diff options
author | Robert Alessi <alessi@robertalessi.net> | 2017-01-07 21:18:57 +0100 |
---|---|---|
committer | Robert Alessi <alessi@robertalessi.net> | 2017-01-07 21:18:57 +0100 |
commit | 749ab4ccc7ec85f9d109dfea22327a80ef07c621 (patch) | |
tree | 9d81d0d6d7c0f5a6f002939ff68cdf3742e70096 | |
parent | a7a9dc290a55543a31f3fbf67ae987a94b8a9f8a (diff) | |
download | arabluatex-749ab4ccc7ec85f9d109dfea22327a80ef07c621.tar.gz |
bugfix: final hamzah was not parsed correctly in some particular cases
-rw-r--r-- | arabluatex_fullvoc.lua | 168 | ||||
-rw-r--r-- | arabluatex_novoc.lua | 12 | ||||
-rw-r--r-- | arabluatex_voc.lua | 132 |
3 files changed, 160 insertions, 152 deletions
diff --git a/arabluatex_fullvoc.lua b/arabluatex_fullvoc.lua index 31956a6..fd2c021 100644 --- a/arabluatex_fullvoc.lua +++ b/arabluatex_fullvoc.lua | |||
@@ -33,14 +33,14 @@ hamzafv = { | |||
33 | {a="i\"'", b="إ"}, | 33 | {a="i\"'", b="إ"}, |
34 | {a="y\"'", b="ئ"}, | 34 | {a="y\"'", b="ئ"}, |
35 | {a="ؤ([^uaiUAI])", b="ؤْ%1"}, | 35 | {a="ؤ([^uaiUAI])", b="ؤْ%1"}, |
36 | {a="ؤ$", b="ؤْ"}, | 36 | {a="ؤ(%p?)$", b="ؤْ%1"}, |
37 | {a="ؤ(%s)", b="ؤْ%1"}, | 37 | {a="ؤ(%p?%s)", b="ؤْ%1"}, |
38 | {a="أ([^uaiUAI])", b="أْ%1"}, | 38 | {a="أ([^uaiUAI])", b="أْ%1"}, |
39 | {a="أ$", b="أْ"}, | 39 | {a="أ(%p?)$", b="أْ%1"}, |
40 | {a="أ(%s)", b="أْ%1"}, | 40 | {a="أ(%p?%s)", b="أْ%1"}, |
41 | {a="ئ([^uaiUAI])", b="ئْ%1"}, | 41 | {a="ئ([^uaiUAI])", b="ئْ%1"}, |
42 | {a="ئ$", b="ئْ"}, | 42 | {a="ئ(%p?)$", b="ئْ%1"}, |
43 | {a="ئ(%s)", b="ئْ%1"}, | 43 | {a="ئ(%p?%s)", b="ئْ%1"}, |
44 | -- hamza takes tašdīd too | 44 | -- hamza takes tašdīd too |
45 | {a="''([Uu])", b="ؤؤ%1"}, | 45 | {a="''([Uu])", b="ؤؤ%1"}, |
46 | {a="''([Aa])", b="أأ%1"}, | 46 | {a="''([Aa])", b="أأ%1"}, |
@@ -58,10 +58,10 @@ hamzafv = { | |||
58 | {a="([^uiUI])\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"}, | 58 | {a="([^uiUI])\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"}, |
59 | {a="^\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="آ%1"}, | 59 | {a="^\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="آ%1"}, |
60 | {a="(%W)\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"}, | 60 | {a="(%W)\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"}, |
61 | {a="(A)(')(uN?)$", b="aآء%3"}, | 61 | {a="(A)(')(uN?%p?)$", b="aآء%3"}, |
62 | {a="(A)(')(uN?)(%W)", b="aآء%3%4"}, | 62 | {a="(A)(')(uN?)(%p?%s)", b="aآء%3%4"}, |
63 | {a="(A)(')(iN?)$", b="aآء%3"}, | 63 | {a="(A)(')(iN?%p?)$", b="aآء%3"}, |
64 | {a="(A)(')(iN?)(%W)", b="aآء%3%4"}, | 64 | {a="(A)(')(iN?)(%p?%s)", b="aآء%3%4"}, |
65 | {a="(A)(')([iI])", b="aآئ%3"}, -- historic madda | 65 | {a="(A)(')([iI])", b="aآئ%3"}, -- historic madda |
66 | {a="(A)(')(u)", b="aآؤ%3"}, -- historic madda | 66 | {a="(A)(')(u)", b="aآؤ%3"}, -- historic madda |
67 | {a="(A)(')", b="aآء"}, -- historic madda | 67 | {a="(A)(')", b="aآء"}, -- historic madda |
@@ -84,31 +84,33 @@ hamzafv = { | |||
84 | -- ^say'aN and .zim'aN are special orthographies | 84 | -- ^say'aN and .zim'aN are special orthographies |
85 | {a="(%^say)(%')(aN)", b="%1ئ%3"}, | 85 | {a="(%^say)(%')(aN)", b="%1ئ%3"}, |
86 | {a="(.zi?m)(%')(aN)", b="%1ئ%3"}, | 86 | {a="(.zi?m)(%')(aN)", b="%1ئ%3"}, |
