/[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 1.4 by wakaba, Sun Apr 20 12:19:13 2008 UTC revision 1.7 by wakaba, Fri Apr 25 23:03:35 2008 UTC
# Line 3  Line 3 
3  <head>  <head>
4  <title>Demo of HTML5 Parsing Algorithm with Scripting Enabled</title>  <title>Demo of HTML5 Parsing Algorithm with Scripting Enabled</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;
# Line 18  Line 23 
23    }    }
24  </style>  </style>
25  <script>  <script>
26      var delayedUpdater = 0;
27    
28    function update () {    function update () {
29        if (delayedUpdater) {
30          clearTimeout (delayedUpdater);
31          delayedUpdater = 0;
32        }
33        delayedUpdater = setTimeout (update2, 100);
34      } // update
35    
36      function update2 () {
37      document.logElement.textContent = '';      document.logElement.textContent = '';
38      var p = new Parser (new InputStream (document.sourceElement.value));      var v = document.sourceElement.value;
39        var p = new Parser (new InputStream (v));
40      var doc = p.doc;      var doc = p.doc;
41      p.parse ();      p.parse ();
42      log (dumpTree (doc, ''));      log (dumpTree (doc, ''));
   } // update  
43    
44        document.links['permalink'].href
45            = location.href + '?s=' + encodeURIComponent (v);
46      } // update2
47    
48      var logIndentLevel = 0;
49    function log (s) {    function log (s) {
50        for (var i = 0; i < logIndentLevel; i++) {
51          s = '  ' + s;
52        }
53      document.logElement.appendChild (document.createTextNode (s + "\n"));      document.logElement.appendChild (document.createTextNode (s + "\n"));
54    } // log    } // log
55    
# Line 77  Line 100 
100          return '';          return '';
101        });        });
102        if (token) return token;        if (token) return token;
103          var m;
104          if ((p.insertionPoint < '</script'.length) &&
105              (m = i.s.match (/^<\/([SCRIPTscript]+)/))) {
106            var v = m[1].substring (0, p.insertionPoint).toLowerCase ();
107            if (v == 'script'.substring (0, p.insertionPoint - '</'.length)) {
108              return {type: 'abort'};
109            }
110          }
111        i.s = i.s.replace (/^</,        i.s = i.s.replace (/^</,
112        function (s) {        function (s) {
113          token = {type: 'char', value: s};          token = {type: 'char', value: s};
# Line 88  Line 119 
119      }      }
120    
121      var token;      var token;
122      i.s = i.s.replace (/^<\/([^>]+)>/, function (s, e) {      i.s = i.s.replace (/^<\/([^>]+)(?:>|$)/, function (s, e) {
123        if (p.insertionPoint < s.length) {        if (p.insertionPoint < s.length ||
124              (p.insertionPoint <= s.length &&
125               s.substring (s.length - 1, 1) != '>')) {
126          token = {type: 'abort'};          token = {type: 'abort'};
127          return s;          return s;
128        }        }
# Line 98  Line 131 
131        return '';        return '';
132      });      });
133      if (token) return token;      if (token) return token;
134      i.s = i.s.replace (/^<([^>]+)>/, function (s, e) {      i.s = i.s.replace (/^<([^>]+)(?:>|$)/, function (s, e) {
135        if (p.insertionPoint < s.length) {        if (p.insertionPoint < s.length ||
136              (p.insertionPoint <= s.length &&
137               s.substring (s.length - 1, 1) != '>')) {
138          token = {type: 'abort'};          token = {type: 'abort'};
139          return s;          return s;
140        }        }
# Line 109  Line 144 
144          tagName = v.toLowerCase ();          tagName = v.toLowerCase ();
145          return '';          return '';
146        });        });
147        e = e.replace (/^\s*(\S+)\s*(?:=\s*"([^"]*)"|'([^']*)'|([^"']+))?/,        e = e.replace (/^\s*([^\s=]+)\s*(?:=\s*(?:"([^"]*)"|'([^']*)'|([^"']+)))?/,
148        function (x, attrName, attrValue1, attrValue2, attrValue3) {        function (x, attrName, attrValue1, attrValue2, attrValue3) {
149          attrs[attrName] = attrValue1 || attrValue2 || attrValue3;          v = attrValue1 || attrValue2 || attrValue3;
150            v = v.replace (/&quot;/g, '"').replace (/&apos;/g, "'")
151                .replace (/&amp;/g, '&');
152            attrs[attrName.toLowerCase ()] = v;
153          return '';          return '';
154        });        });
155          if (e.length) {
156            log ('Broken start tag: "' + e + '"');
157          }
158        token = {type: 'start-tag', value: tagName, attrs: attrs};        token = {type: 'start-tag', value: tagName, attrs: attrs};
159        p.insertionPoint -= s.length;        p.insertionPoint -= s.length;
160        return '';        return '';
# Line 144  Line 185 
185    } // getNextToken    } // getNextToken
186    
187    Parser.prototype.parse = function () {    Parser.prototype.parse = function () {
188      log ('start parsing');      logIndentLevel++;
189        log ('parse: start');
190    
191      while (true) {      while (true) {
192        var token = this.getNextToken ();        var token = this.getNextToken ();
# Line 212  Line 254 
254            this.openElements[this.openElements.length - 1].appendChild (el);            this.openElements[this.openElements.length - 1].appendChild (el);
255    
256            // 11. Let the insertion point have the value of the old ...            // 11. Let the insertion point have the value of the old ...
