def setDictionary(self):
import dictLangDialog
dialog = dictLangDialog.DictLangDialog()
try:
dialog.show()
lang = dialog.selectedLang
if lang == "United States" and enchant.dict_exists("en_US"):
self.wordlist = enchant.request_dict("en_US")
elif lang == "Chinese" and enchant.dict_exists("zh"):
self.wordlist = enchant.request_dict("zh")
elif lang == "Russian" and enchant.dict_exists("ru"):
self.wordlist = enchant.request_dict("ru")
elif lang == "German" and enchant.dict_exists("de_DE"):
self.wordlist = enchant.request_dict("de_DE")
elif lang == "French" and enchant.dict_exists("fr_FR"):
self.wordlist = enchant.request_dict("fr_FR")
elif lang == "Norwegian" and enchant.dict_exists("no"):
self.wordlist = enchant.request_dict("no")
elif lang == "Zulu" and enchant.dict_exists("zu"):
self.wordlist = enchant.request_dict("zu")
elif lang == "Arabic" and enchant.dict_exists("ar"):
self.wordlist = enchant.request_dict("ar")
elif lang == "Hindi" and enchant.dict_exists("hi"):
self.wordlist = enchant.request_dict("hi")
elif lang == "British" and enchant.dict_exists("en_GB"):
self.wordlist = enchant.request_dict("en_GB")
except:
self.wordlist = enchant.request_dict("en_GB")
def toggleSpellcheck(self, v):
self.spellcheck = v
if enchant and self.spellcheck and not self._dict:
if self.currentDict and enchant.dict_exists(self.currentDict):
self._dict = enchant.Dict(self.currentDict)
elif enchant.get_default_language() and enchant.dict_exists(enchant.get_default_language()):
self._dict = enchant.Dict(enchant.get_default_language())
else:
self.spellcheck = False
if self.highlighter:
self.highlighter.rehighlight()
else:
self.spellcheck = False
def _initialize(self):
"""
@raise ImportError: if pyenchant is not installed
@raise enchant.Error: if no default dictionary exists
"""
# lazy import for catching import exceptions on missing Enchant
import enchant
import enchant.checker
import enchant.tokenize
# select a dictionary
language = str(self._preferences.get("SpellCheckDictionary", ""))
if len(language) > 0 and enchant.dict_exists(language):
self._dictionary = enchant.Dict(language)
else:
# try to use default language (may raise enchant.Error)
self._dictionary = enchant.Dict()
language = self._dictionary.tag
self._log.debug("Using dictionary '%s'" % language)
# create a spellchecker that is aware of email addresses and URLs
self._checker = enchant.checker.SpellChecker(language, filters=[enchant.tokenize.EmailFilter, enchant.tokenize.URLFilter])
self._initialized = True
def _initialize(self):
"""
@raise ImportError: if pyenchant is not installed
@raise enchant.Error: if no default dictionary exists
"""
# lazy import for catching import exceptions on missing Enchant
import enchant
import enchant.checker
import enchant.tokenize
# select a dictionary
language = str(self._preferences.get("SpellCheckDictionary", ""))
if len(language) > 0 and enchant.dict_exists(language):
self._dictionary = enchant.Dict(language)
else:
# try to use default language (may raise enchant.Error)
self._dictionary = enchant.Dict()
language = self._dictionary.tag
self._log.debug("Using dictionary '%s'" % language)
# create a spellchecker that is aware of email addresses and URLs
self._checker = enchant.checker.SpellChecker(
language,
filters=[enchant.tokenize.EmailFilter, enchant.tokenize.URLFilter])
self._initialized = True
def initSpellchecker(self):
# TODO: disable spellchecker icon in case of not working enchant
try:
import enchant
spellDictDir = settings.get('spellchecker:directory')
if spellDictDir:
if enchant.__ver_major__ >= 1 and enchant.__ver_minor__ >= 6:
enchant.set_param("enchant.myspell.dictionary.path",
spellDictDir)
else:
print "Your pyenchant version is to old. Please " \
"upgrade to version 1.6.0 or higher, if you want " \
"to use spellchecker."
return None
spellLang = settings.get('spellchecker:lang')
if enchant.dict_exists(spellLang):
self.dict = enchant.Dict(spellLang)
else:
# try dictionary based on the current locale
try:
self.dict = enchant.Dict()
settings.set('spellchecker:lang', self.dict.tag)
except: # we don not have working dictionary...
return None
if self.dict:
self.usePWL(self.dict)
except:
print "can not start spellchecker!!!"
import traceback
traceback.print_exc()
return None
def __init__(self, name):
self._lang = name
if not (self._lang and enchant.dict_exists(self._lang)):
self._lang = self.getDefaultDictionary()
self._dict = enchant.DictWithPWL(self._lang,
self.getCustomDictionaryPath())
def spell_check(request):
"""
Returns a HttpResponse that implements the TinyMCE spellchecker protocol.
