parse5 1.0.1 → 1.1.3
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.
- package/.npmignore +4 -2
- package/README.md +66 -8
- package/index.js +4 -3
- package/lib/common/foreign_content.js +255 -0
- package/lib/common/html.js +264 -0
- package/lib/{const → common}/unicode.js +0 -2
- package/lib/simple_api/simple_api_parser.js +68 -0
- package/lib/simple_api/tokenizer_proxy.js +119 -0
- package/lib/{tokenization_stage → tokenization}/named_entity_trie.js +0 -0
- package/lib/{tokenization_stage → tokenization}/preprocessor.js +2 -2
- package/lib/{tokenization_stage → tokenization}/tokenizer.js +14 -10
- package/lib/tree_adapters/default.js +1 -1
- package/lib/tree_adapters/htmlparser2.js +1 -1
- package/lib/tree_construction/doctype.js +107 -0
- package/lib/{tree_construction_stage → tree_construction}/formatting_element_list.js +0 -0
- package/lib/{tree_construction_stage → tree_construction}/open_element_stack.js +1 -1
- package/lib/{tree_construction_stage → tree_construction}/parser.js +39 -495
- package/lib/{tree_construction_stage → tree_serialization}/tree_serializer.js +3 -4
- package/package.json +42 -33
- package/lib/const/html.js +0 -154
- package/lib/tokenization_stage/parser_simulator.js +0 -2
package/.npmignore
CHANGED
package/README.md
CHANGED
|
@@ -1,16 +1,23 @@
|
|
|
1
1
|

|
|
2
2
|
|
|
3
|
+
[](https://travis-ci.org/inikulin/parse5)
|
|
4
|
+
|
|
3
5
|
Fast full-featured HTML parsing/serialization toolset for Node. Based on WHATWG HTML5 specification.
|
|
4
6
|
To build [TestCafé](http://testcafe.devexpress.com/) we needed fast and ready for production HTML parser, which will parse HTML as a modern browser's parser.
|
|
5
7
|
Existing solutions were either too slow or their output was too inaccurate. So, this is how parse5 was born.
|
|
6
8
|
|
|
9
|
+
**Included tools:**
|
|
10
|
+
* [Parser](#class-parser) - HTML to DOM-tree parser.
|
|
11
|
+
* [SimpleApiParser](#class-simpleapiparser) - [SAX](http://en.wikipedia.org/wiki/Simple_API_for_XML)-style parser for HTML.
|
|
12
|
+
* [TreeSerializer](#class-treeserializer) - DOM-tree to HTML serializer.
|
|
13
|
+
|
|
7
14
|
##Install
|
|
8
15
|
```
|
|
9
16
|
$ npm install parse5
|
|
10
17
|
```
|
|
11
18
|
|
|
12
19
|
|
|
13
|
-
##
|
|
20
|
+
##Usage
|
|
14
21
|
```js
|
|
15
22
|
var Parser = require('parse5').Parser;
|
|
16
23
|
|
|
@@ -43,9 +50,9 @@ So, parse5 is as fast as simple specification incompatible parsers and ~15-times
|
|
|
43
50
|
##API reference
|
|
44
51
|
|
|
45
52
|
###Enum: TreeAdapters
|
|
46
|
-
Provides built-in tree adapters which can be passed as an optional argument to the `Parser` and `TreeSerializer` constructors.
|
|
53
|
+
Provides built-in tree adapters which can be passed as an optional argument to the `Parser` and `TreeSerializer` constructors.
|
|
47
54
|
|
|
48
|
-
####• TreeAdapters.default
|
|
55
|
+
####• TreeAdapters.default
|
|
49
56
|
Default tree format for parse5.
|
|
50
57
|
|
|
51
58
|
|
|
@@ -53,8 +60,8 @@ Default tree format for parse5.
|
|
|
53
60
|
Quite popular [htmlparser2](https://github.com/fb55/htmlparser2) tree format (e.g. used in [cheerio](https://github.com/MatthewMueller/cheerio) and [jsdom](https://github.com/tmpvar/jsdom)).
|
|
54
61
|
|
|
55
62
|
---------------------------------------
|
|
56
|
-
|
|
57
|
-
|
|
63
|
+
|
|
64
|
+
|
|
58
65
|
###Class: Parser
|
|
59
66
|
Provides HTML parsing functionality.
|
|
60
67
|
|
|
@@ -84,7 +91,7 @@ var document = parser.parse('<!DOCTYPE html><html><head></head><body>Hi there!</
|
|
|
84
91
|
|
|
85
92
|
|
|
86
93
|
####• Parser.parseFragment(htmlFragment, [contextElement])
|
|
87
|
-
Parses given `htmlFragment`. Returns `documentFragment` node. Optional `contextElement` argument specifies
|
|
94
|
+
Parses given `htmlFragment`. Returns `documentFragment` node. Optional `contextElement` argument specifies context in which given `htmlFragment` will be parsed (consider it as setting `contextElement.innerHTML` property). If `contextElement` argument is not specified, `<div>` element will be used.
|
|
88
95
|
|
|
89
96
|
*Example:*
|
|
90
97
|
```js
|
|
@@ -96,6 +103,58 @@ var trFragment = parser.parseFragment('<tr><td>Shake it, baby</td></tr>', docume
|
|
|
96
103
|
|
|
97
104
|
---------------------------------------
|
|
98
105
|
|
|
106
|
+
|
|
107
|
+
###Class: SimpleApiParser
|
|
108
|
+
Provides [SAX](https://en.wikipedia.org/wiki/Simple_API_for_XML)-style HTML parsing functionality.
|
|
109
|
+
|
|
110
|
+
####• SimpleApiParser.ctor(handlers)
|
|
111
|
+
Creates new reusable instance of the `SimpleApiParser`. `handlers` argument specifies object that contains parser's event handlers. Possible events and their signatures are shown in the example.
