def get_vocab_from_selector(selector_id):
jpDB = Japanese_DB_handler()
f = jpDB.base_format
data = jpDB.get_item_by_id(f.kanjis, selector_id, f.kanjis.name)
if not data: return None
selector_name = data[0]
item_to_get = www_config.get_vocab_format_including_id()
vocab_list = jpDB.list_word_by_kanjis(selector_name, *item_to_get)
return vocab_list
def get_selector_name_from_id(cls, selector_id):
jpDB = Japanese_DB_handler()
f = jpDB.base_format
table = f.get_table(cls.sub_url)
field = f.get_field(cls.sub_url, 'name')
data = jpDB.get_item_by_id(table, selector_id, field)
if data: return data[0]
def parse(inputFile, outputDir):
# getting configuration and BD.
db_handler = Japanese_DB_handler()
#config_data = _parseConf()
config_data = configuration.get_configuration()
if not config_data :
log.error("couldn't find get configuration data")
return
copyfile(inputFile, _generateFileName(config_data.input_files_bk, 'input'))
f = db_handler.base_format
existing_kanjis = db_handler.list(f.vocab, f.vocab.word)
potentialErrors = []
newEntriesList = []
# Parsing input file.
with open(inputFile, 'r') as fin:
for row in csv.reader(fin, delimiter=' '):
# usefull to just get half of the list
# but question are not necessrely before awnser
# we forced japanese as row[0]
word = row[0]
meaning = row[1]
prononciation = row[2] if row[2] else ''
exemple = ''
if word not in existing_kanjis :
newEntriesList.append(['','',word, prononciation, meaning, exemple])
else :
log.error('already exists : '+word)
nb_of_files = len(newEntriesList)//100
if len(newEntriesList)%100 != 0 :
nb_of_files += 1
outputDir += '/'
for nb in range(1, nb_of_files+1, 1):
fileName = _generateFileName(outputDir, "int", str(nb))
with open(fileName, 'w') as fout:
writer = csv.writer(fout, delimiter= ' ')
writer.writerow(['categorie','tag','word','prononciation','meaning','exemple'])
for entry in newEntriesList[100 * (nb - 1) : 100 * nb] :
writer.writerow(entry)
fileName = _generateFileName(outputDir, "int", '_pottentialErrors')
with open(fileName, 'w') as fout:
writer = csv.writer(fout, delimiter= ' ')
for error in potentialErrors:
writer.writerow(error)
log.error(error)
return
def hello():
jpDB = Japanese_DB_handler()
stat_dict = jpDB.get_db_stat()
output = ''
for list_name, list_info in stat_list_names.items():
most_used, number = list_info
output += template('list_test',
rows=stat_dict[most_used],
list_name=list_name,
number=stat_dict[number])
return output
def categorie_page(categorie_id):
jpDB = Japanese_DB_handler()
f = jpDB.base_format
checked_cat_id = categorie_id if jpDB.check_categorie_existence(
categorie_id) else None
if checked_cat_id:
item_to_get = (f.vocab.word, f.vocab.prononciation, f.vocab.meaning,
f.vocab.example)
vocab_rows = jpDB.list_word_by_categorie(categorie_id, *item_to_get)
else:
vocab_rows = ()
output = template('categorie', name=checked_cat_id, rows=vocab_rows)
return output
def list_cat_tag_from_csv_files(*input_file_list, log_info=False):
csv_all_cat = set() # all cat found in csv
csv_all_tag = set() # all tag found in csv
csv_existing_cat = set() # cat found in csv files already existing in DB.
csv_existing_tag = set() # tag found in csv files already existing in DB.
csv_new_cat = set() # new cat found in at least on csv file.
csv_new_tag = set() # new tag found in at least on csv file.
