icu/icu4c/source/test/testdata/break_rules/line.txt - nest-cam/4320010/icu - Git at Google

 #
 # Copyright (c) 2016, International Business Machines Corporation and others. All Rights Reserved.

 # file: line.txt
 #
 # Reference Line Break rules for intltest rbbi/RBBIMonkeyTest
 #
 # 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.


 type = line;
 locale = en;


 AI = [:LineBreak =  Ambiguous:];
 AL = [[:LineBreak =  Alphabetic:]-[\u2764]];
 BA = [:LineBreak =  Break_After:];
 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:];
 CP = [:LineBreak =  Close_Parenthesis:];
 CR = [:LineBreak =  Carriage_Return:];

 EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
 EM = [\U0001F3FB-\U0001F3FF];

 EX = [:LineBreak =  Exclamation:];
 GL = [:LineBreak =  Glue:];
 HL = [:LineBreak =  Hebrew_Letter:];
 HY = [:LineBreak =  Hyphen:];
 H2 = [:LineBreak =  H2:];
 H3 = [:LineBreak =  H3:];
 ID = [[:LineBreak =  Ideographic:][\u2764]];
 IN = [:LineBreak =  Inseperable:];
 IS = [:LineBreak =  Infix_Numeric:];
 JL = [:LineBreak =  JL:];
 JV = [:LineBreak =  JV:];
 JT = [:LineBreak =  JT:];
 LF = [:LineBreak =  Line_Feed:];
 NL = [:LineBreak =  Next_Line:];
 NS = [[:LineBreak =  Nonstarter:] CJ];
 NU = [:LineBreak =  Numeric:];
 OP = [:LineBreak =  Open_Punctuation:];
 PO = [:LineBreak =  Postfix_Numeric:];
 PR = [:LineBreak =  Prefix_Numeric:];
 QU = [:LineBreak =  Quotation:];
 RI = [:LineBreak =  Regional_Indicator:];
 SA = [:LineBreak =  Complex_Context:];
 SG = [:LineBreak =  Surrogate:];
 SP = [:LineBreak =  Space:];
 SY = [:LineBreak =  Break_Symbols:];
 WJ = [:LineBreak =  Word_Joiner:];
 XX = [:LineBreak =  Unknown:];
 ZW = [:LineBreak =  ZWSpace:];
 ZJ = [\u200D];

 # TODO: adjustment to sets needed only until Unicode properties are updated for Emoji.
 ID   = [ID - EB];
 AL   = [AL - EM];

 dictionary = [:LineBreak = Complex_Context:];

 # Redfine AL. LB1.  TODO: refine according to latest UAX.
 AL = [ AL AI SA SG XX ];

 LB4:        BK ÷;
 LB5:        CR LF;
 LB5.1:      CR ÷;
 LB5.2:      LF ÷;
 LB5.3:      NL ÷;

 LB6:        . (BK | CR | LF | NL);
 LB6.1:      [^BK CR LF NL SP ZW] CM* (BK | CR | LF | NL);

 # 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
 LB14:        OP CM* SP* .;
 LB15:        QU CM* SP* OP;
 LB16:        (CL | CP)CM* SP* NS;
 LB17:        B2 CM* SP* B2;

 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, from Emoji proposal L2/16-011R3
 #      ZWJ x ID
 LB8a:       ZJ (ID | EB | EM);


 # LB9:  X CM -> X
 # LB10: Unattached CM -> AL

 #LB11:       × WJ;
 #            WJ ×

 LB11.1:      [^BK CR LF NL SP ZW] CM* WJ;
 LB11.2:      SP WJ;
 LB11.3:      WJ CM* [^CM];

 LB12:        GL 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 14-17 are moved above LB 7.

