parse5 1.4.0 → 1.5.1

package/lib/simple_api/tokenizer_proxy.js

@@ -1,122 +1,122 @@
-'use strict';
-
-var Tokenizer = require('../tokenization/tokenizer'),
-    ForeignContent = require('../common/foreign_content'),
-    UNICODE = require('../common/unicode'),
-    HTML = require('../common/html');
-
-//Aliases
-var $ = HTML.TAG_NAMES,
-    NS = HTML.NAMESPACES;
-
-
-//Tokenizer proxy
-//NOTE: this proxy simulates adjustment of the Tokenizer which performed by standard parser during tree construction.
-var TokenizerProxy = module.exports = function (html, options) {
-    this.tokenizer = new Tokenizer(html, options);
-
-    this.namespaceStack = [];
-    this.namespaceStackTop = -1;
-    this.currentNamespace = null;
-    this.inForeignContent = false;
-};
-
-//API
-TokenizerProxy.prototype.getNextToken = function () {
-    var token = this.tokenizer.getNextToken();
-
-    if (token.type === Tokenizer.START_TAG_TOKEN)
-        this._handleStartTagToken(token);
-
-    else if (token.type === Tokenizer.END_TAG_TOKEN)
-        this._handleEndTagToken(token);
-
-    else if (token.type === Tokenizer.NULL_CHARACTER_TOKEN && this.inForeignContent) {
-        token.type = Tokenizer.CHARACTER_TOKEN;
-        token.chars = UNICODE.REPLACEMENT_CHARACTER;
-    }
-
-    return token;
-};
-
-//Namespace stack mutations
-TokenizerProxy.prototype._enterNamespace = function (namespace) {
-    this.namespaceStackTop++;
-    this.namespaceStack.push(namespace);
-
-    this.inForeignContent = namespace !== NS.HTML;
-    this.currentNamespace = namespace;
-    this.tokenizer.allowCDATA = this.inForeignContent;
-};
-
-TokenizerProxy.prototype._leaveCurrentNamespace = function () {
-    this.namespaceStackTop--;
-    this.namespaceStack.pop();
-
-    this.currentNamespace = this.namespaceStack[this.namespaceStackTop];
-    this.inForeignContent = this.currentNamespace !== NS.HTML;
-    this.tokenizer.allowCDATA = this.inForeignContent;
-};
-
-//Token handlers
-TokenizerProxy.prototype._ensureTokenizerMode = function (tn) {
-    if (tn === $.TEXTAREA || tn === $.TITLE)
-        this.tokenizer.state = Tokenizer.MODE.RCDATA;
-
-    else if (tn === $.PLAINTEXT)
-        this.tokenizer.state = Tokenizer.MODE.PLAINTEXT;
-
-    else if (tn === $.SCRIPT)
-        this.tokenizer.state = Tokenizer.MODE.SCRIPT_DATA;
-
-    else if (tn === $.STYLE || tn === $.IFRAME || tn === $.XMP ||
-             tn === $.NOEMBED || tn === $.NOFRAMES || tn === $.NOSCRIPT) {
-        this.tokenizer.state = Tokenizer.MODE.RAWTEXT;
-    }
-};
-
-TokenizerProxy.prototype._handleStartTagToken = function (token) {
-    var tn = token.tagName;
-
-    if (tn === $.SVG)
-        this._enterNamespace(NS.SVG);
-
-    else if (tn === $.MATH)
-        this._enterNamespace(NS.MATHML);
-
-    else {
-        if (this.inForeignContent) {
-            if (ForeignContent.causesExit(token))
-                this._leaveCurrentNamespace();
-
-            else if (ForeignContent.isMathMLTextIntegrationPoint(tn, this.currentNamespace) ||
-                     ForeignContent.isHtmlIntegrationPoint(tn, this.currentNamespace, token.attrs)) {
-                this._enterNamespace(NS.HTML);
-            }
-        }
-
-        else
-            this._ensureTokenizerMode(tn);
-    }
-};
-
-TokenizerProxy.prototype._handleEndTagToken = function (token) {
-    var tn = token.tagName;
-
-    if (!this.inForeignContent) {
-        var previousNs = this.namespaceStack[this.namespaceStackTop - 1];
-
-        //NOTE: check for exit from integration point