"""
try:
import enchant
raw = request.raw_post_data
input = json.loads(raw)
id = input["id"]
method = input["method"]
params = input["params"]
lang = params[0]
arg = params[1]
if not enchant.dict_exists(str(lang)):
raise RuntimeError("dictionary not found for language '%s'" % lang)
checker = enchant.Dict(str(lang))
if method == "checkWords":
result = [word for word in arg if not checker.check(word)]
elif method == "getSuggestions":
result = checker.suggest(arg)
else:
raise RuntimeError("Unkown spellcheck method: '%s'" % method)
output = {"id": id, "result": result, "error": None}
except Exception:
logging.exception("Error running spellchecker")
return HttpResponse(_("Error running spellchecker"))
return HttpResponse(json.dumps(output), content_type="application/json")
def aspell(string):
'''
если ok: False, []
если ошибка: True, aspell_sug
'''
enchant.set_param("enchant.aspell.dictionary.path",
"./aspell6-ru-0.99f7-1")
if not enchant.dict_exists('ru_RU'):
copyfile(
'./resources/aspell/ru_RU.dic',
os.path.dirname(enchant.__file__).replace('\\', '/') +
'/share/enchant/myspell/ru_RU.dic')
copyfile(
'./resources/aspell/ru_RU.aff',
os.path.dirname(enchant.__file__).replace('\\', '/') +
'/share/enchant/myspell/ru_RU.aff')
d = enchant.Dict("ru_RU")
if d.check(string): # aspell says OK
# print('aspell says OK')
return False, []
else:
# print('aspell says mistake and suggests:')
aspell_sug = d.suggest(string)
return True, aspell_sug
def spell_check(request):
"""
Returns a HttpResponse that implements the TinyMCE spellchecker protocol.
"""
try:
import enchant
raw = request.raw_post_data
input = simplejson.loads(raw)
id = input['id']
method = input['method']
params = input['params']
lang = params[0]
arg = params[1]
if not enchant.dict_exists(str(lang)):
raise RuntimeError("dictionary not found for language '%s'" % lang)
checker = enchant.Dict(lang)
if method == 'checkWords':
result = [word for word in arg if not checker.check(word)]
elif method == 'getSuggestions':
result = checker.suggest(arg)
else:
raise RuntimeError("Unkown spellcheck method: '%s'" % method)
output = {
'id': id,
'result': result,
'error': None,
}
except Exception:
logging.exception("Error running spellchecker")
return HttpResponse(_("Error running spellchecker"))
return HttpResponse(simplejson.dumps(output),
content_type='application/json')
def spellcheck(request):
"""
Returns a HttpResponse that implements the TinyMCE spellchecker protocol.
"""
try:
raw = request.raw_post_data
input = json.loads(raw)
id = input['id']
method = input['method']
params = input['params']
lang = params[0]
arg = params[1]
if not enchant.dict_exists(str(lang)):
raise RuntimeError("dictionary not found for language '%s'" % lang)
checker = enchant.Dict(str(lang))
if method == 'checkWords':
result = [word for word in arg if word and not checker.check(word)]
elif method == 'getSuggestions':
result = checker.suggest(arg)
else:
raise RuntimeError("Unkown spellcheck method: '%s'" % method)
output = {
'id': id,
'result': result,
'error': None,
}
except Exception:
return HttpResponse("Error running spellchecker")
return HttpResponse(json.dumps(output),
content_type='application/json')
def initSpellchecker(self):
# TODO: disable spellchecker icon in case of not working enchant
try:
import enchant
spellDictDir = settings.get('spellchecker:directory')
if spellDictDir:
if enchant.__ver_major__ >= 1 and enchant.__ver_minor__ >= 6:
enchant.set_param("enchant.myspell.dictionary.path",
spellDictDir)
else:
print "Your pyenchant version is to old. Please " \
"upgrade to version 1.6.0 or higher, if you want " \
"to use spellchecker."
return None
spellLang = settings.get('spellchecker:lang')
if enchant.dict_exists(spellLang):
self.dict = enchant.Dict(spellLang)
else:
# try dictionary based on the current locale
try:
self.dict = enchant.Dict()
settings.set('spellchecker:lang', self.dict.tag)
except: # we don not have working dictionary...
return None
if self.dict:
self.usePWL(self.dict)
except:
print "can not start spellchecker!!!"
import traceback
traceback.print_exc()
return None
def __init__(self,
languages=('en_US', ),
unicode_data=True,
cldr_data=True,
quick=True):
'''
Initialize the emoji matcher
:param languages: A list of languages to use for matching emoji
:type languages: List or tuple of strings
:param unicode_data: Whether to load the UnicodeData.txt file as well
:type unicode_data: Boolean
:param cldr_data: Whether to load data from CLDR as well
:type cldr_data: Boolean
:param quick: Whether to do a quicker but slighly less precise match.
Quick matching is about 4 times faster and usually
good enough.
