当前位置: 技术问答>java相关
lucene中文检索
来源: 互联网 发布时间:2015-06-27
本文导语: lucene只支持检索英文或象英文这种特点的语言. 而不支持中文检索. 不知哪位有好的解决方案或改进过的lucene支持中文检索. | 这个问题在年初就解决了。 我从大富翁的孙老大那学了不少。^_^ ...
lucene只支持检索英文或象英文这种特点的语言.
而不支持中文检索.
不知哪位有好的解决方案或改进过的lucene支持中文检索.
而不支持中文检索.
不知哪位有好的解决方案或改进过的lucene支持中文检索.
|
这个问题在年初就解决了。
我从大富翁的孙老大那学了不少。^_^
下面给你三个类,你看看:
//ChineseTokenizer.java
package org.apache.lucene.analysis.cn;
import java.io.Reader;
import org.apache.lucene.analysis.*;
public final class ChineseTokenizer extends Tokenizer {
public ChineseTokenizer(Reader in) {
input = in;
}
private int offset = 0, bufferIndex=0, dataLen=0;
private final static int MAX_WORD_LEN = 255;
private final static int IO_BUFFER_SIZE = 1024;
private final char[] buffer = new char[MAX_WORD_LEN];
private final char[] ioBuffer = new char[IO_BUFFER_SIZE];
private int length;
private int start;
private final void push(char c) {
if (length == 0) start = offset-1; // start of token
buffer[length++] = Character.toLowerCase(c); // buffer it
}
private final Token flush() {
if (length>0) {
//System.out.println(new String(buffer, 0, length));
return new Token(new String(buffer, 0, length), start, start+length);
}
else
return null;
}
public final Token next() throws java.io.IOException {
length = 0;
start = offset;
while (true) {
final char c;
offset++;
if (bufferIndex >= dataLen) {
dataLen = input.read(ioBuffer);
bufferIndex = 0;
};
if (dataLen == -1) return flush();
else
c = (char) ioBuffer[bufferIndex++];
switch(Character.getType(c)) {
case Character.DECIMAL_DIGIT_NUMBER:
case Character.LOWERCASE_LETTER:
case Character.UPPERCASE_LETTER:
push(c);
if (length == MAX_WORD_LEN) return flush();
break;
case Character.OTHER_LETTER:
if (length>0) {
bufferIndex--;
return flush();
}
push(c);
return flush();
default:
if (length>0) return flush();
break;
}
}
}
}
///////////////////////////////////////////////////////
//ChineseFilter.java
package org.apache.lucene.analysis.cn;
import java.io.Reader;
import java.util.Hashtable;
import org.apache.lucene.analysis.*;
public final class ChineseFilter extends TokenFilter {
// Only English now, Chinese to be added later.
public static final String[] STOP_WORDS = {
"and", "are", "as", "at", "be", "but", "by",
"for", "if", "in", "into", "is", "it",
"no", "not", "of", "on", "or", "such",
"that", "the", "their", "then", "there", "these",
"they", "this", "to", "was", "will", "with"
};
private Hashtable stopTable;
public ChineseFilter(TokenStream in) {
input = in;
stopTable = new Hashtable(STOP_WORDS.length);
for (int i = 0; i 1) {
return token;
}
break;
case Character.OTHER_LETTER:
// One Chinese character as one Chinese word.
// Chinese word extraction to be added later here.
return token;
}
}
}
return null;
}
}
//////////////////////////////////////
//ChineseAnalyzer.java
package org.apache.lucene.analysis.cn;
import java.io.Reader;
import org.apache.lucene.analysis.*;
/**
* Title: ChineseAnalyzer
* Description:
* Subclass of org.apache.lucene.analysis.Analyzer
* build from a ChineseTokenizer, filtered with ChineseFilter.
* Copyright: Copyright (c) 2001
* Company:
* @author Yiyi Sun
* @version 1.0
*
*/
public class ChineseAnalyzer extends Analyzer {
public ChineseAnalyzer() {
}
/**
* Creates a TokenStream which tokenizes all the text in the provided Reader.
*
* @return A TokenStream build from a ChineseTokenizer filtered with ChineseFilter.
