source/test/testdata/break_rules/grapheme.txt

   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}\U0001F3C2\U0001F3C7\U0001F3CC\U0001F46A-\U0001F46D\U0001F46F\U0001F574\U0001F6CC];
  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, r12773
  44 Extended_Pict         = [\U0001F774-\U0001F77F\u2700-\u2701\u2703-\u2704\u270E\u2710-\u2711\u2765-\u2767\U0001F030-\U0001F093\U0001F094-\U0001F09F\U0001F10D-\U0001F10F\U0001F12F\U0001F16C-\U0001F16F\U0001F1AD-\U0001F1E5\U0001F203-\U0001F20F\U0001F23C-\U0001F23F\U0001F249-\U0001F24F\U0001F252-\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\u2605\u2607-\u260D\u260F-\u2610\u2612\u2616-\u2617\u2619-\u261C\u261E-\u261F\u2621\u2624-\u2625\u2627-\u2629\u262B-\u262D\u2630-\u2637\u263B-\u2647\u2654-\u265F\u2661-\u2662\u2664\u2667\u2669-\u267A\u267C-\u267E\u2680-\u2691\u2695\u2698\u269A\u269D-\u269F\u26A2-\u26A9\u26AC-\u26AF\u26B2-\u26BC\u26BF-\u26C3\u26C6-\u26C7\u26C9-\u26CD\u26D0\u26D2\u26D5-\u26E8\u26EB-\u26EF\u26F6\u26FB-\u26FC\u26FE-\u26FF\u2388\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-\U0001F90F\U0001F91F\U0001F928-\U0001F92F\U0001F931-\U0001F932\U0001F93F\U0001F94C-\U0001F94F\U0001F95F-\U0001F97F\U0001F992-\U0001F9BF\U0001F9C1-\U0001F9FF\U0001F6C6-\U0001F6CA\U0001F6E6-\U0001F6E8\U0001F6EA\U0001F6F1-\U0001F6F2\U0001F6D3-\U0001F6DF\U0001F6ED-\U0001F6EF\U0001F6F7-\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) 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:     . ÷;