def main():
if len(sys.argv) < 2 or sys.argv[1] in ('-h','--help'):
print """
%(0)s [-v] [FILE]...
Determine the language of each FILE.
If -v is present, then full ranking information will be given for each file.
Examples:
%(0)s test_texts/*.txt
%(0)s -v README
""".strip() % {'0': sys.argv[0]}
return
elif sys.argv[1] == '-v':
verbose = True
fnames = sys.argv[2:]
else:
verbose = False
fnames = sys.argv[1:]
for fname in fnames:
text = open(fname).read(1024)
ranks = pytextcat.classify(text)
ans = []
for i,(rank,(lang,enc)) in enumerate(ranks):
lang = lang.replace('_',' ').title()
if enc: lang = "%s (%s)" % (lang,enc)
if rank < 1.05: ans.append(lang)
rank = int(100*rank) - 100
ranks[i] = (lang,rank)
print fname, "is probably",
if len(ans) == 1:
print ans[0]
elif len(ans) == 2:
print "%s or %s" % (ans[0], ans[1])
else:
print "%s, or %s" % (', '.join(ans[:-1]), ans[-1])
if verbose:
print
print "Full ranking information is given below:"
print
print "Language Score"
for lang,rank in ranks:
print "%s%s%2d%% worse than best score" \
% (lang,' '*(32-len(lang)),rank)
print
print
def post(self):
text = self.request.get('text')
if not text:
self.render()
return
text = text.encode('utf-8')
ranks = classify(text)
ans = []
for i,(rank,(lang,enc)) in enumerate(ranks):
lang = lang.replace('_',' ').title()
if enc: lang = "%s (%s)" % (lang,enc)
if rank < 1.05: ans.append(lang)
rank = int(100*rank) - 100
ranks[i] = (lang,rank)
self.render({'text': cgi.escape(text), 'ans': humanize_list(ans, 'or'), 'ranks': ranks})
def post(self):
text = self.request.get('text')
if not text:
self.render()
return
text = text.encode('utf-8')
ranks = classify(text)
ans = []
for i, (rank, (lang, enc)) in enumerate(ranks):
lang = lang.replace('_', ' ').title()
if enc: lang = "%s (%s)" % (lang, enc)
if rank < 1.05: ans.append(lang)
rank = int(100 * rank) - 100
ranks[i] = (lang, rank)
self.render({
'text': cgi.escape(text),
'ans': humanize_list(ans, 'or'),
'ranks': ranks
})
