unicode语言字符范围表

u"\u0000-\u007F" # C0控制符及基本拉丁文 (C0 Control and Basic Latin)
u"\u0080-\u00FF" # C1控制符及拉丁文补充
u"\u0100-\u017F" # 拉丁文扩展-A (Latin Extended-A)
u"\u0180-\u024F" # 拉丁文扩展-B (Latin Extended-B)
u"\u0250-\u02AF" # 国际音标扩展 (IPA Extensions)
u"\u02B0-\u02FF" # 空白修饰字母 (Spacing Modifiers)
u"\u0300-\u036F" # 结合用读音符号 (Combining Diacritics Marks)
u"\u0370-\u03FF" # 希腊文及科普特文 (Greek and Coptic)
u"\u0400-\u04FF" # 西里尔字母 (Cyrillic)
u"\u0500-\u052F" # 西里尔字母补充 (Cyrillic Supplement)
u"\u0530-\u058F" # 亚美尼亚语 (Armenian)
u"\u0590-\u05FF" # 希伯来文 (Hebrew)
u"\u0600-\u06FF" # 阿拉伯文 (Arabic)
u"\u0700-\u074F" # 叙利亚文 (Syriac)
u"\u0750-\u077F" # 阿拉伯文补充 (Arabic Supplement)
u"\u0780-\u07BF" # 马尔代夫语 (Thaana)
u"\u07C0-\u077F" # 西非書面語言 (N'Ko)
u"\u0800-\u085F" # 阿维斯塔语及巴列维语 (Avestan and Pahlavi)
u"\u0860-\u087F" # Mandaic
u"\u0880-\u08AF" # 撒马利亚语 (Samaritan)
u"\u0900-\u097F" # 天城文书 (Devanagari)
u"\u0980-\u09FF" # 孟加拉语 (Bengali)
u"\u0A00-\u0A7F" # 锡克教文 (Gurmukhi)
u"\u0A80-\u0AFF" # 古吉拉特文 (Gujarati)
u"\u0B00-\u0B7F" # 奥里亚文 (Oriya)
u"\u0B80-\u0BFF" # 泰米尔文 (Tamil)
u"\u0C00-\u0C7F" # 泰卢固文 (Telugu)
u"\u0C80-\u0CFF" # 卡纳达文 (Kannada)
u"\u0D00-\u0D7F" # 德拉维族语 (Malayalam)
u"\u0D80-\u0DFF" # 僧伽罗语 (Sinhala)
u"\u0E00-\u0E7F" # 泰文 (Thai)
u"\u0E80-\u0EFF" # 老挝文 (Lao)
u"\u0F00-\u0FFF" # 藏文 (Tibetan)
u"\u1000-\u109F" # 缅甸语 (Myanmar)
u"\u10A0-\u10FF" # 格鲁吉亚语 (Georgian)
u"\u1100-\u11FF" # 朝鲜文 (Hangul Jamo)
u"\u1200-\u137F" # 埃塞俄比亚语 (Ethiopic)
u"\u1380-\u139F" # 埃塞俄比亚语补充 (Ethiopic Supplement)
u"\u13A0-\u13FF" # 切罗基语 (Cherokee)
u"\u1400-\u167F" # 统一加拿大土著语音节 (Unified Canadian Aboriginal Syllabics)
u"\u1680-\u169F" # 欧甘字母 (Ogham)
u"\u16A0-\u16FF" # 如尼文 (Runic)
u"\u1700-\u171F" # 塔加拉语 (Tagalog)
u"\u1720-\u173F" # Hanunóo
u"\u1740-\u175F" # Buhid
u"\u1760-\u177F" # Tagbanwa
u"\u1780-\u17FF" # 高棉语 (Khmer)
u"\u1800-\u18AF" # 蒙古文 (Mongolian)
u"\u18B0-\u18FF" # Cham
u"\u1900-\u194F" # Limbu
u"\u1950-\u197F" # 德宏泰语 (Tai Le)
u"\u1980-\u19DF" # 新傣仂语 (New Tai Lue)
u"\u19E0-\u19FF" # 高棉语记号 (Kmer Symbols)
u"\u1A00-\u1A1F" # Buginese
u"\u1A20-\u1A5F" # Batak
u"\u1A80-\u1AEF" # Lanna
u"\u1B00-\u1B7F" # 巴厘语 (Balinese)