257    
258              oldInsertionPoint += this.insertionPoint;
259            this.setInsertionPoint (oldInsertionPoint);            this.setInsertionPoint (oldInsertionPoint);
260    
261            // 12. If there is a script that will execute as soon as ...            // 12. If there is a script that will execute as soon as ...
262                        while (this.scriptExecutedWhenParserResumes) {
263                // 12.1. If the tree construction stage is being called reentrantly
264                if (this.reentrant) {
265                  log ('parse: abort (reentrance)');
266                  logIndentLevel--;
267                  return;
268    
269                // 12.2. Otherwise
270                } else {
271                  // 1.
272                  var script = this.scriptExecutedWhenParserResumes;
273                  this.scriptExecutedWhenParserResumes = null;
274    
275                  // 2. Pause until the script has completed loading.
276                  //
277    
278                  // 3. Let the insertion point to just before the next input char.
279                  this.setInsertionPoint (0);
280    
281                  // 4. Execute the script.
282                  executeScript (this.doc, script);
283    
284                  // 5. Let the insertion point be undefined again.
285                  this.setInsertionPoint (undefined);
286    
287                  // 6. If there is once again a script that will execute ...
288                  //
289                }
290              }
291          } else {          } else {
292            var el = new JSElement (this.doc, token.value);            var el = new JSElement (this.doc, token.value);
293            this.openElements[this.openElements.length - 1].appendChild (el);            this.openElements[this.openElements.length - 1].appendChild (el);
# Line 236  Line 307 
307          break;          break;
308        } else if (token.type == 'abort') {        } else if (token.type == 'abort') {
309          log ('parse: abort');          log ('parse: abort');
310            logIndentLevel--;
311          return;          return;
312        }        }
313      }      }
# Line 270  Line 342 
342      // "delays tha load event" things has completed:      // "delays tha load event" things has completed:
343      // readyState = 'complete'      // readyState = 'complete'
344      log ('load event fired');      log ('load event fired');
345    
346        logIndentLevel--;
347    } // parse    } // parse
348    
349    Parser.prototype.setInsertionPoint = function (ip) {    Parser.prototype.setInsertionPoint = function (ip) {
# Line 303  Line 377 
377      e.parentNode = this;      e.parentNode = this;
378    
379      if (e.localName == 'script') {      if (e.localName == 'script') {
380          logIndentLevel++;
381        log ('Running a script: start');        log ('Running a script: start');
382    
383        var doc = this.ownerDocument || this;        var doc = this.ownerDocument || this;
# Line 321  Line 396 
396        if (e.manakaiAlreadyExecuted) {        if (e.manakaiAlreadyExecuted) {
397          // 2.5. Abort these steps at this point.          // 2.5. Abort these steps at this point.
398          log ('Running a script: aborted');          log ('Running a script: aborted');
399            logIndentLevel--;
400          return e;          return e;
401        }        }
402    
# Line 343  Line 419 
419                   /* && list of scripts that will execute asynchronously is not empty */) {                   /* && list of scripts that will execute asynchronously is not empty */) {
420          // TODO          // TODO
421        } else if (e.src != null && e.manakaiParserInserted) {        } else if (e.src != null && e.manakaiParserInserted) {
422          // TODO          if (p.scriptExecutedWhenParserResumes) {
423              log ('Error: There is a script that will execute as soon as the parser resumes.');
424            }
425            p.scriptExecutedWhenParserResumes = e;
426            log ('Running a script: aborted (src)');
427        } else if (e.src != null) {        } else if (e.src != null) {
428          // TODO          // TODO
429        } else {        } else {
# Line 351  Line 431 
431        }        }
432    
433        log ('Running a script: end');        log ('Running a script: end');
434          logIndentLevel--;
435      }      }
436    
437      return e;      return e;
# Line 359  Line 440 
440    function executeScript (doc, e) {    function executeScript (doc, e) {
441      log ('executing a script block: start');      log ('executing a script block: start');
442    
443      // If the load resulted in an error, then ... firing an error event ...      var s;
444        if (e.src != null) {
445          s = getExternalScript (e.src);
446    
447          // If the load resulted in an error, then ... firing an error event ...
