/[suikacvs]/markup/html/scripting-parser/parser.html
Suika

Diff of /markup/html/scripting-parser/parser.html

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.2 by wakaba, Sun Apr 20 07:48:00 2008 UTC revision 1.11 by wakaba, Sun Apr 27 10:44:36 2008 UTC
# Line 1  Line 1 
1  <!DOCTYPE HTML>  <!DOCTYPE HTML>
2  <html lang=en>  <html lang=en>
3  <head>  <head>
4  <title>Demo of HTML5 Parsing Algorithm with Scripting Enabled</title>  <title>Live Scripting HTML Parser</title>
5  <style>  <style>
6      h1, h2 {
7        margin: 0;
8        font-size: 100%;
9      }
10      p, pre {
11        margin: 0;
12      }
13    textarea {    textarea {
14       display: block;      width: 100%;
15       width: 80%;      -width: 99%;
16       margin-left: auto;      height: 10em;
      margin-right: auto;  
      min-height: 20em;  
17    }    }
18    output {    output {
19      display: block;      display: block;
20      font-family: monospace;      font-family: monospace;
21      white-space: pre;      white-space: -moz-pre-wrap;
22        white-space: pre-wrap;
23    }    }
24  </style>  </style>
25  <script>  <script>
26      var delayedUpdater = 0;
27    
28    function update () {    function update () {
29      document.logElement.textContent = '';      if (delayedUpdater) {
30      var p = new Parser (new InputStream (document.sourceElement.value));        clearTimeout (delayedUpdater);
31      p.parse ();        delayedUpdater = 0;
32      log (dumpTree (p.doc, ''));      }
33        delayedUpdater = setTimeout (update2, 100);
34    } // update    } // update
35    
36      function update2 () {
37        var v = document.sourceElement.value;
38        if (v != document.previousSourceText) {
39          document.previousSourceText = v;
40          document.links['permalink'].href
41              = location.pathname + '?s=' + encodeURIComponent (v);
42          document.links['ldvlink'].href
43              = 'http://software.hixie.ch/utilities/js/live-dom-viewer/?'
44              + encodeURIComponent (v);
45    
46          document.logElement.textContent = '';
47          var p = new Parser (new InputStream (v));
48          var doc = p.doc;
49          p.parse ();
50          
51          log (dumpTree (doc, ''));
52          
53          if (p.hasAsyncScript) {
54            log ('Some script codes are executed asynchronously; it means that the document might be rendered in different ways depending on the network condition and other factors');
55          }
56        }
57      } // update2
58    
59      var logIndentLevel = 0;
60    function log (s) {    function log (s) {
61        for (var i = 0; i < logIndentLevel; i++) {
62          s = '  ' + s;
63        }
64      document.logElement.appendChild (document.createTextNode (s + "\n"));      document.logElement.appendChild (document.createTextNode (s + "\n"));
65    } // log    } // log
66    
# Line 32  Line 68 
68      this.s = s;      this.s = s;
69    } // InputStream    } // InputStream
70    
71    function Parser (i) {    function Parser (i, doc) {
72      this.parseMode = 'pcdata';      this.parseMode = 'pcdata';
73      this.doc = new JSDocument (this);      if (!doc) {
74      this.openElements = [this.doc];        doc = new JSDocument (this);
75      this.in = i;        doc.manakaiIsHTML = true;
76        }
77        this.doc = doc;
78        this.openElements = [doc];
79        this.input = i;
80        this.scriptsExecutedAfterParsing = [];
81        this.scriptsExecutedSoon = [];
82    } // Parser    } // Parser
83    
84    Parser.prototype.getNextToken = function () {    Parser.prototype.getNextToken = function () {
85      var i = this.in;      var p = this;
86        var i = this.input;
87      if (this.parseMode == 'script') {      if (this.parseMode == 'script') {
88        var token;        var token;
89        i.s = i.s.replace (/^([\s\S]+?)<\/[Ss][Cc][Rr][Ii][Pp][Tt]>/,        if (p.insertionPoint <= 0) {
90            return {type: 'abort'};
91          }
92          i.s = i.s.replace (/^([^<]+)/,
93        function (s, t) {        function (s, t) {
94            if (0 < p.insertionPoint && p.insertionPoint < t.length) {