|
|
112
|
+
|
|
113
|
+
*Example:*
|
|
114
|
+
```js
|
|
115
|
+
var parse5 = require('parse5');
|
|
116
|
+
|
|
117
|
+
var parser = new parse5.SimpleApiParser({
|
|
118
|
+
doctype: function(name, publicId, systemId) {
|
|
119
|
+
//Handle doctype here
|
|
120
|
+
},
|
|
121
|
+
|
|
122
|
+
startTag: function(tagName, attrs, selfClosing) {
|
|
123
|
+
//Handle start tags here
|
|
124
|
+
},
|
|
125
|
+
|
|
126
|
+
endTag: function(tagName) {
|
|
127
|
+
//Handle end tags here
|
|
128
|
+
},
|
|
129
|
+
|
|
130
|
+
text: function(text) {
|
|
131
|
+
//Handle texts here
|
|
132
|
+
},
|
|
133
|
+
|
|
134
|
+
comment: function(text) {
|
|
135
|
+
//Handle comments here
|
|
136
|
+
}
|
|
137
|
+
});
|
|
138
|
+
```
|
|
139
|
+
|
|
140
|
+
####• SimpleApiParser.parse(html)
|
|
141
|
+
Raises parser events for the given `html`.
|
|
142
|
+
|
|
143
|
+
*Example:*
|
|
144
|
+
```js
|
|
145
|
+
var parse5 = require('parse5');
|
|
146
|
+
|
|
147
|
+
var parser = new parse5.SimpleApiParser({
|
|
148
|
+
text: function(text) {
|
|
149
|
+
console.log(text);
|
|
150
|
+
}
|
|
151
|
+
});
|
|
152
|
+
|
|
153
|
+
parser.parse('<body>Yo!</body>');
|
|
154
|
+
```
|
|
155
|
+
|
|
156
|
+
---------------------------------------
|
|
157
|
+
|
|
99
158
|
###Class: TreeSerializer
|
|
100
159
|
Provides tree-to-HTML serialization functionality.
|
|
101
160
|
|
|
@@ -135,7 +194,7 @@ var bodyInnerHtml = serializer.serialize(document.childNodes[0].childNodes[1]);
|
|
|
135
194
|
Test data is adopted from [html5lib project](https://github.com/html5lib). Parser is covered by more than 8000 test cases.
|
|
136
195
|
To run tests:
|
|
137
196
|
```
|
|
138
|
-
$
|
|
197
|
+
$ npm test
|
|
139
198
|
```
|
|
140
199
|
|
|
141
200
|
|
|
@@ -163,4 +222,3 @@ If you have any questions, please feel free to create an issue [here on github](
|
|
|
163
222
|
|
|
164
223
|
##Author
|
|
165
224
|
[Ivan Nikulin](https://github.com/inikulin) (ifaaan@gmail.com)
|
|
166
|
-
|
package/index.js
CHANGED
|
@@ -1,7 +1,8 @@
|
|
|
1
|
-
exports.Parser = require('./lib/
|
|
2
|
-
exports.
|
|
1
|
+
exports.Parser = require('./lib/tree_construction/parser');
|
|
2
|
+
exports.SimpleApiParser = require('./lib/simple_api/simple_api_parser');
|
|
3
|
+
exports.TreeSerializer = require('./lib/tree_serialization/tree_serializer');
|
|
3
4
|
|
|
4
5
|
exports.TreeAdapters = {
|
|
5
6
|
default: require('./lib/tree_adapters/default'),
|
|
6
7
|
htmlparser2: require('./lib/tree_adapters/htmlparser2')
|
|
7
|
-
};
|
|
8
|
+
};
|
|
@@ -0,0 +1,255 @@
|
|
|
1
|
+
var Tokenizer = require('../tokenization/tokenizer'),
|
|
2
|
+
HTML = require('./html');
|
|
3
|
+
|
|
4
|
+
//Aliases
|
|
5
|
+
var $ = HTML.TAG_NAMES,
|
|
6
|
+
NS = HTML.NAMESPACES,
|
|
7
|
+
ATTRS = HTML.ATTRS;
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
//MIME types
|
|
11
|
+
var MIME_TYPES = {
|
|
12
|
+
TEXT_HTML: 'text/html',
|
|
13
|
+
APPLICATION_XML: 'application/xhtml+xml'
|
|
14
|
+
};
|
|
15
|
+
|
|
16
|
+
//Attributes
|
|
17
|
+
var DEFINITION_URL_ATTR = 'definitionurl',
|
|
18
|
+
ADJUSTED_DEFINITION_URL_ATTR = 'definitionURL',
|
|
19
|
+
SVG_ATTRS_ADJUSTMENT_MAP = {
|
|
20
|
+
'attributename': 'attributeName',
|
|
21
|
+
'attributetype': 'attributeType',
|
|
22
|
+
'basefrequency': 'baseFrequency',
|
|
23
|
+
'baseprofile': 'baseProfile',
|
|
24
|
+
'calcmode': 'calcMode',
