Merge pull request #960 from fjl/nat-fixes

p2p/nat: fix UPnP auto discovery

Godeps/Godeps.json

@@ -27,7 +27,7 @@
 		},
 		{
 			"ImportPath": "github.com/huin/goupnp",
-			"Rev": "4191d8a85005844ea202fde52799681971b12dfe"
+			"Rev": "c57ae84388ab59076fd547f1abeab71c2edb0a21"
 		},
 		{
 			"ImportPath": "github.com/jackpal/go-nat-pmp",
@@ -89,6 +89,18 @@
 			"ImportPath": "golang.org/x/crypto/scrypt",
 			"Rev": "4ed45ec682102c643324fae5dff8dab085b6c300"
 		},
+		{
+			"ImportPath": "golang.org/x/net/html",
+			"Rev": "e0403b4e005737430c05a57aac078479844f919c"
+		},
+		{
+			"ImportPath": "golang.org/x/text/encoding",
+			"Rev": "c93e7c9fff19fb9139b5ab04ce041833add0134e"
+		},
+		{
+			"ImportPath": "golang.org/x/text/transform",
+			"Rev": "c93e7c9fff19fb9139b5ab04ce041833add0134e"
+		},
 		{
 			"ImportPath": "gopkg.in/check.v1",
 			"Rev": "64131543e7896d5bcc6bd5a76287eb75ea96c673"

Godeps/_workspace/src/github.com/huin/goupnp/goupnp.go

@@ -20,6 +20,8 @@ import (
 	"net/http"
 	"net/url"
 
+	"golang.org/x/net/html/charset"
+
 	"github.com/huin/goupnp/httpu"
 	"github.com/huin/goupnp/ssdp"
 )
@@ -104,6 +106,7 @@ func requestXml(url string, defaultSpace string, doc interface{}) error {
 
 	decoder := xml.NewDecoder(resp.Body)
 	decoder.DefaultSpace = defaultSpace
+	decoder.CharsetReader = charset.NewReaderLabel
 
 	return decoder.Decode(doc)
 }

Godeps/_workspace/src/golang.org/x/net/html/atom/atom.go

+// 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
+
+// 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)
+}

Godeps/_workspace/src/golang.org/x/net/html/atom/atom_test.go

+// 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
+
+import (
+	"sort"
+	"testing"
+)
+
+func TestKnown(t *testing.T) {
+	for _, s := range testAtomList {
+		if atom := Lookup([]byte(s)); atom.String() != s {
+			t.Errorf("Lookup(%q) = %#x (%q)", s, uint32(atom), atom.String())
+		}
+	}
+}
+
+func TestHits(t *testing.T) {
+	for _, a := range table {
+		if a == 0 {
+			continue
+		}
+		got := Lookup([]byte(a.String()))
+		if got != a {
+			t.Errorf("Lookup(%q) = %#x, want %#x", a.String(), uint32(got), uint32(a))
+		}
+	}
+}
+
+func TestMisses(t *testing.T) {
+	testCases := []string{
+		"",
+		"\x00",
+		"\xff",
+		"A",
+		"DIV",
+		"Div",
+		"dIV",
+		"aa",
+		"a\x00",
+		"ab",
+		"abb",
+		"abbr0",
+		"abbr ",
+		" abbr",
+		" a",
+		"acceptcharset",
+		"acceptCharset",
+		"accept_charset",
+		"h0",
+		"h1h2",
+		"h7",
+		"onClick",
+		"λ",
+		// The following string has the same hash (0xa1d7fab7) as "onmouseover".
+		"\x00\x00\x00\x00\x00\x50\x18\xae\x38\xd0\xb7",
+	}
+	for _, tc := range testCases {
+		got := Lookup([]byte(tc))
+		if got != 0 {
+			t.Errorf("Lookup(%q): got %d, want 0", tc, got)
+		}
+	}
+}
+
+func TestForeignObject(t *testing.T) {
+	const (
+		afo = Foreignobject
+		afO = ForeignObject
+		sfo = "foreignobject"
+		sfO = "foreignObject"
+	)
+	if got := Lookup([]byte(sfo)); got != afo {
+		t.Errorf("Lookup(%q): got %#v, want %#v", sfo, got, afo)
+	}
+	if got := Lookup([]byte(sfO)); got != afO {
+		t.Errorf("Lookup(%q): got %#v, want %#v", sfO, got, afO)
+	}
+	if got := afo.String(); got != sfo {
+		t.Errorf("Atom(%#v).String(): got %q, want %q", afo, got, sfo)
+	}
+	if got := afO.String(); got != sfO {
+		t.Errorf("Atom(%#v).String(): got %q, want %q", afO, got, sfO)
+	}
+}
+
+func BenchmarkLookup(b *testing.B) {
+	sortedTable := make([]string, 0, len(table))
+	for _, a := range table {
+		if a != 0 {
+			sortedTable = append(sortedTable, a.String())
+		}
+	}
+	sort.Strings(sortedTable)
+
+	x := make([][]byte, 1000)
+	for i := range x {
+		x[i] = []byte(sortedTable[i%len(sortedTable)])
+	}
+
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		for _, s := range x {
+			Lookup(s)
+		}
+	}
+}

