def test_word_guess_category():
"""
Should guess and set the word category
"""
word = Word()
word.word = 'word'
word.save()
assert word.category == 'word'
word = Word()
word.word = 'come up with'
word.save()
assert word.category == 'phrasal_verb'
word = Word()
word.word = 'get over'
word.save()
assert word.category == 'phrasal_verb'
word = Word()
word.word = 'to put it mildly'
word.save()
assert word.category == 'phrase'
def test_saving_and_retrieving_items(self):
word_ = Word()
word_.save()
first_item = Item()
first_item.text = 'kaizen'
first_item.word = word_
first_item.save()
second_item = Item()
second_item.text = 'genki'
second_item.word = word_
second_item.save()
saved_words = Word.objects.first()
self.assertEqual(saved_words, word_)
saved_items = Item.objects.all()
self.assertEqual(2, saved_items.count())
first_saved_item = saved_items[0]
second_saved_item = saved_items[1]
self.assertEqual(first_saved_item.text, 'kaizen')
self.assertEqual(second_saved_item.text, 'genki')
self.assertEqual(first_saved_item.word, word_)
self.assertEqual(second_saved_item.word, word_)
def handle(self, *args, **options):
Word.objects.all().delete()
files_list = [
f for f in listdir(settings.STATIC_AUDIO)
if isfile(join(settings.STATIC_AUDIO, f))
]
for file_path in files_list:
new_word = Word(
word=file_path.split('.')[0],
transcription='[...]',
audio_path=os.path.join(settings.STATIC_AUDIO, file_path),
)
new_word.save()
def handle(self, *args, **options):
with open(path.join(path.dirname(path.abspath(__file__)), 'lexicon'), 'r') as f:
contents = f.readlines()[1:]
contents = map(lambda x: x.split("\t"), contents)
contents = map(lambda x: x + [''] * (10 - len(x)), contents)
words = map(lambda x: Word(
word=x[0],
prefix=x[1],
stem=x[2],
tone=x[3],
POS=x[4],
word_class=x[5],
gloss=x[6],
no=int(x[7]),
note=x[8],
dialect=x[9]
), contents)
Word.objects.bulk_create(words)
words = {}
for row in reader:
word = dict(text=row['Word'], language=english, frequency=int(row['Frequency']))
if word['text'] not in words:
words[word['text']] = word
else:
words[word['text']]['frequency'] += int(word['frequency'])
words = words.values()
words = sorted(words, key=lambda w: w['frequency'], reverse=True)
existing_words_objects = {word.text: word for word in Word.objects.all()}
existing_words_text = [word.text for word in existing_words_objects.values()]
for word in words:
if word['text'] not in existing_words_text:
word['word'] = Word(text=word['text'])
word['word'].save()
else:
word['word'] = existing_words_objects[word['text']]
raw_words = [word['word'] for word in words if word['text'] not in existing_words_text]
for i in range(len(words)):
words[i]['rank'] = i + 1
for word in words:
print(word['rank'], word['text'], word['frequency'])
word_entries = []
for word in words:
word_entry = WordEntry(word=word['word'], language=english, frequency=word['frequency'], rank=word['rank'])
word_entries.append(word_entry)
def _save_data_to_db(word, spelling, raw_json):
new_word = Word()
new_word.value = word
new_word.spelling = spelling
new_word.raw_od_article = raw_json
new_word.save()
line = f.readline() # 每次读取一行
lst = line.split() # 切分成列表
size = len(lst)
if not line:
break
# 至少应含有两项:名称和释义
# 找到第一个释义项的位置,释义一定含有"."因为要指明词汇类型,如"v."
k = 0
for k in range(size):
if lst[k].find(".") != -1:
break
# 从第一个释义项之前的所有项合在一起是name
name = ""
for i in range(k):
if i != 0:
name += " "
name += lst[i]
# 从第一个释义项到结尾合在一起是explian
explain = ""
for i in range(k, size):
if i != k:
explain += " "
explain += lst[i]
# 保存到数据库
word = Word()
word.name = name
word.explain = explain
word.save()
print("生成完成,见words_word表")
def __yield_words(self, dictionary):
for key in dictionary.keys():
yield Word(lemma=key, description=dictionary[key])
