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_loose_cj.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# This tailors the line break behavior to correspond to CSS 20# line-break=loose (BCP47 -u-lb-loose) as defined for Chinese & Japanese. 21# It sets characters of class CJ to behave like ID. 22# In addition, it allows breaks: 23# * before hyphens 2010 & 2013 (both BA) and 301C, 30A0 (both NS) 24# * before iteration marks 3005, 303B, 309D, 309E, 30FD, 30FE (all NS) 25# * between characters of LineBreak class IN such as 2026 26# * before some centered punct 203C, 2047, 2048, 2049, 30FB, FF1A, FF1B, 27# FF65 (all NS) and FF01, FF1F (both EX). 28# * before suffix characters with LineBreak class PO and EastAsianWidth A,F,W; 29# this includes: 00B0 2030 2032 2033 2035 2103 2109 FE6A FF05 FFE0 30# * after prefix characters with LineBreak class PR and EastAsianWidth A,F,W; 31# this includes: 00A4 00B1 20AC 2116 FE69 FF04 FFE1 FFE5 FFE6 32 33 34type = line; 35locale = ja@lb=loose; 36 37 38AI = [:LineBreak = Ambiguous:]; 39AL = [[:LineBreak = Alphabetic:]]; 40BAX = [\u2010 \u2013]; 41BA = [[:LineBreak = Break_After:] - BAX]; 42BB = [:LineBreak = Break_Before:]; 43BK = [:LineBreak = Mandatory_Break:]; 44B2 = [:LineBreak = Break_Both:]; 45CB = [:LineBreak = Contingent_Break:]; 46CJ = [:LineBreak = Conditional_Japanese_Starter:]; 47CL = [:LineBreak = Close_Punctuation:]; 48CM = [:LineBreak = Combining_Mark:]; 49CP = [:LineBreak = Close_Parenthesis:]; 50CR = [:LineBreak = Carriage_Return:]; 51EB = [[:LineBreak = EB:]\U0001F3C2\U0001F3C7\U0001F3CC\U0001F46A-\U0001F46D\U0001F46F\U0001F574\U0001F6CC]; 52EM = [:LineBreak = EM:]; 53EXX = [\uFF01 \uFF1F]; 54EX = [[:LineBreak = Exclamation:] - EXX]; 55GL = [:LineBreak = Glue:]; 56HL = [:LineBreak = Hebrew_Letter:]; 57HY = [:LineBreak = Hyphen:]; 58H2 = [:LineBreak = H2:]; 59H3 = [:LineBreak = H3:]; 60ID = [[:LineBreak = Ideographic:] CJ]; # CSS Loose tailoring: CJ resolves to ID 61IN = [:LineBreak = Inseperable:]; 62IS = [:LineBreak = Infix_Numeric:]; 63JL = [:LineBreak = JL:]; 64JV = [:LineBreak = JV:]; 65JT = [:LineBreak = JT:]; 66LF = [:LineBreak = Line_Feed:]; 67NL = [:LineBreak = Next_Line:]; 68NSX = [\u301C \u30A0 \u3005 \u303B \u309D \u309E \u30FD \u30FE \u203C \u2047 \u2048 \u2049 \u30FB \uFF1A \uFF1B \uFF65]; 69NS = [[:LineBreak = Nonstarter:] - NSX]; 70NU = [:LineBreak = Numeric:]; 71OP = [:LineBreak = Open_Punctuation:]; 72POX = [\u00B0 \u2030 \u2032 \u2033 \u2035 \u2103 \u2109 \uFE6A \uFF05 \uFFE0]; 73PO = [[:LineBreak = Postfix_Numeric:] - POX]; 74PRX = [\u00A4 \u00B1 \u20AC \u2116 \uFE69 \uFF04 \uFFE1 \uFFE5 \uFFE6]; 75PR = [[:LineBreak = Prefix_Numeric:] - PRX]; 76QU = [:LineBreak = Quotation:]; 77RI = [:LineBreak = Regional_Indicator:]; 78SA = [:LineBreak = Complex_Context:]; 79SG = [:LineBreak = Surrogate:]; 80SP = [:LineBreak = Space:]; 81SY = [:LineBreak = Break_Symbols:]; 82WJ = [:LineBreak = Word_Joiner:]; 83XX = [:LineBreak = Unknown:]; 84ZW = [:LineBreak = ZWSpace:]; 85ZWJ = [:LineBreak = ZWJ:]; 86 87EmojiNRK = [[\p{Emoji}] - [[RI]\u002a\u00230-9©®™〰〽]]; 88# Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r12773 89Extended_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]; 90 91# LB1 - Resolve AI, CB, CJ, SA, SG, and XX into other line breaking classes 92AL = [AL AI SG XX ]; 93dictionary = SA; 94 95# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly 96# list it in the numerous rules that use CM. 97CM = [CM ZWJ]; 98 99LB4: BK ÷; 100LB5: CR LF; 101LB5.1: CR ÷; 102LB5.2: LF ÷; 103LB5.3: NL ÷; 104 105LB6: . (BK | CR | LF | NL); 106LB6.1: [^BK CR LF NL SP ZW] CM* (BK | CR | LF | NL); 107 108# Rules LB14 - LB17. 