-
大小: 964KB文件類型: .rar金幣: 2下載: 0 次發布日期: 2024-02-05
- 語言: Java
- 標簽: ICTCLASjava??
資源簡介
java實現中科大ICTCLAS2015分詞,源代碼和jar包之前都有提供。

代碼片段和文件信息
package?com.code;
import?java.io.UnsupportedEncodingException;
import?utils.SystemParas;
import?com.sun.jna.Library;
import?com.sun.jna.Native;
public?class?NlpirTest?{
//?定義接口CLibrary,繼承自com.sun.jna.Library
public?interface?CLibrary?extends?Library?{
//?定義并初始化接口的靜態變量?這一個語句是來加載?dll?的,?注意?dll?文件的路徑
//可以是絕對路徑也可以是相對路徑,只需要填寫?dll?的文件名,不能加后綴
CLibrary?Instance?=?(CLibrary)?Native.loadLibrary(
“E:\\ICTCLAS2015\\bin\\ICTCLAS2015\\NLPIR“?CLibrary.class);
//?初始化函數聲明
public?int?NLPIR_Init(String?sDataPath?int?encoding
String?sLicenceCode);
//執行分詞函數聲明
public?String?NLPIR_ParagraphProcess(String?sSrc?int?bPOSTagged);
//提取關鍵詞函數聲明
public?String?NLPIR_GetKeyWords(String?sLine?int?nMaxKeyLimit
boolean?bWeightOut);
public?String?NLPIR_GetFileKeyWords(String?sLine?int?nMaxKeyLimit
boolean?bWeightOut);
//添加用戶詞典聲明
public?int?NLPIR_AddUserWord(String?sWord);//add?by?qp?2008.11.10
//刪除用戶詞典聲明
public?int?NLPIR_DelUsrWord(String?sWord);//add?by?qp?2008.11.10
//文件分詞聲明
public?String?NLPIR_GetLastErrorMsg();
//退出函數聲明
public?void?NLPIR_Exit();
public?void?NLPIR_FileProcess(byte[]?bytes?byte[]?bytes2?int?i);
}
public?static?String?transString(String?aidString?String?ori_encoding
String?new_encoding)?{
try?{
return?new?String(aidString.getBytes(ori_encoding)?new_encoding);
}?catch?(UnsupportedEncodingException?e)?{
e.printStackTrace();
}
return?null;
}
public?static?void?main(String[]?args)?throws?Exception?{
String?argu?=?“E:\\ICTCLAS2015“;
//String?system_charset?=?“GBK“;//GBK----0
String?system_charset?=?“UTF-8“;
int?charset_type?=?1;
String?utf8File?=?“test/18屆三中全會.TXT“;
String?utf8FileResult?=?“test/18屆三中全會_result.TXT“;
int?init_flag?=?CLibrary.Instance.NLPIR_Init(argu?charset_type?“0“);
String?nativeBytes?=?null;
if?(0?==?init_flag)?{
nativeBytes?=?CLibrary.Instance.NLPIR_GetLastErrorMsg();
System.err.println(“初始化失敗!fail?reason?is?“+nativeBytes);
return;
}
String?sInput?=?“據悉,質檢總局已將最新有關情況再次通報美方,要求美方加強對輸華玉米的產地來源、運輸及倉儲等環節的管控措施,有效避免輸華玉米被未經我國農業部安全評估并批準的轉基因品系污染。好的壞事的辦法的“;
//String?nativeBytes?=?null;
try?{
//參數0表示不帶詞性,參數1表示帶有詞性
nativeBytes?=?CLibrary.Instance.NLPIR_ParagraphProcess(sInput?0);
System.out.println(“分詞結果為:?“?+?nativeBytes);
//增加用戶詞典后
CLibrary.Instance.NLPIR_AddUserWord(“要求美方加強對輸?n“);
CLibrary.Instance.NLPIR_AddUserWord(“華玉米的產地來源?n“);
nativeBytes?=?CLibrary.Instance.NLPIR_ParagraphProcess(sInput?1);
System.out.println(“增加用戶詞典后分詞結果為:?“?+?nativeBytes);
//刪除用戶詞典后
CLibrary.Instance.NLPIR_DelUsrWord(“要求美方加強對輸“);
nativeBytes?=?CLibrary.Instance.NLPIR_ParagraphProcess(sInput?1);
System.out.println(“刪除用戶詞典后分詞結果為:?“?+?nativeBytes);
CLibrary.Instance.NLPIR_FileProcess(utf8File.getBytes(“utf-8“)?utf8FileResult.getBytes(“utf-8“)0);
int?nCountKey?=?0;
String?nativeByte?=?CLibrary.
