zilinsoft
3262955f2f
------ #### RaUIV4 V4.0.2311.0701 - *.[全新]整合了MyDb、ryControls、MyDb_MySQL等dll文件到RaUI一个项目。 - *.[新增]新增ApkOp类,可以轻松获取APK信息。 - *.[新增]新增JsonExt扩展类,让Json操作更简单。 - *.[新增]新增WebP类,可以支持webp格式的图片。 - *.[改进]ryQuickSQL中的AddField方法改为自动替换已存在的同名值。 - *.[修复]ryQuickSQL中的AddFieldCalc方法无法正常计算的BUG。
273 lines
9.4 KiB
C#
273 lines
9.4 KiB
C#
using System;
|
||
using System.Collections.Generic;
|
||
using System.IO;
|
||
using System.Linq;
|
||
using System.Text;
|
||
|
||
namespace ryCommon
|
||
{
|
||
/// <summary>
|
||
/// 用于取得一个文本文件的编码方式(Encoding)。
|
||
/// </summary>
|
||
public class TxtFileEncoder
|
||
{
|
||
/// <summary>
|
||
/// 用于取得一个文本文件的编码方式(Encoding)。
|
||
/// </summary>
|
||
public TxtFileEncoder()
|
||
{
|
||
//
|
||
// TODO: 在此处添加构造函数逻辑
|
||
//
|
||
}
|
||
/// <summary>
|
||
/// 取得一个文本文件的编码方式。如果无法在文件头部找到有效的前导符，Encoding.Default将被返回。
|
||
/// </summary>
|
||
/// <param name="fileName">文件名。</param>
|
||
/// <returns></returns>
|
||
public static Encoding GetEncoding(string fileName)
|
||
{
|
||
return GetEncoding(fileName, Encoding.Default);
|
||
}
|
||
/// <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(FileStream stream)
|
||
{
|
||
return GetEncoding(stream, Encoding.Default);
|
||
}
|
||
/// <summary>
|
||
/// 取得一个文本文件的编码方式。
|
||
/// </summary>
|
||
/// <param name="fileName">文件名。</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(string fileName, Encoding defaultEncoding)
|
||
{
|
||
Encoding targetEncoding = defaultEncoding;
|
||
try
|
||
{
|
||
FileStream fs = new FileStream(fileName, FileMode.Open, FileAccess.Read);
|
||
try
|
||
{
|
||
targetEncoding = GetEncoding(fs, defaultEncoding);
|
||
}
|
||
catch { }
|
||
fs.Close();
|
||
}
|
||
catch
|
||
{
|
||
return defaultEncoding;
|
||
}
|
||
return targetEncoding;
|
||
}
|
||
/// <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(FileStream stream, Encoding defaultEncoding)
|
||
{
|
||
Encoding targetEncoding = defaultEncoding;
|
||
if (stream != null && stream.Length >= 2)
|
||
{
|
||
//保存文件流的前4个字节
|
||
byte byte1;
|
||
byte byte2;
|
||
byte byte3 = 0;
|
||
byte byte4;
|
||
BinaryReader r = new BinaryReader(stream, System.Text.Encoding.Default);
|
||
byte[] ss;
|
||
ss = r.ReadBytes(stream.Length.ToInt());
|
||
byte1 = ss.Length>=1?ss[0]:byte.MinValue;
|
||
byte2 = ss.Length >= 2 ? ss[1] : byte.MinValue;
|
||
if (stream.Length >= 3)
|
||
{
|
||
byte3 = ss.Length >= 3 ? ss[2] : byte.MinValue;
|
||
}
|
||
if (stream.Length >= 4)
|
||
{
|
||
byte4 = ss.Length >= 4 ? ss[3] : byte.MinValue;
|
||
}
|
||
//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;
|
||
}
|
||
else if (byte1 == 0xFF && byte2 == 0xFE && byte3 != 0xFF)//Unicode
|
||
{
|
||
targetEncoding = Encoding.Unicode;
|
||
}
|
||
else if (byte1 == 0xEF && byte2 == 0xBB && byte3 == 0xBF)//UTF8
|
||
{
|
||
targetEncoding = Encoding.UTF8;
|
||
}
|
||
else if (IsUTF8Bytes(ss))//UTF8
|
||
{
|
||
targetEncoding =new UTF8Encoding(false);
|
||
}
|
||
//恢复Seek位置
|
||
r.Close();
|
||
}
|
||
return targetEncoding;
|
||
}
|
||
|
||
|
||
|
||
// 新增加一个方法，解决了不带BOM的 UTF8 编码问题
|
||
|
||
