Examples of edu.umd.cloud9.util.array.ArrayListOfShorts

edu.umd.cloud9.util.array.ArrayListOfShorts
Object representing a list of shorts, backed by an resizable-array.

      int e = entry.getRightElement();
      String eTerm = eVocab_f2e.get(e);


      //      LOG.info("Pr("+eTerm+"|"+token+")="+probEF);


      if (probEF > 0 && e > 0 && !docLangTokenizer.isStopWord(eTerm) && (translateOnly == null || !translateOnly.equals("indri") || indriPuncPattern.matcher(eTerm).matches()) && (pairsInSCFG == null || pairsInSCFG.contains(new PairOfStrings(token,eTerm)))) {      
        // assuming our bilingual dictionary is learned from normally segmented text, but we want to use bigram tokenizer for CLIR purposes
        // then we need to convert the translations of each source token into a sequence of bigrams
        // we can distribute the translation probability equally to the each bigram
        if (bigramSegment) {
          String[] eTokens = docLangTokenizer.processContent(eTerm);

View Full Code Here

    }


    // in SCFG rule such as a b X1 X2 c --> X1 d e X2 f, we want to find out the src/trg tokens that are aligned to some trg/src token, ignoring the X variable
    // we can then decide if we want to include it as a multi-token phrase in our query representation based on various heuristics (e.g., only include if no X in between of tokens)
    String fPhrase = "";
    ArrayListOfInts sourceTokenIds = new ArrayListOfInts();      
    ArrayListOfInts targetTokenIds = new ArrayListOfInts();
    int f=0;
    for (; f < lhs.length; f++) {
      String fTerm = lhs[f];
      if (queryLangTokenizer.isStopWord(fTerm) || fTerm.matches("\\[X,\\d+\\]") || fTerm.matches("<s>") || fTerm.matches("</s>")) {
        continue;
      }


      srcTokenCnt.increment(fTerm);
      sourceTokenIds.add(f);


      ArrayListOfInts ids;
      if (isPassThrough){
        ids = new ArrayListOfInts();
        ids.add(0);
      }else {
        ids = one2manyAlign.get(f);
      }


      if (ids == null || (isOne2Many == 0 && ids.size() > 1)) {
        continue;
      }


      // find phrase in LHS and match to phrase in RHS
      if (isMany2Many) {
        fPhrase += fTerm + " ";
        targetTokenIds = targetTokenIds.mergeNoDuplicates(ids);        
      }


      String eTerm = null;
      for (int e : ids) {
        eTerm = rhs[e];


        // assumption: if this is pass-through rule, re-stem token in doc-language
        if (isPassThrough || (unknownWords != null && unknownWords.contains(fTerm))) {
          eTerm = stemmed2Stemmed.get(eTerm);
        }


        if (eTerm == null || docLangTokenizer.isStopWord(eTerm)) {
          //          LOG.info("Skipped trg token " + eTerm);
          eTerm = null;
          continue;      
        }
        bagOfTargetTokens.add(eTerm);
        if (isOne2Many <= 1) {
          if (probDist.containsKey(fTerm)) {
            HMapSFW eToken2Prob = probDist.get(fTerm);
            eToken2Prob.increment(eTerm, weight);
          }else {
            HMapSFW eToken2Prob = new HMapSFW();
            eToken2Prob.put(eTerm, weight);
            probDist.put(fTerm, eToken2Prob);
          }
        }
      }


      if (isOne2Many == 2) {
        // if ids.size() > 1 eTerm is a multi-token expression
        // even if eTerm is overwritten here, we need to do above loop to update bagOfTargetTokens
        if (ids.size() > 1) {
          eTerm = isConsecutiveWithStopwords(ids, rhs, docLangTokenizer);     // <---- heuristic
        }


        // no proper translation on target-side (e.g., stopword OR non-consecutive multi-word translation), let's skip
        if (eTerm == null) {

View Full Code Here

      String[] alPair = alignment.split("-");
      int f = Integer.parseInt(alPair[0]);
      int e = Integer.parseInt(alPair[1]);


      if(!one2manyAlign.containsKey(f)){
        one2manyAlign.put(f, new ArrayListOfInts());  
      }
      one2manyAlign.get(f).add(e);
    }


    // for each source token id, sort ids of its translations in ascending order
    for(Integer f : one2manyAlign.keySet()) {
      ArrayListOfInts lst = one2manyAlign.get(f);
      lst.sort();
      one2manyAlign.put(f, lst);
    }


    return one2manyAlign;
  }

View Full Code Here


      // Remember, token position is numbered started from one...
      if (positions.containsKey(term)) {
        positions.get(term).add(i + 1);
      } else {
        ArrayListOfInts l = new ArrayListOfInts();
        l.add(i + 1);
        positions.put(term, l);
      }
    }


    int doclength = 0;
    Iterator<Map.Entry<String, ArrayListOfInts>> it = positions.entrySet().iterator();
    Map.Entry<String, ArrayListOfInts> e;
    ArrayListOfInts positionsList;
    while (it.hasNext()) {
      e = it.next();
      positionsList = e.getValue();


