经验首页 前端设计 程序设计 Java相关 移动开发 数据库/运维 软件/图像 大数据/云计算 其他经验
当前位置:技术经验 » 程序设计 » C# » 查看文章
C#判断文件编码——常用字法
来源:cnblogs  作者:刀奈特程序员  时间:2018/11/12 10:06:21  对本文有异议

  使用中文写文章,当篇幅超过一定程度,必然会使用到诸如:“的”、“你”、“我”这样的常用字。本类思想便是提取中文最常用的一百个字,使用中文世界常用编码(主要有GBKGB2312GB18030UTF-8UTF-32UnicodeBigEndianUnicodeUTF-7等)获得其编码字节,以其为搜索词到目标流进行查找,如果查找得到则表示该流使用此种编码。显而易见此类不适用于小篇幅。

  1. using System.Collections.Generic;
  2. using System.IO;
  3. using System.Text;
  4. namespace YunShenBuZhiChu.MiMaBenJiaMiFa
  5. {
  6. /// <summary>
  7. /// 文字编码检测。
  8. /// 用于检测一篇文章使用什么编码方式进行编码。
  9. /// </summary>
  10. public class StreamBianMaJianCe
  11. {
  12. /// <summary>
  13. /// BigEndianUnicode编码高频汉字编码
  14. /// </summary>
  15. private List<byte[]> _BigEndianUnicodeGaoPinZiFuBianMaLsit = new List<byte[]>()
  16. {
  17. new byte[2]{118,132},new byte[2]{78,0},new byte[2]{86,253},new byte[2]{87,40},new byte[2]{78,186},new byte[2]{78,134},new byte[2]{103,9},new byte[2]{78,45},
  18. new byte[2]{102,47},new byte[2]{94,116},new byte[2]{84,140},new byte[2]{89,39},new byte[2]{78,26},new byte[2]{78,13},new byte[2]{78,58},new byte[2]{83,209},
  19. new byte[2]{79,26},new byte[2]{93,229},new byte[2]{126,207},new byte[2]{78,10},new byte[2]{87,48},new byte[2]{94,2},new byte[2]{137,129},new byte[2]{78,42},
  20. new byte[2]{78,167},new byte[2]{143,217},new byte[2]{81,250},new byte[2]{136,76},new byte[2]{79,92},new byte[2]{117,31},new byte[2]{91,182},new byte[2]{78,229},
  21. new byte[2]{98,16},new byte[2]{82,48},new byte[2]{101,229},new byte[2]{108,17},new byte[2]{103,101},new byte[2]{98,17},new byte[2]{144,232},new byte[2]{91,249},
  22. new byte[2]{143,219},new byte[2]{89,26},new byte[2]{81,104},new byte[2]{94,250},new byte[2]{78,214},new byte[2]{81,108},new byte[2]{95,0},new byte[2]{78,236},
  23. new byte[2]{87,58},new byte[2]{92,85},new byte[2]{101,246},new byte[2]{116,6},new byte[2]{101,176},new byte[2]{101,185},new byte[2]{78,59},new byte[2]{79,1},
  24. new byte[2]{141,68},new byte[2]{91,158},new byte[2]{91,102},new byte[2]{98,165},new byte[2]{82,54},new byte[2]{101,63},new byte[2]{109,78},new byte[2]{117,40},
  25. new byte[2]{84,12},new byte[2]{78,142},new byte[2]{108,213},new byte[2]{154,216},new byte[2]{149,127},new byte[2]{115,176},new byte[2]{103,44},new byte[2]{103,8},
  26. new byte[2]{91,154},new byte[2]{83,22},new byte[2]{82,160},new byte[2]{82,168},new byte[2]{84,8},new byte[2]{84,193},new byte[2]{145,205},new byte[2]{81,115},
  27. new byte[2]{103,58},new byte[2]{82,6},new byte[2]{82,155},new byte[2]{129,234},new byte[2]{89,22},new byte[2]{128,5},new byte[2]{83,58},new byte[2]{128,253},
  28. new byte[2]{139,190},new byte[2]{84,14},new byte[2]{92,49},new byte[2]{123,73},new byte[2]{79,83},new byte[2]{78,11},new byte[2]{78,7},new byte[2]{81,67},
  29. new byte[2]{121,62},new byte[2]{143,199},new byte[2]{82,77},new byte[2]{151,98},new byte[2]{48,2},new byte[2]{255,12},new byte[2]{255,31},new byte[2]{255,1}
  30. };
  31. /// <summary>
  32. /// UTF8编码高频汉字编码
  33. /// </summary>
  34. private List<byte[]> _UTF8GaoPinZiFuBianMaLsit = new List<byte[]>()
  35. {
  36. new byte[3]{231,154,132},new byte[3]{228,184,128},new byte[3]{229,155,189},new byte[3]{229,156,168},new byte[3]{228,186,186},new byte[3]{228,186,134},
  37. new byte[3]{230,156,137},new byte[3]{228,184,173},new byte[3]{230,152,175},new byte[3]{229,185,180},new byte[3]{229,146,140},new byte[3]{229,164,167},
