/[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 1.8 by wakaba, Sun Apr 27 08:56:34 2008 UTC revision 1.11 by wakaba, Sun Apr 27 10:44:36 2008 UTC
# Line 47  Line 47 
47        var p = new Parser (new InputStream (v));        var p = new Parser (new InputStream (v));
48        var doc = p.doc;        var doc = p.doc;
49        p.parse ();        p.parse ();
50          
51        log (dumpTree (doc, ''));        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    } // update2
58    
# Line 73  Line 78 
78      this.openElements = [doc];      this.openElements = [doc];
79      this.input = i;      this.input = i;
80      this.scriptsExecutedAfterParsing = [];      this.scriptsExecutedAfterParsing = [];
81        this.scriptsExecutedSoon = [];
82    } // Parser    } // Parser
83    
84    Parser.prototype.getNextToken = function () {    Parser.prototype.getNextToken = function () {
# Line 150  Line 156 
156          tagName = v.toLowerCase ();          tagName = v.toLowerCase ();
157          return '';          return '';
158        });        });
159        e = e.replace (/^\s*([^\s=]+)\s*(?:=\s*(?:"([^"]*)"|'([^']*)'|([^"']+)))?/,        while (true) {
160        function (x, attrName, attrValue1, attrValue2, attrValue3) {          var m = false;
161          v = attrValue1 || attrValue2 || attrValue3;          e = e.replace (/^\s*([^\s=]+)\s*(?:=\s*(?:"([^"]*)"|'([^']*)'|([^"'\s]*)))?/,
162          v = v.replace (/"/g, '"').replace (/'/g, "'")          function (x, attrName, attrValue1, attrValue2, attrValue3) {
163              .replace (/&/g, '&');            v = attrValue1 || attrValue2 || attrValue3;
164          attrs[attrName.toLowerCase ()] = v;            v = v.replace (/"/g, '"').replace (/'/g, "'")
165          return '';                .replace (/&/g, '&');
166        });            attrs[attrName.toLowerCase ()] = v;
167              m = true;
168              return '';
169            });
170            if (!m) break;
171          }
172        if (e.length) {        if (e.length) {
173          log ('Broken start tag: "' + e + '"');          log ('Broken start tag: "' + e + '"');
174        }        }
# Line 324  Line 335 
335    
336      // "When a script completes loading" rules start applying.      // "When a script completes loading" rules start applying.
337    
338      // TODO: Handles "list of scripts that will execute as soon as possible"      // List of scripts that will execute as soon as possible
339      // and "list of scripts that will execute asynchronously"      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      // Handle "list of scripts that will execute when the document has finished
355      // parsing".      // parsing".
# Line 429  Line 453 
453            log ('Error: There is a script that will execute as soon as the parser resumes.');            log ('Error: There is a script that will execute as soon as the parser resumes.');
454          }          }
455          p.scriptExecutedWhenParserResumes = e;          p.scriptExecutedWhenParserResumes = e;
456          log ('Running a script: aborted (src)');          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        }        }
# Line 479  Line 504 
504        var m;        var m;
505        if (m = uri.match (/^javascript:\s*(?:'([^']*)'|"([^"]+)")\s*$/i)) {        if (m = uri.match (/^javascript:\s*(?:'([^']*)'|"([^"]+)")\s*$/i)) {
506          if (m[1]) {          if (m[1]) {
507            return m[1];            return unescapeJSLiteral (m[1]);
508          } else if (m[2]) {          } else if (m[2]) {
509            return m[2];            return unescapeJSLiteral (m[2]);
510          } else {          } else {
511            return null;            return null;
512          }          }
# Line 502  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 516  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 626  Line 664 
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 644  Line 698 
698          r += '| ' + indent + node.localName + '\n';          r += '| ' + indent + node.localName + '\n';
699          if (node.async) r += '| ' + indent + '  async=""\n';          if (node.async) r += '| ' + indent + '  async=""\n';
700          if (node.defer) r += '| ' + indent + '  defer=""\n';          if (node.defer) r += '| ' + indent + '  defer=""\n';
701          if (node.src) r += '| ' + indent + '  src="' + node.src + '"\n';          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 693  document.write ('aaaaaaa&lt;/p>&lt;scrip Line 749  document.write ('aaaaaaa&lt;/p>&lt;scrip
749  &lt;p>  &lt;p>
750  </textarea>  </textarea>
751    
752  <h2>Log</h2>  <h2 id=log>Log</h2>
753  <p><output></output>  <p><output></output>
754    
755  <h2>Note</h2>  <h2 id=notes>Notes</h2>
756    
757  <p>This is a <em>simplified</em> implementation of  <p>This is a <em>simplified</em> implementation of
758  <a href="http://www.whatwg.org/specs/web-apps/current-work/#parsing">HTML5  <a href="http://www.whatwg.org/specs/web-apps/current-work/#parsing">HTML5
# Line 718  in <code>script</code> element. Line 774  in <code>script</code> element.
774  <li>Only supports <code>script</code> <code>type</code>  <li>Only supports <code>script</code> <code>type</code>
775  <code>text/javascript</code>.  <code>type</code> and <code>language</code>  <code>text/javascript</code>.  <code>type</code> and <code>language</code>
776  attributes are ignored.  attributes are ignored.
777  <li>Only supports <code>document.write</code>.  <li>Only supports limited statements.  It must consist of zero or more
778  The script code must be match to the regular expression  of statements looking similar to the following statements, possibly
779  <code>^\s*(?:document\.write\s*\(<var>v</var>\s*(?:,\s*<var>v</var>\s*)*\)\s*;\s*)*$</code>  introduced, followed, or separated by white space characters:
780  where <var>v</var> is <code>"[^"]*"|'[^']*'</code>.    <ul>
781      <li><code>document.write ("<var>string</var>", ["<var>string</var>", ...]);</code>.
782      <li><code>var s = document.createElement ("script");
783                s.src = "<var>string</var>";
784                document.documentElement.appendChild (s);</code>
785      </ul>
786    Note that strings may be delimited by <code>'</code>s instead of
787    <code>"</code>s.
788  <li>Only supports <code>javascript:</code>  <li>Only supports <code>javascript:</code>
789  <abbr title="Uniform Resourace Identifiers">URI</abbr> scheme in the  <abbr title="Uniform Resourace Identifiers">URI</abbr> scheme in the
790  <code>src</code> attribute of the <code>script</code> element.  In addition,  <code>src</code> attribute of the <code>script</code> element.  In addition,
791  the <abbr title="Uniform Resource Identifiers">URI</abbr> must be conform to  the <abbr title="Uniform Resource Identifiers">URI</abbr> must be conform to
792  the regular expression <code>^javascript:\s*(?:"[^"]*"|'[^']*')\s*$</code>.  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>  </ul>
796    
797  <p>For some reason, this parser does not work in browsers that do  <p>For some reason, this parser does not work in browsers that do
798  not support JavaScript 1.5.  not support JavaScript 1.5.
799    
800  <!-- TODO: multiple attributes are not supported yet -->  <!-- TODO: license -->
801    
802  </body>  </body>
803  </html>  </html>
Legend:
Removed from v.1.8  
changed lines
  Added in v.1.11
admin@suikawiki.org
 ViewVC Help
Powered by ViewVC 1.1.24