87 | {a="([^uai])(')([uai][^%.%^%_]N?)$", b="%1ء%3"}, | 87 | {a="(')(I%p?)$", b="إ%2"}, -- affix pr. 1st person sg. |
88 | {a="([^uai])(')([uai][^%.%^%_]N?)(%W)", b="%1ء%3%4"}, | 88 | {a="(')(I)(%p?%s)", b="إ%2%3"}, -- affix pr. 1st person sg. |
89 | {a="([^uai])(')([uai]N?%p?)$", b="%1ء%3"}, | ||
90 | {a="([^uai])(')([uai]N?)(%p?%s)", b="%1ء%3%4"}, | ||
89 | -- u | 91 | -- u |
90 | {a="(u)(')([uai][^%.%^%_]N?)$", b="%1ؤ%3"}, | 92 | {a="(u)(')([uai]N?%p?)$", b="%1ؤ%3"}, |
91 | {a="(u)(')([uai][^%.%^%_]N?)(%W)", b="%1ؤ%3%4"}, | 93 | {a="(u)(')([uai]N?)(%p?%s)", b="%1ؤ%3%4"}, |
92 | {a="(u)(')$", b="%1ؤْ"}, | 94 | {a="(u)('%p?)$", b="%1ؤْ"}, |
93 | {a="(u)(')(%W)", b="%1ؤْ%3"}, | 95 | {a="(u)(')(%p?%s)", b="%1ؤْ%3"}, |
94 | -- a | 96 | -- a |
95 | {a="(a)(')(A)$", b="%1آ"}, | 97 | {a="(a)(')(A%p?)$", b="%1آ"}, |
96 | {a="(a)(')(A)(%W)", b="%1آ%4"}, | 98 | {a="(a)(')(A)(%p?%s)", b="%1آ%4"}, |
97 | {a="(a)(')([u][^%.%^%_]N?)$", b="%1أ%3"}, | 99 | {a="(a)(')([u]N?%p?)$", b="%1أ%3"}, |
98 | {a="(a)(')([u][^%.%^%_]N?)(%W)", b="%1أ%3%4"}, | 100 | {a="(a)(')([u]N?)(%p?%s)", b="%1أ%3%4"}, |
99 | {a="(a)(')(a)$", b="%1أ%3"}, | 101 | {a="(a)(')(a%p?)$", b="%1أ%3"}, |
100 | {a="(a)(')(a)(%W)", b="%1أ%3%4"}, | 102 | {a="(a)(')(a)(%p?%s)", b="%1أ%3%4"}, |
101 | {a="(a)(')(aN)$", b="%1أً"}, | 103 | {a="(a)(')(aN%p?)$", b="%1أً"}, |
102 | {a="(a)(')(aN)(%W)", b="%1أً%4"}, | 104 | {a="(a)(')(aN)(%p?%s)", b="%1أً%4"}, |
103 | {a="(a)(')([i][^%.%^%_]N?)$", b="%1إ%3"}, | 105 | {a="(a)(')([i]N?%p?)$", b="%1إ%3"}, |
104 | {a="(a)(')([i][^%.%^%_]N?)(%W)", b="%1إ%3%4"}, | 106 | {a="(a)(')([i]N?)(%p?%s)", b="%1إ%3%4"}, |
105 | {a="(a)(')$", b="%1أْ"}, | 107 | {a="(a)('%p?)$", b="%1أْ"}, |
106 | {a="(a)(')(%W)", b="%1أْ%3"}, | 108 | {a="(a)(')(%p?%s)", b="%1أْ%3"}, |
107 | -- i | 109 | -- i |
108 | {a="(i)(')([uai][^%.%^%_]N?)$", b="%1ئ%3"}, | 110 | {a="(i)(')([uai]N?%p?)$", b="%1ئ%3"}, |
109 | {a="(i)(')([uai][^%.%^%_]N?)(%W)", b="%1ئ%3%4"}, | 111 | {a="(i)(')([uai]N?)(%p?%s)", b="%1ئ%3%4"}, |
110 | {a="(i)(')$", b="%1ئْ"}, | 112 | {a="(i)('%p?)$", b="%1ئْ"}, |
111 | {a="(i)(')(%W)", b="%1ئْ%3"}, | 113 | {a="(i)(')(%p?%s)", b="%1ئْ%3"}, |
112 | -- | 114 | -- |
113 | -- middle | 115 | -- middle |
114 | {a="(U)(')", b="%1ء"}, | 116 | {a="(U)(')", b="%1ء"}, |
@@ -141,14 +143,14 @@ hamzafveasy = { -- differences marked below with 'easy' | |||
141 | {a="i\"'", b="إ"}, | 143 | {a="i\"'", b="إ"}, |
142 | {a="y\"'", b="ئ"}, | 144 | {a="y\"'", b="ئ"}, |
143 | {a="ؤ([^uaiUAI])", b="ؤْ%1"}, | 145 | {a="ؤ([^uaiUAI])", b="ؤْ%1"}, |
144 | {a="ؤ$", b="ؤْ"}, | 146 | {a="ؤ(%p?)$", b="ؤْ%1"}, |
145 | {a="ؤ(%s)", b="ؤْ%1"}, | 147 | {a="ؤ(%p?%s)", b="ؤْ%1"}, |
146 | {a="أ([^uaiUAI])", b="أْ%1"}, | 148 | {a="أ([^uaiUAI])", b="أْ%1"}, |
147 | {a="أ$", b="أْ"}, | 149 | {a="أ(%p?)$", b="أْ%1"}, |
148 | {a="أ(%s)", b="أْ%1"}, | 150 | {a="أ(%p?%s)", b="أْ%1"}, |
149 | {a="ئ([^uaiUAI])", b="ئْ%1"}, | 151 | {a="ئ([^uaiUAI])", b="ئْ%1"}, |
150 | {a="ئ$", b="ئْ"}, | 152 | {a="ئ(%p?)$", b="ئْ%1"}, |
151 | {a="ئ(%s)", b="ئْ%1"}, | 153 | {a="ئ(%p?%s)", b="ئْ%1"}, |
152 | -- hamza takes tašdīd too | 154 | -- hamza takes tašdīd too |
153 | {a="''([Uu])", b="ؤؤ%1"}, | 155 | {a="''([Uu])", b="ؤؤ%1"}, |
