Module:Unicode data/blocks

Definition from Wiktionary, the free dictionary
Jump to navigation Jump to search

-- Compiled from http://www.unicode.org/Public/UNIDATA/Blocks.txt.
local blocks = {
	{ 0x000000, 0x00007F, "Basic Latin"                                    },
	{ 0x000080, 0x0000FF, "Latin-1 Supplement"                             },
	{ 0x000100, 0x00017F, "Latin Extended-A"                               },
	{ 0x000180, 0x00024F, "Latin Extended-B"                               },
	{ 0x000250, 0x0002AF, "IPA Extensions"                                 },
	{ 0x0002B0, 0x0002FF, "Spacing Modifier Letters"                       },
	{ 0x000300, 0x00036F, "Combining Diacritical Marks"                    },
	{ 0x000370, 0x0003FF, "Greek and Coptic"                               },
	{ 0x000400, 0x0004FF, "Cyrillic"                                       },
	{ 0x000500, 0x00052F, "Cyrillic Supplement"                            },
	{ 0x000530, 0x00058F, "Armenian"                                       },
	{ 0x000590, 0x0005FF, "Hebrew"                                         },
	{ 0x000600, 0x0006FF, "Arabic"                                         },
	{ 0x000700, 0x00074F, "Syriac"                                         },
	{ 0x000750, 0x00077F, "Arabic Supplement"                              },
	{ 0x000780, 0x0007BF, "Thaana"                                         },
	{ 0x0007C0, 0x0007FF, "NKo"                                            },
	{ 0x000800, 0x00083F, "Samaritan"                                      },
	{ 0x000840, 0x00085F, "Mandaic"                                        },
	{ 0x000860, 0x00086F, "Syriac Supplement"                              },
	{ 0x0008A0, 0x0008FF, "Arabic Extended-A"                              },
	{ 0x000900, 0x00097F, "Devanagari"                                     },
	{ 0x000980, 0x0009FF, "Bengali"                                        },
	{ 0x000A00, 0x000A7F, "Gurmukhi"                                       },
	{ 0x000A80, 0x000AFF, "Gujarati"                                       },
	{ 0x000B00, 0x000B7F, "Oriya"                                          },
	{ 0x000B80, 0x000BFF, "Tamil"                                          },
	{ 0x000C00, 0x000C7F, "Telugu"                                         },
	{ 0x000C80, 0x000CFF, "Kannada"                                        },
	{ 0x000D00, 0x000D7F, "Malayalam"                                      },
	{ 0x000D80, 0x000DFF, "Sinhala"                                        },
	{ 0x000E00, 0x000E7F, "Thai"                                           },
	{ 0x000E80, 0x000EFF, "Lao"                                            },
	{ 0x000F00, 0x000FFF, "Tibetan"                                        },
	{ 0x001000, 0x00109F, "Myanmar"                                        },
	{ 0x0010A0, 0x0010FF, "Georgian"                                       },
	{ 0x001100, 0x0011FF, "Hangul Jamo"                                    },
	{ 0x001200, 0x00137F, "Ethiopic"                                       },
	{ 0x001380, 0x00139F, "Ethiopic Supplement"                            },
	{ 0x0013A0, 0x0013FF, "Cherokee"                                       },
	{ 0x001400, 0x00167F, "Unified Canadian Aboriginal Syllabics"          },
	{ 0x001680, 0x00169F, "Ogham"                                          },
	{ 0x0016A0, 0x0016FF, "Runic"                                          },
	{ 0x001700, 0x00171F, "Tagalog"                                        },
	{ 0x001720, 0x00173F, "Hanunoo"                                        },
	{ 0x001740, 0x00175F, "Buhid"                                          },
	{ 0x001760, 0x00177F, "Tagbanwa"                                       },
	{ 0x001780, 0x0017FF, "Khmer"                                          },
