[Bf-translations-svn] SVN commit: /data/svn/bf-translations [197] branches/fa/fa_to_utf.py: Modified original Arabic converter script to support Farsi.
bf-translations at blender.org
bf-translations at blender.org
Fri Nov 18 09:44:51 CET 2011
Revision: 197
http://projects.blender.org/scm/viewvc.php?view=rev&root=bf-translations&revision=197
Author: leomoon
Date: 2011-11-18 08:44:50 +0000 (Fri, 18 Nov 2011)
Log Message:
-----------
Modified original Arabic converter script to support Farsi. Tested and it's working...
Modified Paths:
--------------
branches/fa/fa_to_utf.py
Modified: branches/fa/fa_to_utf.py
===================================================================
--- branches/fa/fa_to_utf.py 2011-11-18 06:16:53 UTC (rev 196)
+++ branches/fa/fa_to_utf.py 2011-11-18 08:44:50 UTC (rev 197)
@@ -1,5 +1,32 @@
#coding: utf-8
+# ***** BEGIN GPL LICENSE BLOCK *****
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 2
+# of the License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software Foundation,
+# Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+#
+# Authers:
+# -Dalai Felinto
+# -Yousef Harfoush
+# -Bastien Montagne
+# -Amin Babaeipanah (modified for Farsi support)
+#
+# based on The Arabic Writer script by Omar Muhammad
+# thanks for Rabeh Torchi for ideas
+#
+# ***** END GPL LICENSE BLOCK *****
+
import sys
import os
@@ -9,67 +36,71 @@
# Isolated, Beginning, Middle, End
-# http://en.wikipedia.org/wiki/Persian_alphabet
-alefa = ["ﺁ","ﺁ","ﺂ","ﺂ"]
-alefd = ["ﺍ","ﺍ","ﺎ","ﺎ"]
-beeee = ["ﺏ","ﺑ","ﺒ","ﺐ"]
+# http://en.wikipedia.org/wiki/Arabic_alphabet
