def main(args=None):
args = parse(args)
word_filter = create_filter(args.tags)
words = KanjiWord.all()
words = filter(lambda val: word_filter(val.tags), words)
sample = random.sample(words, args.count)
for word in sample:
print word.kanji
def main(args=None):
args = parse(args)
word_filter = create_filter(args.tags)
words = KanjiWord.all()
words = filter(lambda val: word_filter(val.tags), words)
sample = random.sample(words, args.count)
for word in sample:
print word.kanji
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
from models.kanji_word import KanjiWord
from utf8_helper import force_UTF8
import kana
from collections import defaultdict
from itertools import islice
import settings
if __name__ == '__main__':
force_UTF8()
# Get the readings of every single kanji
mapping = defaultdict(list)
for word in KanjiWord.all():
for reading in word.kanji_readings:
mapping[reading['base']].append(reading['reading'])
# Now remove any that are used
# try:
# kanji = Kanji.find(reading['base'])
# except KeyError:
# 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
# ))
#!/usr/bin/env python
# -*- coding: UTF-8 -*-
from models.kanji import Kanji
from models.kanji_word import KanjiWord
from utf8_helper import force_UTF8
import kana
import settings
if __name__ == '__main__':
force_UTF8()
# First we need to read out whitelist
whitelist = set()
for kanji in Kanji.all():
if kanji.suspended:
continue
whitelist.add(kanji.kanji)
# Now we filter out any KanjiWords that use other kanji
for kanji_word in KanjiWord.all():
fine = True
for kanji in kanji_word.kanji:
if kana.is_kana(kanji) and kanji not in whitelist:
fine = False
if fine:
kanji_word.mark_suspended(False)
type=int,
default=10,
help='The number of words to display')
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
# Path for the ignore unused readings file UNUSED_READINGS = 'unused.json' # Path for the jlpt kanji file JLPT_PATH = 'jlpt_kanji.json' # Path for Kanji dictionary FULL_KANJI_DICT = os.path.join(DATA, 'kanjidic2.xml') KANJI_DICT = os.path.join(DATA, 'kanjidic2_common.xml') # KANJI_DICT = os.path.join(DATA, 'kanjidic2.xml') # Html Output templates DATA_HEADER = os.path.join(DATA, 'header.html') DATA_CSS = os.path.join(DATA, 'main.css') EXTRA_DICT_KANJI = os.path.join(DATA, 'extra_dict.json') # Now we setup all the models from models.anki import AnkiModel from models.kanji_word import KanjiWord from models.kanji import Kanji AnkiModel.setup(path=os.path.join(ANKI_PATH, ANKI_USER, ANKI_DB)) KanjiWord.setup(path=os.path.join(DATA, COMPLEX_READINGS)) Kanji.setup(path=os.path.join(DATA, UNUSED_READINGS)) import jlpt jlpt.setup_jlpt(path=os.path.join(DATA, JLPT_PATH))
# Path for Kanji dictionary FULL_KANJI_DICT = os.path.join(DATA, 'kanjidic2.xml') KANJI_DICT = os.path.join(DATA, 'kanjidic2_common.xml') # KANJI_DICT = os.path.join(DATA, 'kanjidic2.xml') # Html Output templates DATA_HEADER = os.path.join(DATA, 'header.html') DATA_CSS = os.path.join(DATA, 'main.css') EXTRA_DICT_KANJI = os.path.join(DATA, 'extra_dict.json') # Now we setup all the models from models.anki import AnkiModel from models.kanji_word import KanjiWord from models.kanji import Kanji AnkiModel.setup(path=os.path.join(ANKI_PATH, ANKI_USER, ANKI_DB)) KanjiWord.setup(path=os.path.join(DATA, COMPLEX_READINGS)) Kanji.setup(path=os.path.join(DATA, UNUSED_READINGS)) import jlpt jlpt.setup_jlpt(path=os.path.join(DATA, JLPT_PATH))
#!/usr/bin/env python
# -*- coding: UTF-8 -*-
from models.kanji import Kanji
from models.kanji_word import KanjiWord
from utf8_helper import force_UTF8
import kana
import settings
if __name__ == '__main__':
force_UTF8()
# First we need to read out whitelist
whitelist = set()
for kanji in Kanji.all():
if kanji.suspended:
continue
whitelist.add(kanji.kanji)
# Now we filter out any KanjiWords that use other kanji
for kanji_word in KanjiWord.all():
fine = True
for kanji in kanji_word.kanji:
if kana.is_kana(kanji) and kanji not in whitelist:
fine = False
if fine:
kanji_word.mark_suspended(False)