Package org.apache.lucene.analysis.wikipedia

Examples of org.apache.lucene.analysis.wikipedia.WikipediaTokenizer

192
193
194
195
196
197
198
199
200
201
202
    Random random = random();
    Analyzer a = new Analyzer() {

      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new WikipediaTokenizer(reader);
        return new TokenStreamComponents(tokenizer, tokenizer);
      }
    };
    checkRandomData(random, a, 100*RANDOM_MULTIPLIER, 8192);
  }
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
    super(Version.LUCENE_46, stopSet);
  }

  @Override
  protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
    Tokenizer tokenizer = new WikipediaTokenizer(reader);
    TokenStream result = new StandardFilter(Version.LUCENE_46, tokenizer);
    result = new LowerCaseFilter(Version.LUCENE_46, result);
    result = new StopFilter(Version.LUCENE_46, result, getStopwordSet());
    return new TokenStreamComponents(tokenizer, result);
  }
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
    super(Version.LUCENE_31, stopSet);
  }
 
  @Override
  protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
    Tokenizer tokenizer = new WikipediaTokenizer(reader);
    TokenStream result = new StandardFilter(Version.LUCENE_31, tokenizer);
    result = new LowerCaseFilter(Version.LUCENE_31, result);
    result = new StopFilter(Version.LUCENE_31, result, stopwords);
    return new TokenStreamComponents(tokenizer, result);
  }
View Full Code Here
34
35
36
37
38
39
40
41
42
43
44
public class WikipediaTokenizerTest extends BaseTokenStreamTestCase {
  protected static final String LINK_PHRASES = "click [[link here again]] click [http://lucene.apache.org here again] [[Category:a b c d]]";

  public void testSimple() throws Exception {
    String text = "This is a [[Category:foo]]";
    WikipediaTokenizer tf = new WikipediaTokenizer(new StringReader(text));
    assertTokenStreamContents(tf,
        new String[] { "This", "is", "a", "foo" },
        new int[] { 0, 5, 8, 21 },
        new int[] { 4, 7, 9, 24 },
        new String[] { "<ALPHANUM>", "<ALPHANUM>", "<ALPHANUM>", CATEGORY },
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
        + "''[[Category:ital_cat]]''  here is some that is ''italics [[Category:foo]] but is never closed."
        + "'''same [[Category:foo]] goes for this '''''and2 [[Category:foo]] and this"
        + " [http://foo.boo.com/test/test/ Test Test] [http://foo.boo.com/test/test/test.html Test Test]"
        + " [http://foo.boo.com/test/test/test.html?g=b&c=d Test Test] <ref>Citation</ref> <sup>martian</sup> <span class=\"glue\">code</span>";
   
    WikipediaTokenizer tf = new WikipediaTokenizer(new StringReader(test));
    assertTokenStreamContents(tf,
      new String[] {"link", "This", "is", "a",
        "foo", "Category", "This", "is", "a", "linked", "bar", "none",
        "withstanding", "Category", "This", "is", "parens", "This", "is", "a",
        "link", "This", "is", "an", "external", "URL",
View Full Code Here
97
98
99
100
101
102
103
104
        EXTERNAL_LINK_URL, EXTERNAL_LINK, EXTERNAL_LINK, CITATION,
        "<ALPHANUM>", "<ALPHANUM>"});
  }

  public void testLinkPhrases() throws Exception {
    WikipediaTokenizer tf = new WikipediaTokenizer(new StringReader(LINK_PHRASES));
    checkLinkPhrases(tf);
  }
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
        new int[] { 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1 });
  }

