Skip to content

Commit 0198f38

Browse files
committed
Add Sindhi.
1 parent acd1487 commit 0198f38

2 files changed

Lines changed: 389 additions & 0 deletions

File tree

Lines changed: 386 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,386 @@
1+
---
2+
general:
3+
name: Sindhi (Arabic)
4+
description: Version 1.0 of conversion rules for the Sindhi language in the Perso-Arabic script
5+
# Updated 2025-11-26, by Randall K. Barry to reverse truncation mark %
6+
# xxxx% (end of string), %xxxx (beginning of string)
7+
8+
parents:
9+
- _ignore_base
10+
11+
case_sensitive: false
12+
13+
roman_to_script:
14+
map:
15+
# Punctuation marks:
16+
# "%": "\u066A"; cannot transliterate the truncation character
17+
"*": "\u066D"
18+
",": "\u060C"
19+
";": "\u061B"
20+
"?": "\u061F"
21+
22+
# Exceptions for specific words
23+
# Allah
24+
"alla\u0304h": "\u0627\u0644\u0644\u0647"
25+
26+
# Qur'an
27+
"qur\u02BCa\u0304n": "\u0642\u0631\u0622\u0646"
28+
29+
# aur (with spaces)
30+
" aur ": " \u0627\u0648\u0631 "
31+
32+
####
33+
# Abdurrahman
34+
"\u02BBabdurrah\u0323ma\u0301n": "\u0639\u0628\u062F\u0627\u0644\u0631\u062D\u0645\u0670\u0646"
35+
"\u02BBabdurrah\u0323ma\u0304n": "\u0639\u0628\u062F\u0627\u0644\u0631\u062D\u0645\u0670\u0646"
36+
37+
# Abd names
38+
"\u02BBabdul\u02BB": "\u0639\u0628\u062F\u0627\u0644\u0639"
39+
"\u02BBabdula": "\u0639\u0628\u062F\u0627\u0644"
40+
"\u02BBabdulb": "\u0639\u0628\u062F\u0627\u0644\u0628"
41+
"\u02BBabdulf": "\u0639\u0628\u062F\u0627\u0644\u0641"
42+
"\u02BBabdulg\u0332h\u0332": "\u0639\u0628\u062F\u0627\u0644\u063A"
43+
"\u02BBabdulh\u0323": "\u0639\u0628\u062F\u0627\u0644\u062D"
44+
"\u02BBabdulh": "\u0639\u0628\u062F\u0627\u0644\u0647 "
45+
"\u02BBabdulj": "\u0639\u0628\u062F\u0627\u0644\u062C"
46+
"\u02BBabdulk\u0332h\u0332": "\u0639\u0628\u062F\u0627\u0644\u062E"
47+
"\u02BBabdulk": "\u0639\u0628\u062F\u0627\u0644\u0643 "
48+
"\u02BBabdulm": "\u0639\u0628\u062F\u0627\u0644\u0645"
49+
"\u02BBabdulq": "\u0639\u0628\u062F\u0627\u0644\u0642"
50+
"\u02BBabdulv": "\u0639\u0628\u062F\u0627\u0644\u0648"
51+
"\u02BBabdunn": "\u0639\u0628\u062F\u0627\u0644\u0646"
52+
"\u02BBabdurr": "\u0639\u0628\u062F\u0627\u0644\u0631"
53+
"\u02BBabdus\u0323s\u0323": "\u0639\u0628\u062F\u0627\u0644\u0325"
54+
"\u02BBabduss": "\u0639\u0628\u062F\u0627\u0644\u0633"
55+
"\u02BBabdushsh": "\u0639\u0628\u062F\u0627\u0644\u0634"
