diff options
| author | Rajeesh K Nambiar <rajeeshknambiar@gmail.com> | 2009-02-03 08:01:47 +0530 |
|---|---|---|
| committer | Rajeesh K Nambiar <rajeeshknambiar@gmail.com> | 2009-02-03 08:01:47 +0530 |
| commit | f771e45350f7a6e155a5ec9446944c0a58ffdcfa (patch) | |
| tree | 1cd3808b8de2a18a1dfc48fb6375eefd7ad82d3b | |
| parent | 6f02e32253b4a3ca60489ae980771f30ec0dd748 (diff) | |
| download | AnjaliOldLipi.git-f771e45350f7a6e155a5ec9446944c0a58ffdcfa.tar.gz AnjaliOldLipi.git-f771e45350f7a6e155a5ec9446944c0a58ffdcfa.tar.xz AnjaliOldLipi.git-f771e45350f7a6e155a5ec9446944c0a58ffdcfa.zip | |
Payyans: Fix converting 'ൈ' from ASCII
| -rwxr-xr-x | payyans/payyans/payyan.py | 14 |
1 files changed, 9 insertions, 5 deletions
diff --git a/payyans/payyans/payyan.py b/payyans/payyans/payyan.py index 0827b8f..819b940 100755 --- a/payyans/payyans/payyan.py +++ b/payyans/payyans/payyan.py @@ -1,7 +1,7 @@ #! /usr/bin/env python # -*- coding: utf-8 -*- # Payyans Ascii to Unicode Convertor -# Copyright 2008 Santhosh Thottingal <santhosh.thottingal@gmail.com>, +# Copyright 2008-2009 Santhosh Thottingal <santhosh.thottingal@gmail.com>, # Nishan Naseer <nishan.naseer@gmail.com>, Manu S Madhav <manusmad@gmail.com>, # Rajeesh K Nambiar <rajeeshknambiar@gmail.com> # http://www.smc.org.in @@ -57,7 +57,7 @@ class Payyan: letter = unicode_text[index:index+charNo] if letter in self.rulesDict: ascii_letter = self.rulesDict[letter] - letter = letter.encode('utf8') + letter = letter.encode('utf-8') '''കിട്ടിയ അക്ഷരങ്ങളുടെ അപ്പുറത്തും ഇപ്പുറത്തും സ്വരചിഹ്നങ്ങള് ഫിറ്റ് ചെയ്യാനുള്ള ബദ്ധപ്പാട്''' if letter == 'ൈ': # പിറകില് രണ്ടു സാധനം പിടിപ്പിക്കുക ascii_text = ascii_text[:-1] + ascii_letter*2 + ascii_text[-1:] @@ -118,12 +118,16 @@ class Payyan: else: unicode_letter = letter if(self.isPrebase(unicode_letter)): - prebase_letter = unicode_letter + # "ൈ" എന്നത് ആസ്കിയില് 2 "െ" ചേര്ന്നതാണ്. It is unique! + if prebase_letter.encode('utf-8') == "െ" and unicode_letter.encode('utf-8') == "െ": + prebase_letter = u"ൈ" + else: + prebase_letter = unicode_letter else: if ((unicode_letter.encode('utf-8') == "എ") | ( unicode_letter.encode('utf-8') == "ഒ" )): unicode_text = unicode_text + self.getVowelSign(prebase_letter , unicode_letter) else: - unicode_text = unicode_text + unicode_letter+ prebase_letter + unicode_text = unicode_text + unicode_letter + prebase_letter prebase_letter="" index = index + 1 @@ -140,7 +144,7 @@ class Payyan: '''ഊഹും. കൊന്നാലും ഇനി മുന്നോട്ടില്ല. മുന്നില് മറ്റവനാകുന്നു. ഏതു്? ''' return 1 # Error - no pdftotext ! else: - self.input_filename = self.input_filename.split(".") [0]+ ".txt" + self.input_filename = os.path.splitext(self.input_filename)[0] + ".txt" if self.input_filename : ascii_file = codecs.open(self.input_filename, encoding = 'utf-8', errors = 'ignore') else : |