ires 0.1.3 → 0.1.4

data/ext/vendor/golang.org/x/net/html/entity_test.go

@@ -0,0 +1,29 @@
+// 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]))
+		}
+	}
+}

data/ext/vendor/golang.org/x/net/html/escape.go

@@ -0,0 +1,258 @@
+// Copyright 2010 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package html
+
+import (
+	"bytes"
+	"strings"
+	"unicode/utf8"
+)
+
+// These replacements permit compatibility with old numeric entities that
+// assumed Windows-1252 encoding.
+// https://html.spec.whatwg.org/multipage/syntax.html#consume-a-character-reference
+var replacementTable = [...]rune{
+	'\u20AC', // First entry is what 0x80 should be replaced with.
+	'\u0081',
+	'\u201A',
+	'\u0192',
+	'\u201E',
+	'\u2026',
+	'\u2020',
+	'\u2021',
+	'\u02C6',
+	'\u2030',
+	'\u0160',
+	'\u2039',
+	'\u0152',
+	'\u008D',
+	'\u017D',
+	'\u008F',
+	'\u0090',
+	'\u2018',
+	'\u2019',
+	'\u201C',
+	'\u201D',
+	'\u2022',
+	'\u2013',
+	'\u2014',
+	'\u02DC',
+	'\u2122',
+	'\u0161',
+	'\u203A',
+	'\u0153',
+	'\u009D',
+	'\u017E',
+	'\u0178', // Last entry is 0x9F.
+	// 0x00->'\uFFFD' is handled programmatically.
+	// 0x0D->'\u000D' is a no-op.
+}
+
+// unescapeEntity reads an entity like "<" from b[src:] and writes the
+// corresponding "<" to b[dst:], returning the incremented dst and src cursors.
+// Precondition: b[src] == '&' && dst <= src.
+// attribute should be true if parsing an attribute value.
+func unescapeEntity(b []byte, dst, src int, attribute bool) (dst1, src1 int) {
+	// https://html.spec.whatwg.org/multipage/syntax.html#consume-a-character-reference
+
+	// i starts at 1 because we already know that s[0] == '&'.
+	i, s := 1, b[src:]
+
+	if len(s) <= 1 {
+		b[dst] = b[src]
+		return dst + 1, src + 1
+	}
+
+	if s[i] == '#' {
+		if len(s) <= 3 { // We need to have at least "&#.".
+			b[dst] = b[src]
+			return dst + 1, src + 1
+		}
+		i++
+		c := s[i]
+		hex := false
+		if c == 'x' || c == 'X' {
+			hex = true
+			i++
+		}
+
+		x := '\x00'
+		for i < len(s) {
+			c = s[i]
+			i++
+			if hex {
+				if '0' <= c && c <= '9' {
+					x = 16*x + rune(c) - '0'
+					continue
+				} else if 'a' <= c && c <= 'f' {
+					x = 16*x + rune(c) - 'a' + 10
+					continue
+				} else if 'A' <= c && c <= 'F' {
+					x = 16*x + rune(c) - 'A' + 10
+					continue
+				}
+			} else if '0' <= c && c <= '9' {
+				x = 10*x + rune(c) - '0'
+				continue
+			}
+			if c != ';' {
+				i--
+			}
+			break
+		}
+
+		if i <= 3 { // No characters matched.
+			b[dst] = b[src]
+			return dst + 1, src + 1
+		}
+
+		if 0x80 <= x && x <= 0x9F {
+			// Replace characters from Windows-1252 with UTF-8 equivalents.
+			x = replacementTable[x-0x80]
+		} else if x == 0 || (0xD800 <= x && x <= 0xDFFF) || x > 0x10FFFF {
+			// Replace invalid characters with the replacement character.
+			x = '\uFFFD'
+		}
+
+		return dst + utf8.EncodeRune(b[dst:], x), src + i
+	}
+
+	// Consume the maximum number of characters possible, with the
+	// consumed characters matching one of the named references.
+
+	for i < len(s) {
+		c := s[i]
+		i++
+		// Lower-cased characters are more common in entities, so we check for them first.
+		if 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' || '0' <= c && c <= '9' {
+			continue
+		}
+		if c != ';' {
+			i--
+		}
+		break
+	}
+
+	entityName := string(s[1:i])
+	if entityName == "" {
+		// No-op.
+	} else if attribute && entityName[len(entityName)-1] != ';' && len(s) > i && s[i] == '=' {
+		// No-op.
+	} else if x := entity[entityName]; x != 0 {
+		return dst + utf8.EncodeRune(b[dst:], x), src + i
+	} else if x := entity2[entityName]; x[0] != 0 {
+		dst1 := dst + utf8.EncodeRune(b[dst:], x[0])
+		return dst1 + utf8.EncodeRune(b[dst1:], x[1]), src + i
+	} else if !attribute {
+		maxLen := len(entityName) - 1
+		if maxLen > longestEntityWithoutSemicolon {
+			maxLen = longestEntityWithoutSemicolon
+		}
+		for j := maxLen; j > 1; j-- {
+			if x := entity[entityName[:j]]; x != 0 {
+				return dst + utf8.EncodeRune(b[dst:], x), src + j + 1
+			}
+		}
+	}
+
+	dst1, src1 = dst+i, src+i
+	copy(b[dst:dst1], b[src:src1])
+	return dst1, src1
+}
+
+// unescape unescapes b's entities in-place, so that "a&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
+}