u"\u1B80-\u1BB0" # 巽他语 (Sundanese)
u"\u1BC0-\u1BFF" # Pahawh Hmong
u"\u1C00-\u1C4F" # 雷布查语(Lepcha)
u"\u1C50-\u1C7F" # Ol Chiki
u"\u1C80-\u1CDF" # 曼尼普尔语 (Meithei/Manipuri)
u"\u1D00-\u1D7F" # 语音学扩展 (Phonetic Extensions)
u"\u1D80-\u1DBF" # 语音学扩展补充 (Phonetic Extensions Supplement)
u"\u1DC0-\u1DFF" # 结合用读音符号补充 (Combining Diacritics Marks Supplement)
u"\u1E00-\u1EFF" # 拉丁文扩充附加 (Latin Extended Additional)
u"\u1F00-\u1FFF" # 希腊语扩充 (Greek Extended)
u"\u2000-\u206F" # 常用标点 (General Punctuation)
u"\u2070-\u209F" # 上标及下标 (Superscripts and Subscripts)
u"\u20A0-\u20CF" # 货币符号 (Currency Symbols)
u"\u20D0-\u20FF" # 组合用记号 (Combining Diacritics Marks for Symbols)
u"\u2100-\u214F" # 字母式符号 (Letterlike Symbols)
u"\u2150-\u218F" # 数字形式 (Number Form)
u"\u2190-\u21FF" # 箭头 (Arrows)
u"\u2200-\u22FF" # 数学运算符 (Mathematical Operator)
u"\u2300-\u23FF" # 杂项工业符号 (Miscellaneous Technical)
u"\u2400-\u243F" # 控制图片 (Control Pictures)
u"\u2440-\u245F" # 光学识别符 (Optical Character Recognition)
u"\u2460-\u24FF" # 封闭式字母数字 (Enclosed Alphanumerics)
u"\u2500-\u257F" # 制表符 (Box Drawing)
u"\u2580-\u259F" # 方块元素 (Block Element)
u"\u25A0-\u25FF" # 几何图形 (Geometric Shapes)
u"\u2600-\u26FF" # 杂项符号 (Miscellaneous Symbols)
u"\u2700-\u27BF" # 印刷符号 (Dingbats)
u"\u27C0-\u27EF" # 杂项数学符号-A (Miscellaneous Mathematical Symbols-A)
u"\u27F0-\u27FF" # 追加箭头-A (Supplemental Arrows-A)
u"\u2800-\u28FF" # 盲文点字模型 (Braille Patterns)
u"\u2900-\u297F" # 追加箭头-B (Supplemental Arrows-B)
u"\u2980-\u29FF" # 杂项数学符号-B (Miscellaneous Mathematical Symbols-B)
u"\u2A00-\u2AFF" # 追加数学运算符 (Supplemental Mathematical Operator)
u"\u2B00-\u2BFF" # 杂项符号和箭头 (Miscellaneous Symbols and Arrows)
u"\u2C00-\u2C5F" # 格拉哥里字母 (Glagolitic)
u"\u2C60-\u2C7F" # 拉丁文扩展-C (Latin Extended-C)
u"\u2C80-\u2CFF" # 古埃及语 (Coptic)
u"\u2D00-\u2D2F" # 格鲁吉亚语补充 (Georgian Supplement)
u"\u2D30-\u2D7F" # 提非纳文 (Tifinagh)
u"\u2D80-\u2DDF" # 埃塞俄比亚语扩展 (Ethiopic Extended)
u"\u2E00-\u2E7F" # 追加标点 (Supplemental Punctuation)
u"\u2E80-\u2EFF" # CJK 部首补充 (CJK Radicals Supplement)
u"\u2F00-\u2FDF" # 康熙字典部首 (Kangxi Radicals)
u"\u2FF0-\u2FFF" # 表意文字描述符 (Ideographic Description Characters)
