2014年2月4日 星期二

中文編碼範圍

中文資訊處理資料


中文編碼範圍

  3400-4DB5(中文)
  4DC0-4DFF(64卦圖案);2630-0637(八卦圖案)
  4E00-9FA5(中文)
  9FA6-9FCB(UNICODE 3.0 後陸續增補。)(u+9fa6-u+9fb3龦龧龨龩龪龫龬龭龮龯龰龱龲龳)和gb 18030-2000中未加入iso 10646的印刷業常用的偏旁和字形部件(u+9fb4-u+9fbb龴龵龶龷龸龹龺龻)

  F900-Fa2D(中文)
  FA30-FAD9(中文。FA6E-FA6F空缺)   2F000-2FFFF(中文。2f800-2fa1d)   20000-20FFF--2B000-2BFFF(中文。2B000-2b734)
  E000–EFFF(私人造字區)
  2E80-2EF3(2E9A空。簡體部件)
  2F00-2FD5(繁體部首)
  3105-3129(注音符號)
  312A-312C(ㄪㄫㄬ)
  2FF0-2FFB(造字框符號)
碼號
字符
意義
例字
範例
2FF0兩個部件由左至右組成⿰木目
2FF1兩個部件由上至下組成⿱士心
2FF2三個部件由左至右組成⿲氵木目
2FF3三個部件由上至下組成⿳米田共
2FF4兩個部件由外而內組成⿴囗口
2FF5三面包圍,下方開口⿵冂口
2FF6三面包圍,上方開口⿶凵㐅
2FF7三面包圍,右方開口⿷匚口
2FF8兩面包圍,兩個部件由左上至右下組成⿸疒丙
2FF9兩面包圍,兩個部件由左下至右上組成⿹?￧ユᄚ
2FFA兩面包圍,兩個部件由右上至左下組成⿺走己
2FFB兩個部件重疊⿻工从

(此表取自維基百科,請放大看。)