154 | {a="''([Aa])", b="أأ%1"}, | 156 | {a="''([Aa])", b="أأ%1"}, |
@@ -167,10 +169,10 @@ hamzafveasy = { -- differences marked below with 'easy' | |||
167 | {a="^\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="آ%1"}, | 169 | {a="^\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="آ%1"}, |
168 | {a="(%W)\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"}, | 170 | {a="(%W)\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"}, |
169 | --easy (begin) | 171 | --easy (begin) |
170 | {a="(A)(')(uN?)$", b="aاء%3"}, | 172 | {a="(A)(')(uN?%p?)$", b="aاء%3"}, |
171 | {a="(A)(')(uN?)(%W)", b="aاء%3%4"}, | 173 | {a="(A)(')(uN?)(%p?%s)", b="aاء%3%4"}, |
172 | {a="(A)(')(iN?)$", b="aاء%3"}, | 174 | {a="(A)(')(iN?%p?)$", b="aاء%3"}, |
173 | {a="(A)(')(iN?)(%W)", b="aاء%3%4"}, | 175 | {a="(A)(')(iN?)(%p?%s)", b="aاء%3%4"}, |
174 | {a="(A)(')([iI])", b="aائ%3"}, -- historic madda | 176 | {a="(A)(')([iI])", b="aائ%3"}, -- historic madda |
175 | {a="(A)(')(u)", b="aاؤ%3"}, -- historic madda | 177 | {a="(A)(')(u)", b="aاؤ%3"}, -- historic madda |
176 | {a="(A)(')", b="aاء"}, -- historic madda | 178 | {a="(A)(')", b="aاء"}, -- historic madda |
@@ -194,31 +196,33 @@ hamzafveasy = { -- differences marked below with 'easy' | |||
194 | -- ^say'aN and .zim'aN are special orthographies | 196 | -- ^say'aN and .zim'aN are special orthographies |
195 | {a="(%^say)(%')(aN)", b="%1ئ%3"}, | 197 | {a="(%^say)(%')(aN)", b="%1ئ%3"}, |
196 | {a="(.zi?m)(%')(aN)", b="%1ئ%3"}, | 198 | {a="(.zi?m)(%')(aN)", b="%1ئ%3"}, |
197 | {a="([^uai])(')([uai][^%.%^%_]N?)$", b="%1ء%3"}, | 199 | {a="(')(I%p?)$", b="إ%2"}, -- affix pr. 1st person sg. |
198 | {a="([^uai])(')([uai][^%.%^%_]N?)(%W)", b="%1ء%3%4"}, | 200 | {a="(')(I)(%p?%s)", b="إ%2%3"}, -- affix pr. 1st person sg. |
201 | {a="([^uai])(')([uai]N?%p?)$", b="%1ء%3"}, | ||
202 | {a="([^uai])(')([uai]N?)(%p?%s)", b="%1ء%3%4"}, | ||
199 | -- u | 203 | -- u |
200 | {a="(u)(')([uai][^%.%^%_]N?)$", b="%1ؤ%3"}, | 204 | {a="(u)(')([uai]N?%p?)$", b="%1ؤ%3"}, |
201 | {a="(u)(')([uai][^%.%^%_]N?)(%W)", b="%1ؤ%3%4"}, | 205 | {a="(u)(')([uai]N?)(%p?%s)", b="%1ؤ%3%4"}, |
202 | {a="(u)(')$", b="%1ؤْ"}, | 206 | {a="(u)('%p?)$", b="%1ؤْ"}, |
203 | {a="(u)(')(%W)", b="%1ؤْ%3"}, | 207 | {a="(u)(')(%p?%s)", b="%1ؤْ%3"}, |
204 | -- a | 208 | -- a |
205 | {a="(a)(')(A)$", b="%1آ"}, | 209 | {a="(a)(')(A%p?)$", b="%1آ"}, |
206 | {a="(a)(')(A)(%W)", b="%1آ%4"}, | 210 | {a="(a)(')(A)(%p?%s)", b="%1آ%4"}, |
207 | {a="(a)(')([u][^%.%^%_]N?)$", b="%1أ%3"}, | 211 | {a="(a)(')([u]N?%p?)$", b="%1أ%3"}, |
208 | {a="(a)(')([u][^%.%^%_]N?)(%W)", b="%1أ%3%4"}, | 212 | {a="(a)(')([u]N?)(%p?%s)", b="%1أ%3%4"}, |
209 | {a="(a)(')(a)$", b="%1أ%3"}, | 213 | {a="(a)(')(a%p?)$", b="%1أ%3"}, |
210 | {a="(a)(')(a)(%W)", b="%1أ%3%4"}, | 214 | {a="(a)(')(a)(%p?%s)", b="%1أ%3%4"}, |
211 | {a="(a)(')(aN)$", b="%1أً"}, | 215 | {a="(a)(')(aN%p?)$", b="%1أً"}, |
212 | {a="(a)(')(aN)(%W)", b="%1أً%4"}, | 216 | {a="(a)(')(aN)(%p?%s)", b="%1أً%4"}, |
213 | {a="(a)(')([i][^%.%^%_]N?)$", b="%1إ%3"}, | 217 | {a="(a)(')([i]N?%p?)$", b="%1إ%3"}, |
214 | {a="(a)(')([i][^%.%^%_]N?)(%W)", b="%1إ%3%4"}, | 218 | {a="(a)(')([i]N?)(%p?%s)", b="%1إ%3%4"}, |
215 | {a="(a)(')$", b="%1أْ"}, | 219 | {a="(a)('%p?)$", b="%1أْ"}, |