	{ 0x001800, 0x0018AF, "Mongolian"                                      },
	{ 0x0018B0, 0x0018FF, "Unified Canadian Aboriginal Syllabics Extended" },
	{ 0x001900, 0x00194F, "Limbu"                                          },
	{ 0x001950, 0x00197F, "Tai Le"                                         },
	{ 0x001980, 0x0019DF, "New Tai Lue"                                    },
	{ 0x0019E0, 0x0019FF, "Khmer Symbols"                                  },
	{ 0x001A00, 0x001A1F, "Buginese"                                       },
	{ 0x001A20, 0x001AAF, "Tai Tham"                                       },
	{ 0x001AB0, 0x001AFF, "Combining Diacritical Marks Extended"           },
	{ 0x001B00, 0x001B7F, "Balinese"                                       },
	{ 0x001B80, 0x001BBF, "Sundanese"                                      },
	{ 0x001BC0, 0x001BFF, "Batak"                                          },
	{ 0x001C00, 0x001C4F, "Lepcha"                                         },
	{ 0x001C50, 0x001C7F, "Ol Chiki"                                       },
	{ 0x001C80, 0x001C8F, "Cyrillic Extended-C"                            },
	{ 0x001C90, 0x001CBF, "Georgian Extended"                              },
	{ 0x001CC0, 0x001CCF, "Sundanese Supplement"                           },
	{ 0x001CD0, 0x001CFF, "Vedic Extensions"                               },
	{ 0x001D00, 0x001D7F, "Phonetic Extensions"                            },
	{ 0x001D80, 0x001DBF, "Phonetic Extensions Supplement"                 },
	{ 0x001DC0, 0x001DFF, "Combining Diacritical Marks Supplement"         },
	{ 0x001E00, 0x001EFF, "Latin Extended Additional"                      },
	{ 0x001F00, 0x001FFF, "Greek Extended"                                 },
	{ 0x002000, 0x00206F, "General Punctuation"                            },
	{ 0x002070, 0x00209F, "Superscripts and Subscripts"                    },
	{ 0x0020A0, 0x0020CF, "Currency Symbols"                               },
	{ 0x0020D0, 0x0020FF, "Combining Diacritical Marks for Symbols"        },
	{ 0x002100, 0x00214F, "Letterlike Symbols"                             },
	{ 0x002150, 0x00218F, "Number Forms"                                   },
	{ 0x002190, 0x0021FF, "Arrows"                                         },
	{ 0x002200, 0x0022FF, "Mathematical Operators"                         },
	{ 0x002300, 0x0023FF, "Miscellaneous Technical"                        },
	{ 0x002400, 0x00243F, "Control Pictures"                               },
	{ 0x002440, 0x00245F, "Optical Character Recognition"                  },
	{ 0x002460, 0x0024FF, "Enclosed Alphanumerics"                         },
	{ 0x002500, 0x00257F, "Box Drawing"                                    },
	{ 0x002580, 0x00259F, "Block Elements"                                 },
	{ 0x0025A0, 0x0025FF, "Geometric Shapes"                               },
	{ 0x002600, 0x0026FF, "Miscellaneous Symbols"                          },
	{ 0x002700, 0x0027BF, "Dingbats"                                       },
	{ 0x0027C0, 0x0027EF, "Miscellaneous Mathematical Symbols-A"           },
	{ 0x0027F0, 0x0027FF, "Supplemental Arrows-A"                          },
	{ 0x002800, 0x0028FF, "Braille Patterns"                               },
	{ 0x002900, 0x00297F, "Supplemental Arrows-B"                          },
	{ 0x002980, 0x0029FF, "Miscellaneous Mathematical Symbols-B"           },
	{ 0x002A00, 0x002AFF, "Supplemental Mathematical Operators"            },
	{ 0x002B00, 0x002BFF, "Miscellaneous Symbols and Arrows"               },
	{ 0x002C00, 0x002C5F, "Glagolitic"                                     },
	{ 0x002C60, 0x002C7F, "Latin Extended-C"                               },
	{ 0x002C80, 0x002CFF, "Coptic"                                         },