|
|
25
|
+
'clippathunits': 'clipPathUnits',
|
|
26
|
+
'contentscripttype': 'contentScriptType',
|
|
27
|
+
'contentstyletype': 'contentStyleType',
|
|
28
|
+
'diffuseconstant': 'diffuseConstant',
|
|
29
|
+
'edgemode': 'edgeMode',
|
|
30
|
+
'externalresourcesrequired': 'externalResourcesRequired',
|
|
31
|
+
'filterres': 'filterRes',
|
|
32
|
+
'filterunits': 'filterUnits',
|
|
33
|
+
'glyphref': 'glyphRef',
|
|
34
|
+
'gradienttransform': 'gradientTransform',
|
|
35
|
+
'gradientunits': 'gradientUnits',
|
|
36
|
+
'kernelmatrix': 'kernelMatrix',
|
|
37
|
+
'kernelunitlength': 'kernelUnitLength',
|
|
38
|
+
'keypoints': 'keyPoints',
|
|
39
|
+
'keysplines': 'keySplines',
|
|
40
|
+
'keytimes': 'keyTimes',
|
|
41
|
+
'lengthadjust': 'lengthAdjust',
|
|
42
|
+
'limitingconeangle': 'limitingConeAngle',
|
|
43
|
+
'markerheight': 'markerHeight',
|
|
44
|
+
'markerunits': 'markerUnits',
|
|
45
|
+
'markerwidth': 'markerWidth',
|
|
46
|
+
'maskcontentunits': 'maskContentUnits',
|
|
47
|
+
'maskunits': 'maskUnits',
|
|
48
|
+
'numoctaves': 'numOctaves',
|
|
49
|
+
'pathlength': 'pathLength',
|
|
50
|
+
'patterncontentunits': 'patternContentUnits',
|
|
51
|
+
'patterntransform': 'patternTransform',
|
|
52
|
+
'patternunits': 'patternUnits',
|
|
53
|
+
'pointsatx': 'pointsAtX',
|
|
54
|
+
'pointsaty': 'pointsAtY',
|
|
55
|
+
'pointsatz': 'pointsAtZ',
|
|
56
|
+
'preservealpha': 'preserveAlpha',
|
|
57
|
+
'preserveaspectratio': 'preserveAspectRatio',
|
|
58
|
+
'primitiveunits': 'primitiveUnits',
|
|
59
|
+
'refx': 'refX',
|
|
60
|
+
'refy': 'refY',
|
|
61
|
+
'repeatcount': 'repeatCount',
|
|
62
|
+
'repeatdur': 'repeatDur',
|
|
63
|
+
'requiredextensions': 'requiredExtensions',
|
|
64
|
+
'requiredfeatures': 'requiredFeatures',
|
|
65
|
+
'specularconstant': 'specularConstant',
|
|
66
|
+
'specularexponent': 'specularExponent',
|
|
67
|
+
'spreadmethod': 'spreadMethod',
|
|
68
|
+
'startoffset': 'startOffset',
|
|
69
|
+
'stddeviation': 'stdDeviation',
|
|
70
|
+
'stitchtiles': 'stitchTiles',
|
|
71
|
+
'surfacescale': 'surfaceScale',
|
|
72
|
+
'systemlanguage': 'systemLanguage',
|
|
73
|
+
'tablevalues': 'tableValues',
|
|
74
|
+
'targetx': 'targetX',
|
|
75
|
+
'targety': 'targetY',
|
|
76
|
+
'textlength': 'textLength',
|
|
77
|
+
'viewbox': 'viewBox',
|
|
78
|
+
'viewtarget': 'viewTarget',
|
|
79
|
+
'xchannelselector': 'xChannelSelector',
|
|
80
|
+
'ychannelselector': 'yChannelSelector',
|
|
81
|
+
'zoomandpan': 'zoomAndPan'
|
|
82
|
+
},
|
|
83
|
+
XML_ATTRS_ADJUSTMENT_MAP = {
|
|
84
|
+
'xlink:actuate': {prefix: 'xlink', name: 'actuate', namespace: NS.XLINK},
|
|
85
|
+
'xlink:arcrole': {prefix: 'xlink', name: 'arcrole', namespace: NS.XLINK},
|
|
86
|
+
'xlink:href': {prefix: 'xlink', name: 'href', namespace: NS.XLINK},
|
|
87
|
+
'xlink:role': {prefix: 'xlink', name: 'role', namespace: NS.XLINK},
|
|
88
|
+
'xlink:show': {prefix: 'xlink', name: 'show', namespace: NS.XLINK},
|
|
89
|
+
'xlink:title': {prefix: 'xlink', name: 'title', namespace: NS.XLINK},
|
|
90
|
+
'xlink:type': {prefix: 'xlink', name: 'type', namespace: NS.XLINK},
|
|
91
|
+
'xml:base': {prefix: 'xml', name: 'base', namespace: NS.XML},
|
|
92
|
+
'xml:lang': {prefix: 'xml', name: 'lang', namespace: NS.XML},
|
|
93
|
+
'xml:space': {prefix: 'xml', name: 'space', namespace: NS.XML},
|
|
94
|
+