448          if (s == null) {
449            log ('error event fired at the script element');
450            return;
451          }
452    
453          log ('External script loaded: "' + s + '"');
454        } else {
455          s = e.text;
456        }
457    
458      // If the load was successful      // If the load was successful
459      log ('load event fired at the script element');      log ('load event fired at the script element');
# Line 368  Line 462 
462      // Scripting is enabled, Document.designMode is disabled,      // Scripting is enabled, Document.designMode is disabled,
463      // Document is the active document in its browsing context      // Document is the active document in its browsing context
464    
       var s;  
       if (e.src != null) {  
         // TODO: from external file  
       } else {  
         s = e.text;  
       }  
   
465        parseAndRunScript (doc, s);        parseAndRunScript (doc, s);
466      }      }
467    
468      log ('executing a script block: end');      log ('executing a script block: end');
469    } // executeScript    } // executeScript
470    
471      function getExternalScript (uri) {
472        if (uri.match (/^javascript:/i)) {
473          var m;
474          if (m = uri.match (/^javascript:\s*(?:'([^']*)'|"([^"]+)")\s*$/i)) {
475            if (m[1]) {
476              return m[1];
477            } else if (m[2]) {
478              return m[2];
479            } else {
480              return null;
481            }
482          } else {
483            log ('Complex javascript: URI is not supported: <' + uri + '>');
484            return null;
485          }
486        } else {
487          log ('URI scheme not supported: <' + uri + '>');
488          return null;
489        }
490      } // getExternalScript
491    
492    function parseAndRunScript (doc, s) {    function parseAndRunScript (doc, s) {
493      while (true) {      while (true) {
494        var matched = false;        var matched = false;
# Line 470  Line 578 
578    }; // document.open    }; // document.open
579    
580    JSDocument.prototype.write = function () {    JSDocument.prototype.write = function () {
581        logIndentLevel++;
582    
583      var p = this._parser;      var p = this._parser;
584    
585      // 1. If the insertion point is undefined, the open() method must be ...      // 1. If the insertion point is undefined, the open() method must be ...
# Line 487  Line 597 
597      p.insertionPoint += s.length;      p.insertionPoint += s.length;
598    
599      // 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
600      // TODO      if (p.scriptExecutedAfterParserResumes) {
601          log ('document.write: processed later (there is an unprocessed <script src>)');
602          logIndentLevel--;
603          return;
604        }
605    
606      // 4. Process the characters that were inserted, ...      // 4. Process the characters that were inserted, ...
607        var originalReentrant = p.reentrant;
608        p.reentrant = true;
609      p.parse ();      p.parse ();
610        p.reentrant = originalReentrant;
611        // TODO: "Abort the processing of any nested invokations of the tokeniser,
612        // yielding control back to the caller." (<script> parsing).  Do we need
613        // to do something here?
614    
615      // 5. Return      // 5. Return
616      log ('document.write: return');      log ('document.write: return');
617    
618        logIndentLevel--;
619      return;      return;
620    }; // document.write    }; // document.write
621    
# Line 532  Line 654 
654    document.logElement = document.getElementsByTagName ('output')[0];    document.logElement = document.getElementsByTagName ('output')[0];
655    update ();    update ();
656  ">  ">
657    <h1>Live Scripting Parser</h1>
658    
659  <textarea onchange=" update () ">&lt;html>  <h2>Markup to test
660    (<a href=data:, id=permalink rel=bookmark>permalink</a>)</h2>
661    <p>
662    <textarea onkeydown=" update () " onchange=" update () " oninput=" update () ">&lt;html>
663  &lt;head>&lt;/head>&lt;body>  &lt;head>&lt;/head>&lt;body>
664  &lt;p>  &lt;p>
665  &lt;script>  &lt;script>
# Line 542  document.write ('aaaaaaa&lt;/p>&lt;scrip Line 668  document.write ('aaaaaaa&lt;/p>&lt;scrip
668  &lt;p>  &lt;p>
669  </textarea>  </textarea>
670    
671  <output></output>  <h2>Log</h2>
672    <p><output></output>
673    
674    <!-- TODO: short description -->
675    
676    <!-- TODO: permalink query -> textarea -->
677    
678    <!-- TODO: multiple attributes are not supported yet -->
679    
680  </body>  </body>
681  </html>  </html>
Legend:
Removed from v.1.4  
changed lines
  Added in v.1.7
admin@suikawiki.org
 ViewVC Help
Powered by ViewVC 1.1.24