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: grapheme.txt 7 # 8 # Reference Grapheme Break rules for intltest rbbi/RBBIMonkeyTest 9 # 10 # 11 # Note: Rule syntax and the monkey test itself are still a work in progress. 12 # They are expected to change with review and the addition of support for rule tailoring. 13 14 type = grapheme; # one of grapheme | word | line | sentence 15 locale = en; 16 17 CR = [\p{Grapheme_Cluster_Break = CR}]; 18 LF = [\p{Grapheme_Cluster_Break = LF}]; 19 20 Control = [[\p{Grapheme_Cluster_Break = Control}]]; 21 Extend = [[\p{Grapheme_Cluster_Break = Extend}]]; 22 ZWJ = [\p{Grapheme_Cluster_Break = ZWJ}]; 23 Regional_Indicator = [\p{Grapheme_Cluster_Break = Regional_Indicator}]; 24 Prepend = [\p{Grapheme_Cluster_Break = Prepend}]; 25 SpacingMark = [\p{Grapheme_Cluster_Break = SpacingMark}]; 26 27 # 28 # Korean Syllable Definitions 29 # 30 L = [\p{Grapheme_Cluster_Break = L}]; 31 V = [\p{Grapheme_Cluster_Break = V}]; 32 T = [\p{Grapheme_Cluster_Break = T}]; 33 LV = [\p{Grapheme_Cluster_Break = LV}]; 34 LVT = [\p{Grapheme_Cluster_Break = LVT}]; 35 36 # Emoji defintions 37 38 EmojiNRK = [[\p{Emoji}] - [Regional_Indicator\u002a\u00230-9]]; 39 E_Base = [\p{Grapheme_Cluster_Break = EB}]; 40 E_Modifier = [\p{Grapheme_Cluster_Break = EM}]; 41 E_Base_GAZ = [\p{Grapheme_Cluster_Break = EBG}]; 42 43 # Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r13267 44 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]; 45 46 47 GB3: CR LF; 48 GB4: (Control | CR | LF) ; 49 GB5: . (Control | CR | LF); 50 51 GB6: L (L | V | LV | LVT); 52 GB7: (LV | V) (V | T); 53 GB8: (LVT | T) T; 54 55 GB10: (E_Base | E_Base_GAZ) Extend* E_Modifier; 56 GB11: (Extended_Pict | EmojiNRK) Extend* ZWJ (Extended_Pict | EmojiNRK); 57 GB9: . (Extend | ZWJ); 58 59 GB9a: . SpacingMark; 60 GB9b: Prepend .; 61 62 # Regional Indicators, split into pairs. 63 # Note that a pair of RIs that is not followed by a third RI will fall into 64 # the normal rules for Extend, etc. 65 # 66 GB12: Regional_Indicator Regional_Indicator Regional_Indicator; 67 GB13: Regional_Indicator Regional_Indicator; 68 69 GB999: . ; 70
