Created
January 21, 2011 00:11
-
-
Save karussell/788990 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"index" : { | |
"refresh_interval" : "2s", | |
"analysis" : { | |
"analyzer" : { | |
"myanalyzer" : { | |
"tokenizer" : "standard", | |
"filter" : ["standard", "lowercase", "stop"] | |
} | |
}, | |
"filter" : { | |
"jetwickfilter": { | |
"type" : "de.jetwick.es.JetwickFilterFactory" | |
} | |
} | |
} | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package de.jetwick.es; | |
import org.apache.lucene.analysis.CharArraySet; | |
import org.apache.lucene.analysis.TokenStream; | |
import de.jetwick.org.apache.solr.analysis.WordDelimiterFilter; | |
import org.elasticsearch.common.settings.Settings; | |
import org.elasticsearch.index.Index; | |
import org.elasticsearch.index.analysis.AbstractTokenFilterFactory; | |
public class JetwickFilterFactory extends AbstractTokenFilterFactory { | |
public JetwickFilterFactory(Index index, Settings indexSettings, String name, Settings settings) { | |
super(index, indexSettings, name); | |
} | |
private CharArraySet protectedWords = null; | |
int generateWordParts = 0; | |
int generateNumberParts = 0; | |
int catenateWords = 0; | |
int catenateNumbers = 0; | |
int catenateAll = 0; | |
int splitOnCaseChange = 0; | |
int splitOnNumerics = 0; | |
int preserveOriginal = 0; | |
int stemEnglishPossessive = 0; | |
String handleAsChar = ""; | |
String handleAsDigit = "@#"; | |
@Override | |
public TokenStream create(TokenStream tokenStream) { | |
byte[] tab = new byte[256]; | |
for (int i = 0; i < 256; i++) { | |
byte code = 0; | |
if (Character.isLowerCase(i) || handleAsChar.contains(String.valueOf((char) i))) { | |
code |= WordDelimiterFilter.LOWER; | |
} else if (Character.isUpperCase(i)) { | |
code |= WordDelimiterFilter.UPPER; | |
} else if (Character.isDigit(i) || handleAsDigit.contains(String.valueOf((char) i))) { | |
code |= WordDelimiterFilter.DIGIT; | |
} | |
if (code == 0) { | |
code = WordDelimiterFilter.SUBWORD_DELIM; | |
} | |
tab[i] = code; | |
} | |
return new WordDelimiterFilter(tokenStream, tab, | |
generateWordParts, generateNumberParts, | |
catenateWords, catenateNumbers, catenateAll, | |
splitOnCaseChange, preserveOriginal, | |
splitOnNumerics, stemEnglishPossessive, protectedWords); | |
} | |
@Override | |
public String name() { | |
return "jetwickfilter"; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment