icuSources/test/testdata/break_rules/line_normal_cj.txt

   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_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 #         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 Chinese & Japanese.
  25 #         It sets characters of class CJ to behave like ID.
  26 #         In addition, it allows breaks:
  27 #         * before hyphens 2010 & 2013 (both BA) and 301C, 30A0 (both NS)
  28
  29 type = line;
  30 locale = ja@lb=normal;
  31
  32 AI = [:LineBreak =  Ambiguous:];
  33 AL = [:LineBreak =  Alphabetic:];
  34 BAX = [\u2010 \u2013];
  35 BA = [[:LineBreak =  Break_After:] - BAX];
  36 BB = [:LineBreak =  Break_Before:];
  37 BK = [:LineBreak =  Mandatory_Break:];
  38 B2 = [:LineBreak =  Break_Both:];
  39 CB = [:LineBreak =  Contingent_Break:];
  40 CJ = [:LineBreak =  Conditional_Japanese_Starter:];
  41 CL = [:LineBreak =  Close_Punctuation:];
  42 CM = [:LineBreak =  Combining_Mark:];
  43 CP = [:LineBreak =  Close_Parenthesis:];
  44 CR = [:LineBreak =  Carriage_Return:];
  45 EB = [[:LineBreak =  EB:] \U0001F46A-\U0001F46D\U0001F46F\U0001F91D\U0001F93C];
  46 EM = [:LineBreak =  EM:];
  47 EX = [:LineBreak =  Exclamation:];
  48 GL = [:LineBreak =  Glue:];
  49 HL = [:LineBreak =  Hebrew_Letter:];
  50 HY = [:LineBreak =  Hyphen:];
  51 H2 = [:LineBreak =  H2:];
  52 H3 = [:LineBreak =  H3:];
  53 ID = [[:LineBreak =  Ideographic:] CJ];  # CSS Normal tailoring: CJ resolves to ID
  54 IN = [:LineBreak =  Inseperable:];
  55 IS = [:LineBreak =  Infix_Numeric:];
  56 JL = [:LineBreak =  JL:];
  57 JV = [:LineBreak =  JV:];
  58 JT = [:LineBreak =  JT:];
  59 LF = [:LineBreak =  Line_Feed:];
  60 NL = [:LineBreak =  Next_Line:];
  61 NSX = [\u301C \u30A0];
  62 NS = [[:LineBreak =  Nonstarter:] - NSX];
  63 NU = [:LineBreak =  Numeric:];
  64 OP = [:LineBreak =  Open_Punctuation:];
  65 PO = [:LineBreak =  Postfix_Numeric:];
  66 PR = [:LineBreak =  Prefix_Numeric:];
  67 QU = [:LineBreak =  Quotation:];
  68 RI = [:LineBreak =  Regional_Indicator:];
  69 SA = [:LineBreak =  Complex_Context:];
  70 SG = [:LineBreak =  Surrogate:];
  71 SP = [:LineBreak =  Space:];
  72 SY = [:LineBreak =  Break_Symbols:];
  73 WJ = [:LineBreak =  Word_Joiner:];
  74 XX = [:LineBreak =  Unknown:];
  75 ZW = [:LineBreak =  ZWSpace:];
  76 ZWJ = [:LineBreak =  ZWJ:];
  77
  78 EmojiNRK = [[\p{Emoji}] - [[RI]\u002a\u00230-9©®™〰〽]];
  79 # Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r13267
  80 Extended_Pict = [\U0001F774-\U0001F77F\U00002700-\U00002701\U00002703-\U00002704\U0000270E\U00002710-\U00002711\U00002765-\U00002767\U0001F030-\U0001F093\U0001F094-\U0001F09F\U0001F10D-\U0001F10F\U0001F12F\U0001F16C-\U0001F16F\U0001F1AD-\U0001F1E5\U0001F260-\U0001F265\U0001F203-\U0001F20F\U0001F23C-\U0001F23F\U0001F249-\U0001F24F\U0001F252-\U0001F25F\U0001F266-\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\U00002605\U00002607-\U0000260D\U0000260F-\U00002610\U00002612\U00002616-\U00002617\U00002619-\U0000261C\U0000261E-\U0000261F\U00002621\U00002624-\U00002625\U00002627-\U00002629\U0