:type quick: Boolean
'''
self._languages = languages
self._quick = quick
self._enchant_dicts = []
if IMPORT_ENCHANT_SUCCESSFUL:
for language in self._languages:
if enchant.dict_exists(language):
self._enchant_dicts.append(enchant.Dict(language))
# From the documentation
# (https://docs.python.org/3.6/library/difflib.html):
# “SequenceMatcher computes and caches detailed information
# about the second sequence, so if you want to compare one
# sequence against many sequences, use set_seq2() to set the
# commonly used sequence once and call set_seq1() repeatedly,
# once for each of the other sequences.”
self._matcher = SequenceMatcher(isjunk=None,
a='',
b='',
autojunk=False)
self._match_cache = {}
self._string1 = ''
self._seq1 = ''
self._len1 = 0
self._string2 = ''
self._string2_number_of_words = 0
self._string2_word_list = []
self._seq2 = ''
self._len2 = 0
self._emoji_dict = {}
self._candidate_cache = {}
# The three data sources are loaded in this order on purpose.
# The data from Unicode is loaded first to put the official
# names first into the list of names to display the official
# names in the candidates, if possible. The second best names
# are the long names of emojione.
if unicode_data:
self._load_unicode_data()
self._load_emojione_data()
if cldr_data:
for language in _expand_languages(self._languages):
self._load_cldr_annotation_data(language)
def __init__(self, language="en_US"):
if not enchant.dict_exists(language):
logging.warning("Spelling_Corrector: Don't have {} , Please check it!!!", language)
logging.warning("Recommend same language for you: {}", enchant.list_languages())
language = "en_US"
self.dict = enchant.Dict(language)
self.check = SpellChecker(language)
self.tokenizer = get_tokenizer(language)
def addspell(self, channel, sender, line):
words = line.split()
if enchant.dict_exists(words[0]):
d = enchant.Dict(words.pop(0))
else:
d = enchant.Dict('en')
for i in words:
d.add(i)
def clean_ques(ques): ques = ques.lower() ques = tokenizer.tokenize(ques) for i in range(len(ques)): if not enchant.dict_exists(ques[i]): ques[i] = dictionary.suggest(ques[i])[0] #ques = [q for q in ques if q not in stop] ques = [stemmer.stem(q) for q in ques if q not in stop] return ques
def __init__(self,language):
'''
Constructor
'''
if enchant.dict_exists(language):
self.dictionnary = enchant.Dict(language)
else:
availableDicos = '[%s]' % ', '.join(map(str, enchant.list_languages()))
sys.exit("No dictionary installed for {}, the available dictionaries are: {}".format(language,availableDicos))
def clean_ques(ques):
ques = ques.lower()
ques = tokenizer.tokenize(ques)
for i in range(len(ques)):
if not enchant.dict_exists(ques[i]):
ques[i] = dictionary.suggest(ques[i])[0]
#ques = [q for q in ques if q not in stop]
ques = [stemmer.stem(q) for q in ques if q not in stop]
return ques
def spell_check(request):
"""
Returns a HttpResponse that implements the TinyMCE spellchecker protocol.
"""
try:
if not enchant:
raise RuntimeError("install pyenchant for spellchecker functionality")
raw = force_text(request.body)
raw = force_text(request.body)
try:
input = json.loads(raw)
id = input['id']
method = input['method']
params = input['params']
lang = params[0]
arg = params[1]
except ValueError:
data = QueryDict(raw.encode('utf8'))
method = data.get('method')
text = data.get('text')
lang = data.get('lang')
if not enchant.dict_exists(str(lang)):
raise RuntimeError("dictionary not found for language {!r}".format(lang))
checker = enchant.Dict(str(lang))
if method == 'spellcheck':
res = {}
for word in text.split():
tmp = word.encode('utf8').strip()
if tmp == '':
continue
if not checker.check(tmp):
res[tmp] = checker.suggest(tmp)
output = dict(words=res)
else:
if method == 'checkWords':
result = [word for word in arg if word and not checker.check(word)]
elif method == 'getSuggestions':
result = checker.suggest(arg)
else:
raise RuntimeError("Unknown spellcheck method: {!r}".format(method))
output = {
'id': id,
'result': result,
'error': None,
}
except Exception:
logging.exception("Error running spellchecker")
return HttpResponse(_("Error running spellchecker"))
return HttpResponse(json.dumps(output),
content_type='application/json')
def set_dict(self, tag):
if tag:
logger.info('Setting dictionary %s', tag)
if tag and enchant and enchant.dict_exists(tag):
self.dict = enchant.Dict(tag)
else:
if tag:
logger.warning('Failed to set dictionary %s', tag)
self.dict = None
self.config_store.set('spelling', 'language', self.current_language())
self.new_dict.emit()
def set_dict(self, tag):
if tag:
logger.info('Setting dictionary %s', tag)
if tag and enchant and enchant.dict_exists(tag):
self.dict = enchant.Dict(tag)
else:
if tag:
logger.warning('Failed to set dictionary %s', tag)
self.dict = None
self.config_store.set('spelling', 'language', self.current_language())
self.new_dict.emit()
def loadDicts():
global text_dic, en_dic
en_dic = en.Dict("ru_RU")
if en.dict_exists("ru_RU"):
if os.path.exists(os.path.expanduser('~/.ExPy/dict.txt')):
buf_dic = en.DictWithPWL("ru_RU",os.path.expanduser('~/.ExPy/dict.txt'))
text_dic = SpellChecker(buf_dic, filters=[EmailFilter,URLFilter])
else:
text_dic = SpellChecker("ru_RU", filters=[EmailFilter,URLFilter])
else:
QtGui.QMessageBox.information(None,
"Не обнаружен словарь", "Не обнаружен русский словарь Hunspell, проверка орфографии невозможна")
def set_dict(self, tag):
if not bool(enchant):
self.dict = None
elif tag and enchant.dict_exists(tag):
self.dict = enchant.Dict(tag)
else:
self.dict = None
if self.dict:
self.tag = self.dict.tag
else:
self.tag = ''
self.new_dict.emit()
def init_language(self):
'''Init self.language.'''