  38. new byte[3]{228,184,154},new byte[3]{228,184,141},new byte[3]{228,184,186},new byte[3]{229,143,145},new byte[3]{228,188,154},new byte[3]{229,183,165},
  39. new byte[3]{231,187,143},new byte[3]{228,184,138},new byte[3]{229,156,176},new byte[3]{229,184,130},new byte[3]{232,166,129},new byte[3]{228,184,170},
  40. new byte[3]{228,186,167},new byte[3]{232,191,153},new byte[3]{229,135,186},new byte[3]{232,161,140},new byte[3]{228,189,156},new byte[3]{231,148,159},
  41. new byte[3]{229,174,182},new byte[3]{228,187,165},new byte[3]{230,136,144},new byte[3]{229,136,176},new byte[3]{230,151,165},new byte[3]{230,176,145},
  42. new byte[3]{230,157,165},new byte[3]{230,136,145},new byte[3]{233,131,168},new byte[3]{229,175,185},new byte[3]{232,191,155},new byte[3]{229,164,154},
  43. new byte[3]{229,133,168},new byte[3]{229,187,186},new byte[3]{228,187,150},new byte[3]{229,133,172},new byte[3]{229,188,128},new byte[3]{228,187,172},
  44. new byte[3]{229,156,186},new byte[3]{229,177,149},new byte[3]{230,151,182},new byte[3]{231,144,134},new byte[3]{230,150,176},new byte[3]{230,150,185},
  45. new byte[3]{228,184,187},new byte[3]{228,188,129},new byte[3]{232,181,132},new byte[3]{229,174,158},new byte[3]{229,173,166},new byte[3]{230,138,165},
  46. new byte[3]{229,136,182},new byte[3]{230,148,191},new byte[3]{230,181,142},new byte[3]{231,148,168},new byte[3]{229,144,140},new byte[3]{228,186,142},
  47. new byte[3]{230,179,149},new byte[3]{233,171,152},new byte[3]{233,149,191},new byte[3]{231,142,176},new byte[3]{230,156,172},new byte[3]{230,156,136},
  48. new byte[3]{229,174,154},new byte[3]{229,140,150},new byte[3]{229,138,160},new byte[3]{229,138,168},new byte[3]{229,144,136},new byte[3]{229,147,129},
  49. new byte[3]{233,135,141},new byte[3]{229,133,179},new byte[3]{230,156,186},new byte[3]{229,136,134},new byte[3]{229,138,155},new byte[3]{232,135,170},
  50. new byte[3]{229,164,150},new byte[3]{232,128,133},new byte[3]{229,140,186},new byte[3]{232,131,189},new byte[3]{232,174,190},new byte[3]{229,144,142},
  51. new byte[3]{229,176,177},new byte[3]{231,173,137},new byte[3]{228,189,147},new byte[3]{228,184,139},new byte[3]{228,184,135},new byte[3]{229,133,131},
  52. new byte[3]{231,164,190},new byte[3]{232,191,135},new byte[3]{229,137,141},new byte[3]{233,157,162},new byte[3]{227,128,130},new byte[3]{239,188,140},
  53. new byte[3]{239,188,159},new byte[3]{239,188,129},
  54. };
  55. /// <summary>
  56. /// Unicode编码高频汉字编码
  57. /// </summary>
  58. private List<byte[]> _UnicodeGaoPinZiFuBianMaLsit = new List<byte[]>()
  59. {
  60. new byte[2]{132,118},new byte[2]{0,78},new byte[2]{253,86},new byte[2]{40,87},new byte[2]{186,78},new byte[2]{134,78},new byte[2]{9,103},new byte[2]{45,78},
  61. new byte[2]{47,102},new byte[2]{116,94},new byte[2]{140,84},new byte[2]{39,89},new byte[2]{26,78},new byte[2]{13,78},new byte[2]{58,78},new byte[2]{209,83},
  62. new byte[2]{26,79},new byte[2]{229,93},new byte[2]{207,126},new byte[2]{10,78},new byte[2]{48,87},new byte[2]{2,94},new byte[2]{129,137},new byte[2]{42,78},
  63. new byte[2]{167,78},new byte[2]{217,143},new byte[2]{250,81},new byte[2]{76,136},new byte[2]{92,79},new byte[2]{31,117},new byte[2]{182,91},new byte[2]{229,78},
