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);
}
public WordLibraryList ImportText(string str)
{
var xmlDoc = new XmlDocument();
xmlDoc.LoadXml(str);
var wlList = new WordLibraryList();
XmlNodeList xns = xmlDoc.SelectNodes("//plist/array/dict");
CountWord = xns.Count;
for (int i = 0; i < xns.Count; i++)
{
XmlNode xn = xns[i];
var nodes = xn.SelectNodes("string");
var wl = new WordLibrary();
wl.Word = nodes[0].InnerText;
wl.Rank = 1;
wl.SetPinyinString(nodes[1].InnerText);
CurrentStatus = i;
wlList.Add(wl);
}
return(wlList);
}
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);
}