c = self.c
language = g.toUnicode(c.config.getString('enchant_language'))
if language:
try:
ok = enchant.dict_exists(language)
except Exception:
ok = False
if not ok:
g.warning('Invalid language code for Enchant', repr(language))
g.es_print('Using "en_US" instead')
language = 'en_US'
self.language = language
def getDefaultDictionary():
if not EnchantDictionary.isInstalled():
return None
default_locale = enchant.get_default_language()
if default_locale and not enchant.dict_exists(default_locale):
default_locale = None
if default_locale is None:
default_locale = QLocale.system().name()
if default_locale is None:
default_locale = self.availableDictionaries()[0]
return default_locale
def set_language(self, code):
if code:
logger.debug('Setting dictionary %s', code)
self.dict = None
if Gspell:
if code:
self.dict = Gspell.Checker.new(Gspell.Language.lookup(code))
elif enchant:
if code and enchant.dict_exists(code):
self.dict = enchant.Dict(code)
if code and not self.dict:
logger.warning('Failed to set dictionary %s', code)
self.config_store.set('spelling', 'language', self.current_language())
self.new_dict.emit()
def init_language(self):
"""Init self.language."""
c = self.c
language = g.checkUnicode(c.config.getString('enchant-language'))
if language:
try:
ok = enchant.dict_exists(language)
except Exception:
ok = False
if not ok:
g.warning('Invalid language code for Enchant', repr(language))
g.es_print('Using "en_US" instead')
g.es_print('Use @string enchant_language to specify your language')
language = 'en_US'
self.language = language
def init_language(self):
'''Init self.language.'''
c = self.c
language = g.toUnicode(c.config.getString('enchant_language'))
if language:
try:
ok = enchant.dict_exists(language)
except Exception:
ok = False
if not ok:
g.warning('Invalid language code for Enchant', repr(language))
g.es_print('Using "en_US" instead')
g.es_print('Use @string enchant_language to specify your language')
language = 'en_US'
self.language = language
def loadDicts():
global text_dic, en_dic
en_dic = en.Dict("ru_RU")
if en.dict_exists("ru_RU"):
if os.path.exists(os.path.expanduser('~/.ExPy/dict.txt')):
buf_dic = en.DictWithPWL("ru_RU",
os.path.expanduser('~/.ExPy/dict.txt'))
text_dic = SpellChecker(buf_dic, filters=[EmailFilter, URLFilter])
else:
text_dic = SpellChecker("ru_RU", filters=[EmailFilter, URLFilter])
else:
QtGui.QMessageBox.information(
None, "Не обнаружен словарь",
"Не обнаружен русский словарь Hunspell, проверка орфографии невозможна"
)
def spell_check(self, post, lang):
""" Check spellings for the given post and given language. """
if enchant.dict_exists(lang):
checker = SpellChecker(lang, filters=[EmailFilter, URLFilter])
checker.set_text(post.text(lang=lang, strip_html=True))
words = [error.word for error in checker]
words = [
word for word in words
if self._not_in_other_dictionaries(word, lang)
]
LOGGER.notice('Mis-spelt words in %s: %s' %
(post.fragment_deps(lang), ', '.join(words)))
else:
LOGGER.notice('No dictionary found for %s' % lang)
def __init__(self, c):
"""Ctor for EnchantClass class."""
self.c = c
language = g.toUnicode(c.config.getString("enchant_language"))
# Set the base language
if language and not enchant.dict_exists(language):
g.warning("Invalid language code for Enchant", repr(language))
g.es_print('Using "en_US" instead')
language = "en_US"
# Compute fn, the full path to the local dictionary.
fn = c.config.getString("enchant_local_dictionary")
if not fn:
fn = g.os_path_finalize_join(g.app.loadDir, "..", "plugins", "spellpyx.txt")
# Fix bug https://github.com/leo-editor/leo-editor/issues/108
if not g.os_path_exists(fn):
fn = g.os_path_finalize_join(g.app.homeDir, ".leo", "spellpyx.txt")
self.open_dict(fn, language)
def __init__(self, c):
"""Ctor for EnchantClass class."""
self.c = c
language = g.toUnicode(c.config.getString('enchant_language'))
# Set the base language
if language and not enchant.dict_exists(language):
g.warning('Invalid language code for Enchant', repr(language))
g.es_print('Using "en_US" instead')
language = 'en_US'
# Compute fn, the full path to the local dictionary.
fn = c.config.getString('enchant_local_dictionary')
if not fn:
fn = g.os_path_finalize_join(g.app.loadDir, "..", "plugins", 'spellpyx.txt')
# Fix bug https://github.com/leo-editor/leo-editor/issues/108
if not g.os_path_exists(fn):
fn = g.os_path_finalize_join(g.app.homeDir, '.leo', 'spellpyx.txt')
self.open_dict(fn, language)
def __init__(self, c):
"""Ctor for EnchantClass class."""