  64. new byte[2]{16,98},new byte[2]{48,82},new byte[2]{229,101},new byte[2]{17,108},new byte[2]{101,103},new byte[2]{17,98},new byte[2]{232,144},new byte[2]{249,91},
  65. new byte[2]{219,143},new byte[2]{26,89},new byte[2]{104,81},new byte[2]{250,94},new byte[2]{214,78},new byte[2]{108,81},new byte[2]{0,95},new byte[2]{236,78},
  66. new byte[2]{58,87},new byte[2]{85,92},new byte[2]{246,101},new byte[2]{6,116},new byte[2]{176,101},new byte[2]{185,101},new byte[2]{59,78},new byte[2]{1,79},
  67. new byte[2]{68,141},new byte[2]{158,91},new byte[2]{102,91},new byte[2]{165,98},new byte[2]{54,82},new byte[2]{63,101},new byte[2]{78,109},new byte[2]{40,117},
  68. new byte[2]{12,84},new byte[2]{142,78},new byte[2]{213,108},new byte[2]{216,154},new byte[2]{127,149},new byte[2]{176,115},new byte[2]{44,103},new byte[2]{8,103},
  69. new byte[2]{154,91},new byte[2]{22,83},new byte[2]{160,82},new byte[2]{168,82},new byte[2]{8,84},new byte[2]{193,84},new byte[2]{205,145},new byte[2]{115,81},
  70. new byte[2]{58,103},new byte[2]{6,82},new byte[2]{155,82},new byte[2]{234,129},new byte[2]{22,89},new byte[2]{5,128},new byte[2]{58,83},new byte[2]{253,128},
  71. new byte[2]{190,139},new byte[2]{14,84},new byte[2]{49,92},new byte[2]{73,123},new byte[2]{83,79},new byte[2]{11,78},new byte[2]{7,78},new byte[2]{67,81},
  72. new byte[2]{62,121},new byte[2]{199,143},new byte[2]{77,82},new byte[2]{98,151},new byte[2]{2,48},new byte[2]{12,255},new byte[2]{31,255},new byte[2]{1,255}
  73. };
  74. /// <summary>
  75. /// UTF32编码高频汉字编码
  76. /// </summary>
  77. private List<byte[]> _UTF32GaoPinZiFuBianMaLsit = new List<byte[]>()
  78. {
  79. new byte[4]{132,118,0,0},new byte[4]{0,78,0,0},new byte[4]{253,86,0,0},new byte[4]{40,87,0,0},new byte[4]{186,78,0,0},new byte[4]{134,78,0,0},new byte[4]{9,103,0,0},
  80. new byte[4]{45,78,0,0},new byte[4]{47,102,0,0},new byte[4]{116,94,0,0},new byte[4]{140,84,0,0},new byte[4]{39,89,0,0},new byte[4]{26,78,0,0},new byte[4]{13,78,0,0},
  81. new byte[4]{58,78,0,0},new byte[4]{209,83,0,0},new byte[4]{26,79,0,0},new byte[4]{229,93,0,0},new byte[4]{207,126,0,0},new byte[4]{10,78,0,0},new byte[4]{48,87,0,0},
  82. new byte[4]{2,94,0,0},new byte[4]{129,137,0,0},new byte[4]{42,78,0,0},new byte[4]{167,78,0,0},new byte[4]{217,143,0,0},new byte[4]{250,81,0,0},new byte[4]{76,136,0,0},
  83. new byte[4]{92,79,0,0},new byte[4]{31,117,0,0},new byte[4]{182,91,0,0},new byte[4]{229,78,0,0},new byte[4]{16,98,0,0},new byte[4]{48,82,0,0},new byte[4]{229,101,0,0},
  84. new byte[4]{17,108,0,0},new byte[4]{101,103,0,0},new byte[4]{17,98,0,0},new byte[4]{232,144,0,0},new byte[4]{249,91,0,0},new byte[4]{219,143,0,0},new byte[4]{26,89,0,0},
  85. new byte[4]{104,81,0,0},new byte[4]{250,94,0,0},new byte[4]{214,78,0,0},new byte[4]{108,81,0,0},new byte[4]{0,95,0,0},new byte[4]{236,78,0,0},new byte[4]{58,87,0,0},
  86. new byte[4]{85,92,0,0},new byte[4]{246,101,0,0},new byte[4]{6,116,0,0},new byte[4]{176,101,0,0},new byte[4]{185,101,0,0},new byte[4]{59,78,0,0},new byte[4]{1,79,0,0},
  87. new byte[4]{68,141,0,0},new byte[4]{158,91,0,0},new byte[4]{102,91,0,0},new byte[4]{165,98,0,0},new byte[4]{54,82,0,0},new byte[4]{63,101,0,0},new byte[4]{78,109,0,0},
  88. new byte[4]{40,117,0,0},new byte[4]{12,84,0,0},new byte[4]{142,78,0,0},new byte[4]{213,108,0,0},new byte[4]{216,154,0,0},new byte[4]{127,149,0,0},new byte[4]{176,115,0,0},
