資源簡介
1.采用經典的vsm模型實現的文本相似度計算。
2.采用中科院ictclas的開源分詞系統
3.包含全部實現源碼
代碼片段和文件信息
package?test;
import?java.util.List;
import?org.ansj.domain.Term;
import?org.ansj.splitWord.analysis.ToAnalysis;
import?org.ansj.util.recognition.NatureRecognition;
import?textReader.*;
public?class?DocWordSegTest?{
/**
?*?@param?args
?*/
public?static?void?main(String[]?args)?{
//?TODO?Auto-generated?method?stub
String?path?=?“d://“;
String?name?=?“test.txt“;
String?content?=?TextExtractor.extractDocFile(path+name);
List?terms?=?ToAnalysis.paser(content);
new?NatureRecognition(terms).recognition();
System.out.println(terms.toString());
}
}
?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2013-03-20?16:34??vsm\
?????文件????????1393??2013-03-20?21:58??vsm\.classpath
?????目錄???????????0??2013-03-29?13:24??vsm\.myeclipse\
?????文件?????????282??2013-03-20?14:59??vsm\.myme
?????文件????????1530??2013-03-20?14:59??vsm\.project
?????目錄???????????0??2013-03-20?14:59??vsm\.settings\
?????文件?????????500??2013-03-20?14:59??vsm\.settings\.jsdtscope
?????文件?????????364??2013-03-20?14:59??vsm\.settings\org.eclipse.jdt.core.prefs
?????文件?????????447??2013-03-20?14:59??vsm\.settings\org.eclipse.wst.common.component
?????文件?????????252??2013-03-20?14:59??vsm\.settings\org.eclipse.wst.common.project.facet.core.xm
?????文件??????????49??2013-03-20?14:59??vsm\.settings\org.eclipse.wst.jsdt.ui.superType.container
?????文件???????????6??2013-03-20?14:59??vsm\.settings\org.eclipse.wst.jsdt.ui.superType.name
?????目錄???????????0??2013-03-20?14:59??vsm\WebRoot\
?????目錄???????????0??2013-03-20?14:59??vsm\WebRoot\me
?????文件??????????36??2013-03-20?14:59??vsm\WebRoot\me
?????目錄???????????0??2013-03-20?14:59??vsm\WebRoot\WEB-INF\
?????目錄???????????0??2013-03-26?14:24??vsm\WebRoot\WEB-INF\classes\
?????目錄???????????0??2013-03-26?22:58??vsm\WebRoot\WEB-INF\classes\test\
?????文件????????1371??2013-03-26?14:33??vsm\WebRoot\WEB-INF\classes\test\DocWordSegTest.class
?????文件????????1049??2013-03-26?14:24??vsm\WebRoot\WEB-INF\classes\test\li
?????文件?????????548??2013-03-26?22:59??vsm\WebRoot\WEB-INF\classes\test\LoggerTest.class
?????文件????????1407??2013-03-27?10:39??vsm\WebRoot\WEB-INF\classes\test\ReadFileTest.class
?????文件????????1698??2013-03-27?22:13??vsm\WebRoot\WEB-INF\classes\test\ResultTest.class
?????文件?????????752??2013-03-26?14:24??vsm\WebRoot\WEB-INF\classes\test\VectorTest.class
?????文件????????4553??2013-03-27?10:38??vsm\WebRoot\WEB-INF\classes\test\WordSegTest.class
?????目錄???????????0??2013-03-26?14:24??vsm\WebRoot\WEB-INF\classes\textReader\
?????目錄???????????0??2013-03-26?14:24??vsm\WebRoot\WEB-INF\classes\textReader\Filters\
?????文件????????2705??2013-03-26?14:24??vsm\WebRoot\WEB-INF\classes\textReader\Filters\ChineseFilter.class
?????文件????????1564??2013-03-26?14:24??vsm\WebRoot\WEB-INF\classes\textReader\Filters\FormatNoiseFilter.class
?????文件????????1195??2013-03-26?14:24??vsm\WebRoot\WEB-INF\classes\textReader\Filters\ParagraphMaker.class
?????文件????????2270??2013-03-26?14:24??vsm\WebRoot\WEB-INF\classes\textReader\Filters\RemarkNoiseFilter.class
............此處省略64個文件信息
- 上一篇:SSM框架在線購物項目
- 下一篇:信息系統項目管理師考試輔導教程第3版(書簽版)
評論
共有 條評論