# pylint: disable=super-init-not-called
self.c = c
language = g.toUnicode(c.config.getString('enchant_language'))
# Set the base language
if language and not enchant.dict_exists(language):
g.warning('Invalid language code for Enchant', repr(language))
g.es_print('Using "en_US" instead')
language = 'en_US'
# Compute fn, the full path to the local dictionary.
fn = c.config.getString('enchant_local_dictionary')
if not fn:
fn = g.os_path_finalize_join(g.app.loadDir, "..", "plugins", 'spellpyx.txt')
# Fix bug https://github.com/leo-editor/leo-editor/issues/108
if not g.os_path_exists(fn):
fn = g.os_path_finalize_join(g.app.homeDir, '.leo', 'spellpyx.txt')
self.open_dict(fn, language)
def spell_check(self, post, lang):
""" Check spellings for the given post and given language. """
if enchant.dict_exists(lang):
checker = SpellChecker(lang, filters=[EmailFilter, URLFilter])
checker.set_text(post.text(lang=lang, strip_html=True))
words = [error.word for error in checker]
words = [
word for word in words if
self._not_in_other_dictionaries(word, lang)
]
LOGGER.notice(
'Mis-spelt words in %s: %s' % (
post.fragment_deps(lang), ', '.join(words)
)
)
else:
LOGGER.notice('No dictionary found for %s' % lang)
def spell_check(request):
"""
Returns a response that implements the TinyMCE spellchecker protocol.
"""
try:
if not enchant:
raise RuntimeError("install pyenchant for spellchecker functionality")
method = request.POST.get("method")
text = request.POST.get("text")
lang = request.POST.get("lang")
if not enchant.dict_exists(lang):
e_msg = f"Dictionary not found for language '{lang}', check pyenchant."
raise RuntimeError(e_msg)
checker = enchant.Dict(lang)
def sanitize_words(text):
"""
Sanitize words in text and recommend suggestions for wrong words.
"""
suggested_words = {}
words = text.split()
for word in words:
word.strip()
word.strip(".,:;'\"")
if not checker.check(word):
suggested_words[word] = checker.suggest(word)
return suggested_words
if method == "spellcheck":
output = {"words": sanitize_words(text)}
else:
e_msg = f"Got an unexpected method '{method}'"
raise RuntimeError(e_msg)
except Exception as err:
logging.exception("Error running spellchecker")
output = {"error": str(err)}
return JsonResponse(output)
def spell(inp):
"spell <word> -- Check spelling of <word>."
if ' ' in inp:
return "This command only supports one word at a time."
if not enchant.dict_exists(locale):
return "Could not find dictionary: "
dictionary = enchant.Dict(locale)
is_correct = dictionary.check(inp)
suggestions = dictionary.suggest(inp)
s_string = ', '.join(suggestions[:10])
if is_correct:
return '"{}" appears to be \x02valid\x02! ' \
'(suggestions: {})'.format(inp, s_string)
else:
return '"{}" appears to be \x02invalid\x02! ' \
'(suggestions: {})'.format(inp, s_string)
def spell(self, channel, sender, line):
if len(line.split()) == 2:
lang, word = line.split()
try:
d = enchant.Dict(lang)
except enchant.errors.DictNotFoundError:
return 'Languages: ' + ', '.join(enchant.list_languages())
return sugg(d, word)
if len(line.split()) == 1:
d = enchant.Dict('en_US')
return sugg(d, line)
if not line:
return 'Usage: [language] {<word for suggestions> | <sentence>}'
words = line.split()
if enchant.dict_exists(words[0]):
c = enchant.checker.SpellChecker(words.pop(0))
else:
c = enchant.checker.SpellChecker('en_US')
c.set_text(' '.join(words))
return 'Unknown words: ' + ', '.join([i.word for i in c])
def spell(inp):
"spell <word> -- Check spelling of <word>."
if ' ' in inp:
return "This command only supports one word at a time."
if not enchant.dict_exists(locale):
return "Could not find dictionary: {}".format(locale)
dictionary = enchant.Dict(locale)
is_correct = dictionary.check(inp)
suggestions = dictionary.suggest(inp)
s_string = ', '.join(suggestions[:10])
if is_correct:
return '"{}" appears to be \x02valid\x02! ' \
'(suggestions: {})'.format(inp, s_string)
else:
return '"{}" appears to be \x02invalid\x02! ' \
'(suggestions: {})'.format(inp, s_string)
def spell_check(request):
"""Spellcheck view."""
