RubyGems - ires - Versions diffs - 0.1.3 → 0.1.4 - Mend

ires 0.1.3 → 0.1.4

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (1024) hide show

data/ext/vendor/golang.org/x/net/html/charset/testdata/README ADDED

@@ -0,0 +1,9 @@
+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).

data/ext/vendor/golang.org/x/net/html/charset/testdata/UTF-16BE-BOM.html ADDED

Binary file

data/ext/vendor/golang.org/x/net/html/charset/testdata/UTF-16LE-BOM.html ADDED

Binary file

data/ext/vendor/golang.org/x/net/html/charset/testdata/UTF-8-BOM-vs-meta-charset.html ADDED

@@ -0,0 +1,49 @@
+<!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>

data/ext/vendor/golang.org/x/net/html/charset/testdata/UTF-8-BOM-vs-meta-content.html ADDED

@@ -0,0 +1,48 @@
+<!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>

data/ext/vendor/golang.org/x/net/html/charset/testdata/meta-charset-attribute.html ADDED

@@ -0,0 +1,48 @@
+<!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>

data/ext/vendor/golang.org/x/net/html/charset/testdata/meta-content-attribute.html ADDED

@@ -0,0 +1,48 @@
+<!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>

data/ext/vendor/golang.org/x/net/html/const.go ADDED

@@ -0,0 +1,104 @@
+// 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, // The 'isindex' element has been removed, but keep it for backwards compatibility.
+	"keygen":     true,
+	"li":         true,
+	"link":       true,
+	"listing":    true,
+	"main":       true,
+	"marquee":    true,
+	"menu":       true,
+	"meta":       true,
+	"nav":        true,
+	"noembed":    true,
+	"noframes":   true,
+	"noscript":   true,
+	"object":     true,
+	"ol":         true,
+	"p":          true,
+	"param":      true,
+	"plaintext":  true,
+	"pre":        true,
+	"script":     true,
+	"section":    true,
+	"select":     true,
+	"source":     true,
+	"style":      true,
+	"summary":    true,
+	"table":      true,
+	"tbody":      true,
+	"td":         true,
+	"template":   true,
+	"textarea":   true,
+	"tfoot":      true,
+	"th":         true,
+	"thead":      true,
+	"title":      true,
+	"tr":         true,
+	"track":      true,
+	"ul":         true,
+	"wbr":        true,
+	"xmp":        true,
+}
+func isSpecialElement(element *Node) bool {
+	switch element.Namespace {
+	case "", "html":
+		return isSpecialElementMap[element.Data]
+	case "svg":
+		return element.Data == "foreignObject"
+	}
+	return false
+}