'xmlns': {prefix: '', name: 'xmlns', namespace: NS.XMLNS},
|
|
95
|
+
'xmlns:xlink': {prefix: 'xmlns', name: 'xlink', namespace: NS.XMLNS}
|
|
96
|
+
|
|
97
|
+
};
|
|
98
|
+
|
|
99
|
+
//SVG tag names adjustment map
|
|
100
|
+
var SVG_TAG_NAMES_ADJUSTMENT_MAP = {
|
|
101
|
+
'altglyph': 'altGlyph',
|
|
102
|
+
'altglyphdef': 'altGlyphDef',
|
|
103
|
+
'altglyphitem': 'altGlyphItem',
|
|
104
|
+
'animatecolor': 'animateColor',
|
|
105
|
+
'animatemotion': 'animateMotion',
|
|
106
|
+
'animatetransform': 'animateTransform',
|
|
107
|
+
'clippath': 'clipPath',
|
|
108
|
+
'feblend': 'feBlend',
|
|
109
|
+
'fecolormatrix': 'feColorMatrix',
|
|
110
|
+
'fecomponenttransfer': 'feComponentTransfer',
|
|
111
|
+
'fecomposite': 'feComposite',
|
|
112
|
+
'feconvolvematrix': 'feConvolveMatrix',
|
|
113
|
+
'fediffuselighting': 'feDiffuseLighting',
|
|
114
|
+
'fedisplacementmap': 'feDisplacementMap',
|
|
115
|
+
'fedistantlight': 'feDistantLight',
|
|
116
|
+
'feflood': 'feFlood',
|
|
117
|
+
'fefunca': 'feFuncA',
|
|
118
|
+
'fefuncb': 'feFuncB',
|
|
119
|
+
'fefuncg': 'feFuncG',
|
|
120
|
+
'fefuncr': 'feFuncR',
|
|
121
|
+
'fegaussianblur': 'feGaussianBlur',
|
|
122
|
+
'feimage': 'feImage',
|
|
123
|
+
'femerge': 'feMerge',
|
|
124
|
+
'femergenode': 'feMergeNode',
|
|
125
|
+
'femorphology': 'feMorphology',
|
|
126
|
+
'feoffset': 'feOffset',
|
|
127
|
+
'fepointlight': 'fePointLight',
|
|
128
|
+
'fespecularlighting': 'feSpecularLighting',
|
|
129
|
+
'fespotlight': 'feSpotLight',
|
|
130
|
+
'fetile': 'feTile',
|
|
131
|
+
'feturbulence': 'feTurbulence',
|
|
132
|
+
'foreignobject': 'foreignObject',
|
|
133
|
+
'glyphref': 'glyphRef',
|
|
134
|
+
'lineargradient': 'linearGradient',
|
|
135
|
+
'radialgradient': 'radialGradient',
|
|
136
|
+
'textpath': 'textPath'
|
|
137
|
+
};
|
|
138
|
+
|
|
139
|
+
//Tags that causes exit from foreign content
|
|
140
|
+
var EXITS_FOREIGN_CONTENT = {};
|
|
141
|
+
|
|
142
|
+
EXITS_FOREIGN_CONTENT[$.B] = true;
|
|
143
|
+
EXITS_FOREIGN_CONTENT[$.BIG] = true;
|
|
144
|
+
EXITS_FOREIGN_CONTENT[$.BLOCKQUOTE] = true;
|
|
145
|
+
EXITS_FOREIGN_CONTENT[$.BODY] = true;
|
|
146
|
+
EXITS_FOREIGN_CONTENT[$.BR] = true;
|
|
147
|
+
EXITS_FOREIGN_CONTENT[$.CENTER] = true;
|
|
148
|
+
EXITS_FOREIGN_CONTENT[$.CODE] = true;
|
|
149
|
+
EXITS_FOREIGN_CONTENT[$.DD] = true;
|
|
150
|
+
EXITS_FOREIGN_CONTENT[$.DIV] = true;
|
|
151
|
+
EXITS_FOREIGN_CONTENT[$.DL] = true;
|
|
152
|
+
EXITS_FOREIGN_CONTENT[$.DT] = true;
|
|
153
|
+
EXITS_FOREIGN_CONTENT[$.EM] = true;
|
|
154
|
+
EXITS_FOREIGN_CONTENT[$.EMBED] = true;
|
|
155
|
+
EXITS_FOREIGN_CONTENT[$.H1] = true;
|
|
156
|
+
EXITS_FOREIGN_CONTENT[$.H2] = true;
|
|
157
|
+
EXITS_FOREIGN_CONTENT[$.H3] = true;
|
|
158
|
+
EXITS_FOREIGN_CONTENT[$.H4] = true;
|
|
159
|
+
EXITS_FOREIGN_CONTENT[$.H5] = true;
|
|
160
|
+
EXITS_FOREIGN_CONTENT[$.H6] = true;
|
|
161
|
+
EXITS_FOREIGN_CONTENT[$.HEAD] = true;
|
|
162
|
+
EXITS_FOREIGN_CONTENT[$.HR] = true;
|
|
163
|
+
EXITS_FOREIGN_CONTENT[$.I] = true;
|
|
164
|
+
EXITS_FOREIGN_CONTENT[$.IMG] = true;
|
|
165
|
+
EXITS_FOREIGN_CONTENT[$.LI] = true;
|
|
166
|
+
EXITS_FOREIGN_CONTENT[$.LISTING] = true;
|
|
167
|
+
EXITS_FOREIGN_CONTENT[$.MENU] = true;
|
|
168
|
+
EXITS_FOREIGN_CONTENT[$.META] = true;
|
|
169
|
+
EXITS_FOREIGN_CONTENT[$.NOBR] = true;
|
|
170
|
+
EXITS_FOREIGN_CONTENT[$.OL] = true;
|
|
171
|
+
