Examples with NormalizeCharMap org.apache.lucene.analysis.charfilter.NormalizeCharMap used on opensource projects

Example 6 with NormalizeCharMap

use of org.apache.lucene.analysis.charfilter.NormalizeCharMap in project lucene-solr by apache.

the class TestCompoundWordTokenFilter method testInvalidOffsets.

// SOLR-2891
// *CompoundWordTokenFilter blindly adds term length to offset, but this can take things out of bounds
// wrt original text if a previous filter increases the length of the word (in this case ü -> ue)
// so in this case we behave like WDF, and preserve any modified offsets
public void testInvalidOffsets() throws Exception {
    final CharArraySet dict = makeDictionary("fall");
    final NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
    builder.add("ü", "ue");
    final NormalizeCharMap normMap = builder.build();
    Analyzer analyzer = new Analyzer() {

        @Override
        protected TokenStreamComponents createComponents(String fieldName) {
            Tokenizer tokenizer = new MockTokenizer(MockTokenizer.WHITESPACE, false);
            TokenFilter filter = new DictionaryCompoundWordTokenFilter(tokenizer, dict);
            return new TokenStreamComponents(tokenizer, filter);
        }

        @Override
        protected Reader initReader(String fieldName, Reader reader) {
            return new MappingCharFilter(normMap, reader);
        }
    };
    assertAnalyzesTo(analyzer, "banküberfall", new String[] { "bankueberfall", "fall" }, new int[] { 0, 0 }, new int[] { 12, 12 });
    analyzer.close();
}

Example 7 with NormalizeCharMap

use of org.apache.lucene.analysis.charfilter.NormalizeCharMap in project lucene-solr by apache.

the class UkrainianMorfologikAnalyzer method initReader.

@Override
protected Reader initReader(String fieldName, Reader reader) {
    NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
    // different apostrophes
    builder.add("’", "'");
    builder.add("‘", "'");
    builder.add("ʼ", "'");
    builder.add("`", "'");
    builder.add("´", "'");
    // ignored characters
    builder.add("́", "");
    builder.add("­", "");
    builder.add("ґ", "г");
    builder.add("Ґ", "Г");
    NormalizeCharMap normMap = builder.build();
    reader = new MappingCharFilter(normMap, reader);
    return reader;
}

Example 8 with NormalizeCharMap

use of org.apache.lucene.analysis.charfilter.NormalizeCharMap in project lucene-solr by apache.

the class TestPathHierarchyTokenizer method testNormalizeWinDelimToLinuxDelim.

public void testNormalizeWinDelimToLinuxDelim() throws Exception {
    NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
    builder.add("\\", "/");
    NormalizeCharMap normMap = builder.build();
    String path = "c:\\a\\b\\c";
    Reader cs = new MappingCharFilter(normMap, new StringReader(path));
    PathHierarchyTokenizer t = new PathHierarchyTokenizer(newAttributeFactory(), DEFAULT_DELIMITER, DEFAULT_DELIMITER, DEFAULT_SKIP);
    t.setReader(cs);
    assertTokenStreamContents(t, new String[] { "c:", "c:/a", "c:/a/b", "c:/a/b/c" }, new int[] { 0, 0, 0, 0 }, new int[] { 2, 4, 6, 8 }, new int[] { 1, 0, 0, 0 }, path.length());
}