +// Section 12.2.5.4.20. +func afterFramesetIM(p *parser) bool { + switch p.tok.Type { + case CommentToken: + p.addChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + case TextToken: + // Ignore all text but whitespace. + s := strings.Map(func(c rune) rune { + switch c { + case ' ', '\t', '\n', '\f', '\r': + return c + } + return -1 + }, p.tok.Data) + if s != "" { + p.addText(s) + } + case StartTagToken: + switch p.tok.DataAtom { + case a.Html: + return inBodyIM(p) + case a.Noframes: + return inHeadIM(p) + } + case EndTagToken: + switch p.tok.DataAtom { + case a.Html: + p.im = afterAfterFramesetIM + return true + } + default: + // Ignore the token. + } + return true +} + +// Section 12.2.5.4.21. +func afterAfterBodyIM(p *parser) bool { + switch p.tok.Type { + case ErrorToken: + // Stop parsing. + return true + case TextToken: + s := strings.TrimLeft(p.tok.Data, whitespace) + if len(s) == 0 { + // It was all whitespace. + return inBodyIM(p) + } + case StartTagToken: + if p.tok.DataAtom == a.Html { + return inBodyIM(p) + } + case CommentToken: + p.doc.AppendChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + return true + case DoctypeToken: + return inBodyIM(p) + } + p.im = inBodyIM + return false +} + +// Section 12.2.5.4.22. +func afterAfterFramesetIM(p *parser) bool { + switch p.tok.Type { + case CommentToken: + p.doc.AppendChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + case TextToken: + // Ignore all text but whitespace. + s := strings.Map(func(c rune) rune { + switch c { + case ' ', '\t', '\n', '\f', '\r': + return c + } + return -1 + }, p.tok.Data) + if s != "" { + p.tok.Data = s + return inBodyIM(p) + } + case StartTagToken: + switch p.tok.DataAtom { + case a.Html: + return inBodyIM(p) + case a.Noframes: + return inHeadIM(p) + } + case DoctypeToken: + return inBodyIM(p) + default: + // Ignore the token. + } + return true +} + +const whitespaceOrNUL = whitespace + "\x00" + +// Section 12.2.5.5. +func parseForeignContent(p *parser) bool { + switch p.tok.Type { + case TextToken: + if p.framesetOK { + p.framesetOK = strings.TrimLeft(p.tok.Data, whitespaceOrNUL) == "" + } + p.tok.Data = strings.Replace(p.tok.Data, "\x00", "\ufffd", -1) + p.addText(p.tok.Data) + case CommentToken: + p.addChild(&Node{ + Type: CommentNode, + Data: p.tok.Data, + }) + case StartTagToken: + b := breakout[p.tok.Data] + if p.tok.DataAtom == a.Font { + loop: + for _, attr := range p.tok.Attr { + switch attr.Key { + case "color", "face", "size": + b = true + break loop + } + } + } + if b { + for i := len(p.oe) - 1; i >= 0; i-- { + n := p.oe[i] + if n.Namespace == "" || htmlIntegrationPoint(n) || mathMLTextIntegrationPoint(n) { + p.oe = p.oe[:i+1] + break + } + } + return false + } + switch p.top().Namespace { + case "math": + adjustAttributeNames(p.tok.Attr, mathMLAttributeAdjustments) + case "svg": + // Adjust SVG tag names. The tokenizer lower-cases tag names, but + // SVG wants e.g. "foreignObject" with a capital second "O". + if x := svgTagNameAdjustments[p.tok.Data]; x != "" { + p.tok.DataAtom = a.Lookup([]byte(x)) + p.tok.Data = x + } + adjustAttributeNames(p.tok.Attr, svgAttributeAdjustments) + default: + panic("html: bad parser state: unexpected namespace") + } + adjustForeignAttributes(p.tok.Attr) + namespace := p.top().Namespace + p.addElement() + p.top().Namespace = namespace + if namespace != "" { + // Don't let the tokenizer go into raw text mode in foreign content + // (e.g. in an SVG <title> tag). + p.tokenizer.NextIsNotRawText() + } + if p.hasSelfClosingToken { + p.oe.pop() + p.acknowledgeSelfClosingTag() + } + case EndTagToken: + for i := len(p.oe) - 1; i >= 0; i-- { + if p.oe[i].Namespace == "" { + return p.im(p) + } + if strings.EqualFold(p.oe[i].Data, p.tok.Data) { + p.oe = p.oe[:i] + break + } + } + return true + default: + // Ignore the token. + } + return true +} + +// Section 12.2.5. +func (p *parser) inForeignContent() bool { + if len(p.oe) == 0 { + return false + } + n := p.oe[len(p.oe)-1] + if n.Namespace == "" { + return false + } + if mathMLTextIntegrationPoint(n) { + if p.tok.Type == StartTagToken && p.tok.DataAtom != a.Mglyph && p.tok.DataAtom != a.Malignmark { + return false + } + if p.tok.Type == TextToken { + return false + } + } + if n.Namespace == "math" && n.DataAtom == a.AnnotationXml && p.tok.Type == StartTagToken && p.tok.DataAtom == a.Svg { + return false + } + if htmlIntegrationPoint(n) && (p.tok.Type == StartTagToken || p.tok.Type == TextToken) { + return false + } + if p.tok.Type == ErrorToken { + return false + } + return true +} + +// parseImpliedToken parses a token as though it had appeared in the parser's +// input. +func (p *parser) parseImpliedToken(t TokenType, dataAtom a.Atom, data string) { + realToken, selfClosing := p.tok, p.hasSelfClosingToken + p.tok = Token{ + Type: t, + DataAtom: dataAtom, + Data: data, + } + p.hasSelfClosingToken = false + p.parseCurrentToken() + p.tok, p.hasSelfClosingToken = realToken, selfClosing +} + +// parseCurrentToken runs the current token through the parsing routines +// until it is consumed. +func (p *parser) parseCurrentToken() { + if p.tok.Type == SelfClosingTagToken { + p.hasSelfClosingToken = true + p.tok.Type = StartTagToken + } + + consumed := false + for !consumed { + if p.inForeignContent() { + consumed = parseForeignContent(p) + } else { + consumed = p.im(p) + } + } + + if p.hasSelfClosingToken { + // This is a parse error, but ignore it. + p.hasSelfClosingToken = false + } +} + +func (p *parser) parse() error { + // Iterate until EOF. Any other error will cause an early return. + var err error + for err != io.EOF { + // CDATA sections are allowed only in foreign content. + n := p.oe.top() + p.tokenizer.AllowCDATA(n != nil && n.Namespace != "") + // Read and parse the next token. + p.tokenizer.Next() + p.tok = p.tokenizer.Token() + if p.tok.Type == ErrorToken { + err = p.tokenizer.Err() + if err != nil && err != io.EOF { + return err + } + } + p.parseCurrentToken() + } + return nil +} + +// Parse returns the parse tree for the HTML from the given Reader. +// The input is assumed to be UTF-8 encoded. +func Parse(r io.Reader) (*Node, error) { + p := &parser{ + tokenizer: NewTokenizer(r), + doc: &Node{ + Type: DocumentNode, + }, + scripting: true, + framesetOK: true, + im: initialIM, + } + err := p.parse() + if err != nil { + return nil, err + } + return p.doc, nil +} + +// ParseFragment parses a fragment of HTML and returns the nodes that were +// found. If the fragment is the InnerHTML for an existing element, pass that +// element in context. +func ParseFragment(r io.Reader, context *Node) ([]*Node, error) { + contextTag := "" + if context != nil { + if context.Type != ElementNode { + return nil, errors.New("html: ParseFragment of non-element Node") + } + // The next check isn't just context.DataAtom.String() == context.Data because + // it is valid to pass an element whose tag isn't a known atom. For example, + // DataAtom == 0 and Data = "tagfromthefuture" is perfectly consistent. + if context.DataAtom != a.Lookup([]byte(context.Data)) { + return nil, fmt.Errorf("html: inconsistent Node: DataAtom=%q, Data=%q", context.DataAtom, context.Data) + } + contextTag = context.DataAtom.String() + } + p := &parser{ + tokenizer: NewTokenizerFragment(r, contextTag), + doc: &Node{ + Type: DocumentNode, + }, + scripting: true, + fragment: true, + context: context, + } + + root := &Node{ + Type: ElementNode, + DataAtom: a.Html, + Data: a.Html.String(), + } + p.doc.AppendChild(root) + p.oe = nodeStack{root} + p.resetInsertionMode() + + for n := context; n != nil; n = n.Parent { + if n.Type == ElementNode && n.DataAtom == a.Form { + p.form = n + break + } + } + + err := p.parse() + if err != nil { + return nil, err + } + + parent := p.doc + if context != nil { + parent = root + } + + var result []*Node + for c := parent.FirstChild; c != nil; { + next := c.NextSibling + parent.RemoveChild(c) + result = append(result, c) + c = next + } + return result, nil +} diff --git a/vendor/golang.org/x/net/html/render.go b/vendor/golang.org/x/net/html/render.go new file mode 100644 index 000000000..d34564f49 --- /dev/null +++ b/vendor/golang.org/x/net/html/render.go @@ -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, +} diff --git a/vendor/golang.org/x/net/html/token.go b/vendor/golang.org/x/net/html/token.go new file mode 100644 index 000000000..893e272a9 --- /dev/null +++ b/vendor/golang.org/x/net/html/token.go @@ -0,0 +1,1219 @@ +// 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" + "errors" + "io" + "strconv" + "strings" + + "golang.org/x/net/html/atom" +) + +// A TokenType is the type of a Token. +type TokenType uint32 + +const ( + // ErrorToken means that an error occurred during tokenization. + ErrorToken TokenType = iota + // TextToken means a text node. + TextToken + // A StartTagToken looks like <a>. + StartTagToken + // An EndTagToken looks like </a>. + EndTagToken + // A SelfClosingTagToken tag looks like <br/>. + SelfClosingTagToken + // A CommentToken looks like <!