  89. new byte[4]{44,103,0,0},new byte[4]{8,103,0,0},new byte[4]{154,91,0,0},new byte[4]{22,83,0,0},new byte[4]{160,82,0,0},new byte[4]{168,82,0,0},new byte[4]{8,84,0,0},
  90. new byte[4]{193,84,0,0},new byte[4]{205,145,0,0},new byte[4]{115,81,0,0},new byte[4]{58,103,0,0},new byte[4]{6,82,0,0},new byte[4]{155,82,0,0},new byte[4]{234,129,0,0},
  91. new byte[4]{22,89,0,0},new byte[4]{5,128,0,0},new byte[4]{58,83,0,0},new byte[4]{253,128,0,0},new byte[4]{190,139,0,0},new byte[4]{14,84,0,0},new byte[4]{49,92,0,0},
  92. new byte[4]{73,123,0,0},new byte[4]{83,79,0,0},new byte[4]{11,78,0,0},new byte[4]{7,78,0,0},new byte[4]{67,81,0,0},new byte[4]{62,121,0,0},new byte[4]{199,143,0,0},
  93. new byte[4]{77,82,0,0},new byte[4]{98,151,0,0},new byte[4]{2,48,0,0},new byte[4]{12,255,0,0},new byte[4]{31,255,0,0},new byte[4]{1,255,0,0}
  94. };
  95. /// <summary>
  96. /// UTF7编码高频汉字编码
  97. /// </summary>
  98. private List<byte[]> _UTF7GaoPinZiFuBianMaLsit = new List<byte[]>()
  99. {
  100. new byte[5]{43,100,111,81,45},new byte[5]{43,84,103,65,45},new byte[5]{43,86,118,48,45},new byte[5]{43,86,121,103,45},new byte[5]{43,84,114,111,45},new byte[5]{43,84,111,89,45},
  101. new byte[5]{43,90,119,107,45},new byte[5]{43,84,105,48,45},new byte[5]{43,90,105,56,45},new byte[5]{43,88,110,81,45},new byte[5]{43,86,73,119,45},new byte[5]{43,87,83,99,45},
  102. new byte[5]{43,84,104,111,45},new byte[5]{43,84,103,48,45},new byte[5]{43,84,106,111,45},new byte[5]{43,85,57,69,45},new byte[5]{43,84,120,111,45},new byte[5]{43,88,101,85,45},
  103. new byte[5]{43,102,115,56,45},new byte[5]{43,84,103,111,45},new byte[5]{43,86,122,65,45},new byte[5]{43,88,103,73,45},new byte[5]{43,105,89,69,45},new byte[5]{43,84,105,111,45},
  104. new byte[5]{43,84,113,99,45},new byte[5]{43,106,57,107,45},new byte[5]{43,85,102,111,45},new byte[5]{43,105,69,119,45},new byte[5]{43,84,49,119,45},new byte[5]{43,100,82,56,45},
  105. new byte[5]{43,87,55,89,45},new byte[5]{43,84,117,85,45},new byte[5]{43,89,104,65,45},new byte[5]{43,85,106,65,45},new byte[5]{43,90,101,85,45},new byte[5]{43,98,66,69,45},
  106. new byte[5]{43,90,50,85,45},new byte[5]{43,89,104,69,45},new byte[5]{43,107,79,103,45},new byte[5]{43,87,47,107,45},new byte[5]{43,106,57,115,45},new byte[5]{43,87,82,111,45},
  107. new byte[5]{43,85,87,103,45},new byte[5]{43,88,118,111,45},new byte[5]{43,84,116,89,45},new byte[5]{43,85,87,119,45},new byte[5]{43,88,119,65,45},new byte[5]{43,84,117,119,45},
  108. new byte[5]{43,86,122,111,45},new byte[5]{43,88,70,85,45},new byte[5]{43,90,102,89,45},new byte[5]{43,100,65,89,45},new byte[5]{43,90,98,65,45},new byte[5]{43,90,98,107,45},
  109. new byte[5]{43,84,106,115,45},new byte[5]{43,84,119,69,45},new byte[5]{43,106,85,81,45},new byte[5]{43,87,53,52,45},new byte[5]{43,87,50,89,45},new byte[5]{43,89,113,85,45},
  110. new byte[5]{43,85,106,89,45},new byte[5]{43,90,84,56,45},new byte[5]{43,98,85,52,45},new byte[5]{43,100,83,103,45},new byte[5]{43,86,65,119,45},new byte[5]{43,84,111,52,45},
  111. new byte[5]{43,98,78,85,45},new byte[5]{43,109,116,103,45},new byte[5]{43,108,88,56,45},new byte[5]{43,99,55,65,45},new byte[5]{43,90,121,119,45},new byte[5]{43,90,119,103,45},
  112. new byte[5]{43,87,53,111,45},new byte[5]{43,85,120,89,45},new byte[5]{43,85,113,65,45},new byte[5]{43,85,113,103,45},new byte[5]{43,86,65,103,45},new byte[5]{43,86,77,69,45},