      // We're storing tfs as shorts, so check for overflow...
      if (positionsList.size() >= TF_CUT) {
        // There are a few ways to handle this... If we're getting such a high tf, then it most
        // likely means that this is a junk doc.
        LOG.warn("Error: tf of " + e.getValue()
            + " will overflow max short value. docno=" + doc.getDocid() + ", term="
            + e.getKey());
        it.remove();
      } else {
        positionsList.trimToSize();
        doclength += positionsList.size();
      }
    }


    if ( positions.size() == 0 ) {
      return positions;
    }


    positions.put("", new ArrayListOfInts(new int[] { doclength }));
    return positions;
  }

View Full Code Here

    assertEquals(1, c.size());
  }


  @Test
  public void testIntersection4() {
    ArrayListOfShorts a = new ArrayListOfShorts();
    a.add((short) 3);


    ArrayListOfShorts b = new ArrayListOfShorts();
    b.add((short) 0);


    ArrayListOfShorts c = a.intersection(b);


    assertEquals(0, c.size());
  }

View Full Code Here

  
  @Test
  public void testMerge1() {
    //CASE: interleaved


    ArrayListOfShorts a = new ArrayListOfShorts();
    a.add((short) 3);
    a.add((short) 7);
    a.add((short) 10);


    ArrayListOfShorts b = new ArrayListOfShorts();
    b.add((short) 0);
    b.add((short) 4);
    b.add((short) 9);


    ArrayListOfShorts c = a.merge(b);


    assertEquals(6, c.size());
    assertEquals(0, c.get(0));
    assertEquals(3, c.get(1));
    assertEquals(4, c.get(2));
    assertEquals(7, c.get(3));
    assertEquals(9, c.get(4));
    assertEquals(10, c.get(5));


    // c should be same as c2
    ArrayListOfShorts c2 = b.merge(a); 
    assertEquals(c, c2);
  }

View Full Code Here


  @Test
  public void testMerge2() {
    //CASE: append


    ArrayListOfShorts a = new ArrayListOfShorts();
    a.add((short) 3);
    a.add((short) 7);
    a.add((short) 10);


    ArrayListOfShorts b = new ArrayListOfShorts();
    b.add((short) 11);
    b.add((short) 19);
    b.add((short) 21);


    ArrayListOfShorts c = a.merge(b);


    assertEquals(6, c.size());
    assertEquals(3, c.get(0));
    assertEquals(7, c.get(1));
    assertEquals(10, c.get(2));
    assertEquals(11, c.get(3));
    assertEquals(19, c.get(4));
    assertEquals(21, c.get(5));


    ArrayListOfShorts c2 = b.merge(a);
    assertEquals(c, c2);
 }

View Full Code Here


  @Test
  public void testMerge3() {
    //CASE: one of the lists are empty
    
    ArrayListOfShorts a = new ArrayListOfShorts();
    a.add((short) 3);
    a.add((short) 7);
    a.add((short) 10);
    
    ArrayListOfShorts b = new ArrayListOfShorts();


    ArrayListOfShorts c = a.merge(b);
    assertEquals(c, a);
    
    ArrayListOfShorts c2 = b.merge(a);
    assertEquals(c, c2);   
  }

View Full Code Here

    assertEquals(c, c2);   
  }


  @Test
  public void testSubList() {
    ArrayListOfShorts a = new ArrayListOfShorts(new short[] {1, 2, 3, 4, 5, 6, 7});
    ArrayListOfShorts b = a.subList(1, 5);
    assertEquals(5, b.size());
    assertEquals(2, b.get(0));
    assertEquals(3, b.get(1));
    assertEquals(4, b.get(2));
    assertEquals(5, b.get(3));
    assertEquals(6, b.get(4));


    a.clear();
    // Make sure b is a new object.
    assertEquals(5, b.size());
    assertEquals(2, b.get(0));
    assertEquals(3, b.get(1));
    assertEquals(4, b.get(2));
    assertEquals(5, b.get(3));
    assertEquals(6, b.get(4));
  }

View Full Code Here

    assertEquals(6, b.get(4));
  }


  @Test
  public void testAddUnique() {
    ArrayListOfShorts a = new ArrayListOfShorts(new short[] {1, 2, 3, 4, 5, 6, 7});
    a.addUnique(new short[] {8, 0, 2, 5, -1, 11, 9});
    assertEquals(12, a.size());
    assertEquals(0, a.get(8));
    assertEquals(-1, a.get(9));
    assertEquals(11, a.get(10));
    assertEquals(9, a.get(11));
  }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of edu.umd.cloud9.util.array.ArrayListOfShorts

bak.pcj.IntIterator

edu.umd.cloud9.example.bfs.BfsNodeTest

edu.umd.cloud9.example.pagerank.PageRankNodeTest

edu.umd.cloud9.io.array.ArrayListOfIntsWritable

edu.umd.cloud9.io.fastutil.Int2FloatOpenHashMapWritableTest

edu.umd.cloud9.io.fastutil.Int2IntOpenHashMapWritableTest

edu.umd.cloud9.io.fastutil.String2FloatOpenHashMapWritableTest

edu.umd.cloud9.io.fastutil.String2IntOpenHashMapWritableTest

edu.umd.cloud9.io.map.HMapIDW

edu.umd.cloud9.io.map.HMapIDWTest

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.