Package it.unimi.dsi.io

Examples of it.unimi.dsi.io.WordReader

100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
      for ( int f = 0; f < seq.factory().numberOfFields(); f++ ) {
        System.out.println( "** Field # " + f + ", " + seq.factory().fieldName( f ) );
        Object field = document.content( f );
        if ( seq.factory().fieldType( f ) == FieldType.TEXT ) {
          Reader reader = (Reader)field;
          WordReader wr = document.wordReader( f );
          wr.setReader( reader );
          MutableString word = new MutableString();
          MutableString nonWord = new MutableString();
            while ( wr.next( word, nonWord ) ) System.out.println( word.toString() + nonWord.toString() );
        } else System.out.println( field );
      }
      doc++;
    }
  }
View Full Code Here
278
279
280
281
282
283
284
285
286
287
288
            throw new RuntimeException( e );
          }
          //logger.debug( "Asked for a new word reader for field " + fieldName( field ) );
          switch ( fieldType( field ) ) {
          case TEXT:
            return new WordReader() {
              private static final long serialVersionUID = 1L;
              public boolean next( final MutableString word, final MutableString nonWord ) throws IOException {
                try {
                  word.readSelfDelimUTF8( rawContent );
                }
View Full Code Here
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
    pl.displayFreeMemory = true;
    pl.start( "Indexing documents..." );

    DocumentIterator iterator = documentSequence.iterator();
    Reader reader;
    WordReader wordReader;
    ObjectList<VirtualDocumentFragment> fragments;
    Document document;

    int documentPointer = 0, documentsInBatch = 0;
    long batchStartTime = System.currentTimeMillis();
    boolean outOfMemoryError = false;

    while ( ( document = iterator.nextDocument() ) != null ) {
     
      long overallTerms = 0;
      if ( building ) builder.startDocument( document.title(), document.uri() );
      for ( int i = 0; i < numberOfIndexedFields; i++ ) {
        switch ( factory.fieldType( indexedField[ i ] ) ) {
        case TEXT:
          reader = (Reader)document.content( indexedField[ i ] );
          wordReader = document.wordReader( indexedField[ i ] );
          wordReader.setReader( reader );
          if ( building ) builder.startTextField();
          scan[ i ].processDocument( map != null ? map[ documentPointer ] : documentPointer, wordReader );
          if ( building ) builder.endTextField();
          overallTerms += scan[ i ].numTerms;
          break;
        case VIRTUAL:
          fragments = (ObjectList<VirtualDocumentFragment>)document.content( indexedField[ i ] );
          wordReader = document.wordReader( indexedField[ i ] );
          virtualDocumentResolver[ i ].context( document );
          for( VirtualDocumentFragment fragment: fragments ) {
            int virtualDocumentPointer = virtualDocumentResolver[ i ].resolve( fragment.documentSpecifier() );
            if ( virtualDocumentPointer < 0 ) continue;
            if ( map != null ) virtualDocumentPointer = map[ virtualDocumentPointer ];
            wordReader.setReader( new FastBufferedReader( fragment.text() ) );
            scan[ i ].processDocument( virtualDocumentPointer, wordReader );
          }
          if ( building ) builder.virtualField( fragments );
          overallTerms += scan[ i ].numTerms;
          break;
View Full Code Here
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
  @SuppressWarnings("unchecked")
  public void build( final DocumentSequence inputSequence ) throws IOException {
    final DocumentIterator docIt = inputSequence.iterator();
    if ( factory != inputSequence.factory() ) throw new IllegalStateException( "The factory provided by the constructor does not correspond to the factory of the input sequence" );
    final int numberOfFields = factory.numberOfFields();
    WordReader wordReader;
    MutableString word = new MutableString();
    MutableString nonWord = new MutableString();
   
    open( "" );
    for (;;) {
      Document document = docIt.nextDocument();
      if ( document == null ) break;
      startDocument( document.title(), document.uri() );
     
      for ( int field = 0; field < numberOfFields; field++ ) {
        Object content = document.content( field );
        if ( factory.fieldType( field ) == FieldType.TEXT ) {
          startTextField();
          wordReader = document.wordReader( field );
          wordReader.setReader( (Reader)content );
          while ( wordReader.next( word, nonWord ) ) add( word, nonWord );
          endTextField();
        }
        else if ( factory.fieldType( field ) == FieldType.VIRTUAL ) virtualField( (ObjectList<VirtualDocumentFragment>)content );
        else nonTextField( content );
      }
View Full Code Here
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
      if ( allBitStreamIndices ) {
        it.unimi.dsi.mg4j.document.DocumentIterator documentIterator = documentSequence.iterator();
        Document document;
        Reader reader;
        WordReader wordReader;
       
