DBCP数据库连接池

Thu, 25 Oct 2007 05:51:00 GMT

摘要: 对于数据库数据不停的��d��和更改，频繁的徏立Connection是很不划��，建立�q�接池是很好的选择�Q�在多个数据库数据之间来回倒换�Q�需要�ؓ每个数据库徏立一个池�Q�本例的目的��是建立一个管理这些池的管理类�Q�达到的目的是：在我们需要一个链接的时候，只要提供需要那个连接池�Q�每个连接池对于一个名字，所有的�q�接池都装蝲入一个Map中）的名字，��可以得到链接进行操作，完毕需要关闭，关闭�q�个链接�q�不会真正的关闭�Q�在池中他还是存在的阅读全文

风舞�?/a> 2007-10-25 13:51 发表评论

Wed, 22 Aug 2007 06:30:00 GMT

�|�络上有很多lucene的分词介�l�，但没有注释，看的云里��N��Q�自��q��了点源代码，做了�Ҏ��释�?/span>

自己写的分词都必��ȝ��?/span>Analyzer�Q�而这�?/span>Analyzer的源代码是这��L��Q?/span>

package org.apache.lucene.analysis;

import java.io.Reader;

public abstract class Analyzer

{

public abstract TokenStream tokenStream(String string, Reader reader);

public int getPositionIncrementGap(String fieldName) {

return 0;

}

�U�色抽象�Ҏ��需要实玎ͼ��q�回的类型是TokenStream�Q��?/span>TokenStream是个抽象�c�，看源代码�Q?/span>

package org.apache.lucene.analysis;

import java.io.IOException;

public abstract class TokenStream

{

public abstract Token next() throws IOException;

public void close() throws IOException {

/* empty */

}

所以返回的应该是这个抽象类的实现类的实例。，在这个抽象类中，有个抽象�Ҏ��Q�红色粗体）需要具体实玎ͼ��q�回Token�Q?/span>Token又是一个类�Q�源代码是：

package org.apache.lucene.analysis;

public final class Token

{

String termText;

int startOffset;

int endOffset;

String type = "word";

private int positionIncrement = 1;

public Token(String text, int start, int end) {

termText = text;

startOffset = start;

endOffset = end;

}

public Token(String text, int start, int end, String typ) {

termText = text;

startOffset = start;

endOffset = end;

type = typ;

}

。。�?/span>

public final String toString() {

StringBuffer sb = new StringBuffer();

sb.append("(" + termText + "," + startOffset + "," + endOffset);

if (!type.equals("word"))

sb.append(",type=" + type);

if (positionIncrement != 1)

sb.append(",posIncr=" + positionIncrement);

sb.append(")");

return sb.toString();

}

四个基本参数构造了他的样子Token 格式:(word,开�?/span>,�l�束,�c�d��)

所以我们要�?/span>next�Q�）�Ҏ��中得到这��L��Token�?/span>

分析到此为止�Q�看个实在的�Q?/span>

首先有个�c�要�l�承Analyzer

public class ChineseAnalyzer extends Analyzer {

public final static String[] STOP_WORDS = {"�?/span>","�?/span>"};

private Set stopTable;

public MMChineseAnalyzer() {

stopTable = StopFilter.makeStopSet(STOP_WORDS);

}

public TokenStream tokenStream(String fieldName, Reader reader) {

return new StopFilter(new ChineseTokenizer(reader), stopTable);

}

StopFilter�?/span>StopFilter extends TokenFilter�Q��?/span>TokenFilter�?/span>TokenFilter extends TokenStream

所�?/span>StopFilter也是�?/span>TokenStream�?/span>

最主要的是ChineseTokenizer(reader)

他也是个TokenStream�Q�他�l�承ChineseTokenizer extends Tokenizer�Q��?/span>Tokenizer extends TokenStream�Q�所以他也要重蝲next�Q�）�Ҏ��Q?/span>

�q�里采用前向最大匹配，用到字典�Q?/span>

字典加蝲�?/span>TreeMap保存

TreeMap�c�通过使用树来实现Map接口.TreeMap提供�?strong>按排序顺序存储关键字/值对的有效手�D�，同时允许快速检索。不像散列映��，树映��保证它的元素按照关键字升序排序�?/span>

字典加蝲代码

public void loadWords() {

if (dictionary == null) {//防止不停的加�?/span>,吧以及加载的攑ֈ�全局变量

dictionary = new TreeMap();