data/ext/vendor/golang.org/x/net/html/doc.go ADDED

@@ -0,0 +1,106 @@
+// Copyright 2010 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+/*
+Package html implements an HTML5-compliant tokenizer and parser.
+Tokenization is done by creating a Tokenizer for an io.Reader r. It is the
+caller's responsibility to ensure that r provides UTF-8 encoded HTML.
+	z := html.NewTokenizer(r)
+Given a Tokenizer z, the HTML is tokenized by repeatedly calling z.Next(),
+which parses the next token and returns its type, or an error:
+	for {
+		tt := z.Next()
+		if tt == html.ErrorToken {
+			// ...
+			return ...
+		}
+		// Process the current token.
+	}
+There are two APIs for retrieving the current token. The high-level API is to
+call Token; the low-level API is to call Text or TagName / TagAttr. Both APIs
+allow optionally calling Raw after Next but before Token, Text, TagName, or
+TagAttr. In EBNF notation, the valid call sequence per token is:
+	Next {Raw} [ Token | Text | TagName {TagAttr} ]
+Token returns an independent data structure that completely describes a token.
+Entities (such as "&lt;") are unescaped, tag names and attribute keys are
+lower-cased, and attributes are collected into a []Attribute. For example:
+	for {
+		if z.Next() == html.ErrorToken {
+			// Returning io.EOF indicates success.
+			return z.Err()
+		}
+		emitToken(z.Token())
+	}
+The low-level API performs fewer allocations and copies, but the contents of
+the []byte values returned by Text, TagName and TagAttr may change on the next
+call to Next. For example, to extract an HTML page's anchor text:
+	depth := 0
+	for {
+		tt := z.Next()
+		switch tt {
+		case ErrorToken:
+			return z.Err()
+		case TextToken:
+			if depth > 0 {
+				// emitBytes should copy the []byte it receives,
+				// if it doesn't process it immediately.
+				emitBytes(z.Text())
+			}
+		case StartTagToken, EndTagToken:
+			tn, _ := z.TagName()
+			if len(tn) == 1 && tn[0] == 'a' {
+				if tt == StartTagToken {
+					depth++
+				} else {
+					depth--
+				}
+			}
+		}
+	}
+Parsing is done by calling Parse with an io.Reader, which returns the root of
+the parse tree (the document element) as a *Node. It is the caller's
+responsibility to ensure that the Reader provides UTF-8 encoded HTML. For
+example, to process each anchor node in depth-first order:
+	doc, err := html.Parse(r)
+	if err != nil {
+		// ...
+	}
+	var f func(*html.Node)
+	f = func(n *html.Node) {
+		if n.Type == html.ElementNode && n.Data == "a" {
+			// Do something with n...
+		}
+		for c := n.FirstChild; c != nil; c = c.NextSibling {
+			f(c)
+		}
+	}
+	f(doc)
+The relevant specifications include:
+https://html.spec.whatwg.org/multipage/syntax.html and
+https://html.spec.whatwg.org/multipage/syntax.html#tokenization
+*/
+package html // import "golang.org/x/net/html"
+// The tokenization algorithm implemented by this package is not a line-by-line
+// transliteration of the relatively verbose state-machine in the WHATWG
+// specification. A more direct approach is used instead, where the program
+// counter implies the state, such as whether it is tokenizing a tag or a text
+// node. Specification compliance is verified by checking expected and actual
+// outputs over a test suite rather than aiming for algorithmic fidelity.
+// TODO(nigeltao): Does a DOM API belong in this package or a separate one?
+// TODO(nigeltao): How does parsing interact with a JavaScript engine?