95              token = {type: 'char', value: t.substring (0, p.insertionPoint)};
96              var ip = p.insertionPoint;
97              p.insertionPoint = 0;
98              return t.substring (ip, t.length);
99            }
100          token = {type: 'char', value: t};          token = {type: 'char', value: t};
101          return '<' + '/script>';          p.insertionPoint -= t.length;
102            return '';
103        });        });
104        if (token) return token;        if (token) return token;
105        i.s = i.s.replace (/^<\/[Ss][Cc][Rr][Ii][Pp][Tt]>/, function () {        i.s = i.s.replace (/^<\/[Ss][Cc][Rr][Ii][Pp][Tt]>/, function (s) {
106            if (p.insertionPoint < s.length) {
107              token = {type: 'abort'};
108              return s;
109            }
110          token = {type: 'end-tag', value: 'script'};          token = {type: 'end-tag', value: 'script'};
111            p.insertionPoint -= s.length;
112            return '';
113          });
114          if (token) return token;
115          var m;
116          if ((p.insertionPoint < '</script'.length) &&
117              (m = i.s.match (/^<\/([SCRIPTscript]+)/))) {
118            var v = m[1].substring (0, p.insertionPoint).toLowerCase ();
119            if (v == 'script'.substring (0, p.insertionPoint - '</'.length)) {
120              return {type: 'abort'};
121            }
122          }
123          i.s = i.s.replace (/^</,
124          function (s) {
125            token = {type: 'char', value: s};
126            p.insertionPoint -= s.length;
127          return '';          return '';
128        });        });
129        if (token) return token;        if (token) return token;
# Line 58  Line 131 
131      }      }
132    
133      var token;      var token;
134      i.s = i.s.replace (/^<\/([^>]+)>/, function (s, e) {      i.s = i.s.replace (/^<\/([^>]+)(?:>|$)/, function (s, e) {
135          if (p.insertionPoint < s.length ||
136              (p.insertionPoint <= s.length &&
137               s.substring (s.length - 1, 1) != '>')) {
138            token = {type: 'abort'};
139            return s;
140          }
141        token = {type: 'end-tag', value: e.toLowerCase ()};        token = {type: 'end-tag', value: e.toLowerCase ()};
142          p.insertionPoint -= s.length;
143        return '';        return '';
144      });      });
145      if (token) return token;      if (token) return token;
146      i.s = i.s.replace (/^<([^>]+)>/, function (s, e) {      i.s = i.s.replace (/^<([^>]+)(?:>|$)/, function (s, e) {
147        token = {type: 'start-tag', value: e.toLowerCase ()};        if (p.insertionPoint < s.length ||
148              (p.insertionPoint <= s.length &&
149               s.substring (s.length - 1, 1) != '>')) {
150            token = {type: 'abort'};
151            return s;
152          }
153          var tagName;
154          var attrs = {};
155          e = e.replace (/^[\S]+/, function (v) {
156            tagName = v.toLowerCase ();
157            return '';
158          });
159          while (true) {
160            var m = false;
161            e = e.replace (/^\s*([^\s=]+)\s*(?:=\s*(?:"([^"]*)"|'([^']*)'|([^"'\s]*)))?/,
162            function (x, attrName, attrValue1, attrValue2, attrValue3) {
163              v = attrValue1 || attrValue2 || attrValue3;
164              v = v.replace (/&quot;/g, '"').replace (/&apos;/g, "'")
165                  .replace (/&amp;/g, '&');
166              attrs[attrName.toLowerCase ()] = v;
167              m = true;
168              return '';
169            });
170            if (!m) break;
171          }
172          if (e.length) {
173            log ('Broken start tag: "' + e + '"');
174          }
175          token = {type: 'start-tag', value: tagName, attrs: attrs};
176          p.insertionPoint -= s.length;
177        return '';        return '';
178      });      });
179      if (token) return token;      if (token) return token;
180        if (p.insertionPoint <= 0) {
181          return {type: 'abort'};
182        }
183      i.s = i.s.replace (/^[^<]+/, function (s) {      i.s = i.s.replace (/^[^<]+/, function (s) {
184          if (p.insertionPoint < s.length) {