        final MutableString word = new MutableString(), nonWord = new MutableString();
       
        int docCounter = 0;
       
        while( ( document = documentIterator.nextDocument() ) != null ) {
          currDoc = permutation != null ? permutation[ docCounter ] : docCounter;

          for( i = 0; i < index.length; i++ ) {
            Object content = document.content( stem || index[ i ].field == null ? indexedField[ i ] : factory.fieldIndex( index[ i ].field ) );
            if ( index[ i ].hasPayloads ) {
              // TODO: write tests for the other case
              if ( allBitStreamIndices ) {
                IndexIterator indexIterator = indexReader[ i ].documents( 0 );
                int pointer = indexIterator.skipTo( currDoc );
                if ( pointer == currDoc ) {
                  Payload payload = indexIterator.payload();
                  if ( ! payload.get().equals( content ) ) LOGGER.error( index[ i ] + ": Document " + currDoc + " has payload " + content + " but the index says " + payload ); 
                }
                else LOGGER.error( index[ i ] + ": Document " + currDoc + " does not appear in the inverted list of term " + t );
              }
              else {
                IndexIterator indexIterator = indexReader[ i ].documents(  0  );
                if ( indexIterator.skipTo( currDoc ) == currDoc ) {
                  if ( ! indexIterator.payload().get().equals( content ) )
                    LOGGER.error( index[ i ] + ": Document " + currDoc + " has payload " + content + " but the index says " + indexIterator.payload().get() );
                }
                else LOGGER.error( index[ i ] + ": Document " + currDoc + " does not appear in the inverted list of term " + t );
              }
            }
            else {
              // text index
              pos = 0;
              termsInDoc[ i ].clear();
              reader = (Reader)content;
              wordReader = document.wordReader( stem || index[ i ].field == null ? indexedField[ i ] : factory.fieldIndex( index[ i ].field ) );
              wordReader.setReader( reader );
              while( wordReader.next( word, nonWord ) ) {
                if ( word.length() == 0 || index[ i ].termProcessor != null && ! index[ i ].termProcessor.processTerm( word ) ) continue;
                if ( ( t = (int)( (BitStreamIndex)index[ i ] ).termMap.getLong( word ) ) == -1 ) LOGGER.error( index[ i ] + ": Could not find term " + word + " in term index" );
                else {
                  if ( index[ i ].hasCounts ) termsInDoc[ i ].put( t, termsInDoc[ i ].get( t ) + 1 );
                  if ( index[ i ].hasPositions ) wordInPos[ i ][ pos++ ] = t;
                }
              }

              if ( allBitStreamIndices ) {
                for( IntIterator x = termsInDoc[ i ].keySet().iterator(); x.hasNext(); ) {
                  t = x.nextInt();

                  IndexIterator indexIterator = indexReader[ i ].documents( t );

                  int pointer = indexIterator.skipTo( currDoc );
                  if ( pointer == currDoc ) {
                    if ( index[ i ].hasCounts ) {
                      int c = indexIterator.count();
                      if ( termsInDoc[ i ].get( t ) !=  c )
                        LOGGER.error( index[ i ] + ": The count for term " + t + " in document " + currDoc + " is " + c + " instead of " + termsInDoc[ i ].get( t ) );
                      else {
                        if ( index[ i ].hasPositions ) {
                          indexIterator.positions( occ[ i ] );

