예제 #1
0
 public boolean process(TextDocument doc) throws BoilerpipeProcessingException {
   return TerminatingBlocksFinder.INSTANCE.process(doc)
       | new DocumentTitleMatchClassifier(doc.getTitle()).process(doc)
       | NumWordsRulesClassifier.INSTANCE.process(doc)
       | IgnoreBlocksAfterContentFilter.DEFAULT_INSTANCE.process(doc)
       | BlockProximityFusion.MAX_DISTANCE_1.process(doc)
       | BoilerplateBlockFilter.INSTANCE.process(doc)
       | BlockProximityFusion.MAX_DISTANCE_1_CONTENT_ONLY.process(doc)
       | KeepLargestBlockFilter.INSTANCE.process(doc)
       | ExpandTitleToContentFilter.INSTANCE.process(doc);
 }
예제 #2
0
 public boolean process(TextDocument doc) throws BoilerpipeProcessingException {
   return TerminatingBlocksFinder.INSTANCE.process(doc)
       | new DocumentTitleMatchClassifier(doc.getTitle()).process(doc)
       | NumWordsRulesClassifier.INSTANCE.process(doc)
       | IgnoreBlocksAfterContentFilter.DEFAULT_INSTANCE.process(doc)
       | TrailingHeadlineToBoilerplateFilter.INSTANCE.process(doc)
       | BlockProximityFusion.MAX_DISTANCE_1.process(doc)
       | BoilerplateBlockFilter.INSTANCE_KEEP_TITLE.process(doc)
       | BlockProximityFusion.MAX_DISTANCE_1_CONTENT_ONLY_SAME_TAGLEVEL.process(doc)
       | KeepLargestBlockFilter.INSTANCE_EXPAND_TO_SAME_TAGLEVEL_MIN_WORDS.process(doc)
       | ExpandTitleToContentFilter.INSTANCE.process(doc)
       | LargeBlockSameTagLevelToContentFilter.INSTANCE.process(doc)
       | ListAtEndFilter.INSTANCE.process(doc);
 }