--x-->. + CommentToken + // A DoctypeToken looks like <!DOCTYPE x> + DoctypeToken +) + +// ErrBufferExceeded means that the buffering limit was exceeded. +var ErrBufferExceeded = errors.New("max buffer exceeded") + +// String returns a string representation of the TokenType. +func (t TokenType) String() string { + switch t { + case ErrorToken: + return "Error" + case TextToken: + return "Text" + case StartTagToken: + return "StartTag" + case EndTagToken: + return "EndTag" + case SelfClosingTagToken: + return "SelfClosingTag" + case CommentToken: + return "Comment" + case DoctypeToken: + return "Doctype" + } + return "Invalid(" + strconv.Itoa(int(t)) + ")" +} + +// An Attribute is an attribute namespace-key-value triple. Namespace is +// non-empty for foreign attributes like xlink, Key is alphabetic (and hence +// does not contain escapable characters like '&', '<' or '>'), and Val is +// unescaped (it looks like "a<b" rather than "a<b"). +// +// Namespace is only used by the parser, not the tokenizer. +type Attribute struct { + Namespace, Key, Val string +} + +// A Token consists of a TokenType and some Data (tag name for start and end +// tags, content for text, comments and doctypes). A tag Token may also contain +// a slice of Attributes. Data is unescaped for all Tokens (it looks like "a<b" +// rather than "a<b"). For tag Tokens, DataAtom is the atom for Data, or +// zero if Data is not a known tag name. +type Token struct { + Type TokenType + DataAtom atom.Atom + Data string + Attr []Attribute +} + +// tagString returns a string representation of a tag Token's Data and Attr. +func (t Token) tagString() string { + if len(t.Attr) == 0 { + return t.Data + } + buf := bytes.NewBufferString(t.Data) + for _, a := range t.Attr { + buf.WriteByte(' ') + buf.WriteString(a.Key) + buf.WriteString(`="`) + escape(buf, a.Val) + buf.WriteByte('"') + } + return buf.String() +} + +// String returns a string representation of the Token. +func (t Token) String() string { + switch t.Type { + case ErrorToken: + return "" + case TextToken: + return EscapeString(t.Data) + case StartTagToken: + return "<" + t.tagString() + ">" + case EndTagToken: + return "</" + t.tagString() + ">" + case SelfClosingTagToken: + return "<" + t.tagString() + "/>" + case CommentToken: + return "<!--" + t.Data + "-->" + case DoctypeToken: + return "<!DOCTYPE " + t.Data + ">" + } + return "Invalid(" + strconv.Itoa(int(t.Type)) + ")" +} + +// span is a range of bytes in a Tokenizer's buffer. The start is inclusive, +// the end is exclusive. +type span struct { + start, end int +} + +// A Tokenizer returns a stream of HTML Tokens. +type Tokenizer struct { + // r is the source of the HTML text. + r io.Reader + // tt is the TokenType of the current token. + tt TokenType + // err is the first error encountered during tokenization. It is possible + // for tt != Error && err != nil to hold: this means that Next returned a + // valid token but the subsequent Next call will return an error token. + // For example, if the HTML text input was just "plain", then the first + // Next call would set z.err to io.EOF but return a TextToken, and all + // subsequent Next calls would return an ErrorToken. + // err is never reset. Once it becomes non-nil, it stays non-nil. + err error + // readErr is the error returned by the io.Reader r. It is separate from + // err because it is valid for an io.Reader to return (n int, err1 error) + // such that n > 0 && err1 != nil, and callers should always process the + // n > 0 bytes before considering the error err1. + readErr error + // buf[raw.start:raw.end] holds the raw bytes of the current token. + // buf[raw.end:] is buffered input that will yield future tokens. + raw span + buf []byte + // maxBuf limits the data buffered in buf. A value of 0 means unlimited. + maxBuf int + // buf[data.start:data.end] holds the raw bytes of the current token's data: + // a text token's text, a tag token's tag name, etc. + data span + // pendingAttr is the attribute key and value currently being tokenized. + // When complete, pendingAttr is pushed onto attr. nAttrReturned is + // incremented on each call to TagAttr. + pendingAttr [2]span + attr [][2]span + nAttrReturned int + // rawTag is the "script" in "</script>" that closes the next token. If + // non-empty, the subsequent call to Next will return a raw or RCDATA text + // token: one that treats "<p>" as text instead of an element. + // rawTag's contents are lower-cased. + rawTag string + // textIsRaw is whether the current text token's data is not escaped. + textIsRaw bool + // convertNUL is whether NUL bytes in the current token's data should + // be converted into \ufffd replacement characters. + convertNUL bool + // allowCDATA is whether CDATA sections are allowed in the current context. + allowCDATA bool +} + +// AllowCDATA sets whether or not the tokenizer recognizes <![CDATA[foo]]> as +// the text "foo". The default value is false, which means to recognize it as +// a bogus comment "<!