import enchant
raw = request.body
input = json.loads(raw)
id = input['id'] if ('id' in input) else None
method = input['method'] if ('method' in input) else {}
params = input['params'] if ('params' in input) else {}
result = {}
try:
if params and method:
lang = params['lang'] if ('lang' in params) else 'en-au'
arg = params['words'] if ('words' in params) else []
if not enchant.dict_exists(str(lang)):
raise RuntimeError("dictionary not found for language '%s'" %
lang)
checker = enchant.Dict(str(lang))
if method == 'spellcheck':
for x in [
word for word in arg
if word and not checker.check(word)
]:
result[x] = checker.suggest(x)
except Exception:
pass
output = {
'id': id,
'result': result,
}
# except Exception:
# logging.exception("Error running spellchecker")
# return HttpResponse("Error running spellchecker")
return HttpResponse(json.dumps(output), content_type='application/json')
def spell_check(request):
"""
Returns a HttpResponse that implements the TinyMCE spellchecker protocol.
"""
try:
if not enchant:
raise RuntimeError(
"install pyenchant for spellchecker functionality")
raw = force_text(request.body)
input = json.loads(raw)
id = input['id']
method = input['method']
params = input['params']
lang = params[0]
arg = params[1]
if not enchant.dict_exists(str(lang)):
raise RuntimeError(
"dictionary not found for language {!r}".format(lang))
checker = enchant.Dict(str(lang))
if method == 'checkWords':
result = [word for word in arg if word and not checker.check(word)]
elif method == 'getSuggestions':
result = checker.suggest(arg)
else:
raise RuntimeError(
"Unknown spellcheck method: {!r}".format(method))
output = {
'id': id,
'result': result,
'error': None,
}
except Exception:
logging.exception("Error running spellchecker")
return HttpResponse(_("Error running spellchecker"))
return HttpResponse(json.dumps(output), content_type='application/json')
def spell_check(request):
"""Spellcheck view."""
import enchant
raw = request.body
input = json.loads(raw)
id = input['id'] if ('id' in input) else None
method = input['method'] if ('method' in input) else {}
params = input['params'] if ('params' in input) else {}
result = {}
try:
if params and method:
lang = params['lang'] if ('lang' in params) else 'en-au'
arg = params['words'] if ('words' in params) else []
if not enchant.dict_exists(str(lang)):
raise RuntimeError(
"dictionary not found for language '%s'" % lang)
checker = enchant.Dict(str(lang))
if method == 'spellcheck':
for x in [word for word in arg if word and not
checker.check(word)]:
result[x] = checker.suggest(x)
except Exception:
pass
output = {
'id': id,
'result': result,
}
# except Exception:
# logging.exception("Error running spellchecker")
# return HttpResponse("Error running spellchecker")
return HttpResponse(json.dumps(output), content_type='application/json')
def spell(inp):
"""spell <word/sentence> -- Check spelling of a word or sentence."""
if not enchant.dict_exists(locale):
return "Could not find dictionary: {}".format(locale)
if len(inp.split(" ")) > 1:
# input is a sentence
checker = SpellChecker(locale)
checker.set_text(inp)
offset = 0
for err in checker:
# find the location of the incorrect word
start = err.wordpos + offset
finish = start + len(err.word)
# get some suggestions for it
suggestions = err.suggest()
s_string = '/'.join(suggestions[:3])
s_string = "\x02{}\x02".format(s_string)
# calculate the offset for the next word
offset = (offset + len(s_string)) - len(err.word)
# replace the word with the suggestions
inp = inp[:start] + s_string + inp[finish:]
return inp
else:
# input is a word
dictionary = enchant.Dict(locale)
is_correct = dictionary.check(inp)
suggestions = dictionary.suggest(inp)
s_string = ', '.join(suggestions[:10])
if is_correct:
return '"{}" appears to be \x02valid\x02! ' \
'(suggestions: {})'.format(inp, s_string)
else:
return '"{}" appears to be \x02invalid\x02! ' \
'(suggestions: {})'.format(inp, s_string)
def spell_check(request):
"""
Returns a HttpResponse that implements the TinyMCE spellchecker protocol.
"""
try:
if not enchant:
raise RuntimeError("install pyenchant for spellchecker functionality")
raw = force_text(request.body)
input = json.loads(raw)
id = input['id']
method = input['method']
params = input['params']
lang = params[0]
arg = params[1]
if not enchant.dict_exists(str(lang)):
raise RuntimeError("dictionary not found for language {!r}".format(lang))
checker = enchant.Dict(str(lang))
if method == 'checkWords':
result = [word for word in arg if word and not checker.check(word)]
elif method == 'getSuggestions':
result = checker.suggest(arg)
else:
raise RuntimeError("Unknown spellcheck method: {!r}".format(method))
output = {
'id': id,
'result': result,
'error': None,
}
except Exception:
logging.exception("Error running spellchecker")
return HttpResponse(_("Error running spellchecker"))
return HttpResponse(json.dumps(output),
content_type='application/json')
def spell_check(request):
"""
Returns a HttpResponse that implements the TinyMCE spellchecker protocol.
