def test_jaconv():
logging.info("=========================================")
logging.info("= jaconv =")
logging.info("=========================================")
test_cases = get_test_cases()
for tc in test_cases:
title = tc['title']
body = tc['body']
logging.info("ひらがな（全角） to カタカナ（全角） for %s" % title)
calc_time(jaconv.hira2kata, body)
logging.debug("result: %s" % jaconv.hira2hkata(body))
logging.info("カタカナ（全角） to ひらがな（全角） for %s" % title)
calc_time(jaconv.kata2hira, body)
logging.debug("result: %s" % jaconv.kata2hira(body))
logging.info("ひらがな（全角） to カタカナ（半角） for %s" % title)
calc_time(jaconv.hira2hkata, body)
logging.debug("result: %s" % jaconv.hira2hkata(body))
logging.info("半角 to 全角 for %s" % title)
calc_time(jaconv.h2z, body)
logging.debug("result: %s" % jaconv.h2z(body))
logging.info("全角 to 半角 for %s" % title)
calc_time(jaconv.z2h, body)
logging.debug("result: %s" % jaconv.z2h(body))
def kataconv(content):
try: #Disable mecab by commenting the following 3 lines
kanji = input("Convert kanji?: ")
if kanji == "Y"or kanji == "y" or kanji == "ｙ" or kanji == "Ｙ":
content = mecab.parse(content)
content = content.replace("\n","")
content = content.replace("‖"," "*32)#act as enter, change num here to fit
content = jaconv.normalize(content)
content = jaconv.z2h(content)
content = jaconv.hira2hkata(content)
print("Output content: "+content)
return content
except Exception as error:
print(error)
def binconv(string):
lst = list(string)
data = []
digi = []
for item in lst:
item = jaconv.hira2hkata(item)
item = jaconv.z2h(item)
item = convmap(item)
data.append(item)
for stri in data:
try:
if len(stri) == 1 and ord(stri)<= 128:
digi.append(int(ord(stri)))
else:
digi.append(int(stri,16))
except:
digi.append(int(255))
return digi
def conductMain():
file = file1.get()
root, ext = os.path.splitext(file)
#db_name = input_box.get()
#print(db_name)
#csvの時
if ext == '.csv':
#dataの読み取り・登録
df = pd.read_csv(file, encoding="shift-jis")
dbname = "database.db" #dbname = str(db_name) + ".db"
c = sqlite3.connect(dbname)
cur = c.cursor()
try:
ddl = 'CREATE TABLE data (id INTEGER PRIMARY KEY AUTOINCREMENT, input_name STRING, input_name_kana STRING, content TEXT)'
cur.execute(ddl)
c.commit()
except sqlite3.OperationalError:
pass
tkinter.messagebox.showinfo(
"Start", "データベースを作成します\n完了画面が出るまで何も触らずにお待ちください")
for k in tqdm(range(len(df))):
input_value = df.loc[k, '得意先略称'][1:]
input_value_han_kana = df.loc[k, '名カナ'][1:]
input_value_kana = jaconv.hira2hkata(input_value_han_kana)
input_value_kana = jaconv.h2z(input_value_kana,
digit=True,
ascii=True)
content = df.loc[k, '備考'][1:]
c.execute(
'INSERT INTO data(input_name, input_name_kana,content) VALUES("'
+ str(input_value) + '", "' + str(input_value_kana) +
'", "' + str(content) + '")')
c.commit()
tkinter.messagebox.showinfo("完了", "データベースが作成されました")
#csv以外
else:
tkinter.messagebox.showinfo("不適切なファイル形式です", "csvファイルを指定してください")
newwindow.destroy()
def test_hira2hkata():
assert_equal(jaconv.hira2hkata('ともえまみ'), 'ﾄﾓｴﾏﾐ')
assert_equal(jaconv.hira2hkata('ともえまみ', ignore='み'), 'ﾄﾓｴﾏみ')
_compare(jaconv.hira2hkata, HIRAGANA, HALF_KANA)
def test_hira2hkata():
assert_equal(jaconv.hira2hkata('ともえまみ'), 'ﾄﾓｴﾏﾐ')
assert_equal(jaconv.hira2hkata('ともえまみ', ignore='み'), 'ﾄﾓｴﾏみ')
_compare(jaconv.hira2hkata, HIRAGANA, HALF_KANA)
def main():
input_filename = args.input
output_filename = args.output
with_nation = args.nation
# validation
if not os.path.exists(input_filename):
print(input_filename, 'は存在しません。')
sys.exit(1)
# 都道府県、市区町村データを格納する変数
prefs = {}
# 全国のデータが必要であれば付与
if with_nation:
prefs['0'] = {
"code": "0",
"name": "全国",
"yomi": "ぜんこく",
"yomi_kana": "ゼンコク",
"yomi_kana_han": "ｾﾞﾝｺｸ",
"cities": {},
"seirei": {},
}
##################################################
#
# 都道府県、市区町村(政令指定都市の区を除く)の処理
#
##################################################
# excelのシート読み込み
df_city = pd.read_excel(input_filename,
usecols='A:E',
header=None,
skiprows=[0])
# カラム名変換
# 団体コード, 都道府県名, 市区町村名, 都道府県名(カナ), 市区町村名(カナ)
df_city.rename(columns={
0: 'code',
1: 'pref_name',
2: 'city_name',
3: 'pref_yomi_kana',
4: 'city_yomi_kana'
},
inplace=True)
# 1行ずつ処理
for i, row in df_city.iterrows():
pref_code = row['code'] // 10000
if isinstance(row['city_name'], float):
# 都道府県
pref = {
'code': str(pref_code),
'name': row['pref_name'],
'yomi': jaconv.kata2hira(jaconv.h2z(row['pref_yomi_kana'])),
'yomi_kana': jaconv.h2z(row['pref_yomi_kana']),
'yomi_kana_han': row['pref_yomi_kana'],
'cities': {},
'seirei': {},
}
prefs[pref_code] = pref
else:
# 市区町村
city_code = int(row['code'])
city = {
'code': str(city_code),
'name': row['city_name'],
'yomi': jaconv.kata2hira(jaconv.h2z(row['city_yomi_kana'])),
'yomi_kana': jaconv.h2z(row['city_yomi_kana']),
'yomi_kana_han': row['city_yomi_kana']
}
prefs[pref_code]['cities'][city_code] = city
####################
#
# 政令指定都市の処理
#
####################
# excelシート読み込み
df_seirei = pd.read_excel(input_filename,
usecols='A:C',
sheet_name=1,
header=None)
# カラム名変換
# 団体コード, 市区町村名, 市区町村名(かな)
df_seirei.rename(columns={
0: 'code',
1: 'city_name',
2: 'city_yomi'
},
inplace=True)
# 1行ずつ処理
seirei_code = 0
for i, row in df_seirei.iterrows():
pref_code = row['code'] // 10000
if '区' in row['city_name']:
# 政令指定都市の区
city_code = row['code']
city = {
'code': str(city_code),
'parent_seirei_code': str(seirei_code),
'name': row['city_name'],
'yomi': row['city_yomi'],
'yomi_kana': jaconv.hira2kata(row['city_yomi']),
'yomi_kana_han': jaconv.hira2hkata(row['city_yomi'])
}
prefs[pref_code]['seirei'][seirei_code][city_code] = city
else:
# 政令指定都市
seirei_code = row['code']
prefs[pref_code]['seirei'][seirei_code] = {}
########################
#
# jsonファイルに書き出し
#
########################
with open(output_filename, 'w', encoding='utf-8') as f:
json.dump(prefs, f, indent=2, ensure_ascii=False)