185            token = {type: 'char', value: s.substring (0, p.insertionPoint)};
186            var ip = p.insertionPoint;
187            p.insertionPoint = 0;
188            return s.substring (ip, s.length);
189          }
190        token = {type: 'char', value: s};        token = {type: 'char', value: s};
191          p.insertionPoint -= s.length;
192        return '';        return '';
193      });      });
194      if (token) return token;      if (token) return token;
195      i.s = i.s.replace (/^[\s\S]/, function (s) {      i.s = i.s.replace (/^[\s\S]/, function (s) {
196        token = {type: 'char', value: s};        token = {type: 'char', value: s};
197          p.insertionPoint -= s.length;
198        return '';        return '';
199      });      });
200      if (token) return token;      if (token) return token;
# Line 82  Line 202 
202    } // getNextToken    } // getNextToken
203    
204    Parser.prototype.parse = function () {    Parser.prototype.parse = function () {
205      log ('start parsing');      logIndentLevel++;
206        log ('parse: start');
207    
208      while (true) {      while (true) {
209        var token = this.getNextToken ();        var token = this.getNextToken ();
# Line 92  Line 213 
213          if (token.value == 'script') {          if (token.value == 'script') {
214            // 1. Create an element for the token in the HTML namespace.            // 1. Create an element for the token in the HTML namespace.
215            var el = new JSElement (this.doc, token.value);            var el = new JSElement (this.doc, token.value);
216              if (token.attrs.async != null) el.async = true;
217              if (token.attrs.defer != null) el.defer = true;
218              if (token.attrs.src != null) el.src = token.attrs.src;
219    
220            // 2. Mark the element as being "parser-inserted".            // 2. Mark the element as being "parser-inserted".
221            el.manakaiParserInserted = true;            el.manakaiParserInserted = true;
# Line 109  Line 233 
233                el.manakaiAppendText (token.value);                el.manakaiAppendText (token.value);
234    
235              // 4.2. Until it returns a token that is not a character token, or              // 4.2. Until it returns a token that is not a character token, or
236              // TODO: 4.3. Until it stops tokenising.              // until it stops tokenising.
237              } else if (token.type == 'eof' ||              } else if (token.type == 'eof' ||
238                         (token.type == 'end-tag' && token.value == 'script')) {                         (token.type == 'end-tag' && token.value == 'script') ||
239                           token.type == 'abort') {
240                // 6. Switched back to the PCDATA state.                // 6. Switched back to the PCDATA state.
241                this.parseMode = 'pcdata';                this.parseMode = 'pcdata';
242    
# Line 138  Line 263 
263            }            }
264    
265            // 9.1. Let the old insertion point have the same value as the ...            // 9.1. Let the old insertion point have the same value as the ...
266              var oldInsertionPoint = this.insertionPoint;
267            // 9.2. Let the insertion point be just before the next input ...            // 9.2. Let the insertion point be just before the next input ...
268              this.setInsertionPoint (0);
269    
270            // 10. Append the new element to the current node.            // 10. Append the new element to the current node.
271            this.openElements[this.openElements.length - 1].appendChild (el);            this.openElements[this.openElements.length - 1].appendChild (el);
272    
273            // 11. Let the insertion point have the value of the old ...            // 11. Let the insertion point have the value of the old ...
274    
275              oldInsertionPoint += this.insertionPoint;
276              this.setInsertionPoint (oldInsertionPoint);
277    
278            // 12. If there is a script that will execute as soon as ...            // 12. If there is a script that will execute as soon as ...