+# http://en.wikipedia.org/wiki/Arabic_characters_in_Unicode
+alfmd = ["ﺁ","ﺁ","ﺂ","ﺂ"]
+alfhz = ["ﺃ","ﺃ","ﺄ","ﺄ"]
+wowhz = ["ﺅ","ﺅ","ﺆ","ﺆ"]
+alfxr = ["ﺇ","ﺇ","ﺈ","ﺈ"]
+hamzk = ["ﺉ","ﺋ","ﺌ","ﺊ"]
+alfff = ["ﺍ","ﺍ","ﺎ","ﺎ"]
+baaaa = ["ﺏ","ﺑ","ﺒ","ﺐ"]
peeee = ["ﭖ","ﭘ","ﭙ","ﭗ"]
-teeee = ["ﺕ","ﺗ","ﺘ","ﺖ"]
-seeee = ["ﺙ","ﺛ","ﺜ","ﺚ"]
-jimmm = ["ﺝ","ﺟ","ﺠ","ﺞ"]
+tamrb = ["ﺓ","ﺓ","ﺔ","ﺔ"]
+taaaa = ["ﺕ","ﺗ","ﺘ","ﺖ"]
+thaaa = ["ﺙ","ﺛ","ﺜ","ﺚ"]
+geeem = ["ﺝ","ﺟ","ﺠ","ﺞ"]
cheee = ["ﭺ","ﭼ","ﭽ","ﭻ"]
-heeee = ["ﺡ","ﺣ","ﺤ","ﺢ"]
-kheee = ["ﺥ","ﺧ","ﺨ","ﺦ"]
-daall = ["ﺩ","ﺩ","ﺪ","ﺪ"]
-zaall = ["ﺫ","ﺫ","ﺬ","ﺬ"]
-reeee = ["ﺭ","ﺭ","ﺮ","ﺮ"]
-zeeee = ["ﺯ","ﺯ","ﺰ","ﺰ"]
+haaaa = ["ﺡ","ﺣ","ﺤ","ﺢ"]
+khaaa = ["ﺥ","ﺧ","ﺨ","ﺦ"]
+daaal = ["ﺩ","ﺩ","ﺪ","ﺪ"]
+thaal = ["ﺫ","ﺫ","ﺬ","ﺬ"]
+raaaa = ["ﺭ","ﺭ","ﺮ","ﺮ"]
+zaaai = ["ﺯ","ﺯ","ﺰ","ﺰ"]
zheee = ["ﮊ","ﮊ","ﮋ","ﮋ"]
-sinnn = ["ﺱ","ﺳ","ﺴ","ﺲ"]
-shinn = ["ﺵ","ﺷ","ﺸ","ﺶ"]
-saddd = ["ﺹ","ﺻ","ﺼ","ﺺ"]
-zaddd = ["ﺽ","ﺿ","ﻀ","ﺾ"]
-taaaa = ["ﻁ","ﻃ","ﻄ","ﻂ"]
-zaaaa = ["ﻅ","ﻇ","ﻈ","ﻆ"]
-eynnn = ["ﻉ","ﻋ","ﻌ","ﻊ"]
-gheyn = ["ﻍ","ﻏ","ﻐ","ﻎ"]
-feeee = ["ﻑ","ﻓ","ﻔ","ﻒ"]
-ghaaf = ["ﻕ","ﻗ","ﻘ","ﻖ"]
-kaaff = ["ک","ﻛ","ﻜ","ﮏ"]
-gaaff = ["ﮒ","ﮔ","ﮕ","ﮓ"]
-laamm = ["ﻝ","ﻟ","ﻠ","ﻞ"]
-mimmm = ["ﻡ","ﻣ","ﻤ","ﻢ"]
-noonn = ["ﻥ","ﻧ","ﻨ","ﻦ"]
-vaavv = ["ﻭ","ﻭ","ﻮ","ﻮ"]
-hehhh = ["ﻩ","ﻫ","ﻬ","ﻪ"]
-yeeee = ["ﯼ","ﯾ","ﯿ","ﯽ"]
+seeen = ["ﺱ","ﺳ","ﺴ","ﺲ"]
+sheen = ["ﺵ","ﺷ","ﺸ","ﺶ"]
+saaad = ["ﺹ","ﺻ","ﺼ","ﺺ"]
+daaad = ["ﺽ","ﺿ","ﻀ","ﺾ"]
+taaah = ["ﻁ","ﻃ","ﻄ","ﻂ"]
+daaah = ["ﻅ","ﻇ","ﻈ","ﻆ"]
+aayen = ["ﻉ","ﻋ","ﻌ","ﻊ"]
+gayen = ["ﻍ","ﻏ","ﻐ","ﻎ"]
+faaaa = ["ﻑ","ﻓ","ﻔ","ﻒ"]
+qaaaf = ["ﻕ","ﻗ","ﻘ","ﻖ"]
