WP谈开发(5)Gb2312编码
由于windows phone不支持gb2312编码，导致了很多的问题。
那首先我们需要判断一段文字是什么编码的。其实每个编码的文字都有其特点。我们只需要知道其特点就能判断出来它是什么编码。
Encod
public class Encod { private static int iUtfBom = 0; /// <summary> /// 取得一个文本文件流的编码方式。 /// </summary> /// <param name="stream">文本文件流。</param> /// <returns></returns> public static Encoding GetEncoding(Stream stream) { Encoding EGb = new HtmlAgilityPack.Gb2312Encoding(); return GetEncoding(stream, EGb); } /// <summary> /// 通过给定的文件流，判断文件的编码类型 /// </summary> /// <param name="fs">文件流</param> /// <returns>文件的编码类型</returns> public static System.Text.Encoding GetType(Stream fs) { byte[] Unicode = new byte[] { 0xFF, 0xFE, 0x41 }; byte[] UnicodeBIG = new byte[] { 0xFE, 0xFF, 0x00 }; byte[] UTF8 = new byte[] { 0xEF, 0xBB, 0xBF }; //带BOM Encoding reVal = new GB2312.GB2312Encoding(); BinaryReader r = new BinaryReader(fs, reVal); int i; int.TryParse(fs.Length.ToString(), out i); byte[] ss = r.ReadBytes(i); if (IsUTF8Bytes(ss) || (ss[0] == 0xEF && ss[1] == 0xBB && ss[2] == 0xBF)) { reVal = Encoding.UTF8; } else if (ss[0] == 0xFE && ss[1] == 0xFF && ss[2] == 0x00) { reVal = Encoding.BigEndianUnicode; } else if (ss[0] == 0xFF && ss[1] == 0xFE && ss[2] == 0x41) { reVal = Encoding.Unicode; } r.Close(); return reVal; } /// <summary> /// 判断是否是不带 BOM 的 UTF8 格式 /// </summary> /// <param name="data"></param> /// <returns></returns> private static bool IsUTF8Bytes(byte[] data) { int charByteCounter = 1; //计算当前正分析的字符应还有的字节数 byte curByte; //当前分析的字节. for (int i = 0; i < data.Length; i++) { curByte = data[i]; if (charByteCounter == 1) { if (curByte >= 0x80) { //判断当前 while (((curByte <<= 1) & 0x80) != 0) { charByteCounter++; } //标记位首位若为非0 则至少以2个1开始 如:110XXXXX...........1111110X if (charByteCounter == 1 || charByteCounter > 6) { return false; } } } else { //若是UTF-8 此时第一位必须为1 if ((curByte & 0xC0) != 0x80) { return false; } charByteCounter--; } } if (charByteCounter > 1) { //throw new Exception("非预期的byte格式"); } return true; } /// <summary> /// 取得一个文本文件流的编码方式。 /// </summary> /// <param name="stream">文本文件流。</param> /// <param name="defaultEncoding">默认编码方式。当该方法无法从文件的头部取得有效的前导符时，将返回该编码方式。</param> /// <returns></returns> public static Encoding GetEncoding(Stream stream, Encoding EGb) { Encoding targetEncoding = EGb; if (stream != null && stream.Length >= 2) { //保存文件流的前4个字节 byte byte1 = 0; byte byte2 = 0; byte byte3 = 0; byte byte4 = 0; //保存当前Seek位置 long origPos = stream.Seek(0, SeekOrigin.Begin); stream.Seek(0, SeekOrigin.Begin); //string so=""; //for (int i = 0; i < 1000; i++) //{ // byte b1 = Convert.ToByte(stream.ReadByte()); // char ch = (char)b1; // so += ch.ToString(); //} int nByte = stream.ReadByte(); byte1 = Convert.ToByte(nByte); byte2 = Convert.ToByte(stream.ReadByte()); if (stream.Length >= 3) { byte3 = Convert.ToByte(stream.ReadByte()); } if (stream.Length >= 4) { byte4 = Convert.ToByte(stream.ReadByte()); } //根据文件流的前4个字节判断Encoding //Unicode {0xFF, 0xFE}; //BE-Unicode {0xFE, 0xFF}; //UTF8 = {0xEF, 0xBB, 0xBF}; if (byte1 == 0xFE && byte2 == 0xFF)//UnicodeBe { targetEncoding = Encoding.BigEndianUnicode; } if (byte1 == 0xFF && byte2 == 0xFE && byte3 != 0xFF)//Unicode { targetEncoding = Encoding.Unicode; } stream.Seek(origPos, SeekOrigin.Begin); byte[] Btst = new byte[100]; stream.Read(Btst, 0, Btst.Length); if (isUTF8(Btst)) { if (byte1 == 0xEF && byte2 == 0xBB && byte3 == 0xBF)//UTF8 { targetEncoding = Encoding.UTF8; iUtfBom = 3; } else { targetEncoding = Encoding.UTF8; } } //恢复Seek位置 stream.Seek(origPos, SeekOrigin.Begin); } return targetEncoding; } private static bool isUTF8(byte[] abytes) { if (abytes.Length < 3) { return false; } int count = 0, index = 0, follow = 0; int b; for (int i = 0; i < 5; i++) { b = abytes[index] & 0xFF; if ((b & 0xBF) == b) { //10xxxxxx index++; } else { break; } } while (count < 10000 && index < abytes.Length) { b = abytes[index++] & 0xFF; if ((b & 0x7F) == b) { //0xxxxxxx follow = 0; } else if ((b & 0xDF) == b) { //110xxxxx 10xxxxxx follow = 1; } else if ((b & 0xEF) == b) { //1110xxxx 10xxxxxx 10xxxxxx follow = 2; } else if ((b & 0xF7) == b) { //11110xxx 10xxxxxx 10xxxxxx 10xxxxxx follow = 3; } else if ((b & 0xFB) == b) { //111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx follow = 4; } else if ((b & 0xFD) == b) { //1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx follow = 5; } else { return false; } for (int i = 0; i < follow && index < abytes.Length; i++) { b = abytes[index++] & 0xFF; if ((b & 0xBF) != b) { //10xxxxxx return false; } } } return true; } }
这个类就用来判断一个文本文件流的编码。当然这里面还缺一样东西。HtmlAgilityPack这个是网上的一个dll。可以用来读取gb2312编码。不过我有一次用这个碰到了一个问题，总是报错超出索引范围。所以我用来读取的是用的另一个，详细的可以点这里去看http://www.cnblogs.com/xuesong/archive/2011/12/15/2288754.html
