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.
6 # file: line_normal.txt
8 # Reference Line Break rules for intltest rbbi/RBBIMonkeyTest
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.
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.
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.
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
26 # It sets characters of class CJ to behave like ID.
30 locale = en@lb=normal;
32 AI = [:LineBreak = Ambiguous:];
33 AL = [:LineBreak = Alphabetic:];
34 BA = [:LineBreak = Break_After:];
35 BB = [:LineBreak = Break_Before:];
36 BK = [:LineBreak = Mandatory_Break:];
37 B2 = [:LineBreak = Break_Both:];
38 CB = [:LineBreak = Contingent_Break:];
39 CJ = [:LineBreak = Conditional_Japanese_Starter:];
40 CL = [:LineBreak = Close_Punctuation:];
41 CM = [:LineBreak = Combining_Mark:];
42 CP = [:LineBreak = Close_Parenthesis:];
43 CR = [:LineBreak = Carriage_Return:];
44 EB = [[:LineBreak = EB:]\U0001F3C2\U0001F3C7\U0001F3CC\U0001F46A-\U0001F46D\U0001F46F\U0001F574\U0001F6CC];
45 EM = [:LineBreak = EM:];
46 EX = [:LineBreak = Exclamation:];
47 GL = [:LineBreak = Glue:];
48 HL = [:LineBreak = Hebrew_Letter:];
49 HY = [:LineBreak = Hyphen:];
50 H2 = [:LineBreak = H2:];
51 H3 = [:LineBreak = H3:];
52 ID = [[:LineBreak = Ideographic:] CJ]; # CSS Normal tailoring: CJ resolves to ID
53 IN = [:LineBreak = Inseperable:];
54 IS = [:LineBreak = Infix_Numeric:];
55 JL = [:LineBreak = JL:];
56 JV = [:LineBreak = JV:];
57 JT = [:LineBreak = JT:];
58 LF = [:LineBreak = Line_Feed:];
59 NL = [:LineBreak = Next_Line:];
60 NS = [:LineBreak = Nonstarter:];
61 NU = [:LineBreak = Numeric:];
62 OP = [:LineBreak = Open_Punctuation:];
63 PO = [:LineBreak = Postfix_Numeric:];
64 PR = [:LineBreak = Prefix_Numeric:];
65 QU = [:LineBreak = Quotation:];
66 RI = [:LineBreak = Regional_Indicator:];
67 SA = [:LineBreak = Complex_Context:];
68 SG = [:LineBreak = Surrogate:];
69 SP = [:LineBreak = Space:];
70 SY = [:LineBreak = Break_Symbols:];
71 WJ = [:LineBreak = Word_Joiner:];
72 XX = [:LineBreak = Unknown:];
73 ZW = [:LineBreak = ZWSpace:];
74 ZWJ = [:LineBreak = ZWJ:];
76 EmojiNRK = [[\p{Emoji}] - [[RI]\u002a\u00230-9©®™〰〽]];
77 # Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r12773
78 Extended_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];
80 # LB1 - Resolve AI, CB, CJ, SA, SG, and XX into other line breaking classes
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.
94 LB6: . (BK | CR | LF | NL);
95 LB6.1: [^BK CR LF NL SP ZW] CM* (BK | CR | LF | NL);
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
103 LB16: (CL | CP)CM* SP* NS;
106 LB7.1: [^ZW SP] CM* [SP ZW];
107 LB7.2: [ZW SP] [SP ZW];
109 # LB8, ICU differs from UAX-14,
115 # ZWJ x (ID | Extended_Pict | EmojiNRK)
116 LB8a: ZWJ (ID | Extended_Pict | EmojiNRK);
120 # LB10: Unattached CM -> AL
125 LB11.1: [^BK CR LF NL SP ZW] CM* WJ;
127 LB11.3: WJ CM* [^CM];
131 LB12a: [^SP BA HY] CM* GL;
133 # LB 13 ICU Tailoring, matches tailoring exmaple 8 from UAX 14.
135 # LB13.1 [^SP] CM* [CL CP EX IS SY] # original UAX 14 rule.
136 # LB13.2 SP CM* [CL CP EX IS SY]
138 LB13.1: [^NU SP] CM* [CL CP IS SY];
139 LB13.2: [^SP] CM* EX;
140 LB13.2: SP [CL CP EX IS SY];
143 # LB 14-17 are moved above LB 7.
148 LB19.1: QU CM* [^CM];
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.
155 LB20.1a: CB CM* ZWJ (ID | Extended_Pict | EmojiNRK);
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.
160 LB21a: HL CM* (HY | BA) CM* [^CM CB];
162 LB21.1: . CM* [BA HY NS];
163 LB21.2: BB CM* [^CM CB];
167 LB22.1: (AL | HL | CM) CM* IN; # The CM is from LB10, treat an unattached CM as AL.
169 LB22.3: (ID | EB | EM) CM* IN;
173 LB23.1: (AL | HL | CM) CM* NU;
174 LB23.2: NU CM* (AL | HL);
176 LB23a.1: PR CM* (ID | EB | EM);
177 LB23a.2: (ID | EB | EM) CM* PO;
179 LB24.2: (PR | PO) CM* (AL | HL);
180 LB24.3: (AL | HL | CM) CM* (PR | PO);
182 # Numbers. Equivalent to Tailoring example 8 from UAx 14.
183 LB25: ((PR | PO)CM*)? ((OP | HY)CM*)? NU (CM*(NU | SY | IS))* (CM*(CL | CP))? (CM*(PR | PO))?;
185 LB26.1: JL CM* (JL | JV | H2 | H3);
186 LB26.2: (JV | H2) CM* (JV | JT);
187 LB26.3: (JT | H3) CM* JT;
189 LB27.1: (JL | JV | JT | H2 | H3) CM* IN;
190 LB27.2: (JL | JV | JT | H2 | H3) CM* PO;
191 LB27.3: PR CM* (JL | JV | JT | H2 | H3);
193 # LB28 Do not break between Alphabetics.
194 # Unattached (leading) CM treated as AL.
195 LB28: (AL | HL | CM)CM* (AL | HL);
197 LB29: IS CM* (AL | HL);
199 # LB30 is adjusted for unattached leading CM being treated as AL.
200 LB30.1: (AL | CM | HL | NU) CM* OP;
201 LB30.2: CP CM* (AL | HL | NU);
203 # LB31 keep pairs of RI together.
204 LB30a.1: RI CM* RI CM* [BK CR LF NL SP ZW WJ GL CL CP EX IS SY QU BA HY NS];
205 LB30a.2: RI CM* RI CM* ZWJ (ID | Extended_Pict | EmojiNRK);
206 LB30a.3: RI CM* RI CM* ÷;
208 # LB30b Do not break between Emoji Base and Emoji Modifier
211 # LB31 Break Everywhere Else.
212 # Include combining marks
213 LB31.1: . CM* ZWJ (ID | Extended_Pict | EmojiNRK);