diff options
Diffstat (limited to 'lib/stdlib/uc_spec/GraphemeBreakProperty.txt')
| -rw-r--r-- | lib/stdlib/uc_spec/GraphemeBreakProperty.txt | 117 |
1 files changed, 32 insertions, 85 deletions
diff --git a/lib/stdlib/uc_spec/GraphemeBreakProperty.txt b/lib/stdlib/uc_spec/GraphemeBreakProperty.txt index 32bb12e47e..52052e6e33 100644 --- a/lib/stdlib/uc_spec/GraphemeBreakProperty.txt +++ b/lib/stdlib/uc_spec/GraphemeBreakProperty.txt @@ -1,6 +1,6 @@ -# GraphemeBreakProperty-10.0.0.txt -# Date: 2017-03-12, 07:03:41 GMT -# © 2017 Unicode®, Inc. +# GraphemeBreakProperty-11.0.0.txt +# Date: 2018-03-16, 20:34:02 GMT +# © 2018 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 # @@ -24,12 +24,13 @@ 08E2 ; Prepend # Cf ARABIC DISPUTED END OF AYAH 0D4E ; Prepend # Lo MALAYALAM LETTER DOT REPH 110BD ; Prepend # Cf KAITHI NUMBER SIGN +110CD ; Prepend # Cf KAITHI NUMBER SIGN ABOVE 111C2..111C3 ; Prepend # Lo [2] SHARADA SIGN JIHVAMULIYA..SHARADA SIGN UPADHMANIYA 11A3A ; Prepend # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA 11A86..11A89 ; Prepend # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11D46 ; Prepend # Lo MASARAM GONDI REPHA -# Total code points: 19 +# Total code points: 20 # ================================================ @@ -95,12 +96,13 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 0730..074A ; Extend # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH 07A6..07B0 ; Extend # Mn [11] THAANA ABAFILI..THAANA SUKUN 07EB..07F3 ; Extend # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; Extend # Mn NKO DANTAYALAN 0816..0819 ; Extend # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH 081B..0823 ; Extend # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A 0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK -08D4..08E1 ; Extend # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08D3..08E1 ; Extend # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE 093C ; Extend # Mn DEVANAGARI SIGN NUKTA @@ -115,6 +117,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 09CD ; Extend # Mn BENGALI SIGN VIRAMA 09D7 ; Extend # Mc BENGALI AU LENGTH MARK 09E2..09E3 ; Extend # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; Extend # Mn BENGALI SANDHI MARK 0A01..0A02 ; Extend # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A3C ; Extend # Mn GURMUKHI SIGN NUKTA 0A41..0A42 ; Extend # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU @@ -145,6 +148,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 0BCD ; Extend # Mn TAMIL SIGN VIRAMA 0BD7 ; Extend # Mc TAMIL AU LENGTH MARK 0C00 ; Extend # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C04 ; Extend # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE 0C3E..0C40 ; Extend # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II 0C46..0C48 ; Extend # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4D ; Extend # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA @@ -273,6 +277,7 @@ A80B ; Extend # Mn SYLOTI NAGRI SIGN ANUSVARA A825..A826 ; Extend # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E A8C4..A8C5 ; Extend # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8E0..A8F1 ; Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; Extend # Mn DEVANAGARI VOWEL SIGN AY A926..A92D ; Extend # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; Extend # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R A980..A982 ; Extend # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR @@ -309,6 +314,8 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10A38..10A3A ; Extend # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW 10A3F ; Extend # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 11001 ; Extend # Mn BRAHMI SIGN ANUSVARA 11038..11046 ; Extend # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA 1107F..11081 ; Extend # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA @@ -320,7 +327,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11173 ; Extend # Mn MAHAJANI SIGN NUKTA 11180..11181 ; Extend # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA 111B6..111BE ; Extend # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O -111CA..111CC ; Extend # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK +111C9..111CC ; Extend # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK 1122F..11231 ; Extend # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI 11234 ; Extend # Mn KHOJKI SIGN ANUSVARA 11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA @@ -328,7 +335,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA 112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA 11300..11301 ; Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU -1133C ; Extend # Mn GRANTHA SIGN NUKTA +1133B..1133C ; Extend # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA 1133E ; Extend # Mc GRANTHA VOWEL SIGN AA 11340 ; Extend # Mn GRANTHA VOWEL SIGN II 11357 ; Extend # Mc GRANTHA AU LENGTH MARK @@ -337,6 +344,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11438..1143F ; Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI 11442..11444 ; Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA 11446 ; Extend # Mn NEWA SIGN NUKTA +1145E ; Extend # Mn NEWA SANDHI MARK 114B0 ; Extend # Mc TIRHUTA VOWEL SIGN AA 114B3..114B8 ; Extend # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114BA ; Extend # Mn TIRHUTA VOWEL SIGN SHORT E @@ -358,8 +366,9 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1171D..1171F ; Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER -11A01..11A06 ; Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O -11A09..11A0A ; Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +1182F..11837 ; Extend # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11839..1183A ; Extend # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +11A01..11A0A ; Extend # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK 11A33..11A38 ; Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA 11A3B..11A3E ; Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA 11A47 ; Extend # Mn ZANABAZAR SQUARE SUBJOINER @@ -379,6 +388,10 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11D3C..11D3D ; Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O 11D3F..11D45 ; Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA 11D47 ; Extend # Mn MASARAM GONDI RA-KARA +11D90..11D91 ; Extend # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D95 ; Extend # Mn GUNJALA GONDI SIGN ANUSVARA +11D97 ; Extend # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; Extend # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -403,10 +416,11 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1F3FB..1F3FF ; Extend # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1901 +# Total code points: 1948 # ================================================ @@ -517,6 +531,7 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK 110B0..110B2 ; SpacingMark # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II 110B7..110B8 ; SpacingMark # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU 1112C ; SpacingMark # Mc CHAKMA VOWEL SIGN E +11145..11146 ; SpacingMark # Mc [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI 11182 ; SpacingMark # Mc SHARADA SIGN VISARGA 111B3..111B5 ; SpacingMark # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II 111BF..111C0 ; SpacingMark # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA @@ -549,7 +564,8 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK 116B6 ; SpacingMark # Mc TAKRI SIGN VIRAMA 11720..11721 ; SpacingMark # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA 11726 ; SpacingMark # Mc AHOM VOWEL SIGN E -11A07..11A08 ; SpacingMark # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +1182C..1182E ; SpacingMark # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II +11838 ; SpacingMark # Mc DOGRA SIGN VISARGA 11A39 ; SpacingMark # Mc ZANABAZAR SQUARE SIGN VISARGA 11A57..11A58 ; SpacingMark # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU 11A97 ; SpacingMark # Mc SOYOMBO SIGN VISARGA @@ -558,11 +574,15 