216 | {a="(a)(')(%W)", b="%1أْ%3"}, | 220 | {a="(a)(')(%p?%s)", b="%1أْ%3"}, |
217 | -- i | 221 | -- i |
218 | {a="(i)(')([uai][^%.%^%_]N?)$", b="%1ئ%3"}, | 222 | {a="(i)(')([uai]N?%p?)$", b="%1ئ%3"}, |
219 | {a="(i)(')([uai][^%.%^%_]N?)(%W)", b="%1ئ%3%4"}, | 223 | {a="(i)(')([uai]N?)(%p?%s)", b="%1ئ%3%4"}, |
220 | {a="(i)(')$", b="%1ئْ"}, | 224 | {a="(i)('%p?)$", b="%1ئْ"}, |
221 | {a="(i)(')(%W)", b="%1ئْ%3"}, | 225 | {a="(i)(')(%p?%s)", b="%1ئْ%3"}, |
222 | -- | 226 | -- |
223 | -- middle | 227 | -- middle |
224 | {a="(U)(')", b="%1ء"}, | 228 | {a="(U)(')", b="%1ء"}, |
@@ -388,12 +392,12 @@ trigraphsfv = { -- trigraphs or more | |||
388 | -- art. with waṣla + lunar consonant (i.e. what remains) | 392 | -- art. with waṣla + lunar consonant (i.e. what remains) |
389 | {a="'l%-", b="ٱلْ"}, | 393 | {a="'l%-", b="ٱلْ"}, |
390 | -- the silent wāw | 394 | -- the silent wāw |
391 | {a="uU$", b="uو"}, | 395 | {a="uU(%p?)$", b="uو%1"}, |
392 | {a="uU(%W)", b="uو%1"}, | 396 | {a="uU(%p?%s)", b="uو%1"}, |
393 | {a="aU$", b="aو"}, | 397 | {a="aU(%p?)$", b="aو%1"}, |
394 | {a="aU(%W)", b="aو%1"}, | 398 | {a="aU(%p?%s)", b="aو%1"}, |
395 | {a="iU$", b="iو"}, | 399 | {a="iU(%p?)$", b="iو%1"}, |
396 | {a="iU(%W)", b="iو%1"}, | 400 | {a="iU(%p?%s)", b="iو%1"}, |
397 | -- words ending in -āT with silent wāw/yāʾ | 401 | -- words ending in -āT with silent wāw/yāʾ |
398 | {a="(_a)UA", b="%1وا"}, | 402 | {a="(_a)UA", b="%1وا"}, |
399 | {a="(_a)U", b="%1و"}, | 403 | {a="(_a)U", b="%1و"}, |
@@ -457,12 +461,12 @@ trigraphsfveasy = { -- trigraphs or more (see 'easy' tag below for the diffs) | |||
457 | -- art. with waṣla + lunar consonant (i.e. what remains) | 461 | -- art. with waṣla + lunar consonant (i.e. what remains) |
458 | {a="'l%-", b="ٱلْ"}, | 462 | {a="'l%-", b="ٱلْ"}, |
459 | -- the silent wāw | 463 | -- the silent wāw |
460 | {a="uU$", b="uو"}, | 464 | {a="uU(%p?)$", b="uو%1"}, |
461 | {a="uU(%W)", b="uو%1"}, | 465 | {a="uU(%p?%s)", b="uو%1"}, |
462 | {a="aU$", b="aو"}, | 466 | {a="aU(%p?)$", b="aو%1"}, |
463 | {a="aU(%W)", b="aو%1"}, | 467 | {a="aU(%p?%s)", b="aو%1"}, |
464 | {a="iU$", b="iو"}, | 468 | {a="iU(%p?)$", b="iو%1"}, |
465 | {a="iU(%W)", b="iو%1"}, | 469 | {a="iU(%p?%s)", b="iو%1"}, |
466 | -- words ending in -āT with silent wāw/yāʾ | 470 | -- words ending in -āT with silent wāw/yāʾ |
467 | {a="(_a)UA", b="%1وا"}, | 471 | {a="(_a)UA", b="%1وا"}, |
468 | {a="(_a)U", b="%1و"}, | 472 | {a="(_a)U", b="%1و"}, |
@@ -538,8 +542,8 @@ digraphsfvidgham = { | |||
538 | -- sukūn begin | 542 | -- sukūn begin |
539 | -- first, take out hyphen if any: | 543 | -- first, take out hyphen if any: |
540 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"}, | 544 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"}, |
541 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])$", b="%1ْ"}, | 545 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy]%p?)$", b="%1ْ"}, |
542 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])([%s])", b="%1ْ%2"}, | 546 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])(%p?%s)", b="%1ْ%2"}, |
543 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])([%_]?[^%_uaiUAIYًٌٍ])", b="%1ْ%2"}, | 547 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])([%_]?[^%_uaiUAIYًٌٍ])", b="%1ْ%2"}, |