*/
public final TokenStream tokenStream(String fieldName, Reader reader) {
TokenStream result = new ChineseTokenizer(reader);
result = new ChineseFilter(result);
return result;
}
}
我后来做了一些修改,加入了自己的功能。这里就不贴出来了。^_^
希望对你有帮助。
我从大富翁的孙老大那学了不少。^_^
下面给你三个类,你看看:
//ChineseTokenizer.java
package org.apache.lucene.analysis.cn;
import java.io.Reader;
import org.apache.lucene.analysis.*;
public final class ChineseTokenizer extends Tokenizer {
public ChineseTokenizer(Reader in) {
input = in;
}
private int offset = 0, bufferIndex=0, dataLen=0;
private final static int MAX_WORD_LEN = 255;
private final static int IO_BUFFER_SIZE = 1024;
private final char[] buffer = new char[MAX_WORD_LEN];
private final char[] ioBuffer = new char[IO_BUFFER_SIZE];
private int length;
private int start;
private final void push(char c) {
if (length == 0) start = offset-1; // start of token
buffer[length++] = Character.toLowerCase(c); // buffer it
}
private final Token flush() {
if (length>0) {
//System.out.println(new String(buffer, 0, length));
return new Token(new String(buffer, 0, length), start, start+length);
}
else
return null;
}
public final Token next() throws java.io.IOException {
length = 0;
start = offset;
while (true) {
final char c;
offset++;
if (bufferIndex >= dataLen) {
dataLen = input.read(ioBuffer);
bufferIndex = 0;
};
if (dataLen == -1) return flush();
else
c = (char) ioBuffer[bufferIndex++];
switch(Character.getType(c)) {
case Character.DECIMAL_DIGIT_NUMBER:
case Character.LOWERCASE_LETTER:
case Character.UPPERCASE_LETTER:
push(c);
if (length == MAX_WORD_LEN) return flush();
break;
case Character.OTHER_LETTER:
if (length>0) {
bufferIndex--;
return flush();
}
push(c);
return flush();
default:
if (length>0) return flush();
break;
}
}
}
}
///////////////////////////////////////////////////////
//ChineseFilter.java
package org.apache.lucene.analysis.cn;
import java.io.Reader;
import java.util.Hashtable;
import org.apache.lucene.analysis.*;
public final class ChineseFilter extends TokenFilter {
// Only English now, Chinese to be added later.
public static final String[] STOP_WORDS = {
"and", "are", "as", "at", "be", "but", "by",
"for", "if", "in", "into", "is", "it",
"no", "not", "of", "on", "or", "such",
"that", "the", "their", "then", "there", "these",
"they", "this", "to", "was", "will", "with"
};
private Hashtable stopTable;
public ChineseFilter(TokenStream in) {
input = in;
stopTable = new Hashtable(STOP_WORDS.length);
for (int i = 0; i 1) {
return token;
}
break;
case Character.OTHER_LETTER:
// One Chinese character as one Chinese word.
// Chinese word extraction to be added later here.
return token;
}
}
}
return null;
}
}
//////////////////////////////////////
//ChineseAnalyzer.java
package org.apache.lucene.analysis.cn;
import java.io.Reader;
import org.apache.lucene.analysis.*;
/**
* Title: ChineseAnalyzer
* Description:
* Subclass of org.apache.lucene.analysis.Analyzer
* build from a ChineseTokenizer, filtered with ChineseFilter.
* Copyright: Copyright (c) 2001
* Company:
* @author Yiyi Sun
* @version 1.0
*
*/
public class ChineseAnalyzer extends Analyzer {
public ChineseAnalyzer() {
}
/**
* Creates a TokenStream which tokenizes all the text in the provided Reader.
*
* @return A TokenStream build from a ChineseTokenizer filtered with ChineseFilter.
*/
public final TokenStream tokenStream(String fieldName, Reader reader) {
TokenStream result = new ChineseTokenizer(reader);
result = new ChineseFilter(result);
return result;
}
}
我后来做了一些修改,加入了自己的功能。这里就不贴出来了。^_^
希望对你有帮助。