def spellchecker():
if request.method == 'POST':
print(request.form.keys(), file=sys.stderr)
print(request.form['lang'], file=sys.stderr)
lang = request.form['lang']
text = request.form['text']
if lang != "ta_IN":
return json.dumps({
'error':
'Language ' + lang +
' is not supported; only takes Tamil (code ta_IN))'
})
lang = "TA"
spell_checker = Speller(lang=lang, mode="web")
result_dict = {'words': {}}
for itr, word in enumerate(filter(len, re.split('\s+', text))):
if word.find("<") >= 0: #HTML Tags, skip
continue
print("checking word %d" % itr, file=sys.stderr)
ok, suggs = spell_checker.REST_interface(word)
if not ok:
result_dict['words'][word] = suggs
return json.dumps(result_dict)
else:
return "RPC interface for TinyMCE Spell Checker!"
def spellchecker():
if request.method == "POST":
print(request.form.keys(), file=sys.stderr)
print(request.form["lang"], file=sys.stderr)
lang = request.form["lang"]
text = request.form["text"]
if lang != "ta_IN":
return json.dumps({
"error":
"Language " + lang +
" is not supported; only takes Tamil (code ta_IN))"
})
lang = "TA"
spell_checker = Speller(lang=lang, mode="web")
result_dict = {"words": {}}
for itr, word in enumerate(filter(len, re.split("\s+", text))):
if word.find("<") >= 0: # HTML Tags, skip
continue
print("checking word %d" % itr, file=sys.stderr)
try:
ok, suggs = spell_checker.REST_interface(word)
pprint.pprint(suggs)
except Exception as ioe:
ok = True
pprint.pprint(ioe)
if not ok:
word = Speller.scrub_ws(word)
result_dict["words"][word] = list(suggs)
return json.dumps(result_dict)
else:
return "RPC interface for TinyMCE Spell Checker!"
def spell_check(request,k1):
speller = Speller(lang=u"TA",mode="web")
notok,suggs = speller.check_word_and_suggest( k1 )
json_string = json.dumps(suggs,ensure_ascii = False)
#creating a Response object to set the content type and the encoding
response = HttpResponse(json_string,content_type="application/json; charset=utf-8" )
return response
def spell_check(request, k1):
speller = Speller(lang="TA", mode="web")
notok, suggs = speller.check_word_and_suggest(k1)
json_string = json.dumps(suggs, ensure_ascii=False)
# creating a Response object to set the content type and the encoding
response = HttpResponse(json_string, content_type="application/json; charset=utf-8")
return response
class SpellTestTamil(unittest.TestCase):
def setUp(self):
self.speller = Speller(lang=u"TA", mode="web")
def test_words_in_dictionary(self):
# test if all the words are in the dictionary
for w in [
u"சவால்", u"மகதம்", u"ஆரதம்", u"பல்லவன்", u"பாதம்", u"கவணம்",
u"செயல்"
]:
ok, _ = self.speller.check_word_and_suggest(w)
self.assertTrue(ok, w)
return
def test_words_in_error(self):
# test if the words in error are flagged
# further test if suggestion contains the right word
debug = False
words_and_fixes = {u"எந்திர": u"எந்திரம்", u"செயல்பட": u"செயல்"}
for w, right_word in words_and_fixes.items():
notok, suggs = self.speller.check_word_and_suggest(w)
if (debug):
pprint(notok)
pprint(suggs)
self.assertFalse(notok, w)
self.assertTrue(right_word in suggs,
u"%s -> (%s)" % (right_word, u", ".join(suggs)))
return
class SpellTestTamil(unittest.TestCase):
def setUp(self):
self.speller = Speller(lang=u"TA",mode="web")
def test_words_in_dictionary(self):
# test if all the words are in the dictionary
for w in [u"சவால்",u"மகதம்",u"ஆரதம்", u"பல்லவன்",u"பாதம்",u"கவணம்", u"செயல்"]:
ok,_ = self.speller.check_word_and_suggest(w)
self.assertTrue( ok, w )
return
def test_words_in_error(self):
# test if the words in error are flagged
# further test if suggestion contains the right word
debug = False
words_and_fixes = { u"எந்திர" : u"எந்திரம்",
u"செயல்பட":u"செயல்"}
for w,right_word in words_and_fixes.items():
notok,suggs = self.speller.check_word_and_suggest( w )
if ( debug ):
pprint(notok)
pprint(suggs)
self.assertFalse( notok, w )
self.assertTrue( right_word in suggs, u"%s -> (%s)"%(right_word,u", ".join(suggs) ))
return
def spell():
if request.method == "GET":
return render_template("spell.html", solution=False)
if request.method != "POST":
return "<B>404! Error</B>"
if u'word' in request.form:
word = request.form['word']
if not word:
return "Enter word!"