-        if (ForeignContent.isMathMLTextIntegrationPoint(tn, previousNs) ||
-            ForeignContent.isHtmlIntegrationPoint(tn, previousNs, token.attrs)) {
-            this._leaveCurrentNamespace();
-        }
-
-        else if (tn === $.SCRIPT)
-            this.tokenizer.state = Tokenizer.MODE.DATA;
-    }
-
-    else if ((tn === $.SVG && this.currentNamespace === NS.SVG) ||
-             (tn === $.MATH && this.currentNamespace === NS.MATHML))
-        this._leaveCurrentNamespace();
-};
+'use strict';
+
+var Tokenizer = require('../tokenization/tokenizer'),
+    ForeignContent = require('../common/foreign_content'),
+    UNICODE = require('../common/unicode'),
+    HTML = require('../common/html');
+
+//Aliases
+var $ = HTML.TAG_NAMES,
+    NS = HTML.NAMESPACES;
+
+
+//Tokenizer proxy
+//NOTE: this proxy simulates adjustment of the Tokenizer which performed by standard parser during tree construction.
+var TokenizerProxy = module.exports = function (html, options) {
+    this.tokenizer = new Tokenizer(html, options);
+
+    this.namespaceStack = [];
+    this.namespaceStackTop = -1;
+    this.currentNamespace = null;
+    this.inForeignContent = false;
+};
+
+//API
+TokenizerProxy.prototype.getNextToken = function () {
+    var token = this.tokenizer.getNextToken();
+
+    if (token.type === Tokenizer.START_TAG_TOKEN)
+        this._handleStartTagToken(token);
+
+    else if (token.type === Tokenizer.END_TAG_TOKEN)
+        this._handleEndTagToken(token);
+
+    else if (token.type === Tokenizer.NULL_CHARACTER_TOKEN && this.inForeignContent) {
+        token.type = Tokenizer.CHARACTER_TOKEN;
+        token.chars = UNICODE.REPLACEMENT_CHARACTER;
+    }
+
+    return token;
+};
+
+//Namespace stack mutations
+TokenizerProxy.prototype._enterNamespace = function (namespace) {
+    this.namespaceStackTop++;
+    this.namespaceStack.push(namespace);
+
+    this.inForeignContent = namespace !== NS.HTML;
+    this.currentNamespace = namespace;
+    this.tokenizer.allowCDATA = this.inForeignContent;
+};
+
+TokenizerProxy.prototype._leaveCurrentNamespace = function () {
+    this.namespaceStackTop--;
+    this.namespaceStack.pop();
+
+    this.currentNamespace = this.namespaceStack[this.namespaceStackTop];
+    this.inForeignContent = this.currentNamespace !== NS.HTML;
+    this.tokenizer.allowCDATA = this.inForeignContent;
+};
+
+//Token handlers
+TokenizerProxy.prototype._ensureTokenizerMode = function (tn) {
+    if (tn === $.TEXTAREA || tn === $.TITLE)
+        this.tokenizer.state = Tokenizer.MODE.RCDATA;
+
+    else if (tn === $.PLAINTEXT)
+        this.tokenizer.state = Tokenizer.MODE.PLAINTEXT;
+
+    else if (tn === $.SCRIPT)
+        this.tokenizer.state = Tokenizer.MODE.SCRIPT_DATA;
+
+    else if (tn === $.STYLE || tn === $.IFRAME || tn === $.XMP ||
+             tn === $.NOEMBED || tn === $.NOFRAMES || tn === $.NOSCRIPT) {
+        this.tokenizer.state = Tokenizer.MODE.RAWTEXT;
+    }
+};
+
+TokenizerProxy.prototype._handleStartTagToken = function (token) {
+    var tn = token.tagName;
+
+    if (tn === $.SVG)
+        this._enterNamespace(NS.SVG);
+
+    else if (tn === $.MATH)
+        this._enterNamespace(NS.MATHML);
+
+    else {
+        if (this.inForeignContent) {
+            if (ForeignContent.causesExit(token))
+                this._leaveCurrentNamespace();
+
+            else if (ForeignContent.isMathMLTextIntegrationPoint(tn, this.currentNamespace) ||
+                     ForeignContent.isHtmlIntegrationPoint(tn, this.currentNamespace, token.attrs)) {