"""
try:
if not enchant:
raise RuntimeError(
"install pyenchant for spellchecker functionality")
raw = force_text(request.body)
input = json.loads(raw)
id = input["id"]
method = input["method"]
params = input["params"]
lang = params[0]
arg = params[1]
if not enchant.dict_exists(str(lang)):
raise RuntimeError(f"dictionary not found for language {lang}")
checker = enchant.Dict(str(lang))
if method == "checkWords":
result = [word for word in arg if word and not checker.check(word)]
elif method == "getSuggestions":
result = checker.suggest(arg)
else:
raise RuntimeError(f"Unknown spellcheck method: {method}")
output = {
"id": id,
"result": result,
"error": None,
}
except Exception:
logging.exception("Error running spellchecker")
return HttpResponse(_("Error running spellchecker"))
return HttpResponse(json.dumps(output), content_type="application/json")
def spell(inp):
"""spell <word/sentence> -- Check spelling of a word or sentence."""
if not enchant.dict_exists(locale):
return "Could not find dictionary: {}".format(locale)
if len(inp.split(" ")) > 1:
# input is a sentence
chkr = SpellChecker(locale)
chkr.set_text(inp)
offset = 0
for err in chkr:
# find the location of the incorrect word
start = err.wordpos + offset
finish = start + len(err.word)
# get some suggestions for it
suggestions = err.suggest()
s_string = '/'.join(suggestions[:3])
s_string = "\x02{}\x02".format(s_string)
# calculate the offset for the next word
offset = (offset + len(s_string)) - len(err.word)
# replace the word with the suggestions
inp = inp[:start] + s_string + inp[finish:]
return inp
else:
# input is a word
dictionary = enchant.Dict(locale)
is_correct = dictionary.check(inp)
suggestions = dictionary.suggest(inp)
s_string = ', '.join(suggestions[:10])
if is_correct:
return '"{}" appears to be \x02valid\x02! ' \
'(suggestions: {})'.format(inp, s_string)
else:
return '"{}" appears to be \x02invalid\x02! ' \
'(suggestions: {})'.format(inp, s_string)
import os
from django.conf import settings
from django.contrib.staticfiles import finders
import enchant
enchant.dict_exists('pl')
DEFAULT_CONFIG = getattr(
settings, 'TINYMCE_DEFAULT_CONFIG', {
'plugins': "spellchecker",
'theme': "advanced",
'toolbar': "undo redo | styleselect | bold italic | link image",
'relative_urls': False,
'width': '100%',
'height': 500,
})
USE_SPELLCHECKER = getattr(settings, 'TINYMCE_SPELLCHECKER', True)
USE_COMPRESSOR = getattr(settings, 'TINYMCE_COMPRESSOR', False)
INCLUDE_JQUERY = getattr(settings, 'TINYMCE_INCLUDE_JQUERY', True)
USE_EXTRA_MEDIA = getattr(settings, 'TINYMCE_EXTRA_MEDIA', None)
USE_FILEBROWSER = getattr(settings, 'TINYMCE_FILEBROWSER', 'filebrowser'
in settings.INSTALLED_APPS)
if 'staticfiles' in settings.INSTALLED_APPS or 'django.contrib.staticfiles' in settings.INSTALLED_APPS:
JS_URL = getattr(settings, 'TINYMCE_JS_URL',
"""
Django settings for CompeteFashion project.
Generated by 'django-admin startproject' using Django 1.9.5.
For more information on this file, see
https://docs.djangoproject.com/en/1.9/topics/settings/
For the full list of settings and their values, see
https://docs.djangoproject.com/en/1.9/ref/settings/
"""
import os
import enchant
enchant.dict_exists('en')
# Build paths inside the project like this: os.path.join(BASE_DIR, ...)
BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
TEMPLATE_PATH = os.path.join(BASE_DIR, 'templates')
STATIC_PATH = os.path.join(BASE_DIR, 'static')
SITE_ID = 1
# Quick-start development settings - unsuitable for production
# See https://docs.djangoproject.com/en/1.9/howto/deployment/checklist/
# SECURITY WARNING: keep the secret key used in production secret!
SECRET_KEY = 'eiyn&c$k!k@7z+clovku%o_)rp5u0en!_=tr=^!=h$_tv6*awu'
# SECURITY WARNING: don't run with debug turned on in production!
DEBUG = True
ALLOWED_HOSTS = []
def check_collection(inpath, outpath, lang, wordFiles=[]):
"""
Checks the orthography of the text in a collection. The expected input are plain text files.