u"\u3000-\u303F" # CJK 符号和标点 (CJK Symbols and Punctuation)
u"\u3040-\u309F" # 日文平假名 (Hiragana)
u"\u30A0-\u30FF" # 日文片假名 (Katakana)
u"\u3100-\u312F" # 注音字母 (Bopomofo)
u"\u3130-\u318F" # 朝鲜文兼容字母 (Hangul Compatibility Jamo)
u"\u3190-\u319F" # 象形字注释标志 (Kanbun)
u"\u31A0-\u31BF" # 注音字母扩展 (Bopomofo Extended)
u"\u31C0-\u31EF" # CJK 笔画 (CJK Strokes)
u"\u31F0-\u31FF" # 日文片假名语音扩展 (Katakana Phonetic Extensions)
u"\u3200-\u32FF" # 封闭式 CJK 文字和月份 (Enclosed CJK Letters and Months)
u"\u3300-\u33FF" # CJK 兼容 (CJK Compatibility)
u"\u3400-\u4DBF" # CJK 统一表意符号扩展 A (CJK Unified Ideographs Extension A)
u"\u4DC0-\u4DFF" # 易经六十四卦符号 (Yijing Hexagrams Symbols)
u"\u4E00-\u9FBF" # CJK 统一表意符号 (CJK Unified Ideographs)
u"\uA000-\uA48F" # 彝文音节 (Yi Syllables)
u"\uA490-\uA4CF" # 彝文字根 (Yi Radicals)
u"\uA500-\uA61F" # Vai
u"\uA660-\uA6FF" # 统一加拿大土著语音节补充 (Unified Canadian Aboriginal Syllabics Supplement)
u"\uA700-\uA71F" # 声调修饰字母 (Modifier Tone Letters)
u"\uA720-\uA7FF" # 拉丁文扩展-D (Latin Extended-D)
u"\uA800-\uA82F" # Syloti Nagri
u"\uA840-\uA87F" # 八思巴字 (Phags-pa)
u"\uA880-\uA8DF" # Saurashtra
u"\uA900-\uA97F" # 爪哇语 (Javanese)
u"\uA980-\uA9DF" # Chakma
u"\uAA00-\uAA3F" # Varang Kshiti
u"\uAA40-\uAA6F" # Sorang Sompeng
u"\uAA80-\uAADF" # Newari
u"\uAB00-\uAB5F" # 越南傣语 (Vi?t Thái)
u"\uAB80-\uABA0" # Kayah Li
u"\uAC00-\uD7AF" # 朝鲜文音节 (Hangul Syllables)
u"\uD800-\uDBFF" # High-half zone of UTF-16
u"\uDC00-\uDFFF" # Low-half zone of UTF-16
u"\uE000-\uF8FF" # 自行使用區域 (Private Use Zone)
u"\uF900-\uFAFF" # CJK 兼容象形文字 (CJK Compatibility Ideographs)
u"\uFB00-\uFB4F" # 字母表達形式 (Alphabetic Presentation Form)
u"\uFB50-\uFDFF" # 阿拉伯表達形式A (Arabic Presentation Form-A)
u"\uFE00-\uFE0F" # 变量选择符 (Variation Selector)
u"\uFE10-\uFE1F" # 竖排形式 (Vertical Forms)
u"\uFE20-\uFE2F" # 组合用半符号 (Combining Half Marks)
u"\uFE30-\uFE4F" # CJK 兼容形式 (CJK Compatibility Forms)
u"\uFE50-\uFE6F" # 小型变体形式 (Small Form Variants)
u"\uFE70-\uFEFF" # 阿拉伯表達形式B (Arabic Presentation Form-B)
u"\uFF00-\uFFEF" # 半型及全型形式 (Halfwidth and Fullwidth Form)
u"\uFFF0-\uFFFF" # 特殊 (Specials)

评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值