From c3eb521a0f10112df6b61d2592351c4eef2e1f9b Mon Sep 17 00:00:00 2001 From: Edward Welbourne Date: Wed, 23 Oct 2019 17:17:49 +0200 Subject: Update UCD data to Unicode 12.1.0's Revision 24 Had to teach the update program to accept category Lm as for Joining_Transparent, for the sake of a new ArabicShaping.txt entry. Added three new Unicode versions, several new scripts and a new word-break class. Updated UCD's test data for tst_QTextBoundaryFinder. This left 57 tests failing; I have commented out the data rows for those tests, pending someone with more knowledge addressing this. Task-number: QTBUG-79631 Task-number: QTBUG-79418 Change-Id: Ic33d3b3551195d47a84d98e84020f57a68f0b201 Reviewed-by: Eskil Abrahamsen Blomfeldt --- util/unicode/data/DerivedAge.txt | 153 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 150 insertions(+), 3 deletions(-) (limited to 'util/unicode/data/DerivedAge.txt') diff --git a/util/unicode/data/DerivedAge.txt b/util/unicode/data/DerivedAge.txt index 917afd413c..6350315050 100644 --- a/util/unicode/data/DerivedAge.txt +++ b/util/unicode/data/DerivedAge.txt @@ -1,6 +1,6 @@ -# DerivedAge-10.0.0.txt -# Date: 2017-04-14, 05:40:18 GMT -# © 2017 Unicode®, Inc. +# DerivedAge-12.1.0.txt +# Date: 2019-04-01, 09:10:08 GMT +# © 2019 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html # @@ -1647,4 +1647,151 @@ A8C5 ; 9.0 # SAURASHTRA SIGN CANDRABINDU # Total code points: 8518 +# ================================================ + +# Age=V11_0 + +# Newly assigned in Unicode 11.0.0 (June, 2018) + +0560 ; 11.0 # ARMENIAN SMALL LETTER TURNED AYB +0588 ; 11.0 # ARMENIAN SMALL LETTER YI WITH STROKE +05EF ; 11.0 # HEBREW YOD TRIANGLE +07FD..07FF ; 11.0 # [3] NKO DANTAYALAN..NKO TAMAN SIGN +08D3 ; 11.0 # ARABIC SMALL LOW WAW +09FE ; 11.0 # BENGALI SANDHI MARK +0A76 ; 11.0 # GURMUKHI ABBREVIATION SIGN +0C04 ; 11.0 # TELUGU SIGN COMBINING ANUSVARA ABOVE +0C84 ; 11.0 # KANNADA SIGN SIDDHAM +1878 ; 11.0 # MONGOLIAN LETTER CHA WITH TWO DOTS +1C90..1CBA ; 11.0 # [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; 11.0 # [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN +2BBA..2BBC ; 11.0 # [3] OVERLAPPING WHITE SQUARES..OVERLAPPING BLACK SQUARES +2BD3..2BEB ; 11.0 # [25] PLUTO FORM TWO..STAR WITH RIGHT HALF BLACK +2BF0..2BFE ; 11.0 # [15] ERIS FORM ONE..REVERSED RIGHT ANGLE +2E4A..2E4E ; 11.0 # [5] DOTTED SOLIDUS..PUNCTUS ELEVATUS MARK +312F ; 11.0 # BOPOMOFO LETTER NN +9FEB..9FEF ; 11.0 # [5] CJK UNIFIED IDEOGRAPH-9FEB..CJK UNIFIED IDEOGRAPH-9FEF +A7AF ; 11.0 # LATIN LETTER SMALL CAPITAL Q +A7B8..A7B9 ; 11.0 # [2] LATIN CAPITAL LETTER U WITH STROKE..LATIN SMALL LETTER U WITH STROKE +A8FE..A8FF ; 11.0 # [2] DEVANAGARI LETTER AY..DEVANAGARI VOWEL SIGN AY +10A34..10A35 ; 11.0 # [2] KHAROSHTHI LETTER TTTA..KHAROSHTHI LETTER VHA +10A48 ; 11.0 # KHAROSHTHI FRACTION ONE HALF +10D00..10D27 ; 11.0 # [40] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA SIGN TASSI +10D30..10D39 ; 11.0 # [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +10F00..10F27 ; 11.0 # [40] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LIGATURE AYIN-DALETH +10F30..10F59 ; 11.0 # [42] SOGDIAN LETTER ALEPH..