Godeps/_workspace/src/golang.org/x/net/html/atom/table_test.go

+// generated by go run gen.go -test; DO NOT EDIT
+
+package atom
+
+var testAtomList = []string{
+	"a",
+	"abbr",
+	"abbr",
+	"accept",
+	"accept-charset",
+	"accesskey",
+	"action",
+	"address",
+	"align",
+	"alt",
+	"annotation",
+	"annotation-xml",
+	"applet",
+	"area",
+	"article",
+	"aside",
+	"async",
+	"audio",
+	"autocomplete",
+	"autofocus",
+	"autoplay",
+	"b",
+	"base",
+	"basefont",
+	"bdi",
+	"bdo",
+	"bgsound",
+	"big",
+	"blink",
+	"blockquote",
+	"body",
+	"br",
+	"button",
+	"canvas",
+	"caption",
+	"center",
+	"challenge",
+	"charset",
+	"checked",
+	"cite",
+	"cite",
+	"class",
+	"code",
+	"col",
+	"colgroup",
+	"color",
+	"cols",
+	"colspan",
+	"command",
+	"command",
+	"content",
+	"contenteditable",
+	"contextmenu",
+	"controls",
+	"coords",
+	"crossorigin",
+	"data",
+	"data",
+	"datalist",
+	"datetime",
+	"dd",
+	"default",
+	"defer",
+	"del",
+	"desc",
+	"details",
+	"dfn",
+	"dialog",
+	"dir",
+	"dirname",
+	"disabled",
+	"div",
+	"dl",
+	"download",
+	"draggable",
+	"dropzone",
+	"dt",
+	"em",
+	"embed",
+	"enctype",
+	"face",
+	"fieldset",
+	"figcaption",
+	"figure",
+	"font",
+	"footer",
+	"for",
+	"foreignObject",
+	"foreignobject",
+	"form",
+	"form",
+	"formaction",
+	"formenctype",
+	"formmethod",
+	"formnovalidate",
+	"formtarget",
+	"frame",
+	"frameset",
+	"h1",
+	"h2",
+	"h3",
+	"h4",
+	"h5",
+	"h6",
+	"head",
+	"header",
+	"headers",
+	"height",
+	"hgroup",
+	"hidden",
+	"high",
+	"hr",
+	"href",
+	"hreflang",
+	"html",
+	"http-equiv",
+	"i",
+	"icon",
+	"id",
+	"iframe",
+	"image",
+	"img",
+	"input",
+	"inputmode",
+	"ins",
+	"isindex",
+	"ismap",
+	"itemid",
+	"itemprop",
+	"itemref",
+	"itemscope",
+	"itemtype",
+	"kbd",
+	"keygen",
+	"keytype",
+	"kind",
+	"label",
+	"label",
+	"lang",
+	"legend",
+	"li",
+	"link",
+	"list",
+	"listing",
+	"loop",
+	"low",
+	"malignmark",
+	"manifest",
+	"map",
+	"mark",
+	"marquee",
+	"math",
+	"max",
+	"maxlength",
+	"media",
+	"mediagroup",
+	"menu",
+	"menuitem",
+	"meta",
+	"meter",
+	"method",
+	"mglyph",
+	"mi",
+	"min",
+	"minlength",
+	"mn",
+	"mo",
+	"ms",
+	"mtext",
+	"multiple",
+	"muted",
+	"name",
+	"nav",
+	"nobr",
+	"noembed",
+	"noframes",
+	"noscript",
+	"novalidate",
+	"object",
+	"ol",
+	"onabort",
+	"onafterprint",
+	"onautocomplete",
+	"onautocompleteerror",
+	"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",
+	"open",
+	"optgroup",
+	"optimum",
+	"option",
+	"output",
+	"p",
+	"param",
+	"pattern",
+	"ping",
+	"placeholder",
+	"plaintext",
+	"poster",
+	"pre",
+	"preload",
+	"progress",
+	"prompt",
+	"public",
+	"q",
+	"radiogroup",
+	"readonly",
+	"rel",
+	"required",
+	"reversed",
+	"rows",
+	"rowspan",
+	"rp",
+	"rt",
+	"ruby",
+	"s",
+	"samp",
+	"sandbox",
+	"scope",
+	"scoped",
+	"script",
+	"seamless",
+	"section",
+	"select",
+	"selected",
+	"shape",
+	"size",
+	"sizes",
+	"small",
+	"sortable",
+	"sorted",
+	"source",
+	"spacer",
+	"span",
+	"span",
+	"spellcheck",
+	"src",
+	"srcdoc",
+	"srclang",
+	"start",
+	"step",
+	"strike",
+	"strong",
+	"style",
+	"style",
+	"sub",
+	"summary",
+	"sup",
+	"svg",
+	"system",
+	"tabindex",
+	"table",
+	"target",
+	"tbody",
+	"td",
+	"template",
+	"textarea",
+	"tfoot",
+	"th",
+	"thead",
+	"time",
+	"title",
+	"title",
+	"tr",
+	"track",
+	"translate",
+	"tt",
+	"type",
+	"typemustmatch",
+	"u",
+	"ul",
+	"usemap",
+	"value",
+	"var",
+	"video",
+	"wbr",
+	"width",
+	"wrap",
+	"xmp",
+}

Godeps/_workspace/src/golang.org/x/net/html/charset/charset.go

+// 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 (
+	"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/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.
+func Lookup(label string) (e encoding.Encoding, name string) {
+	label = strings.ToLower(strings.Trim(label, "\t\n\r\f "))
+	enc := encodings[label]
+	return enc.e, enc.name
+}
+
+// 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"},
+}