+kaaaf = ["ﮎ","ﮐ","ﮑ","ﮏ"]
+gaaaf = ["ﮒ","ﮔ","ﮕ","ﮓ"]
+laaam = ["ﻝ","ﻟ","ﻠ","ﻞ"]
+meeem = ["ﻡ","ﻣ","ﻤ","ﻢ"]
+nooon = ["ﻥ","ﻧ","ﻨ","ﻦ"]
+hhhhh = ["ﻩ","ﻫ","ﻬ","ﻪ"]
+wowww = ["ﻭ","ﻭ","ﻮ","ﻮ"]
+yaamd = ["ﯼ","ﯾ","ﯿ","ﯽ"]
+yaaaa = ["ﻱ","ﻳ","ﻴ","ﻲ"]
+laamd = ["ﻵ","ﻵ","ﻶ","ﻶ"]
+laahz = ["ﻷ","ﻷ","ﻸ","ﻸ"]
+laaxr = ["ﻹ","ﻹ","ﻺ","ﻺ"]
+laaaa = ["ﻻ","ﻻ","ﻼ","ﻼ"]
-yehmz = ["ﺉ","ﺋ","ﺌ","ﺊ"]
-laaad = ["ﻻ","ﻻ","ﻼ","ﻼ"]
-
# defining numbers
-numbers ="0123456789۰۱۲۳۴۵۶۷۸۹"
-#defining Persian unicodec chars
-unicodec ="ﺁﺁﺂﺂﺍﺍﺎﺎﺏﺑﺒﺐﭖﭘﭙﭗﺕﺗﺘﺖﺙﺛﺜﺚﺝﺟﺠﺞﭺﭼﭽﭻﺡﺣﺤﺢﺥﺧﺨﺦﺩﺩﺪﺪﺫﺫﺬﺬﺭﺭﺮﺮﺯﺯﺰﺰﮊﮊﮋﮋﺱﺳﺴﺲﺵﺷﺸﺶﺹﺻﺼﺺﺽﺿﻀﺾﻁﻃﻄﻂﻅﻇﻈﻆﻉﻋﻌﻊﻍﻏﻐﻎﻑﻓﻔﻒﻕﻗﻘﻖکﻛﻜﮏﮒﮔﮕﮓﻝﻟﻠﻞﻡﻣﻤﻢﻥﻧﻨﻦﻭﻭﻮﻮﻩﻫﻬﻪیﻳﻴﻰﺉﺋﺌﺊﻻﻻﻼﻼ"
+numbers ="0123456789٠١٢٣٤٥٦٧٨٩"
+#defining arabic unicodec chars
+unicodec ="ﺁﺁﺂﺂﺃﺃﺄﺄﺅﺅﺆﺆﺇﺇﺈﺈﺉﺋﺌﺊﺍﺍﺎﺎﺏﺑﺒﺐﺓﺓﺔﺔﺕﺗﺘﺖﺙﺛﺜﺚﺝﺟﺠﺞﭺﭼﭽﭻﺡﺣﺤﺢﺥﺧﺨﺦﺩﺩﺪﺪﺫﺫﺬﺬﺭﺭﺮﺮﺯﺯﺰﺰﮊﮊﮋﮋﺱﺳﺴﺲﺵﺷﺸﺶﺹﺻﺼﺺﺽﺿﻀﺾﻁﻃﻄﻂﻅﻇﻈﻆﻉﻋﻌﻊﻍﻏﻐﻎﻑﻓﻔﻒﻕﻗﻘﻖﮎﮐﮑﮏﮒﮔﮕﮓﻝﻟﻠﻞﻡﻣﻤﻢﻥﻧﻨﻦﻩﻫﻬﻪﻭﻭﻮﻮﯼﯾﯿﯽﻱﻳﻴﻲﻵﻵﻶﻶﻷﻷﻸﻸﻹﻹﻺﻺﻻﻻﻼﻼ"
# letters that have only Isolated and End forms
# (and work as word breakers) + laaam and deriveds
-wordbreak ="آادذرزﮊوﻻ"
+wordbreak ="آأؤإاةدذرزوﻵﻷﻹﻻ"
-# defining all Persian letters + araab
-#Persian ="ًٌٍَُِّْْئءؤرلاىةوزظشسيبلاتنمكطضصثقفغعهخحجدذْلآآلأأـلإإ،؟"
-Persian = "ﺁﺍﺉ"
-# defining the araab
-#araab ="ًٌٍَُِّْْ"
-araab = ""
-
+# defining all arabic letters + harakat
+arabic ="ًٌٍَُِّْْئءؤرلایةوزژظشسيبپلاتنمکگطضصثقفغعهخحچجدذْلآآلأأـلإإ،؟"
+# defining the harakat
+harakat ="ًٌٍَُِّْْ"
# defining other symbols
-#sym ="ًٌٍَُِّـ.،؟ @#$%^&*-+|\/=~(){}ْ,:"
-sym = "{}()~=/\|+-*&^%$#@ ٬؟.,:"
+sym ="ًٌٍَُِّـ.،؟ @#$%^&*-+|\/=~(){}ْ,:"
def ProcessInput(input):
"""main function, the code is not self-explanatory.