EXITS_FOREIGN_CONTENT[$.P] = true;
|
|
172
|
+
EXITS_FOREIGN_CONTENT[$.PRE] = true;
|
|
173
|
+
EXITS_FOREIGN_CONTENT[$.RUBY] = true;
|
|
174
|
+
EXITS_FOREIGN_CONTENT[$.S] = true;
|
|
175
|
+
EXITS_FOREIGN_CONTENT[$.SMALL] = true;
|
|
176
|
+
EXITS_FOREIGN_CONTENT[$.SPAN] = true;
|
|
177
|
+
EXITS_FOREIGN_CONTENT[$.STRONG] = true;
|
|
178
|
+
EXITS_FOREIGN_CONTENT[$.STRIKE] = true;
|
|
179
|
+
EXITS_FOREIGN_CONTENT[$.SUB] = true;
|
|
180
|
+
EXITS_FOREIGN_CONTENT[$.SUP] = true;
|
|
181
|
+
EXITS_FOREIGN_CONTENT[$.TABLE] = true;
|
|
182
|
+
EXITS_FOREIGN_CONTENT[$.TT] = true;
|
|
183
|
+
EXITS_FOREIGN_CONTENT[$.U] = true;
|
|
184
|
+
EXITS_FOREIGN_CONTENT[$.UL] = true;
|
|
185
|
+
EXITS_FOREIGN_CONTENT[$.VAR] = true;
|
|
186
|
+
|
|
187
|
+
//Check exit from foreign content
|
|
188
|
+
exports.causesExit = function (startTagToken) {
|
|
189
|
+
var tn = startTagToken.tagName;
|
|
190
|
+
|
|
191
|
+
if (tn === $.FONT && (Tokenizer.getTokenAttr(startTagToken, ATTRS.COLOR) !== null ||
|
|
192
|
+
Tokenizer.getTokenAttr(startTagToken, ATTRS.SIZE) !== null ||
|
|
193
|
+
Tokenizer.getTokenAttr(startTagToken, ATTRS.FACE) !== null)) {
|
|
194
|
+
return true;
|
|
195
|
+
}
|
|
196
|
+
|
|
197
|
+
return EXITS_FOREIGN_CONTENT[tn];
|
|
198
|
+
};
|
|
199
|
+
|
|
200
|
+
//Token adjustments
|
|
201
|
+
exports.adjustTokenMathMLAttrs = function (token) {
|
|
202
|
+
for (var i = 0; i < token.attrs.length; i++) {
|
|
203
|
+
if (token.attrs[i].name === DEFINITION_URL_ATTR) {
|
|
204
|
+
token.attrs[i].name = ADJUSTED_DEFINITION_URL_ATTR;
|
|
205
|
+
break;
|
|
206
|
+
}
|
|
207
|
+
}
|
|
208
|
+
};
|
|
209
|
+
|
|
210
|
+
exports.adjustTokenSVGAttrs = function (token) {
|
|
211
|
+
for (var i = 0; i < token.attrs.length; i++) {
|
|
212
|
+
var adjustedAttrName = SVG_ATTRS_ADJUSTMENT_MAP[token.attrs[i].name];
|
|
213
|
+
|
|
214
|
+
if (adjustedAttrName)
|
|
215
|
+
token.attrs[i].name = adjustedAttrName;
|
|
216
|
+
}
|
|
217
|
+
};
|
|
218
|
+
|
|
219
|
+
exports.adjustTokenXMLAttrs = function (token) {
|
|
220
|
+
for (var i = 0; i < token.attrs.length; i++) {
|
|
221
|
+
var adjustedAttrEntry = XML_ATTRS_ADJUSTMENT_MAP[token.attrs[i].name];
|
|
222
|
+
|
|
223
|
+
if (adjustedAttrEntry) {
|
|
224
|
+
token.attrs[i].prefix = adjustedAttrEntry.prefix;
|
|
225
|
+
token.attrs[i].name = adjustedAttrEntry.name;
|
|
226
|
+
token.attrs[i].namespace = adjustedAttrEntry.namespace;
|
|
227
|
+
}
|
|
228
|
+
}
|
|
229
|
+
};
|
|
230
|
+
|
|
231
|
+
exports.adjustTokenSVGTagName = function (token) {
|
|
232
|
+
var adjustedTagName = SVG_TAG_NAMES_ADJUSTMENT_MAP[token.tagName];
|
|
233
|
+
|
|
234
|
+
if (adjustedTagName)
|
|
235
|
+
token.tagName = adjustedTagName;
|
|
236
|
+
};
|
|
237
|
+
|
|
238
|
+
//Integration points
|
|
239
|
+
exports.isMathMLTextIntegrationPoint = function (tn, ns) {
|
|
240
|
+
return ns === NS.MATHML && (tn === $.MI || tn === $.MO || tn === $.MN || tn === $.MS || tn === $.MTEXT);
|
|
241
|
+
};
|
|
242
|
+
|
|
243
|
+
exports.isHtmlIntegrationPoint = function (tn, ns, attrs) {
|
|
244
|
+
if (ns === NS.MATHML && tn === $.ANNOTATION_XML) {
|
|
245
|
+
for (var i = 0; i < attrs.length; i++) {
|
|
246
|
+
if (attrs[i].name === ATTRS.ENCODING) {
|
|
247
|
+
var value = attrs[i].value.toLowerCase();
|
|
248
|
+
|
|
249
|
+
return value === MIME_TYPES.TEXT_HTML || value === MIME_TYPES.APPLICATION_XML;