Godeps/_workspace/src/golang.org/x/net/html/charset/charset_test.go

+// 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
+
+import (
+	"bytes"
+	"encoding/xml"
+	"io/ioutil"
+	"runtime"
+	"strings"
+	"testing"
+
+	"golang.org/x/text/transform"
+)
+
+func transformString(t transform.Transformer, s string) (string, error) {
+	r := transform.NewReader(strings.NewReader(s), t)
+	b, err := ioutil.ReadAll(r)
+	return string(b), err
+}
+
+var testCases = []struct {
+	utf8, other, otherEncoding string
+}{
+	{"Résumé", "Résumé", "utf8"},
+	{"Résumé", "R\xe9sum\xe9", "latin1"},
+	{"これは漢字です。", "S0\x8c0o0\"oW[g0Y0\x020", "UTF-16LE"},
+	{"これは漢字です。", "0S0\x8c0oo\"[W0g0Y0\x02", "UTF-16BE"},
+	{"Hello, world", "Hello, world", "ASCII"},
+	{"Gdańsk", "Gda\xf1sk", "ISO-8859-2"},
+	{"Ââ Čč Đđ Ŋŋ Õõ Šš Žž Åå Ää", "\xc2\xe2 \xc8\xe8 \xa9\xb9 \xaf\xbf \xd5\xf5 \xaa\xba \xac\xbc \xc5\xe5 \xc4\xe4", "ISO-8859-10"},
+	{"สำหรับ", "\xca\xd3\xcb\xc3\u047a", "ISO-8859-11"},
+	{"latviešu", "latvie\xf0u", "ISO-8859-13"},
+	{"Seònaid", "Se\xf2naid", "ISO-8859-14"},
+	{"€1 is cheap", "\xa41 is cheap", "ISO-8859-15"},
+	{"românește", "rom\xe2ne\xbate", "ISO-8859-16"},
+	{"nutraĵo", "nutra\xbco", "ISO-8859-3"},
+	{"Kalâdlit", "Kal\xe2dlit", "ISO-8859-4"},
+	{"русский", "\xe0\xe3\xe1\xe1\xda\xd8\xd9", "ISO-8859-5"},
+	{"ελληνικά", "\xe5\xeb\xeb\xe7\xed\xe9\xea\xdc", "ISO-8859-7"},
+	{"Kağan", "Ka\xf0an", "ISO-8859-9"},
+	{"Résumé", "R\x8esum\x8e", "macintosh"},
+	{"Gdańsk", "Gda\xf1sk", "windows-1250"},
+	{"русский", "\xf0\xf3\xf1\xf1\xea\xe8\xe9", "windows-1251"},
+	{"Résumé", "R\xe9sum\xe9", "windows-1252"},
+	{"ελληνικά", "\xe5\xeb\xeb\xe7\xed\xe9\xea\xdc", "windows-1253"},
+	{"Kağan", "Ka\xf0an", "windows-1254"},
+	{"עִבְרִית", "\xf2\xc4\xe1\xc0\xf8\xc4\xe9\xfa", "windows-1255"},
+	{"العربية", "\xc7\xe1\xda\xd1\xc8\xed\xc9", "windows-1256"},
+	{"latviešu", "latvie\xf0u", "windows-1257"},
+	{"Việt", "Vi\xea\xf2t", "windows-1258"},
+	{"สำหรับ", "\xca\xd3\xcb\xc3\u047a", "windows-874"},
+	{"русский", "\xd2\xd5\xd3\xd3\xcb\xc9\xca", "KOI8-R"},
+	{"українська", "\xd5\xcb\xd2\xc1\xa7\xce\xd3\xd8\xcb\xc1", "KOI8-U"},
+	{"Hello 常用國字標準字體表", "Hello \xb1`\xa5\u03b0\xea\xa6r\xbc\u0437\u01e6r\xc5\xe9\xaa\xed", "big5"},
+	{"Hello 常用國字標準字體表", "Hello \xb3\xa3\xd3\xc3\x87\xf8\xd7\xd6\x98\xcb\x9c\xca\xd7\xd6\xf3\x77\xb1\xed", "gbk"},
+	{"Hello 常用國字標準字體表", "Hello \xb3\xa3\xd3\xc3\x87\xf8\xd7\xd6\x98\xcb\x9c\xca\xd7\xd6\xf3\x77\xb1\xed", "gb18030"},
+	{"עִבְרִית", "\x81\x30\xfb\x30\x81\x30\xf6\x34\x81\x30\xf9\x33\x81\x30\xf6\x30\x81\x30\xfb\x36\x81\x30\xf6\x34\x81\x30\xfa\x31\x81\x30\xfb\x38", "gb18030"},
+	{"㧯", "\x82\x31\x89\x38", "gb18030"},
+	{"これは漢字です。", "\x82\xb1\x82\xea\x82\xcd\x8a\xbf\x8e\x9a\x82\xc5\x82\xb7\x81B", "SJIS"},
+	{"Hello, 世界!", "Hello, \x90\xa2\x8aE!", "SJIS"},
+	{"ｲｳｴｵｶ", "\xb2\xb3\xb4\xb5\xb6", "SJIS"},
+	{"これは漢字です。", "\xa4\xb3\xa4\xec\xa4\u03f4\xc1\xbb\xfa\xa4\u01e4\xb9\xa1\xa3", "EUC-JP"},
+	{"Hello, 世界!", "Hello, \x1b$B@$3&\x1b(B!", "ISO-2022-JP"},
+	{"네이트 | 즐거움의 시작, 슈파스(Spaβ) NATE", "\xb3\xd7\xc0\xcc\xc6\xae | \xc1\xf1\xb0\xc5\xbf\xf2\xc0\xc7 \xbd\xc3\xc0\xdb, \xbd\xb4\xc6\xc4\xbd\xba(Spa\xa5\xe2) NATE", "EUC-KR"},
+}
+
+func TestDecode(t *testing.T) {
+	for _, tc := range testCases {
+		e, _ := Lookup(tc.otherEncoding)
+		if e == nil {
+			t.Errorf("%s: not found", tc.otherEncoding)
+			continue
+		}
+		s, err := transformString(e.NewDecoder(), tc.other)
+		if err != nil {
+			t.Errorf("%s: decode %q: %v", tc.otherEncoding, tc.other, err)
+			continue
+		}
+		if s != tc.utf8 {
+			t.Errorf("%s: got %q, want %q", tc.otherEncoding, s, tc.utf8)
+		}
+	}
+}
+
+func TestEncode(t *testing.T) {
+	for _, tc := range testCases {
+		e, _ := Lookup(tc.otherEncoding)
+		if e == nil {
+			t.Errorf("%s: not found", tc.otherEncoding)
+			continue
+		}
+		s, err := transformString(e.NewEncoder(), tc.utf8)
+		if err != nil {
+			t.Errorf("%s: encode %q: %s", tc.otherEncoding, tc.utf8, err)
+			continue
+		}
+		if s != tc.other {
+			t.Errorf("%s: got %q, want %q", tc.otherEncoding, s, tc.other)
+		}
+	}
+}
+
+// TestNames verifies that you can pass an encoding's name to Lookup and get
+// the same encoding back (except for "replacement").
+func TestNames(t *testing.T) {
+	for _, e := range encodings {
+		if e.name == "replacement" {
+			continue
+		}
+		_, got := Lookup(e.name)
+		if got != e.name {
+			t.Errorf("got %q, want %q", got, e.name)
+			continue
+		}
+	}
+}
+
+var sniffTestCases = []struct {
+	filename, declared, want string
+}{
+	{"HTTP-charset.html", "text/html; charset=iso-8859-15", "iso-8859-15"},
+	{"UTF-16LE-BOM.html", "", "utf-16le"},
+	{"UTF-16BE-BOM.html", "", "utf-16be"},
+	{"meta-content-attribute.html", "text/html", "iso-8859-15"},
+	{"meta-charset-attribute.html", "text/html", "iso-8859-15"},
+	{"No-encoding-declaration.html", "text/html", "utf-8"},
+	{"HTTP-vs-UTF-8-BOM.html", "text/html; charset=iso-8859-15", "utf-8"},
+	{"HTTP-vs-meta-content.html", "text/html; charset=iso-8859-15", "iso-8859-15"},
+	{"HTTP-vs-meta-charset.html", "text/html; charset=iso-8859-15", "iso-8859-15"},
+	{"UTF-8-BOM-vs-meta-content.html", "text/html", "utf-8"},
+	{"UTF-8-BOM-vs-meta-charset.html", "text/html", "utf-8"},
+}
+
+func TestSniff(t *testing.T) {
+	switch runtime.GOOS {
+	case "nacl": // platforms that don't permit direct file system access
+		t.Skipf("not supported on %q", runtime.GOOS)
+	}
+
+	for _, tc := range sniffTestCases {
+		content, err := ioutil.ReadFile("testdata/" + tc.filename)
+		if err != nil {
+			t.Errorf("%s: error reading file: %v", tc.filename, err)
+			continue
+		}
+
+		_, name, _ := DetermineEncoding(content, tc.declared)
+		if name != tc.want {
+			t.Errorf("%s: got %q, want %q", tc.filename, name, tc.want)
+			continue
+		}
+	}
+}
+
+func TestReader(t *testing.T) {
+	switch runtime.GOOS {
+	case "nacl": // platforms that don't permit direct file system access
+		t.Skipf("not supported on %q", runtime.GOOS)
+	}
+
+	for _, tc := range sniffTestCases {
+		content, err := ioutil.ReadFile("testdata/" + tc.filename)
+		if err != nil {
+			t.Errorf("%s: error reading file: %v", tc.filename, err)
+			continue
+		}
+
+		r, err := NewReader(bytes.NewReader(content), tc.declared)
+		if err != nil {
+			t.Errorf("%s: error creating reader: %v", tc.filename, err)
+			continue
+		}
+
+		got, err := ioutil.ReadAll(r)
+		if err != nil {
+			t.Errorf("%s: error reading from charset.NewReader: %v", tc.filename, err)
+			continue
+		}
+
+		e, _ := Lookup(tc.want)
+		want, err := ioutil.ReadAll(transform.NewReader(bytes.NewReader(content), e.NewDecoder()))
+		if err != nil {
+			t.Errorf("%s: error decoding with hard-coded charset name: %v", tc.filename, err)
+			continue
+		}
+
+		if !bytes.Equal(got, want) {
+			t.Errorf("%s: got %q, want %q", tc.filename, got, want)
+			continue
+		}
+	}
+}
+
+var metaTestCases = []struct {
+	meta, want string
+}{
+	{"", ""},
+	{"text/html", ""},
+	{"text/html; charset utf-8", ""},
+	{"text/html; charset=latin-2", "latin-2"},
+	{"text/html; charset; charset = utf-8", "utf-8"},
+	{`charset="big5"`, "big5"},
+	{"charset='shift_jis'", "shift_jis"},
+}
+
+func TestFromMeta(t *testing.T) {
+	for _, tc := range metaTestCases {
+		got := fromMetaElement(tc.meta)
+		if got != tc.want {
+			t.Errorf("%q: got %q, want %q", tc.meta, got, tc.want)
+		}
+	}
+}
+
+func TestXML(t *testing.T) {
+	const s = "<?xml version=\"1.0\" encoding=\"windows-1252\"?><a><Word>r\xe9sum\xe9</Word></a>"
+
+	d := xml.NewDecoder(strings.NewReader(s))
+	d.CharsetReader = NewReaderLabel
+
+	var a struct {
+		Word string
+	}
+	err := d.Decode(&a)
+	if err != nil {
+		t.Fatalf("Decode: %v", err)
+	}
+
+	want := "résumé"
+	if a.Word != want {
+		t.Errorf("got %q, want %q", a.Word, want)
+	}
+}

