%%% memo % not_cjk=15 {is not cjk characters} % kanji=16 {kanji} % kana=17 {hiragana, katakana} % other_kchar=18 {cjk symbol codes} % hangul=19 {hangul codes} \def\KC#1#2{[#1] \the\kcatcode"#2} \def\kc#1#2{[#1] \the\kcatcode`#1,\the\kcatcode"#2\ifnum`#1="#2 \else !! No match !!\fi} \def\kco#1{\the\kcatcode"#1} \message{not cjk:} \message{\KC{A}{0041}}% U+0041 Basic Latin \message{\KC{À}{00C0}}% U+00C0 "Latin-1 Letters" in Latin-1 Supplement \message{\KC{Ā}{0100}}% U+0100 Latin Extended-A \message{\KC{ƀ}{0180}}% U+0180 Latin Extended-B \message{\KC{Ḁ}{1E00}}% U+1E00 Latin Extended Additional \message{kanji:} \message{\kc{⺀}{2E80}}% U+2E80 CJK Radicals Supplement \message{\kc{⼀}{2F00}}% U+2F00 Kangxi Radicals \message{\kc{ㄅ}{3105}}% U+3105 Bopomofo \message{\kc{㆐}{3190}}% U+3190 Kanbun \message{\kc{ㆠ}{31A0}}% U+31A0 Bopomofo Extended \message{\kc{㇀}{31C0}}% U+31C0 CJK Strokes \message{\kc{㐀}{3400}}% U+3400 CJK Unified Ideographs Extension A \message{\kc{一}{4E00}}% U+4E00 CJK Unified Ideographs \message{\kc{豈}{F900}}% U+F900 CJK Compatibility Ideographs \message{\kc{𠀀}{20000}}% U+20000 CJK Unified Ideographs Extension B \message{\kc{𪜀}{2A700}}% U+2A700 CJK Unified Ideographs Extension C \message{\kc{𫝀}{2B740}}% U+2B740 CJK Unified Ideographs Extension D \message{\kc{𫠠}{2B820}}% U+2B820 CJK Unified Ideographs Extension E \message{\kc{𬺰}{2CEB0}}% U+2CEB0 CJK Unified Ideographs Extension F \message{\kc{𮯰}{2EBF0}}% U+2EBF0 CJK Unified Ideographs Extension I \message{\kc{丽}{2F800}}% U+2F800 CJK Compatibility Ideographs Supplement \message{\kc{𰀀}{30000}}% U+30000 CJK Unified Ideographs Extension G \message{\kc{𱍐}{31350}}% U+31350 CJK Unified Ideographs Extension H \message{kana:} \message{\kc{あ}{3042}}% U+3042 Hiragana \message{\kc{ア}{30A2}}% U+30A2 Katakana \message{\kc{ㇰ}{31F0}}% U+31F0 Katakana Phonetic Extensions \message{\kc{𚿰}{1AFF0}}% U+1AFF0 Kana Extended-B \message{\kc{𛀀}{1B000}}% U+1B000 Kana Supplement \message{\kc{𛄀}{1B100}}% U+1B100 Kana Extended-A \message{\kc{𛅐}{1B150}}% U+1B150 Small Kana Extension \message{\kc{0}{FF10}}% U+FF10 "Fullwidth ASCII variants" in Halfwidth and Fullwidth Forms \message{\kc{ヲ}{FF66}}% U+FF66 "Halfwidth Katakana variants" in Halfwidth and Fullwidth Forms \message{other kchar:} \message{\kc{§}{00A7}}% U+00A7 Latin-1 Supplement \message{\kc{@}{FF20}}% U+FF20 Halfwidth and Fullwidth Forms \message{hangul:} \message{\kc{ᄀ}{1100}}% U+1100 Hangul Jamo \message{\kc{ㄱ}{3131}}% U+3131 Hangul Compatibility Jamo \message{\kc{ꥠ}{A960}}% U+A960 Hangul Jamo Extended-A \message{\kc{가}{AC00}}% U+AC00 Hangul Syllables \message{\kc{ힰ}{D7B0}}% U+D7B0 Hangul Jamo Extended-B \message{others:} \message{\kco{0250}}% IPA Extensions \message{\kco{02B0}}% Spacing Modifier Letters \message{\kco{0300}}% Combining Diacritical Marks \message{\kco{0370}}% Greek and Coptic \message{\kco{0400}}% Cyrillic \message{\kco{0500}}% Cyrillic Supplement \message{\kco{0530}}% Armenian \message{\kco{0590}}% Hebrew \message{\kco{0600}}% Arabic \message{\kco{0700}}% Syriac \message{\kco{0750}}% Arabic Supplement \message{\kco{0780}}% Thaana \message{\kco{07C0}}% NKo \message{\kco{0800}}% Samaritan \message{\kco{0840}}% Mandaic \message{\kco{0860}}% Syriac Supplement \message{\kco{08A0}}% Arabic