When the plain text is extracted from documents, we will often have many words hyphenated and broken into two lines. This is often the case with documents where narrow text columns are used, such as newsletters. In order to increase search efficiency, this filter puts hyphenated words broken into two lines back together. This filter should be used on indexing time only. Example field definition in schema.xml: 
 <fieldtype name="text" class="solr.TextField" positionIncrementGap="100"> <analyzer type="index"> <tokenizer class="solr.WhitespaceTokenizerFactory"/> <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> <filter class="solr.StopFilterFactory" ignoreCase="true"/> <filter class="solr.HyphenatedWordsFilterFactory"/> <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/> <filter class="solr.LowerCaseFilterFactory"/> <filter class="solr.RemoveDuplicatesTokenFilterFactory"/> </analyzer> <analyzer type="query"> <tokenizer class="solr.WhitespaceTokenizerFactory"/> <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> <filter class="solr.StopFilterFactory" ignoreCase="true"/> <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/> <filter class="solr.LowerCaseFilterFactory"/> <filter class="solr.RemoveDuplicatesTokenFilterFactory"/> </analyzer> </fieldtype>
Inheritance: TokenFilter
HyphenatedWordsFilter Class Documentation
Esempio n. 1
0
 //JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
 //ORIGINAL LINE: public void testOffsets() throws Exception
 public virtual void testOffsets()
 {
     string input = "abc- def geh 1234- 5678-";
     TokenStream ts = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
     ts = new HyphenatedWordsFilter(ts);
     assertTokenStreamContents(ts, new string[] {"abcdef", "geh", "12345678-"}, new int[] {0, 9, 13}, new int[] {8, 12, 24});
 }
Esempio n. 2
0
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testOffsets() throws Exception
        public virtual void testOffsets()
        {
            string      input = "abc- def geh 1234- 5678-";
            TokenStream ts    = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);

            ts = new HyphenatedWordsFilter(ts);
            assertTokenStreamContents(ts, new string[] { "abcdef", "geh", "12345678-" }, new int[] { 0, 9, 13 }, new int[] { 8, 12, 24 });
        }
Esempio n. 3
0
 /// <summary>
 /// Test that HyphenatedWordsFilter behaves correctly with a final hyphen
 /// </summary>
 //JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
 //ORIGINAL LINE: public void testHyphenAtEnd() throws Exception
 public virtual void testHyphenAtEnd()
 {
     string input = "ecologi-\r\ncal devel-\r\n\r\nop compre-\u0009hensive-hands-on and ecology-";
       // first test
       TokenStream ts = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
       ts = new HyphenatedWordsFilter(ts);
       assertTokenStreamContents(ts, new string[] {"ecological", "develop", "comprehensive-hands-on", "and", "ecology-"});
 }
Esempio n. 4
0
        /// <summary>
        /// Test that HyphenatedWordsFilter behaves correctly with a final hyphen
        /// </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testHyphenAtEnd() throws Exception
        public virtual void testHyphenAtEnd()
        {
            string input = "ecologi-\r\ncal devel-\r\n\r\nop compre-\u0009hensive-hands-on and ecology-";
            // first test
            TokenStream ts = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);

            ts = new HyphenatedWordsFilter(ts);
            assertTokenStreamContents(ts, new string[] { "ecological", "develop", "comprehensive-hands-on", "and", "ecology-" });
        }