Godeps/_workspace/src/golang.org/x/net/html/charset/gen.go

+// Copyright 2013 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+// +build ignore
+
+package main
+
+// Download https://encoding.spec.whatwg.org/encodings.json and use it to
+// generate table.go.
+
+import (
+	"encoding/json"
+	"fmt"
+	"log"
+	"net/http"
+	"strings"
+)
+
+type enc struct {
+	Name   string
+	Labels []string
+}
+
+type group struct {
+	Encodings []enc
+	Heading   string
+}
+
+const specURL = "https://encoding.spec.whatwg.org/encodings.json"
+
+func main() {
+	resp, err := http.Get(specURL)
+	if err != nil {
+		log.Fatalf("error fetching %s: %s", specURL, err)
+	}
+	if resp.StatusCode != 200 {
+		log.Fatalf("error fetching %s: HTTP status %s", specURL, resp.Status)
+	}
+	defer resp.Body.Close()
+
+	var groups []group
+	d := json.NewDecoder(resp.Body)
+	err = d.Decode(&groups)
+	if err != nil {
+		log.Fatalf("error reading encodings.json: %s", err)
+	}
+
+	fmt.Println("// generated by go run gen.go; DO NOT EDIT")
+	fmt.Println()
+	fmt.Println("package charset")
+	fmt.Println()
+
+	fmt.Println("import (")
+	fmt.Println(`"golang.org/x/text/encoding"`)
+	for _, pkg := range []string{"charmap", "japanese", "korean", "simplifiedchinese", "traditionalchinese", "unicode"} {
+		fmt.Printf("\"golang.org/x/text/encoding/%s\"\n", pkg)
+	}
+	fmt.Println(")")
+	fmt.Println()
+
+	fmt.Println("var encodings = map[string]struct{e encoding.Encoding; name string} {")
+	for _, g := range groups {
+		for _, e := range g.Encodings {
+			goName, ok := miscNames[e.Name]
+			if !ok {
+				for k, v := range prefixes {
+					if strings.HasPrefix(e.Name, k) {
+						goName = v + e.Name[len(k):]
+						break
+					}
+				}
+				if goName == "" {
+					log.Fatalf("unrecognized encoding name: %s", e.Name)
+				}
+			}
+
+			for _, label := range e.Labels {
+				fmt.Printf("%q: {%s, %q},\n", label, goName, e.Name)
+			}
+		}
+	}
+	fmt.Println("}")
+}
+
+var prefixes = map[string]string{
+	"iso-8859-": "charmap.ISO8859_",
+	"windows-":  "charmap.Windows",
+}
+
+var miscNames = map[string]string{
+	"utf-8":          "encoding.Nop",
+	"ibm866":         "charmap.CodePage866",
+	"iso-8859-8-i":   "charmap.ISO8859_8",
+	"koi8-r":         "charmap.KOI8R",
+	"koi8-u":         "charmap.KOI8U",
+	"macintosh":      "charmap.Macintosh",
+	"x-mac-cyrillic": "charmap.MacintoshCyrillic",
+	"gbk":            "simplifiedchinese.GBK",
+	"gb18030":        "simplifiedchinese.GB18030",
+	"hz-gb-2312":     "simplifiedchinese.HZGB2312",
+	"big5":           "traditionalchinese.Big5",
+	"euc-jp":         "japanese.EUCJP",
+	"iso-2022-jp":    "japanese.ISO2022JP",
+	"shift_jis":      "japanese.ShiftJIS",
+	"euc-kr":         "korean.EUCKR",
+	"replacement":    "encoding.Replacement",
+	"utf-16be":       "unicode.UTF16(unicode.BigEndian, unicode.IgnoreBOM)",
+	"utf-16le":       "unicode.UTF16(unicode.LittleEndian, unicode.IgnoreBOM)",
+	"x-user-defined": "charmap.XUserDefined",
+}

Godeps/_workspace/src/golang.org/x/net/html/charset/testdata/HTTP-charset.html

+<!DOCTYPE html>
+<html  lang="en" >
+<head>
+  <title>HTTP charset</title>
+<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
+<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
+<link rel="stylesheet" type="text/css" href="./generatedtests.css">
+<script src="http://w3c-test.org/resources/testharness.js"></script>
+<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
+<meta name='flags' content='http'>
+<meta name="assert" content="The character encoding of a page can be set using the HTTP header charset declaration.">
+<style type='text/css'>
+.test div { width: 50px; }</style>
+<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-15.css">
+</head>
+<body>
+<p class='title'>HTTP charset</p>
+
+
+<div id='log'></div>
+
+
+<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
+
+
+
+
+
+<div class='description'>
+<p class="assertion" title="Assertion">The character encoding of a page can be set using the HTTP header charset declaration.</p>
+<div class="notes"><p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00C3;&#x0153;&#x00C3;&#x20AC;&#x00C3;&#x0161;</code>. This matches the sequence of bytes above when they are interpreted as ISO 8859-15. If the class name matches the selector then the test will pass.</p><p>The only character encoding declaration for this HTML file is in the HTTP header, which sets the encoding to ISO 8859-15.</p></p>
+</div>
+</div>
+<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-003">Next test</a></div><div class="doctype">HTML5</div>
+<p class="jump">the-input-byte-stream-001<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#basics" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-001" target="_blank">Detailed results for this test</a><br/>	<a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
+<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
+				<li>The test is read from a server that supports HTTP.</li></ul></div>
+</div>
+<script>
+test(function() {
+assert_equals(document.getElementById('box').offsetWidth, 100);
+}, " ");
+</script>
+
+</body>
+</html>
+
+

