/// <summary>
/// 对文本进行分词
/// </summary>
/// <param name="bytes">输入的字符串byte数组</param>
/// <param name="enc">编码方式</param>
/// <returns>分词结果列表</returns>
public List <ResultTerm> Segment(byte[] bytes, Encoding enc)
{
result_t[] result = new result_t[bytes.Length];
int posStrArrLen = 0;
byte[] bys = new byte[bytes.Length];
int i = 0;
int nWrdCnt = ICTCLAS_ParagraphProcessAW_B(bytes, result, getCodeType(enc), true);
List <ResultTerm> returnResult = new List <ResultTerm>(nWrdCnt);
result_t r;
//取字符串真实长度:
byte[] gbbytes = bytes; // enc.GetBytes(str);
for (i = 0; i < result.Length; i++)
{
r = result[i];
if (r.length != 0)
{
posStrArrLen = 0;
for (int l = 0; l < 8; l++)
{
if (r.sPos[l] == 0)
{
posStrArrLen = l;
break;
}
}
ResultTerm word = new ResultTerm();
word.Word = enc.GetString(gbbytes, r.start, r.length);
word.POS = r.POS_id;
word.POSStr = Encoding.ASCII.GetString(r.sPos, 0, posStrArrLen);
returnResult.Add(word);
}
}
result = null;
return(returnResult);
}
/// <summary>
/// 对文本进行分词
/// </summary>
/// <param name="str">要分词的字符串</param>
/// <returns>分词结果列表</returns>
public List <ResultTerm> Segment(string str)
{
result_t[] result = new result_t[str.Length];
int posStrArrLen = 0;
result_t r;
byte[] bytes = Encoding.UTF8.GetBytes(str);
int nWrdCnt = ICTCLAS_ParagraphProcessAW_B(bytes, result, eCodeType.CODE_TYPE_UTF8, true);
List <ResultTerm> returnResult = new List <ResultTerm>(nWrdCnt);
for (int i = 0; i < result.Length; i++)
{
r = result[i];
if (r.length != 0)
{
posStrArrLen = 0;
for (int l = 0; l < 8; l++)
{
if (r.sPos[l] == 0)
{
posStrArrLen = l;
break;
}
}
ResultTerm word = new ResultTerm();
word.Word = Encoding.UTF8.GetString(bytes, r.start, r.length);
word.POS = r.POS_id;
word.POSStr = Encoding.ASCII.GetString(r.sPos, 0, posStrArrLen);
returnResult.Add(word);
}
}
result = null;
return(returnResult);
}
/// <summary>
/// ���ı����зִ�
/// </summary>
/// <param name="bytes">������ַ���byte����</param>
/// <param name="enc">���뷽ʽ</param>
/// <returns>�ִʽ���б�</returns>
public List<ResultTerm> Segment(byte[] bytes, Encoding enc)
{
result_t[] result = new result_t[bytes.Length];
int posStrArrLen = 0;
byte[] bys = new byte[bytes.Length];
int i = 0;
int nWrdCnt = ICTCLAS_ParagraphProcessAW_B(bytes, result, getCodeType(enc), true);
List<ResultTerm> returnResult = new List<ResultTerm>(nWrdCnt);
result_t r;
//ȡ�ַ�����ʵ����:
byte[] gbbytes = bytes; // enc.GetBytes(str);
for (i = 0; i < result.Length; i++)
{
r = result[i];
if (r.length != 0)
{
posStrArrLen = 0;
for (int l = 0; l < 8; l++)
{
if (r.sPos[l] == 0)
{
posStrArrLen = l;
break;
}
}
ResultTerm word = new ResultTerm();
word.Word = enc.GetString(gbbytes, r.start, r.length);
word.POS = r.POS_id;
word.POSStr = Encoding.ASCII.GetString(r.sPos, 0, posStrArrLen);
returnResult.Add(word);
}
}
result = null;
return returnResult;
}
/// <summary>
/// ���ı����зִ�
/// </summary>
/// <param name="str">Ҫ�ִʵ��ַ���</param>
/// <returns>�ִʽ���б�</returns>
public List<ResultTerm> Segment(string str)
{
result_t[] result = new result_t[str.Length];
int posStrArrLen = 0;
result_t r;
byte[] bytes = Encoding.UTF8.GetBytes(str);
int nWrdCnt = ICTCLAS_ParagraphProcessAW_B(bytes, result, eCodeType.CODE_TYPE_UTF8, true);
List<ResultTerm> returnResult = new List<ResultTerm>(nWrdCnt);
for (int i = 0; i < result.Length; i++)
{
r = result[i];
if (r.length != 0)
{
posStrArrLen =0;
for(int l = 0; l<8 ;l++)
{
if (r.sPos[l]==0 )
{
posStrArrLen = l;
break;
}
}
ResultTerm word = new ResultTerm();
word.Word = Encoding.UTF8.GetString(bytes, r.start, r.length);
word.POS = r.POS_id;
word.POSStr = Encoding.ASCII.GetString(r.sPos, 0, posStrArrLen);
returnResult.Add(word);
}
}
result = null;
return returnResult;
}