 LB18:        SP ÷;

 LB19:        . CM* QU;
 LB19.1:      QU CM* [^CM];

 # LB 20   Break before and after CB.
 #         Interaction with LB8a:  ZJ x ID is tricky because CM includes ZJ.
 #                                 ZJ acts like a CM to the left, combining with CB.
 #                                 ZJ acts independently to the right, no break from ID by LB8a.
 LB20:        . CM* ÷ CB;
 LB20.1a:     CB CM* ZJ (ID | EB | EM);
 LB20.1b:      CB CM* ÷;

 # 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.
 LB21a:       HL CM* (HY | BA) CM* [^CM CB];

 LB21.1:      . CM* [BA HY NS];
 LB21.2:      BB CM* [^CM CB];

 LB21b:       SY CM* HL;

 LB22.1:        (AL | HL | CM) CM* IN;   # The CM is from LB10, treat an unattached CM as AL.
 LB22.2:       EX CM* IN;
 LB22.3:       (ID | EB | EM) CM* IN;
 LB22.4:       IN CM* IN;
 LB22.5:       NU CM* IN;

 LB23.1:      (ID | EB | EM) CM* PO;
 LB23.2:      (AL | HL | CM) CM* NU;
 LB23.3:      NU CM* (AL | HL);

 LB24.1:      PR CM* (ID | EB | EM);
 LB24.2:      PR CM* (AL | HL);
 LB24.3:      PO CM* (AL | HL);

 # 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);
 LB26.3:      (JT | H3) CM* JT;

 LB27.1:      (JL | JV | JT | H2 | H3) CM* IN;
 LB27.2:      (JL | JV | JT | H2 | H3) CM* PO;
 LB27.3:      PR CM* (JL | JV | JT | H2 | H3);

 # LB28 Do not break between Alphabetics.
 #      Unattached (leading) CM treated as AL.
 LB28:        (AL | HL | CM)CM* (AL | HL);

 LB29:        IS CM* (AL | HL);

 # LB30  is adjusted for unattached leading CM being treated as AL.
 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* ZJ (ID | EB | EM);
 LB30a.3:     RI CM* RI CM* ÷;

 # LB30b Do not break between Emoji Base and Emoji Modifier
 LB30b:       EB CM* EM;

 # LB31 Break Everywhere Else.
 #      Include combining marks
 LB31.1:        . CM* ZJ (ID | EB | EM);
 LB31.2:        . CM* ÷;
	#
	# Copyright (c) 2016, International Business Machines Corporation and others. All Rights Reserved.

	# file: line.txt
	#
	# Reference Line Break rules for intltest rbbi/RBBIMonkeyTest
	#
	# 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.


	type = line;
	locale = en;


	AI = [:LineBreak = Ambiguous:];
	AL = [[:LineBreak = Alphabetic:]-[\u2764]];
	BA = [:LineBreak = Break_After:];
	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:];
	CP = [:LineBreak = Close_Parenthesis:];
	CR = [:LineBreak = Carriage_Return:];

	EB = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C3-\U0001F3C4\U0001F3CA-\U0001F3CB\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F469\U0001F46E\U0001F470-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F575\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F918];
	EM = [\U0001F3FB-\U0001F3FF];

	EX = [:LineBreak = Exclamation:];
	GL = [:LineBreak = Glue:];
	HL = [:LineBreak = Hebrew_Letter:];
	HY = [:LineBreak = Hyphen:];
	H2 = [:LineBreak = H2:];
	H3 = [:LineBreak = H3:];
	ID = [[:LineBreak = Ideographic:][\u2764]];
	IN = [:LineBreak = Inseperable:];
	IS = [:LineBreak = Infix_Numeric:];
	JL = [:LineBreak = JL:];
	JV = [:LineBreak = JV:];
	JT = [:LineBreak = JT:];
	LF = [:LineBreak = Line_Feed:];
	NL = [:LineBreak = Next_Line:];
	NS = [[:LineBreak = Nonstarter:] CJ];
	NU = [:LineBreak = Numeric:];
	OP = [:LineBreak = Open_Punctuation:];
	PO = [:LineBreak = Postfix_Numeric:];
	PR = [:LineBreak = Prefix_Numeric:];
	QU = [:LineBreak = Quotation:];
	RI = [:LineBreak = Regional_Indicator:];
	SA = [:LineBreak = Complex_Context:];
	SG = [:LineBreak = Surrogate:];
	SP = [:LineBreak = Space:];
	SY = [:LineBreak = Break_Symbols:];
	WJ = [:LineBreak = Word_Joiner:];
	XX = [:LineBreak = Unknown:];
	ZW = [:LineBreak = ZWSpace:];
	ZJ = [\u200D];

