elasticsearch 1.1.0 mmseg 英文数字分词

elasticsearch 1.1.0  mmseg 插件的版本是1.2.2 版本。该版本没有解决英文数字分词问题。

比如  user123。分词后 user123

 

解决1：

mmseg插件升级 elasticsearch-analysis-mmseg-1.4.0。
https://github.com/medcl/elasticsearch-analysis-mmseg/commit/61b5e8199425c845a3060fe39f40e59868dd364b 

index:
analysis:
tokenizer:
mmseg_maxword:
type: mmseg
seg_type: max_word
mmseg_complex:
type: mmseg
seg_type: complex
analyzer:
mmseg_maxword:
type: custom
filter:
- lowercase
- cut_letter_digit
tokenizer: mmseg_maxword
mmseg:
type: custom
filter:
- lowercase
- cut_letter_digit
tokenizer: mmseg_maxword
mmseg_complex:
type: custom
filter:
- lowercase
tokenizer: mmseg_complex
#index.analysis.analyzer.default.type : "org.elasticsearch.index.analysis.MMsegAnalyzerProvider"
#index.analysis.analyzer.default.type : "ik"
index.analysis.analyzer.default.type : "mmseg"

 

解决2：

         修改1.2.2 版本jar包中的MMSegAnalyzer，然后替换class

         

package com.chenlb.mmseg4j.analysis;

import java.io.File;
import java.io.Reader;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.Analyzer.TokenStreamComponents;

import com.chenlb.mmseg4j.Dictionary;
import com.chenlb.mmseg4j.MaxWordSeg;
import com.chenlb.mmseg4j.Seg;

/**
* 榛樿浣跨敤 max-word
*
* @see {@link SimpleAnalyzer}, {@link ComplexAnalyzer}, {@link MaxWordAnalyzer}
*
* @author chenlb
*/
public class MMSegAnalyzer extends Analyzer {

protected Dictionary dic;

/**
* @see Dictionary#getInstance()
*/
public MMSegAnalyzer() {
dic = Dictionary.getInstance();
}

/**
* @param path 璇嶅簱璺緞
* @see Dictionary#getInstance(String)
*/
public MMSegAnalyzer(String path) {
dic = Dictionary.getInstance(path);
}

/**
* @param path 璇嶅簱鐩綍
* @see Dictionary#getInstance(File)
*/
public MMSegAnalyzer(File path) {
dic = Dictionary.getInstance(path);
}

public MMSegAnalyzer(Dictionary dic) {
super();
this.dic = dic;
}

protected Seg newSeg() {
return new MaxWordSeg(dic);
}

public Dictionary getDict() {
return dic;
}

/*@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
return new TokenStreamComponents(new MMSegTokenizer(newSeg(), reader));
}*/
@Override
protected TokenStreamComponents createComponents(String fieldName,
Reader reader) {
Tokenizer t = new MMSegTokenizer(newSeg(), reader);
return new TokenStreamComponents(t, new CutLetterDigitFilter(t));
}

}