Lucene分析器的實現(xiàn)。

Lucene分詞器Tokenizer，它的繼承子類的實現(xiàn)。

Tokenizer類的繼承關(guān)系，如圖所示：

ChineseTokenizer類實現(xiàn)中文分詞

中文分詞在Lucene中的處理很簡單，就是單個字分。它的實現(xiàn)類為ChineseTokenizer，在包org.apache.lucene.analysis.cn中，源代碼如下：

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) {??? // 對待分詞的文本進行預(yù)處理，輸入到緩沖區(qū)buffer中

??????? if (length == 0) start = offset-1;??????????? // 根據(jù)詞條長度，設(shè)置起始位置索引
??????? buffer[length++] = Character.toLowerCase(c); // 預(yù)處理：將中文Unicode碼轉(zhuǎn)化成小寫

??? }

??? private final Token flush() { // 根據(jù)緩沖區(qū)預(yù)處理后的文本，構(gòu)造詞條

??????? if (length>0) {
??????????? return new Token(new String(buffer, 0, length), start, start+length);
??????? }
??????? else
??????????? return null;
??? }

??? public final Token next() throws java.io.IOException {??? // 返回下一個詞條

??????? length = 0;
??????? start = offset;

??????? while (true) {

??????????? final char c;
??????????? offset++;

??????????? if (bufferIndex >= dataLen) { // 當緩沖區(qū)沒有溢出
??????????????? dataLen = input.read(ioBuffer);
??????????????? bufferIndex = 0;
??????????? }

??????????? if (dataLen == -1) return flush();
??????????? else
??????????????? c = 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--;
??????????????????? offset--;
??????????????????? return flush();
??????????????? }
??????????????? push(c);
??????????????? return flush();

??????????? default:
??????????????? if (length>0) return flush();
??????????????? break;
??????????? }
??????? }

??? }
}

這里，還提及到一個CJKTokenizer分詞類，它處理分詞的時候，比ChineseTokenizer分詞處理要好一點，但是也存在弊病，源代碼給了一個例子，如下：

如果一個中文詞匯C1C2C3C4被索引，使用ChineseTokenizer分詞，返回的詞條(Token)為：C1，C2，C3，C4；使用CJKTokenizer進行分詞，則返回的詞條(Token)為：C1C2，C2C3，C3C4。

問題在于：當檢索關(guān)鍵字為C1，C1C2，C1C3，C4C2，C1C2C3……的時候，ChineseTokenizer可以對其實現(xiàn)分詞，而CJKTokenizer就不能實現(xiàn)分詞了。

CJKTokenizer類實現(xiàn)中文分詞

CJKTokenizer類的源代碼如下所示：

package org.apache.lucene.analysis.cjk;

import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.Tokenizer;

import java.io.Reader;

public final class CJKTokenizer extends Tokenizer {
????? /** Max word length */
??? private static final int MAX_WORD_LEN = 255;

?? /** buffer size: */
??? private static final int IO_BUFFER_SIZE = 256;

???? /** word offset, used to imply which character(in ) is parsed */
??? private int offset = 0;

??? /** the index used only for ioBuffer */
??? private int bufferIndex = 0;

??? /** data length */
??? private int dataLen = 0;

??? /**
???? * 字符緩沖區(qū)，存儲那些經(jīng)過處理后返回的詞條
???? */
??? private final char[] buffer = new char[MAX_WORD_LEN];

??? /**
???? * I/O buffer, used to store the content of the input(one of the <br>
???? * members of Tokenizer)
???? */
??? private final char[] ioBuffer = new char[IO_BUFFER_SIZE];

??? /** word type: single=>ASCII double=>non-ASCII word=>default */
??? private String tokenType = "word";

??? private boolean preIsTokened = false;

?????? public CJKTokenizer(Reader in) {
??????? input = in;
??? }

????????? public final Token next() throws java.io.IOException {

??????? int length = 0;

??????? /** the position used to create Token */
??????? int start = offset;

??????? while (true) {
??????????? /** current charactor */
??????????? char c;

??????????? /** unicode block of current charactor for detail */
??????????? Character.UnicodeBlock ub;

??????????? offset++;

