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
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""Make a list of words that enchant spell checker does not
approve. Words are parsed from the files given as arguments.
One or more word list files can be given, those words are deemed
OK even if enchant would flag them wrong.
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 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
Author: Tapio Lehtonen <tale@debian.org>
"""
def handleCommandLine():
""" Get arguments and options from command line. """
from optparse import OptionParser
usage = """usage: %prog [options] filename
Print out unknown words found in filename. Options
-p and --wordlist can be given several times."""
lhelpstr = """What language is the text to proofread? For example fi_FI."""
parser = OptionParser(usage=usage)
parser.set_defaults(verbose=False, listonly=True, wordlists=[])
parser.add_option("-p", "--wordlist",
action="append", type="string", dest="wordlists",
help="File with OK words one per line.",
metavar="Wordlist")
parser.add_option("-d", "--language",
action="store", type="string", dest="language",
help=lhelpstr)
parser.add_option("-l", "--listonly",
action="store_true", dest="listonly",
help=lhelpstr)
parser.add_option("-v", action="store_true", dest="verbose",
help="Be verbose.")
parser.add_option("-q", action="store_false", dest="verbose",
help="Be quiet.")
(options, args) = parser.parse_args()
if len(args) != 1:
parser.error("incorrect number of arguments")
if options.verbose:
if (options.wordlists == [] or options.wordlists == None):
print "No extra wordlist files."
else:
print "Extra wordlists: ",
for f in options.wordlists:
print f + " ",
print
if options.language:
print "Proofreading using language ", options.language, "."
else:
print "Proofreading using default language."
return (options, args)
if __name__ == "__main__":
"""Use like this
./make-fi-all.py -d fi_FI fi_all.po > foo.txt 2>&1
Then do
sort foo.txt | uniq | tee unknown_words.txt | wc"""
from enchant.checker import SpellChecker
o, a = handleCommandLine()
if o.verbose:
print "options ", o
print "arguments ", a
try:
textF = open(a[0], "r")
except IOError, value:
print "Erroria", value
sys.exit(4)
if o.verbose:
import sys
print "Language is", o.language
print "STDOUT encoding ", sys.stdout.encoding
print "sys default encoding ", sys.getdefaultencoding()
checker = SpellChecker(o.language)
if o.verbose:
if checker.wants_unicode:
print "Checker wants Unicode text to check."
else:
print "Checker wants normal strings text to check."
#Read in Personal word lists, may be several files
for pN in o.wordlists:
try:
pF = open(pN, "r")
except IOError, value:
print "Error, personal word list could not be opened for reading ", pN
sys.exit(5)
for word in pF.readlines():
if len(word) > 0:
if (word[0] != "#"):
checker.add_to_personal(word)
unknWords={}
for text in textF.readlines():
utext = unicode(text, "utf-8")
if o.verbose:
print "Text as read:"
print text
print "Text to check is:"
for u in utext:
print u.encode("utf-8"),
print
checker.set_text(utext)
for err in checker:
if o.verbose:
print "isinstance basestring", isinstance(err.word, basestring)
print "isinstance str", isinstance(err.word, str)
print "isinstance unicode", isinstance(err.word, unicode)
print err.word.encode("utf-8")
if unknWords.has_key(err.word):
unknWords[err.word] += 1
else:
unknWords[err.word] = 1
textF.close()
#Sort alphabetically and print out as count word
wlist = unknWords.keys()
wlist.sort()
for w in wlist:
print str(unknWords[w]).rjust(8).encode("utf-8"), " ",
print w.encode("utf-8")
|