                          for( int j = 0; j < c; j++ )
                            if ( wordInPos[ i ][ occ[ i ][ j ] ] != t ) 
                              LOGGER.error( index[ i ] + ": The occurrence of index " + i + " of term " + t + " (position " + occ[ i ] +") in document " + currDoc + " is occupied instead by term " + wordInPos[ i ][ occ[ i ][ j ] ] );
                        }
                      }
                    }
                  }
                  else LOGGER.error( index[ i ] + ": Document " + currDoc + " does not appear in the inverted list of term " + t + "(skipTo returned " + pointer + ")" );
                }
              }
              else {
                for( IntIterator x = termsInDoc[ i ].keySet().iterator(); x.hasNext(); ) {
                  t = x.nextInt();
                  IndexIterator indexIterator = termLists ? indexReader[ i ].documents( terms[ i ].get( t ) ) : indexReader[ i ].documents( t );

                  if ( indexIterator.skipTo( currDoc ) == currDoc ) {
                    if ( index[ i ].hasCounts ) {
                      int c = indexIterator.count();
                      if ( termsInDoc[ i ].get( t ) !=  c )
                        LOGGER.error( index[ i ] + ": The count for term " + t + " in document " + currDoc + " is " + c + " instead of " + termsInDoc[ i ].get( t ) );
                      else {
                        if ( index[ i ].hasPositions ) {
                          indexIterator.positions( occ[ i ] );

                          for( int j = 0; j < c; j++ )
                            if ( wordInPos[ i ][ occ[ i ][ j ] ] != t ) 
                              LOGGER.error( index[ i ] + ": The occurrence of index " + i + " of term " + t + " (position " + occ[ i ] +") in document " + currDoc + " is occupied instead by term " + wordInPos[ i ][ occ[ i ][ j ] ] );
                        }
                      }
                    }
                  }
                  else LOGGER.error( index[ i ] + ": Document " + currDoc + " does not appear in the inverted list of term " + t );
                }
              }
            }
          }
          docCounter++;
          document.close();
          pl.update();
        }
      }
      else {
        LOGGER.warn( "Random access tests require very slow single-term scanning as not all indices are disk based" );

        it.unimi.dsi.mg4j.document.DocumentIterator documentIterator = documentSequence.iterator();
        Document document;
        Reader reader;
        WordReader wordReader;
       
        final MutableString word = new MutableString(), nonWord = new MutableString();
       
        int docCounter = 0;
       
        while( ( document = documentIterator.nextDocument() ) != null ) {
          currDoc = permutation != null ? permutation[ docCounter ] : docCounter;

          for( i = 0; i < index.length; i++ ) {
            Object content = document.content( stem || index[ i ].field == null ? indexedField[ i ] : factory.fieldIndex( index[ i ].field ) );
            if ( index[ i ].hasPayloads ) {
              if ( allBitStreamIndices ) {
                IndexIterator indexIterator = indexReader[ i ].documents( 0 );
                int pointer = indexIterator.skipTo( currDoc );
                if ( pointer == currDoc ) {
                  Payload payload = indexIterator.payload();
                  if ( ! payload.get().equals( content ) ) LOGGER.error( index[ i ] + ": Document " + currDoc + " has payload " + content + " but the index says " + payload ); 
                }
                else LOGGER.error( index[ i ] + ": Document " + currDoc + " does not appear in the inverted list of term " + t );
              }
              else {
                IndexIterator indexIterator = indexReader[ i ].documents( "#" );
                if ( indexIterator.skipTo( currDoc ) == currDoc ) {
                  if ( ! indexIterator.payload().get().equals( content ) )
                    LOGGER.error( index[ i ] + ": Document " + currDoc + " has payload " + content + " but the index says " + indexIterator.payload().get() );
                }
                else LOGGER.error( index[ i ] + ": Document " + currDoc + " does not appear in the inverted list of term " + t );
              }
            }
            else {
              pos = 0;
              reader = (Reader)content;
              wordReader = document.wordReader( stem || index[ i ].field == null ? indexedField[ i ] : factory.fieldIndex( index[ i ].field ) );
              wordReader.setReader( reader );
              while( wordReader.next( word, nonWord ) ) {
                if ( word.length() == 0 || index[ i ].termProcessor != null && ! index[ i ].termProcessor.processTerm( word ) ) continue;
                IndexIterator indexIterator = indexReader[ i ].documents( word );
                if ( currDoc != indexIterator.skipTo( currDoc ) )
                  LOGGER.error( index[ i ] + ": Document " + currDoc + " does not appear in the inverted list of term " + word );
                else if ( index[ i ].hasPositions ) {
View Full Code Here
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
    numberOfDocuments = 0;