  //Java 內部函數
  private static final String[] blockNames = {
  /*0000..007F;*/ "Basic Latin",
  /*0080..00FF;*/ "Latin-1 Supplement",
  /*0100..017F;*/ "Latin Extended-A",
  /*0180..024F;*/ "Latin Extended-B",
  /*0250..02AF;*/ "IPA Extensions",
  /*02B0..02FF;*/ "Spacing Modifier Letters",
  /*0300..036F;*/ "Combining Diacritical Marks",
  /*0370..03FF;*/ "Greek",
  /*0400..04FF;*/ "Cyrillic",
  /*0530..058F;*/ "Armenian",
  /*0590..05FF;*/ "Hebrew",
  /*0600..06FF;*/ "Arabic",
  /*0700..074F;*/ "Syriac",
  /*0780..07BF;*/ "Thaana",
  /*0900..097F;*/ "Devanagari",
  /*0980..09FF;*/ "Bengali",
  /*0A00..0A7F;*/ "Gurmukhi",
  /*0A80..0AFF;*/ "Gujarati",
  /*0B00..0B7F;*/ "Oriya",
  /*0B80..0BFF;*/ "Tamil",
  /*0C00..0C7F;*/ "Telugu",
  /*0C80..0CFF;*/ "Kannada",
  /*0D00..0D7F;*/ "Malayalam",
  /*0D80..0DFF;*/ "Sinhala",
  /*0E00..0E7F;*/ "Thai",
  /*0E80..0EFF;*/ "Lao",
  /*0F00..0FFF;*/ "Tibetan",
  /*1000..109F;*/ "Myanmar",
  /*10A0..10FF;*/ "Georgian",
  /*1100..11FF;*/ "Hangul Jamo",
  /*1200..137F;*/ "Ethiopic",
  /*13A0..13FF;*/ "Cherokee",
  /*1400..167F;*/ "Unified Canadian Aboriginal Syllabics",
  /*1680..169F;*/ "Ogham",
  /*16A0..16FF;*/ "Runic",
  /*1780..17FF;*/ "Khmer",
  /*1800..18AF;*/ "Mongolian",
  /*1E00..1EFF;*/ "Latin Extended Additional",
  /*1F00..1FFF;*/ "Greek Extended",
  /*2000..206F;*/ "General Punctuation",
  /*2070..209F;*/ "Superscripts and Subscripts",
  /*20A0..20CF;*/ "Currency Symbols",
  /*20D0..20FF;*/ "Combining Marks for Symbols",
  /*2100..214F;*/ "Letterlike Symbols",
  /*2150..218F;*/ "Number Forms",
  /*2190..21FF;*/ "Arrows",
  /*2200..22FF;*/ "Mathematical Operators",
  /*2300..23FF;*/ "Miscellaneous Technical",
  /*2400..243F;*/ "Control Pictures",
  /*2440..245F;*/ "Optical Character Recognition",
  /*2460..24FF;*/ "Enclosed Alphanumerics",
  /*2500..257F;*/ "Box Drawing",
  /*2580..259F;*/ "Block Elements",
  /*25A0..25FF;*/ "Geometric Shapes",
  /*2600..26FF;*/ "Miscellaneous Symbols",
  /*2700..27BF;*/ "Dingbats",
  /*2800..28FF;*/ "Braille Patterns",
  /*2E80..2EFF;*/ "CJK Radicals Supplement",字典用字
  /*2F00..2FDF;*/ "Kangxi Radicals",
  /*2FF0..2FFF;*/ "Ideographic Description Characters",
  /*3000..303F;*/ "CJK Symbols and Punctuation",標點符號
  /*3040..309F;*/ "Hiragana",
  /*30A0..30FF;*/ "Katakana",
  /*3100..312F;*/ "Bopomofo",
  /*3130..318F;*/ "Hangul Compatibility Jamo",
  /*3190..319F;*/ "Kanbun",
  /*31A0..31BF;*/ "Bopomofo Extended",
  /*3200..32FF;*/ "Enclosed CJK Letters and Months",
  /*3300..33FF;*/ "CJK Compatibility",日文使用
  /*3400..4DB5;*/ "CJK Unified Ideographs Extension A",擴充字A區
  /*4E00..9FFF;*/ "CJK Unified Ideographs",中文漢字區
  /*A000..A48F;*/ "Yi Syllables",
  /*A490..A4CF;*/ "Yi Radicals",
  /*AC00..D7A3;*/ "Hangul Syllables",
  /*E000..F8FF;*/ "Private Use",
  /*F900..FAFF;*/ "CJK Compatibility Ideographs",
  /*FB00..FB4F;*/ "Alphabetic Presentation Forms",
  /*FB50..FDFF;*/ "Arabic Presentation Forms-A",
  /*FE20..FE2F;*/ "Combining Half Marks",
  /*FE30..FE4F;*/ "CJK Compatibility Forms",
  /*FE50..FE6F;*/ "Small Form Variants",
  /*FE70..FEFE;*/ "Arabic Presentation Forms-B",
  /*FEFF..FEFF;*/ "Specials",
  /*FF00..FFEF;*/ "Halfwidth and Fullwidth Forms",
  //missing Specials add manually
  /*10300..1032F;*/ "Old Italic", // 84
  /*10330..1034F;*/ "Gothic",
  /*10400..1044F;*/ "Deseret",
  /*1D000..1D0FF;*/ "Byzantine Musical Symbols",
  /*1D100..1D1FF;*/ "Musical Symbols",
  /*1D400..1D7FF;*/ "Mathematical Alphanumeric Symbols",
  /*20000..2A6D6;*/ "CJK Unified Ideographs Extension B",
  /*2F800..2FA1F;*/ "CJK Compatibility Ideographs Supplement",
  /*E0000..E007F;*/ "Tags",
  //missing 2 private use add manually  
  };
  //ADD THOSE MANUALLY
  //F0000..FFFFD; "Private Use",
  //100000..10FFFD; "Private Use"
  //FFF0..FFFD; "Specials",

沒有留言:

張貼留言