  113. new byte[5]{43,107,99,48,45},new byte[5]{43,85,88,77,45},new byte[5]{43,90,122,111,45},new byte[5]{43,85,103,89,45},new byte[5]{43,85,112,115,45},new byte[5]{43,103,101,111,45},
  114. new byte[5]{43,87,82,89,45},new byte[5]{43,103,65,85,45},new byte[5]{43,85,122,111,45},new byte[5]{43,103,80,48,45},new byte[5]{43,105,55,52,45},new byte[5]{43,86,65,52,45},
  115. new byte[5]{43,88,68,69,45},new byte[5]{43,101,48,107,45},new byte[5]{43,84,49,77,45},new byte[5]{43,84,103,115,45},new byte[5]{43,84,103,99,45},new byte[5]{43,85,85,77,45},
  116. new byte[5]{43,101,84,52,45},new byte[5]{43,106,56,99,45},new byte[5]{43,85,107,48,45},new byte[5]{43,108,50,73,45},new byte[5]{43,77,65,73,45},new byte[5]{43,47,119,119,45},
  117. new byte[5]{43,47,120,56,45},new byte[5]{43,47,119,69,45}
  118. };
  119. /// <summary>
  120. /// GB18030编码高频汉字编码
  121. /// </summary>
  122. private List<byte[]> _GB18030GaoPinZiFuBianMaLsit = new List<byte[]>()
  123. {
  124. new byte[2]{181,196},new byte[2]{210,187},new byte[2]{185,250},new byte[2]{212,218},new byte[2]{200,203},new byte[2]{193,203},new byte[2]{211,208},new byte[2]{214,208},new byte[2]{202,199},
  125. new byte[2]{196,234},new byte[2]{186,205},new byte[2]{180,243},new byte[2]{210,181},new byte[2]{178,187},new byte[2]{206,170},new byte[2]{183,162},new byte[2]{187,225},new byte[2]{185,164},
  126. new byte[2]{190,173},new byte[2]{201,207},new byte[2]{181,216},new byte[2]{202,208},new byte[2]{210,170},new byte[2]{184,246},new byte[2]{178,250},new byte[2]{213,226},new byte[2]{179,246},
  127. new byte[2]{208,208},new byte[2]{215,247},new byte[2]{201,250},new byte[2]{188,210},new byte[2]{210,212},new byte[2]{179,201},new byte[2]{181,189},new byte[2]{200,213},new byte[2]{195,241},
  128. new byte[2]{192,180},new byte[2]{206,210},new byte[2]{178,191},new byte[2]{182,212},new byte[2]{189,248},new byte[2]{182,224},new byte[2]{200,171},new byte[2]{189,168},new byte[2]{203,251},
  129. new byte[2]{185,171},new byte[2]{191,170},new byte[2]{195,199},new byte[2]{179,161},new byte[2]{213,185},new byte[2]{202,177},new byte[2]{192,237},new byte[2]{208,194},new byte[2]{183,189},
  130. new byte[2]{214,247},new byte[2]{198,243},new byte[2]{215,202},new byte[2]{202,181},new byte[2]{209,167},new byte[2]{177,168},new byte[2]{214,198},new byte[2]{213,254},new byte[2]{188,195},
  131. new byte[2]{211,195},new byte[2]{205,172},new byte[2]{211,218},new byte[2]{183,168},new byte[2]{184,223},new byte[2]{179,164},new byte[2]{207,214},new byte[2]{177,190},new byte[2]{212,194},
  132. new byte[2]{182,168},new byte[2]{187,175},new byte[2]{188,211},new byte[2]{182,175},new byte[2]{186,207},new byte[2]{198,183},new byte[2]{214,216},new byte[2]{185,216},new byte[2]{187,250},
  133. new byte[2]{183,214},new byte[2]{193,166},new byte[2]{215,212},new byte[2]{205,226},new byte[2]{213,223},new byte[2]{199,248},new byte[2]{196,220},new byte[2]{201,232},new byte[2]{186,243},
  134. new byte[2]{190,205},new byte[2]{181,200},new byte[2]{204,229},new byte[2]{207,194},new byte[2]{205,242},new byte[2]{212,170},new byte[2]{201,231},new byte[2]{185,253},new byte[2]{199,176},
  135. new byte[2]{195,230},new byte[2]{161,163},new byte[2]{163,172},new byte[2]{163,191},new byte[2]{163,161}
  136. };
  137. /// <summary>
  138. /// 表示需要猜测编码的流。
  139. /// </summary>
  140. private Stream _thisStream;
  141. /// <summary>
  142. /// 构造函数