  public void testLinks() throws Exception {
    String test = "[http://lucene.apache.org/java/docs/index.html#news here] [http://lucene.apache.org/java/docs/index.html?b=c here] [https://lucene.apache.org/java/docs/index.html?b=c here]";
    WikipediaTokenizer tf = new WikipediaTokenizer(new StringReader(test));
    assertTokenStreamContents(tf,
        new String[] { "http://lucene.apache.org/java/docs/index.html#news", "here",
          "http://lucene.apache.org/java/docs/index.html?b=c", "here",
          "https://lucene.apache.org/java/docs/index.html?b=c", "here" },
        new String[] { EXTERNAL_LINK_URL, EXTERNAL_LINK,
View Full Code Here
125
126
127
128
129
130
131
132
133
134
135
136
137
138
  public void testLucene1133() throws Exception {
    Set<String> untoks = new HashSet<String>();
    untoks.add(WikipediaTokenizer.CATEGORY);
    untoks.add(WikipediaTokenizer.ITALICS);
    //should be exactly the same, regardless of untoks
    WikipediaTokenizer tf = new WikipediaTokenizer(new StringReader(LINK_PHRASES), WikipediaTokenizer.TOKENS_ONLY, untoks);
    checkLinkPhrases(tf);
    String test = "[[Category:a b c d]] [[Category:e f g]] [[link here]] [[link there]] ''italics here'' something ''more italics'' [[Category:h   i   j]]";
    tf = new WikipediaTokenizer(new StringReader(test), WikipediaTokenizer.UNTOKENIZED_ONLY, untoks);
    assertTokenStreamContents(tf,
        new String[] { "a b c d", "e f g", "link", "here", "link",
          "there", "italics here", "something", "more italics", "h   i   j" },
        new int[] { 11, 32, 42, 47, 56, 61, 71, 86, 98, 124 },
        new int[] { 18, 37, 46, 51, 60, 66, 83, 95, 110, 133 },
View Full Code Here
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
    Set<String> untoks = new HashSet<String>();
    untoks.add(WikipediaTokenizer.CATEGORY);
    untoks.add(WikipediaTokenizer.ITALICS);
    String test = "[[Category:a b c d]] [[Category:e f g]] [[link here]] [[link there]] ''italics here'' something ''more italics'' [[Category:h   i   j]]";
    //should output all the indivual tokens plus the untokenized tokens as well.  Untokenized tokens
    WikipediaTokenizer tf = new WikipediaTokenizer(new StringReader(test), WikipediaTokenizer.BOTH, untoks);
    assertTokenStreamContents(tf,
        new String[] { "a b c d", "a", "b", "c", "d", "e f g", "e", "f", "g",
          "link", "here", "link", "there", "italics here", "italics", "here",
          "something", "more italics", "more", "italics", "h   i   j", "h", "i", "j" },
        new int[] { 11, 11, 13, 15, 17, 32, 32, 34, 36, 42, 47, 56, 61, 71, 71, 79, 86, 98,  98,  103, 124, 124, 128, 132 },
        new int[] { 18, 12, 14, 16, 18, 37, 33, 35, 37, 46, 51, 60, 66, 83, 78, 83, 95, 110, 102, 110, 133, 125, 129, 133 },
        new int[] { 1,  0,  1,  1,  1,  1,  0,  1,  1,  1,  1,  1,  1,  1,  0,  1,  1,  1,   0,   1,   1,   0,   1,   1 }
       );
   
    // now check the flags, TODO: add way to check flags from BaseTokenStreamTestCase?
    tf = new WikipediaTokenizer(new StringReader(test), WikipediaTokenizer.BOTH, untoks);
    int expectedFlags[] = new int[] { UNTOKENIZED_TOKEN_FLAG, 0, 0, 0, 0, UNTOKENIZED_TOKEN_FLAG, 0, 0, 0, 0,
        0, 0, 0, UNTOKENIZED_TOKEN_FLAG, 0, 0, 0, UNTOKENIZED_TOKEN_FLAG, 0, 0, UNTOKENIZED_TOKEN_FLAG, 0, 0, 0 };
    FlagsAttribute flagsAtt = tf.addAttribute(FlagsAttribute.class);
    tf.reset();
    for (int i = 0; i < expectedFlags.length; i++) {
      assertTrue(tf.incrementToken());
      assertEquals("flags " + i, expectedFlags[i], flagsAtt.getFlags());
    }
    assertFalse(tf.incrementToken());
    tf.close();
  }
View Full Code Here
38
39
40
41
42
43
44
45
46
47
48
public class WikipediaTokenizerTest extends BaseTokenStreamTestCase {
  protected static final String LINK_PHRASES = "click [[link here again]] click [http://lucene.apache.org here again] [[Category:a b c d]]";

  public void testSimple() throws Exception {
    String text = "This is a [[Category:foo]]";
    WikipediaTokenizer tf = new WikipediaTokenizer(new StringReader(text));
    assertTokenStreamContents(tf,
        new String[] { "This", "is", "a", "foo" },
        new int[] { 0, 5, 8, 21 },
        new int[] { 4, 7, 9, 24 },
        new String[] { "<ALPHANUM>", "<ALPHANUM>", "<ALPHANUM>", CATEGORY },
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.wikipedia.WikipediaTokenizer

  • org.apache.lucene.analysis.core.TestBugInSomething
  • org.apache.lucene.analysis.wikipedia.WikipediaTokenizerFactory
  • org.apache.lucene.analysis.wikipedia.WikipediaTokenizerTest
  • org.apache.mahout.analysis.WikipediaAnalyzer
  • org.apache.mahout.text.wikipedia.WikipediaAnalyzer
  • org.apache.solr.analysis.WikipediaTokenizerFactory
    • 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.