data/ext/vendor/golang.org/x/net/html/doctype.go ADDED

@@ -0,0 +1,156 @@
+// Copyright 2011 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+package html
+import (
+	"strings"
+)
+// parseDoctype parses the data from a DoctypeToken into a name,
+// public identifier, and system identifier. It returns a Node whose Type
+// is DoctypeNode, whose Data is the name, and which has attributes
+// named "system" and "public" for the two identifiers if they were present.
+// quirks is whether the document should be parsed in "quirks mode".
+func parseDoctype(s string) (n *Node, quirks bool) {
+	n = &Node{Type: DoctypeNode}
+	// Find the name.
+	space := strings.IndexAny(s, whitespace)
+	if space == -1 {
+		space = len(s)
+	}
+	n.Data = s[:space]
+	// The comparison to "html" is case-sensitive.
+	if n.Data != "html" {
+		quirks = true
+	}
+	n.Data = strings.ToLower(n.Data)
+	s = strings.TrimLeft(s[space:], whitespace)
+	if len(s) < 6 {
+		// It can't start with "PUBLIC" or "SYSTEM".
+		// Ignore the rest of the string.
+		return n, quirks || s != ""
+	}
+	key := strings.ToLower(s[:6])
+	s = s[6:]
+	for key == "public" || key == "system" {
+		s = strings.TrimLeft(s, whitespace)
+		if s == "" {
+			break
+		}
+		quote := s[0]
+		if quote != '"' && quote != '\'' {
+			break
+		}
+		s = s[1:]
+		q := strings.IndexRune(s, rune(quote))
+		var id string
+		if q == -1 {
+			id = s
+			s = ""
+		} else {
+			id = s[:q]
+			s = s[q+1:]
+		}
+		n.Attr = append(n.Attr, Attribute{Key: key, Val: id})
+		if key == "public" {
+			key = "system"
+		} else {
+			key = ""
+		}
+	}
+	if key != "" || s != "" {
+		quirks = true
+	} else if len(n.Attr) > 0 {
+		if n.Attr[0].Key == "public" {
+			public := strings.ToLower(n.Attr[0].Val)
+			switch public {
+			case "-//w3o//dtd w3 html strict 3.0//en//", "-/w3d/dtd html 4.0 transitional/en", "html":
+				quirks = true
+			default:
+				for _, q := range quirkyIDs {
+					if strings.HasPrefix(public, q) {
+						quirks = true
+						break
+					}
+				}
+			}
+			// The following two public IDs only cause quirks mode if there is no system ID.
+			if len(n.Attr) == 1 && (strings.HasPrefix(public, "-//w3c//dtd html 4.01 frameset//") ||
+				strings.HasPrefix(public, "-//w3c//dtd html 4.01 transitional//")) {
+				quirks = true
+			}
+		}
+		if lastAttr := n.Attr[len(n.Attr)-1]; lastAttr.Key == "system" &&
+			strings.ToLower(lastAttr.Val) == "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd" {
+			quirks = true
+		}
+	}
+	return n, quirks
+}
+// quirkyIDs is a list of public doctype identifiers that cause a document
+// to be interpreted in quirks mode. The identifiers should be in lower case.
+var quirkyIDs = []string{
+	"+//silmaril//dtd html pro v0r11 19970101//",
+	"-//advasoft ltd//dtd html 3.0 aswedit + extensions//",
+	"-//as//dtd html 3.0 aswedit + extensions//",
+	"-//ietf//dtd html 2.0 level 1//",
+	"-//ietf//dtd html 2.0 level 2//",
+	"-//ietf//dtd html 2.0 strict level 1//",
+	"-//ietf//dtd html 2.0 strict level 2//",
+	"-//ietf//dtd html 2.0 strict//",
+	"-//ietf//dtd html 2.0//",
+	"-//ietf//dtd html 2.1e//",
+	"-//ietf//dtd html 3.0//",
+	"-//ietf//dtd html 3.2 final//",
+	"-//ietf//dtd html 3.2//",
+	"-//ietf//dtd html 3//",
+	"-//ietf//dtd html level 0//",
+	"-//ietf//dtd html level 1//",
+	"-//ietf//dtd html level 2//",
+	"-//ietf//dtd html level 3//",
+	"-//ietf//dtd html strict level 0//",
+	"-//ietf//dtd html strict level 1//",
+	"-//ietf//dtd html strict level 2//",
+	"-//ietf//dtd html strict level 3//",
+	"-//ietf//dtd html strict//",
+	"-//ietf//dtd html//",
+	"-//metrius//dtd metrius presentational//",
+	"-//microsoft//dtd internet explorer 2.0 html strict//",
+	"-//microsoft//dtd internet explorer 2.0 html//",
+	"-//microsoft//dtd internet explorer 2.0 tables//",
+	"-//microsoft//dtd internet explorer 3.0 html strict//",
+	"-//microsoft//dtd internet explorer 3.0 html//",
+	"-//microsoft//dtd internet explorer 3.0 tables//",
+	"-//netscape comm. corp.//dtd html//",
+	"-//netscape comm. corp.//dtd strict html//",
+	"-//o'reilly and associates//dtd html 2.0//",
+	"-//o'reilly and associates//dtd html extended 1.0//",
+	"-//o'reilly and associates//dtd html extended relaxed 1.0//",
+	"-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//",
+	"-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//",
+	"-//spyglass//dtd html 2.0 extended//",
+	"-//sq//dtd html 2.0 hotmetal + extensions//",
+	"-//sun microsystems corp.//dtd hotjava html//",
+	"-//sun microsystems corp.//dtd hotjava strict html//",
+	"-//w3c//dtd html 3 1995-03-24//",
+	"-//w3c//dtd html 3.2 draft//",
+	"-//w3c//dtd html 3.2 final//",
+	"-//w3c//dtd html 3.2//",
+	"-//w3c//dtd html 3.2s draft//",
+	"-//w3c//dtd html 4.0 frameset//",
+	"-//w3c//dtd html 4.0 transitional//",
+	"-//w3c//dtd html experimental 19960712//",
+	"-//w3c//dtd html experimental 970421//",
+	"-//w3c//dtd w3 html//",
+	"-//w3o//dtd w3 html 3.0//",
+	"-//webtechs//dtd mozilla html 2.0//",
+	"-//webtechs//dtd mozilla html//",
+}