279                        while (this.scriptExecutedWhenParserResumes) {
280                // 12.1. If the tree construction stage is being called reentrantly
281                if (this.reentrant) {
282                  log ('parse: abort (reentrance)');
283                  logIndentLevel--;
284                  return;
285    
286                // 12.2. Otherwise
287                } else {
288                  // 1.
289                  var script = this.scriptExecutedWhenParserResumes;
290                  this.scriptExecutedWhenParserResumes = null;
291    
292                  // 2. Pause until the script has completed loading.
293                  //
294    
295                  // 3. Let the insertion point to just before the next input char.
296                  this.setInsertionPoint (0);
297    
298                  // 4. Execute the script.
299                  executeScript (this.doc, script);
300    
301                  // 5. Let the insertion point be undefined again.
302                  this.setInsertionPoint (undefined);
303    
304                  // 6. If there is once again a script that will execute ...
305                  //
306                }
307              }
308          } else {          } else {
309            var el = new JSElement (this.doc, token.value);            var el = new JSElement (this.doc, token.value);
310            this.openElements[this.openElements.length - 1].appendChild (el);            this.openElements[this.openElements.length - 1].appendChild (el);
# Line 161  Line 317 
317          } else {          } else {
318            log ('parse error: unmatched end tag: ' + token.value);            log ('parse error: unmatched end tag: ' + token.value);
319          }          }
320          } else if (token.type == 'char') {
321            this.openElements[this.openElements.length - 1].manakaiAppendText
322                (token.value);
323        } else if (token.type == 'eof') {        } else if (token.type == 'eof') {
324          break;          break;
325          } else if (token.type == 'abort') {
326            log ('parse: abort');
327            logIndentLevel--;
328            return;
329        }        }
330      }      }
331    
332      log ('stop parsing');      log ('stop parsing');
333    
334        // readyState = 'interactive'
335    
336        // "When a script completes loading" rules start applying.
337    
338        // List of scripts that will execute as soon as possible
339        for (var i = 0; i < this.scriptsExecutedSoon.length; i++) {
340          var e = this.scriptsExecutedSoon[i];
341    
342          // If it has completed loading
343          log ('Execute an external script not inserted by parser...');
344          executeScript (this.doc, e);
345    
346          // NOTE: It MAY be executed before the end of the parsing, according
347          // to the spec.
348          this.hasAsyncScript = true;
349        }
350    
351        // TODO: Handles
352        // "list of scripts that will execute asynchronously"
353    
354        // Handle "list of scripts that will execute when the document has finished
355        // parsing".
356        var list = this.scriptsExecutedAfterParsing;
357        while (list.length > 0) {
358          // TODO: break unless completed loading
359    
360          // Step 1.
361          //
362    
363          // Step 2. and Step 3.
364          log ('Executing a |defer|red script...');
365          executeScript (this.doc, list.shift ());
366    
367          // Step 4.
368        }
369    
370        log ('DOMContentLoaded event fired');
371    
372        // "delays tha load event" things has completed:
373        // readyState = 'complete'
374        log ('load event fired');
375    
376        logIndentLevel--;
377    } // parse    } // parse
378    
379      Parser.prototype.setInsertionPoint = function (ip) {
380        if (ip == undefined || ip == null || isNaN (ip)) {
381          log ('insertion point: set to undefined');
382          this.insertionPoint = undefined;
383        } else if (ip == this.input.s.length) {
384          log ('insertion point: end of file');
385          this.insertionPoint = ip;
386        } else {
387          log ('insertion point: set to ' + ip +
388               ' (before "' + this.input.s.substring (0, 10) + '")');
389          this.insertionPoint = ip;
390        }
391      }; // setInsertionPoint
392    
393    function JSDocument (p) {    function JSDocument (p) {
394      this.childNodes = [];      this.childNodes = [];
395      this._parser = p;      this._parser = p;
# Line 186  Line 407 
407      e.parentNode = this;      e.parentNode = this;
408    
409      if (e.localName == 'script') {      if (e.localName == 'script') {
410        log ('start running a script');        logIndentLevel++;
411          log ('Running a script: start');
412    
413        var doc = this.ownerDocument;        var doc = this.ownerDocument || this;
414        var p = doc._parser;        var p = doc._parser;
415    
416        // 1. Script type        // 1. Script type
# Line 203  Line 425 
425        // 2.4. If the script element has its "already executed" flag set        // 2.4. If the script element has its "already executed" flag set
426        if (e.manakaiAlreadyExecuted) {        if (e.manakaiAlreadyExecuted) {
427          // 2.5. Abort these steps at this point.          // 2.5. Abort these steps at this point.