56+
"\u02BBabdutt": "\u0639\u0628\u062F\u0627\u0644\u062A"
57+
"\u02BBabduz\u0323z\u0323": "\u0639\u0628\u062F\u0627\u0644\u0636"
58+
"\u02BBabduz\u0324z\u0324": "\u0639\u0628\u062F\u0627\u0644\u0638"
59+
60+
# Abu names
61+
"%abu\u0304": "\u0627\u0628\u0648\u0020"
62+
"abu\u0304": "\u0627\u0628\u0648\u200C\u0627\u0644"
63+
64+
####
65+
66+
#lillah
67+
"lilla\u0304h": "\u0644\u0644\u0647"
68+
69+
#billah
70+
"billa\u0304h": "\u0628\u0644\u0644\u0647"
71+
72+
# Rahman
73+
"rah\u0323ma\u0304n": "\u0631\u062D\u0645\u0646"
74+
75+
# Nuzhat
76+
"nuzhat": "\u0646\u0632\u0647\u062A"
77+
78+
# Uddin names
79+
"i\u0304uddi\u0304n%": "\u0649\u200C\u0627\u0644\u062F\u0651\u064A\u0646"
80+
"uddi\u0304n%": "\u200C\u0627\u0644\u062F\u0651\u064A\u0646"
81+
82+
# ta'lif
83+
84+
# Ibn when it appears in the middle of a name sequence
85+
"ibn": "\u0628\u0646"
86+
87+
# Numbers (\u06F0-06F9 for Eastern Arabic digits)
88+
"0": "\u06F0"
89+
"1": "\u06F1"
90+
"2": "\u06F2"
91+
"3": "\u06F3"
92+
"4": "\u06F4"
93+
"5": "\u06F5"
94+
"6": "\u06F6"
95+
"7": "\u06F7"
96+
"8": "\u06F8"
97+
"9": "\u06F9"
98+
99+
"bhbh": "\u0680\u0651"
100+
"bh": "\u0680"
101+
"b\u0324b\u0324": "\u067B\u0651"
102+
"b\u0324": "\u067B"
103+
"bb": "\u0628\u0651"
104+
"b": "\u0628"
105+
"chch": "\u0687\u0651"
106+
"ch": "\u0687"
107+
"cc": "\u0686\u0651"
108+
"c": "\u0686"
109+
"d\u0323hd\u0323h": "\u068D\u0651"
110+
"d\u0323h": "\u068D"
111+
"dhdh": "\u068C\u0651"
112+
"dh": "\u068C"
113+
"d\u0324d\u0324": "\u068F\u0651"
114+
"d\u0324": "\u068F"
115+
"dd": "\u062F\u0651"
116+
"d": "\u062F"
117+
"ff": "\u0641\u0651"
118+
"f": "\u0641"
119+
"g\u0332h\u0332g\u0332h\u0332": "\u063A\u0651"
120+
"g\u0332h\u0332": "\u063A"
121+
"ghgh": "\u06AF\u0647\u0651"
122+
"gha%": "\u06AF\u0647\u06C1"
123+
"ghe%": "\u06AF\u0647\u06C1"
124+
"ghi%": "\u06AF\u0647\u06C1"
125+
"gho%": "\u06AF\u0647\u06C1"
126+
"ghi%": "\u06AF\u0647\u06C1"
127+
"gh%": "\u06AF\u0647\u06C1"
128+
"gh": "\u06AF\u0647"
129+
"g\u0308g\u0308": "\u0683\u0651"
130+
"g\u0308": "\u0683"
131+
"gg": "\u06AF\u0651"
132+
"g": "\u06AF"
133+
"j\u0308j\u0308": "\u0684\u0651"
134+
"j\u0308": "\u0684"
135+
"jhjh": "\u062C\u0647\u0651"
136+
"jha%": "\u062C\u0647\u06C1"
137+
"jhe%": "\u062C\u0647\u06C1"
138+
"jhi%": "\u062C\u0647\u06C1"
139+
"jho%": "\u062C\u0647\u06C1"
140+
"jhu%": "\u062C\u0647\u06C1"
141+
"jh%": "\u062C\u0647\u06C1"