  143. /// </summary>
  144. /// <param name="_canShuStream">参数流</param>
  145. public StreamBianMaJianCe(Stream _canShuStream)
  146. {
  147. if (_canShuStream == null || _canShuStream.Length < 100)
  148. {
  149. throw new System.NullReferenceException("WenZiBianMaJianCe构造函数参数_canShuStream不能为空且长度不能小于100");
  150. }
  151. _thisStream = _canShuStream;
  152. }
  153. /// <summary>
  154. /// 检测。
  155. /// </summary>
  156. /// <returns>流的编码</returns>
  157. public Encoding JianCe()
  158. {
  159. byte[] _streamByte = DuQuWeiZiJie();
  160. Encoding _returnEncoding = Encoding.UTF8;
  161. //通过BOM头来判断编码,有BOM头也就没必要去猜了。
  162. if (GenJuBomCaiBianMa(_streamByte, out _returnEncoding) == false)
  163. {
  164. _returnEncoding = CaiJieWenZiBianMa(_streamByte);
  165. }
  166. return _returnEncoding;
  167. }
  168. /// <summary>
  169. /// 读取数据为字节。
  170. /// </summary>
  171. /// <returns></returns>
  172. private byte[] DuQuWeiZiJie()
  173. {
  174. BinaryReader _BinaryReader = new BinaryReader(_thisStream);
  175. byte[] _returnByte = new byte[_thisStream.Length];
  176. //判断流的长度。
  177. if (_thisStream.Length < (long)int.MaxValue)//小于整型值的情况
  178. {
  179. _BinaryReader.Read(_returnByte, 0, (int)_thisStream.Length);
  180. }
  181. else//大于整型值的情况
  182. {
  183. long _index = 0;
  184. while (_index < _returnByte.Length)
  185. {
  186. _returnByte.CopyTo(_BinaryReader.ReadBytes(1024), _index);
  187. _index = _index + 1024L;
  188. }
  189. }
  190. return _returnByte;
  191. }
  192. /// <summary>
  193. /// 根据BOM头返回编码格式。
  194. /// </summary>
  195. /// <param name="_streamByte">流的字节组。</param>
  196. /// <returns></returns>
  197. private bool GenJuBomCaiBianMa(byte[] _streamByte, out Encoding _ruCanEncoding)
  198. {
  199. //132 49 149 51 GB-18030
  200. if (_streamByte[0] == 132 && _streamByte[1] == 49 && _streamByte[2] == 149 && _streamByte[3] == 51)
  201. {
  202. _ruCanEncoding = Encoding.GetEncoding("GB-18030");
  203. return true;
  204. }
  205. //239 187 191 UTF-8
  206. if (_streamByte[0] == 239 && _streamByte[1] == 187 && _streamByte[2] == 191)
  207. {
  208. _ruCanEncoding = Encoding.UTF8;
  209. return true;
  210. }
  211. //254 255 Unicode
  212. if (_streamByte[0] == 254 && _streamByte[1] == 255)
  213. {
  214. _ruCanEncoding = Encoding.Unicode;
  215. return true;
  216. }
  217. if (_streamByte[0] == 255 && _streamByte[1] == 254)
  218. {
  219. //255 254 0 0 UTF-32
  220. if (_streamByte[2] == 0 && _streamByte[3] == 0)
  221. {
  222. _ruCanEncoding = Encoding.UTF32;
  223. }
  224. //255 254 BigEndianUnicode
  225. _ruCanEncoding = Encoding.BigEndianUnicode;
  226. return true;
  227. }
  228. //43 47 118 UTF-7
  229. if (_streamByte[0] == 43 && _streamByte[1] == 47 && _streamByte[2] == 118)
  230. {
  231. //[ 56 | 57 | 43 | 47 ]
  232. if (_streamByte[3] == 56 || _streamByte[3] == 57 || _streamByte[3] == 43 || _streamByte[3] == 47)
  233. {
  234. _ruCanEncoding = Encoding.UTF7;
  235. return true;
  236. }
  237. }
  238. _ruCanEncoding = null;
  239. return false;
  240. }
  241. /// <summary>
  242. /// 猜解文字编码,适用于没有BOM头的情况。
  243. /// </summary>
  244. /// <param name="_streamByte">流的字节组。</param>
  245. /// <returns></returns>
  246. private Encoding CaiJieWenZiBianMa(byte[] _streamByte)
  247. {
  248. //按照中文世界编码使用概率确定猜解顺序。
  249. //UTF8
