OLD | NEW |
1 # | 1 # |
2 # Copyright (C) 2016 and later: Unicode, Inc. and others. | 2 # Copyright (C) 2016 and later: Unicode, Inc. and others. |
3 # License & terms of use: http://www.unicode.org/copyright.html | 3 # License & terms of use: http://www.unicode.org/copyright.html |
4 # Copyright (C) 2002-2016, International Business Machines Corporation | 4 # Copyright (C) 2002-2016, International Business Machines Corporation |
5 # and others. All Rights Reserved. | 5 # and others. All Rights Reserved. |
6 # | 6 # |
7 # file: word.txt | 7 # file: word.txt |
8 # | 8 # |
9 # ICU Word Break Rules | 9 # ICU Word Break Rules |
10 # See Unicode Standard Annex #29. | 10 # See Unicode Standard Annex #29. |
(...skipping 21 matching lines...) Expand all Loading... |
32 $Newline = [\p{Word_Break = Newline} ]; | 32 $Newline = [\p{Word_Break = Newline} ]; |
33 $Extend = [\p{Word_Break = Extend}]; | 33 $Extend = [\p{Word_Break = Extend}]; |
34 $ZWJ = [\p{Word_Break = ZWJ}]; | 34 $ZWJ = [\p{Word_Break = ZWJ}]; |
35 $Regional_Indicator = [\p{Word_Break = Regional_Indicator}]; | 35 $Regional_Indicator = [\p{Word_Break = Regional_Indicator}]; |
36 $Format = [\p{Word_Break = Format}]; | 36 $Format = [\p{Word_Break = Format}]; |
37 $Katakana = [\p{Word_Break = Katakana}]; | 37 $Katakana = [\p{Word_Break = Katakana}]; |
38 $Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}]; | 38 $Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}]; |
39 $ALetter = [\p{Word_Break = ALetter}]; | 39 $ALetter = [\p{Word_Break = ALetter}]; |
40 $Single_Quote = [\p{Word_Break = Single_Quote}]; | 40 $Single_Quote = [\p{Word_Break = Single_Quote}]; |
41 $Double_Quote = [\p{Word_Break = Double_Quote}]; | 41 $Double_Quote = [\p{Word_Break = Double_Quote}]; |
42 $MidNumLet = [\p{Word_Break = MidNumLet}]; | 42 # Remove two full stop characters from $MidNumLet and add them to $MidNum |
| 43 # to break a hostname into its components at the cost of breaking |
| 44 # 'e.g.' and 'i.e.' as well. |
| 45 # $MidNumLet is used in rules 6/7 (rules of our interest) and rules 11/12. |
| 46 # Because it's OR'd with $MidNum in rules 11/12, rules 11/12 are not affected |
| 47 # while rules 6/7 are reverted to the old behavior we want. |
| 48 $MidNumLet = [[\p{Word_Break = MidNumLet}] - [\u002E \uFF0E]]; |
43 $MidLetter = [\p{Word_Break = MidLetter}]; | 49 $MidLetter = [\p{Word_Break = MidLetter}]; |
44 $MidNum = [\p{Word_Break = MidNum}]; | 50 $MidNum = [\p{Word_Break = MidNum}[\u002E \uFF0E]]; |
45 $Numeric = [\p{Word_Break = Numeric}]; | 51 $Numeric = [\p{Word_Break = Numeric}[\uff10-\uff19]]; #includes fullwidth d
igits |