-- [CDATA[foo]] -->" instead. +// +// Strictly speaking, an HTML5 compliant tokenizer should allow CDATA if and +// only if tokenizing foreign content, such as MathML and SVG. However, +// tracking foreign-contentness is difficult to do purely in the tokenizer, +// as opposed to the parser, due to HTML integration points: an <svg> element +// can contain a <foreignObject> that is foreign-to-SVG but not foreign-to- +// HTML. For strict compliance with the HTML5 tokenization algorithm, it is the +// responsibility of the user of a tokenizer to call AllowCDATA as appropriate. +// In practice, if using the tokenizer without caring whether MathML or SVG +// CDATA is text or comments, such as tokenizing HTML to find all the anchor +// text, it is acceptable to ignore this responsibility. +func (z *Tokenizer) AllowCDATA(allowCDATA bool) { + z.allowCDATA = allowCDATA +} + +// NextIsNotRawText instructs the tokenizer that the next token should not be +// considered as 'raw text'. Some elements, such as script and title elements, +// normally require the next token after the opening tag to be 'raw text' that +// has no child elements. For example, tokenizing "<title>a<b>c</b>d</title>" +// yields a start tag token for "<title>", a text token for "a<b>c</b>d", and +// an end tag token for "</title>". There are no distinct start tag or end tag +// tokens for the "<b>" and "</b>". +// +// This tokenizer implementation will generally look for raw text at the right +// times. Strictly speaking, an HTML5 compliant tokenizer should not look for +// raw text if in foreign content: <title> generally needs raw text, but a +// <title> inside an <svg> does not. Another example is that a <textarea> +// generally needs raw text, but a <textarea> is not allowed as an immediate +// child of a <select>; in normal parsing, a <textarea> implies </select>, but +// one cannot close the implicit element when parsing a <select>'s InnerHTML. +// Similarly to AllowCDATA, tracking the correct moment to override raw-text- +// ness is difficult to do purely in the tokenizer, as opposed to the parser. +// For strict compliance with the HTML5 tokenization algorithm, it is the +// responsibility of the user of a tokenizer to call NextIsNotRawText as +// appropriate. In practice, like AllowCDATA, it is acceptable to ignore this +// responsibility for basic usage. +// +// Note that this 'raw text' concept is different from the one offered by the +// Tokenizer.Raw method. +func (z *Tokenizer) NextIsNotRawText() { + z.rawTag = "" +} + +// Err returns the error associated with the most recent ErrorToken token. +// This is typically io.EOF, meaning the end of tokenization. +func (z *Tokenizer) Err() error { + if z.tt != ErrorToken { + return nil + } + return z.err +} + +// readByte returns the next byte from the input stream, doing a buffered read +// from z.r into z.buf if necessary. z.buf[z.raw.start:z.raw.end] remains a contiguous byte +// slice that holds all the bytes read so far for the current token. +// It sets z.err if the underlying reader returns an error. +// Pre-condition: z.err == nil. +func (z *Tokenizer) readByte() byte { + if z.raw.end >= len(z.buf) { + // Our buffer is exhausted and we have to read from z.r. Check if the + // previous read resulted in an error. + if z.readErr != nil { + z.err = z.readErr + return 0 + } + // We copy z.buf[z.raw.start:z.raw.end] to the beginning of z.buf. If the length + // z.raw.end - z.raw.start is more than half the capacity of z.buf, then we + // allocate a new buffer before the copy. + c := cap(z.buf) + d := z.raw.end - z.raw.start + var buf1 []byte + if 2*d > c { + buf1 = make([]byte, d, 2*c) + } else { + buf1 = z.buf[:d] + } + copy(buf1, z.buf[z.raw.start:z.raw.end]) + if x := z.raw.start; x != 0 { + // Adjust the data/attr spans to refer to the same contents after the copy. + z.data.start -= x + z.data.end -= x + z.pendingAttr[0].start -= x + z.pendingAttr[0].end -= x + z.pendingAttr[1].start -= x + z.pendingAttr[1].end -= x + for i := range z.attr { + z.attr[i][0].start -= x + z.attr[i][0].end -= x + z.attr[i][1].start -= x + z.attr[i][1].end -= x + } + } + z.raw.start, z.raw.end, z.buf = 0, d, buf1[:d] + // Now that we have copied the live bytes to the start of the buffer, + // we read from z.r into the remainder. + var n int + n, z.readErr = readAtLeastOneByte(z.r, buf1[d:cap(buf1)]) + if n == 0 { + z.err = z.readErr + return 0 + } + z.buf = buf1[:d+n] + } + x := z.buf[z.raw.end] + z.raw.end++ + if z.maxBuf > 0 && z.raw.end-z.raw.start >= z.maxBuf { + z.err = ErrBufferExceeded + return 0 + } + return x +} + +// Buffered returns a slice containing data buffered but not yet tokenized. +func (z *Tokenizer) Buffered() []byte { + return z.buf[z.raw.end:] +} + +// readAtLeastOneByte wraps an io.Reader so that reading cannot return (0, nil). +// It returns io.ErrNoProgress if the underlying r.Read method returns (0, nil) +// too many times in succession. +func readAtLeastOneByte(r io.Reader, b []byte) (int, error) { + for i := 0; i < 100; i++ { + n, err := r.Read(b) + if n != 0 || err != nil { + return n, err + } + } + return 0, io.ErrNoProgress +} + +// skipWhiteSpace skips past any white space. +func (z *Tokenizer) skipWhiteSpace() { + if z.err != nil { + return + } + for { + c := z.readByte() + if z.err != nil { + return + } + switch c { + case ' ', '\n', '\r', '\t', '\f': + // No-op. + default: + z.raw.end-- + return + } + } +} + +// readRawOrRCDATA