+                this._enterNamespace(NS.HTML);
+            }
+        }
+
+        else
+            this._ensureTokenizerMode(tn);
+    }
+};
+
+TokenizerProxy.prototype._handleEndTagToken = function (token) {
+    var tn = token.tagName;
+
+    if (!this.inForeignContent) {
+        var previousNs = this.namespaceStack[this.namespaceStackTop - 1];
+
+        //NOTE: check for exit from integration point
+        if (ForeignContent.isMathMLTextIntegrationPoint(tn, previousNs) ||
+            ForeignContent.isHtmlIntegrationPoint(tn, previousNs, token.attrs)) {
+            this._leaveCurrentNamespace();
+        }
+
+        else if (tn === $.SCRIPT)
+            this.tokenizer.state = Tokenizer.MODE.DATA;
+    }
+
+    else if ((tn === $.SVG && this.currentNamespace === NS.SVG) ||
+             (tn === $.MATH && this.currentNamespace === NS.MATHML))
+        this._leaveCurrentNamespace();
+};

package/lib/tokenization/location_info_mixin.js

@@ -1,80 +1,80 @@
-'use strict';
-
-exports.assign = function (tokenizer) {
-    //NOTE: obtain Tokenizer proto this way to avoid module circular references
-    var tokenizerProto = Object.getPrototypeOf(tokenizer);
-
-    tokenizer.tokenStartLoc = -1;
-
-    //NOTE: add location info builder method
-    tokenizer._attachLocationInfo = function (token) {
-        token.location = {
-            start: this.tokenStartLoc,
-            end: -1
-        };
-    };
-
-    //NOTE: patch token creation methods and attach location objects
-    tokenizer._createStartTagToken = function (tagNameFirstCh) {
-        tokenizerProto._createStartTagToken.call(this, tagNameFirstCh);
-        this._attachLocationInfo(this.currentToken);
-    };
-
-    tokenizer._createEndTagToken = function (tagNameFirstCh) {
-        tokenizerProto._createEndTagToken.call(this, tagNameFirstCh);
-        this._attachLocationInfo(this.currentToken);
-    };
-
-    tokenizer._createCommentToken = function () {
-        tokenizerProto._createCommentToken.call(this);
-        this._attachLocationInfo(this.currentToken);
-    };
-
-    tokenizer._createDoctypeToken = function (doctypeNameFirstCh) {
-        tokenizerProto._createDoctypeToken.call(this, doctypeNameFirstCh);
-        this._attachLocationInfo(this.currentToken);
-    };
-
-    tokenizer._createCharacterToken = function (type, ch) {
-        tokenizerProto._createCharacterToken.call(this, type, ch);
-        this._attachLocationInfo(this.currentCharacterToken);
-    };
-
-    //NOTE: patch token emission methods to determine end location
-    tokenizer._emitCurrentToken = function () {
-        //NOTE: if we have pending character tokenmake it's end location equal to the
-        //current token's start location.
-        if (this.currentCharacterToken)
-            this.currentCharacterToken.location.end = this.currentToken.location.start;
-
-        this.currentToken.location.end = this.preprocessor.pos + 1;
-        tokenizerProto._emitCurrentToken.call(this);
-    };
-
-    tokenizer._emitCurrentCharacterToken = function () {
-        //NOTE: if we have character token and it's location wasn't set in the _emitCurrentToken(),
-        //then set it's location at the current preprocessor position
-        if (this.currentCharacterToken && this.currentCharacterToken.location.end === -1) {
-            //NOTE: we don't need to increment preprocessor position here, since character token
-            //emission here is always forced by the start of the next token character token.
