Package org.apache.lucene.queries.mlt

Examples of org.apache.lucene.queries.mlt.MoreLikeThis

2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
      id = Integer.parseInt(getString(docNum, "text"));
    } catch (NumberFormatException nfe) {
      errorMsg("Invalid document number");
      return;
    }
    MoreLikeThis mlt = new MoreLikeThis(ir);
    try {
      mlt.setFieldNames((String[])Util.fieldNames(ir, true).toArray(new String[0]));
    } catch (Exception e) {
      errorMsg("Exception collecting field names: " + e.toString());
      return;
    }
    mlt.setMinTermFreq(1);
    mlt.setMaxQueryTerms(50);
    Analyzer a = createAnalyzer(find("srchOptTabs"));
    if (a == null) {
      return;
    }
    mlt.setAnalyzer(a);
    Object[] rows = getSelectedItems(docTable);
    BooleanQuery similar = null;
    if (rows != null && rows.length > 0) {
      // collect text from fields
      StringBuilder sb = new StringBuilder();
      for (int i = 0; i < rows.length; i++) {
        Field f = (Field)getProperty(rows[i], "field");
        if (f == null) {
          continue;
        }
        String s = f.stringValue();
        if (s == null || s.trim().length() == 0) {
          continue;
        }
        if (sb.length() > 0) sb.append(" ");
        sb.append(s);
      }
      try {
        similar = (BooleanQuery)mlt.like("field", new StringReader(sb.toString()));
      } catch (Exception e) {
        e.printStackTrace();
        errorMsg("FAILED: " + e.getMessage());
        return;
      }
    } else {
      try {
        similar = (BooleanQuery)mlt.like(id);
      } catch (Exception e) {
        e.printStackTrace();
        errorMsg("FAILED: " + e.getMessage());
        return;
      }
View Full Code Here
117
118
119
120
121
122
123
124
125
126
127
   */
  @Override
  public void train(AtomicReader atomicReader, String textFieldName, String classFieldName, Analyzer analyzer, Query query) throws IOException {
    this.textFieldNames = new String[]{textFieldName};
    this.classFieldName = classFieldName;
    mlt = new MoreLikeThis(atomicReader);
    mlt.setAnalyzer(analyzer);
    mlt.setFieldNames(new String[]{textFieldName});
    indexSearcher = new IndexSearcher(atomicReader);
    this.query = query;
  }
View Full Code Here
131
132
133
134
135
136
137
138
139
140
141
   */
  @Override
  public void train(AtomicReader atomicReader, String[] textFieldNames, String classFieldName, Analyzer analyzer, Query query) throws IOException {
    this.textFieldNames = textFieldNames;
    this.classFieldName = classFieldName;
    mlt = new MoreLikeThis(atomicReader);
    mlt.setAnalyzer(analyzer);
    mlt.setFieldNames(textFieldNames);
    indexSearcher = new IndexSearcher(atomicReader);
    this.query = query;
  }
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
   */
  @Override
  public void train(AtomicReader atomicReader, String[] textFieldNames, String classFieldName, Analyzer analyzer, Query query) throws IOException {
    this.textFieldNames = textFieldNames;
    this.classFieldName = classFieldName;
    mlt = new MoreLikeThis(atomicReader);
    mlt.setAnalyzer(analyzer);
    mlt.setFieldNames(textFieldNames);
    indexSearcher = new IndexSearcher(atomicReader);
    if (minDocsFreq > 0) {
      mlt.setMinDocFreq(minDocsFreq);
View Full Code Here
95
96
97
98
99
100
101
102
103
104
   */
  @Override
  public void train(AtomicReader atomicReader, String textFieldName, String classFieldName, Analyzer analyzer) throws IOException {
    this.textFieldName = textFieldName;
    this.classFieldName = classFieldName;
    mlt = new MoreLikeThis(atomicReader);
    mlt.setAnalyzer(analyzer);
    mlt.setFieldNames(new String[]{textFieldName});
    indexSearcher = new IndexSearcher(atomicReader);
  }
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
   */
  @Override
  public void train(AtomicReader atomicReader, String[] textFieldNames, String classFieldName, Analyzer analyzer, Query query) throws IOException {
    this.textFieldNames = textFieldNames;
    this.classFieldName = classFieldName;
    mlt = new MoreLikeThis(atomicReader);
    mlt.setAnalyzer(analyzer);
    mlt.setFieldNames(textFieldNames);
    indexSearcher = new IndexSearcher(atomicReader);
    if (minDocsFreq > 0) {
      mlt.setMinDocFreq(minDocsFreq);
View Full Code Here
98
99
100
101
102
103
104
105
106
107
   */
  @Override
  public void train(AtomicReader atomicReader, String textFieldName, String classFieldName, Analyzer analyzer) throws IOException {
    this.textFieldName = textFieldName;
    this.classFieldName = classFieldName;
    mlt = new MoreLikeThis(atomicReader);
    mlt.setAnalyzer(analyzer);
    mlt.setFieldNames(new String[]{textFieldName});
    indexSearcher = new IndexSearcher(atomicReader);
  }
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
   */
  @Override
  public void train(AtomicReader atomicReader, String[] textFieldNames, String classFieldName, Analyzer analyzer, Query query) throws IOException {
    this.textFieldNames = textFieldNames;
    this.classFieldName = classFieldName;
    mlt = new MoreLikeThis(atomicReader);
    mlt.setAnalyzer(analyzer);
    mlt.setFieldNames(textFieldNames);
    indexSearcher = new IndexSearcher(atomicReader);
    if (minDocsFreq > 0) {
      mlt.setMinDocFreq(minDocsFreq);
View Full Code Here
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
*/
public class MoreLikeThisHelper {