reads until the next "</foo>", where "foo" is z.rawTag and +// is typically something like "script" or "textarea". +func (z *Tokenizer) readRawOrRCDATA() { + if z.rawTag == "script" { + z.readScript() + z.textIsRaw = true + z.rawTag = "" + return + } +loop: + for { + c := z.readByte() + if z.err != nil { + break loop + } + if c != '<' { + continue loop + } + c = z.readByte() + if z.err != nil { + break loop + } + if c != '/' { + continue loop + } + if z.readRawEndTag() || z.err != nil { + break loop + } + } + z.data.end = z.raw.end + // A textarea's or title's RCDATA can contain escaped entities. + z.textIsRaw = z.rawTag != "textarea" && z.rawTag != "title" + z.rawTag = "" +} + +// readRawEndTag attempts to read a tag like "</foo>", where "foo" is z.rawTag. +// If it succeeds, it backs up the input position to reconsume the tag and +// returns true. Otherwise it returns false. The opening "</" has already been +// consumed. +func (z *Tokenizer) readRawEndTag() bool { + for i := 0; i < len(z.rawTag); i++ { + c := z.readByte() + if z.err != nil { + return false + } + if c != z.rawTag[i] && c != z.rawTag[i]-('a'-'A') { + z.raw.end-- + return false + } + } + c := z.readByte() + if z.err != nil { + return false + } + switch c { + case ' ', '\n', '\r', '\t', '\f', '/', '>': + // The 3 is 2 for the leading "</" plus 1 for the trailing character c. + z.raw.end -= 3 + len(z.rawTag) + return true + } + z.raw.end-- + return false +} + +// readScript reads until the next </script> tag, following the byzantine +// rules for escaping/hiding the closing tag. +func (z *Tokenizer) readScript() { + defer func() { + z.data.end = z.raw.end + }() + var c byte + +scriptData: + c = z.readByte() + if z.err != nil { + return + } + if c == '<' { + goto scriptDataLessThanSign + } + goto scriptData + +scriptDataLessThanSign: + c = z.readByte() + if z.err != nil { + return + } + switch c { + case '/': + goto scriptDataEndTagOpen + case '!': + goto scriptDataEscapeStart + } + z.raw.end-- + goto scriptData + +scriptDataEndTagOpen: + if z.readRawEndTag() || z.err != nil { + return + } + goto scriptData + +scriptDataEscapeStart: + c = z.readByte() + if z.err != nil { + return + } + if c == '-' { + goto scriptDataEscapeStartDash + } + z.raw.end-- + goto scriptData + +scriptDataEscapeStartDash: + c = z.readByte() + if z.err != nil { + return + } + if c == '-' { + goto scriptDataEscapedDashDash + } + z.raw.end-- + goto scriptData + +scriptDataEscaped: + c = z.readByte() + if z.err != nil { + return + } + switch c { + case '-': + goto scriptDataEscapedDash + case '<': + goto scriptDataEscapedLessThanSign + } + goto scriptDataEscaped + +scriptDataEscapedDash: + c = z.readByte() + if z.err != nil { + return + } + switch c { + case '-': + goto scriptDataEscapedDashDash + case '<': + goto scriptDataEscapedLessThanSign + } + goto scriptDataEscaped + +scriptDataEscapedDashDash: + c = z.readByte() + if z.err != nil { + return + } + switch c { + case '-': + goto scriptDataEscapedDashDash + case '<': + goto scriptDataEscapedLessThanSign + case '>': + goto scriptData + } + goto scriptDataEscaped + +scriptDataEscapedLessThanSign: + c = z.readByte() + if z.err != nil { + return + } + if c == '/' { + goto scriptDataEscapedEndTagOpen + } + if 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' { + goto scriptDataDoubleEscapeStart + } + z.raw.end-- + goto scriptData + +scriptDataEscapedEndTagOpen: + if z.readRawEndTag() || z.err != nil { + return + } + goto scriptDataEscaped + +scriptDataDoubleEscapeStart: + z.raw.end-- + for i := 0; i < len("script"); i++ { + c = z.readByte() + if z.err != nil { + return + } + if c != "script"[i] && c != "SCRIPT"[i] { + z.raw.end-- + goto scriptDataEscaped + } + } + c = z.readByte() + if z.err != nil { + return + } + switch c { + case ' ', '\n', '\r', '\t', '\f', '/', '>': + goto scriptDataDoubleEscaped + } + z.raw.end-- + goto scriptDataEscaped + +scriptDataDoubleEscaped: + c = z.readByte() + if z.err != nil { + return + } + switch c { + case '-': + goto scriptDataDoubleEscapedDash + case '<': + goto scriptDataDoubleEscapedLessThanSign + } + goto scriptDataDoubleEscaped + +scriptDataDoubleEscapedDash: + c = z.readByte() + if z.err != nil { + return + } + switch c { + case '-': + goto scriptDataDoubleEscapedDashDash + case '<': + goto scriptDataDoubleEscapedLessThanSign + } + goto scriptDataDoubleEscaped + +scriptDataDoubleEscapedDashDash: + c = z.readByte() + if z.err != nil { + return + } + switch c { + case '-': + goto scriptDataDoubleEscapedDashDash + case '<': + goto scriptDataDoubleEscapedLessThanSign + case '>': + goto scriptData + } + goto scriptDataDoubleEscaped + +scriptDataDoubleEscapedLessThanSign: + c = z.readByte() + if z.err != nil { + return + } + if c == '/' { + goto scriptDataDoubleEscapeEnd + } + z.raw.end-- + goto scriptDataDoubleEscaped + +scriptDataDoubleEscapeEnd: + if z.readRawEndTag() { + z.raw.end += len("</script>") + goto scriptDataEscaped + } + if z.err != nil { + return + } + goto scriptDataDoubleEscaped +} + +// readComment reads the next comment token starting with "<!