mediawiki-extensions-Visual.../modules/parser/mediawiki.HTML5TreeBuilder.node.js
Gabriel Wicke 8368e17d6a Biggish token transform system refactoring
* All parser pipelines including tokenizer and DOM stuff are now constructed
  from a 'recipe' data structure in a ParserPipelineFactory.

* All sub-pipelines of these can now be cached

* Event registrations to a pipeline are directly forwarded to the last
  pipeline member to save relatively expensive event forwarding.

* Some APIs for on-demand expansion / format conversion of parameters from
  parser functions are added:

  param.to('tokens/expanded', cb)
  param.to('text/wiki', cb) (this does not work yet)

  All parameters are additionally wrapped into a Param object that provides
  method for positional parameter naming (.named() or conversion to a dict
  (.dict()).

* The async token transform manager is now separated from a frame object, with
  the frame holding arguments, an on-demand expansion method and loop checks.

* Only keys of template parameters are now expanded. Parser functions or
  template arguments trigger an expansion on-demand. This (unsurprisingly)
  makes a big performance difference with typical switch-heavy template
  systems.

* Return values from async transforms are no longer used in favor of plain
  callbacks. This saves the complication of having to maintain two code paths.
  A trick in transformTokens still avoids the construction of unneeded
  TokenAccumulators.

* The results of template expansions are no longer buffered.

* 301 parser tests are passing

Known issues:

* Cosmetic cleanup remains to do
* Some parser functions do not support async expansions yet, and need to be
  modified.

Change-Id: I1a7690baffbe8141cadf67270904a1b2e1df879a
2012-04-25 16:51:36 +02:00

142 lines
3.9 KiB
JavaScript

/* Front-end/Wrapper for a particular tree builder, in this case the
* parser/tree builder from the node 'html5' module. Feed it tokens using
* processToken, and it will build you a DOM tree retrievable using .document
* or .body(). */
var events = require('events'),
HTML5 = require('./html5/index');
FauxHTML5 = {};
FauxHTML5.TreeBuilder = function ( env ) {
// The parser we are going to emit our tokens to
this.parser = new HTML5.Parser();
// Sets up the parser
this.parser.parse(this);
// implicitly start a new document
this.processToken(new TagTk( 'body' ));
this.env = env;
};
// Inherit from EventEmitter
FauxHTML5.TreeBuilder.prototype = new events.EventEmitter();
FauxHTML5.TreeBuilder.prototype.constructor = FauxHTML5.TreeBuilder;
/**
* Register for (token) 'chunk' and 'end' events from a token emitter,
* normally the TokenTransformDispatcher.
*/
FauxHTML5.TreeBuilder.prototype.addListenersOn = function ( emitter ) {
emitter.addListener('chunk', this.onChunk.bind( this ) );
emitter.addListener('end', this.onEnd.bind( this ) );
};
FauxHTML5.TreeBuilder.prototype.onChunk = function ( tokens ) {
this.env.dp( 'chunk: ' + JSON.stringify( tokens, null, 2 ) );
for (var i = 0, length = tokens.length; i < length; i++) {
this.processToken(tokens[i]);
}
};
FauxHTML5.TreeBuilder.prototype.onEnd = function ( ) {
//console.warn('Fauxhtml5 onEnd');
// FIXME HACK: For some reason the end token is not processed sometimes,
// which normally fixes the body reference up.
var document = this.parser.document;
document.body = document.getElementsByTagName('body')[0];
//console.warn( 'onEnd: ' + document.body.innerHTML );
this.emit( 'document', document );
// XXX: more clean up to allow reuse.
this.parser.setup();
this.processToken(new TagTk( 'body' ));
};
FauxHTML5.TreeBuilder.prototype._att = function (maybeAttribs) {
var atts = [];
if ( maybeAttribs && $.isArray( maybeAttribs ) ) {
for(var i = 0, length = maybeAttribs.length; i < length; i++) {
var att = maybeAttribs[i];
atts.push({nodeName: att.k, nodeValue: att.v});
}
}
return atts;
};
// Adapt the token format to internal HTML tree builder format, call the actual
// html tree builder by emitting the token.
FauxHTML5.TreeBuilder.prototype.processToken = function (token) {
if ( token.dataAttribs ) {
if ( ! token.attribs ) {
token.attribs = [];
}
token.attribs.push(
{
// Mediawiki-specific round-trip / non-semantic information
k: 'data-mw',
v: JSON.stringify( token.dataAttribs )
} );
}
switch( token.constructor ) {
case String:
this.emit('token', {type: 'Characters', data: token});
break;
case NlTk:
break;
case TagTk:
this.emit('token', {type: 'StartTag',
name: token.name,
data: this._att(token.attribs)});
break;
case SelfclosingTagTk:
this.emit('token', {type: 'StartTag',
name: token.name,
data: this._att(token.attribs)});
if ( HTML5.VOID_ELEMENTS.indexOf( token.name.toLowerCase() ) < 0 ) {
// VOID_ELEMENTS are automagically treated as self-closing by
// the tree builder
this.emit('token', {type: 'EndTag',
name: token.name,
data: this._att(token.attribs)});
}
break;
case EndTagTk:
this.emit('token', {type: 'EndTag',
name: token.name,
data: this._att(token.attribs)});
break;
case CommentTk:
this.emit('token', {type: 'Comment',
data: token.value});
break;
case EOFTk:
this.emit('end');
this.emit('token', { type: 'EOF' } );
this.document = this.parser.document;
if ( ! this.document.body ) {
// HACK: This should not be needed really.
this.document.body = this.parser.document.getElementsByTagName('body')[0];
}
// Emit the document to consumers
//this.emit('document', this.document);
break;
default:
console.warn("Unhandled token: " + JSON.stringify(token));
break;
break;
}
};
if (typeof module == "object") {
module.exports.FauxHTML5 = FauxHTML5;
}