third_codes/elasticsearch-analysis-ik
1
0
Fork 0
Code Issues 1 Pull Requests Packages Projects Releases Wiki Activity

make it work with the latest elasticsearch

Browse Source
This commit is contained in:
arkxu 2013-11-10 18:03:29 -08:00
parent ce6e7fd070
commit 6480991bbb
10 changed files with 40 additions and 49 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
pom.xml
View File

@ -31,7 +31,7 @@
</parent>
<properties>
<elasticsearch.version>0.90.2</elasticsearch.version>
<elasticsearch.version>0.90.6</elasticsearch.version>
</properties>
<repositories>
@ -76,6 +76,7 @@
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.10</version>
<scope>test</scope>
</dependency>
</dependencies>

20
src/main/java/org/elasticsearch/index/analysis/IkAnalyzerProvider.java
View File

@ -12,28 +12,14 @@ import org.wltea.analyzer.lucene.IKAnalyzer;
public class IkAnalyzerProvider extends AbstractIndexAnalyzerProvider<IKAnalyzer> {
private final IKAnalyzer analyzer;
@Inject
public IkAnalyzerProvider(Index index, @IndexSettings Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
super(index, indexSettings, name, settings);
Dictionary.initial(new Configuration(settings));
analyzer=new IKAnalyzer(indexSettings,settings);
Dictionary.initial(new Configuration(env));
analyzer=new IKAnalyzer(indexSettings, settings, env);
}
public IkAnalyzerProvider(Index index, Settings indexSettings, String name,
Settings settings) {
super(index, indexSettings, name, settings);
Dictionary.initial(new Configuration(settings));
analyzer=new IKAnalyzer(indexSettings,settings);
}
public IkAnalyzerProvider(Index index, Settings indexSettings,
String prefixSettings, String name, Settings settings) {
super(index, indexSettings, prefixSettings, name, settings);
Dictionary.initial(new Configuration(settings));
analyzer=new IKAnalyzer(indexSettings,settings);
}
@Override public IKAnalyzer get() {
return this.analyzer;
}

13
src/main/java/org/elasticsearch/index/analysis/IkTokenizerFactory.java
View File

@ -4,6 +4,7 @@ import org.apache.lucene.analysis.Tokenizer;
import org.elasticsearch.common.inject.Inject;
import org.elasticsearch.common.inject.assistedinject.Assisted;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.Index;
import org.elasticsearch.index.settings.IndexSettings;
import org.wltea.analyzer.cfg.Configuration;
@ -13,18 +14,20 @@ import org.wltea.analyzer.lucene.IKTokenizer;
import java.io.Reader;
public class IkTokenizerFactory extends AbstractTokenizerFactory {
private Environment environment;
private Settings settings;
@Inject
public IkTokenizerFactory(Index index,@IndexSettings Settings indexSettings,@Assisted String name, @Assisted Settings settings) {
super(index, indexSettings, name, settings);
this.settings=settings;
Dictionary.initial(new Configuration(settings));
public IkTokenizerFactory(Index index, @IndexSettings Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
super(index, indexSettings, name, settings);
this.environment = env;
this.settings = settings;
Dictionary.initial(new Configuration(env));
}
@Override
public Tokenizer create(Reader reader) {
return new IKTokenizer(reader, settings);
return new IKTokenizer(reader, settings, environment);
}
}

13
src/main/java/org/wltea/analyzer/cfg/Configuration.java
View File

@ -3,17 +3,16 @@
*/
package org.wltea.analyzer.cfg;
import org.elasticsearch.common.logging.ESLogger;
import org.elasticsearch.common.logging.Loggers;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import java.io.*;
import java.util.ArrayList;
import java.util.InvalidPropertiesFormatException;
import java.util.List;
import java.util.Properties;
import org.elasticsearch.common.logging.ESLogger;
import org.elasticsearch.common.logging.Loggers;
import org.elasticsearch.env.Environment;
public class Configuration {
private static String FILE_NAME = "ik/IKAnalyzer.cfg.xml";
@ -23,10 +22,10 @@ public class Configuration {
private Properties props;
private Environment environment;
public Configuration(Settings settings){
public Configuration(Environment env){
logger = Loggers.getLogger("ik-analyzer");
props = new Properties();
environment=new Environment(settings);
environment = env;
File fileConfig= new File(environment.configFile(), FILE_NAME);