	{ 0x002D00, 0x002D2F, "Georgian Supplement"                            },
	{ 0x002D30, 0x002D7F, "Tifinagh"                                       },
	{ 0x002D80, 0x002DDF, "Ethiopic Extended"                              },
	{ 0x002DE0, 0x002DFF, "Cyrillic Extended-A"                            },
	{ 0x002E00, 0x002E7F, "Supplemental Punctuation"                       },
	{ 0x002E80, 0x002EFF, "CJK Radicals Supplement"                        },
	{ 0x002F00, 0x002FDF, "Kangxi Radicals"                                },
	{ 0x002FF0, 0x002FFF, "Ideographic Description Characters"             },
	{ 0x003000, 0x00303F, "CJK Symbols and Punctuation"                    },
	{ 0x003040, 0x00309F, "Hiragana"                                       },
	{ 0x0030A0, 0x0030FF, "Katakana"                                       },
	{ 0x003100, 0x00312F, "Bopomofo"                                       },
	{ 0x003130, 0x00318F, "Hangul Compatibility Jamo"                      },
	{ 0x003190, 0x00319F, "Kanbun"                                         },
	{ 0x0031A0, 0x0031BF, "Bopomofo Extended"                              },
	{ 0x0031C0, 0x0031EF, "CJK Strokes"                                    },
	{ 0x0031F0, 0x0031FF, "Katakana Phonetic Extensions"                   },
	{ 0x003200, 0x0032FF, "Enclosed CJK Letters and Months"                },
	{ 0x003300, 0x0033FF, "CJK Compatibility"                              },
	{ 0x003400, 0x004DBF, "CJK Unified Ideographs Extension A"             },
	{ 0x004DC0, 0x004DFF, "Yijing Hexagram Symbols"                        },
	{ 0x004E00, 0x009FFF, "CJK Unified Ideographs"                         },
	{ 0x00A000, 0x00A48F, "Yi Syllables"                                   },
	{ 0x00A490, 0x00A4CF, "Yi Radicals"                                    },
	{ 0x00A4D0, 0x00A4FF, "Lisu"                                           },
	{ 0x00A500, 0x00A63F, "Vai"                                            },
	{ 0x00A640, 0x00A69F, "Cyrillic Extended-B"                            },
	{ 0x00A6A0, 0x00A6FF, "Bamum"                                          },
	{ 0x00A700, 0x00A71F, "Modifier Tone Letters"                          },
	{ 0x00A720, 0x00A7FF, "Latin Extended-D"                               },
	{ 0x00A800, 0x00A82F, "Syloti Nagri"                                   },
	{ 0x00A830, 0x00A83F, "Common Indic Number Forms"                      },
	{ 0x00A840, 0x00A87F, "Phags-pa"                                       },
	{ 0x00A880, 0x00A8DF, "Saurashtra"                                     },
	{ 0x00A8E0, 0x00A8FF, "Devanagari Extended"                            },
	{ 0x00A900, 0x00A92F, "Kayah Li"                                       },
	{ 0x00A930, 0x00A95F, "Rejang"                                         },
	{ 0x00A960, 0x00A97F, "Hangul Jamo Extended-A"                         },
	{ 0x00A980, 0x00A9DF, "Javanese"                                       },
	{ 0x00A9E0, 0x00A9FF, "Myanmar Extended-B"                             },
	{ 0x00AA00, 0x00AA5F, "Cham"                                           },
	{ 0x00AA60, 0x00AA7F, "Myanmar Extended-A"                             },
	{ 0x00AA80, 0x00AADF, "Tai Viet"                                       },
	{ 0x00AAE0, 0x00AAFF, "Meetei Mayek Extensions"                        },
	{ 0x00AB00, 0x00AB2F, "Ethiopic Extended-A"                            },
	{ 0x00AB30, 0x00AB6F, "Latin Extended-E"                               },
	{ 0x00AB70, 0x00ABBF, "Cherokee Supplement"                            },
	{ 0x00ABC0, 0x00ABFF, "Meetei Mayek"                                   },
	{ 0x00AC00, 0x00D7AF, "Hangul Syllables"                               },
	{ 0x00D7B0, 0x00D7FF, "Hangul Jamo Extended-B"                         },
	{ 0x00D800, 0x00DB7F, "High Surrogates"                                },