428          log ('running a script: aborted');          log ('Running a script: aborted');
429            logIndentLevel--;
430          return e;          return e;
431        }        }
432    
# Line 218  Line 441 
441        // 5.1.        // 5.1.
442        if (/* TODO: If the document is still being parsed && */        if (/* TODO: If the document is still being parsed && */
443            e.defer && !e.async) {            e.defer && !e.async) {
444          // TODO          p.scriptsExecutedAfterParsing.push (e);
445            log ('Running a script: aborted (defer)');
446        } else if (e.async && e.src != null) {        } else if (e.async && e.src != null) {
447          // TODO          // TODO
448        } else if (e.async && e.src == null        } else if (e.async && e.src == null
449                   /* && list of scripts that will execute asynchronously is not empty */) {                   /* && list of scripts that will execute asynchronously is not empty */) {
450          // TODO          // TODO
451        } else if (e.src != null && e.manakaiParserInserted) {        } else if (e.src != null && e.manakaiParserInserted) {
452          // TODO          if (p.scriptExecutedWhenParserResumes) {
453              log ('Error: There is a script that will execute as soon as the parser resumes.');
454            }
455            p.scriptExecutedWhenParserResumes = e;
456            log ('Running a script: aborted (src parser-inserted)');
457        } else if (e.src != null) {        } else if (e.src != null) {
458          // TODO          p.scriptsExecutedSoon.push (e);
459            log ('Running a script: aborted (src)');
460        } else {        } else {
461          executeScript (doc, e); // even if other scripts are already executing.          executeScript (doc, e); // even if other scripts are already executing.
462        }        }
463    
464        log ('end running a script');        log ('Running a script: end');
465          logIndentLevel--;
466      }      }
467    
468      return e;      return e;
# Line 241  Line 471 
471    function executeScript (doc, e) {    function executeScript (doc, e) {
472      log ('executing a script block: start');      log ('executing a script block: start');
473    
474      // If the load resulted in an error, then ... firing an error event ...      var s;
475        if (e.src != null) {
476          s = getExternalScript (e.src);
477    
478          // If the load resulted in an error, then ... firing an error event ...
479          if (s == null) {
480            log ('error event fired at the script element');
481            return;
482          }
483    
484          log ('External script loaded: "' + s + '"');
485        } else {
486          s = e.text;
487        }
488    
489      // If the load was successful      // If the load was successful
490      log ('load event fired at the script element');      log ('load event fired at the script element');
# Line 250  Line 493 
493      // Scripting is enabled, Document.designMode is disabled,      // Scripting is enabled, Document.designMode is disabled,
494      // Document is the active document in its browsing context      // Document is the active document in its browsing context
495    
       var s;  
       if (e.src != null) {  
         // TODO: from external file  
       } else {  
         s = e.text;  
       }  
   
496        parseAndRunScript (doc, s);        parseAndRunScript (doc, s);
497      }      }
498    
499      log ('executing a script block: end');      log ('executing a script block: end');
500    } // executeScript    } // executeScript
501    
502      function getExternalScript (uri) {
503        if (uri.match (/^javascript:/i)) {
504          var m;
505          if (m = uri.match (/^javascript:\s*(?:'([^']*)'|"([^"]+)")\s*$/i)) {
506            if (m[1]) {
507              return unescapeJSLiteral (m[1]);
508            } else if (m[2]) {
509              return unescapeJSLiteral (m[2]);
510            } else {
511              return null;
512            }
513          } else {
514            log ('Complex javascript: URI is not supported: <' + uri + '>');
515            return null;
516          }
517        } else {