	# TODO: adjustment to sets needed only until Unicode properties are updated for Emoji.
	ID = [ID - EB];
	AL = [AL - EM];

	dictionary = [:LineBreak = Complex_Context:];

	# Redfine AL. LB1. TODO: refine according to latest UAX.
	AL = [ AL AI SA SG XX ];

	LB4: BK ÷;
	LB5: CR LF;
	LB5.1: CR ÷;
	LB5.2: LF ÷;
	LB5.3: NL ÷;

	LB6: . (BK \| CR \| LF \| NL);
	LB6.1: [^BK CR LF NL SP ZW] CM* (BK \| CR \| LF \| NL);

	# 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
	LB14: OP CM* SP* .;
	LB15: QU CM* SP* OP;
	LB16: (CL \| CP)CM* SP* NS;
	LB17: B2 CM* SP* B2;

	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, from Emoji proposal L2/16-011R3
	# ZWJ x ID
	LB8a: ZJ (ID \| EB \| EM);


	# LB9: X CM -> X
	# LB10: Unattached CM -> AL

	#LB11: × WJ;
	# WJ ×

	LB11.1: [^BK CR LF NL SP ZW] CM* WJ;
	LB11.2: SP WJ;
	LB11.3: WJ CM* [^CM];

	LB12: GL 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 14-17 are moved above LB 7.

	LB18: SP ÷;

	LB19: . CM* QU;
	LB19.1: QU CM* [^CM];

	# LB 20 Break before and after CB.
	# Interaction with LB8a: ZJ x ID is tricky because CM includes ZJ.
	# ZJ acts like a CM to the left, combining with CB.
	# ZJ acts independently to the right, no break from ID by LB8a.
	LB20: . CM* ÷ CB;
	LB20.1a: CB CM* ZJ (ID \| EB \| EM);
	LB20.1b: CB CM* ÷;

	# 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.
	LB21a: HL CM* (HY \| BA) CM* [^CM CB];

	LB21.1: . CM* [BA HY NS];
	LB21.2: BB CM* [^CM CB];

	LB21b: SY CM* HL;

	LB22.1: (AL \| HL \| CM) CM* IN; # The CM is from LB10, treat an unattached CM as AL.
	LB22.2: EX CM* IN;
	LB22.3: (ID \| EB \| EM) CM* IN;
	LB22.4: IN CM* IN;
	LB22.5: NU CM* IN;

	LB23.1: (ID \| EB \| EM) CM* PO;
	LB23.2: (AL \| HL \| CM) CM* NU;
	LB23.3: NU CM* (AL \| HL);

	LB24.1: PR CM* (ID \| EB \| EM);
	LB24.2: PR CM* (AL \| HL);
	LB24.3: PO CM* (AL \| HL);

	# 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);
	LB26.3: (JT \| H3) CM* JT;

	LB27.1: (JL \| JV \| JT \| H2 \| H3) CM* IN;
	LB27.2: (JL \| JV \| JT \| H2 \| H3) CM* PO;
	LB27.3: PR CM* (JL \| JV \| JT \| H2 \| H3);

	# LB28 Do not break between Alphabetics.
	# Unattached (leading) CM treated as AL.
	LB28: (AL \| HL \| CM)CM* (AL \| HL);

	LB29: IS CM* (AL \| HL);

	# LB30 is adjusted for unattached leading CM being treated as AL.
	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* ZJ (ID \| EB \| EM);
	LB30a.3: RI CM* RI CM* ÷;

	# LB30b Do not break between Emoji Base and Emoji Modifier
	LB30b: EB CM* EM;

	# LB31 Break Everywhere Else.
	# Include combining marks
	LB31.1: . CM* ZJ (ID \| EB \| EM);
	LB31.2: . CM* ÷;