public static void SplitBIG5() {
try {
ICTCLAS2011 testICTCLAS2011 = new ICTCLAS2011();
String argu = ".";
if (ICTCLAS2011.ICTCLAS_Init(argu.getBytes("GB2312"), 2) == false) { // UTF8切分
System.out.println("Init Fail!");
return;
}
String argu1 = "TestBIG.txt";
String argu2 = "TestBIG_result.txt";
testICTCLAS2011.ICTCLAS_FileProcess(argu1.getBytes("GB2312"), argu2.getBytes("GB2312"), 1);
// 释放分词组件资源
ICTCLAS2011.ICTCLAS_Exit();
} catch (Exception ex) {
}
}
public static void Split(String sInput) {
try {
ICTCLAS2011 testICTCLAS2011 = new ICTCLAS2011();
String argu = "F:\\workspace\\wordAutoErrorCorrection\\";
System.out.println("ICTCLAS_Init");
if (ICTCLAS2011.ICTCLAS_Init(argu.getBytes("GB2312"), 0) == false) {
System.out.println("Init Fail!");
return;
}
/*
* 设置词性标注集
ID 代表词性集
1 计算所一级标注集
0 计算所二级标注集
2 北大二级标注集
3 北大一级标注集
*/
testICTCLAS2011.ICTCLAS_SetPOSmap(2);
// 导入用户词典前
byte nativeBytes[] = testICTCLAS2011.ICTCLAS_ParagraphProcess(sInput.getBytes("GB2312"), 0);
String nativeStr = new String(nativeBytes, 0, nativeBytes.length, "GB2312");
System.out.println("未导入用户词典： " + nativeStr);
// 文件分词
String argu1 = "movie.txt";
String argu2 = "TestGBK_result.txt";
testICTCLAS2011.ICTCLAS_FileProcess(argu1.getBytes("GB2312"), argu2.getBytes("GB2312"), 0);
/*
//导入用户词典
String sUserDict = "userdic.txt";
int nCount = testICTCLAS2011.ICTCLAS_ImportUserDict(sUserDict.getBytes("GB2312"));
testICTCLAS2011.ICTCLAS_SaveTheUsrDic();//保存用户词典
System.out.println("导入个用户词： " + nCount);
nativeBytes = testICTCLAS2011.ICTCLAS_ParagraphProcess(sInput.getBytes("GB2312"), 1);
nativeStr = new String(nativeBytes, 0, nativeBytes.length, "GB2312");
System.out.println("导入用户词典后： " + nativeStr);
//动态添加用户词
String sWordUser = "******";
testICTCLAS2011.ICTCLAS_AddUserWord(sWordUser.getBytes("GB2312"));
testICTCLAS2011.ICTCLAS_SaveTheUsrDic();//保存用户词典
nativeBytes = testICTCLAS2011.ICTCLAS_ParagraphProcess(sInput.getBytes("GB2312"), 1);
nativeStr = new String(nativeBytes, 0, nativeBytes.length, "GB2312");
System.out.println("动态添加用户词后: " + nativeStr);
//分词高级接口
nativeBytes = testICTCLAS2011.nativeProcAPara(sInput.getBytes("GB2312"));
int nativeElementSize = testICTCLAS2011.ICTCLAS_GetElemLength(0);//size of result_t in native code
int nElement = nativeBytes.length / nativeElementSize;
byte nativeBytesTmp[] = new byte[nativeBytes.length];
//关键词提取
int nCountKey = testICTCLAS2011.ICTCLAS_KeyWord(nativeBytesTmp, nElement);
Result[] resultArr = new Result[nCountKey];
DataInputStream dis = new DataInputStream(new ByteArrayInputStream(nativeBytesTmp));
int iSkipNum;
for (int i = 0; i < nCountKey; i++)
{
resultArr[i] = new Result();
resultArr[i].start = Integer.reverseBytes(dis.readInt());
iSkipNum = testICTCLAS2011.ICTCLAS_GetElemLength(1) - 4;
if (iSkipNum > 0)
{
dis.skipBytes(iSkipNum);
}
resultArr[i].length = Integer.reverseBytes(dis.readInt());
iSkipNum = testICTCLAS2011.ICTCLAS_GetElemLength(2) - 4;
if (iSkipNum > 0)
{
dis.skipBytes(iSkipNum);
}
dis.skipBytes(testICTCLAS2011.ICTCLAS_GetElemLength(3));
resultArr[i].posId = Integer.reverseBytes(dis.readInt());
iSkipNum = testICTCLAS2011.ICTCLAS_GetElemLength(4) - 4;
if (iSkipNum > 0)
{
dis.skipBytes(iSkipNum);
}
resultArr[i].wordId = Integer.reverseBytes(dis.readInt());
iSkipNum = testICTCLAS2011.ICTCLAS_GetElemLength(5) - 4;
if (iSkipNum > 0)
{
dis.skipBytes(iSkipNum);
}
resultArr[i].word_type = Integer.reverseBytes(dis.readInt());
iSkipNum = testICTCLAS2011.ICTCLAS_GetElemLength(6) - 4;
if (iSkipNum > 0)
{
dis.skipBytes(iSkipNum);
}
resultArr[i].weight = Integer.reverseBytes(dis.readInt());
iSkipNum = testICTCLAS2011.ICTCLAS_GetElemLength(7) - 4;
if (iSkipNum > 0)
{
dis.skipBytes(iSkipNum);
}
}
dis.close();
for (int i = 0; i < resultArr.length; i++)
{
System.out.println("start=" + resultArr[i].start + ",length=" + resultArr[i].length + "pos=" + resultArr[i].posId + "word=" + resultArr[i].wordId + " weight=" + resultArr[i].weight);
}*/
// 释放分词组件资源
ICTCLAS2011.ICTCLAS_Exit();
} catch (Exception ex) {
}
}