Godeps/_workspace/src/golang.org/x/net/html/charset/testdata/HTTP-vs-UTF-8-BOM.html

+<!DOCTYPE html>
+<html  lang="en" >
+<head>
+  <title>HTTP vs UTF-8 BOM</title>
+<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
+<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
+<link rel="stylesheet" type="text/css" href="./generatedtests.css">
+<script src="http://w3c-test.org/resources/testharness.js"></script>
+<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
+<meta name='flags' content='http'>
+<meta name="assert" content="A character encoding set in the HTTP header has lower precedence than the UTF-8 signature.">
+<style type='text/css'>
+.test div { width: 50px; }</style>
+<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-utf8.css">
+</head>
+<body>
+<p class='title'>HTTP vs UTF-8 BOM</p>
+
+
+<div id='log'></div>
+
+
+<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
+
+
+
+
+
+<div class='description'>
+<p class="assertion" title="Assertion">A character encoding set in the HTTP header has lower precedence than the UTF-8 signature.</p>
+<div class="notes"><p><p>The HTTP header attempts to set the character encoding to ISO 8859-15. The page starts with a UTF-8 signature.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00FD;&#x00E4;&#x00E8;</code>. This matches the sequence of bytes above when they are interpreted as UTF-8. If the class name matches the selector then the test will pass.</p><p>If the test is unsuccessful, the characters &#x00EF;&#x00BB;&#x00BF; should appear at the top of the page.  These represent the bytes that make up the UTF-8 signature when encountered in the ISO 8859-15 encoding.</p></p>
+</div>
+</div>
+<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-022">Next test</a></div><div class="doctype">HTML5</div>
+<p class="jump">the-input-byte-stream-034<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#precedence" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-034" target="_blank">Detailed results for this test</a><br/>	<a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
+<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
+				<li>The test is read from a server that supports HTTP.</li></ul></div>
+</div>
+<script>
+test(function() {
+assert_equals(document.getElementById('box').offsetWidth, 100);
+}, " ");
+</script>
+
+</body>
+</html>
+
+

Godeps/_workspace/src/golang.org/x/net/html/charset/testdata/HTTP-vs-meta-charset.html

+<!DOCTYPE html>
+<html  lang="en" >
+<head>
+ <meta charset="iso-8859-1" > <title>HTTP vs meta charset</title>
+<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
+<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
+<link rel="stylesheet" type="text/css" href="./generatedtests.css">
+<script src="http://w3c-test.org/resources/testharness.js"></script>
+<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
+<meta name='flags' content='http'>
+<meta name="assert" content="The HTTP header has a higher precedence than an encoding declaration in a meta charset attribute.">
+<style type='text/css'>
+.test div { width: 50px; }.test div { width: 90px; }
+</style>
+<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-15.css">
+</head>
+<body>
+<p class='title'>HTTP vs meta charset</p>
+
+
+<div id='log'></div>
+
+
+<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
+
+
+
+
+
+<div class='description'>
+<p class="assertion" title="Assertion">The HTTP header has a higher precedence than an encoding declaration in a meta charset attribute.</p>
+<div class="notes"><p><p>The HTTP header attempts to set the character encoding to ISO 8859-15. The page contains an encoding declaration in a meta charset attribute that attempts to set the character encoding to ISO 8859-1.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00C3;&#x0153;&#x00C3;&#x20AC;&#x00C3;&#x0161;</code>. This matches the sequence of bytes above when they are interpreted as ISO 8859-15. If the class name matches the selector then the test will pass.</p></p>
+</div>
+</div>
+<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-037">Next test</a></div><div class="doctype">HTML5</div>
+<p class="jump">the-input-byte-stream-018<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#precedence" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-018" target="_blank">Detailed results for this test</a><br/>	<a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
+<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
+				<li>The test is read from a server that supports HTTP.</li></ul></div>
+</div>
+<script>
+test(function() {
+assert_equals(document.getElementById('box').offsetWidth, 100);
+}, " ");
+</script>
+
+</body>
+</html>
+
+

Godeps/_workspace/src/golang.org/x/net/html/charset/testdata/HTTP-vs-meta-content.html

+<!DOCTYPE html>
+<html  lang="en" >
+<head>
+ <meta http-equiv="content-type" content="text/html;charset=iso-8859-1" > <title>HTTP vs meta content</title>
+<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
+<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
+<link rel="stylesheet" type="text/css" href="./generatedtests.css">
+<script src="http://w3c-test.org/resources/testharness.js"></script>
+<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
+<meta name='flags' content='http'>
+<meta name="assert" content="The HTTP header has a higher precedence than an encoding declaration in a meta content attribute.">
+<style type='text/css'>
+.test div { width: 50px; }.test div { width: 90px; }
+</style>
+<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-15.css">
+</head>
+<body>
+<p class='title'>HTTP vs meta content</p>
+
+
+<div id='log'></div>
+
+
+<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
+
+
+
+
+
+<div class='description'>
+<p class="assertion" title="Assertion">The HTTP header has a higher precedence than an encoding declaration in a meta content attribute.</p>
+<div class="notes"><p><p>The HTTP header attempts to set the character encoding to ISO 8859-15. The page contains an encoding declaration in a meta content attribute that attempts to set the character encoding to ISO 8859-1.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00C3;&#x0153;&#x00C3;&#x20AC;&#x00C3;&#x0161;</code>. This matches the sequence of bytes above when they are interpreted as ISO 8859-15. If the class name matches the selector then the test will pass.</p></p>
+</div>
+</div>
+<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-018">Next test</a></div><div class="doctype">HTML5</div>
+<p class="jump">the-input-byte-stream-016<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#precedence" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-016" target="_blank">Detailed results for this test</a><br/>	<a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
+<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
+				<li>The test is read from a server that supports HTTP.</li></ul></div>
+</div>
+<script>
+test(function() {
+assert_equals(document.getElementById('box').offsetWidth, 100);
+}, " ");
+</script>
+
+</body>
+</html>
+
+

Godeps/_workspace/src/golang.org/x/net/html/charset/testdata/No-encoding-declaration.html