|
|
250
|
+
}
|
|
251
|
+
}
|
|
252
|
+
}
|
|
253
|
+
|
|
254
|
+
return ns === NS.SVG && (tn === $.FOREIGN_OBJECT || tn === $.DESC || tn === $.TITLE);
|
|
255
|
+
};
|
|
@@ -0,0 +1,264 @@
|
|
|
1
|
+
var NS = exports.NAMESPACES = {
|
|
2
|
+
HTML: 'http://www.w3.org/1999/xhtml',
|
|
3
|
+
MATHML: 'http://www.w3.org/1998/Math/MathML',
|
|
4
|
+
SVG: 'http://www.w3.org/2000/svg',
|
|
5
|
+
XLINK: 'http://www.w3.org/1999/xlink',
|
|
6
|
+
XML: 'http://www.w3.org/XML/1998/namespace',
|
|
7
|
+
XMLNS: 'http://www.w3.org/2000/xmlns/'
|
|
8
|
+
};
|
|
9
|
+
|
|
10
|
+
exports.ATTRS = {
|
|
11
|
+
TYPE: 'type',
|
|
12
|
+
ACTION: 'action',
|
|
13
|
+
ENCODING: 'encoding',
|
|
14
|
+
PROMPT: 'prompt',
|
|
15
|
+
NAME: 'name',
|
|
16
|
+
COLOR: 'color',
|
|
17
|
+
FACE: 'face',
|
|
18
|
+
SIZE: 'size'
|
|
19
|
+
};
|
|
20
|
+
|
|
21
|
+
var $ = exports.TAG_NAMES = {
|
|
22
|
+
A: 'a',
|
|
23
|
+
ADDRESS: 'address',
|
|
24
|
+
ANNOTATION_XML: 'annotation-xml',
|
|
25
|
+
APPLET: 'applet',
|
|
26
|
+
AREA: 'area',
|
|
27
|
+
ARTICLE: 'article',
|
|
28
|
+
ASIDE: 'aside',
|
|
29
|
+
|
|
30
|
+
B: 'b',
|
|
31
|
+
BASE: 'base',
|
|
32
|
+
BASEFONT: 'basefont',
|
|
33
|
+
BGSOUND: 'bgsound',
|
|
34
|
+
BIG: 'big',
|
|
35
|
+
BLOCKQUOTE: 'blockquote',
|
|
36
|
+
BODY: 'body',
|
|
37
|
+
BR: 'br',
|
|
38
|
+
BUTTON: 'button',
|
|
39
|
+
|
|
40
|
+
CAPTION: 'caption',
|
|
41
|
+
CENTER: 'center',
|
|
42
|
+
CODE: 'code',
|
|
43
|
+
COL: 'col',
|
|
44
|
+
COLGROUP: 'colgroup',
|
|
45
|
+
COMMAND: 'command',
|
|
46
|
+
|
|
47
|
+
DD: 'dd',
|
|
48
|
+
DESC: 'desc',
|
|
49
|
+
DETAILS: 'details',
|
|
50
|
+
DIALOG: 'dialog',
|
|
51
|
+
DIR: 'dir',
|
|
52
|
+
DIV: 'div',
|
|
53
|
+
DL: 'dl',
|
|
54
|
+
DT: 'dt',
|
|
55
|
+
|
|
56
|
+
EM: 'em',
|
|
57
|
+
EMBED: 'embed',
|
|
58
|
+
|
|
59
|
+
FIELDSET: 'fieldset',
|
|
60
|
+
FIGCAPTION: 'figcaption',
|
|
61
|
+
FIGURE: 'figure',
|
|
62
|
+
FONT: 'font',
|
|
63
|
+
FOOTER: 'footer',
|
|
64
|
+
FOREIGN_OBJECT: 'foreignObject',
|
|
65
|
+
FORM: 'form',
|
|
66
|
+
FRAME: 'frame',
|
|
67
|
+
FRAMESET: 'frameset',
|
|
68
|
+
|
|
69
|
+
H1: 'h1',
|
|
70
|
+
H2: 'h2',
|
|
71
|
+
H3: 'h3',
|
|
72
|
+
H4: 'h4',
|
|
73
|
+
H5: 'h5',
|
|
74
|
+
H6: 'h6',
|
|
75
|
+
HEAD: 'head',
|
|
76
|
+
HEADER: 'header',
|
|
77
|
+
HGROUP: 'hgroup',
|
|
78
|
+
HR: 'hr',
|
|
79
|
+
HTML: 'html',
|
|
80
|
+
|
|
81
|
+
I: 'i',
|
|
82
|
+
IMG: 'img',
|
|
83
|
+
IMAGE: 'image',
|
|
84
|
+
INPUT: 'input',
|
|
85
|
+
IFRAME: 'iframe',
|
|
86
|
+
ISINDEX: 'isindex',
|
|
87
|
+
|
|
88
|
+
KEYGEN: 'keygen',
|
|
89
|
+
|
|
90
|
+
LABEL: 'label',
|
|
91
|
+
LI: 'li',
|
|
92
|
+
LINK: 'link',
|
|
93
|
+
LISTING: 'listing',
|
|
94
|
+
|
|
95
|
+
MAIN: 'main',
|
|
96
|
+
MALIGNMARK: 'malignmark',
|
|
97
|
+
MARQUEE: 'marquee',
|
|
98
|
+
MATH: 'math',
|
|
99
|
+
MENU: 'menu',
|
|
100
|
+
MENUITEM: 'menuitem',
|
|
101
|
+
META: 'meta',
|
|
102
|
+
MGLYPH: 'mglyph',
|
|
103
|
+
MI: 'mi',
|
|
104
|
+
MO: 'mo',
|
|
105
|
+
MN: 'mn',
|
|
106
|
+
MS: 'ms',
|
|
107
|
+
MTEXT: 'mtext',
|
|
108
|
+
|
|
109
|
+
NAV: 'nav',
|
|
110
|
+
NOBR: 'nobr',
|
|
111
|
+
NOFRAMES: 'noframes',
|
|
112
|
+
NOEMBED: 'noembed',
|
|
113
|
+
NOSCRIPT: 'noscript',
|
|
114
|
+
|
|
115
|
+
OBJECT: 'object',
|
|
116
|
+
OL: 'ol',
|
|
117
|
+
OPTGROUP: 'optgroup',
|
|
118
|
+
OPTION: 'option',
|
|
119
|
+
|
|
120
|
+
P: 'p',
|
|