46 $ExtendNumLet = [\p{Word_Break = ExtendNumLet}]; | 52 $ExtendNumLet = [\p{Word_Break = ExtendNumLet}]; |
47 $E_Base = [\p{Word_Break = EB}\U0001F3C2\U0001F3C7\U0001F3CC\U0001F4
6A-\U0001F46D\U0001F46F\U0001F574\U0001F6CC]; | 53 $E_Base = [\p{Word_Break = EB}\U0001F3C2\U0001F3C7\U0001F3CC\U0001F4
6A-\U0001F46D\U0001F46F\U0001F574\U0001F6CC]; |
48 $E_Modifier = [\p{Word_Break = EM}]; | 54 $E_Modifier = [\p{Word_Break = EM}]; |
49 | 55 |
50 # Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPic
tographic.txt, r12773 | 56 # Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPic
tographic.txt, r12773 |
51 $Extended_Pict = [\U0001F774-\U0001F77F\u2700-\u2701\u2703-\u2704\u270E\u27
10-\u2711\u2765-\u2767\U0001F030-\U0001F093\U0001F094-\U0001F09F\U0001F10D-\U000
1F10F\U0001F12F\U0001F16C-\U0001F16F\U0001F1AD-\U0001F1E5\U0001F203-\U0001F20F\U
0001F23C-\U0001F23F\U0001F249-\U0001F24F\U0001F252-\U0001F2FF\U0001F7D5-\U0001F7
FF\U0001F000-\U0001F003\U0001F005-\U0001F02B\U0001F02C-\U0001F02F\U0001F322-\U00
01F323\U0001F394-\U0001F395\U0001F398\U0001F39C-\U0001F39D\U0001F3F1-\U0001F3F2\
U0001F3F6\U0001F4FE\U0001F53E-\U0001F548\U0001F54F\U0001F568-\U0001F56E\U0001F57
1-\U0001F572\U0001F57B-\U0001F586\U0001F588-\U0001F589\U0001F58E-\U0001F58F\U000
1F591-\U0001F594\U0001F597-\U0001F5A3\U0001F5A6-\U0001F5A7\U0001F5A9-\U0001F5B0\
U0001F5B3-\U0001F5BB\U0001F5BD-\U0001F5C1\U0001F5C5-\U0001F5D0\U0001F5D4-\U0001F
5DB\U0001F5DF-\U0001F5E0\U0001F5E2\U0001F5E4-\U0001F5E7\U0001F5E9-\U0001F5EE\U00
01F5F0-\U0001F5F2\U0001F5F4-\U0001F5F9\u2605\u2607-\u260D\u260F-\u2610\u2612\u26
16-\u2617\u2619-\u261C\u261E-\u261F\u2621\u2624-\u2625\u2627-\u2629\u262B-\u262D
\u2630-\u2637\u263B-\u2647\u2654-\u265F\u2661-\u2662\u2664\u2667\u2669-\u267A\u2
67C-\u267E\u2680-\u2691\u2695\u2698\u269A\u269D-\u269F\u26A2-\u26A9\u26AC-\u26AF
\u26B2-\u26BC\u26BF-\u26C3\u26C6-\u26C7\u26C9-\u26CD\u26D0\u26D2\u26D5-\u26E8\u2
6EB-\u26EF\u26F6\u26FB-\u26FC\u26FE-\u26FF\u2388\U0001FA00-\U0001FFFD\U0001F0A0-
\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F
0AF-\U0001F0B0\U0001F0C0\U0001F0D0\U0001F0F6-\U0001F0FF\U0001F80C-\U0001F80F\U00
01F848-\U0001F84F\U0001F85A-\U0001F85F\U0001F888-\U0001F88F\U0001F8AE-\U0001F8FF
\U0001F900-\U0001F90F\U0001F91F\U0001F928-\U0001F92F\U0001F931-\U0001F932\U0001F
93F\U0001F94C-\U0001F94F\U0001F95F-\U0001F97F\U0001F992-\U0001F9BF\U0001F9C1-\U0
001F9FF\U0001F6C6-\U0001F6CA\U0001F6E6-\U0001F6E8\U0001F6EA\U0001F6F1-\U0001F6F2
\U0001F6D3-\U0001F6DF\U0001F6ED-\U0001F6EF\U0001F6F7-\U0001F6FF]; | 57 $Extended_Pict = [\U0001F774-\U0001F77F\u2700-\u2701\u2703-\u2704\u270E\u27
10-\u2711\u2765-\u2767\U0001F030-\U0001F093\U0001F094-\U0001F09F\U0001F10D-\U000