+<!DOCTYPE html>
+<html  lang="en" >
+<head>
+  <title>No encoding declaration</title>
+<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
+<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
+<link rel="stylesheet" type="text/css" href="./generatedtests.css">
+<script src="http://w3c-test.org/resources/testharness.js"></script>
+<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
+<meta name='flags' content='http'>
+<meta name="assert" content="A page with no encoding information in HTTP, BOM, XML declaration or meta element will be treated as UTF-8.">
+<style type='text/css'>
+.test div { width: 50px; }</style>
+<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-utf8.css">
+</head>
+<body>
+<p class='title'>No encoding declaration</p>
+
+
+<div id='log'></div>
+
+
+<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
+
+
+
+
+
+<div class='description'>
+<p class="assertion" title="Assertion">A page with no encoding information in HTTP, BOM, XML declaration or meta element will be treated as UTF-8.</p>
+<div class="notes"><p><p>The test on this page contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00FD;&#x00E4;&#x00E8;</code>. This matches the sequence of bytes above when they are interpreted as UTF-8. If the class name matches the selector then the test will pass.</p></p>
+</div>
+</div>
+<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-034">Next test</a></div><div class="doctype">HTML5</div>
+<p class="jump">the-input-byte-stream-015<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#basics" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-015" target="_blank">Detailed results for this test</a><br/>	<a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
+<div class='prereq'>Assumptions: <ul><li>The test is read from a server that supports HTTP.</li></ul></div>
+</div>
+<script>
+test(function() {
+assert_equals(document.getElementById('box').offsetWidth, 100);
+}, " ");
+</script>
+
+</body>
+</html>
+
+

Godeps/_workspace/src/golang.org/x/net/html/charset/testdata/README

+These test cases come from
+http://www.w3.org/International/tests/repository/html5/the-input-byte-stream/results-basics
+
+Distributed under both the W3C Test Suite License
+(http://www.w3.org/Consortium/Legal/2008/04-testsuite-license)
+and the W3C 3-clause BSD License
+(http://www.w3.org/Consortium/Legal/2008/03-bsd-license).
+To contribute to a W3C Test Suite, see the policies and contribution
+forms (http://www.w3.org/2004/10/27-testcases).

Godeps/_workspace/src/golang.org/x/net/html/charset/testdata/UTF-16BE-BOM.html

 <!DOCTYPE html>

Godeps/_workspace/src/golang.org/x/net/html/charset/testdata/UTF-16LE-BOM.html

 <!DOCTYPE html>

Godeps/_workspace/src/golang.org/x/net/html/charset/testdata/UTF-8-BOM-vs-meta-charset.html

+<!DOCTYPE html>
+<html  lang="en" >
+<head>
+ <meta charset="iso-8859-15"> <title>UTF-8 BOM vs meta charset</title>
+<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
+<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
+<link rel="stylesheet" type="text/css" href="./generatedtests.css">
+<script src="http://w3c-test.org/resources/testharness.js"></script>
+<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
+<meta name='flags' content='http'>
+<meta name="assert" content="A page with a UTF-8 BOM will be recognized as UTF-8 even if the meta charset attribute declares a different encoding.">
+<style type='text/css'>
+.test div { width: 50px; }.test div { width: 90px; }
+</style>
+<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-utf8.css">
+</head>
+<body>
+<p class='title'>UTF-8 BOM vs meta charset</p>
+
+
+<div id='log'></div>
+
+
+<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
+
+
+
+
+
+<div class='description'>
+<p class="assertion" title="Assertion">A page with a UTF-8 BOM will be recognized as UTF-8 even if the meta charset attribute declares a different encoding.</p>
+<div class="notes"><p><p>The page contains an encoding declaration in a meta charset attribute that attempts to set the character encoding to ISO 8859-15, but the file starts with a UTF-8 signature.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00FD;&#x00E4;&#x00E8;</code>. This matches the sequence of bytes above when they are interpreted as UTF-8. If the class name matches the selector then the test will pass.</p></p>
+</div>
+</div>
+<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-024">Next test</a></div><div class="doctype">HTML5</div>
+<p class="jump">the-input-byte-stream-038<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#precedence" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-038" target="_blank">Detailed results for this test</a><br/>	<a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
+<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
+				<li>The test is read from a server that supports HTTP.</li></ul></div>
+</div>
+<script>
+test(function() {
+assert_equals(document.getElementById('box').offsetWidth, 100);
+}, " ");
+</script>
+
+</body>
+</html>
+
+

Godeps/_workspace/src/golang.org/x/net/html/charset/testdata/UTF-8-BOM-vs-meta-content.html

+<!DOCTYPE html>
+<html  lang="en" >
+<head>
+ <meta http-equiv="content-type" content="text/html; charset=iso-8859-15"> <title>UTF-8 BOM vs meta content</title>
+<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
+<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
+<link rel="stylesheet" type="text/css" href="./generatedtests.css">
+<script src="http://w3c-test.org/resources/testharness.js"></script>
+<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
+<meta name='flags' content='http'>
+<meta name="assert" content="A page with a UTF-8 BOM will be recognized as UTF-8 even if the meta content attribute declares a different encoding.">
+<style type='text/css'>
+.test div { width: 50px; }</style>
+<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-utf8.css">
+</head>
+<body>
+<p class='title'>UTF-8 BOM vs meta content</p>
+
+
+<div id='log'></div>
+
+
+<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
+
+
+
+
+
+<div class='description'>
+<p class="assertion" title="Assertion">A page with a UTF-8 BOM will be recognized as UTF-8 even if the meta content attribute declares a different encoding.</p>
+<div class="notes"><p><p>The page contains an encoding declaration in a meta content attribute that attempts to set the character encoding to ISO 8859-15, but the file starts with a UTF-8 signature.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00FD;&#x00E4;&#x00E8;</code>. This matches the sequence of bytes above when they are interpreted as UTF-8. If the class name matches the selector then the test will pass.</p></p>
+</div>
+</div>
+<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-038">Next test</a></div><div class="doctype">HTML5</div>
+<p class="jump">the-input-byte-stream-037<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#precedence" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-037" target="_blank">Detailed results for this test</a><br/>	<a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
+<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
+				<li>The test is read from a server that supports HTTP.</li></ul></div>
+</div>
+<script>
+test(function() {
+assert_equals(document.getElementById('box').offsetWidth, 100);
+}, " ");
+</script>
+
+</body>
+</html>
+
+

Godeps/_workspace/src/golang.org/x/net/html/charset/testdata/meta-charset-attribute.html

+<!DOCTYPE html>
+<html  lang="en" >
+<head>
+ <meta charset="iso-8859-15"> <title>meta charset attribute</title>
+<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
+<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
+<link rel="stylesheet" type="text/css" href="./generatedtests.css">
+<script src="http://w3c-test.org/resources/testharness.js"></script>
+<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
+<meta name='flags' content='http'>
+<meta name="assert" content="The character encoding of the page can be set by a meta element with charset attribute.">
+<style type='text/css'>
+.test div { width: 50px; }</style>
+<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-15.css">
+</head>
+<body>
+<p class='title'>meta charset attribute</p>
+
+
+<div id='log'></div>
+
+
+<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
+
+
+
+
+
+<div class='description'>
+<p class="assertion" title="Assertion">The character encoding of the page can be set by a meta element with charset attribute.</p>
+<div class="notes"><p><p>The only character encoding declaration for this HTML file is in the charset attribute of the meta element, which declares the encoding to be ISO 8859-15.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00C3;&#x0153;&#x00C3;&#x20AC;&#x00C3;&#x0161;</code>. This matches the sequence of bytes above when they are interpreted as ISO 8859-15. If the class name matches the selector then the test will pass.</p></p>
+</div>
+</div>
+<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-015">Next test</a></div><div class="doctype">HTML5</div>
+<p class="jump">the-input-byte-stream-009<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#basics" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-009" target="_blank">Detailed results for this test</a><br/>	<a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
+<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
+				<li>The test is read from a server that supports HTTP.</li></ul></div>
+</div>
+<script>
+test(function() {
+assert_equals(document.getElementById('box').offsetWidth, 100);
+}, " ");
+</script>
+
+</body>
+</html>
+
+