-            //So, we already have advanced position here.
-            this.currentCharacterToken.location.end = this.preprocessor.pos;
-        }
-
-        tokenizerProto._emitCurrentCharacterToken.call(this);
-    };
-
-    //NOTE: patch initial states for each mode to obtain token start position
-    Object.keys(tokenizerProto.MODE)
-
-        .map(function (modeName) {
-            return tokenizerProto.MODE[modeName];
-        })
-
-        .forEach(function (state) {
-            tokenizer[state] = function (cp) {
-                this.tokenStartLoc = this.preprocessor.pos;
-                tokenizerProto[state].call(this, cp);
-            };
-        });
-};
+'use strict';
+
+exports.assign = function (tokenizer) {
+    //NOTE: obtain Tokenizer proto this way to avoid module circular references
+    var tokenizerProto = Object.getPrototypeOf(tokenizer);
+
+    tokenizer.tokenStartLoc = -1;
+
+    //NOTE: add location info builder method
+    tokenizer._attachLocationInfo = function (token) {
+        token.location = {
+            start: this.tokenStartLoc,
+            end: -1
+        };
+    };
+
+    //NOTE: patch token creation methods and attach location objects
+    tokenizer._createStartTagToken = function (tagNameFirstCh) {
+        tokenizerProto._createStartTagToken.call(this, tagNameFirstCh);
+        this._attachLocationInfo(this.currentToken);
+    };
+
+    tokenizer._createEndTagToken = function (tagNameFirstCh) {
+        tokenizerProto._createEndTagToken.call(this, tagNameFirstCh);
+        this._attachLocationInfo(this.currentToken);
+    };
+
+    tokenizer._createCommentToken = function () {
+        tokenizerProto._createCommentToken.call(this);
+        this._attachLocationInfo(this.currentToken);
+    };
+
+    tokenizer._createDoctypeToken = function (doctypeNameFirstCh) {
+        tokenizerProto._createDoctypeToken.call(this, doctypeNameFirstCh);
+        this._attachLocationInfo(this.currentToken);
+    };
+
+    tokenizer._createCharacterToken = function (type, ch) {
+        tokenizerProto._createCharacterToken.call(this, type, ch);
+        this._attachLocationInfo(this.currentCharacterToken);
+    };
+
+    //NOTE: patch token emission methods to determine end location
+    tokenizer._emitCurrentToken = function () {
+        //NOTE: if we have pending character token make it's end location equal to the
+        //current token's start location.
+        if (this.currentCharacterToken)
+            this.currentCharacterToken.location.end = this.currentToken.location.start;
+
+        this.currentToken.location.end = this.preprocessor.pos + 1;
+        tokenizerProto._emitCurrentToken.call(this);
+    };
+
+    tokenizer._emitCurrentCharacterToken = function () {
+        //NOTE: if we have character token and it's location wasn't set in the _emitCurrentToken(),
+        //then set it's location at the current preprocessor position
+        if (this.currentCharacterToken && this.currentCharacterToken.location.end === -1) {
+            //NOTE: we don't need to increment preprocessor position, since character token
+            //emission is always forced by the start of the next character token here.
+            //So, we already have advanced position.
+            this.currentCharacterToken.location.end = this.preprocessor.pos;
+        }
+
+        tokenizerProto._emitCurrentCharacterToken.call(this);
+    };
+
+    //NOTE: patch initial states for each mode to obtain token start position
+    Object.keys(tokenizerProto.MODE)
+
+        .map(function (modeName) {
+            return tokenizerProto.MODE[modeName];
+        })
+
+        .forEach(function (state) {
+            tokenizer[state] = function (cp) {
+                this.tokenStartLoc = this.preprocessor.pos;
+                tokenizerProto[state].call(this, cp);
+            };
+        });
+};