    public static Query getMoreLikeThis(IndexReader reader, Analyzer analyzer, String mltQueryString) {
        Query moreLikeThisQuery = null;
        MoreLikeThis mlt = new MoreLikeThis(reader);
        mlt.setAnalyzer(analyzer);
        try {
            String text = null;
            String[] fields = {};
            for (String param : mltQueryString.split("&")) {
                String[] keyValuePair = param.split("=");
                if (keyValuePair.length != 2 || keyValuePair[0] == null || keyValuePair[1] == null) {
                    throw new RuntimeException("Unparsable native Lucene MLT query: " + mltQueryString);
                } else {
                    if ("stream.body".equals(keyValuePair[0])) {
                        text = keyValuePair[1];
                    } else if ("mlt.fl".equals(keyValuePair[0])) {
                        fields = keyValuePair[1].split(",");
                    } else if ("mlt.mindf".equals(keyValuePair[0])) {
                        mlt.setMinDocFreq(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.mintf".equals(keyValuePair[0])) {
                        mlt.setMinTermFreq(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.boost".equals(keyValuePair[0])) {
                        mlt.setBoost(Boolean.parseBoolean(keyValuePair[1]));
                    } else if ("mlt.qf".equals(keyValuePair[0])) {
                        mlt.setBoostFactor(Float.parseFloat(keyValuePair[1]));
                    } else if ("mlt.maxdf".equals(keyValuePair[0])) {
                        mlt.setMaxDocFreq(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.maxdfp".equals(keyValuePair[0])) {
                        mlt.setMaxDocFreqPct(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.maxntp".equals(keyValuePair[0])) {
                        mlt.setMaxNumTokensParsed(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.maxqt".equals(keyValuePair[0])) {
                        mlt.setMaxQueryTerms(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.maxwl".equals(keyValuePair[0])) {
                        mlt.setMaxWordLen(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.minwl".equals(keyValuePair[0])) {
                        mlt.setMinWordLen(Integer.parseInt(keyValuePair[1]));
                    }
                }
            }
            if (text != null) {
                if (FieldNames.PATH.equals(fields[0])) {
                    IndexSearcher searcher = new IndexSearcher(reader);
                    TermQuery q = new TermQuery(new Term(FieldNames.PATH, text));
                    TopDocs top = searcher.search(q, 1);
                    if (top.totalHits == 0) {
                        mlt.setFieldNames(fields);
                        moreLikeThisQuery = mlt.like(new StringReader(text), mlt.getFieldNames()[0]);
                    } else{
                        ScoreDoc d = top.scoreDocs[0];
                        Document doc = reader.document(d.doc);
                        List<String> fieldNames = new ArrayList<String>();
                        for (IndexableField f : doc.getFields()) {
                            if (!FieldNames.PATH.equals(f.name())) {
                                fieldNames.add(f.name());
                            }
                        }
                        String[] docFields = fieldNames.toArray(new String[0]);
                        mlt.setFieldNames(docFields);
                        moreLikeThisQuery = mlt.like(d.doc);
                    }
                } else {
                    mlt.setFieldNames(fields);
                    moreLikeThisQuery = mlt.like(new StringReader(text), mlt.getFieldNames()[0]);
                }
            }
            return moreLikeThisQuery;
        } catch (Exception e) {
            throw new RuntimeException("could not handle MLT query " + mltQueryString);
View Full Code Here
27
28
29
30
31
32
33
34
35
36
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
*/
public class MoreLikeThisHelper {