518          log ('URI scheme not supported: <' + uri + '>');
519          return null;
520        }
521      } // getExternalScript
522    
523    function parseAndRunScript (doc, s) {    function parseAndRunScript (doc, s) {
524      while (true) {      while (true) {
525        var matched = false;        var matched = false;
# Line 270  Line 527 
527          matched = true;          matched = true;
528          var args = [];          var args = [];
529          t.replace (/('[^']*'|"[^"]*")/g, function (s, v) {          t.replace (/('[^']*'|"[^"]*")/g, function (s, v) {
530            args.push (v.substring (1, v.length - 1));            args.push (unescapeJSLiteral (v.substring (1, v.length - 1)));
531            return '';            return '';
532          });          });
533          doc.write.apply (doc, args);          doc.write.apply (doc, args);
534          return '';          return '';
535        });        });
536          s = s.replace (/^\s*var\s+s\s*=\s*document\.createElement\s*\(\s*['"]script['"]\s*\)\s*;\s*s\.src\s*=\s*(?:'(javascript:[^']*)'|"(javascript:[^"]*)")\s*;\s*document\.documentElement\.appendChild\s*\(\s*s\s*\)\s*;\s*/,
537          function (s, t, u) {
538            matched = true;
539            var args = [unescapeJSLiteral (t ? t : u)];
540            doc._insertExternalScript.apply (doc, args);
541            return '';
542          });
543        if (s == '') break;        if (s == '') break;
544        if (!matched) {        if (!matched) {
545          log ('Script parse error: "' + s + '"');          log ('Script parse error: "' + s + '"');
# Line 284  Line 548 
548      }      }
549    } // parseAndRunScript    } // parseAndRunScript
550    
551      function unescapeJSLiteral (s) {
552        return s.replace (/\\u([0-9A-Fa-f]{4})/g, function (t, v) {
553          return String.fromCharCode (parseInt ('0x' + v));
554        });
555      } // unescapeJSLiteral
556    
557    function JSText (data) {    function JSText (data) {
558      this.data = data;      this.data = data;
559    } // JSText    } // JSText
# Line 299  Line 569 
569      }      }
570    }; // manakaiAppendText    }; // manakaiAppendText
571    
572      JSDocument.prototype.open = function () {
573        // Two or fewer arguments
574    
575        // Step 1.
576        var type = arguments[0] || 'text/html';
577        
578        // Step 2.
579        var replace = arguments[1] == 'replace';
580    
581        // Step 3.
582        if (this._parser &&
583            !this._parser.scriptCreated &&
584            this._parser.input.insertionPoint != undefined) {
585          log ('document.open () in parsing mode is ignored');
586          return this;
587        }
588    
589        // Step 4.
590        log ('onbeforeunload event fired');
591        log ('onunload event fired');
592    
593        // Step 5.
594        if (this._parser) {
595          // Discard the parser.
596        }
597    
598        // Step 6.
599        log ('document cleared by document.open ()');
600        this.childNodes = [];
601    
602        // Step 7.
603        this._parser = new Parser (new InputStream (''), this);
604        this._parser.scriptCreated = true;
605    
606        // Step 8.
607        this.manakaiIsHTML = true;
608    
609        // Step 9.
610        // If not text/html, ...
611    
612        // Step 10.
613        if (!replace) {
614          // History      
615        }
616    
617        // Step 11.
618        this._parser.setInsertionPoint (this._parser.input.s.length);
619    
620        // Step 12.
621        return this;
622      }; // document.open
623    
624    JSDocument.prototype.write = function () {    JSDocument.prototype.write = function () {
625        logIndentLevel++;
626    
627        var p = this._parser;
628    
629      // 1. If the insertion point is undefined, the open() method must be ...      // 1. If the insertion point is undefined, the open() method must be ...
630      //      if (isNaN (p.insertionPoint) || p.insertionPoint == undefined) {
631          this.open ();
632          p = this._parser;
633        }
634    
635      // 2. ... inserted into the input stream just before the insertion point.      // 2. ... inserted into the input stream just before the insertion point.
