def morph(ctx, app_id, sentence_file, json_flag, sentence, info_filter,
pos_filter, request_id):
# type: (Context, unicode, Optional[IO], bool, unicode, unicode, unicode, unicode) -> None # NOQA
""" Morphological analysis for Japanese."""
app_id = clean_app_id(app_id)
sentence = clean_sentence(sentence, sentence_file)
if info_filter:
info_filter = info_filter.replace(',', '|')
if pos_filter:
pos_filter = pos_filter.replace(',', '|')
api = GoolabsAPI(app_id)
ret = api.morph(
sentence=sentence,
info_filter=info_filter,
pos_filter=pos_filter,
request_id=request_id,
)
if json_flag:
click.echo(format_json(api.response.json()))
return
for words in ret['word_list']:
for word in words:
click.echo(','.join(word))
def get_posChecker(keyword_list):
app_id = "72557413b523d38db2d1de26f8095928d43d6d0882707ed41249f9edb643db45"
api = GoolabsAPI(app_id)
check_list = []
for keyword in keyword_list:
check_list.append(
str(api.morph(sentence=keyword)["word_list"][0][0][1]))
if len(list(set(check_list))):
return True
else:
return False
def get_request(text):
api = GoolabsAPI(key)
response = api.morph(sentence=text)
return response
def get_promise_content(letter):
api = GoolabsAPI(GOO_API_KEY)
index = 0
# letter = "クリスマスに岩見と一緒に東京駅に来て"
# 時刻情報正規化API
# chrono_response = api.chrono(sentence=letter)
# 固有表現抽出API
entity_response = api.entity(sentence=letter)
# 形態素解析API
# morph_response = api.morph(sentence=letter)
date = ''
hour = ''
min = ''
place = ''
for i in range(len(entity_response["ne_list"])):
# 日付の抽出
if entity_response["ne_list"][i][1] == "DAT":
day_response = api.chrono(sentence=entity_response["ne_list"][i][0])
if len(day_response['datetime_list']) != 0:
date = day_response["datetime_list"][0][1]
# 約束内容の要素番号を算出
day = entity_response["ne_list"][i][0]
index = letter.find(day) + len(day)
# 時間の抽出
elif entity_response["ne_list"][i][1] == "TIM":
time_len = len(entity_response["ne_list"][i][0])
for j in range(time_len):
if entity_response["ne_list"][i][0][j] == u"時":
hour = entity_response["ne_list"][i][0][0:j]
hour_n = j
# 約束内容の要素番号を算出
time = entity_response["ne_list"][i][0]
index = letter.find(time) + len(time)
if j != time_len - 1:
if entity_response["ne_list"][i][0][j + 1] == u"半":
min = "30"
elif entity_response["ne_list"][i][0][j] == u"分":
min = entity_response["ne_list"][i][0][hour_n + 1:j]
elif entity_response["ne_list"][i][1] == "LOC":
place = entity_response["ne_list"][i][0]
# 約束内容を出力
# 約束内容の最初の文字に格助詞が入ってるか調べる
morph_response = api.morph(sentence=letter[index:len(letter)])
if morph_response["word_list"][0][0][1] == u"格助詞" or morph_response["word_list"][0][0][1] == u"読点":
par_len = len(morph_response["word_list"][0][0][0])
content = letter[index + par_len:len(letter)]
else:
content = letter[index:len(letter)]
return {'date': date, 'hour': hour, 'min': min, 'content': content, 'place': place}
unix_socket="/Applications/MAMP/tmp/mysql/mysql.soc\
k",
host="localhost",
db="Wordrop",
user="******",
passwd="root",
charset="utf8")
cur = connector.cursor()
cur.execute("select * from home;")
app_id = "2d84d0d734ebefeb1f4dcf8ae106ec9d2f3b72a5be084a1014d6e27a9002ffef"
api = GoolabsAPI(app_id)
response = api.morph(pos_filter="名詞", sentence=tex) #sentenceにある言葉を形態素解析する
value = response["word_list"] #形態素解析の結果を代入 \
response = api.entity(sentence=value) #名詞の固有表現を求める \
list = response.values()
pp(value)
response = api.entity(sentence=value[0][0][0])
print type(value)
ss = []
count = 0
for row in f:
chat_text = row
print(row)
app_id = "13346dab6a67b41a884de45bcbf4bdc523ced4da711c35346f0a8501ef0b23fe"
api = GoolabsAPI(app_id)
echat_text = chat_text.encode('shift-jis')
uchat_text = echat_text.decode('shift-jis')
# # See sample response below.
# ret = api.entity(sentence=uchat_text)
# with open('./data/entity_response.json', 'w', newline='', encoding='utf-8') as f:
# f.write(str(ret))
# See sample response below.
ret = api.morph(sentence=uchat_text)
with open('./data/morph_response.json', 'w', newline='',
encoding='utf-8') as f:
f.write(str(ret))
# print (json.dumps(ret, sort_keys = True, indent = 4))
# {'word_list': [[['トイレットペーパー', '名詞', 'トイレットペーパー'], \
# ['を', '格助詞', 'ヲ'], ['5', 'Number', 'ゴ'], ['個', '助数詞', 'コ'], \
# ['持', '動詞語幹', 'モ'], ['っ', '動詞活用語尾', 'ッ'], ['て', '動詞接尾辞', 'テ'], \
# ['い', '動詞語幹', 'イ'], ['く', '動詞接尾辞', 'ク'], ['よ', '終助詞', 'ヨ'], ['。', '句点', '＄']]], \
# 'request_id': 'labs.goo.ne.jp\t1477797716\t0'}
for i in ret:
groupDict = ret[i]
break
# print (groupDict[0][0][0])