Package com.ikanow.infinit.e.harvest.enrichment.custom

Examples of com.ikanow.infinit.e.harvest.enrichment.custom.UnstructuredAnalysisHarvester

1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
    }//(only only)
  }//TESTED (fullText_docMetaTests.json, import_lookups_test_uahSah)
 
  protected void requiresUnstructuredAnalysis() {
    if (null == _uah) {
      _uah = new UnstructuredAnalysisHarvester();
      _uah.setContext(_hc);
     
      if (null != _sah) {
        _sah.addUnstructuredHandler(_uah);
      }
View Full Code Here
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
          }//TOTEST
          else if (null != searchDoc.getMetadata()){
            savedMeta = searchDoc.getMetadata().remove("searchEngineSubsystem");
              // (this is normally null)
          }//TOTEST
          UnstructuredAnalysisHarvester dummyUAH = new UnstructuredAnalysisHarvester();
          boolean bMoreDocs = (nPage < nMaxPages - 1);
          Object[] searchResults = null;
          try {
            dummyUAH.executeHarvest(context, src, searchDoc, false, bMoreDocs);
              // (the leading false means that we never sleep *before* the query, only after)
            searchResults = searchDoc.getMetaData().get("searchEngineSubsystem");
          }
          finally {
            if (null != savedMeta) { // (this is really obscure but handle the case where someone has created this meta field already)
View Full Code Here
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
  //

  private void enrichSource(SourcePojo source, List<DocumentPojo> toAdd, List<DocumentPojo> toUpdate, List<DocumentPojo> toRemove)
  {
    StructuredAnalysisHarvester sah = null;
    UnstructuredAnalysisHarvester usah = null;

    // Create metadata from the text using regex (also calculate header/footer information if desired)
    if (source.getUnstructuredAnalysisConfig() != null)
    {
      usah = new UnstructuredAnalysisHarvester();

      // If performing structured analysis also then need to mux them
      // since the UAH will run on the body/description potentially created by the SAH
      // and the SAH will take the metadata generated by UAH to create entities and events
      if (source.getStructuredAnalysisConfig() != null) {
        sah = new StructuredAnalysisHarvester();
        sah.addUnstructuredHandler(usah);
      }
      else {
        toAdd = usah.executeHarvest(this, source, toAdd);
      }
    }

    // For sources that generate structured data, we can turn that into entities and events
    // and fill in document fields from the metadata (that can be used by entity extraction)
View Full Code Here
TOP

Related Classes of com.ikanow.infinit.e.harvest.enrichment.custom.UnstructuredAnalysisHarvester

  • com.google.gson.Gson
  • com.google.gson.GsonBuilder
  • com.google.gson.stream.JsonReader
  • com.ikanow.infinit.e.data_model.store.config.source.SimpleTextCleanserPojo
  • com.ikanow.infinit.e.data_model.store.config.source.SourcePojo
  • com.ikanow.infinit.e.data_model.store.config.source.SourceRssConfigPojo
  • com.ikanow.infinit.e.data_model.store.config.source.UnstructuredAnalysisConfigPojo
  • com.ikanow.infinit.e.data_model.store.document.DocumentPojo
  • com.ikanow.infinit.e.harvest.extraction.document.file.JsonToMetadataParser
  • com.ikanow.infinit.e.harvest.extraction.document.file.XmlToMetadataParser
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.