    final DocumentIterator docIt = inputSequence.iterator();
    if ( factory != inputSequence.factory() ) throw new IllegalStateException( "The factory provided by the constructor does not correspond to the factory of the input sequence" );
    final int numberOfFields = factory.numberOfFields();
    WordReader wordReader;
    MutableString word = new MutableString();
    MutableString nonWord = new MutableString();
    open( "" );
    for (;;) {
      Document document = docIt.nextDocument();
      if ( document == null ) break;
      startDocument( document.title(), document.uri() );
     
      for ( int field = 0; field < numberOfFields; field++ ) {
        Object content = document.content( field );
        if ( factory.fieldType( field ) == FieldType.TEXT ) {
          startTextField();
          wordReader = document.wordReader( field );
          wordReader.setReader( (Reader)content );
          while ( wordReader.next( word, nonWord ) ) add( word, nonWord );
          endTextField();
        }
        else if ( factory.fieldType( field ) == FieldType.VIRTUAL ) virtualField( (ObjectList<VirtualDocumentFragment>)content );
        else nonTextField( content );
      }
View Full Code Here
200
201
202
203
204
205
206
207
208
209
210
211
    for ( int doc = 0; doc < coll.size(); doc++ ) {
      Document docum = coll.document( doc );
      for ( int i = 0; i < nfields; i++ ) {
        int field = fieldNumber[ i ];
        Reader content = (Reader)docum.content( field );
        WordReader wordReader = docum.wordReader( field );
        wordReader.setReader( content );
        StringTokenizer tok = new StringTokenizer( document[ doc ][ arrayIndex[ i ] ] );
        System.err.println( "Checking document " + doc + " field " + fieldName[ i ] + " (" + field + ")" );
        checkSameWords( wordReader, tok );
      }
      docum.close();
View Full Code Here
251
252
253
254
255
256
257
258
259
260
261
262
    int doc = 0;
    while ( ( docum = iterator.nextDocument() ) != null ) {
      for ( int i = 0; i < nfields; i++ ) {
        int field = fieldNumber[ i ];
        Reader content = (Reader)docum.content( field );
        WordReader wordReader = docum.wordReader( field );
        wordReader.setReader( content );
        StringTokenizer tok = new StringTokenizer( document[ doc ][ arrayIndex[ i ] ] );
        System.err.println( "Checking sequentially document " + doc + " field " + fieldName[ i ] + " (" + field + ")" );
        checkSameWords( wordReader, tok );
      }
      docum.close();
View Full Code Here
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
        for (int i = 0; i < min(k, results.size()); i++) {
          Document document = collection
              .document(results.get(i).document);
          Reader reader = (Reader) document.content(fieldIndex);
          WordReader wordReader = document.wordReader(fieldIndex);
          wordReader.setReader(reader);

          MutableString word = new MutableString();
          MutableString nonWord = new MutableString();
          final LongRBTreeSet set = new LongRBTreeSet();

          while (wordReader.next(word, nonWord)) {
            if (processor.processTerm(word)) {
              long termId = index.getTermId(word);
              if (termId >= 0)
                if (set.add(termId))
                  relFreq
View Full Code Here
337
338
339
340
341
342
343
344
345
346
347
348
349
350
        long unknown = index.getUnknownTermId();

        Multiset<Long> words = HashMultiset.create();

        for (int contentId : contents) {
            final WordReader reader = doc.wordReader(0);

            // Loop over terms
            while (reader.next(token, separator)) {
                final Long termId = index.getTermId(token);
                if (termId == unknown) continue;
                words.add(termId);
            }
        } // loop over content
View Full Code Here
TOP

Related Classes of it.unimi.dsi.io.WordReader

  • it.unimi.dsi.mg4j.document.AbstractDocumentCollection
  • it.unimi.dsi.mg4j.document.DocumentCollectionTest
  • it.unimi.dsi.mg4j.document.SimpleCompressedDocumentCollectionBuilder
  • it.unimi.dsi.mg4j.document.ZipDocumentCollection$ZipFactory
  • it.unimi.dsi.mg4j.document.ZipDocumentCollectionBuilder
  • it.unimi.dsi.mg4j.test.Verifier
  • it.unimi.dsi.mg4j.tool.Scan
  • net.bpiwowar.mg4j.extensions.adhoc.MG4JScorer$PseudoRF$TopRanked
  • net.bpiwowar.mg4j.extensions.adhoc.RelevanceModel
  • net.bpiwowar.mg4j.extensions.tasks.CatCollectionBatches
    • 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.