--". The opening +// "<!--" has already been consumed. +func (z *Tokenizer) readComment() { + z.data.start = z.raw.end + defer func() { + if z.data.end < z.data.start { + // It's a comment with no data, like <!-->. + z.data.end = z.data.start + } + }() + for dashCount := 2; ; { + c := z.readByte() + if z.err != nil { + // Ignore up to two dashes at EOF. + if dashCount > 2 { + dashCount = 2 + } + z.data.end = z.raw.end - dashCount + return + } + switch c { + case '-': + dashCount++ + continue + case '>': + if dashCount >= 2 { + z.data.end = z.raw.end - len("-->") + return + } + case '!': + if dashCount >= 2 { + c = z.readByte() + if z.err != nil { + z.data.end = z.raw.end + return + } + if c == '>' { + z.data.end = z.raw.end - len("--!>") + return + } + } + } + dashCount = 0 + } +} + +// readUntilCloseAngle reads until the next ">". +func (z *Tokenizer) readUntilCloseAngle() { + z.data.start = z.raw.end + for { + c := z.readByte() + if z.err != nil { + z.data.end = z.raw.end + return + } + if c == '>' { + z.data.end = z.raw.end - len(">") + return + } + } +} + +// readMarkupDeclaration reads the next token starting with "<!". It might be +// a "<!--comment-->", a "<!DOCTYPE foo>", a "<![CDATA[section]]>" or +// "<!a bogus comment". The opening "<!" has already been consumed. +func (z *Tokenizer) readMarkupDeclaration() TokenType { + z.data.start = z.raw.end + var c [2]byte + for i := 0; i < 2; i++ { + c[i] = z.readByte() + if z.err != nil { + z.data.end = z.raw.end + return CommentToken + } + } + if c[0] == '-' && c[1] == '-' { + z.readComment() + return CommentToken + } + z.raw.end -= 2 + if z.readDoctype() { + return DoctypeToken + } + if z.allowCDATA && z.readCDATA() { + z.convertNUL = true + return TextToken + } + // It's a bogus comment. + z.readUntilCloseAngle() + return CommentToken +} + +// readDoctype attempts to read a doctype declaration and returns true if +// successful. The opening "<!" has already been consumed. +func (z *Tokenizer) readDoctype() bool { + const s = "DOCTYPE" + for i := 0; i < len(s); i++ { + c := z.readByte() + if z.err != nil { + z.data.end = z.raw.end + return false + } + if c != s[i] && c != s[i]+('a'-'A') { + // Back up to read the fragment of "DOCTYPE" again. + z.raw.end = z.data.start + return false + } + } + if z.skipWhiteSpace(); z.err != nil { + z.data.start = z.raw.end + z.data.end = z.raw.end + return true + } + z.readUntilCloseAngle() + return true +} + +// readCDATA attempts to read a CDATA section and returns true if +// successful. The opening "<!" has already been consumed. +func (z *Tokenizer) readCDATA() bool { + const s = "[CDATA[" + for i := 0; i < len(s); i++ { + c := z.readByte() + if z.err != nil { + z.data.end = z.raw.end + return false + } + if c != s[i] { + // Back up to read the fragment of "[CDATA[" again. + z.raw.end = z.data.start + return false + } + } + z.data.start = z.raw.end + brackets := 0 + for { + c := z.readByte() + if z.err != nil { + z.data.end = z.raw.end + return true + } + switch c { + case ']': + brackets++ + case '>': + if brackets >= 2 { + z.data.end = z.raw.end - len("]]>") + return true + } + brackets = 0 + default: + brackets = 0 + } + } +} + +// startTagIn returns whether the start tag in z.buf[z.data.start:z.data.end] +// case-insensitively matches any element of ss. +func (z *Tokenizer) startTagIn(ss ...string) bool { +loop: + for _, s := range ss { + if z.data.end-z.data.start != len(s) { + continue loop + } + for i := 0; i < len(s); i++ { + c := z.buf[z.data.start+i] + if 'A' <= c && c <= 'Z' { + c += 'a' - 'A' + } + if c != s[i] { + continue loop + } + } + return true + } + return false +} + +// readStartTag reads the next start tag token. The opening "<a" has already +// been consumed, where 'a' means anything in [A-Za-z]. +func (z *Tokenizer) readStartTag() TokenType { + z.readTag(true) + if z.err != nil { + return ErrorToken + } + // Several tags flag the tokenizer's next token as raw. + c, raw := z.buf[z.data.start], false + if 'A' <= c && c <= 'Z' { + c += 'a' - 'A' + } + switch c { + case 'i': + raw = z.startTagIn("iframe") + case 'n': + raw = z.startTagIn("noembed", "noframes", "noscript") + case 'p': + raw = z.startTagIn("plaintext") + case 's': + raw = z.startTagIn("script", "style") + case 't': + raw = z.startTagIn("textarea", "title") + case 'x': + raw = z.startTagIn("xmp") + } + if raw { + z.rawTag = strings.ToLower(string(z.buf[z.data.start:z.data.end])) + } + // Look for a self-closing token like "<br/>". + if z.err == nil && z.buf[z.raw.end-2] == '/' { + return SelfClosingTagToken + } + return StartTagToken +} + +// readTag reads the next tag token and its attributes. If