1# 2# Copyright (C) 2016 and later: Unicode, Inc. and others. 3# License & terms of use: http://www.unicode.org/copyright.html 4# Copyright (c) 2016, International Business Machines Corporation and others. All Rights Reserved. 5# 6# file: line_normal.txt 7# 8# Reference Line Break rules for intltest rbbi/RBBIMonkeyTest 9# 10# Note: Rule syntax and the monkey test itself are still a work in progress. 11# They are expected to change with review and the addition of support for rule tailoring. 12# 13# Line Breaking Rules 14# Implement default line breaking as defined by 15# Unicode Standard Annex #14 Revision 34 for Unicode 8.0 16# http://www.unicode.org/reports/tr14/ 17# tailored as noted in 2nd paragraph below. 18# 19# TODO: Rule LB 8 remains as it was in Unicode 5.2 20# This is only because of a limitation of ICU break engine implementation, 21# not because the older behavior is desirable. 22# 23# This tailors the line break behavior to correspond to CSS 24# line-break=normal (BCP47 -u-lb-normal) as defined for languages other than 25# Chinese & Japanese. 26# It sets characters of class CJ to behave like ID. 27 28 29type = line; 30locale = en@lb=normal; 31 32AI = [:LineBreak = Ambiguous:]; 33AL = [:LineBreak = Alphabetic:]; 34BA = [:LineBreak = Break_After:]; 35BB = [:LineBreak = Break_Before:]; 36BK = [:LineBreak = Mandatory_Break:]; 37B2 = [:LineBreak = Break_Both:]; 38CB = [:LineBreak = Contingent_Break:]; 39CJ = [:LineBreak = Conditional_Japanese_Starter:]; 40CL = [:LineBreak = Close_Punctuation:]; 41CM = [:LineBreak = Combining_Mark:]; 42CP = [:LineBreak = Close_Parenthesis:]; 43CR = [:LineBreak = Carriage_Return:]; 44EB = [[:LineBreak = EB:]\U0001F3C2\U0001F3C7\U0001F3CC\U0001F46A-\U0001F46D\U0001F46F\U0001F574\U0001F6CC]; 45EM = [:LineBreak = EM:]; 46EX = [:LineBreak = Exclamation:]; 47GL = [:LineBreak = Glue:]; 48HL = [:LineBreak = Hebrew_Letter:]; 49HY = [:LineBreak = Hyphen:]; 50H2 = [:LineBreak = H2:]; 51H3 = [:LineBreak = H3:]; 52ID = [[:LineBreak = Ideographic:] CJ]; # CSS Normal tailoring: CJ resolves to ID 53IN = [:LineBreak = Inseperable:]; 54IS = [:LineBreak = Infix_Numeric:]; 55JL = [:LineBreak = JL:]; 56JV = [:LineBreak = JV:]; 57JT = [:LineBreak = JT:]; 58LF = [:LineBreak = Line_Feed:]; 59NL = [:LineBreak = Next_Line:]; 60NS = [:LineBreak = Nonstarter:]; 61NU = [:LineBreak = Numeric:]; 62OP = [:LineBreak = Open_Punctuation:]; 63PO = [:LineBreak = Postfix_Numeric:]; 64PR = [:LineBreak = Prefix_Numeric:]; 65QU = [:LineBreak = Quotation:]; 66RI = [:LineBreak = Regional_Indicator:]; 67SA = [:LineBreak = Complex_Context:]; 68SG = [:LineBreak = Surrogate:]; 69SP = [:LineBreak = Space:]; 70SY = [:LineBreak = Break_Symbols:]; 71WJ = [:LineBreak = Word_Joiner:]; 72XX = [:LineBreak = Unknown:]; 73ZW = [:LineBreak = ZWSpace:]; 74ZWJ = [:LineBreak = ZWJ:]; 75 76EmojiNRK = [[\p{Emoji}] - [[RI]\u002a\u00230-9©®™〰〽]]; 77# Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r12773 78Extended_Pict = [\U0001F774-\U0001F77F\u2700-\u2701\u2703-\u2704\u270E\u2710-\u2711\u2765-\u2767\U0001F030-\U0001F093\U0001F094-\U0001F09F\U0001F10D-\U0001F10F\U0001F12F\U0001F16C-\U0001F16F\U0001F1AD-\U0001F1E5\U0001F203-\U0001F20F\U0001F23C-\U0001F23F\U0001F249-\U0001F24F\U0001F252-\U0001F2FF\U0001F7D5-\U0001F7FF\U0001F000-\U0001F003\U0001F005-\U0001F02B\U0001F02C-\U0001F02F\U0001F322-\U0001F323\U0001F394-\U0001F395\U0001F398\U0001F39C-\U0001F39D\U0001F3F1-\U0001F3F2\U0001F3F6\U0001F4FE\U0001F53E-\U0001F548\U0001F54F\U0001F568-\U0001F56E\U0001F571-\U0001F572\U0001F57B-\U0001F586\U0001F588-\U0001F589\U0001F58E-\U0001F58F\U0001F591-\U0001F594\U0001F597-\U0001F5A3\U0001F5A6-\U0001F5A7\U0001F5A9-\U0001F5B0\U0001F5B3-\U0001F5BB\U0001F5BD-\U0001F5C1\U0001F5C5-\U0001F5D0\U0001F5D4-\U0001F5DB\U0001F5DF-\U0001F5E0\U0001F5E2\U0001F5E4-\U0001F5E7\U0001F5E9-\U0001F5EE\U0001F5F0-\U0001F5F2\U0001F5F4-\U0001F5F9\u2605\u2607-\u260D\u260F-\u2610\u2612\u2616-\u2617\u2619-\u261C\u261E-\u261F\u2621\u2624-\u2625\u2627-\u2629\u262B-\u262D\u2630-\u2637\u263B-\u2647\u2654-\u265F\u2661-\u2662\u2664\u2667\u2669-\u267A\u267C-\u267E\u2680-\u2691\u2695\u2698\u269A\u269D-\u269F\u26A2-\u26A9\u26AC-\u26AF\u26B2-\u26BC\u26BF-\u26C3\u26C6-\u26C7\u26C9-\u26CD\u26D0\u26D2\u26D5-\u26E8\u26EB-\u26EF\u26F6\u26FB-\u26FC\u26FE-\u26FF\u2388\U0001FA00-\U0001FFFD\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F0AF-\U0001F0B0\U0001F0C0\U0001F0D0\U0001F0F6-\U0001F0FF\U0001F80C-\U0001F80F\U0001F848-\U0001F84F\U0001F85A-\U0001F85F\U0001F888-\U0001F88F\U0001F8AE-\U0001F8FF\U0001F900-\U0001F90F\U0001F91F\U0001F928-\U0001F92F\U0001F931-\U0001F932\U0001F93F\U0001F94C-\U0001F94F\U0001F95F-\U0001F97F\U0001F992-\U0001F9BF\U0001F9C1-\U0001F9FF\U0001F6C6-\U0001F6CA\U0001F6E6-\U0001F6E8\U0001F6EA\U0001F6F1-\U0001F6F2\U0001F6D3-\U0001F6DF\U0001F6ED-\U0001F6EF\U0001F6F7-\U0001F6FF]; 79 80# LB1 - Resolve AI, CB, CJ, SA, SG, and XX into other line breaking classes 81AL = [AL AI SG XX ]; 82dictionary = SA; 83 84# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly 85# list it in the numerous rules that use CM. 86CM = [CM ZWJ]; 87 88LB4: BK ÷; 89LB5: CR LF; 90LB5.1: CR ÷; 91LB5.2: LF ÷; 92LB5.3: NL ÷; 93 94LB6: . (BK | CR | LF | NL); 95LB6.1: [^BK CR LF NL SP ZW] CM* (BK | CR | LF | NL); 96 97# Rules LB14 - LB17. 98# Moved before LB7, because they can match a longer sequence that would also match LB7, 99# for example, the sequence "OP CM SP AL" matches LB14 while the prefix of it, 100# "while only the prefix "OP CM SP" matches LB7.1 101LB14: OP CM* SP* .; 102LB15: QU CM* SP* OP; 103LB16: (CL | CP)CM* SP* NS; 104LB17: B2 CM* SP* B2; 105 106LB7.1: [^ZW SP] CM* [SP ZW]; 107LB7.2: [ZW SP] [SP ZW]; 108 109# LB8, ICU differs from UAX-14, 110# ICU: ZW ÷; 111# UAX 14: ZW SP* ÷; 112LB8: ZW ÷; 113 114# LB8a 115# ZWJ x (ID | Extended_Pict | EmojiNRK) 116LB8a: ZWJ (ID | Extended_Pict | EmojiNRK); 117 118 119# LB9: X CM -> X 120# LB10: Unattached CM -> AL 121 122#LB11: × WJ; 123# WJ × 124 125LB11.1: [^BK CR LF NL SP ZW] CM* WJ; 126LB11.2: SP WJ; 127LB11.3: WJ CM* [^CM]; 128 129LB12: GL CM* [^CM]; 130 131LB12a: [^SP BA HY] CM* GL; 132 133# LB 13 ICU Tailoring, matches tailoring exmaple 8 from UAX 14. 