呵呵,接: //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 < STOP_WORDS.length; i++) stopTable.put(STOP_WORDS[i], STOP_WORDS[i]); } public final Token next() throws java.io.IOException { for (Token token = input.next(); token != null; token = input.next()) { String text = token.termText(); if (stopTable.get(text) == null) { switch (Character.getType(text.charAt(0))) { case Character.LOWERCASE_LETTER: case Character.UPPERCASE_LETTER: // English word/token should larger than 1 character. if (text.length()>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.javapackage 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; } }
解决中文问题的代码有吗?拜托了。
我在lucene的相关论坛上看过,可是,我想对于office文档来说还是要像pdf一样,自己来从数据流中提取文字信息吧?
有free的代码吗?
//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 < STOP_WORDS.length; i++)
stopTable.put(STOP_WORDS[i], STOP_WORDS[i]);
}
public final Token next() throws java.io.IOException {
for (Token token = input.next(); token != null; token = input.next()) {
String text = token.termText();
if (stopTable.get(text) == null) {
switch (Character.getType(text.charAt(0))) {
case Character.LOWERCASE_LETTER:
case Character.UPPERCASE_LETTER:
// English word/token should larger than 1 character.
if (text.length()>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.javapackage 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;
}
}
还有,这段程序应该还是解惜不了office文档吧.
1.没有见中文的“的 了 你 我 ”等常用自过滤掉。
2.因为遇到菲alpha字符就把当作一个汉字返回,这样会把很多中文标点和控制符号也作为token存入index文件。
3.西文的词可以由alpha字符隔断,但是,对于中文,因为词与词之间没有分隔符,所以必须用词典来分词。先试图找到字典中的最大匹配,在字典中没有任何匹配的情况下,才把单个子作为token返回。对于从office文档 pdf中提取text,大家有何高见。好多pdftotext convert都是不支持中文的。
1.没有把中文的“的 了 你 我 ”等超过高频字过滤掉。
2.因为遇到非alpha字符就把当它当作一个汉字返回,这样会把很多中文标点和控制符号也作为token存入index文件。
3.西文的词可以由非alpha字符隔断,但是,对于中文,因为词与词之间没有分隔符,所以必须用词典来分词。先试图找到字典中的最大匹配,在字典中没有任何匹配的情况下,才把单个字作为token返回。对于从office文档 pdf中提取text,大家有何高见。好多pdftotext convert都是不支持中文的。