?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????文件????????381??2015-03-10?10:19??fenci\.project
?????文件???????4076??2015-03-10?13:43??fenci\src\com\code\NlpirTest.java
?????文件???????4156??2015-03-10?14:46??fenci\src\com\code\test1.java
?????文件????????209??2015-03-10?10:29??fenci\src\utils\SystemParas.java
?????文件???????1408??2015-03-10?10:30??fenci\src\utils\ReadConfigUtil.java
?????文件????????508??2015-03-10?10:38??fenci\bin\utils\SystemParas.class
?????文件???????2208??2015-03-10?10:38??fenci\bin\utils\ReadConfigUtil.class
?????文件???????3370??2015-03-10?13:43??fenci\bin\com\code\NlpirTest.class
?????文件???????3361??2015-03-10?14:46??fenci\bin\com\code\test1.class
?????文件???????1002??2015-03-10?14:46??fenci\bin\com\code\test1$CLibrary.class
?????文件????????598??2015-03-10?10:19??fenci\.settings\org.eclipse.jdt.core.prefs
?????文件????????353??2015-03-10?10:38??fenci\.classpath
?????文件?????914639??2015-03-10?10:36??fenci\jna-4.0.0.jar
?????文件??????66143??2015-03-10?11:22??fenci\test\18屆三中全會.TXT
?????文件???????5593??2015-03-10?11:19??fenci\test\English.txt
?????文件????????157??2015-03-10?11:19??fenci\test\中英文混雜示例.txt
?????文件???????6528??2015-03-10?11:19??fenci\test\屌絲,一個字頭的誕生.TXT
?????文件????????966??2015-03-10?11:19??fenci\test\用戶詞典.txt
?????文件??????33792??2015-03-10?11:19??fenci\test\遷鋼語料\漢語詞性對照表.doc
?????文件???????1012??2015-03-10?11:19??fenci\test\遷鋼語料\煉鋼.txt
?????文件????????585??2015-03-10?11:19??fenci\test\遷鋼語料\遷鋼.txt
?????文件???????1229??2015-03-10?11:19??fenci\test\遷鋼語料\遷鋼公司煉鋼作業部潤滑脂國產化降成本收效大.txt
?????文件???????1161??2015-03-10?11:19??fenci\test\遷鋼語料\遷鋼創新高.txt
?????文件???????1722??2015-03-10?11:19??fenci\test\遷鋼語料\首鋼遷鋼無氟煉鋼技術效益顯著.txt
?????文件????????941??2015-03-10?11:19??fenci\test\遷鋼語料\首鋼遷鋼通過超快冷工藝完成X70萬噸訂單.txt
?????文件????????820??2015-03-10?11:19??fenci\test\遷鋼語料\首鋼重組.txt
?????文件????????423??2015-03-10?11:19??fenci\test\docs\0-兩棲戰車亮相.txt
?????文件????????966??2015-03-10?11:19??fenci\test\docs\1-遼寧阜新官員涉嫌淫亂事件舉報者被刑拘.txt
?????文件???????1035??2015-03-10?11:19??fenci\test\docs\2-遼寧一男子女廁用手機拍照被拘(圖).txt
?????文件???????5271??2015-03-10?11:19??fenci\test\docs\3-兩人打甲流疫苗后死亡?另有15例較嚴重異常反應.txt
............此處省略18個文件信息
評論
共有 條評論