	{ 0x00DB80, 0x00DBFF, "High Private Use Surrogates"                    },
	{ 0x00DC00, 0x00DFFF, "Low Surrogates"                                 },
	{ 0x00E000, 0x00F8FF, "Private Use Area"                               },
	{ 0x00F900, 0x00FAFF, "CJK Compatibility Ideographs"                   },
	{ 0x00FB00, 0x00FB4F, "Alphabetic Presentation Forms"                  },
	{ 0x00FB50, 0x00FDFF, "Arabic Presentation Forms-A"                    },
	{ 0x00FE00, 0x00FE0F, "Variation Selectors"                            },
	{ 0x00FE10, 0x00FE1F, "Vertical Forms"                                 },
	{ 0x00FE20, 0x00FE2F, "Combining Half Marks"                           },
	{ 0x00FE30, 0x00FE4F, "CJK Compatibility Forms"                        },
	{ 0x00FE50, 0x00FE6F, "Small Form Variants"                            },
	{ 0x00FE70, 0x00FEFF, "Arabic Presentation Forms-B"                    },
	{ 0x00FF00, 0x00FFEF, "Halfwidth and Fullwidth Forms"                  },
	{ 0x00FFF0, 0x00FFFF, "Specials"                                       },
	{ 0x010000, 0x01007F, "Linear B Syllabary"                             },
	{ 0x010080, 0x0100FF, "Linear B Ideograms"                             },
	{ 0x010100, 0x01013F, "Aegean Numbers"                                 },
	{ 0x010140, 0x01018F, "Ancient Greek Numbers"                          },
	{ 0x010190, 0x0101CF, "Ancient Symbols"                                },
	{ 0x0101D0, 0x0101FF, "Phaistos Disc"                                  },
	{ 0x010280, 0x01029F, "Lycian"                                         },
	{ 0x0102A0, 0x0102DF, "Carian"                                         },
	{ 0x0102E0, 0x0102FF, "Coptic Epact Numbers"                           },
	{ 0x010300, 0x01032F, "Old Italic"                                     },
	{ 0x010330, 0x01034F, "Gothic"                                         },
	{ 0x010350, 0x01037F, "Old Permic"                                     },
	{ 0x010380, 0x01039F, "Ugaritic"                                       },
	{ 0x0103A0, 0x0103DF, "Old Persian"                                    },
	{ 0x010400, 0x01044F, "Deseret"                                        },
	{ 0x010450, 0x01047F, "Shavian"                                        },
	{ 0x010480, 0x0104AF, "Osmanya"                                        },
	{ 0x0104B0, 0x0104FF, "Osage"                                          },
	{ 0x010500, 0x01052F, "Elbasan"                                        },
	{ 0x010530, 0x01056F, "Caucasian Albanian"                             },
	{ 0x010600, 0x01077F, "Linear A"                                       },
	{ 0x010800, 0x01083F, "Cypriot Syllabary"                              },
	{ 0x010840, 0x01085F, "Imperial Aramaic"                               },
	{ 0x010860, 0x01087F, "Palmyrene"                                      },
	{ 0x010880, 0x0108AF, "Nabataean"                                      },
	{ 0x0108E0, 0x0108FF, "Hatran"                                         },
	{ 0x010900, 0x01091F, "Phoenician"                                     },
	{ 0x010920, 0x01093F, "Lydian"                                         },
	{ 0x010980, 0x01099F, "Meroitic Hieroglyphs"                           },
	{ 0x0109A0, 0x0109FF, "Meroitic Cursive"                               },
	{ 0x010A00, 0x010A5F, "Kharoshthi"                                     },
	{ 0x010A60, 0x010A7F, "Old South Arabian"                              },
	{ 0x010A80, 0x010A9F, "Old North Arabian"                              },
	{ 0x010AC0, 0x010AFF, "Manichaean"                                     },
	{ 0x010B00, 0x010B3F, "Avestan"                                        },
	{ 0x010B40, 0x010B5F, "Inscriptional Parthian"                         },
