X-Git-Url: https://git.saurik.com/apple/icu.git/blobdiff_plain/f59164e3d128c7675a4d3934206346a3384e53a5..f3c0d7a59d99c2a94c6b8822291f0e42be3773c9:/icuSources/test/testdata/break_rules/word_POSIX.txt

diff --git a/icuSources/test/testdata/break_rules/word_POSIX.txt b/icuSources/test/testdata/break_rules/word_POSIX.txt
index cb366456..13475071 100644
--- a/icuSources/test/testdata/break_rules/word_POSIX.txt
+++ b/icuSources/test/testdata/break_rules/word_POSIX.txt
@@ -1,4 +1,6 @@
 #
+# Copyright (C) 2016 and later: Unicode, Inc. and others.
+# License & terms of use: http://www.unicode.org/copyright.html
 # Copyright (c) 2016, International Business Machines Corporation and others. All Rights Reserved.
 
 # file: word_POSIX.txt
@@ -11,17 +13,14 @@
 type = word;      # one of grapheme | word | line | sentence
 locale = en_US_POSIX;
 
-E_Base = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C2-\U0001F3C4\U0001F3C7\U0001F3CA-\U0001F3CC\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F574-\U0001F575\U0001F57A\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F6CC\U0001F918-\U0001F91E\U0001F926\U0001F930\U0001F933-\U0001F939\U0001F93C-\U0001F93E];
-E_Modifier = [\U0001F3FB-\U0001F3FF];
-ZWJ = [\u200D];
-GAZ = [\u2640\u2642\u2764\u2695-\u2696\u2708\U0001F308\U0001F33E\U0001F373\U0001F393\U0001F3A4\U0001F3A8\U0001F3EB\U0001F3ED\U0001F466-\U0001F469\U0001F48B\U0001F4BB-\U0001F4BC\U0001F527\U0001F52C\U0001F5E8\U0001F680\U0001F692];
 
 CR                 = [\p{Word_Break = CR}];
 LF                 = [\p{Word_Break = LF}];
 Newline            = [\p{Word_Break = Newline}];
-Extend             = [[[\p{Word_Break = Extend}][:Block=Tags:]]-ZWJ];
+Extend             = [\p{Word_Break = Extend}];
+ZWJ                = [\p{Word_Break = ZWJ}];
 Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
-Format             = [[\p{Word_Break = Format}]-[:Block=Tags:]];
+Format             = [\p{Word_Break = Format}];
 Katakana           = [\p{Word_Break = Katakana}];
 Hebrew_Letter      = [\p{Word_Break = Hebrew_Letter}];
 ALetter            = [\p{Word_Break = ALetter}];
@@ -32,6 +31,12 @@ MidLetter          = [\p{Word_Break = MidLetter} - [\:]];
 MidNum             = [\p{Word_Break = MidNum} [.]];
 Numeric            = [\p{Word_Break = Numeric}];
 ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
+E_Base             = [[\p{Word_Break = EB}] \U0001F46A-\U0001F46D\U0001F46F\U0001F91D\U0001F93C];
+E_Modifier         = [\p{Word_Break = EM}];
+EmojiNRK           = [[\p{Emoji}] - [[Regional_Indicator]\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];
+EBG                = [\p{Word_Break = EBG}];
 
 #define dicitionary, with the effect being that those characters don't appear in test data.
 
@@ -62,7 +67,7 @@ WB3:   CR LF;
 WB3a:  (Newline | CR | LF) ÷;
 WB3b:  . ÷ (Newline | CR | LF);   # actually redundant? No other rule combines.
                                   # (but needed with UAX treat-as scheme.)
-WB3c:   ZWJ GAZ;
+WB3c:   ZWJ (Extended_Pict | EmojiNRK);
 
 WB5:    AHLetter ExtFmt* AHLetter;
 
@@ -82,15 +87,15 @@ WB13:   Katakana ExtFmt* Katakana;
 WB13a:  (AHLetter | Numeric | Katakana | ExtendNumLet) ExtFmt* ExtendNumLet;
 WB13b:  ExtendNumLet ExtFmt* (AHLetter | Numeric | Katakana);
 
-# WB rule 13c, pairs of Regional Indicators stay unbroken.
+# WB rule 15 - 17, pairs of Regional Indicators stay unbroken.
 #              Interacts with WB3c.
-WB13c.1:  Regional_Indicator ExtFmt* Regional_Indicator ExtFmt* ZWJ GAZ;
-WB13c.2:  Regional_Indicator ExtFmt* Regional_Indicator ExtFmt* ÷;
+WB15:  Regional_Indicator ExtFmt* Regional_Indicator ExtFmt* ZWJ (Extended_Pict | EmojiNRK);
+WB17:  Regional_Indicator ExtFmt* Regional_Indicator ExtFmt* ÷;
 
-WB13d:  (E_Base | GAZ) ExtFmt* E_Modifier;
+WB14:  (E_Base | EBG) ExtFmt* E_Modifier;
 
-# Rule WB 14   Any ÷ Any
-#    Interacts with WB3c, do not break between ZWJ and GAZ.
-WB14.1: . ExtFmt* ZWJ GAZ;
-WB14.2: . ExtFmt* ÷;
+# Rule WB 999   Any ÷ Any
+#    Interacts with WB3c, do not break between ZWJ and (Extended_Pict | EBG).
+WB999.1: . ExtFmt* ZWJ (Extended_Pict | EmojiNRK);
+WB999.2: . ExtFmt* ÷;