jpDB = Japanese_DB_handler()
f = jpDB.base_format
jpDB_cat = set(jpDB.select(f.categories, f.categories.name))
jpDB_tag = set(jpDB.select(f.tags, f.tags.name))
for input_file in input_file_list:
found_cat, found_tag = _list_cat_tag_process_single_file(input_file)
csv_all_cat.update(found_cat)
csv_all_tag.update(found_tag)
csv_existing_cat = csv_all_cat & jpDB_cat
csv_existing_tag = csv_all_tag & jpDB_tag
csv_new_cat = csv_all_cat - csv_existing_cat
csv_new_tag = csv_all_tag - csv_existing_tag
if log_info:
_log_separator('categories')
log.info('1 : existing categories : ')
_log_set(csv_existing_cat)
log.info(' ')
log.info('2 : existing categories : ')
_log_set(csv_new_cat)
log.info(' ')
_log_separator('tags')
log.info('1 : existing tags : ')
_log_set(csv_existing_tag)
log.info(' ')
log.info('2 : existing tags : ')
_log_set(csv_new_tag)
log.info(' ')
return csv_existing_cat, csv_new_cat, csv_existing_tag, csv_new_tag
def words_page():
item_to_get = www_config.get_vocab_format_including_id()
vocab_list = Japanese_DB_handler().list_all_words(*item_to_get)
name = application_title + ", words"
css_file = main_css
body = header_kioku()
body += create_add_word_page()
body += list_vocabulary(www_config.get_vocab_format_as_string(),
vocab_list)
data = page_base_structure(name, css_file, body)
return data
def add_word_status(method='GET'):
print('aaaaaa')
#word = request.forms.get('word')
#prononciation = request.forms.get('prononciation')
#meaning = request.forms.get('meaning')
#example = request.forms.get('example')
#categorie = request.forms.get('categorie')
#tag = request.forms.get('tag')
status = Japanese_DB_handler().add_single_word(
request.GET.word, request.GET.prononciation, request.GET.meaning,
request.GET.example, request.GET.categorie, request.GET.tag)
name = application_title + ': add new word, status'
css_file = main_css
body = header_kioku()
body += template('add_word_status', request.GET.word, status)
data = page_base_structure(name, css_file, body)
return data
def _add_vocab_fromCsv_dir(csv_file_list, add_categories, add_tags):
cat_in_csv = set()
tag_in_csv = set()
vocab_entries = set()
error_entries = []
fields = [
'categorie', 'tag', 'word', 'prononciation', 'meaning', 'example'
]
delimiter = _get_delimiter()
delimiter = " "
for file in csv_file_list:
with open(file, 'r') as csv_file:
reader = csv.DictReader(csv_file,
fieldnames=fields,
delimiter=delimiter)
for row in reader:
if row['tag'] != 'tag':
if "ERROR" in row['tag']:
error_entries.append(_format_row(row))
else:
cat_in_csv.add(row['categorie'])
tag_in_csv.add(row['tag'])
vocab_entries.add(_format_row(row))
jpDb = Japanese_DB_handler()
if add_categories:
jpDb.add_categories(*tuple(cat_in_csv), silent=True)
if add_tags:
jpDb.add_tags(*tuple(tag_in_csv), silent=True)
status = jpDb.add_vocab(*tuple(vocab_entries))
return status, error_entries
def get_word_data(word_id):
jpDB = Japanese_DB_handler()
return jpDB.get_word_info(word_id)
def get_selector_list_data():
jpDB = Japanese_DB_handler()
sel_list = jpDB.list_categorie_by_usage(include_id=True)
sel_number = jpDB.count(jpDB.base_format.categories)
return sel_list, sel_number
import os
import sys
import csv
from japanese.Japanese_DB_handler import Japanese_DB_handler
import configuration as configuration
logging.basicConfig()
log = logging.getLogger()
log.setLevel(logging.DEBUG)
output_dir = sys.argv[1]
if not os.path.exists(output_dir):
log.error('directory not found : ' + str(output_dir))
sys.exit(1)
jpDB = Japanese_DB_handler()
f = jpDB.base_format
config_data = configuration.get_configuration()
if not config_data:
log.error("couldn't find get configuration data")
sys.exit(1)
cat_dir = {}
tag_dir = {}
cat_list = jpDB.list_categorie_by_usage()
tag_list = jpDB.list_tag_by_usage()
for cat, _ in cat_list:
if not cat: continue
def categories_page():
jpDB = Japanese_DB_handler()
data = jpDB.list_categorie_by_usage()
output = template('full_list', rows=data, list_name='categories')
return output
def update_name(orig_name, new_name):
return Japanese_DB_handler().edit_cat(orig_name, new_name)
def get_selector_list_data():
jpDB = Japanese_DB_handler()
sel_list = jpDB.list_core_p_by_usage(include_id=True)
sel_number = jpDB.count(jpDB.base_format.core_prononciations)
return sel_list, sel_number
def stat_test():
jpDB = Japanese_DB_handler()
print(jpDB)
print(jpDB.base_format)
stat_dict = jpDB.get_db_stat()
return str(dict(stat_dict['most_used_categories']))
def _get_DB_format():
global db_format
if not db_format: db_format = Japanese_DB_handler().base_format
return db_format
def parse(inputFile, outputDir):