	{ 0x010B60, 0x010B7F, "Inscriptional Pahlavi"                          },
	{ 0x010B80, 0x010BAF, "Psalter Pahlavi"                                },
	{ 0x010C00, 0x010C4F, "Old Turkic"                                     },
	{ 0x010C80, 0x010CFF, "Old Hungarian"                                  },
	{ 0x010D00, 0x010D3F, "Hanifi Rohingya"                                },
	{ 0x010E60, 0x010E7F, "Rumi Numeral Symbols"                           },
	{ 0x010F00, 0x010F2F, "Old Sogdian"                                    },
	{ 0x010F30, 0x010F6F, "Sogdian"                                        },
	{ 0x010FE0, 0x010FFF, "Elymaic"                                        },
	{ 0x011000, 0x01107F, "Brahmi"                                         },
	{ 0x011080, 0x0110CF, "Kaithi"                                         },
	{ 0x0110D0, 0x0110FF, "Sora Sompeng"                                   },
	{ 0x011100, 0x01114F, "Chakma"                                         },
	{ 0x011150, 0x01117F, "Mahajani"                                       },
	{ 0x011180, 0x0111DF, "Sharada"                                        },
	{ 0x0111E0, 0x0111FF, "Sinhala Archaic Numbers"                        },
	{ 0x011200, 0x01124F, "Khojki"                                         },
	{ 0x011280, 0x0112AF, "Multani"                                        },
	{ 0x0112B0, 0x0112FF, "Khudawadi"                                      },
	{ 0x011300, 0x01137F, "Grantha"                                        },
	{ 0x011400, 0x01147F, "Newa"                                           },
	{ 0x011480, 0x0114DF, "Tirhuta"                                        },
	{ 0x011580, 0x0115FF, "Siddham"                                        },
	{ 0x011600, 0x01165F, "Modi"                                           },
	{ 0x011660, 0x01167F, "Mongolian Supplement"                           },
	{ 0x011680, 0x0116CF, "Takri"                                          },
	{ 0x011700, 0x01173F, "Ahom"                                           },
	{ 0x011800, 0x01184F, "Dogra"                                          },
	{ 0x0118A0, 0x0118FF, "Warang Citi"                                    },
	{ 0x0119A0, 0x0119FF, "Nandinagari"                                    },
	{ 0x011A00, 0x011A4F, "Zanabazar Square"                               },
	{ 0x011A50, 0x011AAF, "Soyombo"                                        },
	{ 0x011AC0, 0x011AFF, "Pau Cin Hau"                                    },
	{ 0x011C00, 0x011C6F, "Bhaiksuki"                                      },
	{ 0x011C70, 0x011CBF, "Marchen"                                        },
	{ 0x011D00, 0x011D5F, "Masaram Gondi"                                  },
	{ 0x011D60, 0x011DAF, "Gunjala Gondi"                                  },
	{ 0x011EE0, 0x011EFF, "Makasar"                                        },
	{ 0x011FC0, 0x011FFF, "Tamil Supplement"                               },
	{ 0x012000, 0x0123FF, "Cuneiform"                                      },
	{ 0x012400, 0x01247F, "Cuneiform Numbers and Punctuation"              },
	{ 0x012480, 0x01254F, "Early Dynastic Cuneiform"                       },
	{ 0x013000, 0x01342F, "Egyptian Hieroglyphs"                           },
	{ 0x013430, 0x01343F, "Egyptian Hieroglyph Format Controls"            },
	{ 0x014400, 0x01467F, "Anatolian Hieroglyphs"                          },
	{ 0x016800, 0x016A3F, "Bamum Supplement"                               },
	{ 0x016A40, 0x016A6F, "Mro"                                            },
	{ 0x016AD0, 0x016AFF, "Bassa Vah"                                      },
	{ 0x016B00, 0x016B8F, "Pahawh Hmong"                                   },
	{ 0x016E40, 0x016E9F, "Medefaidrin"                                    },
	{ 0x016F00, 0x016F9F, "Miao"                                           },