/// <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 GetEncoding(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 = Encoding.Default;
|
||
|
||
BinaryReader r = new BinaryReader(fs, System.Text.Encoding.Default);
|
||
byte[] ss = r.ReadBytes(4);
|
||
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;
|
||
}
|
||
else
|
||
{
|
||
if (ss[0] == 0xEF && ss[1] == 0xBB && ss[2] == 0xBF)
|
||
{
|
||
reVal = Encoding.UTF8;
|
||
}
|
||
else
|
||
{
|
||
int.TryParse(fs.Length.ToString(), out int i);
|
||
ss = r.ReadBytes(i);
|
||
|
||
if (GetBytesEncoding(ss)==Encoding.UTF8)
|
||
reVal = Encoding.UTF8;
|
||
}
|
||
}
|
||
r.Close();
|
||
return reVal;
|
||
|
||
}
|
||
private static Encoding GetBytesEncoding(byte[] bs)
|
||
{
|
||
int len = bs.Length;
|
||
if (len >= 3 && bs[0] == 0xEF && bs[1] == 0xBB && bs[2] == 0xBF)
|
||
{
|
||
return Encoding.UTF8;
|
||
}
|
||
int[] cs = { 7, 5, 4, 3, 2, 1, 0, 6, 14, 30, 62, 126 };
|
||
for (int i = 0; i < len; i++)
|
||
{
|
||
int bits = -1;
|
||
for (int j = 0; j < 6; j++)
|
||
{
|
||
if (bs[i] >> cs[j] == cs[j + 6])
|
||
{
|
||
bits = j;
|
||
break;
|
||
}
|
||
}
|
||
if (bits == -1)
|
||
{
|
||
return Encoding.Default;
|
||
}
|
||
while (bits-- > 0)
|
||
{
|
||
i++;
|
||
if (i == len || bs[i] >> 6 != 2)
|
||
{
|
||
return Encoding.Default;
|
||
}
|
||
}
|
||
}
|
||
return Encoding.UTF8;
|
||
}
|
||
private static byte UTF8CharacterMask1Byte = 0b1000_0000;
|
||
private static byte Valid1Byte = 0b0000_0000;//0b0xxx_xxxx
|
||
|
||
private static byte UTF8CharacterMask2Byte = 0b1110_0000;
|
||
private static byte Valid2Byte = 0b1100_0000;//0b110x_xxxx
|
||
|
||
private static byte UTF8CharacterMask3Byte = 0b1111_0000;
|
||
private static byte Valid3Byte = 0b1110_0000;//0b1110_xxxx
|
||
|
||
private static byte UTF8CharacterMask4Byte = 0b1111_1000;
|
||
private static byte Valid4Byte = 0b1111_0000;//0b1111_0xxx
|
||
|
||
private static byte UTF8CharacterMaskForExtraByte = 0b1100_0000;
|
||
private static byte ValidExtraByte = 0b1000_0000;//0b10xx_xxxx
|
||
/// <summary>
|
||
/// 判断是否是不带 BOM 的 UTF8 格式
|
||
/// </summary>
|
||
/// <param name="bytes"></param>
|
||
/// <returns></returns>
|
||
public static bool IsUTF8Bytes(byte[] bytes)
|
||
{
|
||
short extraByteCount = 0;
|
||
|
||
foreach (byte bt in bytes)
|
||
{
|
||
|
||
if (extraByteCount > 0)
|
||
{
|
||
extraByteCount--;
|
||
|
||
// Extra Byte Pattern.
|
||
if ((bt & UTF8CharacterMaskForExtraByte) != ValidExtraByte)
|
||
return false;
|
||
continue;
|
||
}
|
||
else
|
||
{
|
||
// 1 Byte Pattern.
|
||
if ((bt & UTF8CharacterMask1Byte) == Valid1Byte)
|
||
{
|
||
continue;
|
||
}
|
||
|
||
// 2 Bytes Pattern.
|
||
if ((bt & UTF8CharacterMask2Byte) == Valid2Byte)
|
||
{
|
||
extraByteCount = 1;
|
||
continue;
|
||
}
|
||
|
||
// 3 Bytes Pattern.
|
||
if ((bt & UTF8CharacterMask3Byte) == Valid3Byte)
|
||
{
|
||
extraByteCount = 2;
|
||
continue;
|
||
}
|
||
|
||
// 4 Bytes Pattern.
|
||
if ((bt & UTF8CharacterMask4Byte) == Valid4Byte)
|
||
{
|
||
extraByteCount = 3;
|
||
continue;
|
||
}
|
||
|
||
// invalid UTF8-Bytes.
|
||
return false;
|
||
}
|
||
}
|
||
|
||
return extraByteCount >= 0;
|
||
}
|
||
}
|
||
}
|