544 | -- take out sukūn in cases of assimilation | 548 | -- take out sukūn in cases of assimilation |
545 | {a="(n)(ْ)(%s)(ر)", b="%1%3%4"}, | 549 | {a="(n)(ْ)(%s)(ر)", b="%1%3%4"}, |
@@ -646,8 +650,8 @@ digraphsfv = { | |||
646 | -- sukūn begin | 650 | -- sukūn begin |
647 | -- first, take out hyphen if any: | 651 | -- first, take out hyphen if any: |
648 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"}, | 652 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"}, |
649 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])$", b="%1ْ"}, | 653 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy]%p?)$", b="%1ْ"}, |
650 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])([%s])", b="%1ْ%2"}, | 654 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])(%p?%s)", b="%1ْ%2"}, |
651 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])([%_]?[^%_uaiUAIYًٌٍ])", b="%1ْ%2"}, | 655 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])([%_]?[^%_uaiUAIYًٌٍ])", b="%1ْ%2"}, |
652 | -- take out sukūn in cases of assimilation | 656 | -- take out sukūn in cases of assimilation |
653 | -- {a="(n)(ْ)(%s)(ر)", b="%1%3%4"}, | 657 | -- {a="(n)(ْ)(%s)(ر)", b="%1%3%4"}, |
@@ -757,8 +761,8 @@ digraphsfveasy = { -- see the differences under 'easy' marker below | |||
757 | {a="ْ", b=""}, | 761 | {a="ْ", b=""}, |
758 | -- first, take out hyphen if any: | 762 | -- first, take out hyphen if any: |
759 | -- {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"}, | 763 | -- {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"}, |
760 | -- {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])$", b="%1ْ"}, | 764 | -- {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy]%p?)$", b="%1ْ"}, |
761 | -- {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])([%s])", b="%1ْ%2"}, | 765 | -- {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])(%p?%s)", b="%1ْ%2"}, |
762 | -- {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])([%_]?[^%_uaiUAIًٌٍ])", b="%1ْ%2"}, | 766 | -- {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])([%_]?[^%_uaiUAIًٌٍ])", b="%1ْ%2"}, |
763 | -- take out sukūn in cases of assimilation | 767 | -- take out sukūn in cases of assimilation |
764 | -- {a="(n)(ْ)(%s)(ر)", b="%1%3%4"}, | 768 | -- {a="(n)(ْ)(%s)(ر)", b="%1%3%4"}, |
diff --git a/arabluatex_novoc.lua b/arabluatex_novoc.lua index a79be82..cc5ea66 100644 --- a/arabluatex_novoc.lua +++ b/arabluatex_novoc.lua | |||
@@ -109,12 +109,12 @@ trigraphsnv = { -- trigraphs or more | |||
109 | -- art. with waṣla + lunar consonant (i.e. what remains) | 109 | -- art. with waṣla + lunar consonant (i.e. what remains) |
110 | {a="'l%-", b="ال"}, | 110 | {a="'l%-", b="ال"}, |
111 | -- the silent wāw | 111 | -- the silent wāw |
112 | {a="uU$", b="uو"}, | 112 | {a="uU(%p?)$", b="uو%1"}, |
113 | {a="uU(%W)", b="uو%1"}, | 113 | {a="uU(%p?%s)", b="uو%1"}, |
114 | {a="aU$", b="aو"}, | 114 | {a="aU(%p?)$", b="aو%1"}, |
115 | {a="aU(%W)", b="aو%1"}, | 115 | {a="aU(%p?%s)", b="aو%1"}, |
116 | {a="iU$", b="iو"}, | 116 | {a="iU(%p?)$", b="iو%1"}, |
117 | {a="iU(%W)", b="iو%1"}, | 117 | {a="iU(%p?%s)", b="iو%1"}, |
118 | -- words ending in -āT with silent wāw/yāʾ | 118 | -- words ending in -āT with silent wāw/yāʾ |
