Package org.apache.lucene.demo.html

Examples of org.apache.lucene.demo.html.HTMLParser$JJCalls

96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
    // Add the uid as a field, so that index can be incrementally maintained.
    // This field is not stored with document, it is indexed, but it is not
    // tokenized prior to indexing.
    doc.add(new Field("uid", uid(f), false, true, false));

    HTMLParser parser = new HTMLParser(f);

    // Add the tag-stripped contents as a Reader-valued Text field so it will
    // get tokenized and indexed.
    doc.add(Field.Text("contents", parser.getReader()));

    // Add the summary as an UnIndexed field, so that it is stored and returned
    // with hit documents for display.
    doc.add(Field.UnIndexed("summary", parser.getSummary()));

    // Add the title as a separate Text field, so that it can be searched
    // separately.
    doc.add(Field.Text("title", parser.getTitle()));

    // return the document
    return doc;
  }
View Full Code Here
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
    // 5. skip until end of doc header
    read("</DOCHDR>",null,false,false);
    // 6. collect until end of doc
    sb = read("</DOC>",null,false,true);
    // this is the next document, so parse it 
    HTMLParser p = new HTMLParser(new StringReader(sb.toString()));
    // title
    String title = p.getTitle();
    // properties
    Properties props = p.getMetaTags();
    // body
    Reader r = p.getReader();
    char c[] = new char[1024];
    StringBuffer bodyBuf = new StringBuffer();
    int n;
    while ((n = r.read(c)) >= 0) {
      if (n>0) {
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
    // This field is not stored with document, it is indexed, but it is not
    // tokenized prior to indexing.
    doc.add(new Field("uid", uid(f), Field.Store.NO, Field.Index.UN_TOKENIZED));

    FileInputStream fis = new FileInputStream(f);
    HTMLParser parser = new HTMLParser(fis);
     
    // Add the tag-stripped contents as a Reader-valued Text field so it will
    // get tokenized and indexed.
    doc.add(new Field("contents", parser.getReader()));

    // Add the summary as a field that is stored and returned with
    // hit documents for display.
    doc.add(new Field("summary", parser.getSummary(), Field.Store.YES, Field.Index.NO));

    // Add the title as a field that it can be searched and that is stored.
    doc.add(new Field("title", parser.getTitle(), Field.Store.YES, Field.Index.TOKENIZED));

    // return the document
    return doc;
  }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
    // This field is not stored with document, it is indexed, but it is not
    // tokenized prior to indexing.
    doc.add(new Field("uid", uid(f), Field.Store.NO, Field.Index.UN_TOKENIZED));

    FileInputStream fis = new FileInputStream(f);
    HTMLParser parser = new HTMLParser(fis);
     
    // Add the tag-stripped contents as a Reader-valued Text field so it will
    // get tokenized and indexed.
    doc.add(new Field("contents", parser.getReader()));

    // Add the summary as a field that is stored and returned with
    // hit documents for display.
    doc.add(new Field("summary", parser.getSummary(), Field.Store.YES, Field.Index.NO));

    // Add the title as a field that it can be searched and that is stored.
    doc.add(new Field("title", parser.getTitle(), Field.Store.YES, Field.Index.TOKENIZED));

    // return the document
    return doc;
  }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
    // This field is not stored with document, it is indexed, but it is not
    // tokenized prior to indexing.
    doc.add(new Field("uid", uid(f), Field.Store.NO, Field.Index.NOT_ANALYZED));

    FileInputStream fis = new FileInputStream(f);
    HTMLParser parser = new HTMLParser(fis);
     
    // Add the tag-stripped contents as a Reader-valued Text field so it will
    // get tokenized and indexed.
    doc.add(new Field("contents", parser.getReader()));

    // Add the summary as a field that is stored and returned with
    // hit documents for display.
    doc.add(new Field("summary", parser.getSummary(), Field.Store.YES, Field.Index.NO));

    // Add the title as a field that it can be searched and that is stored.
    doc.add(new Field("title", parser.getTitle(), Field.Store.YES, Field.Index.ANALYZED));

    // return the document
    return doc;
  }
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
    // Add the uid as a field, so that index can be incrementally maintained.
    // This field is not stored with document, it is indexed, but it is not
    // tokenized prior to indexing.
    doc.add(new Field("uid", uid(f), false, true, false));

    HTMLParser parser = new HTMLParser(f);

    // Add the tag-stripped contents as a Reader-valued Text field so it will
    // get tokenized and indexed.
    doc.add(Field.Text("contents", parser.getReader()));

    // Add the summary as an UnIndexed field, so that it is stored and returned
    // with hit documents for display.
    doc.add(Field.UnIndexed("summary", parser.getSummary()));

    // Add the title as a separate Text field, so that it can be searched
    // separately.
    doc.add(Field.Text("title", parser.getTitle()));

    // return the document
    return doc;
  }
View Full Code Here
TOP

Related Classes of org.apache.lucene.demo.html.HTMLParser$JJCalls

  • org.apache.lucene.benchmark.byTask.feeds.TrecDocMaker
  • org.apache.lucene.demo.HTMLDocument
    • 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.