Godeps/_workspace/src/golang.org/x/net/html/charset/testdata/meta-content-attribute.html

+<!DOCTYPE html>
+<html  lang="en" >
+<head>
+ <meta http-equiv="content-type" content="text/html; charset=iso-8859-15"> <title>meta content attribute</title>
+<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
+<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
+<link rel="stylesheet" type="text/css" href="./generatedtests.css">
+<script src="http://w3c-test.org/resources/testharness.js"></script>
+<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
+<meta name='flags' content='http'>
+<meta name="assert" content="The character encoding of the page can be set by a meta element with http-equiv and content attributes.">
+<style type='text/css'>
+.test div { width: 50px; }</style>
+<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-15.css">
+</head>
+<body>
+<p class='title'>meta content attribute</p>
+
+
+<div id='log'></div>
+
+
+<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
+
+
+
+
+
+<div class='description'>
+<p class="assertion" title="Assertion">The character encoding of the page can be set by a meta element with http-equiv and content attributes.</p>
+<div class="notes"><p><p>The only character encoding declaration for this HTML file is in the content attribute of the meta element, which declares the encoding to be ISO 8859-15.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00C3;&#x0153;&#x00C3;&#x20AC;&#x00C3;&#x0161;</code>. This matches the sequence of bytes above when they are interpreted as ISO 8859-15. If the class name matches the selector then the test will pass.</p></p>
+</div>
+</div>
+<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-009">Next test</a></div><div class="doctype">HTML5</div>
+<p class="jump">the-input-byte-stream-007<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#basics" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-007" target="_blank">Detailed results for this test</a><br/>	<a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
+<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
+				<li>The test is read from a server that supports HTTP.</li></ul></div>
+</div>
+<script>
+test(function() {
+assert_equals(document.getElementById('box').offsetWidth, 100);
+}, " ");
+</script>
+
+</body>
+</html>
+
+

Godeps/_workspace/src/golang.org/x/net/html/const.go

+// 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
+}

Godeps/_workspace/src/golang.org/x/net/html/doc.go

+// 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
+
+// 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?

Godeps/_workspace/src/golang.org/x/net/html/doctype.go

+// 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//",
+}

Godeps/_workspace/src/golang.org/x/net/html/entity_test.go

+// 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 (
+	"testing"
+	"unicode/utf8"
+)
+
+func TestEntityLength(t *testing.T) {
+	// We verify that the length of UTF-8 encoding of each value is <= 1 + len(key).
+	// The +1 comes from the leading "&". This property implies that the length of
+	// unescaped text is <= the length of escaped text.
+	for k, v := range entity {
+		if 1+len(k) < utf8.RuneLen(v) {
+			t.Error("escaped entity &" + k + " is shorter than its UTF-8 encoding " + string(v))
+		}
+		if len(k) > longestEntityWithoutSemicolon && k[len(k)-1] != ';' {
+			t.Errorf("entity name %s is %d characters, but longestEntityWithoutSemicolon=%d", k, len(k), longestEntityWithoutSemicolon)
+		}
+	}
+	for k, v := range entity2 {
+		if 1+len(k) < utf8.RuneLen(v[0])+utf8.RuneLen(v[1]) {
+			t.Error("escaped entity &" + k + " is shorter than its UTF-8 encoding " + string(v[0]) + string(v[1]))
+		}
+	}
+}

Godeps/_workspace/src/golang.org/x/net/html/escape.go

+// 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&lt;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 = "&amp;"
+		case '\'':
+			// "&#39;" is shorter than "&apos;" and apos was not in HTML until HTML5.
+			esc = "&#39;"
+		case '<':
+			esc = "&lt;"
+		case '>':
+			esc = "&gt;"
+		case '"':
+			// "&#34;" is shorter than "&quot;".
+			esc = "&#34;"
+		case '\r':
+			esc = "&#13;"
+		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 "&lt;". 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 "&lt;" to become "<". It unescapes a
+// larger range of entities than EscapeString escapes. For example, "&aacute;"
+// unescapes to "á", as does "&#225;" 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
+}

Godeps/_workspace/src/golang.org/x/net/html/escape_test.go

+// 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 html
+
+import "testing"
+
+type unescapeTest struct {
+	// A short description of the test case.
+	desc string
+	// The HTML text.
+	html string
+	// The unescaped text.
+	unescaped string
+}
+
+var unescapeTests = []unescapeTest{
+	// Handle no entities.
+	{
+		"copy",
+		"A\ttext\nstring",
+		"A\ttext\nstring",
+	},
+	// Handle simple named entities.
+	{
+		"simple",
+		"& > <",
+		"& > <",
+	},
+	// Handle hitting the end of the string.
+	{
+		"stringEnd",
+		"&amp &amp",
+		"& &",
+	},
+	// Handle entities with two codepoints.
+	{
+		"multiCodepoint",
+		"text &gesl; blah",
+		"text \u22db\ufe00 blah",
+	},
+	// Handle decimal numeric entities.
+	{
+		"decimalEntity",
+		"Delta = &#916; ",
+		"Delta = Δ ",
+	},
+	// Handle hexadecimal numeric entities.
+	{
+		"hexadecimalEntity",
+		"Lambda = &#x3bb; = &#X3Bb ",
+		"Lambda = λ = λ ",
+	},
+	// Handle numeric early termination.
+	{
+		"numericEnds",
+		"&# &#x &#128;43 &copy = &#169f = &#xa9",
+		"&# &#x €43 © = ©f = ©",
+	},
+	// Handle numeric ISO-8859-1 entity replacements.
+	{
+		"numericReplacements",
+		"Footnote&#x87;",
+		"Footnote‡",
+	},
+}
+
+func TestUnescape(t *testing.T) {
+	for _, tt := range unescapeTests {
+		unescaped := UnescapeString(tt.html)
+		if unescaped != tt.unescaped {
+			t.Errorf("TestUnescape %s: want %q, got %q", tt.desc, tt.unescaped, unescaped)
+		}
+	}
+}
+
+func TestUnescapeEscape(t *testing.T) {
+	ss := []string{
+		``,
+		`abc def`,
+		`a & b`,
+		`a&amp;b`,
+		`a &amp b`,
+		`&quot;`,
+		`"`,
+		`"<&>"`,
+		`&quot;&lt;&amp;&gt;&quot;`,
+		`3&5==1 && 0<1, "0&lt;1", a+acute=&aacute;`,
+		`The special characters are: <, >, &, ' and "`,
+	}
+	for _, s := range ss {
+		if got := UnescapeString(EscapeString(s)); got != s {
+			t.Errorf("got %q want %q", got, s)
+		}
+	}
+}

