最近想Tesseract训练自己的字库,尝试输出所有的gb2312字符集到txt文档,看了半天才搞明白
gb2312分区和位两者共同拼接成字符编码
//01 - 09区为特殊符号
//10 - 15区没有编码
//16 - 55区为一级汉字,按拼音排序,共3755个
//56 - 87区为二级汉字,按部首/笔画排序,共3008个
//88 - 94区没有编码
var gb = Encoding.GetEncoding("gb2312");
//01 - 09区为特殊符号 位 都是0-60 都+0xA0
for (int i = 01; i <= 09; i++)
{
for (int j = 0; j < 0x60; j++)
{
var strhex = $"{Convert.ToString((i + 0xA0), 16)}{Convert.ToString((j + 0xA0), 16)}";
var bytes = HexStringToByteArray(strhex);
var txt = gb.GetString(bytes).Trim();
if (!string.IsNullOrEmpty(txt))
richTextBox1.AppendText(txt + "\r\n");
}
}
//16 - 55区为一级汉字,按拼音排序,共3755个
for (int i = 16; i <= 55; i++)
{
for (int j = 0; j < 0x60; j++)
{
var strhex = $"{Convert.ToString((i + 0xA0), 16)}{Convert.ToString((j + 0xA0), 16)}";
var bytes = HexStringToByteArray(strhex);
var txt = gb.GetString(bytes).Trim();
if (!string.IsNullOrEmpty(txt))
richTextBox1.AppendText(txt + "\r\n");
}
}
//56 - 87区为二级汉字,按部首/笔画排序,共3008个
for (int i = 56; i <= 87; i++)
{
for (int j = 0; j < 0x60; j++)
{
var strhex = $"{Convert.ToString((i + 0xA0), 16)}{Convert.ToString((j + 0xA0), 16)}";
var bytes = HexStringToByteArray(strhex);
var txt = gb.GetString(bytes).Trim();
if (!string.IsNullOrEmpty(txt))
richTextBox1.AppendText(txt + "\r\n");
}
}
依赖的byte[]转hex和hex转byte[]方法
public byte[] HexStringToByteArray(string s)
{
s = s.Replace(" ", "");
byte[] buffer = new byte[s.Length / 2];
for (int i = 0; i < s.Length; i += 2)
buffer[i / 2] = (byte)Convert.ToByte(s.Substring(i, 2), 16);
return buffer;
}
public string ByteArrayToHexString(byte[] data, bool bFormat = false)
{
StringBuilder sb = new StringBuilder(data.Length * 3);
foreach (byte b in data)
sb.Append(Convert.ToString(b, 16).PadLeft(2, '0').PadRight(3, ' '));
string strResult = sb.ToString().Trim().ToUpper();
if (!bFormat) strResult = strResult.Replace(" ", "");
return strResult;
}