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK 11CA9 ; SpacingMark # Mc MARCHEN SUBJOINED LETTER YA 11CB1 ; SpacingMark # Mc MARCHEN VOWEL SIGN I 11CB4 ; SpacingMark # Mc MARCHEN VOWEL SIGN O +11D8A..11D8E ; SpacingMark # Mc [5] GUNJALA GONDI VOWEL SIGN AA..GUNJALA GONDI VOWEL SIGN UU +11D93..11D94 ; SpacingMark # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU +11D96 ; SpacingMark # Mc GUNJALA GONDI SIGN VISARGA +11EF5..11EF6 ; SpacingMark # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O 16F51..16F7E ; SpacingMark # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 1D166 ; SpacingMark # Mc MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D16D ; SpacingMark # Mc MUSICAL SYMBOL COMBINING AUGMENTATION DOT -# Total code points: 348 +# Total code points: 362 # ================================================ @@ -1395,81 +1415,8 @@ D789..D7A3 ; LVT # Lo [27] HANGUL SYLLABLE HIG..HANGUL SYLLABLE HIH # ================================================ -261D ; E_Base # So WHITE UP POINTING INDEX -26F9 ; E_Base # So PERSON WITH BALL -270A..270D ; E_Base # So [4] RAISED FIST..WRITING HAND -1F385 ; E_Base # So FATHER CHRISTMAS -1F3C2..1F3C4 ; E_Base # So [3] SNOWBOARDER..SURFER -1F3C7 ; E_Base # So HORSE RACING -1F3CA..1F3CC ; E_Base # So [3] SWIMMER..GOLFER -1F442..1F443 ; E_Base # So [2] EAR..NOSE -1F446..1F450 ; E_Base # So [11] WHITE UP POINTING BACKHAND INDEX..OPEN HANDS SIGN -1F46E ; E_Base # So POLICE OFFICER -1F470..1F478 ; E_Base # So [9] BRIDE WITH VEIL..PRINCESS -1F47C ; E_Base # So BABY ANGEL -1F481..1F483 ; E_Base # So [3] INFORMATION DESK PERSON..DANCER -1F485..1F487 ; E_Base # So [3] NAIL POLISH..HAIRCUT -1F4AA ; E_Base # So FLEXED BICEPS -1F574..1F575 ; E_Base # So [2] MAN IN BUSINESS SUIT LEVITATING..SLEUTH OR SPY -1F57A ; E_Base # So MAN DANCING -1F590 ; E_Base # So RAISED HAND WITH FINGERS SPLAYED -1F595..1F596 ; E_Base # So [2] REVERSED HAND WITH MIDDLE FINGER EXTENDED..RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS -1F645..1F647 ; E_Base # So [3] FACE WITH NO GOOD GESTURE..PERSON BOWING DEEPLY -1F64B..1F64F ; E_Base # So [5] HAPPY PERSON RAISING ONE HAND..PERSON WITH FOLDED HANDS -1F6A3 ; E_Base # So ROWBOAT -1F6B4..1F6B6 ; E_Base # So [3] BICYCLIST..PEDESTRIAN -1F6C0 ; E_Base # So BATH -1F6CC ; E_Base # So SLEEPING ACCOMMODATION -1F918..1F91C ; E_Base # So [5] SIGN OF THE HORNS..RIGHT-FACING FIST -1F91E..1F91F ; E_Base # So [2] HAND WITH INDEX AND MIDDLE FINGERS CROSSED..I LOVE YOU HAND SIGN -1F926 ; E_Base # So FACE PALM -1F930..1F939 ; E_Base # So [10] PREGNANT WOMAN..JUGGLING -1F93D..1F93E ; E_Base # So [2] WATER POLO..HANDBALL -1F9D1..1F9DD ; E_Base # So [13] ADULT..ELF - -# Total code points: 98 - -# ================================================ - -1F3FB..1F3FF ; E_Modifier # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 - -# Total code points: 5 - -# ================================================ - 200D ; ZWJ # Cf ZERO WIDTH JOINER # Total code points: 1 -# ================================================ - -2640 ; Glue_After_Zwj # So FEMALE SIGN -2642 ; Glue_After_Zwj # So MALE SIGN -2695..2696 ; Glue_After_Zwj # So [2] STAFF OF AESCULAPIUS..SCALES -2708 ; Glue_After_Zwj # So AIRPLANE -2764 ; Glue_After_Zwj # So HEAVY BLACK HEART -1F308 ; Glue_After_Zwj # So RAINBOW -1F33E ; Glue_After_Zwj # So EAR OF RICE -1F373 ; Glue_After_Zwj # So COOKING -1F393 ; Glue_After_Zwj # So GRADUATION CAP -1F3A4 ; Glue_After_Zwj # So MICROPHONE -1F3A8 ; Glue_After_Zwj # So ARTIST PALETTE -1F3EB ; Glue_After_Zwj # So SCHOOL -1F3ED ; Glue_After_Zwj # So FACTORY -1F48B ; Glue_After_Zwj # So KISS MARK -1F4BB..1F4BC ; Glue_After_Zwj # So [2] PERSONAL COMPUTER..BRIEFCASE -1F527 ; Glue_After_Zwj # So WRENCH -1F52C ; Glue_After_Zwj # So MICROSCOPE -1F5E8 ; Glue_After_Zwj # So LEFT SPEECH BUBBLE -1F680 ; Glue_After_Zwj # So ROCKET -1F692 ; Glue_After_Zwj # So FIRE ENGINE - -# Total code points: 22 - -# ================================================ - -1F466..1F469 ; E_Base_GAZ # So [4] BOY..WOMAN - -# Total code points: 4 - # EOF |