saveAttr, those +// attributes are saved in z.attr, otherwise z.attr is set to an empty slice. +// The opening "<a" or "</a" has already been consumed, where 'a' means anything +// in [A-Za-z]. +func (z *Tokenizer) readTag(saveAttr bool) { + z.attr = z.attr[:0] + z.nAttrReturned = 0 + // Read the tag name and attribute key/value pairs. + z.readTagName() + if z.skipWhiteSpace(); z.err != nil { + return + } + for { + c := z.readByte() + if z.err != nil || c == '>' { + break + } + z.raw.end-- + z.readTagAttrKey() + z.readTagAttrVal() + // Save pendingAttr if saveAttr and that attribute has a non-empty key. + if saveAttr && z.pendingAttr[0].start != z.pendingAttr[0].end { + z.attr = append(z.attr, z.pendingAttr) + } + if z.skipWhiteSpace(); z.err != nil { + break + } + } +} + +// readTagName sets z.data to the "div" in "<div k=v>". The reader (z.raw.end) +// is positioned such that the first byte of the tag name (the "d" in "<div") +// has already been consumed. +func (z *Tokenizer) readTagName() { + z.data.start = z.raw.end - 1 + for { + c := z.readByte() + if z.err != nil { + z.data.end = z.raw.end + return + } + switch c { + case ' ', '\n', '\r', '\t', '\f': + z.data.end = z.raw.end - 1 + return + case '/', '>': + z.raw.end-- + z.data.end = z.raw.end + return + } + } +} + +// readTagAttrKey sets z.pendingAttr[0] to the "k" in "<div k=v>". +// Precondition: z.err == nil. +func (z *Tokenizer) readTagAttrKey() { + z.pendingAttr[0].start = z.raw.end + for { + c := z.readByte() + if z.err != nil { + z.pendingAttr[0].end = z.raw.end + return + } + switch c { + case ' ', '\n', '\r', '\t', '\f', '/': + z.pendingAttr[0].end = z.raw.end - 1 + return + case '=', '>': + z.raw.end-- + z.pendingAttr[0].end = z.raw.end + return + } + } +} + +// readTagAttrVal sets z.pendingAttr[1] to the "v" in "<div k=v>". +func (z *Tokenizer) readTagAttrVal() { + z.pendingAttr[1].start = z.raw.end + z.pendingAttr[1].end = z.raw.end + if z.skipWhiteSpace(); z.err != nil { + return + } + c := z.readByte() + if z.err != nil { + return + } + if c != '=' { + z.raw.end-- + return + } + if z.skipWhiteSpace(); z.err != nil { + return + } + quote := z.readByte() + if z.err != nil { + return + } + switch quote { + case '>': + z.raw.end-- + return + + case '\'', '"': + z.pendingAttr[1].start = z.raw.end + for { + c := z.readByte() + if z.err != nil { + z.pendingAttr[1].end = z.raw.end + return + } + if c == quote { + z.pendingAttr[1].end = z.raw.end - 1 + return + } + } + + default: + z.pendingAttr[1].start = z.raw.end - 1 + for { + c := z.readByte() + if z.err != nil { + z.pendingAttr[1].end = z.raw.end + return + } + switch c { + case ' ', '\n', '\r', '\t', '\f': + z.pendingAttr[1].end = z.raw.end - 1 + return + case '>': + z.raw.end-- + z.pendingAttr[1].end = z.raw.end + return + } + } + } +} + +// Next scans the next token and returns its type. +func (z *Tokenizer) Next() TokenType { + z.raw.start = z.raw.end + z.data.start = z.raw.end + z.data.end = z.raw.end + if z.err != nil { + z.tt = ErrorToken + return z.tt + } + if z.rawTag != "" { + if z.rawTag == "plaintext" { + // Read everything up to EOF. + for z.err == nil { + z.readByte() + } + z.data.end = z.raw.end + z.textIsRaw = true + } else { + z.readRawOrRCDATA() + } + if z.data.end > z.data.start { + z.tt = TextToken + z.convertNUL = true + return z.tt + } + } + z.textIsRaw = false + z.convertNUL = false + +loop: + for { + c := z.readByte() + if z.err != nil { + break loop + } + if c != '<' { + continue loop + } + + // Check if the '<' we have just read is part of a tag, comment + // or doctype. If not, it's part of the accumulated text token. + c = z.readByte() + if z.err != nil { + break loop + } + var tokenType TokenType + switch { + case 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z': + tokenType = StartTagToken + case c == '/': + tokenType = EndTagToken + case c == '!' || c == '?': + // We use CommentToken to mean any of "<!--actual comments-->", + // "<!DOCTYPE declarations>" and "<?xml processing instructions?>". + tokenType = CommentToken + default: + // Reconsume the current character. + z.raw.end-- + continue + } + + // We have a non-text token, but we might have accumulated some text + // before that. If so, we return the text first, and return the non- + // text token on the subsequent call to Next. + if x := z.raw.end - len("<a"); z.raw.start < x { + z.raw.end = x + z.data.end = x + z.tt = TextToken + return z.tt + } + switch tokenType { + case StartTagToken: + z.tt = z.readStartTag() + return z.tt + case EndTagToken: + c = z.readByte() + if z.err != nil { + break loop + } + if c == '>' { + // "</>" does not generate a token at all. Generate an empty comment + // to allow passthrough clients to pick up the data using Raw. + // Reset the tokenizer state and start again. + z.tt = CommentToken + return z.tt + } + if 