Extended-A \message{\kco{0900}}% Devanagari \message{\kco{0980}}% Bengali \message{\kco{0A00}}% Gurmukhi \message{\kco{0A80}}% Gujarati \message{\kco{0B00}}% Oriya \message{\kco{0B80}}% Tamil \message{\kco{0C00}}% Telugu \message{\kco{0C80}}% Kannada \message{\kco{0D00}}% Malayalam \message{\kco{0D80}}% Sinhala \message{\kco{0E00}}% Thai \message{\kco{0E80}}% Lao \message{\kco{0F00}}% Tibetan \message{\kco{1000}}% Myanmar \message{\kco{10A0}}% Georgian \message{\kco{1200}}% Ethiopic \message{\kco{1380}}% Ethiopic Supplement \message{\kco{13A0}}% Cherokee \message{\kco{1400}}% Unified Canadian Aboriginal Syllabics \message{\kco{1680}}% Ogham \message{\kco{16A0}}% Runic \message{\kco{1700}}% Tagalog \message{\kco{1720}}% Hanunoo \message{\kco{1740}}% Buhid \message{\kco{1760}}% Tagbanwa \message{\kco{1780}}% Khmer \message{\kco{1800}}% Mongolian \message{\kco{18B0}}% Unified Canadian Aboriginal Syllabics Extended \message{\kco{1900}}% Limbu \message{\kco{1950}}% Tai Le \message{\kco{1980}}% New Tai Lue \message{\kco{19E0}}% Khmer Symbols \message{\kco{1A00}}% Buginese \message{\kco{1A20}}% Tai Tham \message{\kco{1AB0}}% Combining Diacritical Marks Extended \message{\kco{1B00}}% Balinese \message{\kco{1B80}}% Sundanese \message{\kco{1BC0}}% Batak \message{\kco{1C00}}% Lepcha \message{\kco{1C50}}% Ol Chiki \message{\kco{1C80}}% Cyrillic Extended-C \message{\kco{1C90}}% Georgian Extended \message{\kco{1CC0}}% Sundanese Supplement \message{\kco{1CD0}}% Vedic Extensions \message{\kco{1D00}}% Phonetic Extensions \message{\kco{1D80}}% Phonetic Extensions Supplement \message{\kco{1DC0}}% Combining Diacritical Marks Supplement \message{\kco{1F00}}% Greek Extended \message{\kco{2000}}% General Punctuation \message{\kco{2070}}% Superscripts and Subscripts \message{\kco{20A0}}% Currency Symbols \message{\kco{20D0}}% Combining Diacritical Marks for Symbols \message{\kco{2100}}% Letterlike Symbols \message{\kco{2150}}% Number Forms \message{\kco{2190}}% Arrows \message{\kco{2200}}% Mathematical Operators \message{\kco{2300}}% Miscellaneous Technical \message{\kco{2400}}% Control Pictures \message{\kco{2440}}% Optical Character Recognition \message{\kco{2460}}% Enclosed Alphanumerics \message{\kco{2500}}% Box Drawing \message{\kco{2580}}% Block Elements \message{\kco{25A0}}% Geometric Shapes \message{\kco{2600}}% Miscellaneous Symbols \message{\kco{2700}}% Dingbats \message{\kco{27C0}}% Miscellaneous Mathematical Symbols-A \message{\kco{27F0}}% Supplemental Arrows-A \message{\kco{2800}}% Braille Patterns \message{\kco{2900}}% Supplemental Arrows-B \message{\kco{2980}}% Miscellaneous Mathematical Symbols-B \message{\kco{2A00}}% Supplemental Mathematical Operators \message{\kco{2B00}}% Miscellaneous Symbols and Arrows \message{\kco{2C00}}% Glagolitic \message{\kco{2C60}}% Latin Extended-C \message{\kco{2C80}}% Coptic \message{\kco{2D00}}% Georgian Supplement \message{\kco{2D30}}% Tifinagh \message{\kco{2D80}}% Ethiopic Extended \message{\kco{2DE0}}% Cyrillic Extended-A \message{\kco{2E00}}% Supplemental Punctuation \message{\kco{2FF0}}% Ideographic Description Characters \message{\kco{3000}}% CJK Symbols and Punctuation \message{\kco{3200}}% Enclosed CJK Letters and Months \message{\kco{3300}}% CJK Compatibility \message{\kco{4DC0}}% Yijing Hexagram Symbols \message{\kco{A000}}% Yi Syllables \message{\kco{A490}}% Yi Radicals \message{\kco{A4D0}}% Lisu \message{\kco{A500}}% Vai \message{\kco{A640}}% Cyrillic Extended-B \message{\kco{A6A0}}% Bamum \message{\kco{A700}}% Modifier Tone Letters \message{\kco{A720}}% Latin Extended-D \message{\kco{A800}}% Syloti Nagri \message{\kco{A830}}% Common Indic Number Forms \message{\kco{A840}}% Phags-pa \message{\kco{A880}}% Saurashtra \message{\kco{A8E0}}% Devanagari Extended \message{\kco{A900}}% Kayah Li \message{\kco{A930}}% Rejang \message{\kco{A980}}% Javanese \message{\kco{A9E0}}% Myanmar Extended-B \message{\kco{AA00}}% Cham \message{\kco{AA60}}% Myanmar Extended-A \message{\kco{AA80}}% Tai Viet \message{\kco{AAE0}}% Meetei Mayek Extensions \message{\kco{AB00}}% Ethiopic Extended-A \message{\kco{AB30}}% Latin Extended-E \message{\kco{AB70}}% Cherokee Supplement \message{\kco{ABC0}}% Meetei Mayek \message{\kco{D800}}% High Surrogates \message{\kco{DB80}}% High Private Use Surrogates \message{\kco{DC00}}% Low Surrogates \message{\kco{E000}}% Private Use Area \message{\kco{FB00}}% Alphabetic Presentation Forms \message{\kco{FB50}}% Arabic Presentation Forms-A \message{\kco{FE00}}% Variation Selectors \message{\kco{FE10}}% Vertical Forms \message{\kco{FE20}}% Combining Half Marks \message{\kco{FE30}}% CJK Compatibility Forms \message{\kco{FE50}}% Small Form Variants \message{\kco{FE70}}% Arabic Presentation Forms-B \message{\kco{FF00}}% Halfwidth and Fullwidth Forms \message{\kco{FFF0}}% Specials \message{\kco{10000}}% Linear B Syllabary \message{\kco{10080}}% Linear B Ideograms \message{\kco{10100}}% Aegean Numbers \message{\kco{10140}}% Ancient Greek Numbers \message{\kco{10190}}% Ancient Symbols \message{\kco{101D0}}% Phaistos Disc \message{\kco{10280}}% Lycian \message{\kco{102A0}}% Carian \message{\kco{102E0}}% Coptic Epact Numbers \message{\kco{10300}}% Old Italic \message{\kco{10330}}% Gothic \message{\kco{10350}}% Old Permic \message{\kco{10380}}% Ugaritic \message{\kco{103A0}}% Old Persian \message{\kco{10400}}% Deseret \message{\kco{10450}}% Shavian \message{\kco{10480}}% Osmanya \message{\kco{104B0}}% Osage \message{\kco{10500}}% Elbasan \message{\kco{10530}}% Caucasian Albanian \message{\kco{10600}}% Linear A \message{\kco{10800}}% Cypriot Syllabary \message{\kco{10840}}% Imperial Aramaic \message{\kco{10860}}% Palmyrene \message{\kco{10880}}% Nabataean \message{\kco{108E0}}% Hatran \message{\kco{10900}}% Phoenician \message{\kco{10920}}% Lydian \message{\kco{10980}}% Meroitic Hieroglyphs \message{\kco{109A0}}% Meroitic Cursive \message{\kco{10A00}}% Kharoshthi \message{\kco{10A60}}% Old South Arabian \message{\kco{10A80}}% Old North Arabian \message{\kco{10AC0}}% Manichaean \message{\kco{10B00}}% Avestan \message{\kco{10B40}}% Inscriptional Parthian \message{\kco{10B60}}% Inscriptional Pahlavi \message{\kco{10B80}}% Psalter Pahlavi \message{\kco{10C00}}% Old Turkic \message{\kco{10C80}}% Old Hungarian \message{\kco{10D00}}% Hanifi Rohingya \message{\kco{10E60}}% Rumi Numeral Symbols \message{\kco{10E80}}% Yezidi \message{\kco{10EC0}}% Arabic Extended-C \message{\kco{10F00}}% Old Sogdian \message{\kco{10F30}}% Sogdian \message{\kco{10FB0}}% Chorasmian \message{\kco{10FE0}}% Elymaic \message{\kco{11000}}% Brahmi \message{\kco{11080}}% Kaithi \message{\kco{110D0}}% Sora Sompeng \message{\kco{11100}}% Chakma \message{\kco{11150}}% Mahajani \message{\kco{11180}}% Sharada \message{\kco{111E0}}% Sinhala Archaic Numbers \message{\kco{11200}}% Khojki \message{\kco{11280}}% Multani \message{\kco{112B0}}% Khudawadi \message{\kco{11300}}% Grantha \message{\kco{11400}}% Newa \message{\kco{11480}}% Tirhuta \message{\kco{11580}}% Siddham \message{\kco{11600}}% Modi \message{\kco{11660}}% Mongolian Supplement \message{\kco{11680}}% Takri \message{\kco{11700}}% Ahom \message{\kco{11800}}% Dogra \message{\kco{118A0}}% Warang Citi \message{\kco{11900}}% Dives Akuru \message{\kco{119A0}}% Nandinagari \message{\kco{11A00}}% Zanabazar Square \message{\kco{11A50}}% Soyombo \message{\kco{11AC0}}% Pau Cin Hau \message{\kco{11B00}}% Devanagari Extended-A \message{\kco{11C00}}% Bhaiksuki \message{\kco{11C70}}% Marchen \message{\kco{11D00}}% Masaram Gondi \message{\kco{11D60}}% Gunjala Gondi \message{\kco{11EE0}}% Makasar \message{\kco{11F00}}% Kawi \message{\kco{11FB0}}% Lisu Supplement \message{\kco{11FC0}}% Tamil Supplement \message{\kco{12000}}% Cuneiform \message{\kco{12400}}% Cuneiform Numbers and Punctuation \message{\kco{12480}}% Early Dynastic Cuneiform \message{\kco{13000}}% Egyptian Hieroglyphs \message{\kco{13430}}% Egyptian Hieroglyph Format Controls \message{\kco{14400}}% Anatolian Hieroglyphs \message{\kco{16800}}% Bamum Supplement \message{\kco{16A40}}% Mro \message{\kco{16AD0}}% Bassa Vah \message{\kco{16B00}}% Pahawh Hmong \message{\kco{16E40}}% Medefaidrin \message{\kco{16F00}}% Miao \message{\kco{16FE0}}% Ideographic Symbols and Punctuation \message{\kco{17000}}% Tangut \message{\kco{18800}}% Tangut Components \message{\kco{18B00}}% Khitan Small Script \message{\kco{18D00}}% Tangut Supplement \message{\kco{1B170}}% Nushu \message{\kco{1BC00}}% Duployan \message{\kco{1BCA0}}% Shorthand Format Controls \message{\kco{1D000}}% Byzantine Musical Symbols \message{\kco{1D100}}% Musical Symbols \message{\kco{1D200}}% Ancient Greek Musical Notation \message{\kco{1D2C0}}% Kaktovik Numerals \message{\kco{1D2E0}}% Mayan Numerals \message{\kco{1D300}}% Tai Xuan Jing Symbols \message{\kco{1D360}}% Counting Rod Numerals \message{\kco{1D400}}% Mathematical Alphanumeric Symbols \message{\kco{1D800}}% Sutton SignWriting \message{\kco{1E000}}% Glagolitic Supplement \message{\kco{1E030}}% Cyrillic Extended-D \message{\kco{1E100}}% Nyiakeng Puachue Hmong \message{\kco{1E2C0}}% Wancho \message{\kco{1E4D0}}% Nag Mundari \message{\kco{1E800}}% Mende Kikakui \message{\kco{1E900}}% Adlam \message{\kco{1EC70}}% Indic Siyaq Numbers \message{\kco{1ED00}}% Ottoman Siyaq Numbers \message{\kco{1EE00}}% Arabic Mathematical Alphabetic Symbols \message{\kco{1F000}}% Mahjong Tiles \message{\kco{1F030}}% Domino Tiles \message{\kco{1F0A0}}% Playing Cards \message{\kco{1F100}}% Enclosed Alphanumeric Supplement \message{\kco{1F200}}% Enclosed Ideographic Supplement \message{\kco{1F300}}% Miscellaneous Symbols and Pictographs \message{\kco{1F600}}% Emoticons \message{\kco{1F650}}% Ornamental Dingbats \message{\kco{1F680}}% Transport and Map Symbols \message{\kco{1F700}}% Alchemical Symbols \message{\kco{1F780}}% Geometric Shapes Extended \message{\kco{1F800}}% Supplemental Arrows-C \message{\kco{1F900}}% Supplemental Symbols and Pictographs \message{\kco{1FA00}}% Chess Symbols \message{\kco{1FA70}}% Symbols and Pictographs Extended-A \message{\kco{1FB00}}% Symbols for Legacy Computing \message{\kco{E0000}}% Tags \message{\kco{E0100}}% Variation Selectors Supplement \message{\kco{F0000}}% Supplementary Private Use Area-A \message{\kco{100000}}% Supplementary Private Use Area-B %%% block separation \message{check block separation default:} \message{\KC{§}{00A7}}% U+00A7 Latin-1 Supplement \message{\KC{À}{00C0}}% U+00C0 "Latin-1 Letters" in Latin-1 Supplement \message{\KC{0}{FF10}}% U+FF10 "Fullwidth ASCII variants" in Halfwidth and Fullwidth Forms \message{\KC{@}{FF20}}% U+FF20 Halfwidth and Fullwidth Forms \message{\KC{ヲ}{FF66}}% U+FF66 "Halfwidth Katakana variants" in Halfwidth and Fullwidth Forms \message{1st:} \kcatcode"00A7=18% U+00A7+§ Latin-1 Supplement, symbols \kcatcode"00C0=18% U+00C0:À Latin-1 Supplement, Latin-1 letters \kcatcode"FF10=18% U+FF10:0 "Fullwidth ASCII variants" in Halfwidth and Fullwidth Forms \kcatcode"FF20=18% U+FF20:@ Halfwidth and Fullwidth Forms \kcatcode"FF66=18% U+FF66:ヲ "Halfwidth Katakana variants" in Halfwidth and Fullwidth Forms \message{\KC{§}{00A7}}% U+00A7 Latin-1 Supplement \message{\KC{À}{00C0}}% U+00C0 "Latin-1 Letters" in Latin-1 Supplement \message{\KC{0}{FF10}}% U+FF10 "Fullwidth ASCII variants" in Halfwidth and Fullwidth Forms \message{\KC{@}{FF20}}% U+FF20 Halfwidth and Fullwidth Forms \message{\KC{ヲ}{FF66}}% U+FF66 "Halfwidth Katakana variants" in Halfwidth and Fullwidth Forms \message{2nd:} \kcatcode"00A7=17% U+00A7+§ Latin-1 Supplement, symbols \kcatcode"00C0=18% U+00C0:À Latin-1 Supplement, Latin-1 letters \kcatcode"FF10=16% U+FF10:0 "Fullwidth ASCII variants" in Halfwidth and Fullwidth Forms \kcatcode"FF20=17% U+FF20:@ Halfwidth and Fullwidth Forms \kcatcode"FF66=18% U+FF66:ヲ "Halfwidth Katakana variants" in Halfwidth and Fullwidth Forms \message{\KC{§}{00A7}}% U+00A7 Latin-1 Supplement \message{\KC{À}{00C0}}% U+00C0 "Latin-1 Letters" in Latin-1 Supplement \message{\KC{0}{FF10}}% U+FF10 "Fullwidth ASCII variants" in Halfwidth and Fullwidth Forms \message{\KC{@}{FF20}}% U+FF20 Halfwidth and Fullwidth Forms \message{\KC{ヲ}{FF66}}% U+FF66 "Halfwidth Katakana variants" in Halfwidth and Fullwidth Forms \message{3rd:} \kcatcode"00A7=18% U+00A7+§ Latin-1 Supplement, symbols \kcatcode"00C0=17% U+00C0:À Latin-1 Supplement, Latin-1 letters \kcatcode"FF10=19% U+FF10:0 "Fullwidth ASCII variants" in Halfwidth and Fullwidth Forms \kcatcode"FF20=18% U+FF20:@ Halfwidth and Fullwidth Forms \kcatcode"FF66=17% U+FF66:ヲ "Halfwidth Katakana variants" in Halfwidth and Fullwidth Forms \message{\KC{§}{00A7}}% U+00A7 Latin-1 Supplement \message{\KC{À}{00C0}}% U+00C0 "Latin-1 Letters" in Latin-1 Supplement \message{\KC{0}{FF10}}% U+FF10 "Fullwidth ASCII variants" in Halfwidth and Fullwidth Forms \message{\KC{@}{FF20}}% U+FF20 Halfwidth and Fullwidth Forms \message{\KC{ヲ}{FF66}}% U+FF66 "Halfwidth Katakana variants" in Halfwidth and Fullwidth Forms \end