    public static Query getMoreLikeThis(IndexReader reader, Analyzer analyzer, String mltQueryString) {
        Query moreLikeThisQuery = null;
        MoreLikeThis mlt = new MoreLikeThis(reader);
        mlt.setAnalyzer(analyzer);
        try {
            String text = null;
            for (String param : mltQueryString.split("&")) {
                String[] keyValuePair = param.split("=");
                if (keyValuePair.length != 2 || keyValuePair[0] == null || keyValuePair[1] == null) {
                    throw new RuntimeException("Unparsable native Lucene MLT query: " + mltQueryString);
                } else {
                    if ("stream.body".equals(keyValuePair[0])) {
                        text = keyValuePair[1];
                    } else if ("mlt.fl".equals(keyValuePair[0])) {
                        mlt.setFieldNames(keyValuePair[1].split(","));
                    } else if ("mlt.mindf".equals(keyValuePair[0])) {
                        mlt.setMinDocFreq(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.mintf".equals(keyValuePair[0])) {
                        mlt.setMinTermFreq(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.boost".equals(keyValuePair[0])) {
                        mlt.setBoost(Boolean.parseBoolean(keyValuePair[1]));
                    } else if ("mlt.qf".equals(keyValuePair[0])) {
                        mlt.setBoostFactor(Float.parseFloat(keyValuePair[1]));
                    } else if ("mlt.maxdf".equals(keyValuePair[0])) {
                        mlt.setMaxDocFreq(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.maxdfp".equals(keyValuePair[0])) {
                        mlt.setMaxDocFreqPct(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.maxntp".equals(keyValuePair[0])) {
                        mlt.setMaxNumTokensParsed(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.maxqt".equals(keyValuePair[0])) {
                        mlt.setMaxQueryTerms(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.maxwl".equals(keyValuePair[0])) {
                        mlt.setMaxWordLen(Integer.parseInt(keyValuePair[1]));
                    } else if ("mlt.minwl".equals(keyValuePair[0])) {
                        mlt.setMinWordLen(Integer.parseInt(keyValuePair[1]));
                    }
                }
            }
            if (text != null) {
                moreLikeThisQuery = mlt.like(new StringReader(text), mlt.getFieldNames()[0]);
            }
            return moreLikeThisQuery;
        } catch (Exception e) {
            throw new RuntimeException("could not handle MLT query " + mltQueryString);
        }
View Full Code Here
TOP

Related Classes of org.apache.lucene.queries.mlt.MoreLikeThis

  • org.apache.jackrabbit.oak.plugins.index.lucene.util.MoreLikeThisHelper
  • org.apache.lucene.analysis.tokenattributes.CharTermAttribute
  • org.apache.lucene.analysis.TokenStream
  • org.apache.lucene.classification.KNearestNeighborClassifier
  • org.apache.lucene.document.Document
  • org.apache.lucene.index.Fields
  • org.apache.lucene.index.IndexableField
  • org.apache.lucene.index.Term
  • org.apache.lucene.index.Terms
  • org.apache.lucene.index.TermsEnum
    • 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.