- It requires understanding of Persian alphabet.
+ It requires understanding of arabic alphabet.
"""
words = ""
@@ -81,21 +112,21 @@
g = 0
while g < ln:
- b=a=1 #ignoring/discarding the araab
+ b=a=1 #ignoring/discarding the harakat
# see how many chars I need to skip to get the next
- # non-araab char in the left (a) or the right (b)
+ # non-harakat char in the left (a) or the right (b)
- while g-b >= 0 and x[g-b] in araab: b+=1
- while g+a < ln and x[g+a] in araab: a+=1
+ while g-b >= 0 and x[g-b] in harakat: b+=1
+ while g+a < ln and x[g+a] in harakat: a+=1
# get the position
- if x[g] not in wordbreak and g+a < ln and x[g+a] in Persian and x[g+a] != "ء":
- if g-b >= 0 and x[g-b] not in wordbreak and x[g-b] in Persian and x[g-b] != "ء":
+ if x[g] not in wordbreak and g+a < ln and x[g+a] in arabic and x[g+a] != "ء":
+ if g-b >= 0 and x[g-b] not in wordbreak and x[g-b] in arabic and x[g-b] != "ء":
pos = 2 # middle
else:
pos = 1 # beggining
else:
- if g-b >= 0 and x[g-b] not in wordbreak and x[g-b] in Persian and x[g-b] != "ء":
+ if g-b >= 0 and x[g-b] not in wordbreak and x[g-b] in arabic and x[g-b] != "ء":
pos = 3 # end
else:
pos = 0 # isolated
@@ -114,33 +145,38 @@
# dealing with letters, output each
# letter with its right position
- elif x[g]=="آ": chr=alefa[pos]
- elif x[g]=="ا": chr=alefd[pos]
- elif x[g]=="ب": chr=beeee[pos]
+ elif x[g]=="آ": chr=alfmd[pos]
+ elif x[g]=="أ": chr=alfhz[pos]
+ elif x[g]=="ؤ": chr=wowhz[pos]
+ elif x[g]=="إ": chr=alfxr[pos]
+ elif x[g]=="ئ": chr=hamzk[pos]
+ elif x[g]=="ا": chr=alfff[pos]
+ elif x[g]=="ب": chr=baaaa[pos]
elif x[g]=="پ": chr=peeee[pos]
- elif x[g]=="ت": chr=teeee[pos]
- elif x[g]=="ث": chr=seeee[pos]
- elif x[g]=="ج": chr=jimmm[pos]
+ elif x[g]=="ة": chr=tamrb[pos]
+ elif x[g]=="ت": chr=taaaa[pos]
+ elif x[g]=="ث": chr=thaaa[pos]
+ elif x[g]=="ج": chr=geeem[pos]
elif x[g]=="چ": chr=cheee[pos]
- elif x[g]=="ح": chr=heeee[pos]
- elif x[g]=="خ": chr=kheee[pos]
- elif x[g]=="د": chr=daall[pos]
- elif x[g]=="ذ": chr=zaall[pos]
- elif x[g]=="ر": chr=reeee[pos]
- elif x[g]=="ز": chr=zeeee[pos]
- elif x[g]=="ژ": chr=zheee[pos]
- elif x[g]=="س": chr=sinnn[pos]
- elif x[g]=="ش": chr=shinn[pos]
- elif x[g]=="ص": chr=saddd[pos]
- elif x[g]=="ض": chr=zaddd[pos]
- elif x[g]=="ط": chr=taaaa[pos]
- elif x[g]=="ظ": chr=zaaaa[pos]