data/ext/vendor/golang.org/x/net/html/escape_test.go

@@ -0,0 +1,97 @@
+// 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)
+		}
+	}
+}

data/ext/vendor/golang.org/x/net/html/example_test.go

@@ -0,0 +1,40 @@
+// 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
+}

data/ext/vendor/golang.org/x/net/html/foreign.go

@@ -0,0 +1,226 @@
+// Copyright 2011 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package html
+
+import (
+	"strings"
+)
+
+func adjustAttributeNames(aa []Attribute, nameMap map[string]string) {
+	for i := range aa {
+		if newName, ok := nameMap[aa[i].Key]; ok {
+			aa[i].Key = newName
+		}
+	}
+}
+
+func adjustForeignAttributes(aa []Attribute) {
+	for i, a := range aa {
+		if a.Key == "" || a.Key[0] != 'x' {
+			continue
+		}
+		switch a.Key {
+		case "xlink:actuate", "xlink:arcrole", "xlink:href", "xlink:role", "xlink:show",
+			"xlink:title", "xlink:type", "xml:base", "xml:lang", "xml:space", "xmlns:xlink":
+			j := strings.Index(a.Key, ":")
+			aa[i].Namespace = a.Key[:j]
+			aa[i].Key = a.Key[j+1:]
+		}
+	}
+}
+
+func htmlIntegrationPoint(n *Node) bool {
+	if n.Type != ElementNode {
+		return false
+	}
+	switch n.Namespace {
+	case "math":
+		if n.Data == "annotation-xml" {
+			for _, a := range n.Attr {
+				if a.Key == "encoding" {
+					val := strings.ToLower(a.Val)
+					if val == "text/html" || val == "application/xhtml+xml" {
+						return true
+					}
+				}
+			}
+		}
+	case "svg":
+		switch n.Data {
+		case "desc", "foreignObject", "title":
+			return true
+		}
+	}
+	return false
+}
+
+func mathMLTextIntegrationPoint(n *Node) bool {
+	if n.Namespace != "math" {
+		return false
+	}
+	switch n.Data {
+	case "mi", "mo", "mn", "ms", "mtext":
+		return true
+	}
+	return false
+}
+
+// Section 12.2.5.5.
+var breakout = map[string]bool{
+	"b":          true,
+	"big":        true,
+	"blockquote": true,
+	"body":       true,
+	"br":         true,
+	"center":     true,
+	"code":       true,
+	"dd":         true,
+	"div":        true,
+	"dl":         true,
+	"dt":         true,
+	"em":         true,
+	"embed":      true,
+	"h1":         true,
+	"h2":         true,
+	"h3":         true,
+	"h4":         true,
+	"h5":         true,
+	"h6":         true,
+	"head":       true,
+	"hr":         true,
+	"i":          true,
+	"img":        true,
+	"li":         true,
+	"listing":    true,
+	"menu":       true,
+	"meta":       true,
+	"nobr":       true,
+	"ol":         true,
+	"p":          true,
+	"pre":        true,
+	"ruby":       true,
+	"s":          true,
+	"small":      true,
+	"span":       true,
+	"strong":     true,
+	"strike":     true,
+	"sub":        true,
+	"sup":        true,
+	"table":      true,
+	"tt":         true,
+	"u":          true,
+	"ul":         true,
+	"var":        true,
+}
+
+// Section 12.2.5.5.
+var svgTagNameAdjustments = map[string]string{
+	"altglyph":            "altGlyph",
+	"altglyphdef":         "altGlyphDef",
+	"altglyphitem":        "altGlyphItem",
+	"animatecolor":        "animateColor",
+	"animatemotion":       "animateMotion",
+	"animatetransform":    "animateTransform",
+	"clippath":            "clipPath",
+	"feblend":             "feBlend",
+	"fecolormatrix":       "feColorMatrix",
+	"fecomponenttransfer": "feComponentTransfer",
+	"fecomposite":         "feComposite",
+	"feconvolvematrix":    "feConvolveMatrix",
+	"fediffuselighting":   "feDiffuseLighting",
+	"fedisplacementmap":   "feDisplacementMap",
+	"fedistantlight":      "feDistantLight",
+	"feflood":             "feFlood",
+	"fefunca":             "feFuncA",
+	"fefuncb":             "feFuncB",
+	"fefuncg":             "feFuncG",
+	"fefuncr":             "feFuncR",
+	"fegaussianblur":      "feGaussianBlur",
