/// <summary>
/// 从文本文件读取字典
/// </summary>
/// <param name="fileName"></param>
static public T_DictFile LoadFromTextDict(String fileName)
{
T_DictFile dictFile = new T_DictFile();
String dictStr = CFile.ReadFileToString(fileName, "utf-8");
String[] words = CRegex.Split(dictStr, "\r\n");
foreach (String word in words)
{
String[] wp = CRegex.Split(word, @"\|");
if (wp == null)
{
continue;
}
if (wp.Length != 2)
{
continue;
}
int pos = 0;
try
{
pos = int.Parse(wp[1]);
}
catch
{
continue;
}
T_DictStruct dict = new T_DictStruct();
dict.Word = wp[0];
dict.Pos = pos;
if (dict.Word.Contains("一") || dict.Word.Contains("二") ||
dict.Word.Contains("三") || dict.Word.Contains("四") ||
dict.Word.Contains("五") || dict.Word.Contains("六") ||
dict.Word.Contains("七") || dict.Word.Contains("八") ||
dict.Word.Contains("九") || dict.Word.Contains("十"))
{
dict.Pos |= (int)T_POS.POS_A_M;
}
if (dict.Word == "字典")
{
dict.Pos = (int)T_POS.POS_D_N;
}
dictFile.Dicts.Add(dict);
}
return(dictFile);
}
static public T_DictFile LoadFromBinFileEx(String fileName)
{
T_DictFile dictFile = new T_DictFile();
dictFile.Dicts = new List <T_DictStruct>();
FileStream fs = new FileStream(fileName, FileMode.Open, FileAccess.Read);
byte[] version = new byte[32];
fs.Read(version, 0, version.Length);
String ver = Encoding.UTF8.GetString(version, 0, version.Length);
String verNumStr = CRegex.GetMatch(ver, "KTDictSeg Dict V(.+)", true);
if (verNumStr == null || verNumStr == "")
{
//1.3以前版本
fs.Close();
return(LoadFromBinFile(fileName));
}
while (fs.Position < fs.Length)
{
byte[] buf = new byte[sizeof(int)];
fs.Read(buf, 0, buf.Length);
int length = BitConverter.ToInt32(buf, 0);
buf = new byte[length];
T_DictStruct dict = new T_DictStruct();
fs.Read(buf, 0, buf.Length);
dict.Word = Encoding.UTF8.GetString(buf, 0, length - sizeof(int) - sizeof(double));
dict.Pos = BitConverter.ToInt32(buf, length - sizeof(int) - sizeof(double));
dict.Frequency = BitConverter.ToDouble(buf, length - sizeof(double));
dictFile.Dicts.Add(dict);
}
fs.Close();
return(dictFile);
}