- elif x[g]=="ع": chr=eynnn[pos]
- elif x[g]=="غ": chr=gheyn[pos]
- elif x[g]=="ف": chr=feeee[pos]
- elif x[g]=="ق": chr=ghaaf[pos]
- elif x[g]=="ک": chr=kaaff[pos]
- elif x[g]=="گ": chr=gaaff[pos]
+ elif x[g]=="ح": chr=haaaa[pos]
+ elif x[g]=="خ": chr=khaaa[pos]
+ elif x[g]=="د": chr=daaal[pos]
+ elif x[g]=="ذ": chr=thaal[pos]
+ elif x[g]=="ر": chr=raaaa[pos]
+ elif x[g]=="ز": chr=zaaai[pos]
+ elif x[g]=="ژ": chr=zaaai[pos]
+ elif x[g]=="س": chr=seeen[pos]
+ elif x[g]=="ش": chr=sheen[pos]
+ elif x[g]=="ص": chr=saaad[pos]
+ elif x[g]=="ض": chr=daaad[pos]
+ elif x[g]=="ط": chr=taaah[pos]
+ elif x[g]=="ظ": chr=daaah[pos]
+ elif x[g]=="ع": chr=aayen[pos]
+ elif x[g]=="غ": chr=gayen[pos]
+ elif x[g]=="ف": chr=faaaa[pos]
+ elif x[g]=="ق": chr=qaaaf[pos]
+ elif x[g]=="ک": chr=kaaaf[pos]
+ elif x[g]=="گ": chr=gaaaf[pos]
elif x[g]=="ل":
# dealing with (la combination)
# in this case the char has two chars in one
@@ -148,20 +184,23 @@
g = g+1
if g == ln:
g = g-1
- chr=laamm[pos]
- elif x[g]=="ا": chr=laaad[pos]
- #elif x[g]=="أ": chr=laahz[pos]
- #elif x[g]=="إ": chr=laaxr[pos]
- #elif x[g]=="آ": chr=laamd[pos]
+ chr=laaam[pos]
+ elif x[g]=="ا": chr=laaaa[pos]
+ elif x[g]=="أ": chr=laahz[pos]
+ elif x[g]=="إ": chr=laaxr[pos]
+ elif x[g]=="آ": chr=laamd[pos]
else:
g = g-1
- chr=laamm[pos]
- elif x[g]=="م": chr=mimmm[pos]
- elif x[g]=="ن": chr=noonn[pos]
- elif x[g]=="و": chr=vaavv[pos]
- elif x[g]=="ه": chr=hehhh[pos]
- elif x[g]=="ی": chr=yeeee[pos]
- elif x[g]=="ئ": chr=yehmz[pos]
+ chr=laaam[pos]
+ elif x[g]=="م": chr=meeem[pos]
+ elif x[g]=="ن": chr=nooon[pos]
+ elif x[g]=="ه": chr=hhhhh[pos]
+ elif x[g]=="و": chr=wowww[pos]
+ elif x[g]=="ی": chr=yaamd[pos]
+ elif x[g]=="ي": chr=yaaaa[pos]
+ elif x[g]=="لآ": chr=laamd[pos]
+ elif x[g]=="لأ": chr=laahz[pos]
+ elif x[g]=="لإ": chr=laaxr[pos]
elif x[g]=="لا": chr=laaaa[pos]
#if the char is a symbol, add it
elif x[g] in sym:
@@ -177,7 +216,7 @@
chr = x[g]
else:
chr = x[g]
- #if the char is an Persian reversed letter, reverse it back!
+ #if the char is an arabic reversed letter, reverse it back!
elif x[g] in unicodec: chr=x[g]
# advance to the next char
@@ -222,6 +261,7 @@
if __name__ == "__main__":
+ #argument parsing
import argparse
@@ Diff output truncated at 10240 characters. @@
More information about the Bf-translations-svn
mailing list