	{ 0x016FE0, 0x016FFF, "Ideographic Symbols and Punctuation"            },
	{ 0x017000, 0x0187FF, "Tangut"                                         },
	{ 0x018800, 0x018AFF, "Tangut Components"                              },
	{ 0x01B000, 0x01B0FF, "Kana Supplement"                                },
	{ 0x01B100, 0x01B12F, "Kana Extended-A"                                },
	{ 0x01B130, 0x01B16F, "Small Kana Extension"                           },
	{ 0x01B170, 0x01B2FF, "Nushu"                                          },
	{ 0x01BC00, 0x01BC9F, "Duployan"                                       },
	{ 0x01BCA0, 0x01BCAF, "Shorthand Format Controls"                      },
	{ 0x01D000, 0x01D0FF, "Byzantine Musical Symbols"                      },
	{ 0x01D100, 0x01D1FF, "Musical Symbols"                                },
	{ 0x01D200, 0x01D24F, "Ancient Greek Musical Notation"                 },
	{ 0x01D2E0, 0x01D2FF, "Mayan Numerals"                                 },
	{ 0x01D300, 0x01D35F, "Tai Xuan Jing Symbols"                          },
	{ 0x01D360, 0x01D37F, "Counting Rod Numerals"                          },
	{ 0x01D400, 0x01D7FF, "Mathematical Alphanumeric Symbols"              },
	{ 0x01D800, 0x01DAAF, "Sutton SignWriting"                             },
	{ 0x01E000, 0x01E02F, "Glagolitic Supplement"                          },
	{ 0x01E100, 0x01E14F, "Nyiakeng Puachue Hmong"                         },
	{ 0x01E2C0, 0x01E2FF, "Wancho"                                         },
	{ 0x01E800, 0x01E8DF, "Mende Kikakui"                                  },
	{ 0x01E900, 0x01E95F, "Adlam"                                          },
	{ 0x01EC70, 0x01ECBF, "Indic Siyaq Numbers"                            },
	{ 0x01ED00, 0x01ED4F, "Ottoman Siyaq Numbers"                          },
	{ 0x01EE00, 0x01EEFF, "Arabic Mathematical Alphabetic Symbols"         },
	{ 0x01F000, 0x01F02F, "Mahjong Tiles"                                  },
	{ 0x01F030, 0x01F09F, "Domino Tiles"                                   },
	{ 0x01F0A0, 0x01F0FF, "Playing Cards"                                  },
	{ 0x01F100, 0x01F1FF, "Enclosed Alphanumeric Supplement"               },
	{ 0x01F200, 0x01F2FF, "Enclosed Ideographic Supplement"                },
	{ 0x01F300, 0x01F5FF, "Miscellaneous Symbols and Pictographs"          },
	{ 0x01F600, 0x01F64F, "Emoticons"                                      },
	{ 0x01F650, 0x01F67F, "Ornamental Dingbats"                            },
	{ 0x01F680, 0x01F6FF, "Transport and Map Symbols"                      },
	{ 0x01F700, 0x01F77F, "Alchemical Symbols"                             },
	{ 0x01F780, 0x01F7FF, "Geometric Shapes Extended"                      },
	{ 0x01F800, 0x01F8FF, "Supplemental Arrows-C"                          },
	{ 0x01F900, 0x01F9FF, "Supplemental Symbols and Pictographs"           },
	{ 0x01FA00, 0x01FA6F, "Chess Symbols"                                  },
	{ 0x01FA70, 0x01FAFF, "Symbols and Pictographs Extended-A"             },
	{ 0x020000, 0x02A6DF, "CJK Unified Ideographs Extension B"             },
	{ 0x02A700, 0x02B73F, "CJK Unified Ideographs Extension C"             },
	{ 0x02B740, 0x02B81F, "CJK Unified Ideographs Extension D"             },
	{ 0x02B820, 0x02CEAF, "CJK Unified Ideographs Extension E"             },
	{ 0x02CEB0, 0x02EBEF, "CJK Unified Ideographs Extension F"             },
	{ 0x02F800, 0x02FA1F, "CJK Compatibility Ideographs Supplement"        },
	{ 0x0E0000, 0x0E007F, "Tags"                                           },
	{ 0x0E0100, 0x0E01EF, "Variation Selectors Supplement"                 },
	{ 0x0F0000, 0x0FFFFF, "Supplementary Private Use Area-A"               },
	{ 0x100000, 0x10FFFF, "Supplementary Private Use Area-B"               },
}

blocks.length = #blocks

return blocks