private WordLibrary ReadOnePhrase(FileStream fs, int nextStartPosition)
{
WordLibrary wl = new WordLibrary();
var magic = BinFileHelper.ReadInt32(fs);
var hanzi_offset = BinFileHelper.ReadInt16(fs);
wl.Rank = fs.ReadByte();
var x6 = fs.ReadByte(); //不知道干啥的
var unknown8 = BinFileHelper.ReadInt64(fs); //新增的，不知道什么意思
var pyBytesLen = hanzi_offset - 18;
var pyBytes = BinFileHelper.ReadArray(fs, pyBytesLen);
var pyStr = Encoding.Unicode.GetString(pyBytes);
var split = BinFileHelper.ReadInt16(fs); //00 00 分割拼音和汉字
var wordBytesLen = nextStartPosition - (int)fs.Position - 2; //结尾还有个00 00
var wordBytes = BinFileHelper.ReadArray(fs, wordBytesLen);
BinFileHelper.ReadInt16(fs); //00 00分割
var word = Encoding.Unicode.GetString(wordBytes);
wl.Word = word;
try
{
wl.SetPinyinString(pyStr);
wl.CodeType = CodeType.Pinyin;
}
catch
{
wl.CodeType = CodeType.NoCode;
ImportLineErrorNotice?.Invoke(wl.Word + " 的编码缺失");
}
return(wl);
}
private WordLibrary ReadOnePhrase(FileStream fs, int nextStartPosition)
{
WordLibrary wl = new WordLibrary();
var magic = BinFileHelper.ReadInt32(fs);
var hanzi_offset = BinFileHelper.ReadInt16(fs);
wl.Rank = fs.ReadByte();
var x6 = fs.ReadByte(); //不知道干啥的
var unknown8 = BinFileHelper.ReadInt64(fs); //新增的，不知道什么意思
var pyBytesLen = hanzi_offset - 18;
var pyBytes = BinFileHelper.ReadArray(fs, pyBytesLen);
var wubiStr = Encoding.Unicode.GetString(pyBytes);
var split = BinFileHelper.ReadInt16(fs); //00 00 分割拼音和汉字
var wordBytesLen = nextStartPosition - (int)fs.Position - 2; //结尾还有个00 00
var wordBytes = BinFileHelper.ReadArray(fs, wordBytesLen);
BinFileHelper.ReadInt16(fs); //00 00分割
var word = Encoding.Unicode.GetString(wordBytes);
wl.Word = word;
try
{
wl.SetCode(CodeType.Wubi98, wubiStr);
}
catch
{
return(null);
}
wl.CodeType = CodeType.Wubi98;
return(wl);
}
private IList <WordLibrary> ReadAPinyinWord(FileStream fs)
{
var num = new byte[4];
fs.Read(num, 0, 4);
int samePYcount = num[0] + num[1] * 256;
int pinyinLen = num[2] + num[3] * 256;
//接下来读拼音
var str = new byte[256];
for (int i = 0; i < pinyinLen; i++)
{
str[i] = (byte)fs.ReadByte();
}
var wordPY = new List <string>();
for (int i = 0; i < pinyinLen / 2; i++)
{
int key = str[i * 2] + str[i * 2 + 1] * 256;
//Debug.Assert(key < pyDic.Count);
if (key < pyDic.Count)
{
wordPY.Add(pyDic[key]);
}
else
{
wordPY.Add(a2zchar[key - pyDic.Count].ToString());
}
//return null; // 用于调试，忽略编码异常的记录，不中止运行
}
//wordPY = wordPY.Remove(wordPY.Length - 1); //移除最后一个单引号
//接下来读词语
var pyAndWord = new List <WordLibrary>();
for (int s = 0; s < samePYcount; s++) //同音词，使用前面相同的拼音
{
num = new byte[2];
fs.Read(num, 0, 2);
int hzBytecount = num[0] + num[1] * 256;
str = new byte[hzBytecount];
fs.Read(str, 0, hzBytecount);
string word = Encoding.Unicode.GetString(str);
short unknown1 = BinFileHelper.ReadInt16(fs); //全部是10,肯定不是词频，具体是什么不知道
int unknown2 = BinFileHelper.ReadInt32(fs); //每个字对应的数字不一样，不知道是不是词频
pyAndWord.Add(new WordLibrary {
Word = word, PinYin = wordPY.ToArray(), Rank = DefaultRank
});
CurrentStatus++;
//接下来10个字节什么意思呢？暂时先忽略了
var temp = new byte[6];
for (int i = 0; i < 6; i++)
{
temp[i] = (byte)fs.ReadByte();
}
}
return(pyAndWord);
}
//4字节使用同一个拼音的词条数x，2字节拼音长度n，n字节拼音的编号，（2字节汉字的长度y，y*2字节汉字的内容Unicode编码，2字节词频，2字节未知，4字节未知）*x
public WordLibraryList Import(string path)
{
var pyAndWord = new WordLibraryList();
var fs = new FileStream(path, FileMode.Open, FileAccess.Read);
fs.Position = 0x18;
CountWord = BinFileHelper.ReadInt32(fs);
CurrentStatus = 0;
fs.Position = 0x30;
while (CurrentStatus < CountWord)
{
int samePyCount = BinFileHelper.ReadInt16(fs);
int unkown1 = BinFileHelper.ReadInt16(fs);
short pyLength = BinFileHelper.ReadInt16(fs);
var pyArray = new string[pyLength / 2];
for (int i = 0; i < pyLength / 2; i++)