119 | {a="(_a)UA", b="%1وا"}, | 119 | {a="(_a)UA", b="%1وا"}, |
120 | {a="(_a)U", b="%1و"}, | 120 | {a="(_a)U", b="%1و"}, |
diff --git a/arabluatex_voc.lua b/arabluatex_voc.lua index 6be30d1..4f8e0aa 100644 --- a/arabluatex_voc.lua +++ b/arabluatex_voc.lua | |||
@@ -194,10 +194,10 @@ hamza = { | |||
194 | {a="([^uiUI])\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"}, | 194 | {a="([^uiUI])\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"}, |
195 | {a="^\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="آ%1"}, | 195 | {a="^\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="آ%1"}, |
196 | {a="(%W)\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"}, | 196 | {a="(%W)\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"}, |
197 | {a="(A)(')(uN?)$", b="aآء%3"}, | 197 | {a="(A)(')(uN?%p?)$", b="aآء%3"}, |
198 | {a="(A)(')(uN?)(%W)", b="aآء%3%4"}, | 198 | {a="(A)(')(uN?)(%p?%s)", b="aآء%3%4"}, |
199 | {a="(A)(')(iN?)$", b="aآء%3"}, | 199 | {a="(A)(')(iN?%p?)$", b="aآء%3"}, |
200 | {a="(A)(')(iN?)(%W)", b="aآء%3%4"}, | 200 | {a="(A)(')(iN?)(%p?%s)", b="aآء%3%4"}, |
201 | {a="(A)(')([iI])", b="aآئ%3"}, -- historic madda | 201 | {a="(A)(')([iI])", b="aآئ%3"}, -- historic madda |
202 | {a="(A)(')(u)", b="aآؤ%3"}, -- historic madda | 202 | {a="(A)(')(u)", b="aآؤ%3"}, -- historic madda |
203 | {a="(A)(')", b="aآء"}, -- historic madda | 203 | {a="(A)(')", b="aآء"}, -- historic madda |
@@ -220,31 +220,33 @@ hamza = { | |||
220 | -- ^say'aN and .zim'aN are special orthographies | 220 | -- ^say'aN and .zim'aN are special orthographies |
221 | {a="(%^say)(%')(aN)", b="%1ئ%3"}, | 221 | {a="(%^say)(%')(aN)", b="%1ئ%3"}, |
222 | {a="(.zi?m)(%')(aN)", b="%1ئ%3"}, | 222 | {a="(.zi?m)(%')(aN)", b="%1ئ%3"}, |
223 | {a="([^uai])(')([uai][^%.%^%_]N?)$", b="%1ء%3"}, | 223 | {a="(')(I%p?)$", b="إ%2"}, -- affix pr. 1st person sg. |
224 | {a="([^uai])(')([uai][^%.%^%_]N?)(%W)", b="%1ء%3%4"}, | 224 | {a="(')(I)(%p?%s)", b="إ%2%3"}, -- affix pr. 1st person sg. |
225 | {a="([^uai])(')([uai]N?%p?)$", b="%1ء%3"}, | ||
226 | {a="([^uai])(')([uai]N?)(%p?%s)", b="%1ء%3%4"}, | ||
225 | -- u | 227 | -- u |
226 | {a="(u)(')([uai][^%.%^%_]N?)$", b="%1ؤ%3"}, | 228 | {a="(u)(')([uai]N?%p?)$", b="%1ؤ%3"}, |
227 | {a="(u)(')([uai][^%.%^%_]N?)(%W)", b="%1ؤ%3%4"}, | 229 | {a="(u)(')([uai]N?)(%p?%s)", b="%1ؤ%3%4"}, |
228 | {a="(u)(')$", b="%1ؤ"}, | 230 | {a="(u)('%p?)$", b="%1ؤ"}, |
229 | {a="(u)(')(%W)", b="%1ؤ%3"}, | 231 | {a="(u)(')(%p?%s)", b="%1ؤ%3"}, |
230 | -- a | 232 | -- a |
231 | {a="(a)(')(A)$", b="%1آ"}, | 233 | {a="(a)(')(A%p?)$", b="%1آ"}, |
232 | {a="(a)(')(A)(%W)", b="%1آ%4"}, | 234 | {a="(a)(')(A)(%p?%s)", b="%1آ%4"}, |
233 | {a="(a)(')([u][^%.%^%_]N?)$", b="%1أ%3"}, | 235 | {a="(a)(')([u]N?%p?)$", b="%1أ%3"}, |
234 | {a="(a)(')([u][^%.%^%_]N?)(%W)", b="%1أ%3%4"}, | 236 | {a="(a)(')([u]N?)(%p?%s)", b="%1أ%3%4"}, |
235 | {a="(a)(')(a)$", b="%1أ%3"}, | 237 | {a="(a)(')(a%p?)$", b="%1أ%3"}, |
236 | {a="(a)(')(a)(%W)", b="%1أ%3%4"}, | 238 | {a="(a)(')(a)(%p?%s)", b="%1أ%3%4"}, |
237 | {a="(a)(')(aN)$", b="%1أً"}, | 239 | {a="(a)(')(aN%p?)$", b="%1أً"}, |
238 | {a="(a)(')(aN)(%W)", b="%1أً%4"}, | 240 | {a="(a)(')(aN)(%p?%s)", b="%1أً%4"}, |
