1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
|
#! /usr/bin/env python
# -*- coding: utf-8 -*-
# Payyans Ascii to Unicode Convertor
# 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
#
# 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 3 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 Library 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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
import sys
import codecs
import os
from optparse import OptionParser
class Payyan:
def __init__(self):
self.input_filename =""
self.output_filename=""
self.mapping_filename=""
self.rulesDict=None
self.pdf=0
def word2ASCII(self, unicode_text):
index = 0
prebase_letter = ""
ascii_text=""
self.direction = "u2a"
self.rulesDict = self.LoadRules()
while index < len(unicode_text):
'''This takes care of conjuncts '''
for charNo in [3,2,1]:
letter = unicode_text[index:index+charNo]
if letter in self.rulesDict:
ascii_letter = self.rulesDict[letter]
letter = letter.encode('utf-8')
'''Fixing the prebase mathra'''
'''TODO: Make it generic , so that usable for all indian languages'''
if letter == 'ൈ':
ascii_text = ascii_text[:-1] + ascii_letter*2 + ascii_text[-1:]
elif (letter == 'ോ') | (letter == 'ൊ') | (letter == 'ൌ'): #prebase+postbase mathra case
ascii_text = ascii_text[:-1] + ascii_letter[0] + ascii_text[-1:] + ascii_letter[1]
elif (letter == 'െ') | (letter == 'േ') |(letter == '്ര'): #only prebase
ascii_text = ascii_text[:-1] + ascii_letter + ascii_text[-1:]
else:
ascii_text = ascii_text + ascii_letter
index = index+charNo
break
else:
if(charNo==1):
index=index+1
ascii_text = ascii_text + letter
break;
'''Did not get'''
ascii_letter = letter
return ascii_text
def Uni2Ascii(self):
if self.input_filename :
uni_file = codecs.open(self.input_filename, encoding = 'utf-8', errors = 'ignore')
else :
uni_file = codecs.open(sys.stdin, encoding = 'utf-8', errors = 'ignore')
text = ""
if self.output_filename :
output_file = codecs.open(self.output_filename, encoding = 'utf-8', errors = 'ignore', mode='w+')
while 1:
text =uni_file.readline()
if text == "":
break
ascii_text = ""
ascii_text = self.word2ASCII(text)
if self.output_filename :
output_file.write(ascii_text)
else:
print ascii_text.encode('utf-8')
return 0
def word2Unicode(self, ascii_text):
index = 0
post_index = 0
prebase_letter = ""
postbase_letter = ""
unicode_text = ""
next_ucode_letter = ""
self.direction="a2u"
self.rulesDict = self.LoadRules()
while index < len(ascii_text):
for charNo in [2,1]:
letter = ascii_text[index:index+charNo]
if letter in self.rulesDict:
unicode_letter = self.rulesDict[letter]
if(self.isPrebase(unicode_letter)):
prebase_letter = unicode_letter
else:
post_index = index+charNo
if post_index < len(ascii_text):
letter = ascii_text[post_index]
if letter in self.rulesDict:
next_ucode_letter = self.rulesDict[letter]
if self.isPostbase(next_ucode_letter):
postbase_letter = next_ucode_letter
index = index + 1
if ((unicode_letter.encode('utf-8') == "എ") |
( unicode_letter.encode('utf-8') == "ഒ" )):
unicode_text = unicode_text + postbase_letter + self.getVowelSign(prebase_letter , unicode_letter)
else:
unicode_text = unicode_text + unicode_letter + postbase_letter + prebase_letter
prebase_letter=""
postbase_letter=""
index = index + charNo
break
else:
if charNo == 1:
unicode_text = unicode_text + letter
index = index + 1
break
unicode_letter = letter
return unicode_text
def Ascii2Uni(self):
if self.pdf :
command = "pdftotext '" + self.input_filename +"'"
process = os.popen(command, 'r')
status = process.close()
if status:
print "The input file is a PDF file. To convert this the pdftotext utility is required. "
print "This feature is available only for GNU/Linux Operating system."
return 1 # Error - no pdftotext !
else:
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 :
ascii_file = codecs.open(sys.stdin, encoding = 'utf-8', errors = 'ignore')
text = ""
if self.output_filename :
output_file = codecs.open(self.output_filename, encoding = 'utf-8', errors = 'ignore', mode='w+')
while 1:
text =ascii_file.readline()
if text == "":
break
unicode_text = ""
unicode_text = self.word2Unicode(text)
if self.output_filename :
output_file.write(unicode_text)
else:
print unicode_text.encode('utf-8')
return 0
def getVowelSign(self, vowel_letter, vowel_sign_letter):
vowel= vowel_letter.encode('utf-8')
vowel_sign= vowel_sign_letter.encode('utf-8')
if vowel == "എ":
if vowel_sign == "െ":
return "ഐ"
if vowel == "ഒ":
if vowel_sign == "ാ":
return "ഓ"
if vowel_sign =="ൗ":
return "ഔ"
return (vowel_letter+ vowel_sign_letter)
def isPrebase(self, letter):
unicode_letter = letter.encode('utf-8')
if( ( unicode_letter == "േ" ) | ( unicode_letter == "ൈ" ) | ( unicode_letter == "ൊ" ) | ( unicode_letter == "ോ" ) | ( unicode_letter == "ൌ" )
| ( unicode_letter == "്ര" ) | ( unicode_letter == "െ" )
):
return True
else:
return False
def isPostbase(self, letter):
unicode_letter = letter.encode('utf-8')
if ( (unicode_letter == "്യ") | (unicode_letter == "്വ") ):
return True
else:
return False
def LoadRules(self):
if(self.rulesDict):
return self.rulesDict
rules_dict = dict()
line = []
line_number = 0
rules_file = codecs. open(self.mapping_filename,encoding='utf-8', errors='ignore')
while 1:
''' Keep the line number. Required for error reporting'''
line_number = line_number +1
text = unicode( rules_file.readline())
if text == "":
break
'''Ignore the comments'''
if text[0] == '#':
continue
line = text.strip()
if(line == ""):
continue
if(len(line.split("=")) != 2):
print "Error: Syntax Error in the Ascii to Unicode Map in line number ", line_number
print "Line: "+ text
return 2 # Error - Syntax error in Mapping file
lhs = line.split("=") [ 0 ]
rhs = line.split("=") [ 1 ]
lhs=lhs.strip()
rhs=rhs.strip()
if self.direction == 'a2u':
rules_dict[lhs]=rhs
else:
rules_dict[rhs]=lhs
return rules_dict
|