134# 135# LB13.1 [^SP] CM* [CL CP EX IS SY] # original UAX 14 rule. 136# LB13.2 SP CM* [CL CP EX IS SY] 137 138LB13.1: [^NU SP] CM* [CL CP IS SY]; 139LB13.2: [^SP] CM* EX; 140LB13.2: SP [CL CP EX IS SY]; 141 142 143# LB 14-17 are moved above LB 7. 144 145LB18: SP ÷; 146 147LB19: . CM* QU; 148LB19.1: QU CM* [^CM]; 149 150# LB 20 Break before and after CB. 151# Interaction with LB8a: ZWJ x ID is tricky because CM includes ZWJ. 152# ZWJ acts like a CM to the left, combining with CB. 153# ZWJ acts independently to the right, no break from ID by LB8a. 154LB20: . CM* ÷ CB; 155LB20.1a: CB CM* ZWJ (ID | Extended_Pict | EmojiNRK); 156LB20.1b: CB CM* ÷; 157 158# Note: Rule 21a must come before 21 to prevent 21.1 from matching HL BA, then 159# not picking up the continuing match after the BA from 21a. 160LB21a: HL CM* (HY | BA) CM* [^CM CB]; 161 162LB21.1: . CM* [BA HY NS]; 163LB21.2: BB CM* [^CM CB]; 164 165LB21b: SY CM* HL; 166 167LB22.1: (AL | HL | CM) CM* IN; # The CM is from LB10, treat an unattached CM as AL. 168LB22.2: EX CM* IN; 169LB22.3: (ID | EB | EM) CM* IN; 170LB22.4: IN CM* IN; 171LB22.5: NU CM* IN; 172 173LB23.1: (AL | HL | CM) CM* NU; 174LB23.2: NU CM* (AL | HL); 175 176LB23a.1: PR CM* (ID | EB | EM); 177LB23a.2: (ID | EB | EM) CM* PO; 178 179LB24.2: (PR | PO) CM* (AL | HL); 180LB24.3: (AL | HL | CM) CM* (PR | PO); 181 182# Numbers. Equivalent to Tailoring example 8 from UAx 14. 183LB25: ((PR | PO)CM*)? ((OP | HY)CM*)? NU (CM*(NU | SY | IS))* (CM*(CL | CP))? (CM*(PR | PO))?; 184 185LB26.1: JL CM* (JL | JV | H2 | H3); 186LB26.2: (JV | H2) CM* (JV | JT); 187LB26.3: (JT | H3) CM* JT; 188 189LB27.1: (JL | JV | JT | H2 | H3) CM* IN; 190LB27.2: (JL | JV | JT | H2 | H3) CM* PO; 191LB27.3: PR CM* (JL | JV | JT | H2 | H3); 192 193# LB28 Do not break between Alphabetics. 194# Unattached (leading) CM treated as AL. 195LB28: (AL | HL | CM)CM* (AL | HL); 196 197LB29: IS CM* (AL | HL); 198 199# LB30 is adjusted for unattached leading CM being treated as AL. 200LB30.1: (AL | CM | HL | NU) CM* OP; 201LB30.2: CP CM* (AL | HL | NU); 202 203# LB31 keep pairs of RI together. 204LB30a.1: RI CM* RI CM* [BK CR LF NL SP ZW WJ GL CL CP EX IS SY QU BA HY NS]; 205LB30a.2: RI CM* RI CM* ZWJ (ID | Extended_Pict | EmojiNRK); 206LB30a.3: RI CM* RI CM* ÷; 207 208# LB30b Do not break between Emoji Base and Emoji Modifier 209LB30b: EB CM* EM; 210 211# LB31 Break Everywhere Else. 212# Include combining marks 213LB31.1: . CM* ZWJ (ID | Extended_Pict | EmojiNRK); 214LB31.2: . CM* ÷; 215