def query(self, query):
""" return raw result (dict) """
cons = {
"meaning": [],
"synonym": [],
"antonym": [],
"usage_example": [],
"part of speech": []
}
meanings = vb.meaning(query, format="list")
if meanings:
cons["meaning"] = [
e.replace("<i>",
"").replace("</i>",
"").replace("[i]",
"").replace("[/i]", "")
for e in meanings
]
synonyms = vb.synonym(query, format="list")
if synonyms:
cons["synonym"] = synonyms
antonyms = vb.antonym(query, format="list")
if antonyms:
cons["antonym"] = antonyms
ps = vb.part_of_speech(query, format="list")
if ps:
cons["part of speech"] = ps
examples = vb.usage_example(query, format="list")
if examples:
cons["usage_example"] = [
e.replace("[", "").replace("]", "") for e in examples
]
return cons
def get_classification(word):
full_meaning = vb.part_of_speech(word, format='dict')
classification = None
if full_meaning:
classification = full_meaning[0]['text']
if classification is None:
classification = ''
return classification
def validateWordThoroughly(word):
partOfSpeech = vb.part_of_speech(word)
# Hack: If a part of speech was found, then we know this is a valid word.
# TODO - add a check here to remove words that invalid by my family's
# rules (i.e. proper nouns)
if (partOfSpeech):
return True
return False
def get_dictionary(subject):
cons = {"meaning": [], "synonym": [], "antonym": [], "example": [], "part of speech": []}
meanings = vb.meaning(subject, format="list")
if meanings:
cons["meaning"] = [e.replace("<i>", "").replace("</i>", "").replace("[i]", "") .replace("[/i]", "") for e in meanings]
synonyms = vb.synonym(subject, format="list")
if synonyms:
cons["synonym"] = synonyms
antonyms = vb.antonym(subject, format="list")
if antonyms:
cons["antonym"] = antonyms
ps = vb.part_of_speech(subject, format="list")
if ps:
cons["part of speech"] = ps
examples = vb.usage_example(subject, format="list")
if examples:
cons["example"] = [e.replace("[", "").replace("]", "") for e in examples]
return cons
def parse_in_ids(all_books):
cur_id = 0
words_idd = 0
alls = set()
for book in all_books:
for word in book[0]:
alls.add(word)
print(len(alls))
for book in all_books:
for word in book[0]:
if word not in all_ids:
if words_idd % 100 == 0:
print("ID'd the first " + str(words_idd) + " words")
words_idd += 1
try:
def_of_word = vb.part_of_speech(word)
if def_of_word is None or def_of_word is False:
all_ids[word] = -1
continue
def_of_word = json.loads(def_of_word)
except:
def_of_word = [{"text": None}]
for elt in def_of_word:
types = elt['text']
break
if types in all_word_types:
all_ids[word] = all_word_types[types]
else:
all_word_types[types] = cur_id
cur_id += 1
all_ids[word] = all_word_types[types]
pickle.dump(all_ids, open("ids.txt", "wb"))
try:
pickle.dump(all_ids, "ids.txt")
except:
print("didn't work")
print(len(all_ids))
print(all_ids)
def test_partOfSpeech_found(self, mock_api_call):
res = [{
"word": "hello",
"partOfSpeech": "interjection",
"text": "greeting"
}, {
"word": "hello",
"partOfSpeech": "verb-intransitive",
"text": "To call."
}]
mock_api_call.return_value = mock.Mock()
mock_api_call.return_value.status_code = 200
mock_api_call.return_value.json.return_value = res
expected_result = '[{"text": "interjection", "example": "greeting", "seq": 0}, {"text": "verb-intransitive", "example": "To call.", "seq": 1}]'
result = vb.part_of_speech("hello")
if sys.version_info[:2] <= (2, 7):
self.assertItemsEqual(expected_result, result)
else:
self.assertCountEqual(expected_result, result)
def test_partOfSpeech_not_found(self, mock_api_call):
mock_api_call.return_value = mock.Mock()
mock_api_call.return_value.status_code = 404
self.assertFalse(vb.part_of_speech("hello"))
from find_article import findarticle
from vocabulary.vocabulary import Vocabulary as vb
from random import randint
list_of_words = findarticle("Barack")[1].split(
) # Imports the article and splits it into list of words
# Does some magic and stores typeofword as the type of word
key_words = {}
word_testing = randint(0, len(list_of_words))
while len(key_words) != 20:
try:
typeofword = vb.part_of_speech(list_of_words[word_testing],
format="list")[0][0]
except TypeError:
typeofword = "False"
if typeofword in [
"preposition",
"interjection",
"conjunction",
"False",
"verb",
"pronoun",
]:
word_testing = randint(0, len(list_of_words))
elif list_of_words[word_testing].lower() in [
"the", "of", "and", "a", "to", "in", "is", "you", "that", "it",
"he", "was", "for", "on", "are", "as", "with", "his", "they", "I",
"at", "be", "this", "have", "from", "or", "one"
]:
def findPOS(word):
try:
return((vb.part_of_speech("difficult").split(',')[1]).split('"text": ')[1])
except:
return None
