honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Analysis: Add phonetic encodder called `bm` or `beider_morse`, closes #1552.

This commit is contained in:
Shay Banon 2011-12-21 03:53:44 +02:00
parent 2b838b808e
commit a488424404
2 changed files with 23 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pom.xml
View File

@ -124,7 +124,7 @@
<dependency> <dependency>
<groupId>commons-codec</groupId> <groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId> <artifactId>commons-codec</artifactId>
<version>1.5</version> <version>1.6</version>
<scope>compile</scope> <scope>compile</scope>
</dependency> </dependency>

22
src/main/java/org/elasticsearch/index/analysis/phonetic/PhoneticTokenFilterFactory.java
View File

@ -21,6 +21,9 @@ package org.elasticsearch.index.analysis.phonetic;
import org.apache.commons.codec.Encoder; import org.apache.commons.codec.Encoder;
import org.apache.commons.codec.language.*; import org.apache.commons.codec.language.*;
import org.apache.commons.codec.language.bm.BeiderMorseEncoder;
import org.apache.commons.codec.language.bm.NameType;
import org.apache.commons.codec.language.bm.RuleType;
import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.TokenStream;
import org.elasticsearch.ElasticSearchIllegalArgumentException; import org.elasticsearch.ElasticSearchIllegalArgumentException;
import org.elasticsearch.common.inject.Inject; import org.elasticsearch.common.inject.Inject;
@ -67,6 +70,25 @@ public class PhoneticTokenFilterFactory extends AbstractTokenFilterFactory {
DoubleMetaphone doubleMetaphone = new DoubleMetaphone(); DoubleMetaphone doubleMetaphone = new DoubleMetaphone();
doubleMetaphone.setMaxCodeLen(settings.getAsInt("max_code_len", doubleMetaphone.getMaxCodeLen())); doubleMetaphone.setMaxCodeLen(settings.getAsInt("max_code_len", doubleMetaphone.getMaxCodeLen()));
this.encoder = doubleMetaphone; this.encoder = doubleMetaphone;
} else if ("bm".equalsIgnoreCase(encoder) || "beider_morse".equalsIgnoreCase(encoder)) {
BeiderMorseEncoder bm = new BeiderMorseEncoder();
String ruleType = settings.get("rule_type", "approx");
if ("approx".equalsIgnoreCase(ruleType)) {
bm.setRuleType(RuleType.APPROX);
} else if ("exact".equalsIgnoreCase(ruleType)) {
bm.setRuleType(RuleType.EXACT);
} else {
throw new ElasticSearchIllegalArgumentException("No matching rule type [" + ruleType + "] for beider morse encoder");
}
String nameType = settings.get("name_type", "generic");
if ("GENERIC".equalsIgnoreCase(nameType)) {
bm.setNameType(NameType.GENERIC);
} else if ("ASHKENAZI".equalsIgnoreCase(nameType)) {
bm.setNameType(NameType.ASHKENAZI);
} else if ("SEPHARDIC".equalsIgnoreCase(nameType)) {
bm.setNameType(NameType.SEPHARDIC);
}
this.encoder = bm;
} else { } else {
throw new ElasticSearchIllegalArgumentException("unknown encoder [" + encoder + "] for phonetic token filter"); throw new ElasticSearchIllegalArgumentException("unknown encoder [" + encoder + "] for phonetic token filter");
} }