121
|
+
PARAM: 'param',
|
|
122
|
+
PLAINTEXT: 'plaintext',
|
|
123
|
+
PRE: 'pre',
|
|
124
|
+
|
|
125
|
+
RP: 'rp',
|
|
126
|
+
RT: 'rt',
|
|
127
|
+
RUBY: 'ruby',
|
|
128
|
+
|
|
129
|
+
S: 's',
|
|
130
|
+
SCRIPT: 'script',
|
|
131
|
+
SECTION: 'section',
|
|
132
|
+
SELECT: 'select',
|
|
133
|
+
SOURCE: 'source',
|
|
134
|
+
SMALL: 'small',
|
|
135
|
+
SPAN: 'span',
|
|
136
|
+
STRIKE: 'strike',
|
|
137
|
+
STRONG: 'strong',
|
|
138
|
+
STYLE: 'style',
|
|
139
|
+
SUB: 'sub',
|
|
140
|
+
SUMMARY: 'summary',
|
|
141
|
+
SUP: 'sup',
|
|
142
|
+
|
|
143
|
+
TABLE: 'table',
|
|
144
|
+
TBODY: 'tbody',
|
|
145
|
+
TEXTAREA: 'textarea',
|
|
146
|
+
TFOOT: 'tfoot',
|
|
147
|
+
TD: 'td',
|
|
148
|
+
TH: 'th',
|
|
149
|
+
THEAD: 'thead',
|
|
150
|
+
TITLE: 'title',
|
|
151
|
+
TR: 'tr',
|
|
152
|
+
TRACK: 'track',
|
|
153
|
+
TT: 'tt',
|
|
154
|
+
|
|
155
|
+
U: 'u',
|
|
156
|
+
UL: 'ul',
|
|
157
|
+
|
|
158
|
+
SVG: 'svg',
|
|
159
|
+
|
|
160
|
+
VAR: 'var',
|
|
161
|
+
|
|
162
|
+
WBR: 'wbr',
|
|
163
|
+
|
|
164
|
+
XMP: 'xmp'
|
|
165
|
+
};
|
|
166
|
+
|
|
167
|
+
var SPECIAL_ELEMENTS = exports.SPECIAL_ELEMENTS = {};
|
|
168
|
+
|
|
169
|
+
SPECIAL_ELEMENTS[NS.HTML] = {};
|
|
170
|
+
SPECIAL_ELEMENTS[NS.HTML][$.ADDRESS] = true;
|
|
171
|
+
SPECIAL_ELEMENTS[NS.HTML][$.APPLET] = true;
|
|
172
|
+
SPECIAL_ELEMENTS[NS.HTML][$.AREA] = true;
|
|
173
|
+
SPECIAL_ELEMENTS[NS.HTML][$.ARTICLE] = true;
|
|
174
|
+
SPECIAL_ELEMENTS[NS.HTML][$.ASIDE] = true;
|
|
175
|
+
SPECIAL_ELEMENTS[NS.HTML][$.BASE] = true;
|
|
176
|
+
SPECIAL_ELEMENTS[NS.HTML][$.BASEFONT] = true;
|
|
177
|
+
SPECIAL_ELEMENTS[NS.HTML][$.BGSOUND] = true;
|
|
178
|
+
SPECIAL_ELEMENTS[NS.HTML][$.BLOCKQUOTE] = true;
|
|
179
|
+
SPECIAL_ELEMENTS[NS.HTML][$.BODY] = true;
|
|
180
|
+
SPECIAL_ELEMENTS[NS.HTML][$.BR] = true;
|
|
181
|
+
SPECIAL_ELEMENTS[NS.HTML][$.BUTTON] = true;
|
|
182
|
+
SPECIAL_ELEMENTS[NS.HTML][$.CAPTION] = true;
|
|
183
|
+
SPECIAL_ELEMENTS[NS.HTML][$.CENTER] = true;
|
|
184
|
+
SPECIAL_ELEMENTS[NS.HTML][$.COL] = true;
|
|
185
|
+
SPECIAL_ELEMENTS[NS.HTML][$.COLGROUP] = true;
|
|
186
|
+
SPECIAL_ELEMENTS[NS.HTML][$.DD] = true;
|
|
187
|
+
SPECIAL_ELEMENTS[NS.HTML][$.DETAILS] = true;
|
|
188
|
+
SPECIAL_ELEMENTS[NS.HTML][$.DIR] = true;
|
|
189
|
+
SPECIAL_ELEMENTS[NS.HTML][$.DIV] = true;
|
|
190
|
+
SPECIAL_ELEMENTS[NS.HTML][$.DL] = true;
|
|
191
|
+
SPECIAL_ELEMENTS[NS.HTML][$.DT] = true;
|
|
192
|
+
SPECIAL_ELEMENTS[NS.HTML][$.EMBED] = true;
|
|
193
|
+
SPECIAL_ELEMENTS[NS.HTML][$.FIELDSET] = true;
|
|
194
|
+
SPECIAL_ELEMENTS[NS.HTML][$.FIGCAPTION] = true;
|
|
195
|
+
SPECIAL_ELEMENTS[NS.HTML][$.FIGURE] = true;
|
|
196
|
+
SPECIAL_ELEMENTS[NS.HTML][$.FOOTER] = true;
|
|
197
|
+
SPECIAL_ELEMENTS[NS.HTML][$.FORM] = true;
|
|
198
|
+
SPECIAL_ELEMENTS[NS.HTML][$.FRAME] = true;
|
|
199
|
+
SPECIAL_ELEMENTS[NS.HTML][$.FRAMESET] = true;
|
|
200
|
+
SPECIAL_ELEMENTS[NS.HTML][$.H1] = true;
|
|
201
|
+
SPECIAL_ELEMENTS[NS.HTML][$.H2] = true;
|
|
202
|
+
SPECIAL_ELEMENTS[NS.HTML][$.H3] = true;
|
|
203
|
+
SPECIAL_ELEMENTS[NS.HTML][$.H4] = true;
|
|
204
|
+
SPECIAL_ELEMENTS[NS.HTML][$.H5] = true;
|
|
205
|
+
SPECIAL_ELEMENTS[NS.HTML][$.H6] = true;
|
|
206
|
+
SPECIAL_ELEMENTS[NS.HTML][$.HEAD] = true;
|
|
207
|
+
SPECIAL_ELEMENTS[NS.HTML][$.HEADER] = true;
|
|
208
|
+
SPECIAL_ELEMENTS[NS.HTML][$.HGROUP] = true;
|
|
209
|
+
