| 1 | // -*- Coding: utf-8; -*- |
| 2 | //-------------------------------------------------------------------- |
| 3 | // Copyright (c) 1999-2002, International Business Machines |
| 4 | // Corporation and others. All Rights Reserved. |
| 5 | //-------------------------------------------------------------------- |
| 6 | // THIS IS A MACHINE-GENERATED FILE |
| 7 | // Tool: dumpicurules.bat |
| 8 | // Source: ../../../impl/data/Transliterator_Hebrew_Latin.txt |
| 9 | // Date: Sat Jul 27 10:31:07 2002 |
| 10 | //-------------------------------------------------------------------- |
| 11 | |
| 12 | // Hebrew_Latin |
| 13 | |
| 14 | t_Hebr_Latn { |
| 15 | Rule { |
| 16 | //-------------------------------------------------------------------- |
| 17 | //-------------------------------------------------------------------- |
| 18 | //-------------------------------------------------------------------- |
| 19 | |
| 20 | // Transliteration table for Hebrew |
| 21 | // Based on the UNGEGN table at: |
| 22 | // http://www.eki.ee/wgrs/rom1_he.pdf |
| 23 | // |
| 24 | // Exceptions: |
| 25 | // - Accents are added to disambiguate letters |
| 26 | // - Combinations of dagesh, shin/sin dot that produce different |
| 27 | // letters are not yet encoded. |
| 28 | // |
| 29 | // To test, open: |
| 30 | // http://oss.software.ibm.com/cgi-bin/icu/tr |
| 31 | // Click Edit, paste in this file, Save As hebrew-latin/XXX |
| 32 | // (where XXX is a username) |
| 33 | // Now go back to the main window, and try it out. |
| 34 | // Use hebrew-latin/XXX for Output 1, and (Inverse) for Output 2 |
| 35 | // Paste in hebrew text in Input, and hit Transliterate. |
| 36 | // |
| 37 | // For more information, see" |
| 38 | // http://oss.software.ibm.com/icu/userguide/Transliteration.html |
| 39 | |
| 40 | ":: [[:Hebrew:] [\u05B0-\u05B9\u05BB-\u05BC\u05C1-\u05C2\u2135-\u2138̄\u05BF]] ;" |
| 41 | ":: nfkd (nfc) ;" |
| 42 | "$letterAfter = [:M:]* [:L:] ;" |
| 43 | |
| 44 | // move longer items here to avoid masking |
| 45 | |
| 46 | "ח <> ẖ ;" |
| 47 | "צ <> ẕ } $letterAfter;" |
| 48 | "ץ <> ẕ ;" |
| 49 | "ש <> ş ;" |
| 50 | "ת <> ţ ;" |
| 51 | |
| 52 | "א <> ʼ ;" |
| 53 | "ב <> b ;" |
| 54 | "ג <> g ;" |
| 55 | "ד <> d ;" |
| 56 | "ה <> h ;" |
| 57 | "ו <> w ;" |
| 58 | "ז <> z ;" |
| 59 | "ט <> t ;" |
| 60 | "י <> y ;" |
| 61 | "כ <> k } $letterAfter;" |
| 62 | "ך <> k ;" |
| 63 | "ל <> l ;" |
| 64 | "מ <> m } $letterAfter;" |
| 65 | "ם <> m ;" |
| 66 | "נ <> n } $letterAfter;" |
| 67 | "ן <> n ;" |
| 68 | "ס <> s ;" |
| 69 | "ע <> ʻ ;" |
| 70 | "פ <> p } $letterAfter;" |
| 71 | "ף <> p ;" |
| 72 | "ק <> q ;" |
| 73 | "ר <> r ;" |
| 74 | |
| 75 | "װ > | וו;" // HEBREW LIGATURE YIDDISH DOUBLE VAV |
| 76 | "ױ > | וי;" // HEBREW LIGATURE YIDDISH VAV YOD |
| 77 | "ײ > | יי ;" // HEBREW LIGATURE YIDDISH DOUBLE YOD |
| 78 | |
| 79 | |
| 80 | "ּ <> ̇ ;" // dagesh just goes to overdot for now |
| 81 | "ׁ <> ̌ ;" // shin dot -> sh |
| 82 | "ׂ <> ̂ ;" // sin dot -> s |
| 83 | |
| 84 | // points |
| 85 | "ֲ <> à ;" |
| 86 | "ָ <> á ;" |
| 87 | "ֱ <> è ;" |
| 88 | "ֵ <> é ;" |
| 89 | "ְ <> ê ;" |
| 90 | "ִ <> i ;" |
| 91 | "ֹ <> ò ;" |
| 92 | "ֻ <> u ;" |
| 93 | |
| 94 | "ַ <> a ;" |
| 95 | "ֶ <> e ;" |
| 96 | "ֳ <> o ;" |
| 97 | |
| 98 | "\u05BF <> ̄ ;" |
| 99 | |
| 100 | // fallbacks |
| 101 | "ק < c ;" |
| 102 | "פ < f } $letterAfter;" |
| 103 | "ף < f ;" |
| 104 | "ז < j ;" |
| 105 | "ו < v ;" |
| 106 | "כס < x ;" |
| 107 | |
| 108 | ":: (lower);" |
| 109 | ":: nfc (nfd) ;" |
| 110 | ":: ([[:Latin:] [\u02BB-\u02BC\u0300-\u0302\u0307\u030C\u0327\u0331\u0340-\u0341 ̄ ]]);" |
| 111 | } |
| 112 | } |