class DictionaryTest(unittest.TestCase):
def setUp(self):
self.dict = Dictionary(os.path.join(os.path.dirname(__file__), '..',
'examples', 'stardict-quick_eng-rus-2.4.2/quick_english-russian'))
self.in_memory_dict = Dictionary(os.path.join(os.path.dirname(__file__), '..',
'examples', 'stardict-quick_eng-rus-2.4.2/quick_english-russian'), in_memory=True)
def test001Idx(self):
self.assertEqual(self.dict.idx['test'], (581161, 16,))
def test002Dict(self):
self.assertEqual(self.dict.dict['test'], 'проверка')
def test003Dictionary(self):
self.assertEqual(self.dict['test'], 'проверка')
def test004Contains(self):
self.assertTrue('test' in self.dict)
self.assertFalse('testtt' in self.dict)
def test005Delitem(self):
self.dict['test']
del self.dict['test']
self.assertFalse('test' in self.dict._dict_cache)
def test006Len(self):
self.assertEqual(len(self.dict), 31705)
def test007Eq(self):
y = Dictionary(os.path.join(os.path.dirname(__file__), '..',
'examples', 'stardict-quick_eng-rus-2.4.2/quick_english-russian'))
self.assertTrue(self.dict == y)
def test008Ne(self):
y = Dictionary(os.path.join(os.path.dirname(__file__), '..',
'examples', 'stardict-quick_eng-rus-2.4.2/quick_english-russian'))
self.assertFalse(self.dict != y)
def test009Repr(self):
self.assertEqual(repr(self.dict),
'''<class 'pystardict.Dictionary'> quick_english-russian''')
def test010Clear(self):
self.dict['test']
self.dict.clear()
self.assertEqual(len(self.dict._dict_cache), 0)
def test011Get(self):
self.assertEqual(self.dict.get('test', 't'), 'проверка')
self.assertEqual(self.dict.get('testtt', 't'), 't')
def test012InMemoryDict(self):
self.assertEqual(self.in_memory_dict['test'], 'проверка')
def test013IterateDict(self):
for k, v in self.in_memory_dict.items():
self.assertEqual(self.in_memory_dict[k], v)
def handle(self, *args, **options):
for fname in glob.glob('sources/*.dict'):
dict_name = Path(fname).stem
dict1 = Dictionary(os.path.join('sources', dict_name))
print('Importing the %s dictionary...' % dict_name)
for word in Word.objects.all():
word_data = dict1.get(word.content)
soup = BeautifulSoup(word_data, "html.parser")
word.phrase_set.all().delete()
i = 0
for ex in soup.find_all('ex'):
if ex.text:
phrase = Phrase(word=word, content=ex.text)
phrase.save()
i += 1
if i >= 10:
break
# One dictionary is enough for now
break
def handle(self, *args, **options):
for fname in glob.glob('sources/*.dict'):
dict_name = Path(fname).stem
dict1 = Dictionary(os.path.join('sources', dict_name))
print('Updating transcription from %s dictionary...' % dict_name)
for word in Word.objects.all():
word_data = dict1.get(word.content)
soup = BeautifulSoup(word_data, "html.parser")
trans_vars = soup.find_all('c', attrs={'c': 'teal'})
for trans_var in trans_vars:
if trans_var.text.startswith('['):
word.transcription = trans_var.text[1:-1]
word.save()
break
word.phrase_set.all().delete()
for ex in soup.find_all('ex'):
if ex.text:
phrase = Phrase(word=word, content=ex.text)
phrase.save()
break
break
class stardict(import_dictionary):
def __init__(self, path, stardict_db_folder, stardict_db_name):
import_dictionary.__init__(self)
self.dict1 = Dictionary(
os.path.join(path, stardict_db_folder, stardict_db_name))
def add_words_to_dictionary(self):
try:
dictionary_id = self.check_dictionary(self.dict1.ifo.bookname,
self.dict1.ifo.wordcount,
abstractive=1)
print("\n'Add all new words to Dictionary '{0}':\n".format(
self.dict1.ifo.bookname))
for w in tqdm(self.dict1.idx._idx):
word = w.decode('Utf-8')
word_id = self.check_word(word)
definition = self.dict1.get(word)
self.db.write_definition(dictionary_id, word_id, definition)
self.db._commit()
return dictionary_id
except:
self.db.db_connection.rollback()
raise
class DictionaryTest(unittest.TestCase):
def setUp(self):
self.dict = Dictionary(
os.path.join(os.path.dirname(__file__), '..', 'examples',
'stardict-quick_eng-rus-2.4.2/quick_english-russian'))
self.in_memory_dict = Dictionary(os.path.join(
os.path.dirname(__file__), '..', 'examples',
'stardict-quick_eng-rus-2.4.2/quick_english-russian'),
in_memory=True)
def test001Idx(self):
self.assertEqual(self.dict.idx['test'], (
581161,
16,
))
def test002Dict(self):
self.assertEqual(self.dict.dict['test'], 'проверка')
def test003Dictionary(self):
self.assertEqual(self.dict['test'], 'проверка')
def test004Contains(self):
self.assertTrue('test' in self.dict)
self.assertFalse('testtt' in self.dict)
def test005Delitem(self):
self.dict['test']
del self.dict['test']
self.assertFalse('test' in self.dict._dict_cache)
def test006Len(self):
self.assertEqual(len(self.dict), 31705)
def test007Eq(self):
y = Dictionary(
os.path.join(os.path.dirname(__file__), '..', 'examples',
'stardict-quick_eng-rus-2.4.2/quick_english-russian'))
self.assertTrue(self.dict == y)
def test008Ne(self):
y = Dictionary(
os.path.join(os.path.dirname(__file__), '..', 'examples',
'stardict-quick_eng-rus-2.4.2/quick_english-russian'))
self.assertFalse(self.dict != y)
def test009Repr(self):
self.assertEqual(
repr(self.dict),
'''<class 'pystardict.Dictionary'> quick_english-russian''')
def test010Clear(self):
self.dict['test']
self.dict.clear()
self.assertEqual(len(self.dict._dict_cache), 0)
def test011Get(self):
self.assertEqual(self.dict.get('test', 't'), 'проверка')
self.assertEqual(self.dict.get('testtt', 't'), 't')
def test012InMemoryDict(self):
self.assertEqual(self.in_memory_dict['test'], 'проверка')
def test013IterateDict(self):
for k, v in self.in_memory_dict.items():
self.assertEqual(self.in_memory_dict[k], v)
import xml.etree.ElementTree as ET
from pystardict import Dictionary
f = ET.parse(sys.argv[1])
unknown_words_f = open('uwords.txt', 'w')
words_f = open('pwords.txt', 'w')
dict_bel_rus = Dictionary(sys.argv[2])
words = set()
path = './/Paradigm'
for paradigm in f.findall(path):
lem = paradigm.attrib['Lemma'].replace('´', '')
words.add(lem)
print("Parsed: {} words".format(len(words)))
translated = 0
for element in words:
if dict_bel_rus.has_key(element):
translated += 1
rus_eq = dict_bel_rus.get(element).split("\n")[1]
words_f.write("{} | {}\n".format(element, rus_eq))
else:
unknown_words_f.write(element + "\n")
print("{} were translated".format(translated))
unknown_words_f.close()
words_f.close()