1
src/main/java/org/wltea/analyzer/core/AnalyzeContext.java
View File

@ -32,7 +32,6 @@ import java.util.LinkedList;
import java.util.Map;
import java.util.Set;
import org.wltea.analyzer.cfg.Configuration;
import org.wltea.analyzer.dic.Dictionary;
/**

9
src/main/java/org/wltea/analyzer/core/IKSegmenter.java
View File

@ -29,6 +29,7 @@ import java.util.ArrayList;
import java.util.List;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.wltea.analyzer.cfg.Configuration;
import org.wltea.analyzer.dic.Dictionary;
@ -55,13 +56,17 @@ public final class IKSegmenter {
* IK分词器构造函数
* @param input
*/
public IKSegmenter(Reader input , Settings settings){
public IKSegmenter(Reader input , Settings settings, Environment environment){
this.input = input;
this.cfg = new Configuration(settings);
this.cfg = new Configuration(environment);
this.useSmart = settings.get("use_smart", "true").equals("true");
this.init();
}
public IKSegmenter(Reader input){
new IKSegmenter(input, null,null);
}
// /**
// * IK分词器构造函数
// * @param input

10
src/main/java/org/wltea/analyzer/dic/Dictionary.java
View File

@ -25,16 +25,14 @@
*/
package org.wltea.analyzer.dic;
import org.elasticsearch.common.logging.ESLogger;
import org.elasticsearch.common.logging.Loggers;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.wltea.analyzer.cfg.Configuration;
import java.io.*;
import java.util.Collection;
import java.util.List;
import org.elasticsearch.common.logging.ESLogger;
import org.elasticsearch.common.logging.Loggers;
import org.wltea.analyzer.cfg.Configuration;
/**
* 词典管理类,单子模式
*/

8
src/main/java/org/wltea/analyzer/lucene/IKAnalyzer.java
View File

@ -29,7 +29,7 @@ import java.io.Reader;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Tokenizer;
import org.elasticsearch.common.settings.Settings;
import org.wltea.analyzer.dic.Dictionary;
import org.elasticsearch.env.Environment;
/**
* IK分词器，Lucene Analyzer接口实现
@ -67,10 +67,12 @@ public final class IKAnalyzer extends Analyzer{
}
Settings settings;
Environment environment;
public IKAnalyzer(Settings indexSetting,Settings settings) {
public IKAnalyzer(Settings indexSetting,Settings settings, Environment environment) {
super();
this.settings=settings;
this.environment= environment;
}
/**
@ -78,7 +80,7 @@ public final class IKAnalyzer extends Analyzer{
*/
@Override
protected TokenStreamComponents createComponents(String fieldName, final Reader in) {
Tokenizer _IKTokenizer = new IKTokenizer(in , settings);
Tokenizer _IKTokenizer = new IKTokenizer(in , settings, environment);
return new TokenStreamComponents(_IKTokenizer);
}

7
src/main/java/org/wltea/analyzer/lucene/IKTokenizer.java
View File

@ -33,9 +33,8 @@ import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import org.elasticsearch.common.settings.ImmutableSettings;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.wltea.analyzer.core.IKSegmenter;
import org.wltea.analyzer.core.Lexeme;
@ -61,13 +60,13 @@ public final class IKTokenizer extends Tokenizer {
* Lucene 4.0 Tokenizer适配器类构造函数
* @param in
*/
public IKTokenizer(Reader in , Settings settings){
public IKTokenizer(Reader in , Settings settings, Environment environment){
super(in);
offsetAtt = addAttribute(OffsetAttribute.class);
termAtt = addAttribute(CharTermAttribute.class);
typeAtt = addAttribute(TypeAttribute.class);
_IKImplement = new IKSegmenter(input , settings);
_IKImplement = new IKSegmenter(input , settings, environment);
}
/* (non-Javadoc)

5
src/main/java/org/wltea/analyzer/query/SWMCQueryBuilder.java
View File

@ -34,7 +34,6 @@ import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.Query;
import org.apache.lucene.util.Version;
import org.elasticsearch.common.settings.Settings;
import org.wltea.analyzer.core.IKSegmenter;
import org.wltea.analyzer.core.Lexeme;
@ -71,8 +70,8 @@ public class SWMCQueryBuilder {
*/
private static List<Lexeme> doAnalyze(String keywords){
List<Lexeme> lexemes = new ArrayList<Lexeme>();
Settings settings=null;
IKSegmenter ikSeg = new IKSegmenter(new StringReader(keywords) , settings);
IKSegmenter ikSeg = new IKSegmenter(new StringReader(keywords));
try{
Lexeme l = null;
while( (l = ikSeg.next()) != null){