Package com.browseengine.bobo.util.BigNestedIntArray

Examples of com.browseengine.bobo.util.BigNestedIntArray.BufferedLoader

37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
  @Override
  public void load(String fieldName, AtomicReader reader, TermListFactory<T> listFactory,
      WorkArea workArea) throws IOException {
    String field = fieldName.intern();
    int maxdoc = reader.maxDoc();
    BufferedLoader loader = getBufferedLoader(maxdoc, workArea);
    BufferedLoader weightLoader = getBufferedLoader(maxdoc, null);

    @SuppressWarnings("unchecked")
    TermValueList<T> list = (listFactory == null ? (TermValueList<T>) new TermStringList()
        : listFactory.createTermList());
    IntArrayList minIDList = new IntArrayList();
    IntArrayList maxIDList = new IntArrayList();
    IntArrayList freqList = new IntArrayList();
    OpenBitSet bitset = new OpenBitSet(maxdoc + 1);
    int negativeValueCount = getNegativeValueCount(reader, field);
    int t = 1; // valid term id starts from 1
    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);

    _overflow = false;

    String pre = null;

    int df = 0;
    int minID = -1;
    int maxID = -1;
    int docID = -1;
    int valId = 0;

    Terms terms = reader.terms(field);
    if (terms != null) {
      TermsEnum termsEnum = terms.iterator(null);
      BytesRef text;
      while ((text = termsEnum.next()) != null) {
        String strText = text.utf8ToString();
        String val = null;
        int weight = 0;
        String[] split = strText.split("\u0000");
        if (split.length > 1) {
          val = split[0];
          weight = Integer.parseInt(split[split.length - 1]);
        } else {
          continue;
        }

        if (pre == null || !val.equals(pre)) {
          if (pre != null) {
            freqList.add(df);
            minIDList.add(minID);
            maxIDList.add(maxID);
          }
          list.add(val);
          df = 0;
          minID = -1;
          maxID = -1;
          valId = (t - 1 < negativeValueCount) ? (negativeValueCount - t + 1) : t;
          t++;
        }

        Term term = new Term(field, strText);
        DocsEnum docsEnum = reader.termDocsEnum(term);
        if (docsEnum != null) {
          while ((docID = docsEnum.nextDoc()) != DocsEnum.NO_MORE_DOCS) {
            df++;

            if (!loader.add(docID, valId)) {
              logOverflow(fieldName);
            } else {
              weightLoader.add(docID, weight);
            }

            if (docID < minID) minID = docID;
            bitset.fastSet(docID);
            while (docsEnum.nextDoc() != DocsEnum.NO_MORE_DOCS) {
              docID = docsEnum.docID();
              df++;
              if (!loader.add(docID, valId)) {
                logOverflow(fieldName);
              } else {
                weightLoader.add(docID, weight);
              }
              bitset.fastSet(docID);
            }
            if (docID > maxID) maxID = docID;
          }
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
   */
  public void load(String fieldName, AtomicReader reader, TermListFactory<T> listFactory,
      WorkArea workArea) throws IOException {
    String field = fieldName.intern();
    int maxdoc = reader.maxDoc();
    BufferedLoader loader = getBufferedLoader(maxdoc, workArea);

    @SuppressWarnings("unchecked")
    TermValueList<T> list = (listFactory == null ? (TermValueList<T>) new TermStringList()
        : listFactory.createTermList());
    IntArrayList minIDList = new IntArrayList();
    IntArrayList maxIDList = new IntArrayList();
    IntArrayList freqList = new IntArrayList();
    OpenBitSet bitset = new OpenBitSet(maxdoc + 1);
    int negativeValueCount = getNegativeValueCount(reader, field);
    int t = 1; // valid term id starts from 1
    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);

    _overflow = false;

    Terms terms = reader.terms(field);
    if (terms != null) {
      TermsEnum termsEnum = terms.iterator(null);
      BytesRef text;
      while ((text = termsEnum.next()) != null) {
        String strText = text.utf8ToString();
        list.add(strText);