109# Moved before LB7, because they can match a longer sequence that would also match LB7, 110# for example, the sequence "OP CM SP AL" matches LB14 while the prefix of it, 111# "while only the prefix "OP CM SP" matches LB7.1 112LB14: OP CM* SP* .; 113LB15: QU CM* SP* OP; 114LB16: (CL | CP)CM* SP* NS; 115LB17: B2 CM* SP* B2; 116 117LB7.1: [^ZW SP] CM* [SP ZW]; 118LB7.2: [ZW SP] [SP ZW]; 119 120# LB8, ICU differs from UAX-14, 121# ICU: ZW ÷; 122# UAX 14: ZW SP* ÷; 123LB8: ZW ÷; 124 125# LB8a 126# ZWJ x (ID | Extended_Pict | EmojiNRK) 127LB8a: ZWJ (ID | Extended_Pict | EmojiNRK); 128 129 130# LB9: X CM -> X 131# LB10: Unattached CM -> AL 132 133#LB11: × WJ; 134# WJ × 135 136LB11.1: [^BK CR LF NL SP ZW] CM* WJ; 137LB11.2: SP WJ; 138LB11.3: WJ CM* [^CM]; 139 140LB12: GL CM* [^CM]; 141 142LB12a: [^SP BA BAX HY] CM* GL; 143 144# LB 13 ICU Tailoring, matches tailoring exmaple 8 from UAX 14. 145# 146# LB13.1 [^SP] CM* [CL CP EX IS SY] # original UAX 14 rule. 147# LB13.2 SP CM* [CL CP EX IS SY] 148 149LB13.1: [^NU SP] CM* [CL CP IS SY]; 150LB13.2: [^SP] CM* EX; 151LB13.2: SP [CL CP EX IS SY]; 152 153 154# LB 14-17 are moved above LB 7. 155 156LB18: SP ÷; 157 158LB19: . CM* QU; 159LB19.1: QU CM* [^CM]; 160 161# LB 20 Break before and after CB. 162# Interaction with LB8a: ZWJ x ID is tricky because CM includes ZWJ. 163# ZWJ acts like a CM to the left, combining with CB. 164# ZWJ acts independently to the right, no break from ID by LB8a. 165LB20: . CM* ÷ CB; 166LB20.1a: CB CM* ZWJ (ID | Extended_Pict | EmojiNRK); 167LB20.1b: CB CM* ÷; 168 169# Note: Rule 21a must come before 21 to prevent 21.1 from matching HL BA, then 170# not picking up the continuing match after the BA from 21a. 171# LB 21a Don't break after Hebrew + Hyphen 172# HL (HY | BA) x 173 174LB21a: HL CM* (HY | BA | BAX) CM* [^CM CB]?; 175 176LB21.1: . CM* [BA HY NS]; 177LB21.2: BB CM* [^CM CB]; 178 179LB21b: SY CM* HL; 180 181LB22.1: (AL | HL | CM) CM* IN; # The CM is from LB10, treat an unattached CM as AL. 182LB22.2: EX CM* IN; 183LB22.3: (ID | EB | EM) CM* IN; 184# LB22.4: IN CM* IN; # delete this rule for CSS loose. 185LB22.5: NU CM* IN; 186 187LB23.1: (AL | HL | CM) CM* NU; 188LB23.2: NU CM* (AL | HL); 189 190LB23a.1: PR CM* (ID | EB | EM); 191LB23a.2: (ID | EB | EM) CM* PO; 192 193LB24.2: (PR | PO | POX) CM* (AL | HL); 194LB24.3: (AL | HL | CM) CM* (PR | PO | POX); 195 196# Numbers. Equivalent to Tailoring example 8 from UAx 14. 197# Loose_cj tailoring: do not include $PRX at the beginning or $POX at the end. 198LB25: ((PR | PO | POX)CM*)? ((OP | HY)CM*)? NU (CM*(NU | SY | IS))* (CM*(CL | CP))? (CM*(PR | PRX | PO))?; 199 200LB26.1: JL CM* (JL | JV | H2 | H3); 201LB26.2: (JV | H2) CM* (JV | JT); 202LB26.3: (JT | H3) CM* JT; 203 204LB27.1: (JL | JV | JT | H2 | H3) CM* IN; 205LB27.2: (JL | JV | JT | H2 | H3) CM* PO; 206LB27.3: PR CM* (JL | JV | JT | H2 | H3); 207 208# LB28 Do not break between Alphabetics. 209# Unattached (leading) CM treated as AL. 210LB28: (AL | HL | CM)CM* (AL | HL); 211 212LB29: IS CM* (AL | HL); 213 214# LB30 is adjusted for unattached leading CM being treated as AL. 215LB30.1: (AL | CM | HL | NU) CM* OP; 216LB30.2: CP CM* (AL | HL | NU); 217 218# LB31 keep pairs of RI together. 219LB30a.1: RI CM* RI CM* [BK CR LF NL SP ZW WJ GL CL CP EX IS SY QU BA HY NS]; 220LB30a.2: RI CM* RI CM* ZWJ (ID | Extended_Pict | EmojiNRK); 221LB30a.3: RI CM* RI CM* ÷; 222 223# LB30b Do not break between Emoji Base and Emoji Modifier 224LB30b: EB CM* EM; 225 226# LB31 Break Everywhere Else. 227# Include combining marks 228LB31.1: . CM* ZWJ (ID | Extended_Pict | EmojiNRK); 229LB31.2: . CM* ÷; 230