def synsets(self, word, pos=None):
synsets = []
words_file_name = 'all.{}'.format(
self._lang) if pos == None else '{}.{}'.format(pos, self._lang)
with utils.read_file('{}/words/{}'.format(PYIWN_DATA_HOME,
words_file_name)) as fo:
for line in fo:
sp = utils.clean_line(line)
if word == sp[1]:
synset_id = sp[0]
pos = sp[2] if pos == None and len(sp) == 3 else pos
break
synset_file_name = 'all.{}'.format(
self._lang) if pos == None else '{}.{}'.format(pos, self._lang)
with utils.read_file('{}/synsets/{}'.format(PYIWN_DATA_HOME,
synset_file_name)) as fo:
for line in fo:
sp = utils.clean_line(line)
synset_data = utils.synset_data(sp, pos)
if word in synset_data[2]:
synset_id, head_word, lemma_names, pos, gloss, examples = synset_data[
0], synset_data[1], synset_data[2], synset_data[
3], synset_data[4], synset_data[5]
synsets.append(
Synset(synset_id, head_word, lemma_names, pos, gloss,
examples))
return synsets
def ontology_nodes(self):
ontology_node_idx_list = []
with utils.read_file('{}/ontology/map'.format(PYIWN_DATA_HOME)) as fo:
for line in fo:
sp = utils.clean_line(line)
if self._synset_id == int(sp[0]):
ontology_node_idx_list = [int(idx) for idx in sp[1].split(',')]
break
ontology_nodes_list = []
with utils.read_file('{}/ontology/nodes'.format(PYIWN_DATA_HOME)) as fo:
for line in fo:
sp = utils.clean_line(line)
if int(sp[0]) in ontology_node_idx_list:
ontology_nodes_list.append(' '.join(sp[1:]))
return ontology_nodes_list
def all_words(self, pos=None):
words = []
words_file_name = 'all.{}'.format(self._lang) if pos == None else '{}.{}'.format(pos, self._lang)
with utils.read_file('{}/words/{}'.format(PYIWN_DATA_HOME, words_file_name)) as fo:
for line in fo:
sp = utils.clean_line(line)
words.append(sp[1])
return words
def _relations(self, relation):
synset_id_list = []
with utils.read_file('{}/synset_relations/{}.{}'.format(PYIWN_DATA_HOME, relation, self._pos)) as fo:
for line in fo:
sp = utils.clean_line(line)
sp[0] = int(sp[0])
if self._synset_id == sp[0]:
synset_id_list = [int(idx) for idx in sp[1].split(',')]
break
synsets = []
with utils.read_file('{}/synsets/{}.hindi'.format(PYIWN_DATA_HOME, self._pos)) as fo:
for line in fo:
sp = utils.clean_line(line)
if int(sp[0]) in synset_id_list:
synset_data = utils.synset_data(sp, self._pos)
synset_id, head_word, lemma_names, pos, gloss, examples = synset_data[0], synset_data[1], synset_data[2], synset_data[3], synset_data[4], synset_data[5]
synsets.append(Synset(synset_id, head_word, lemma_names, pos, gloss, examples))
return synsets
def all_synsets(self, pos=None):
synsets = []
synset_file_name = 'all.{}'.format(self._lang) if pos == None else '{}.{}'.format(pos, self._lang)
with utils.read_file('{}/synsets/{}'.format(PYIWN_DATA_HOME, synset_file_name)) as fo:
for line in fo:
sp = utils.clean_line(line)
synset_data = utils.synset_data(sp, pos)
synset_id, head_word, lemma_names, pos, gloss, examples = synset_data[0], synset_data[1], synset_data[2], synset_data[3], synset_data[4], synset_data[5]
synsets.append(Synset(synset_id, head_word, lemma_names, pos, gloss, examples))
return synsets
def antonym(self):
antonym_synset_id = -1
with utils.read_file('{}/synset_relations/antonyms'.format(PYIWN_DATA_HOME)) as fo:
for line in fo:
if self._name in line:
antonym_synset_id = int(line.split('\t')[2])
break
synsets = []
with utils.read_file('{}/synsets/{}.hindi'.format(PYIWN_DATA_HOME, self._synset.pos())) as fo:
for line in fo:
sp = utils.clean_line(line)
if int(sp[0]) == antonym_synset_id:
synset_data = utils.synset_data(sp, self._synset.pos())
synset_id, head_word, lemma_names, pos, gloss, examples = synset_data[0], synset_data[1], synset_data[2], synset_data[3], synset_data[4], synset_data[5]
synsets.append(Synset(synset_id, head_word, lemma_names, pos, gloss, examples))
return synsets
def gradation(self):
with utils.read_file('{}/synset_relations/gradation'.format(PYIWN_DATA_HOME)) as fo:
for line in fo:
if str(self._synset.synset_id()) in line:
sp = line.split('\t')
synset_id_list = [int(sp[0]), int(sp[2]), int(sp[4])]
break
synsets = []
with utils.read_file('{}/synsets/{}.hindi'.format(PYIWN_DATA_HOME, self._synset.pos())) as fo:
for line in fo:
sp = utils.clean_line(line)
if int(sp[0]) in synset_id_list:
synset_data = utils.synset_data(sp, self._synset.pos())
synset_id, head_word, lemma_names, pos, gloss, examples = synset_data[0], synset_data[1], synset_data[2], synset_data[3], synset_data[4], synset_data[5]
synsets.append(Synset(synset_id, head_word, lemma_names, pos, gloss, examples))
return {'low': synsets[0], 'medium': synsets[1], 'high': synsets[2]}
