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);
}
/// <summary>
/// 读取一个词汇的词和解释
/// </summary>
/// <param name="inflatedBytes"></param>
/// <param name="offsetWords"></param>
/// <param name="offsetXml"></param>
/// <param name="dataLen"></param>
/// <param name="wordStringDecoder"></param>
/// <param name="xmlStringDecoder"></param>
/// <param name="i"></param>
/// <returns></returns>
private InternalWord ReadDefinitionData(byte[] inflatedBytes, int offsetWords,
int offsetXml, int dataLen, Encoding wordStringDecoder,
Encoding xmlStringDecoder, int i)
{
var idxData = new int[6];
GetIdxData(inflatedBytes, dataLen * i, idxData);
int lastWordPos = idxData[0];
int lastXmlPos = idxData[1];
int flags = idxData[2];
int refs = idxData[3]; //这个词有多少种解释
int currentWordOffset = idxData[4]; //词的Offset位置
int currenXmlOffset = idxData[5]; //解释XML的Offset位置
InternalWord word = new InternalWord();
string xml = xmlStringDecoder.GetString(inflatedBytes, offsetXml + lastXmlPos, currenXmlOffset - lastXmlPos);
if (!string.IsNullOrEmpty(xml))
{
word.Descriptions.Add(currenXmlOffset, xml);
}
while (refs-- > 0)
{
int position = (offsetWords + lastWordPos);
int ref1 = BitConverter.ToInt32(inflatedBytes, position);
GetIdxData(inflatedBytes, dataLen * ref1, idxData);
lastXmlPos = idxData[1];
currenXmlOffset = idxData[5];
//if (string.IsNullOrEmpty(xml))
//{
xml = xmlStringDecoder.GetString(inflatedBytes, offsetXml + lastXmlPos, currenXmlOffset - lastXmlPos);
word.Descriptions.Add(currenXmlOffset, xml);
//}
//else
//{
// xml = xmlStringDecoder.GetString(inflatedBytes, offsetXml + lastXmlPos, currenXmlOffset - lastXmlPos);
//}
lastWordPos += 4;
}
//defData[1] = xml;
int position1 = offsetWords + lastWordPos;
byte[] w = BinFileHelper.ReadArray(inflatedBytes, position1, currentWordOffset - lastWordPos);
word.Word = wordStringDecoder.GetString(w);
//if (word == "buy" || word == "bought")
//{
// Debug.Write("Refs:" + currenXmlOffset);
//}
//defData[0] = word;
//return new KeyValuePair<string, string>(word, xml);
return(word);
}
public WordLibraryList Import(string path)
{
var pyAndWord = new WordLibraryList();
var fs = new FileStream(path, FileMode.Open, FileAccess.Read);
fs.Position = 0x00;
var headerstr = "Freeime Dictionary";
var header = Encoding.ASCII.GetString(BinFileHelper.ReadArray(fs, headerstr.Length));
Debug.Assert(header.Equals(headerstr));
DictCodeType curType;
fs.Position = 0x23;
var headerTypeBytes = BinFileHelper.ReadArray(fs, 4);
var headerTypeStr = Encoding.Unicode.GetString(headerTypeBytes);
if (headerTypeStr.Equals("拼音"))
{
curType = DictCodeType.Pinyin;
}
else if (headerTypeStr.Equals("五笔"))
{
curType = DictCodeType.Wubi98;
}
else
{
throw new NotImplementedException("未知词库，请在反馈中提交文件");
}
var phrase_start = 0x1B620; // 'a'词条所在
fs.Position = phrase_start;
while (true)
{
var wl = ReadOnePhrase(fs, curType);
if (wl != null)
{
pyAndWord.Add(wl);
}
if (fs.Length == fs.Position) //文件结束
{
fs.Close();
break;
}
}
return(pyAndWord);
}
/// <summary>
/// 读取一个词汇的词和解释
/// </summary>
/// <param name="inflatedBytes"></param>
/// <param name="offsetWords"></param>
/// <param name="offsetXml"></param>
/// <param name="dataLen"></param>
/// <param name="wordStringDecoder"></param>
/// <param name="xmlStringDecoder"></param>
/// <param name="i"></param>
/// <returns>Key为词汇，Value为解释</returns>
private KeyValuePair <string, string> ReadDefinitionData(byte[] inflatedBytes, int offsetWords,
int offsetXml, int dataLen, Encoding wordStringDecoder,
Encoding xmlStringDecoder, int i)
{
var idxData = new int[6];
GetIdxData(inflatedBytes, dataLen * i, idxData);
int lastWordPos = idxData[0];
int lastXmlPos = idxData[1];
int flags = idxData[2];
int refs = idxData[3];
int currentWordOffset = idxData[4];
int currenXmlOffset = idxData[5];
string xml = xmlStringDecoder.GetString(inflatedBytes, offsetXml + lastXmlPos, currenXmlOffset - lastXmlPos);
while (refs-- > 0)
{
int position = (offsetWords + lastWordPos);
int ref1 = BitConverter.ToInt32(inflatedBytes, position);
GetIdxData(inflatedBytes, dataLen * ref1, idxData);
lastXmlPos = idxData[1];
currenXmlOffset = idxData[5];
if (string.IsNullOrEmpty(xml))
{
xml = xmlStringDecoder.GetString(inflatedBytes, offsetXml + lastXmlPos, currenXmlOffset - lastXmlPos);
}
else
{
xml =
xmlStringDecoder.GetString(inflatedBytes, offsetXml + lastXmlPos, currenXmlOffset - lastXmlPos) +
", " + xml;
}
lastWordPos += 4;
}
//defData[1] = xml;
int position1 = offsetWords + lastWordPos;
byte[] w = BinFileHelper.ReadArray(inflatedBytes, position1, currentWordOffset - lastWordPos);
string word = wordStringDecoder.GetString(w);
//defData[0] = word;
return(new KeyValuePair <string, string>(word, xml));
}
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, DictCodeType type)
{
WordLibrary wl = new WordLibrary();
var codeBytesLen = fs.ReadByte();
var wordBytesLen = fs.ReadByte();
var split = fs.ReadByte();
// 0x64对应正常词组（包含中英混拼，如"阿Q"）。
Debug.Assert(split.Equals(0x64) || split.Equals(0x32) ||
split.Equals(0x10) || split.Equals(0x66) ||
split.Equals(0x67)); // 0x67: "$X[计算器]calc"
var codeBytes = BinFileHelper.ReadArray(fs, codeBytesLen);
var codeStr = Encoding.ASCII.GetString(codeBytes);
var wordBytes = BinFileHelper.ReadArray(fs, wordBytesLen);
var word = Encoding.Unicode.GetString(wordBytes);
if (split.Equals(0x32)) // 如“醃(腌)”，后者是相应简化字？
{
word = word.Substring(0, 1); // 暂定只取首字
}
Debug.Assert(word.IndexOf("(") < 0);
wl.Word = word;
try
{
if (type == DictCodeType.Pinyin)
{
wl.CodeType = CodeType.Pinyin;
wl.SetPinyinString(codeStr);
}
else if (type == DictCodeType.Wubi98)
{
wl.CodeType = CodeType.Wubi98;
wl.SetCode(CodeType.Wubi98, codeStr);
}
}
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 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);
}