lang = "TA"
if "lang" in request.form:
lang = request.form["lang"]
ok, suggs = Speller(lang=lang, mode="web").REST_interface(word)
if ok:
HTML = "<B style='color:green;'>OK!</B>"
else:
data_suggs = json.loads(suggs)
data_suggs2 = u"<br/>\n".join([
u"<option>%d %s</option>" % (itr + 1, s_word)
for itr, s_word in enumerate(data_suggs.values()[0])
])
HTML = "<B style='color:red;'>Not OK!</B><br /><select>" + data_suggs2 + "\n</select><br/>"
return render_template("spell.html",
solution=True,
HTML=HTML,
word=word)
return redirect(url_for('spell'))
def spellchecker():
if request.method == 'POST':
print(request.form.keys(),file=sys.stderr)
print(request.form['lang'],file=sys.stderr)
lang = request.form['lang']
text = request.form['text']
if lang != "ta_IN":
return json.dumps({'error':'Language '+lang+' is not supported; only takes Tamil (code ta_IN))'})
lang = "TA"
spell_checker = Speller(lang=lang,mode="web")
result_dict = {'words':{}}
for itr,word in enumerate( filter(len,re.split('\s+',text)) ):
if word.find("<") >= 0: #HTML Tags, skip
continue
print("checking word %d"%itr,file=sys.stderr)
try:
ok,suggs = spell_checker.REST_interface(word)
pprint.pprint(suggs)
except Exception as ioe:
ok = True
pprint.pprint(ioe)
if not ok:
word = Speller.scrub_ws(word)
result_dict['words'][word] = suggs
return json.dumps(result_dict)
else:
return "RPC interface for TinyMCE Spell Checker!"
def spell_get_only():
if u'word' in request.args:
word = request.args['word']
if not word:
return "Enter word!"
lang="TA"
if "lang" in request.args:
lang = request.args["lang"]
ok,suggs = Speller(lang=lang,mode="web").REST_interface(word)
if ok:
return "<B style='color:green;'>OK!</B>"
data_suggs = suggs
data_suggs2 = u"<br/>\n".join( [u"%d %s"%(itr+1,s_word) for itr,s_word in enumerate( data_suggs.values()[0])])
return "<B style='color:red;'>Not OK!</B><br />"+data_suggs2+"\n<br/>"+suggs
return 'spell check with ?word=$word&lang=en'
# -*- coding: utf-8 -*-
# (C) 2016-17 Muthiah Annamalai
import codecs
import os
from pprint import pprint
from opentamiltests import *
from spell import Speller, LoadDictionary, OttruSplit, Mayangoli
from tamil import utf8
TA_SPELLER = Speller(lang=u"TA", mode="web")
class SpellTestFiles(unittest.TestCase):
def setUp(self):
self.speller = TA_SPELLER
def test_file10(self):
nwords = 31
npass = 13
nfail = 18
fail_n_suggs = dict()
obj = {
"total": nwords,
"correct_words": npass,
"wrong_words": nfail,
"word_suggestions": fail_n_suggs,
}
filename = "data/doc10.spell"
self._tester(filename, obj)
def test_basic(self):
filename = os.path.join("data", "doc1.spell")
sys.stdin.close()
obj = Speller(filename, lang="ta")
self.assertTrue(obj.in_tamil_mode())
def setUp(self):
self.speller = Speller(lang=u"TA", mode="web")
def setUp(self):
self.speller = Speller(lang=u"TA",mode="web")
def test_basic(self):
filename = os.path.join("data","doc1.spell")
sys.stdin.close()
obj = Speller(filename,lang="ta")
self.assertTrue(obj.in_tamil_mode())
