ICU-64232.0.1.tar.gz

[apple/icu.git] / icuSources / test / testdata / break_rules / line.txt

diff --git a/icuSources/test/testdata/break_rules/line.txt b/icuSources/test/testdata/break_rules/line.txt
index bb29a2d11448951e866c7f513e5db9a98883da69..b33994b2a7a2762a442f35eeed997c0482e5a8ae 100644 (file)
--- a/icuSources/test/testdata/break_rules/line.txt
+++ b/icuSources/test/testdata/break_rules/line.txt
@@ -19,13 +19,14 @@ locale = en;
 AI = [:LineBreak =  Ambiguous:];
 AL = [:LineBreak =  Alphabetic:];
 BA = [:LineBreak =  Break_After:];
 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:];
 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];
 CP = [:LineBreak =  Close_Parenthesis:];
 CR = [:LineBreak =  Carriage_Return:];
 EB = [[:LineBreak =  EB:] \U0001F46A-\U0001F46D\U0001F46F\U0001F91D\U0001F93C];


@@ -66,7 +67,7 @@ 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.
 
 # 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;
 
 LB4:        BK ÷;
 LB5:        CR LF;


@@ -77,23 +78,39 @@ LB5.3:      NL ÷;
 LB6:        . (BK | CR | LF | NL);
 LB6.1:      [^BK CR LF NL SP ZW] CM* (BK | CR | LF | NL);
 
 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.
 # 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* .;
 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;
 
 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];
 
 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
 #      Don't match a CM on the right - let other rules pick up CM sequences, where
 # LB8a
 #      ZWJ x
 #      Don't match a CM on the right - let other rules pick up CM sequences, where


@@ -115,15 +132,9 @@ LB12:        GL CM* [^CM];
 
 LB12a:       [^SP BA HY] CM* GL;
 
 
 LB12a:       [^SP BA HY] CM* GL;
 

-# LB 13 ICU Tailoring, matches tailoring example 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.
 
 
 # LB 14-17 are moved above LB 7.
 


@@ -142,6 +153,9 @@ LB20.2:      . CM* ÷ CB;
 LB20.3:      CB CM* ZWJ [^CM];
 LB20.4:      CB CM* ÷;
 
 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.
 LB21a:       HL CM* (HY | BA) CM* [^CM CB];
 # 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];


@@ -166,8 +180,6 @@ LB23a.2:     (ID | EB | EM) CM* PO;
 LB24.2:      (PR | PO) CM* (AL | HL);
 LB24.3:      (AL | HL | CM) CM* (PR | PO);
 
 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);
 
 LB26.1:      JL CM* (JL | JV | H2 | H3);
 LB26.2:      (JV | H2) CM* (JV | JT);


@@ -188,8 +200,8 @@ LB30.1:      (AL | CM | HL | NU) CM* OP;
 LB30.2:      CP CM* (AL | HL | NU);
 
 # LB30a  keep pairs of RI together.
 LB30.2:      CP CM* (AL | HL | NU);
 
 # 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* [CM-ZWJ] ÷ [^BK CR LF NL SP ZW WJ CL CP EX IS SY GL QU BA HY NS CM];
+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
 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