  250. if (GaoPinZiJianCeUFT8(_streamByte) == true)
  251. {
  252. return Encoding.UTF8;
  253. }
  254. //gb18030
  255. if (GaoPinZiJianCeGB18030(_streamByte) == true)
  256. {
  257. return Encoding.GetEncoding("gb18030");
  258. }
  259. //UTF7
  260. if (GaoPinZiJianCeUTF7(_streamByte) == true)
  261. {
  262. return Encoding.UTF7;
  263. }
  264. //UTF-32任何字符都以四个字节编码,必然可以被四整除
  265. if (_streamByte.Length % 4 == 0)
  266. {
  267. if (GaoPinZiJianCeUTF32(_streamByte) == true)//UTF32
  268. {
  269. return Encoding.UTF32;
  270. }
  271. }
  272. //BigEndianUnicode和Unicode任何字符都以二个字节编码,必然可以被二整除
  273. if (_streamByte.Length % 2 == 0)
  274. {
  275. //Unicode
  276. if (GaoPinZiJianCeUnicode(_streamByte) == true)
  277. {
  278. return Encoding.Unicode;
  279. }
  280. //BigEndianUnicod
  281. if (GaoPinZiJianCeBigEndianUnicode(_streamByte) == true)
  282. {
  283. return Encoding.BigEndianUnicode;
  284. }
  285. }
  286. //如果上述猜解都失败了,则返回UTF-8。
  287. return Encoding.UTF8;
  288. }
  289. /// <summary>
  290. /// 高频字检查法,UFT8编码方法
  291. /// </summary>
  292. /// <param name="_streamByte">流字节组</param>
  293. /// <returns></returns>
  294. private bool GaoPinZiJianCeUFT8(byte[] _streamByte)
  295. {
  296. //命中次数。
  297. int _mingZhongCiShu = 0;
  298. foreach (byte[] bShuZu in _UTF8GaoPinZiFuBianMaLsit)
  299. {
  300. for (int i = 0; i < _streamByte.Length; i++)
  301. {
  302. //判断首编码是否相等
  303. if (bShuZu[0] == _streamByte[i])
  304. {
  305. //如果首字节相等,则检查后面二个字节是否也相等
  306. if ((i + 1 < _streamByte.Length && _streamByte[i + 1] == bShuZu[1])
  307. && (i + 2 < _streamByte.Length && _streamByte[i + 2] == bShuZu[2]))
  308. {
  309. _mingZhongCiShu++;
  310. }
  311. }
  312. }
  313. //UTF-8有一定几率与其他编码冲突,故而增加命中次数,减少误差。
  314. if (_mingZhongCiShu > 2)
  315. {
  316. return true;
  317. }
  318. }
  319. return false;
  320. }
  321. /// <summary>
  322. /// 高频字检查法,Unicode编码方法
  323. /// </summary>
  324. /// <param name="_streamByte">流字节组</param>
  325. /// <returns></returns>
  326. private bool GaoPinZiJianCeUnicode(byte[] _streamByte)
  327. {
  328. foreach (byte[] bShuZu in _UnicodeGaoPinZiFuBianMaLsit)
  329. {
  330. for (int i = 0; i < _streamByte.Length; i++)
  331. {
  332. //判断首编码是否相等
  333. if (bShuZu[0] == _streamByte[i]
  334. && (i + 1 < _streamByte.Length && _streamByte[i + 1] == bShuZu[1]))
  335. {
  336. //如果首字节相等,则检查后面二个字节是否也相等
  337. return true;
  338. }
  339. }
  340. }
  341. return false;
  342. }
  343. /// <summary>
  344. /// 高频字检查法,UTF32编码方法
  345. /// </summary>
  346. /// <param name="_streamByte">流字节组</param>
  347. /// <returns></returns>
  348. private bool GaoPinZiJianCeUTF32(byte[] _streamByte)
  349. {
  350. foreach (byte[] bShuZu in _UTF32GaoPinZiFuBianMaLsit)
  351. {
  352. for (int i = 0; i < _streamByte.Length; i++)
  353. {
  354. //判断首编码是否相等
  355. if (bShuZu[0] == _streamByte[i])
  356. {
  357. //如果首字节相等,则检查后面二个字节是否也相等
  358. if ((i + 1 < _streamByte.Length && _streamByte[i + 1] == bShuZu[1])
  359. && (i + 2 < _streamByte.Length && _streamByte[i + 2] == bShuZu[2])
  360. && (i + 3 < _streamByte.Length && _streamByte[i + 3] == bShuZu[3]))
  361. {
  362. return true;
  363. }
  364. }
  365. }
  366. }
  367. return false;
  368. }
  369. /// <summary>
  370. /// 高频字检查法,UTF7编码方法
  371. /// </summary>
  372. /// <param name="_streamByte">流字节组</param>
  373. /// <returns></returns>