# getting configuration and BD.
db_handler = Japanese_DB_handler()
#config_data = _parseConf()
config_data = configuration.get_configuration()
if not config_data:
log.error("couldn't find get configuration data")
return
copyfile(inputFile, _generateFileName(config_data.input_files_bk, 'input'))
f = db_handler.base_format
existing_kanjis = db_handler.list(f.vocab, f.vocab.word)
potentialErrors = []
newEntriesList = []
# Parsing input file.
with open(inputFile, 'r') as fin:
for row in csv.reader(fin, delimiter=' '):
# usefull to just get half of the list
# but question are not necessrely before awnser
# we forced japanese as row[0]
if not _is_cjk(row[0][0]):
continue
japanese = row[0]
french = row[1]
# print(japanese)
# 3 cases :
# 1, juste kana
# 2, a bunch of kanji and kana prononciation
# 3, 2 + a sentence exemple.
# 1) no kanjis
status = True
if ' ' not in japanese:
word = japanese
prononciation = ''
exemple = ''
else:
potentialKanjis, afterKanjis = japanese.split(' ', 1)
# remove trailing spaces.
afterKanjis = _delTrailingSpaces(afterKanjis)
if afterKanjis[:2] == 'する':
potentialKanjis += ' (する)'
afterKanjis = _delTrailingSpaces(afterKanjis[2:])
if afterKanjis[:2] == 'な ':
potentialKanjis += ' (な)'
afterKanjis = _delTrailingSpaces(afterKanjis[1:])
# x) Potentials errors : Full phrase.
if len(potentialKanjis) > 7:
log.error('potential error :' + potentialKanjis)
status = False
potentialErrors.append(row)
# 2) just kanjis and prononciation
elif ' ' not in afterKanjis:
word = potentialKanjis
prononciation = _delTrailingSpaces(afterKanjis)
exemple = ''
# 3) kanjis prononciation and exemple
else:
word = potentialKanjis
prononciation, exemple = afterKanjis.split(' ', 1)
prononciation = _delTrailingSpaces(prononciation)
exemple = _delTrailingSpaces(exemple)
if status and word not in existing_kanjis:
newEntriesList.append(
['', '', word, prononciation, french, exemple])
else:
log.error('already exists : ' + word)
nb_of_files = len(newEntriesList) // 100
if len(newEntriesList) % 100 != 0:
nb_of_files += 1
outputDir += '/'
for nb in range(1, nb_of_files + 1, 1):
fileName = _generateFileName(outputDir, "int", str(nb))
with open(fileName, 'w') as fout:
writer = csv.writer(fout, delimiter=' ')
writer.writerow([
'categorie', 'tag', 'word', 'prononciation', 'meaning',
'exemple'
])
for entry in newEntriesList[100 * (nb - 1):100 * nb]:
writer.writerow(entry)
fileName = _generateFileName(outputDir, "int", '_pottentialErrors')
with open(fileName, 'w') as fout:
writer = csv.writer(fout, delimiter=' ')
for error in potentialErrors:
writer.writerow(error)
log.error(error)
return
def _jpdb():
global _jpdb_object
if not _jpdb_object: _jpdb_object = Japanese_DB_handler()
return _jpdb_object