InputStream is = null;

InputStreamReader isr = null;

BufferedReader br = null;

try {

is = new FileInputStream("c:/dictionary.txt");//字典文�g路径

isr = new InputStreamReader(is, "UTF-8");

br = new BufferedReader(isr);

String word = null;

while ((word = br.readLine()) != null) {

int wordLength = word.length();

if ((word.indexOf("#") == -1)//可以为字典增加注�?/span>,主要前面�?/span>#��可�?/span>

&& (wordLength <= WORD_MAX_LENGTH)) {

dictionary.put(word.intern(), "1");

int i = wordLength - 1;

while (i >= 2) {

String temp = word.substring(0, i).intern();

if (!dictionary.containsKey(temp)) {

dictionary.put(temp, "2");

}

i--;

}

} catch (IOException e) {

e.printStackTrace();

} finally {

try {

if (br != null) {

br.close();

}

if (isr != null) {

isr.close();

}

if (is != null) {

is.close();

}

} catch (IOException e) {

e.printStackTrace();

}

System.out.println(dictionary.size());

}

下面��是next()�Ҏ��

//�q�个next��是�q�回Token 格式:(word,开�?/span>,�l�束,�c�d��)

public Token next() throws IOException {

System.out.println("load dictory");

// 装蝲词典

loadWords();

System.out.println("load dictory over");

StringBuffer word = new StringBuffer();

while (true) {

char c;//一个字�W?/span>

char nextChar;//下个字符

Character.UnicodeBlock cUnicodeBlock;//一个字�W�的所�?/span>unicode�?/span>

Character.UnicodeBlock nextCharUnicodeBlock;//下个字符的所�?/span>unicode�?/span>

offset++;//偏移�?/span>

if (bufferIndex >= dataLength) {//初始�?/span>,��d��input,�q�且�~�存的指针�ؓ开�?/span>

dataLength = input.read(ioBuffer);

bufferIndex = 0;

}

if (dataLength == -1) {//�l�束�q�回

if (word.length() == 0) {

return null;

} else {

break;

}

c = ioBuffer[bufferIndex++];//取得�W�一个字�W?/span>

cUnicodeBlock = Character.UnicodeBlock.of(c);//取得�W�一个字�W�的unicode�?/span>

nextChar = ioBuffer[bufferIndex];//取得下字�W?/span>

nextCharUnicodeBlock = Character.UnicodeBlock.of(nextChar);

//�q?/span>2个字�W�是否是一�?/span>

boolean isSameUnicodeBlock = cUnicodeBlock.toString()

.equalsIgnoreCase(nextCharUnicodeBlock.toString());

//�W�一字符是亚�z�字

if (cUnicodeBlock == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS) {

//�c�d��为双字节

tokenType = "double";//双字�?/span>

if (word.length() == 0) {

word.append(c);

// 增强部分--开�?/span> 字符所�?/span>unicode块不�?/span>,退出��@�?/span> 多余代码

if (word.length() != 0 && (!isSameUnicodeBlock)) {

break;

}

// 增强部分--�l�束

} else {

//�?/span>2个字�W�组�?/span>,是否是字兔R��面有�?/span>,如果�?/span>,增加�?/span>word

String temp = (word.toString() + c).intern();

if (dictionary.containsKey(temp)) {

word.append(c);

// 增强部分--开�?/span>

if (word.length() != 0 && (!isSameUnicodeBlock)) {

break;

}

// 增强部分--�l�束

} else {

bufferIndex--;

offset--;

break;

}

} else if (cUnicodeBlock == Character.UnicodeBlock.BASIC_LATIN) {

tokenType = "single";//单字�?/span>

if (Character.isWhitespace(c)) {

if (word.length() != 0)

break;

} else {

word.append(c);

// 增强部分--开�?/span>

if (word.length() != 0 && (!isSameUnicodeBlock)) {

break;

}

// 增强部分--�l�束

}

System.out.println("word="+word);

}

//构�?/span>token�q�回

Token token = new Token(word.toString(), offset - word.length(),

offset, tokenType);

//word清空

word.setLength(0);

System.out.println(token);

return token;

}

整个while循环��是最主要的了.(END)

风舞�?/a> 2007-08-22 14:30 发表评论

日本亚洲色大成网站www久久 ,亚洲国产超清无码专区,久久精品国产亚洲Aⅴ香蕉

DBCP数据库连接池

断点�l�传 Java版（原）

Java转换全角半角