636      log ('document.write: insert "' + Array.join (arguments, '') + '"');      var s = Array.join (arguments, '');
637        log ('document.write: insert "' + s + '"' +
638             ' before "' +
639             p.input.s.substring (p.insertionPoint, p.insertionPoint + 10) + '"');
640        p.input.s = p.input.s.substring (0, p.insertionPoint) + s
641            + p.input.s.substring (p.insertionPoint, p.input.s.length);
642        p.insertionPoint += s.length;
643    
644      // 3. If there is a script that will execute as soon as the parser resumes      // 3. If there is a script that will execute as soon as the parser resumes
645      // TODO      if (p.scriptExecutedAfterParserResumes) {
646          log ('document.write: processed later (there is an unprocessed <script src>)');
647          logIndentLevel--;
648          return;
649        }
650    
651      // 4. Process the characters that were inserted, ...      // 4. Process the characters that were inserted, ...
652        var originalReentrant = p.reentrant;
653        p.reentrant = true;
654        p.parse ();
655        p.reentrant = originalReentrant;
656        // TODO: "Abort the processing of any nested invokations of the tokeniser,
657        // yielding control back to the caller." (<script> parsing).  Do we need
658        // to do something here?
659    
660      // 5. Return      // 5. Return
661      log ('document.write: return');      log ('document.write: return');
662    
663        logIndentLevel--;
664      return;      return;
665    }; // document.write    }; // document.write
666    
667      JSDocument.prototype._insertExternalScript = function (uri) {
668        var s = new JSElement (this, 'script');
669        s.src = uri;
670        this.documentElement.appendChild (s);
671      }; // _insertExternalScript
672    
673      JSDocument.prototype.__defineGetter__ ('documentElement', function () {
674        var cn = this.childNodes;
675        for (var i = 0; i < cn.length; i++) {
676          if (cn[i] instanceof JSElement) {
677            return cn[i]
678          }
679        }
680        return null;
681      });
682    
683    JSElement.prototype.__defineGetter__ ('text', function () {    JSElement.prototype.__defineGetter__ ('text', function () {
684      var r = '';      var r = '';
685      for (var i = 0; i < this.childNodes.length; i++) {      for (var i = 0; i < this.childNodes.length; i++) {
# Line 332  Line 696 
696        var node = n.childNodes[i];        var node = n.childNodes[i];
697        if (node instanceof JSElement) {        if (node instanceof JSElement) {
698          r += '| ' + indent + node.localName + '\n';          r += '| ' + indent + node.localName + '\n';
699            if (node.async) r += '| ' + indent + '  async=""\n';
700            if (node.defer) r += '| ' + indent + '  defer=""\n';
701            if (node.src != null) {
702              r += '| ' + indent + '  src="' + node.src + '"\n';
703            }
704          r += dumpTree (node, indent + '  ');          r += dumpTree (node, indent + '  ');
705        } else if (node instanceof JSText) {        } else if (node instanceof JSText) {
706          r += '| ' + indent + '"' + node.data + '"\n';          r += '| ' + indent + '"' + node.data + '"\n';
# Line 345  Line 714 
714  </head>  </head>
715  <body onload="  <body onload="
716    document.sourceElement = document.getElementsByTagName ('textarea')[0];    document.sourceElement = document.getElementsByTagName ('textarea')[0];
717    
718      var q = location.search;
719      if (q != null) {
720        q = q.substring (1).split (/;/);
721        for (var i = 0; i < q.length; i++) {
722          var v = q[i].split (/=/, 2);
723          v[0] = decodeURIComponent (v[0]);
724          v[1] = decodeURIComponent (v[1] || '');
725          if (v[0] == 's') {
726            document.sourceElement.value = v[1];
