Examples of HTMLStripCharFilter

Examples of org.apache.lucene.analysis.charfilter.HTMLStripCharFilter

43
44
45
46
47
48
49
50
51
52
53
54
55
  Set<String> escapedTags = null;
  Pattern TAG_NAME_PATTERN = Pattern.compile("[^\\s,]+");

  @Override
  public HTMLStripCharFilter create(Reader input) {
    HTMLStripCharFilter charFilter;
    if (null == escapedTags) {
      charFilter = new HTMLStripCharFilter(input);
    } else {
      charFilter = new HTMLStripCharFilter(input, escapedTags);
    }
    return charFilter;
  }
View Full Code Here

Examples of org.apache.lucene.analysis.charfilter.HTMLStripCharFilter

182
183
184
185
186
187
188
189
190
191
192
    public void IncrementsOffsetCorrectlyWithAnotherReader() throws IOException {
        int[] expectedOffsets = {0, 5, 10, 15};
        int curPos = 0;

        Tokenizer t = new Tokenizer(
                new HTMLStripCharFilter(new StringReader("test <a href=\"foo\">test</a> test test")), HSpellLoader.readDefaultPrefixes()
        );

        Reference<String> ref = new Reference<String>("");
        while (true) {
            int token_type = t.nextToken(ref);
View Full Code Here

Examples of org.apache.lucene.analysis.charfilter.HTMLStripCharFilter

200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
    @Test
    public void IncrementsOffsetCorrectlyWithAnotherReader2() throws IOException {
        String input = "test1 <a href=\"foo\">testlink</a> test2 test3";

        BaseCharFilter filter = new HTMLStripCharFilter(new StringReader(input));
        Tokenizer t = new Tokenizer(filter, HSpellLoader.readDefaultPrefixes());

        Reference<String> token = new Reference<String>("");

        t.nextToken(token);
        assertEquals(0, filter.correctOffset(t.getOffset()));
        assertEquals(5, t.getLengthInSource());

        t.nextToken(token);
        assertEquals(20, filter.correctOffset(t.getOffset()));
        assertEquals(8, t.getLengthInSource());

        t.nextToken(token);
        assertEquals(33, filter.correctOffset(t.getOffset()));
        assertEquals(5, t.getLengthInSource());

        t.nextToken(token);
        assertEquals(39, filter.correctOffset(t.getOffset()));
        assertEquals(5, t.getLengthInSource());
    }
View Full Code Here

Examples of org.apache.lucene.analysis.charfilter.HTMLStripCharFilter

90
91
92
93
94
95
96
97
98
99
100
101
        return dirHash;
    }

    private static String getTags(File basedir, String path, boolean compressed) {
        char[] content = new char[1024 * 8];
        try (HTMLStripCharFilter r = new HTMLStripCharFilter(getXrefReader(basedir, path, compressed))) {
            int len = r.read(content);
            return new String(content, 0, len);
        } catch (Exception e) {
            OpenGrokLogger.getLogger().log(
                    Level.WARNING, "An error reading tags from " + basedir + path
                    + (compressed ? ".gz" : ""), e);
View Full Code Here

Examples of org.apache.lucene.analysis.charfilter.HTMLStripCharFilter

364
365
366
367
368
369
370
371
372
373
374
375
                                    + filename)), null, null, null, filename,
                                    tags, nhits > 100, false, ret);
                        } else if (Genre.XREFABLE == genre && data != null && summarizer != null) {
                            int l;
                            try (Reader r = RuntimeEnvironment.getInstance().isCompressXref() ?
                                     new HTMLStripCharFilter(new BufferedReader(new InputStreamReader(new GZIPInputStream(new FileInputStream(data + Prefix.XREF_P + filename + ".gz"))))) :
                                     new HTMLStripCharFilter(new BufferedReader(new FileReader(data + Prefix.XREF_P + filename)))) {
                                l = r.read(content);
                            }
                            //TODO FIX below fragmenter according to either summarizer or context (to get line numbers, might be hard, since xref writers will need to be fixed too, they generate just one line of html code now :( )
                            Summary sum = summarizer.getSummary(new String(content, 0, l));
                            Fragment fragments[] = sum.getFragments();
View Full Code Here

Examples of org.apache.lucene.analysis.charfilter.HTMLStripCharFilter

83
84
85
86
87
88
89
      return new TokenStreamComponents(source, result);
    }

    @Override
    protected Reader initReader(String fieldName, Reader reader) {
      return new HTMLStripCharFilter(reader);
    }
View Full Code Here

Examples of org.apache.lucene.analysis.charfilter.HTMLStripCharFilter

51
52
53
54
55
56
57
        return escapedTags;
    }

    @Override
    public Reader create(Reader tokenStream) {
        return new HTMLStripCharFilter(tokenStream, escapedTags);
    }
View Full Code Here

Examples of org.apache.solr.analysis.HTMLStripCharFilter

72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
  private Object stripHTML(String value, String column) {
    StringBuilder out = new StringBuilder();
    StringReader strReader = new StringReader(value);
    try {
      HTMLStripCharFilter html = new HTMLStripCharFilter(CharReader.get(strReader.markSupported() ? strReader : new BufferedReader(strReader)));
      char[] cbuf = new char[1024 * 10];
      while (true) {
        int count = html.read(cbuf);
        if (count == -1)
          break; // end of stream mark is -1
        if (count > 0)
          out.append(cbuf, 0, count);
      }
      html.close();
    } catch (IOException e) {
      throw new DataImportHandlerException(DataImportHandlerException.SEVERE,
              "Failed stripping HTML for column: " + column, e);
    }
    return out.toString();
View Full Code Here

Examples of org.apache.solr.analysis.HTMLStripCharFilter

73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
  private Object stripHTML(String value, String column) {
    StringBuilder out = new StringBuilder();
    StringReader strReader = new StringReader(value);
    try {
      HTMLStripCharFilter html = new HTMLStripCharFilter(CharReader.get(strReader.markSupported() ? strReader : new BufferedReader(strReader)));
      char[] cbuf = new char[1024 * 10];
      while (true) {
        int count = html.read(cbuf);
        if (count == -1)
          break; // end of stream mark is -1
        if (count > 0)
          out.append(cbuf, 0, count);
      }
      html.close();
    } catch (IOException e) {
      throw new DataImportHandlerException(DataImportHandlerException.SEVERE,
              "Failed stripping HTML for column: " + column, e);
    }
    return out.toString();
View Full Code Here

Examples of org.elasticsearch.common.lucene.analysis.HTMLStripCharFilter

55
56
57
58
59
60
61
    public int readAheadLimit() {
        return readAheadLimit;
    }

    @Override public CharStream create(CharStream tokenStream) {
        return new HTMLStripCharFilter(tokenStream, escapedTags, readAheadLimit);
    }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.