資源簡介
自己動手制作主題搜索引擎,包含數(shù)據(jù)抓取和搜索,數(shù)據(jù)抓取采用啟發(fā)式爬蟲,搜索利用正常思路
代碼片段和文件信息
package?com.huaban.analysis.jieba;
import?java.util.regex.Pattern;
public?class?CharacterUtil?{
????public?static?Pattern?reSkip?=?Pattern.compile(“(\\d+\\.\\d+|[a-zA-Z0-9]+)“);
????private?static?final?char[]?connectors?=?new?char[]?{?‘+‘?‘#‘?‘&‘?‘.‘?‘_‘?‘-‘?};
????public?static?boolean?isChineseLetter(char?ch)?{
????????if?(ch?>=?0x4E00?&&?ch?<=?0x9FA5)
????????????return?true;
????????return?false;
????}
????public?static?boolean?isEnglishLetter(char?ch)?{
????????if?((ch?>=?0x0041?&&?ch?<=?0x005A)?||?(ch?>=?0x0061?&&?ch?<=?0x007A))
????????????return?true;
????????return?false;
????}
????public?static?boolean?isDigit(char?ch)?{
????????if?(ch?>=?0x0030?&&?ch?<=?0x0039)
????????????return?true;
????????return?false;
????}
????public?static?boolean?isConnector(char?ch)?{
????????for?(char?connector?:?connectors)
????????????if?(ch?==?connector)
????????????????return?true;
????????return?false;
????}
????public?static?boolean?ccFind(char?ch)?{
????????if?(isChineseLetter(ch))
????????????return?true;
????????if?(isEnglishLetter(ch))
????????????return?true;
????????if?(isDigit(ch))
????????????return?true;
????????if?(isConnector(ch))
????????????return?true;
????????return?false;
????}
????/**
?????*?全角?to?半角大寫?to?小寫
?????*?
?????*?@param?input
?????*????????????輸入字符
?????*?@return?轉(zhuǎn)換后的字符
?????*/
????public?static?char?regularize(char?input)?{
????????if?(input?==?12288)?{
????????????return?32;
????????}
????????else?if?(input?>?65280?&&?input?65375)?{
????????????return?(char)?(input?-?65248);
????????}
????????else?if?(input?>=?‘A‘?&&?input?<=?‘Z‘)?{
????????????return?(input?+=?32);
????????}
????????return?input;
????}
}
?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2016-05-21?00:52??search\
?????文件?????????454??2016-05-20?20:30??search\.classpath
?????文件?????????382??2016-05-14?16:51??search\.project
?????目錄???????????0??2016-05-14?16:51??search\.settings\
?????文件?????????598??2016-05-14?16:51??search\.settings\org.eclipse.jdt.core.prefs
?????目錄???????????0??2016-05-21?00:44??search\bin\
?????目錄???????????0??2016-05-20?20:30??search\bin\com\
?????目錄???????????0??2016-05-20?20:30??search\bin\com\huaban\
?????目錄???????????0??2016-05-20?20:30??search\bin\com\huaban\analysis\
?????目錄???????????0??2016-05-20?20:30??search\bin\com\huaban\analysis\jieba\
?????文件????????1546??2016-05-20?20:30??search\bin\com\huaban\analysis\jieba\CharacterUtil.class
?????文件????????5503??2016-05-20?20:30??search\bin\com\huaban\analysis\jieba\DictSegment.class
?????文件????????1703??2016-05-20?20:30??search\bin\com\huaban\analysis\jieba\Hit.class
?????文件????????1226??2016-05-20?20:30??search\bin\com\huaban\analysis\jieba\Jieba
?????文件????????8447??2016-05-20?20:30??search\bin\com\huaban\analysis\jieba\Jieba
?????文件?????????467??2016-05-20?20:30??search\bin\com\huaban\analysis\jieba\Node.class
?????文件????????1104??2016-05-20?20:30??search\bin\com\huaban\analysis\jieba\Pair.class
?????文件?????????842??2016-05-20?20:30??search\bin\com\huaban\analysis\jieba\SegToken.class
?????目錄???????????0??2016-05-20?20:30??search\bin\com\huaban\analysis\jieba\viterbi\
?????文件????????9018??2016-05-20?20:30??search\bin\com\huaban\analysis\jieba\viterbi\FinalSeg.class
?????文件????????7621??2016-05-20?20:30??search\bin\com\huaban\analysis\jieba\WordDictionary.class
?????文件?????5071839??2016-05-20?20:30??search\bin\dict.txt
?????目錄???????????0??2016-05-21?00:44??search\bin\iktest\
?????文件?????????407??2016-05-20?20:30??search\bin\iktest\dict1.txt
?????文件????????1081??2016-05-20?20:30??search\bin\iktest\IKtest.class
?????文件??????391274??2016-05-20?20:30??search\bin\iktest\mydict.txt
?????文件????????5877??2016-05-21?00:44??search\bin\iktest\SAA.class
?????文件????????7859??2016-05-21?00:37??search\bin\iktest\Search.class
?????文件????????2973??2016-05-20?20:34??search\bin\iktest\stopwords.txt
?????文件???????35530??2016-05-20?20:30??search\bin\jieba.java.code.st
?????目錄???????????0??2016-05-20?20:30??search\bin\main\
............此處省略56個文件信息
- 上一篇:項目管理project作業(yè)
- 下一篇:微博分類語料
評論
共有 條評論