000262B-\U0000262D\U00002630-\U00002637\U0000263B-\U00002647\U00002654-\U0000265F\U00002661-\U00002662\U00002664\U00002667\U00002669-\U0000267A\U0000267C-\U0000267E\U00002680-\U00002691\U00002695\U00002698\U0000269A\U0000269D-\U0000269F\U000026A2-\U000026A9\U000026AC-\U000026AF\U000026B2-\U000026BC\U000026BF-\U000026C3\U000026C6-\U000026C7\U000026C9-\U000026CD\U000026D0\U000026D2\U000026D5-\U000026E8\U000026EB-\U000026EF\U000026F6\U000026FB-\U000026FC\U000026FE-\U000026FF\U00002388\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-\U0001F90B\U0001F91F\U0001F928-\U0001F92F\U0001F931-\U0001F932\U0001F94C\U0001F95F-\U0001F96B\U0001F992-\U0001F997\U0001F9D0-\U0001F9E6\U0001F90C-\U0001F90F\U0001F93F\U0001F94D-\U0001F94F\U0001F96C-\U0001F97F\U0001F998-\U0001F9BF\U0001F9C1-\U0001F9CF\U0001F9E7-\U0001F9FF\U0001F6C6-\U0001F6CA\U0001F6D3-\U0001F6D4\U0001F6E6-\U0001F6E8\U0001F6EA\U0001F6F1-\U0001F6F2\U0001F6F7-\U0001F6F8\U0001F6D5-\U0001F6DF\U0001F6ED-\U0001F6EF\U0001F6F9-\U0001F6FF];
  81
  82 # LB1 - Resolve AI, CB, CJ, SA, SG, and XX into other line breaking classes
  83 AL = [AL AI SG XX ];
  84 dictionary = SA;
  85
  86 # By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
  87 #         list it in the numerous rules that use CM.
  88 CM = [CM ZWJ];
  89
  90 LB4:        BK ÷;
  91 LB5:        CR LF;
  92 LB5.1:      CR ÷;
  93 LB5.2:      LF ÷;
  94 LB5.3:      NL ÷;
  95
  96 LB6:        . (BK | CR | LF | NL);
  97 LB6.1:      [^BK CR LF NL SP ZW] CM* (BK | CR | LF | NL);
  98
  99 # Rules LB14 - LB17.
 100 # Moved before LB7, because they can match a longer sequence that would also match LB7,
 101 # for example, the sequence "OP CM SP AL" matches LB14 while the prefix of it,
 102 #                           "while only the prefix "OP CM SP" matches LB7.1
 103 LB14:        OP CM* SP* .;
 104 LB15:        QU CM* SP* OP;
 105
 106 # Do not break between closing punctuation and $NS, even with intervening spaces
 107 # But DO allow a break between closing punctuation and $NSX, don't include it here
 108 LB16:        (CL | CP)CM* SP* NS;
 109 LB17:        B2 CM* SP* B2;
 110
 111 LB7.1:      [^ZW SP] CM* [SP ZW];
 112 LB7.2:      [ZW SP] [SP ZW];
 113
 114 # LB8, ICU differs from UAX-14,
 115 #    ICU:    ZW ÷;
 116 #    UAX 14: ZW SP* ÷;
 117 LB8:        ZW ÷;
 118
 119 # LB8a
 120 #      ZWJ x (ID | Extended_Pict | EmojiNRK)
 121 LB8a:       ZWJ (ID | Extended_Pict | EmojiNRK);
 122
 123
 124 # LB9:  X CM -> X
 125 # LB10: Unattached CM -> AL
 126
 127 #LB11:       × WJ;
 128 #            WJ ×
 129
 130 LB11.1:      [^BK CR LF NL SP ZW] CM* WJ;
 131 LB11.2:      SP WJ;
 132 LB11.3:      WJ CM* [^CM];
 133
 134 LB12:        GL CM* [^CM];
 135
 136 LB12a:       [^SP BA BAX HY] CM* GL;
 137
 138 # LB 13 ICU Tailoring, matches tailoring exmaple 8 from UAX 14.
 139 #
 140 #   LB13.1   [^SP] CM* [CL CP EX IS SY]    # original UAX 14 rule.
 141 #   LB13.2   SP    CM* [CL CP EX IS SY]
 142
 143 LB13.1: [^NU SP] CM* [CL CP IS SY];
 144 LB13.2: [^SP] CM* EX;
 145 LB13.2: SP [CL CP EX IS SY];
 146
 147
 148 # LB 14-17 are moved above LB 7.