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +110CD ; 11.0 # KAITHI NUMBER SIGN ABOVE +11144..11146 ; 11.0 # [3] CHAKMA LETTER LHAA..CHAKMA VOWEL SIGN EI +1133B ; 11.0 # COMBINING BINDU BELOW +1145E ; 11.0 # NEWA SANDHI MARK +1171A ; 11.0 # AHOM LETTER ALTERNATE BA +11800..1183B ; 11.0 # [60] DOGRA LETTER A..DOGRA ABBREVIATION SIGN +11A9D ; 11.0 # SOYOMBO MARK PLUTA +11D60..11D65 ; 11.0 # [6] GUNJALA GONDI LETTER A..GUNJALA GONDI LETTER UU +11D67..11D68 ; 11.0 # [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI +11D6A..11D8E ; 11.0 # [37] GUNJALA GONDI LETTER OO..GUNJALA GONDI VOWEL SIGN UU +11D90..11D91 ; 11.0 # [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D93..11D98 ; 11.0 # [6] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI OM +11DA0..11DA9 ; 11.0 # [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE +11EE0..11EF8 ; 11.0 # [25] MAKASAR LETTER KA..MAKASAR END OF SECTION +16E40..16E9A ; 11.0 # [91] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN EXCLAMATION OH +187ED..187F1 ; 11.0 # [5] TANGUT IDEOGRAPH-187ED..TANGUT IDEOGRAPH-187F1 +1D2E0..1D2F3 ; 11.0 # [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN +1D372..1D378 ; 11.0 # [7] IDEOGRAPHIC TALLY MARK ONE..TALLY MARK FIVE +1EC71..1ECB4 ; 11.0 # [68] INDIC SIYAQ NUMBER ONE..INDIC SIYAQ ALTERNATE LAKH MARK +1F12F ; 11.0 # COPYLEFT SYMBOL +1F6F9 ; 11.0 # SKATEBOARD +1F7D5..1F7D8 ; 11.0 # [4] CIRCLED TRIANGLE..NEGATIVE CIRCLED SQUARE +1F94D..1F94F ; 11.0 # [3] LACROSSE STICK AND BALL..FLYING DISC +1F96C..1F970 ; 11.0 # [5] LEAFY GREEN..SMILING FACE WITH SMILING EYES AND THREE HEARTS +1F973..1F976 ; 11.0 # [4] FACE WITH PARTY HORN AND PARTY HAT..FREEZING FACE +1F97A ; 11.0 # FACE WITH PLEADING EYES +1F97C..1F97F ; 11.0 # [4] LAB COAT..FLAT SHOE +1F998..1F9A2 ; 11.0 # [11] KANGAROO..SWAN +1F9B0..1F9B9 ; 11.0 # [10] EMOJI COMPONENT RED HAIR..SUPERVILLAIN +1F9C1..1F9C2 ; 11.0 # [2] CUPCAKE..SALT SHAKER +1F9E7..1F9FF ; 11.0 # [25] RED GIFT ENVELOPE..NAZAR AMULET +1FA60..1FA6D ; 11.0 # [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER + +# Total code points: 684 + +# ================================================ + +# Age=V12_0 + +# Newly assigned in Unicode 12.0.0 (March, 2019) + +0C77 ; 12.0 # TELUGU SIGN SIDDHAM +0E86 ; 12.0 # LAO LETTER PALI GHA +0E89 ; 12.0 # LAO LETTER PALI CHA +0E8C ; 12.0 # LAO LETTER PALI JHA +0E8E..0E93 ; 12.0 # [6] LAO LETTER PALI NYA..LAO LETTER PALI NNA +0E98 ; 12.0 # LAO LETTER PALI DHA +0EA0 ; 12.0 # LAO LETTER PALI BHA +0EA8..0EA9 ; 12.0 # [2] LAO LETTER SANSKRIT SHA..LAO LETTER SANSKRIT SSA +0EAC ; 12.0 # LAO LETTER PALI LLA +0EBA ; 12.0 # LAO SIGN PALI VIRAMA +1CFA ; 12.0 # VEDIC SIGN DOUBLE ANUSVARA ANTARGOMUKHA +2BC9 ; 12.0 # NEPTUNE FORM TWO +2BFF ; 12.0 # HELLSCHREIBER PAUSE SYMBOL +2E4F ; 12.0 # CORNISH VERSE DIVIDER +A7BA..A7BF ; 12.0 # [6] LATIN CAPITAL LETTER GLOTTAL A..LATIN SMALL LETTER GLOTTAL U +A7C2..A7C6 ; 12.0 # [5] LATIN CAPITAL