jdbm开源文件数据库在全文检索中的使用

import jdbm.*;
。。。
JDBMRecordManager newsindex = new JDBMRecordManager(filename);
JDBMHashtable hashtable = newsindex.getHashtable("words");
。。。
//建立索引方法，wordBreaker将文章敲碎成一个个词
public void index(String docid, String body) {
try {
wordBreaker.setText(body);
String[] words = wordBreaker.breakAll();
for (int i = 0; i < words.length; i++) {
if (words != null && words.length() != 0) {
String docs = (String) hashtable.get(words);
if (docs == null) {
hashtable.put(words, docid);
}
else {
if(docs.indexOf(docid)==-1){
hashtable.put(words, docid + "," + docs);
}
}
}
}
}
catch (Exception ex) {
ex.printStackTrace();
}
}
//输出所有数据看看，测试使用的方法
public void show(){
try {
JDBMEnumeration enum = hashtable.keys();
while (enum.hasMoreElements()) {
String aKey= (String)enum.nextElement();
String value= (String)hashtable.get(aKey);
System.out.println(aKey+ ":" + value);
}
}
catch (Exception ex) {
}
}
//记得关闭jdbm文件
public void close(){
try {
hashtable.dispose();
newsindex.close();
}
catch (Exception ex) {
}
}
另外附上二元分词程序WordBreaker：
import java.text.*;
import java.util.*;
public class WordBreaker {
char[] punctuations = new char[] {
'。', '，', '；', '：', '“', '”', '（', '）', '！', '？', '◎', '＃', '￥', '％', '…',
'※', '×', '【', '】', '『', '』', '《', '》', '、'};
public WordBreaker() {
}
public void setText(String text){
this.sourceText = text;
}
private String sourceText = "";
public String[] breakAll() {
StringBuffer enWord = new StringBuffer();
StringBuffer cnWord = new StringBuffer();
boolean lastInsertCn = false;
for (int i = 0; i < sourceText.length(); i++) {
char c = sourceText.charAt(i);
if (c > 255 && isWord(c)) {
cnWord.append(c);
lastInsertCn = true;
}
else if (c < 255) {
if (lastInsertCn) {
enWord.append(' ');
enWord.append(c);
lastInsertCn = false;
}
else {
enWord.append(c);
}
}
}
String str = cnWord.toString();
String[] result = new String[str.length() - 1];
for (int i = 0; i < str.length() - 1; i++) {
char c1 = str.charAt(i);
char c2 = str.charAt(i + 1);
result = "" + c1 + c2;
}
String[] allEnWords = enWord.toString().split("\\p{Punct}|\\s+");
String[] ret = new String[allEnWords.length + result.length];
System.arraycopy(result,0,ret,0,result.length);
System.arraycopy(allEnWords,0,ret,result.length,allEnWords.length);
return ret;
}
public static void main(String[] args) {
WordBreaker wb = new WordBreaker();
wb.setText("在目前的80名发审委员的机制下，监管部门人员不足1/3，"
+ "没有绝对话语权。发审委的工作等于是完全独立于监管部门之上的。"
+ "从这个意义上，面对市场的诘责，证监会有替人受过之嫌。");
wb.printArray(wb.breakAll());
}
private void printArray(Object[] os) {
for (int i = 0; i < os.length; i++) {
System.out.println(os);
}
}
private boolean isWord(char c) {
for (int i = 0; i < punctuations.length; i++) {
if (c == punctuations) {
return false;
}
}
return true;
}
}