Godeps/_workspace/src/golang.org/x/net/html/example_test.go

+// 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.
+
+// This example demonstrates parsing HTML data and walking the resulting tree.
+package html_test
+
+import (
+	"fmt"
+	"log"
+	"strings"
+
+	"golang.org/x/net/html"
+)
+
+func ExampleParse() {
+	s := `<p>Links:</p><ul><li><a href="foo">Foo</a><li><a href="/bar/baz">BarBaz</a></ul>`
+	doc, err := html.Parse(strings.NewReader(s))
+	if err != nil {
+		log.Fatal(err)
+	}
+	var f func(*html.Node)
+	f = func(n *html.Node) {
+		if n.Type == html.ElementNode && n.Data == "a" {
+			for _, a := range n.Attr {
+				if a.Key == "href" {
+					fmt.Println(a.Val)
+					break
+				}
+			}
+		}
+		for c := n.FirstChild; c != nil; c = c.NextSibling {
+			f(c)
+		}
+	}
+	f(doc)
+	// Output:
+	// foo
+	// /bar/baz
+}

Godeps/_workspace/src/golang.org/x/net/html/foreign.go

+// 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",
+}

Godeps/_workspace/src/golang.org/x/net/html/node.go

+// 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&lt;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]
+}

Godeps/_workspace/src/golang.org/x/net/html/node_test.go

+// 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 (
+	"fmt"
+)
+
+// checkTreeConsistency checks that a node and its descendants are all
+// consistent in their parent/child/sibling relationships.
+func checkTreeConsistency(n *Node) error {
+	return checkTreeConsistency1(n, 0)
+}
+
+func checkTreeConsistency1(n *Node, depth int) error {
+	if depth == 1e4 {
+		return fmt.Errorf("html: tree looks like it contains a cycle")
+	}
+	if err := checkNodeConsistency(n); err != nil {
+		return err
+	}
+	for c := n.FirstChild; c != nil; c = c.NextSibling {
+		if err := checkTreeConsistency1(c, depth+1); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// checkNodeConsistency checks that a node's parent/child/sibling relationships
+// are consistent.
+func checkNodeConsistency(n *Node) error {
+	if n == nil {
+		return nil
+	}
+
+	nParent := 0
+	for p := n.Parent; p != nil; p = p.Parent {
+		nParent++
+		if nParent == 1e4 {
+			return fmt.Errorf("html: parent list looks like an infinite loop")
+		}
+	}
+
+	nForward := 0
+	for c := n.FirstChild; c != nil; c = c.NextSibling {
+		nForward++
+		if nForward == 1e6 {
+			return fmt.Errorf("html: forward list of children looks like an infinite loop")
+		}
+		if c.Parent != n {
+			return fmt.Errorf("html: inconsistent child/parent relationship")
+		}
+	}
+
+	nBackward := 0
+	for c := n.LastChild; c != nil; c = c.PrevSibling {
+		nBackward++
+		if nBackward == 1e6 {
+			return fmt.Errorf("html: backward list of children looks like an infinite loop")
+		}
+		if c.Parent != n {
+			return fmt.Errorf("html: inconsistent child/parent relationship")
+		}
+	}
+
+	if n.Parent != nil {
+		if n.Parent == n {
+			return fmt.Errorf("html: inconsistent parent relationship")
+		}
+		if n.Parent == n.FirstChild {
+			return fmt.Errorf("html: inconsistent parent/first relationship")
+		}
+		if n.Parent == n.LastChild {
+			return fmt.Errorf("html: inconsistent parent/last relationship")
+		}
+		if n.Parent == n.PrevSibling {
+			return fmt.Errorf("html: inconsistent parent/prev relationship")
+		}
+		if n.Parent == n.NextSibling {
+			return fmt.Errorf("html: inconsistent parent/next relationship")
+		}
+
+		parentHasNAsAChild := false
+		for c := n.Parent.FirstChild; c != nil; c = c.NextSibling {
+			if c == n {
+				parentHasNAsAChild = true
+				break
+			}
+		}
+		if !parentHasNAsAChild {
+			return fmt.Errorf("html: inconsistent parent/child relationship")
+		}
+	}
+
+	if n.PrevSibling != nil && n.PrevSibling.NextSibling != n {
+		return fmt.Errorf("html: inconsistent prev/next relationship")
+	}
+	if n.NextSibling != nil && n.NextSibling.PrevSibling != n {
+		return fmt.Errorf("html: inconsistent next/prev relationship")
+	}
+
+	if (n.FirstChild == nil) != (n.LastChild == nil) {
+		return fmt.Errorf("html: inconsistent first/last relationship")
+	}
+	if n.FirstChild != nil && n.FirstChild == n.LastChild {
+		// We have a sole child.
+		if n.FirstChild.PrevSibling != nil || n.FirstChild.NextSibling != nil {
+			return fmt.Errorf("html: inconsistent sole child's sibling relationship")
+		}
+	}
+
+	seen := map[*Node]bool{}
+
+	var last *Node
+	for c := n.FirstChild; c != nil; c = c.NextSibling {
+		if seen[c] {
+			return fmt.Errorf("html: inconsistent repeated child")
+		}
+		seen[c] = true
+		last = c
+	}
+	if last != n.LastChild {
+		return fmt.Errorf("html: inconsistent last relationship")
+	}
+
+	var first *Node
+	for c := n.LastChild; c != nil; c = c.PrevSibling {
+		if !seen[c] {
+			return fmt.Errorf("html: inconsistent missing child")
+		}
+		delete(seen, c)
+		first = c
+	}
+	if first != n.FirstChild {
+		return fmt.Errorf("html: inconsistent first relationship")
+	}
+
+	if len(seen) != 0 {
+		return fmt.Errorf("html: inconsistent forwards/backwards child list")
+	}
+
+	return nil
+}

Godeps/_workspace/src/golang.org/x/net/html/testdata/webkit/README

+The *.dat files in this directory are copied from The WebKit Open Source
+Project, specifically $WEBKITROOT/LayoutTests/html5lib/resources.
+WebKit is licensed under a BSD style license.
+http://webkit.org/coding/bsd-license.html says:
+
+Copyright (C) 2009 Apple Inc. All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice,
+this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+this list of conditions and the following disclaimer in the documentation
+and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY APPLE INC. AND ITS CONTRIBUTORS "AS IS" AND ANY
+EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR ITS CONTRIBUTORS BE LIABLE FOR ANY
+DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+

Godeps/_workspace/src/golang.org/x/net/html/testdata/webkit/scripted/adoption01.dat

+#data
+<p><b id="A"><script>document.getElementById("A").id = "B"</script></p>TEXT</b>
+#errors
+#document
+| <html>
+|   <head>
+|   <body>
+|     <p>
+|       <b>
+|         id="B"
+|         <script>
+|           "document.getElementById("A").id = "B""
+|     <b>
+|       id="A"
+|       "TEXT"