??????????? if (bufferIndex >= dataLen) {
??????????????? dataLen = input.read(ioBuffer);
??????????????? bufferIndex = 0;
??????????? }

??????????? if (dataLen == -1) {
??????????????? if (length > 0) {
??????????????????? if (preIsTokened == true) {
??????????????????????? length = 0;
??????????????????????? preIsTokened = false;
??????????????????? }

??????????????????? break;
??????????????? } else {
??????????????????? return null;
??????????????? }
??????????? } else {
??????????????? //get current character
??????????????? c = ioBuffer[bufferIndex++];

??????????????? //get the UnicodeBlock of the current character
??????????????? ub = Character.UnicodeBlock.of(c);
??????????? }

??????????? //if the current character is ASCII or Extend ASCII
??????????? if ((ub == Character.UnicodeBlock.BASIC_LATIN)
??????????????????? || (ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS)
?????????????? ) {
??????????????? if (ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {
??????????????????? /** convert HALFWIDTH_AND_FULLWIDTH_FORMS to BASIC_LATIN */
??????????????????? int i = (int) c;
??????????????????? i = i - 65248;
??????????????????? c = (char) i;
??????????????? }

??????????????? // if the current character is a letter or "_" "+" "#"
??????????????? if (Character.isLetterOrDigit(c)
??????????????????????? || ((c == '_') || (c == '+') || (c == '#'))
?????????????????? ) {
??????????????????? if (length == 0) {
??????????????????????? // "javaC1C2C3C4linux" <br>
??????????????????????? //????? ^--: the current character begin to token the ASCII
??????????????????????? // letter
??????????????????????? start = offset - 1;
??????????????????? } else if (tokenType == "double") {
??????????????????????? offset--;
??????????????????????? bufferIndex--;
??????????????????????? tokenType = "single";

??????????????????????? if (preIsTokened == true) {
??????????????????????????? // there is only one non-ASCII has been stored
??????????????????????????? length = 0;
??????????????????????????? preIsTokened = false;

??????????????????????????? break;
??????????????????????? } else {
??????????????????????????? break;
??????????????????????? }
??????????????????? }

??????????????????? // store the LowerCase(c) in the buffer
??????????????????? buffer[length++] = Character.toLowerCase(c);
??????????????????? tokenType = "single";

??????????????????? // break the procedure if buffer overflowed!
??????????????????? if (length == MAX_WORD_LEN) {
??????????????????????? break;
??????????????????? }
??????????????? } else if (length > 0) {
??????????????????? if (preIsTokened == true) {
??????????????????????? length = 0;
??????????????????????? preIsTokened = false;
??????????????????? } else {
??????????????????????? break;
??????????????????? }
??????????????? }
??????????? } else {
?????????????? // non-ASCII letter, eg."C1C2C3C4"
??????????????? if (Character.isLetter(c)) {
??????????????????? if (length == 0) {
??????????????????????? start = offset - 1;
??????????????????????? buffer[length++] = c;
??????????????????????? tokenType = "double";
??????????????????? } else {
??????????????????????? if (tokenType == "single") {
??????????????????????????? offset--;
??????????????????????????? bufferIndex--;

??????????????????????????? //return the previous ASCII characters
??????????????????????????? break;
??????????????????????? } else {
??????????????????????????? buffer[length++] = c;
??????????????????????????? tokenType = "double";

??????????????????????????? if (length == 2) {
??????????????????????????????? offset--;
??????????????????????????????? bufferIndex--;
??????????????????????????????? preIsTokened = true;

??????????????????????????????? break;
??????????????????????????? }
??????????????????????? }
??????????????????? }
??????????????? } else if (length > 0) {
??????????????????? if (preIsTokened == true) {
??????????????????????? // empty the buffer
??????????????????????? length = 0;
??????????????????????? preIsTokened = false;
??????????????????? } else {
??????????????????????? break;
??????????????????? }
??????????????? }
??????????? }
??????? }

??????? return new Token(new String(buffer, 0, length), start, start + length,
???????????????????????? tokenType
??????????????????????? );
??? }
}

?

Lucene-2.2.0 源代碼閱讀學習(6)