239 | {a="(a)(')([i][^%.%^%_]N?)$", b="%1إ%3"}, | 241 | {a="(a)(')([i]N?%p?)$", b="%1إ%3"}, |
240 | {a="(a)(')([i][^%.%^%_]N?)(%W)", b="%1إ%3%4"}, | 242 | {a="(a)(')([i]N?)(%p?%s)", b="%1إ%3%4"}, |
241 | {a="(a)(')$", b="%1أ"}, | 243 | {a="(a)('%p?)$", b="%1أ"}, |
242 | {a="(a)(')(%W)", b="%1أ%3"}, | 244 | {a="(a)(')(%p?%s)", b="%1أ%3"}, |
243 | -- i | 245 | -- i |
244 | {a="(i)(')([uai][^%.%^%_]N?)$", b="%1ئ%3"}, | 246 | {a="(i)(')([uai]N?%p?)$", b="%1ئ%3"}, |
245 | {a="(i)(')([uai][^%.%^%_]N?)(%W)", b="%1ئ%3%4"}, | 247 | {a="(i)(')([uai]N?)(%p?%s)", b="%1ئ%3%4"}, |
246 | {a="(i)(')$", b="%1ئ"}, | 248 | {a="(i)('%p?)$", b="%1ئ"}, |
247 | {a="(i)(')(%W)", b="%1ئ%3"}, | 249 | {a="(i)(')(%p?%s)", b="%1ئ%3"}, |
248 | -- | 250 | -- |
249 | -- middle | 251 | -- middle |
250 | {a="(U)(')", b="%1ء"}, | 252 | {a="(U)(')", b="%1ء"}, |
@@ -294,10 +296,10 @@ hamzaeasy = { -- differences marked below with 'easy' | |||
294 | {a="^\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="آ%1"}, | 296 | {a="^\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="آ%1"}, |
295 | {a="(%W)\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"}, | 297 | {a="(%W)\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"}, |
296 | --easy (begin) | 298 | --easy (begin) |
297 | {a="(A)(')(uN?)$", b="aاء%3"}, | 299 | {a="(A)(')(uN?%p?)$", b="aاء%3"}, |
298 | {a="(A)(')(uN?)(%W)", b="aاء%3%4"}, | 300 | {a="(A)(')(uN?)(%p?%s)", b="aاء%3%4"}, |
299 | {a="(A)(')(iN?)$", b="aاء%3"}, | 301 | {a="(A)(')(iN?%p?)$", b="aاء%3"}, |
300 | {a="(A)(')(iN?)(%W)", b="aاء%3%4"}, | 302 | {a="(A)(')(iN?)(%p?%s)", b="aاء%3%4"}, |
301 | {a="(A)(')([iI])", b="aائ%3"}, -- historic madda | 303 | {a="(A)(')([iI])", b="aائ%3"}, -- historic madda |
302 | {a="(A)(')(u)", b="aاؤ%3"}, -- historic madda | 304 | {a="(A)(')(u)", b="aاؤ%3"}, -- historic madda |
303 | {a="(A)(')", b="aاء"}, -- historic madda | 305 | {a="(A)(')", b="aاء"}, -- historic madda |
@@ -321,31 +323,33 @@ hamzaeasy = { -- differences marked below with 'easy' | |||
321 | -- ^say'aN and .zim'aN are special orthographies | 323 | -- ^say'aN and .zim'aN are special orthographies |
322 | {a="(%^say)(%')(aN)", b="%1ئ%3"}, | 324 | {a="(%^say)(%')(aN)", b="%1ئ%3"}, |
323 | {a="(.zi?m)(%')(aN)", b="%1ئ%3"}, | 325 | {a="(.zi?m)(%')(aN)", b="%1ئ%3"}, |
324 | {a="([^uai])(')([uai][^%.%^%_]N?)$", b="%1ء%3"}, | 326 | {a="(')(I%p?)$", b="إ%2"}, -- affix pr. 1st person sg. |
325 | {a="([^uai])(')([uai][^%.%^%_]N?)(%W)", b="%1ء%3%4"}, | 327 | {a="(')(I)(%p?%s)", b="إ%2%3"}, -- affix pr. 1st person sg. |
328 | {a="([^uai])(')([uai]N?%p?)$", b="%1ء%3"}, | ||
329 | {a="([^uai])(')([uai]N?)(%p?%s)", b="%1ء%3%4"}, | ||
326 | -- u | 330 | -- u |
327 | {a="(u)(')([uai][^%.%^%_]N?)$", b="%1ؤ%3"}, | 331 | {a="(u)(')([uai]N?%p?)$", b="%1ؤ%3"}, |
328 | {a="(u)(')([uai][^%.%^%_]N?)(%W)", b="%1ؤ%3%4"}, | 332 | {a="(u)(')([uai]N?)(%p?%s)", b="%1ؤ%3%4"}, |
329 | {a="(u)(')$", b="%1ؤ"}, | 333 | {a="(u)('%p?)$", b="%1ؤ"}, |
330 | {a="(u)(')(%W)", b="%1ؤ%3"}, | 334 | {a="(u)(')(%p?%s)", b="%1ؤ%3"}, |
331 | -- a | 335 | -- a |
332 | {a="(a)(')(A)$", b="%1آ"}, | 336 | {a="(a)(')(A%p?)$", b="%1آ"}, |
333 | {a="(a)(')(A)(%W)", b="%1آ%4"}, | 337 | {a="(a)(')(A)(%p?%s)", b="%1آ%4"}, |
