# file: line.txt
#
-# Reference Line Break rules for intltest rbbi/RBBIMonkeyTest
+# Reference Line Break rules for intltest rbbi/RBBIMonkeyTest.
+# Rules derived from Unicode Standard Annex #14 Revision 40 for Unicode 11.0
#
# Note: Rule syntax and the monkey test itself are still a work in progress.
# They are expected to change with review and the addition of support for rule tailoring.
AI = [:LineBreak = Ambiguous:];
AL = [:LineBreak = Alphabetic:];
BA = [:LineBreak = Break_After:];
+HH = [\u2010]; # \u2010 is HYPHEN, default line break is BA.
BB = [:LineBreak = Break_Before:];
BK = [:LineBreak = Mandatory_Break:];
B2 = [:LineBreak = Break_Both:];
CB = [:LineBreak = Contingent_Break:];
CJ = [:LineBreak = Conditional_Japanese_Starter:];
CL = [:LineBreak = Close_Punctuation:];
-CM = [:LineBreak = Combining_Mark:];
+CMS = [:LineBreak = Combining_Mark:];
CP = [:LineBreak = Close_Parenthesis:];
CR = [:LineBreak = Carriage_Return:];
EB = [[:LineBreak = EB:] \U0001F46A-\U0001F46D\U0001F46F\U0001F91D\U0001F93C];
ZW = [:LineBreak = ZWSpace:];
ZWJ = [:LineBreak = ZWJ:];
-EmojiNRK = [[\p{Emoji}] - [[RI]\u002a\u00230-9©®™〰〽]];
-# Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r13267
-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];
-
# LB1 - Resolve AI, CB, CJ, SA, SG, and XX into other line breaking classes
AL = [AL AI SG XX ];
dictionary = SA;
# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
# list it in the numerous rules that use CM.
-CM = [CM ZWJ];
+CM = [CMS ZWJ];
LB4: BK ÷;
LB5: CR LF;
LB6: . (BK | CR | LF | NL);
LB6.1: [^BK CR LF NL SP ZW] CM* (BK | CR | LF | NL);
+# LB8 break after ZW SP*.
+# Precedes LB7 because both rules will match the sequences like ZW SP,
+# and LB8 must take precedence.
+
+LB8: ZW SP* ÷ [^ZW SP BK CR LF NL];
+
+# Numbers. Equivalent to Tailoring example 8 from UAX 14.
+# Moved up, before LB14, because it can match longer sequences which must take precedence.
+LB25: ((PR | PO)CM*)? ((OP | HY)CM*)? (IS CM*)? NU (CM*(NU | SY | IS))* (CM*(CL | CP))? (CM*(PR | PO))?;
+
# Rules LB14 - LB17.
-# Moved before LB7, because they can match a longer sequence that would also match LB7,
-# for example, the sequence "OP CM SP AL" matches LB14 while the prefix of it,
-# "while only the prefix "OP CM SP" matches LB7.1
+# Moved up, before LB7, because they can match a longer sequence that would also match LB7.
+# For example, the sequence "OP CM SP AL" matches LB14
+# while the prefix of it, "OP CM SP" matches LB7.1
LB14: OP CM* SP* .;
+
+# LB 14a Break before an IS that begins a number and follows a space.
+LB14a: SP ÷ IS CM* NU;
+
+# LB14b × IS
+LB14b.1: [^SP] CM* IS;
+LB14b.2: SP IS;
+
LB15: QU CM* SP* OP;
LB16: (CL | CP)CM* SP* NS;
LB17: B2 CM* SP* B2;
+
+# LB7 Do not break before spaces or zero width space.
+
LB7.1: [^ZW SP] CM* [SP ZW];
LB7.2: [ZW SP] [SP ZW];
-# LB8, ICU differs from UAX-14,
-# ICU: ZW ÷;
-# UAX 14: ZW SP* ÷;
-LB8: ZW ÷;
-
# LB8a
-# ZWJ x (ID | Extended_Pict | EmojiNRK)
-LB8a: ZWJ (ID | Extended_Pict | EmojiNRK);
+# ZWJ x
+# Don't match a CM on the right - let other rules pick up CM sequences, where
+# the ZWJ behaves as just another generic CM.