LETTER ANGLICANA W..LATIN CAPITAL LETTER Z WITH PALATAL HOOK +AB66..AB67 ; 12.0 # [2] LATIN SMALL LETTER DZ DIGRAPH WITH RETROFLEX HOOK..LATIN SMALL LETTER TS DIGRAPH WITH RETROFLEX HOOK +10FE0..10FF6 ; 12.0 # [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH +1145F ; 12.0 # NEWA LETTER VEDIC ANUSVARA +116B8 ; 12.0 # TAKRI LETTER ARCHAIC KHA +119A0..119A7 ; 12.0 # [8] NANDINAGARI LETTER A..NANDINAGARI LETTER VOCALIC RR +119AA..119D7 ; 12.0 # [46] NANDINAGARI LETTER E..NANDINAGARI VOWEL SIGN VOCALIC RR +119DA..119E4 ; 12.0 # [11] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN PRISHTHAMATRA E +11A84..11A85 ; 12.0 # [2] SOYOMBO SIGN JIHVAMULIYA..SOYOMBO SIGN UPADHMANIYA +11FC0..11FF1 ; 12.0 # [50] TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH..TAMIL SIGN VAKAIYARAA +11FFF ; 12.0 # TAMIL PUNCTUATION END OF TEXT +13430..13438 ; 12.0 # [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT +16F45..16F4A ; 12.0 # [6] MIAO LETTER BRI..MIAO LETTER RTE +16F4F ; 12.0 # MIAO SIGN CONSONANT MODIFIER BAR +16F7F..16F87 ; 12.0 # [9] MIAO VOWEL SIGN UOG..MIAO VOWEL SIGN UI +16FE2..16FE3 ; 12.0 # [2] OLD CHINESE HOOK MARK..OLD CHINESE ITERATION MARK +187F2..187F7 ; 12.0 # [6] TANGUT IDEOGRAPH-187F2..TANGUT IDEOGRAPH-187F7 +1B150..1B152 ; 12.0 # [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B164..1B167 ; 12.0 # [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N +1E100..1E12C ; 12.0 # [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W +1E130..1E13D ; 12.0 # [14] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER +1E140..1E149 ; 12.0 # [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE +1E14E..1E14F ; 12.0 # [2] NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ..NYIAKENG PUACHUE HMONG CIRCLED CA +1E2C0..1E2F9 ; 12.0 # [58] WANCHO LETTER AA..WANCHO DIGIT NINE +1E2FF ; 12.0 # WANCHO NGUN SIGN +1E94B ; 12.0 # ADLAM NASALIZATION MARK +1ED01..1ED3D ; 12.0 # [61] OTTOMAN SIYAQ NUMBER ONE..OTTOMAN SIYAQ FRACTION ONE SIXTH +1F16C ; 12.0 # RAISED MR SIGN +1F6D5 ; 12.0 # HINDU TEMPLE +1F6FA ; 12.0 # AUTO RICKSHAW +1F7E0..1F7EB ; 12.0 # [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE +1F90D..1F90F ; 12.0 # [3] WHITE HEART..PINCHING HAND +1F93F ; 12.0 # DIVING MASK +1F971 ; 12.0 # YAWNING FACE +1F97B ; 12.0 # SARI +1F9A5..1F9AA ; 12.0 # [6] SLOTH..OYSTER +1F9AE..1F9AF ; 12.0 # [2] GUIDE DOG..PROBING CANE +1F9BA..1F9BF ; 12.0 # [6] SAFETY VEST..MECHANICAL LEG +1F9C3..1F9CA ; 12.0 # [8] BEVERAGE BOX..ICE CUBE +1F9CD..1F9CF ; 12.0 # [3] STANDING PERSON..DEAF PERSON +1FA00..1FA53 ; 12.0 # [84] NEUTRAL CHESS KING..BLACK CHESS KNIGHT-BISHOP +1FA70..1FA73 ; 12.0 # [4] BALLET SHOES..SHORTS +1FA78..1FA7A ; 12.0 # [3] DROP OF BLOOD..STETHOSCOPE +1FA80..1FA82 ; 12.0 # [3] YO-YO..PARACHUTE +1FA90..1FA95 ; 12.0 # [6] RINGED PLANET..BANJO + +# Total code points: 554 + +# ================================================ + +# Age=V12_1 + +# Newly assigned in Unicode 12.1.0 (May, 2019) + +32FF ; 12.1 # SQUARE ERA NAME REIWA + +# Total code points: 1 + # EOF -- cgit v1.2.3