  374. private bool GaoPinZiJianCeUTF7(byte[] _streamByte)
  375. {
  376. foreach (byte[] bShuZu in _UTF7GaoPinZiFuBianMaLsit)
  377. {
  378. for (int i = 0; i < _streamByte.Length; i++)
  379. {
  380. //判断首编码是否相等
  381. if (bShuZu[0] == _streamByte[i])
  382. {
  383. //如果首字节相等,则检查后面二个字节是否也相等
  384. if ((i + 1 < _streamByte.Length && _streamByte[i + 1] == bShuZu[1])
  385. && (i + 2 < _streamByte.Length && _streamByte[i + 2] == bShuZu[2])
  386. && (i + 3 < _streamByte.Length && _streamByte[i + 3] == bShuZu[3])
  387. && (i + 4 < _streamByte.Length && _streamByte[i + 4] == bShuZu[4]))
  388. {
  389. return true;
  390. }
  391. }
  392. }
  393. }
  394. return false;
  395. }
  396. /// <summary>
  397. /// 高频字检查法,GB18030编码方法
  398. /// </summary>
  399. /// <param name="_streamByte">流字节组</param>
  400. /// <returns></returns>
  401. private bool GaoPinZiJianCeGB18030(byte[] _streamByte)
  402. {
  403. foreach (byte[] bShuZu in _GB18030GaoPinZiFuBianMaLsit)
  404. {
  405. for (int i = 0; i < _streamByte.Length; i++)
  406. {
  407. //判断首编码是否相等
  408. if (bShuZu[0] == _streamByte[i])
  409. {
  410. //如果首字节相等,则检查后面二个字节是否也相等
  411. if ((i + 1 < _streamByte.Length && _streamByte[i + 1] == bShuZu[0]))
  412. {
  413. return true;
  414. }
  415. }
  416. }
  417. }
  418. return false;
  419. }
  420. /// <summary>
  421. /// 高频字检查法,Unicode编码方法
  422. /// </summary>
  423. /// <param name="_streamByte">流字节组</param>
  424. /// <returns></returns>
  425. private bool GaoPinZiJianCeBigEndianUnicode(byte[] _streamByte)
  426. {
  427. foreach (byte[] bShuZu in _BigEndianUnicodeGaoPinZiFuBianMaLsit)
  428. {
  429. for (int i = 0; i < _streamByte.Length; i++)
  430. {
  431. //判断首编码是否相等
  432. if (bShuZu[0] == _streamByte[i])
  433. {
  434. //如果首字节相等,则检查后面二个字节是否也相等
  435. if ((i + 1 < _streamByte.Length && _streamByte[i + 1] == bShuZu[1]))
  436. {
  437. return true;
  438. }
  439. }
  440. }
  441. }
  442. return false;
  443. }
  444. }
  445. }
  1. //使用示例
  2. //爬虫判断网页编码
  3. WebRequest _WebRequest = WebRequest.Create(@"https://www.cnblogs.com/j20171203/");
  4. WebResponse _WebResponse = _WebRequest.GetResponse();
  5. Stream _Stream = _WebResponse.GetResponseStream();
  6. MemoryStream _MemoryStream = new MemoryStream();
  7. const int bufferLength = 1024;
  8. byte[] buffer = new byte[bufferLength];
  9. int actual = 1;
  10. while (true)
  11. {
  12. actual = _Stream.Read(buffer, 0, bufferLength);
  13. _MemoryStream.Write(buffer, 0, actual);
  14. if (actual == 0)
  15. {
  16. break;
  17. }
  18. }
  19. _MemoryStream.Position = 0;
  20. StreamBianMaJianCe _StreamBianMaJianCe = new StreamBianMaJianCe(_MemoryStream);
  21. Encoding _jieGuoEncoding = _StreamBianMaJianCe.JianCe();
  22. _Stream.Close();
  23. _Stream.Dispose();
  24. _WebResponse.Close();

 

写作时间:2018-07-19

=====================================================================================

本文只代表本人的见解,可能存在错误,仅用于技术交流。如果你喜欢该文,可以扫下面的二维码打赏我(打赏敬请备注“博客园打赏”五字)。

 友情链接:直通硅谷  点职佳  北美留学生论坛

本站QQ群:前端 618073944 | Java 606181507 | Python 626812652 | C/C++ 612253063 | 微信 634508462 | 苹果 692586424 | C#/.net 182808419 | PHP 305140648 | 运维 608723728

W3xue 的所有内容仅供测试,对任何法律问题及风险不承担任何责任。通过使用本站内容随之而来的风险与本站无关。
关于我们  |  意见建议  |  捐助我们  |  报错有奖  |  广告合作、友情链接(目前9元/月)请联系QQ:27243702 沸活量
皖ICP备17017327号-2 皖公网安备34020702000426号