{
short idx = BinFileHelper.ReadInt16(fs);
try
{
pyArray[i] = PinYinDic[idx];
}
catch
{
pyArray[i] = "--";
}
}
for (int i = 0; i < samePyCount; i++)
{
short wordByteLength = BinFileHelper.ReadInt16(fs);
var wordArray = new byte[wordByteLength];
fs.Read(wordArray, 0, wordByteLength);
string word = Encoding.Unicode.GetString(wordArray);
short count = BinFileHelper.ReadInt16(fs);
short count2 = BinFileHelper.ReadInt16(fs);
int unknown = BinFileHelper.ReadInt32(fs); //不知道干啥的
if (pyArray.Length == word.Length)
{
var wl = new WordLibrary {
Rank = count, Word = word, PinYin = pyArray
};
pyAndWord.Add(wl);
}
else
{
Debug.WriteLine("Error data: word:[" + word + "] pinyin:[" + string.Join(",", pyArray) + "]");
}
CurrentStatus++;
}
}
return(pyAndWord);
}
private IList <WordLibrary> ReadAPinyinWord(FileStream fs)
{
var num = new byte[4];
fs.Read(num, 0, 4);
int samePYcount = num[0] + num[1] * 256;
int count = num[2] + num[3] * 256;
//接下来读拼音
var str = new byte[256];
for (int i = 0; i < count; i++)
{
str[i] = (byte)fs.ReadByte();
}
var wordPY = new List <string>();
for (int i = 0; i < count / 2; i++)
{
int key = str[i * 2] + str[i * 2 + 1] * 256;
wordPY.Add(pyDic[key]);
}
//wordPY = wordPY.Remove(wordPY.Length - 1); //移除最后一个单引号
//接下来读词语
var pyAndWord = new List <WordLibrary>();
for (int s = 0; s < samePYcount; s++) //同音词，使用前面相同的拼音
{
num = new byte[2];
fs.Read(num, 0, 2);
int hzBytecount = num[0] + num[1] * 256;
str = new byte[hzBytecount];
fs.Read(str, 0, hzBytecount);
string word = Encoding.Unicode.GetString(str);
short wlcount = BinFileHelper.ReadInt16(fs);
pyAndWord.Add(new WordLibrary {
Word = word, PinYin = wordPY.ToArray(), Count = wlcount
});
CurrentStatus++;
//接下来10个字节什么意思呢？暂时先忽略了
var temp = new byte[10];
for (int i = 0; i < 10; i++)
{
temp[i] = (byte)fs.ReadByte();
}
}
return(pyAndWord);
}
public IList <InternalWord> Parse(string ld2File)
{
using (var fs = new FileStream(ld2File, FileMode.Open, FileAccess.Read))
{
Debug.WriteLine("文件：" + ld2File);
byte[] bs = BinFileHelper.ReadArray(fs, 4);
string v = Encoding.ASCII.GetString(bs);
Debug.WriteLine("类型：" + v);
fs.Position = 0x18;
Debug.WriteLine("版本：" + BinFileHelper.ReadInt16(fs) + "." + BinFileHelper.ReadInt16(fs));
Debug.WriteLine("ID: 0x" + (BinFileHelper.ReadInt64(fs).ToString("x")));
fs.Position = 0x5c;
int offsetData = BinFileHelper.ReadInt32(fs) + 0x60;
if (fs.Length > offsetData)
{
Debug.WriteLine("简介地址：0x" + (offsetData).ToString("x"));
fs.Position = offsetData;
int type = BinFileHelper.ReadInt32(fs);
Debug.WriteLine("简介类型：0x" + (type).ToString("x"));
fs.Position = offsetData + 4;
int offsetWithInfo = BinFileHelper.ReadInt32(fs) + offsetData + 12;
if (type == 3)
{
// without additional information
return(ReadDictionary(fs, offsetData));
}
else if (fs.Length > offsetWithInfo - 0x1C)
{
return(ReadDictionary(fs, offsetWithInfo));
}
else
{
Debug.WriteLine("文件不包含字典数据。网上字典？");
}
}
else
{
Debug.WriteLine("文件不包含字典数据。网上字典？");
}
return(null);
}
}
private WordLibrary ReadOnePhrase(FileStream fs, int nextStartPosition)
{
WordLibrary wl = new WordLibrary();
var magic = BinFileHelper.ReadInt32(fs);
var hanzi_offset = BinFileHelper.ReadInt16(fs);
wl.Rank = fs.ReadByte();
var x6 = fs.ReadByte();//不知道干啥的
var pyBytesLen = hanzi_offset - 10;
var pyBytes = BinFileHelper.ReadArray(fs, pyBytesLen);
var pyStr = Encoding.Unicode.GetString(pyBytes);
var split = BinFileHelper.ReadInt16(fs); //00 00 分割拼音和汉字
var wordBytesLen = nextStartPosition - (int)fs.Position - 2; //结尾还有个00 00
var wordBytes = BinFileHelper.ReadArray(fs, wordBytesLen);
BinFileHelper.ReadInt16(fs);//00 00分割
var word = Encoding.Unicode.GetString(wordBytes);
wl.Word = word;
wl.SetPinyinString(pyStr);
wl.CodeType = CodeType.Pinyin;
return(wl);
}