334 | {a="(a)(')([u][^%.%^%_]N?)$", b="%1أ%3"}, | 338 | {a="(a)(')([u]N?%p?)$", b="%1أ%3"}, |
335 | {a="(a)(')([u][^%.%^%_]N?)(%W)", b="%1أ%3%4"}, | 339 | {a="(a)(')([u]N?)(%p?%s)", b="%1أ%3%4"}, |
336 | {a="(a)(')(a)$", b="%1أ%3"}, | 340 | {a="(a)(')(a%p?)$", b="%1أ%3"}, |
337 | {a="(a)(')(a)(%W)", b="%1أ%3%4"}, | 341 | {a="(a)(')(a)(%p?%s)", b="%1أ%3%4"}, |
338 | {a="(a)(')(aN)$", b="%1أً"}, | 342 | {a="(a)(')(aN%p?)$", b="%1أً"}, |
339 | {a="(a)(')(aN)(%W)", b="%1أً%4"}, | 343 | {a="(a)(')(aN)(%p?%s)", b="%1أً%4"}, |
340 | {a="(a)(')([i][^%.%^%_]N?)$", b="%1إ%3"}, | 344 | {a="(a)(')([i]N?%p?)$", b="%1إ%3"}, |
341 | {a="(a)(')([i][^%.%^%_]N?)(%W)", b="%1إ%3%4"}, | 345 | {a="(a)(')([i]N?)(%p?%s)", b="%1إ%3%4"}, |
342 | {a="(a)(')$", b="%1أ"}, | 346 | {a="(a)('%p?)$", b="%1أ"}, |
343 | {a="(a)(')(%W)", b="%1أ%3"}, | 347 | {a="(a)(')(%p?%s)", b="%1أ%3"}, |
344 | -- i | 348 | -- i |
345 | {a="(i)(')([uai][^%.%^%_]N?)$", b="%1ئ%3"}, | 349 | {a="(i)(')([uai]N?%p?)$", b="%1ئ%3"}, |
346 | {a="(i)(')([uai][^%.%^%_]N?)(%W)", b="%1ئ%3%4"}, | 350 | {a="(i)(')([uai]N?)(%p?%s)", b="%1ئ%3%4"}, |
347 | {a="(i)(')$", b="%1ئ"}, | 351 | {a="(i)('%p?)$", b="%1ئ"}, |
348 | {a="(i)(')(%W)", b="%1ئ%3"}, | 352 | {a="(i)(')(%p?%s)", b="%1ئ%3"}, |
349 | -- | 353 | -- |
350 | -- middle | 354 | -- middle |
351 | {a="(U)(')", b="%1ء"}, | 355 | {a="(U)(')", b="%1ء"}, |
@@ -509,12 +513,12 @@ trigraphs = { -- trigraphs or more | |||
509 | -- art. with waṣla + lunar consonant (i.e. what remains) | 513 | -- art. with waṣla + lunar consonant (i.e. what remains) |
510 | {a="'l%-", b="ال"}, | 514 | {a="'l%-", b="ال"}, |
511 | -- the silent wāw | 515 | -- the silent wāw |
512 | {a="uU$", b="uو"}, | 516 | {a="uU(%p?)$", b="uو%1"}, |
513 | {a="uU(%W)", b="uو%1"}, | 517 | {a="uU(%p?%s)", b="uو%1"}, |
514 | {a="aU$", b="aو"}, | 518 | {a="aU(%p?)$", b="aو%1"}, |
515 | {a="aU(%W)", b="aو%1"}, | 519 | {a="aU(%p?%s)", b="aو%1"}, |
516 | {a="iU$", b="iو"}, | 520 | {a="iU(%p?)$", b="iو%1"}, |
517 | {a="iU(%W)", b="iو%1"}, | 521 | {a="iU(%p?%s)", b="iو%1"}, |
518 | -- words ending in -āT with silent wāw/yāʾ | 522 | -- words ending in -āT with silent wāw/yāʾ |
519 | {a="(_a)UA", b="%1وا"}, | 523 | {a="(_a)UA", b="%1وا"}, |
520 | {a="(_a)U", b="%1و"}, | 524 | {a="(_a)U", b="%1و"}, |
@@ -587,12 +591,12 @@ trigraphseasy = { -- differences marked below with 'easy' | |||
587 | -- art. with waṣla + lunar consonant (i.e. what remains) | 591 | -- art. with waṣla + lunar consonant (i.e. what remains) |
588 | {a="'l%-", b="ال"}, | 592 | {a="'l%-", b="ال"}, |
589 | -- the silent wāw | 593 | -- the silent wāw |
590 | {a="uU$", b="uو"}, | 594 | {a="uU(%p?)$", b="uو%1"}, |
591 | {a="uU(%W)", b="uو%1"}, | 595 | {a="uU(%p?%s)", b="uو%1"}, |
592 | {a="aU$", b="aو"}, | 596 | {a="aU(%p?)$", b="aو%1"}, |
593 | {a="aU(%W)", b="aو%1"}, | 597 | {a="aU(%p?%s)", b="aو%1"}, |
594 | {a="iU$", b="iو"}, | 598 | {a="iU(%p?)$", b="iو%1"}, |
595 | {a="iU(%W)", b="iو%1"}, | 599 | {a="iU(%p?%s)", b="iو%1"}, |
596 | -- words ending in -āT with silent wāw/yāʾ | 600 | -- words ending in -āT with silent wāw/yāʾ |
597 | {a="(_a)UA", b="%1وا"}, | 601 | {a="(_a)UA", b="%1وا"}, |
598 | {a="(_a)U", b="%1و"}, | 602 | {a="(_a)U", b="%1و"}, |