SPECIAL_ELEMENTS[NS.HTML][$.HR] = true;
|
|
210
|
+
SPECIAL_ELEMENTS[NS.HTML][$.HTML] = true;
|
|
211
|
+
SPECIAL_ELEMENTS[NS.HTML][$.IFRAME] = true;
|
|
212
|
+
SPECIAL_ELEMENTS[NS.HTML][$.IMG] = true;
|
|
213
|
+
SPECIAL_ELEMENTS[NS.HTML][$.INPUT] = true;
|
|
214
|
+
SPECIAL_ELEMENTS[NS.HTML][$.ISINDEX] = true;
|
|
215
|
+
SPECIAL_ELEMENTS[NS.HTML][$.LI] = true;
|
|
216
|
+
SPECIAL_ELEMENTS[NS.HTML][$.LINK] = true;
|
|
217
|
+
SPECIAL_ELEMENTS[NS.HTML][$.LISTING] = true;
|
|
218
|
+
SPECIAL_ELEMENTS[NS.HTML][$.MAIN] = true;
|
|
219
|
+
SPECIAL_ELEMENTS[NS.HTML][$.MARQUEE] = true;
|
|
220
|
+
SPECIAL_ELEMENTS[NS.HTML][$.MENU] = true;
|
|
221
|
+
SPECIAL_ELEMENTS[NS.HTML][$.MENUITEM] = true;
|
|
222
|
+
SPECIAL_ELEMENTS[NS.HTML][$.META] = true;
|
|
223
|
+
SPECIAL_ELEMENTS[NS.HTML][$.NAV] = true;
|
|
224
|
+
SPECIAL_ELEMENTS[NS.HTML][$.NOEMBED] = true;
|
|
225
|
+
SPECIAL_ELEMENTS[NS.HTML][$.NOFRAMES] = true;
|
|
226
|
+
SPECIAL_ELEMENTS[NS.HTML][$.NOSCRIPT] = true;
|
|
227
|
+
SPECIAL_ELEMENTS[NS.HTML][$.OBJECT] = true;
|
|
228
|
+
SPECIAL_ELEMENTS[NS.HTML][$.OL] = true;
|
|
229
|
+
SPECIAL_ELEMENTS[NS.HTML][$.P] = true;
|
|
230
|
+
SPECIAL_ELEMENTS[NS.HTML][$.PARAM] = true;
|
|
231
|
+
SPECIAL_ELEMENTS[NS.HTML][$.PLAINTEXT] = true;
|
|
232
|
+
SPECIAL_ELEMENTS[NS.HTML][$.PRE] = true;
|
|
233
|
+
SPECIAL_ELEMENTS[NS.HTML][$.SCRIPT] = true;
|
|
234
|
+
SPECIAL_ELEMENTS[NS.HTML][$.SECTION] = true;
|
|
235
|
+
SPECIAL_ELEMENTS[NS.HTML][$.SELECT] = true;
|
|
236
|
+
SPECIAL_ELEMENTS[NS.HTML][$.SOURCE] = true;
|
|
237
|
+
SPECIAL_ELEMENTS[NS.HTML][$.STYLE] = true;
|
|
238
|
+
SPECIAL_ELEMENTS[NS.HTML][$.SUMMARY] = true;
|
|
239
|
+
SPECIAL_ELEMENTS[NS.HTML][$.TABLE] = true;
|
|
240
|
+
SPECIAL_ELEMENTS[NS.HTML][$.TBODY] = true;
|
|
241
|
+
SPECIAL_ELEMENTS[NS.HTML][$.TD] = true;
|
|
242
|
+
SPECIAL_ELEMENTS[NS.HTML][$.TEXTAREA] = true;
|
|
243
|
+
SPECIAL_ELEMENTS[NS.HTML][$.TFOOT] = true;
|
|
244
|
+
SPECIAL_ELEMENTS[NS.HTML][$.TH] = true;
|
|
245
|
+
SPECIAL_ELEMENTS[NS.HTML][$.THEAD] = true;
|
|
246
|
+
SPECIAL_ELEMENTS[NS.HTML][$.TITLE] = true;
|
|
247
|
+
SPECIAL_ELEMENTS[NS.HTML][$.TR] = true;
|
|
248
|
+
SPECIAL_ELEMENTS[NS.HTML][$.TRACK] = true;
|
|
249
|
+
SPECIAL_ELEMENTS[NS.HTML][$.UL] = true;
|
|
250
|
+
SPECIAL_ELEMENTS[NS.HTML][$.WBR] = true;
|
|
251
|
+
SPECIAL_ELEMENTS[NS.HTML][$.XMP] = true;
|
|
252
|
+
|
|
253
|
+
SPECIAL_ELEMENTS[NS.MATHML] = {};
|
|
254
|
+
SPECIAL_ELEMENTS[NS.MATHML][$.MI] = true;
|
|
255
|
+
SPECIAL_ELEMENTS[NS.MATHML][$.MO] = true;
|
|
256
|
+
SPECIAL_ELEMENTS[NS.MATHML][$.MN] = true;
|
|
257
|
+
SPECIAL_ELEMENTS[NS.MATHML][$.MS] = true;
|
|
258
|
+
SPECIAL_ELEMENTS[NS.MATHML][$.MTEXT] = true;
|
|
259
|
+
SPECIAL_ELEMENTS[NS.MATHML][$.ANNOTATION_XML] = true;
|
|
260
|
+
|
|
261
|
+
SPECIAL_ELEMENTS[NS.SVG] = {};
|
|
262
|
+
SPECIAL_ELEMENTS[NS.SVG][$.TITLE] = true;
|
|
263
|
+
SPECIAL_ELEMENTS[NS.SVG][$.FOREIGN_OBJECT] = true;
|
|
264
|
+
SPECIAL_ELEMENTS[NS.SVG][$.DESC] = true;
|
|
@@ -1,4 +1,3 @@
|
|
|
1
|
-
exports.NULL_CHARACTER = '\u0000';
|
|
2
1
|
exports.REPLACEMENT_CHARACTER = '\uFFFD';
|
|
3
2
|
|
|
4
3
|
exports.CODE_POINTS = {
|
|
@@ -46,4 +45,3 @@ exports.CODE_POINT_SEQUENCES = {
|
|
|
46
45
|
PUBLIC_STRING: [0x50, 0x55, 0x42, 0x4C, 0x49, 0x43], //PUBLIC
|
|
47
46
|
SYSTEM_STRING: [0x53, 0x59, 0x53, 0x54, 0x45, 0x4D] //SYSTEM
|
|
48
47
|
};
|
|
49
|
-
|