def __init__(self):
super().__init__()
self.entries = dict()
category = NotImplemented # type: str
with open(database_path('vocab_category.txt')) as f:
for row in f:
match_obj = re.match(r'([^\t]*)\t([^\t]*)\t([^\t]*)[\t\n]', row)
if not match_obj:
category = row.strip().lower()
if not category:
continue
else:
vocab, reading, english = match_obj.groups()
if vocab not in self.entries.keys():
self.entries[vocab] = {
'vocab': vocab,
'reading': reading,
'english': english,
'categories': [category]
}
vocab = ''
else:
if category not in self.entries[vocab]['categories']:
self.entries[vocab]['categories'].append(category)
self._lookup = dict()
self._lookup_categories = []
self._categories = dict()
self._category = ''
self._do_categories()
def __init__(self):
self.entries = dict()
with open(database_path('hanzi_variant.tsv')) as f:
next(f)
for row in f:
contents = row.split('\t')
self.entries[contents[1]] = contents[-3]
def __init__(self):
self.entries = dict()
with open(database_path('hsk_vocab.tsv')) as f:
for row in f:
contents = row.split('\t')
level = contents[-3][-1]
if level.isdigit():
self.entries.setdefault(contents[-3],
[]).append(contents[0])
def __init__(self):
self.entries = []
with open(database_path('hanzi_level.txt')) as f:
category = None
for row in f:
if row[0].isdigit():
category = row.strip()
else:
self.entries.append((row.strip(), category))
def __init__(self):
self.entries = []
with open(database_path('SpoonFed.tsv')) as f:
next(f)
for row in f:
contents = row.split('\t')
self.entries.append({
'Chinese': contents[2],
'English': contents[0]
})
def __init__(self):
super().__init__()
self.levels = []
category = NotImplemented # type: str
with open(database_path('hanzi_level.txt')) as f:
for row in f:
match_obj = re.match(r'(\d+)-(\d+) (\S+)', row)
if match_obj is not None:
_, _, category = match_obj.groups()
else:
self.levels.append([row.strip(), category])
def __init__(self):
super().__init__()
self.entries = dict()
with open(database_path(self.filename), encoding=self.encoding) as f:
keys = f.readline().strip().split('\t')
for row in f:
values = row.strip().split('\t')
self.entries[values[self.index_column]] = \
dict(zip(keys, [BeautifulSoup(value, "html.parser").text for value in values]))
self._lookup = []
self._lookup_params = []
def __init__(self):
super().__init__()
self.entries = dict()
with open(database_path('hsk_vocab.tsv')) as f:
keys = f.readline().strip().split('\t')
for row in f:
item = row.strip().split('\t')
self.entries.setdefault(item[0], []).append(dict(zip(keys, item)))
# if item[1] and item[1] != item[0]:
# self.entries.setdefault(item[1], []).append(dict(zip(keys, item)))
self._lookup = []
self._lookup_params = []
def __init__(self):
self.entries = dict()
with open(database_path('vocab_category.txt')) as f:
category = None
vocab_list = None
for row in f:
contents = row.split('\t')
if len(contents) == 1:
if category and vocab_list:
self.entries[category] = vocab_list
category = contents[0].strip()
vocab_list = []
else:
vocab_list.append(contents[0])
def __init__(self):
super().__init__()
self.dictionary = dict()
with open(database_path('cedict_ts.u8'), encoding='utf8') as f:
for row in f.readlines():
result = re.fullmatch(r'(\w+) (\w+) \[(.+)\] /(.+)/\n', row)
if result is not None:
trad, simp, pinyin, eng = result.groups()
self.dictionary.setdefault(simp, [])
self.dictionary.setdefault(trad, [])
self.dictionary[simp].append({
'traditional': trad,
'simplified': simp,
'reading': pinyin,
'english': eng
})
if trad != simp:
self.dictionary[trad].append(self.dictionary[simp][-1])
