def __init__(self, runnable, path, cache_file, only_alpha=False):
self.hunspell = Hunspell(runnable, path)
self._cache_file = cache_file
self.cached_words = {}
if cache_file != None:
self.read_cache()
self.only_alpha = only_alpha
if self.only_alpha is True:
self.alpha_matcher = re.compile("[^\W\d_]+", re.UNICODE)
self.hunspell.start()
class Hunspell_chache_aimed(object):
def __init__(self, runnable, path, cache_file, only_alpha=False):
self.hunspell = Hunspell(runnable, path)
self._cache_file = cache_file
self.cached_words = {}
if cache_file != None:
self.read_cache()
self.only_alpha = only_alpha
if self.only_alpha is True:
self.alpha_matcher = re.compile("[^\W\d_]+", re.UNICODE)
self.hunspell.start()
def read_cache(self):
if not os.path.exists(self._cache_file):
return
for l_utf in open(self._cache_file):
l = l_utf.strip().decode('utf-8')
if len(l.split(' ')) == 1:
self.cached_words[l] = l
if len(l.split(' ')) == 2:
orig, stemmed = l.split(' ')
self.cached_words[orig] = stemmed
def write_cache(self):
with open(self._cache_file, "w") as f:
for tok in self.cached_words:
print 4655555555555555555555
f.write(u'{0} {1}\n'.format(tok,
self.cached_words[tok]).encode('utf-8'))
def cached_stem(self, word):
if self.only_alpha is True:
if self.alpha_matcher.match(word) == None or\
self.alpha_matcher.match(word).group() != word:
return word
if word in self.cached_words:
return self.cached_words[word]
stem = self.hunspell.stem_word(word)
self.cached_words[word] = stem
return stem
class Hunspell_chache_aimed(object):
def __init__(self, runnable, path, cache_file, only_alpha=False):
self.hunspell = Hunspell(runnable, path)
self._cache_file = cache_file
self.cached_words = {}
if cache_file != None:
self.read_cache()
self.only_alpha = only_alpha
if self.only_alpha is True:
self.alpha_matcher = re.compile("[^\W\d_]+", re.UNICODE)
self.hunspell.start()
def read_cache(self):
if not os.path.exists(self._cache_file):
return
for l_utf in open(self._cache_file):
l = l_utf.strip().decode('utf-8')
if len(l.split(' ')) == 1:
self.cached_words[l] = l
if len(l.split(' ')) == 2:
orig, stemmed = l.split(' ')
self.cached_words[orig] = stemmed
def write_cache(self):
with open(self._cache_file, "w") as f:
for tok in self.cached_words:
print 4655555555555555555555
f.write(u'{0} {1}\n'.format(
tok, self.cached_words[tok]).encode('utf-8'))
def cached_stem(self, word):
if self.only_alpha is True:
if self.alpha_matcher.match(word) == None or\
self.alpha_matcher.match(word).group() != word:
return word
if word in self.cached_words:
return self.cached_words[word]
stem = self.hunspell.stem_word(word)
self.cached_words[word] = stem
return stem
def __init__(self, runnable, path, cache_file, only_alpha=False):
self.hunspell = Hunspell(runnable, path)
self._cache_file = cache_file
self.cached_words = {}
if cache_file != None:
self.read_cache()
self.only_alpha = only_alpha
if self.only_alpha is True:
self.alpha_matcher = re.compile("[^\W\d_]+", re.UNICODE)
self.hunspell.start()