+	"feimage":             "feImage",
+	"femerge":             "feMerge",
+	"femergenode":         "feMergeNode",
+	"femorphology":        "feMorphology",
+	"feoffset":            "feOffset",
+	"fepointlight":        "fePointLight",
+	"fespecularlighting":  "feSpecularLighting",
+	"fespotlight":         "feSpotLight",
+	"fetile":              "feTile",
+	"feturbulence":        "feTurbulence",
+	"foreignobject":       "foreignObject",
+	"glyphref":            "glyphRef",
+	"lineargradient":      "linearGradient",
+	"radialgradient":      "radialGradient",
+	"textpath":            "textPath",
+}
+
+// Section 12.2.5.1
+var mathMLAttributeAdjustments = map[string]string{
+	"definitionurl": "definitionURL",
+}
+
+var svgAttributeAdjustments = map[string]string{
+	"attributename":             "attributeName",
+	"attributetype":             "attributeType",
+	"basefrequency":             "baseFrequency",
+	"baseprofile":               "baseProfile",
+	"calcmode":                  "calcMode",
+	"clippathunits":             "clipPathUnits",
+	"contentscripttype":         "contentScriptType",
+	"contentstyletype":          "contentStyleType",
+	"diffuseconstant":           "diffuseConstant",
+	"edgemode":                  "edgeMode",
+	"externalresourcesrequired": "externalResourcesRequired",
+	"filterres":                 "filterRes",
+	"filterunits":               "filterUnits",
+	"glyphref":                  "glyphRef",
+	"gradienttransform":         "gradientTransform",
+	"gradientunits":             "gradientUnits",
+	"kernelmatrix":              "kernelMatrix",
+	"kernelunitlength":          "kernelUnitLength",
+	"keypoints":                 "keyPoints",
+	"keysplines":                "keySplines",
+	"keytimes":                  "keyTimes",
+	"lengthadjust":              "lengthAdjust",
+	"limitingconeangle":         "limitingConeAngle",
+	"markerheight":              "markerHeight",
+	"markerunits":               "markerUnits",
+	"markerwidth":               "markerWidth",
+	"maskcontentunits":          "maskContentUnits",
+	"maskunits":                 "maskUnits",
+	"numoctaves":                "numOctaves",
+	"pathlength":                "pathLength",
+	"patterncontentunits":       "patternContentUnits",
+	"patterntransform":          "patternTransform",
+	"patternunits":              "patternUnits",
+	"pointsatx":                 "pointsAtX",
+	"pointsaty":                 "pointsAtY",
+	"pointsatz":                 "pointsAtZ",
+	"preservealpha":             "preserveAlpha",
+	"preserveaspectratio":       "preserveAspectRatio",
+	"primitiveunits":            "primitiveUnits",
+	"refx":                      "refX",
+	"refy":                      "refY",
+	"repeatcount":               "repeatCount",
+	"repeatdur":                 "repeatDur",
+	"requiredextensions":        "requiredExtensions",
+	"requiredfeatures":          "requiredFeatures",
+	"specularconstant":          "specularConstant",
+	"specularexponent":          "specularExponent",
+	"spreadmethod":              "spreadMethod",
+	"startoffset":               "startOffset",
+	"stddeviation":              "stdDeviation",
+	"stitchtiles":               "stitchTiles",
+	"surfacescale":              "surfaceScale",
+	"systemlanguage":            "systemLanguage",
+	"tablevalues":               "tableValues",
+	"targetx":                   "targetX",
+	"targety":                   "targetY",
+	"textlength":                "textLength",
+	"viewbox":                   "viewBox",
+	"viewtarget":                "viewTarget",
+	"xchannelselector":          "xChannelSelector",
+	"ychannelselector":          "yChannelSelector",
+	"zoomandpan":                "zoomAndPan",
+}