142+
"jh": "\u062C\u0647"
143+
"jj": "\u062C\u0651"
144+
"j": "\u062C"
145+
"k\u0332h\u0332k\u0332h\u0332": "\u062E\u0651"
146+
"k\u0332h\u0332": "\u062E"
147+
"khkh": "\u06A9\u0651"
148+
"kh": "\u06A9"
149+
"kk": "\u06AA\u0651"
150+
"k": "\u06AA"
151+
"ll": "\u0644\u0651"
152+
"l": "\u0644"
153+
"mm": "\u0645\u0651"
154+
"m": "\u0645"
155+
"n\u0303n\u0303": "\u0683\u0651"
156+
"n\u0307n\u0307": "\u06B1\u0651"
157+
"n\u0323n\u0323": "\u06BB\u0651"
158+
"n\u0303": "\u0683"
159+
"n\u0307": "\u06B1"
160+
"n\u0323": "\u06BB"
161+
"nn": "\u0646\u0651"
162+
"n": "\u0646"
163+
"phph": "\u06A6\u0651"
164+
"ph": "\u06A6"
165+
"pp": "\u067E\u0651"
166+
"p": "\u067E"
167+
"qq": "\u0642\u0651"
168+
"q": "\u0642"
169+
"r\u0323r\u0323": "\u0699\u0651"
170+
"r\u0323": "\u0699"
171+
"rr": "\u0631\u0651"
172+
"r": "\u0631"
173+
"s\u0323s\u0323": "\u0635\u0651"
174+
"s\u0323": "\u0635"
175+
"s\u0332s\u0332": "\u062B\u0651"
176+
"s\u0332": "\u062B"
177+
"shsh": "\u0634\u0651"
178+
"sh": "\u0634"
179+
"ss": "\u0633\u0651"
180+
"s": "\u0633"
181+
"t\u0323ht\u0323h": "\u067A\u0651"
182+
"t\u0323t\u0323": "\u067D\u0651"
183+
"t\u0324t\u0324": "\u0637\u0651"
184+
"t\u0323h": "\u067A"
185+
"t\u0323": "\u067D"
186+
"t\u0324": "\u0637"
187+
"thth": "\u067F\u0651"
188+
"th": "\u067F"
189+
"tt": "\u062A\u0651"
190+
"t": "\u062A"
191+
"vv": "\u0648\u0651"
192+
"v": "\u0648"
193+
"ww": "\u0648\u0651"
194+
"w": "\u0648"
195+
"yy": "\u064A\u0651"
196+
"y": "\u064A"
197+
"z\u0323z\u0323": "\u0636\u0651"
198+
"z\u0324z\u0324": "\u0638\u0651"
199+
"z\u0332z\u0332": "\u0630\u0651"
200+
"z\u0323": "\u0636"
201+
"z\u0324": "\u0638"
202+
"z\u0332": "\u0630"
203+
"zz": "\u0632\u0651"
204+
"z": "\u0632"
205+
"h\u0323h\u0323": "\u062D\u0651"
206+
"h\u0323": "\u062D"
207+
"hh": "\u0647\u0651"
208+
"ha%": "\u0647\u06C1"
209+
"he%": "\u0647\u06C1"
210+
"hi%": "\u0647\u06C1"
211+
"ho%": "\u0647\u06C1"
212+
"hu%": "\u0647\u06C1"
213+
"h%": "\u0647\u06C1"
214+
"h": "\u0647"
215+
216+
# prime = ZWNJ"
217+
"\u02B9a\u0304": "\u200C\u0622"
218+
"a\u0304\u02BC\u02B9": "\u0627\u0621\u200C"
219+
"i\u0304\u02B9": "\u0649\u200C"
220+
"\u02B9": "\u200C"
221+
222+
# Izafah here
223+
"a\u0304-yi%": "\u0627\u0626\u06D2"
224+
"u\u0304-yi%": "\u0648\u0626\u06D2"
225+
"o-yi%": "\u0648\u0626\u06D2"
226+
"e-yi%": "\u06D2"
227+
"i\u0304-yi%": "\u0649"
228+
"h-yi%": "\u06C0"
229+