1F10F\U0001F12F\U0001F16C-\U0001F16F\U0001F1AD-\U0001F1E5\U0001F203-\U0001F20F\U
0001F23C-\U0001F23F\U0001F249-\U0001F24F\U0001F252-\U0001F2FF\U0001F7D5-\U0001F7
FF\U0001F000-\U0001F003\U0001F005-\U0001F02B\U0001F02C-\U0001F02F\U0001F322-\U00
01F323\U0001F394-\U0001F395\U0001F398\U0001F39C-\U0001F39D\U0001F3F1-\U0001F3F2\
U0001F3F6\U0001F4FE\U0001F53E-\U0001F548\U0001F54F\U0001F568-\U0001F56E\U0001F57
1-\U0001F572\U0001F57B-\U0001F586\U0001F588-\U0001F589\U0001F58E-\U0001F58F\U000
1F591-\U0001F594\U0001F597-\U0001F5A3\U0001F5A6-\U0001F5A7\U0001F5A9-\U0001F5B0\
U0001F5B3-\U0001F5BB\U0001F5BD-\U0001F5C1\U0001F5C5-\U0001F5D0\U0001F5D4-\U0001F
5DB\U0001F5DF-\U0001F5E0\U0001F5E2\U0001F5E4-\U0001F5E7\U0001F5E9-\U0001F5EE\U00
01F5F0-\U0001F5F2\U0001F5F4-\U0001F5F9\u2605\u2607-\u260D\u260F-\u2610\u2612\u26
16-\u2617\u2619-\u261C\u261E-\u261F\u2621\u2624-\u2625\u2627-\u2629\u262B-\u262D
\u2630-\u2637\u263B-\u2647\u2654-\u265F\u2661-\u2662\u2664\u2667\u2669-\u267A\u2
67C-\u267E\u2680-\u2691\u2695\u2698\u269A\u269D-\u269F\u26A2-\u26A9\u26AC-\u26AF
\u26B2-\u26BC\u26BF-\u26C3\u26C6-\u26C7\u26C9-\u26CD\u26D0\u26D2\u26D5-\u26E8\u2
6EB-\u26EF\u26F6\u26FB-\u26FC\u26FE-\u26FF\u2388\U0001FA00-\U0001FFFD\U0001F0A0-
\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F
0AF-\U0001F0B0\U0001F0C0\U0001F0D0\U0001F0F6-\U0001F0FF\U0001F80C-\U0001F80F\U00
01F848-\U0001F84F\U0001F85A-\U0001F85F\U0001F888-\U0001F88F\U0001F8AE-\U0001F8FF
\U0001F900-\U0001F90F\U0001F91F\U0001F928-\U0001F92F\U0001F931-\U0001F932\U0001F
93F\U0001F94C-\U0001F94F\U0001F95F-\U0001F97F\U0001F992-\U0001F9BF\U0001F9C1-\U0
001F9FF\U0001F6C6-\U0001F6CA\U0001F6E6-\U0001F6E8\U0001F6EA\U0001F6F1-\U0001F6F2
\U0001F6D3-\U0001F6DF\U0001F6ED-\U0001F6EF\U0001F6F7-\U0001F6FF]; |
52 $EBG = [\p{Word_Break = EBG}]; | 58 $EBG = [\p{Word_Break = EBG}]; |
53 $EmojiNRK = [[\p{Emoji}] - [\p{Word_Break = Regional_Indicator}\u002a\
u00230-9©®™〰〽]]; | 59 $EmojiNRK = [[\p{Emoji}] - [\p{Word_Break = Regional_Indicator}\u002a\
u00230-9©®™〰〽]]; |
54 | 60 |
55 $Han = [:Han:]; | 61 $Han = [:Han:]; |
(...skipping 263 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
319 $Double_QuoteEx $Hebrew_LetterEx; | 325 $Double_QuoteEx $Hebrew_LetterEx; |
320 | 326 |
321 # rule 11 | 327 # rule 11 |
322 ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx; | 328 ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx; |
323 | 329 |
324 # rule 13c | 330 # rule 13c |
325 $Regional_IndicatorEx*; | 331 $Regional_IndicatorEx*; |
326 | 332 |
327 # For dictionary-based break | 333 # For dictionary-based break |
328 $dictionary $dictionary; | 334 $dictionary $dictionary; |
OLD | NEW |