727          }
728        }
729      }
730    
731    document.logElement = document.getElementsByTagName ('output')[0];    document.logElement = document.getElementsByTagName ('output')[0];
732    update ();    update ();
733  ">  ">
734    <h1>Live Scripting <abbr title="Hypertext Markup Language">HTML</abbr>
735    Parser</h1>
736    
737  <textarea onchange=" update () ">&lt;html>  <h2>Markup to test
738    (<a href=data:, id=permalink rel=bookmark>permalink</a>,
739    <a href="http://software.hixie.ch/utilities/js/live-dom-viewer/"
740        id=ldvlink>Live <abbr title="Document Object Model">DOM</abbr>
741        Viewer</a>)</h2>
742    <p>
743    <textarea onkeydown=" update () " onchange=" update () " oninput=" update () ">&lt;html>
744  &lt;head>&lt;/head>&lt;body>  &lt;head>&lt;/head>&lt;body>
745  &lt;p>  &lt;p>
746  &lt;script>  &lt;script>
747  document.write ('aaaaaaa&lt;/p>\n&lt;script>\ndocument.write("cccccc")\n&lt;/', 'script>\nbbbbbb');  document.write ('aaaaaaa&lt;/p>&lt;script>document.write("cccccc");&lt;/', 'script>bbbbbb');
748  &lt;/script>  &lt;/script>
749  &lt;p>  &lt;p>
750  </textarea>  </textarea>
751    
752  <output></output>  <h2 id=log>Log</h2>
753    <p><output></output>
754    
755    <h2 id=notes>Notes</h2>
756    
757    <p>This is a <em>simplified</em> implementation of
758    <a href="http://www.whatwg.org/specs/web-apps/current-work/#parsing">HTML5
759    Parsing Algorithm</a>.  It only implements script-related part of the
760    algorithm.  Especially, this parser:
761    <ul>
762    <li>Does not support <code>DOCTYPE</code> and comment tokens.
763    <li>Does not support entities except for <code>&amp;quot;</code>,
764    <code>&amp;apos;</code>, and <code>&amp;amp;</code> in <code>script</code>
765    <code>src</code> attribute value.
766    <li>Does not support omissions of start or end tags, the <abbr>AAA</abbr>
767    algorithm, and so on.
768    <li>Does not raise parse errors for invalid attribute specifications in start
769    or end tags.
770    <li>Does not support CDATA/PCDATA element other than <code>script</code>.
771    <li>Does not support <code>&lt;!--</code>..<code>--></code> parsing rule
772    in <code>script</code> element.
773    <li>Does not support foreign (SVG or MathML) elements.
774    <li>Only supports <code>script</code> <code>type</code>
775    <code>text/javascript</code>.  <code>type</code> and <code>language</code>
776    attributes are ignored.
777    <li>Only supports limited statements.  It must consist of zero or more
778    of statements looking similar to the following statements, possibly
779    introduced, followed, or separated by white space characters:
780      <ul>
781      <li><code>document.write ("<var>string</var>", ["<var>string</var>", ...]);</code>.
782      <li><code>var s = document.createElement ("script");
783                s.src = "<var>string</var>";
784                document.documentElement.appendChild (s);</code>
785      </ul>
786    Note that strings may be delimited by <code>'</code>s instead of
787    <code>"</code>s.
788    <li>Only supports <code>javascript:</code>
789    <abbr title="Uniform Resourace Identifiers">URI</abbr> scheme in the
790    <code>src</code> attribute of the <code>script</code> element.  In addition,
791    the <abbr title="Uniform Resource Identifiers">URI</abbr> must be conform to
792    the regular expression <code>^javascript:\s*(?:"[^"]*"|'[^']*')\s*$</code>.
793    <li>Only supports <code>\u<var>HHHH</var></code> escapes in JavaScript
794    string literals.
795    </ul>
796    
797    <p>For some reason, this parser does not work in browsers that do
798    not support JavaScript 1.5.
799    
800    <!-- TODO: license -->
801    
802  </body>  </body>
803  </html>  </html>
Legend:
Removed from v.1.2  
changed lines
  Added in v.1.11
admin@suikawiki.org
 ViewVC Help
Powered by ViewVC 1.1.24