"-yi%": "\u06C0"
230+
"al-i%": "\u0644"
231+
"ul-i%": "\u0644"
232+
"-i%": ""
233+
234+
# Hyphenated prefixes:
235+
"bi-": "\u0628"
236+
"%al-a\u0304": "\u0627\u0644\u0627"
237+
"%ul-a\u0304": "\u0627\u0644\u0627"
238+
"al-": "\u0627\u0644"
239+
"ul-": "\u0627\u0644"
240+
"lil-i": "\u0644\u0644"
241+
"lil-": "\u0644\u0644"
242+
243+
# al-/ul- plus sun letters
244+
"ar-r": "\u0627\u0644\u0631"
245+
"ur-r": "\u0627\u0644\u0631"
246+
"az\u0332-z\u0332": "\u0627\u0644\u0630"
247+
"uz\u0332-z\u0332": "\u0627\u0644\u0630"
248+
"ad-d": "\u0627\u0644\u0627"
249+
"ud-d": "\u0627\u0644\u0627"
250+
"as\u0332-s\u0332": "\u0627\u0644\u062B"
251+
"us\u0332-s\u0332": "\u0627\u0644\u062B"
252+
"at-t": "\u0627\u0644\u062A"
253+
"ut-t": "\u0627\u0644\u062A"
254+
"an-n": "\u0627\u0644\u0646"
255+
"un-n": "\u0627\u0644\u0646"
256+
"al-l": "\u0627\u0644\u0644"
257+
"ul-l": "\u0627\u0644\u0644"
258+
"az\u0324-z\u0324": "\u0627\u0644\u0638"
259+
"uz\u0324-z\u0324": "\u0627\u0644\u0638"
260+
"at\u0324-t\u0324": "\u0627\u0644\u0637"
261+
"ut\u0324-t\u0324": "\u0627\u0644\u0637"
262+
"az\u0323-z\u0323": "\u0627\u0644\u0636"
263+
"uz\u0323-z\u0323": "\u0627\u0644\u0636"
264+
"as\u0323-s\u0323": "\u0627\u0644\u0635"
265+
"us\u0323-s\u0323": "\u0627\u0644\u0635"
266+
"ash-sh": "\u0627\u0644\u0634"
267+
"ush-sh": "\u0627\u0644\u0634"
268+
"as-s": "\u0627\u0644\u0633"
269+
"us-s": "\u0627\u0644\u0633"
270+
"az-z": "\u0627\u0644\u0632"
271+
"uz-z": "\u0627\u0644\u0632"
272+
273+
# Diphthongs here
274+
"a\u0304i\u0304": "\u0627\u0678\u064A"
275+
"a\u0304i%": "\u0627\u0621"
276+
"ai%": "\u06D2"
277+
"%ai": "\u0627\u064A"
278+
"ai": "\u064A"
279+
"\u02BBau": "\u0639\u0648"
280+
"au": "\u0648"
281+
282+
# ayn-alif combo
283+
"\u02BBa\u0304\u02BE%": "\u0639\u0627\u0621"
284+
"\u02BBa\u0304\u02BC%": "\u0639\u0627\u0621"
285+
"%\u02BBa\u0304%": "\u0639\u0627"
286+
287+
# hamza and vowel combo
288+
# [in final position]
289+
"u\u0304\u02BEi\u0304%": "\u0648\u0626\u0649"
290+
"u\u0304\u02BCi\u0304%": "\u0648\u0626\u0649"
291+
"\u02BEi\u0304%": "\u0626\u0649"
292+
"\u02BCi\u0304%": "\u0626\u0649"
293+
"\u02BEe%": "\u0626\u06D2"
294+
"\u02BCe%": "\u0626\u06D2"
295+
296+
"\u02BEu\u0304%": "\u0624"
297+
"\u02BCu\u0304%": "\u0624"
298+
"\u02BEo%": "\u0624"
299+
"\u02BCo%": "\u0624"
300+
301+
# [in medial position]
302+
"a\u02BEa": "\u0623"
303+
"a\u02BCa": "\u0623"
304+