Arguments:
inpath (string): path to the input files, including file name pattern
outpath (string): path to the output file, including the output file's name
lang (string): which dictionary to use, e.g. "es", "fr", "de"
wordFiles (list): optional; list of strings; paths to files with lists of words which will not be treated as errors (e.g. named entities)
"""
try:
enchant.dict_exists(lang)
try:
tknzr = get_tokenizer(lang)
except enchant.errors.TokenizerNotFoundError:
tknzr = get_tokenizer()
chk = checker.SpellChecker(lang, tokenize=tknzr)
except enchant.errors.DictNotFoundError:
print("ERROR: The dictionary " + lang + "doesn't exist. Please choose another dictionary.")
sys.exit(0)
all_words = []
all_num = []
all_idnos = []
print("...checking...")
for file in glob.glob(inpath):
idno = os.path.basename(file)[-10:-4]
all_idnos.append(idno)
err_words = []
with open(file, "r", encoding="UTF-8") as fin:
intext = fin.read().lower()
chk.set_text(intext)
if len(wordFiles) !=0:
allCorrects = ""
for file in wordFiles:
with open(file, "r", encoding="UTF-8") as f:
corrects = f.read().lower()
allCorrects = allCorrects + corrects
for err in chk:
if not wordFiles or err.word not in allCorrects:
err_words.append(err.word)
all_words.append(err_words)
err_num = collections.Counter(err_words)
all_num.append(err_num)
print("..." + str(len(err_num)) + " different errors found in " + idno)
df = pd.DataFrame(all_num,index=all_idnos).T
df = df.fillna(0)
df = df.astype(int)
df["sum"] = df.sum(axis=1)
# df = df.sort("sum", ascending=False)
df = df.sort_values(by="sum", ascending=False)
df.to_csv(outpath)
print("done")
def test_HasENUS():
"""Test that the en_US language is available through default broker."""
assert dict_exists("en_US")
def __init__(self, lang):
import enchant
self.lang = str(lang)
if not enchant.dict_exists(lang):
raise RuntimeError("dictionary not found for language '%s'" % lang)
self.backend = enchant.Dict(lang)
def setDict(self, d):
self.currentDict = d
if d and enchant.dict_exists(d):
self._dict = enchant.Dict(d)
if self.highlighter:
self.highlighter.rehighlight()
def set_language(self, language):
if not enchant.dict_exists(language):
return
self.language = language
self.spellchecker = enchant.Dict(language)
print "Check a mis-spelled word: "
print "\tcheck(\"Helo\"): {}".format(d.check("Helo"))
print "\n"
print "suggest a word:"
print "* ordered from most likely replacement to least likely"
print "\tsuggest(\"Helo\"): {}".format(d.suggest("Helo"))
print "\n"
print "attempt to determine language:"
print "\ttag: {}".format(d.tag)
print "\n"
print "check whether dictionaries exist:"
print "\tenchant.dict_exists(\"en_US\"): {}".format(enchant.dict_exists("en_US"))
print "\tenchant.dict_exists(\"fake\"): {}".format(enchant.dict_exists("fake"))
print "\n"
print "List available dictionaries:"
print "\tenchant.list_languages(): {}".format(enchant.list_languages())
print "\n"
print "Providers:"
print "* Different providers exist using different frameworks: (aspell, MySpell)."
print "\tprovider: {}".format(d.provider)
print "\tprovider.name: {}".format(d.provider.name)
print "\tprovider.file: {}".format(d.provider.file)
print "\n"
print "Brokers:"
def set_language(self, language):
if not enchant.dict_exists(language):
return
self.language = language
self.spellchecker = enchant.Dict(language)
def check_collection(inpath, outpath, lang, wordFiles=[]):
"""
Checks the orthography of the text in a collection. The expected input are plain text files.
Arguments:
inpath (string): path to the input files, including file name pattern
outpath (string): path to the output file, including the output file's name
lang (string): which dictionary to use, e.g. "es", "fr", "de"
wordFiles (list): optional; list of strings; paths to files with lists of words which will not be treated as errors (e.g. named entities)
"""
try:
enchant.dict_exists(lang)
try:
tknzr = get_tokenizer(lang)
except enchant.errors.TokenizerNotFoundError:
tknzr = get_tokenizer()
chk = checker.SpellChecker(lang, tokenize=tknzr)
except enchant.errors.DictNotFoundError:
print("ERROR: The dictionary " + lang +
"doesn't exist. Please choose another dictionary.")
sys.exit(0)
all_words = []
all_num = []
all_idnos = []
print("...checking...")
for file in glob.glob(inpath):
idno, ext = os.path.basename(file).split(".")
all_idnos.append(idno)
err_words = []
with open(file, "r", encoding="UTF-8") as fin:
intext = fin.read().lower()
chk.set_text(intext)
if len(wordFiles) != 0:
allCorrects = ""
for file in wordFiles:
with open(file, "r", encoding="UTF-8") as f:
corrects = f.read().lower()
allCorrects = allCorrects + corrects
for err in chk:
if not wordFiles or err.word not in allCorrects:
err_words.append(err.word)
all_words.append(err_words)
err_num = collections.Counter(err_words)
all_num.append(err_num)
print("..." + str(len(err_num)) + " different errors found in " + idno)
df = pd.DataFrame(all_num, index=all_idnos).T
df = df.fillna(0)
df = df.astype(int)
df["sum"] = df.sum(axis=1)
# df = df.sort("sum", ascending=False)
df = df.sort_values(by="sum", ascending=False)
df.to_csv(outpath)
print("done")