 149
 150 LB18:        SP ÷;
 151
 152 LB19:        . CM* QU;
 153 LB19.1:      QU CM* [^CM];
 154
 155 # LB 20   Break before and after CB.
 156 #         Interaction with LB8a:  ZWJ x ID is tricky because CM includes ZWJ.
 157 #                                 ZWJ acts like a CM to the left, combining with CB.
 158 #                                 ZWJ acts independently to the right, no break from ID by LB8a.
 159 LB20:        . CM* ÷ CB;
 160 LB20.1a:     CB CM* ZWJ (ID | Extended_Pict | EmojiNRK);
 161 LB20.1b:      CB CM* ÷;
 162
 163 # Note: Rule 21a must come before 21 to prevent 21.1 from matching HL BA, then
 164 #       not picking up the continuing match after the BA from 21a.
 165 # TODO: For CJ tailorings (with BAX) does this rule want to include BAX? If so,
 166 #       should "HL BAX" not break when followed by a CB? Thats what the current
 167 #       rules do, which is why "[^CM CB]?" includes the ?.
 168 LB21a:       HL CM* (HY | BA | BAX) CM* [^CM CB]?;
 169
 170 # DO allow breaks here before $BAXcm and $NSXcm, so don't include them
 171 LB21.1:      . CM* [BA HY NS];
 172 LB21.2:      BB CM* [^CM CB];
 173
 174 LB21b:       SY CM* HL;
 175
 176 LB22.1:        (AL | HL | CM) CM* IN;   # The CM is from LB10, treat an unattached CM as AL.
 177 LB22.2:       EX CM* IN;
 178 LB22.3:       (ID | EB | EM) CM* IN;
 179 LB22.4:       IN CM* IN;
 180 LB22.5:       NU CM* IN;
 181
 182 LB23.1:      (AL | HL | CM) CM* NU;
 183 LB23.2:      NU CM* (AL | HL);
 184
 185 LB23a.1:     PR CM* (ID | EB | EM);
 186 LB23a.2:     (ID | EB | EM) CM* PO;
 187
 188 LB24.2:      (PR | PO) CM* (AL | HL);
 189 LB24.3:      (AL | HL | CM) CM* (PR | PO);
 190
 191 # Numbers. Equivalent to Tailoring example 8 from UAx 14.
 192 LB25:        ((PR | PO)CM*)? ((OP | HY)CM*)? NU (CM*(NU | SY | IS))* (CM*(CL | CP))? (CM*(PR | PO))?;
 193
 194 LB26.1:      JL CM* (JL | JV | H2 | H3);
 195 LB26.2:      (JV | H2) CM* (JV | JT);
 196 LB26.3:      (JT | H3) CM* JT;
 197
 198 LB27.1:      (JL | JV | JT | H2 | H3) CM* IN;
 199 LB27.2:      (JL | JV | JT | H2 | H3) CM* PO;
 200 LB27.3:      PR CM* (JL | JV | JT | H2 | H3);
 201
 202 # LB28 Do not break between Alphabetics.
 203 #      Unattached (leading) CM treated as AL.
 204 LB28:        (AL | HL | CM)CM* (AL | HL);
 205
 206 LB29:        IS CM* (AL | HL);
 207
 208 # LB30  is adjusted for unattached leading CM being treated as AL.
 209 LB30.1:      (AL | CM | HL | NU) CM* OP;
 210 LB30.2:      CP CM* (AL | HL | NU);
 211
 212 # LB31  keep pairs of RI together.
 213 LB30a.1:     RI CM* RI CM* [BK CR LF NL SP ZW WJ GL CL CP EX IS SY QU BA HY NS];
 214 LB30a.2:     RI CM* RI CM* ZWJ (ID | Extended_Pict | EmojiNRK);
 215 LB30a.3:     RI CM* RI CM* ÷;
 216
 217 # LB30b Do not break between Emoji Base and Emoji Modifier
 218 LB30b:       EB CM* EM;
 219
 220 # LB31 Break Everywhere Else.
 221 #      Include combining marks
 222 LB31.1:        . CM* ZWJ (ID | Extended_Pict | EmojiNRK);
 223 LB31.2:        . CM* ÷;