        Term term = new Term(field, strText);
        DocsEnum docsEnum = reader.termDocsEnum(term);
        int df = 0;
        int minID = -1;
        int maxID = -1;
        int docID = -1;
        int valId = (t - 1 < negativeValueCount) ? (negativeValueCount - t + 1) : t;
        while ((docID = docsEnum.nextDoc()) != DocsEnum.NO_MORE_DOCS) {
          df++;
          if (!loader.add(docID, valId)) logOverflow(fieldName);
          minID = docID;
          bitset.fastSet(docID);
          while (docsEnum.nextDoc() != DocsEnum.NO_MORE_DOCS) {
            docID = docsEnum.docID();
            df++;
            if (!loader.add(docID, valId)) logOverflow(fieldName);
            bitset.fastSet(docID);
          }
          maxID = docID;
        }
        freqList.add(df);
View Full Code Here
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
    }
  }

  protected BufferedLoader getBufferedLoader(int maxdoc, WorkArea workArea) {
    if (workArea == null) {
      return new BufferedLoader(maxdoc, _maxItems, new BigIntBuffer());
    } else {
      BigIntBuffer buffer = workArea.get(BigIntBuffer.class);
      if (buffer == null) {
        buffer = new BigIntBuffer();
        workArea.put(buffer);
      } else {
        buffer.reset();
      }

      BufferedLoader loader = workArea.get(BufferedLoader.class);
      if (loader == null || loader.capacity() < maxdoc) {
        loader = new BufferedLoader(maxdoc, _maxItems, buffer);
        workArea.put(loader);
      } else {
        loader.reset(maxdoc, _maxItems, buffer);
      }
      return loader;
    }
  }
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
   */
  public void load(String fieldName, AtomicReader reader, TermListFactory<T> listFactory,
      WorkArea workArea) throws IOException {
    String field = fieldName.intern();
    int maxdoc = reader.maxDoc();
    BufferedLoader loader = getBufferedLoader(maxdoc, workArea);

    @SuppressWarnings("unchecked")
    TermValueList<T> list = (listFactory == null ? (TermValueList<T>) new TermStringList()
        : listFactory.createTermList());
    IntArrayList minIDList = new IntArrayList();
    IntArrayList maxIDList = new IntArrayList();
    IntArrayList freqList = new IntArrayList();
    OpenBitSet bitset = new OpenBitSet(maxdoc + 1);
    int negativeValueCount = getNegativeValueCount(reader, field);
    int t = 0; // current term number
    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);
    t++;

    _overflow = false;

    Terms terms = reader.terms(field);
    if (terms != null) {
      TermsEnum termsEnum = terms.iterator(null);
      BytesRef text;
      while ((text = termsEnum.next()) != null) {
        String strText = text.utf8ToString();
        list.add(strText);

        Term term = new Term(field, strText);
        DocsEnum docsEnum = reader.termDocsEnum(term);
        // freqList.add(tenum.docFreq()); // removed because the df doesn't take into account
        // the num of deletedDocs
        int df = 0;
        int minID = -1;
        int maxID = -1;
        int docID = -1;
        int valId = (t - 1 < negativeValueCount) ? (negativeValueCount - t + 1) : t;
        while ((docID = docsEnum.nextDoc()) != DocsEnum.NO_MORE_DOCS) {
          df++;
          if (!loader.add(docID, valId)) logOverflow(fieldName);
          minID = docID;
          bitset.fastSet(docID);
          while (docsEnum.nextDoc() != DocsEnum.NO_MORE_DOCS) {
            docID = docsEnum.docID();
            df++;
            if (!loader.add(docID, valId)) logOverflow(fieldName);
            bitset.fastSet(docID);
          }
          maxID = docID;
        }
        freqList.add(df);
View Full Code Here
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
    }
  }

  protected BufferedLoader getBufferedLoader(int maxdoc, WorkArea workArea) {
    if (workArea == null) {
      return new BufferedLoader(maxdoc, _maxItems, new BigIntBuffer());
    } else {
      BigIntBuffer buffer = workArea.get(BigIntBuffer.class);
      if (buffer == null) {
        buffer = new BigIntBuffer();
        workArea.put(buffer);
      } else {
        buffer.reset();
      }

      BufferedLoader loader = workArea.get(BufferedLoader.class);
      if (loader == null || loader.capacity() < maxdoc) {
        loader = new BufferedLoader(maxdoc, _maxItems, buffer);
        workArea.put(loader);
      } else {
        loader.reset(maxdoc, _maxItems, buffer);
      }
      return loader;
    }
  }
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
  @Override
  public void load(String fieldName, AtomicReader reader, TermListFactory<T> listFactory,
      WorkArea workArea) throws IOException {
    String field = fieldName.intern();
    int maxdoc = reader.maxDoc();
    BufferedLoader loader = getBufferedLoader(maxdoc, workArea);
    BufferedLoader weightLoader = getBufferedLoader(maxdoc, null);

    @SuppressWarnings("unchecked")
    TermValueList<T> list = (listFactory == null ? (TermValueList<T>) new TermStringList()
        : listFactory.createTermList());
    IntArrayList minIDList = new IntArrayList();
    IntArrayList maxIDList = new IntArrayList();
    IntArrayList freqList = new IntArrayList();
    OpenBitSet bitset = new OpenBitSet(maxdoc + 1);
    int negativeValueCount = getNegativeValueCount(reader, field);
    int t = 0; // current term number
    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);
    t++;

    _overflow = false;

    String pre = null;

    int df = 0;
    int minID = -1;
    int maxID = -1;
    int docID = -1;
    int valId = 0;

    Terms terms = reader.terms(field);
    if (terms != null) {
      TermsEnum termsEnum = terms.iterator(null);
      BytesRef text;
      while ((text = termsEnum.next()) != null) {
        String strText = text.utf8ToString();
        String val = null;
        int weight = 0;
        String[] split = strText.split("\u0000");
        if (split.length > 1) {
          val = split[0];
          weight = Integer.parseInt(split[split.length - 1]);
        } else {
          continue;
        }

        if (pre == null || !val.equals(pre)) {
          if (pre != null) {
            freqList.add(df);
            minIDList.add(minID);
            maxIDList.add(maxID);
          }
          list.add(val);
          df = 0;
          minID = -1;
          maxID = -1;
          valId = (t - 1 < negativeValueCount) ? (negativeValueCount - t + 1) : t;
          t++;
        }

        Term term = new Term(field, strText);
        DocsEnum docsEnum = reader.termDocsEnum(term);
        if (docsEnum != null) {
          while ((docID = docsEnum.nextDoc()) != DocsEnum.NO_MORE_DOCS) {
            df++;

            if (!loader.add(docID, valId)) {
              logOverflow(fieldName);
            } else {
              weightLoader.add(docID, weight);
            }

            if (docID < minID) minID = docID;
            bitset.fastSet(docID);
            while (docsEnum.nextDoc() != DocsEnum.NO_MORE_DOCS) {
              docID = docsEnum.docID();
              df++;
              if (!loader.add(docID, valId)) {
                logOverflow(fieldName);
              } else {
                weightLoader.add(docID, weight);
              }
              bitset.fastSet(docID);
            }
            if (docID > maxID) maxID = docID;
          }
View Full Code Here
TOP

Related Classes of com.browseengine.bobo.util.BigNestedIntArray.BufferedLoader

  • com.browseengine.bobo.facets.data.MultiValueFacetDataCache
  • com.browseengine.bobo.facets.data.MultiValueWithWeightFacetDataCache
  • com.browseengine.bobo.util.test.BigNestedIntArrayTest
    • 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.