def load_anki_data(kanji_list):
kanji_list = set(kanji_list)
# Find out which kanji we actually have cards for
expected = set()
for kanji in Kanji.all():
if kanji.suspended:
continue
expected.add(kanji.kanji)
# Kanji words also get to add to the whitelist
actual = set()
for word in Counter.all() + KanjiWord.all():
if word.suspended:
continue
# Add all the kanji in the word
for kanji in word.kanji:
# Make sure we only add kanji
if kana.is_kana(kanji):
continue
actual.add(kanji)
extra = load_extra(settings.EXTRA_DICT_KANJI)
# Find which kanji we have no cards for
missing = actual - expected
if len(missing):
message("Missing Kanji Found", ' '.join(missing))
# Notify the user of any kanji that don't have examples (no kanji-words)
no_example = expected - actual
if len(no_example):
message("Kanji with no Examples", ' '.join(no_example))
# Notify the user of any kanji that aren't in our dictionary
unknown = (expected | actual) - (kanji_list | extra)
if len(unknown):
message("Unknown Kanji, not in Dict:", ' '.join(unknown))
# Now we finally make our known kanji list
known = (expected | actual)
return known
def load_anki_data(kanji_list):
kanji_list = set(kanji_list)
# Find out which kanji we actually have cards for
expected = set()
for kanji in Kanji.all():
if kanji.suspended:
continue
expected.add(kanji.kanji)
# Kanji words also get to add to the whitelist
actual = set()
for word in Counter.all() + KanjiWord.all():
if word.suspended:
continue
# Add all the kanji in the word
for kanji in word.kanji:
# Make sure we only add kanji
if kana.is_kana(kanji):
continue
actual.add(kanji)
extra = load_extra(settings.EXTRA_DICT_KANJI)
# Find which kanji we have no cards for
missing = actual - expected
if len(missing):
message("Missing Kanji Found", ' '.join(missing))
# Notify the user of any kanji that don't have examples (no kanji-words)
no_example = expected - actual
if len(no_example):
message("Kanji with no Examples", ' '.join(no_example))
# Notify the user of any kanji that aren't in our dictionary
unknown = (expected | actual) - (kanji_list | extra)
if len(unknown):
message("Unknown Kanji, not in Dict:", ' '.join(unknown))
# Now we finally make our known kanji list
known = (expected | actual)
return known
# if kana.is_kana(reading['base']):
# raise AnkiModel.Error(u"Kana mismatch: %s word(%s) reading(%s)" % (
# reading['base'], word.kanji, word.reading
# ))
# else:
# raise AnkiModel.Error(u"Kanji not found, but in use: %s word(%s)" % (
# reading['base'], word.kanji
# ))
# if reading['reading'] not in kanji.readings and kanji.kanji != '々':
# print '%s(%s) word(%s)' % (
# kanji.kanji,
# reading['reading'],
# word.kanji,
# )
for kanji in Kanji.all():
for reading in kanji._readings:
possible = map(unicode, reading.get_all())
# See if we can find the reading in our kanji words list
found = False
for use in mapping[kanji.kanji]:
if use in possible:
found = True
# Ignore any that are used
if found:
continue
# See if its been ignored
string = "(kanji: %s) %s" % (kanji.kanji, reading)
out = parser.parse_args(args)
return out
if __name__ == '__main__':
force_UTF8()
args = parse()
# Find all the kanji that are in the deck
all_kanji = set()
for word in KanjiWord.all():
for kanji in word.kanji:
all_kanji.add(kanji)
for kanji in Kanji.all():
all_kanji.add(kanji)
# Count which kanji the input data has
data = Counter(unicode(sys.stdin.read()))
for char, count in data.most_common():
# we don't want kana
if kana.is_kana(char):
del data[char]
# Nor do we want kanji we know
if char in all_kanji:
del data[char]
# Nor any non-kanji chars
if not kana.is_kanji(char):
del data[char]