"a\u0304\u02BEa": "\u0627\u0621"
305+
"a\u0304\u02BCa": "\u0627\u0621"
306+
"a\u02BEa\u0304": "\u0622"
307+
"a\u02BCa\u0304": "\u0622"
308+
"o\u02BEi\u0304": "\u0648\u0626\u064A"
309+
"o\u02BCi\u0304": "\u0648\u0626\u064A"
310+
"o\u02BEi": "\u0648\u0626"
311+
"o\u02BCi": "\u0648\u0626"
312+
"\u02BEi\u0304": "\u0626\u064A"
313+
"\u02BCi\u0304": "\u0626\u064A"
314+
"\u02BEi": "\u0626"
315+
"\u02BCi": "\u0626"
316+
"\u02BEe": "\u0626\u064A"
317+
"\u02BCe": "\u0626\u064A"
318+
319+
"\u02BEu\u0304": "\u0624"
320+
"\u02BCu\u0304": "\u0624"
321+
"u\u0304\u02BE": "\u0624"
322+
"u\u0304\u02BC": "\u0624"
323+
"\u02BEo": "\u0624"
324+
"\u02BCo": "\u0624"
325+
"o\u02BE": "\u0624"
326+
"o\u02BC": "\u0624"
327+
"au\u02BE": "\u0624"
328+
"au\u02BC": "\u0624"
329+
330+
"\u02BEa": "\u0626"
331+
"\u02BCa": "\u0626"
332+
333+
"i\u0304%": "\u0649"
334+
"a\u0301%": "\u0649\u0670"
335+
336+
# A
337+
"\u02BBa\u0304": "\u0639\u0627"
338+
"\u02BBa": "\u0639"
339+
"%a\u02BB": "\u0627\u0639"
340+
"a\u02BB": "\u0639"
341+
"%a\u0304": "\u0622"
342+
"a\u0304": "\u0627"
343+
"a\u0301": "\u0649"
344+
"ayy": "\u064A\u0651"
345+
"%a": "\u0627"
346+
"a": ""
347+
"a\u0304i\u0304": "\u0627\u0678\u064A"
348+
349+
# E
350+
"e%": "\u064A"
351+
"%e": "\u0627\u064A"
352+
"e": "\u064A"
353+
354+
# I
355+
"\u02BBI\u0304": "\u0639\u064A"
356+
"\u02BBi\u0304": "\u0639\u064A"
357+
"i\u02BB": "\u0639"
358+
"\u02BBI": "\u0639"
359+
"%i\u0304": "\u0627\u064A"
360+
"i\u0304y": "\u064A"
361+
"i\u0304": "\u064A"
362+
"iyy": "\u064A\u0651"
363+
"%i": "\u0627"
364+
"i": ""
365+
"ia\u0304%": "\u064A\u0627"
366+
"%I\u0304\u02BC": "\u0622\u0678"
367+
368+
# O
369+
"oi%": "\u0648\u0621"
370+
"%o": "\u0627\u0648"
371+
"o": "\u0648"
372+
373+
# U
374+
"\u02BBu\u0304": "\u0639\u0648"
375+
"\u02BBu": "\u0639"
376+
"%u\u0304": "\u0627\u0648"
377+
"u\u0304": "\u0648"
378+
"%u": "\u064A\u0648"
379+
"u": ""
380+
381+
# ain (alone)
382+
"\u02BB": "\u0639"
383+
384+
# hamza (alone in final position)
385+
"\u02BE%": "\u0621"
386+
"\u02BC%": "\u0621"

scriptshifter/tables/index.yml

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -334,6 +334,9 @@ selkup_cyrillic:
334334
marc_code: sel
335335
shor_cyrillic:
336336
name: Shor (Cyrillic)
337+
sindhi_arabic:
338+
marc_code: snd
339+
name: Sindhi (Arabic)
337340
sinhalese:
338341
marc_code: sin
339342
name: Sinhalese

0 commit comments

Comments
 (0)