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' { + z.readTag(false) + if z.err != nil { + z.tt = ErrorToken + } else { + z.tt = EndTagToken + } + return z.tt + } + z.raw.end-- + z.readUntilCloseAngle() + z.tt = CommentToken + return z.tt + case CommentToken: + if c == '!' { + z.tt = z.readMarkupDeclaration() + return z.tt + } + z.raw.end-- + z.readUntilCloseAngle() + z.tt = CommentToken + return z.tt + } + } + if z.raw.start < z.raw.end { + z.data.end = z.raw.end + z.tt = TextToken + return z.tt + } + z.tt = ErrorToken + return z.tt +} + +// Raw returns the unmodified text of the current token. Calling Next, Token, +// Text, TagName or TagAttr may change the contents of the returned slice. +func (z *Tokenizer) Raw() []byte { + return z.buf[z.raw.start:z.raw.end] +} + +// convertNewlines converts "\r" and "\r\n" in s to "\n". +// The conversion happens in place, but the resulting slice may be shorter. +func convertNewlines(s []byte) []byte { + for i, c := range s { + if c != '\r' { + continue + } + + src := i + 1 + if src >= len(s) || s[src] != '\n' { + s[i] = '\n' + continue + } + + dst := i + for src < len(s) { + if s[src] == '\r' { + if src+1 < len(s) && s[src+1] == '\n' { + src++ + } + s[dst] = '\n' + } else { + s[dst] = s[src] + } + src++ + dst++ + } + return s[:dst] + } + return s +} + +var ( + nul = []byte("\x00") + replacement = []byte("\ufffd") +) + +// Text returns the unescaped text of a text, comment or doctype token. The +// contents of the returned slice may change on the next call to Next. +func (z *Tokenizer) Text() []byte { + switch z.tt { + case TextToken, CommentToken, DoctypeToken: + s := z.buf[z.data.start:z.data.end] + z.data.start = z.raw.end + z.data.end = z.raw.end + s = convertNewlines(s) + if (z.convertNUL || z.tt == CommentToken) && bytes.Contains(s, nul) { + s = bytes.Replace(s, nul, replacement, -1) + } + if !z.textIsRaw { + s = unescape(s, false) + } + return s + } + return nil +} + +// TagName returns the lower-cased name of a tag token (the `img` out of +// `<IMG SRC="foo">`) and whether the tag has attributes. +// The contents of the returned slice may change on the next call to Next. +func (z *Tokenizer) TagName() (name []byte, hasAttr bool) { + if z.data.start < z.data.end { + switch z.tt { + case StartTagToken, EndTagToken, SelfClosingTagToken: + s := z.buf[z.data.start:z.data.end] + z.data.start = z.raw.end + z.data.end = z.raw.end + return lower(s), z.nAttrReturned < len(z.attr) + } + } + return nil, false +} + +// TagAttr returns the lower-cased key and unescaped value of the next unparsed +// attribute for the current tag token and whether there are more attributes. +// The contents of the returned slices may change on the next call to Next. +func (z *Tokenizer) TagAttr() (key, val []byte, moreAttr bool) { + if z.nAttrReturned < len(z.attr) { + switch z.tt { + case StartTagToken, SelfClosingTagToken: + x := z.attr[z.nAttrReturned] + z.nAttrReturned++ + key = z.buf[x[0].start:x[0].end] + val = z.buf[x[1].start:x[1].end] + return lower(key), unescape(convertNewlines(val), true), z.nAttrReturned < len(z.attr) + } + } + return nil, nil, false +} + +// Token returns the next Token. The result's Data and Attr values remain valid +// after subsequent Next calls. +func (z *Tokenizer) Token() Token { + t := Token{Type: z.tt} + switch z.tt { + case TextToken, CommentToken, DoctypeToken: + t.Data = string(z.Text()) + case StartTagToken, SelfClosingTagToken, EndTagToken: + name, moreAttr := z.TagName() + for moreAttr { + var key, val []byte + key, val, moreAttr = z.TagAttr() + t.Attr = append(t.Attr, Attribute{"", atom.String(key), string(val)}) + } + if a := atom.Lookup(name); a != 0 { + t.DataAtom, t.Data = a, a.String() + } else { + t.DataAtom, t.Data = 0, string(name) + } + } + return t +} + +// SetMaxBuf sets a limit on the amount of data buffered during tokenization. +// A value of 0 means unlimited. +func (z *Tokenizer) SetMaxBuf(n int) { + z.maxBuf = n +} + +// NewTokenizer returns a new HTML Tokenizer for the given Reader. +// The input is assumed to be UTF-8 encoded. +func NewTokenizer(r io.Reader) *Tokenizer { + return NewTokenizerFragment(r, "") +} + +// NewTokenizerFragment returns a new HTML Tokenizer for the given Reader, for +// tokenizing an existing element's InnerHTML fragment. contextTag is that +// element's tag, such as "div" or "iframe". +// +// For example, how the InnerHTML "a<b" is tokenized depends on whether it is +// for a <p> tag or a <script> tag. +// +// The input is assumed to be UTF-8 encoded. +func NewTokenizerFragment(r io.Reader, contextTag string) *Tokenizer { + z := &Tokenizer{ + r: r, + buf: make([]byte, 0, 4096), + } + if contextTag != "" { + switch s := strings.ToLower(contextTag); s { + case "iframe", "noembed", "noframes", "noscript", "plaintext", "script", "style", "title", "textarea", "xmp": + z.rawTag = s + } + } + return z +} |