+LB8a: ZWJ [^CM];
# LB9: X CM -> X
#LB11: × WJ;
# WJ ×
-LB11.1: [^BK CR LF NL SP ZW] CM* WJ;
+LB11.1: [^SP] CM* WJ;
LB11.2: SP WJ;
LB11.3: WJ CM* [^CM];
LB12a: [^SP BA HY] CM* GL;
-# LB 13 ICU Tailoring, matches tailoring exmaple 8 from UAX 14.
-#
-# LB13.1 [^SP] CM* [CL CP EX IS SY] # original UAX 14 rule.
-# LB13.2 SP CM* [CL CP EX IS SY]
-
-LB13.1: [^NU SP] CM* [CL CP IS SY];
-LB13.2: [^SP] CM* EX;
-LB13.2: SP [CL CP EX IS SY];
-
+# LB 13 Do not break before ‘]’ or ‘!’ or ‘/’, even after spaces.
+LB13.1: [^SP] CM* [CL CP EX SY];
+LB13.2: SP [CL CP EX SY];
# LB 14-17 are moved above LB 7.
LB19.1: QU CM* [^CM];
# LB 20 Break before and after CB.
-# Interaction with LB8a: ZWJ x ID is tricky because CM includes ZWJ.
+# Interaction with LB8a: ZWJ x . is tricky because CM includes ZWJ.
# ZWJ acts like a CM to the left, combining with CB.
-# ZWJ acts independently to the right, no break from ID by LB8a.
-LB20: . CM* ÷ CB;
-LB20.1a: CB CM* ZWJ (ID | Extended_Pict | EmojiNRK);
-LB20.1b: CB CM* ÷;
+# ZWJ acts independently to the right, no break after by LB8a.
+LB20.1: . CM* ZWJ CB;
+LB20.2: . CM* ÷ CB;
+
+LB20.3: CB CM* ZWJ [^CM];
+LB20.4: CB CM* ÷;
+
+# LB 20.09 Don't break between Hyphens and Letters when there is a break preceding the hyphen.
+LB20.09: ^(HY | HH) CM* AL;
# Note: Rule 21a must come before 21 to prevent 21.1 from matching HL BA, then
# not picking up the continuing match after the BA from 21a.
LB24.2: (PR | PO) CM* (AL | HL);
LB24.3: (AL | HL | CM) CM* (PR | PO);
-# Numbers. Equivalent to Tailoring example 8 from UAX 14.
-LB25: ((PR | PO)CM*)? ((OP | HY)CM*)? NU (CM*(NU | SY | IS))* (CM*(CL | CP))? (CM*(PR | PO))?;
LB26.1: JL CM* (JL | JV | H2 | H3);
LB26.2: (JV | H2) CM* (JV | JT);
LB30.1: (AL | CM | HL | NU) CM* OP;
LB30.2: CP CM* (AL | HL | NU);
-# LB31 keep pairs of RI together.
-LB30a.1: RI CM* RI CM* [BK CR LF NL SP ZW WJ GL CL CP EX IS SY QU BA HY NS];
-LB30a.2: RI CM* RI CM* ZWJ (ID | Extended_Pict | EmojiNRK);
-LB30a.3: RI CM* RI CM* ÷;
+# LB30a keep pairs of RI together.
+LB30a.1: RI CM* RI ÷ [^BK CR LF NL SP ZW WJ CL CP EX IS SY GL QU BA HY NS CM];
+LB30a.2: RI CM* RI CM* CMS ÷ [^BK CR LF NL SP ZW WJ CL CP EX IS SY GL QU BA HY NS CM];
+LB30a.3: RI CM* RI CM* [BK CR LF NL SP ZW WJ GL CL CP EX IS SY QU BA HY NS ZWJ]?;
# LB30b Do not break between Emoji Base and Emoji Modifier
LB30b: EB CM* EM;
# LB31 Break Everywhere Else.
# Include combining marks
-LB31.1: . CM* ZWJ (ID | Extended_Pict | EmojiNRK);
+LB31.1: . CM* ZWJ [^CM];
LB31.2: . CM* ÷;
projects / apple / icu.git / blobdiff