From dd1ca719573181981e245a268f75e57fbd54b7c8 Mon Sep 17 00:00:00 2001 From: k2font Date: Tue, 14 Apr 2020 20:18:21 +0900 Subject: [PATCH] Fix some indent. --- pseudo-chinese.py | 90 ++++++++++++++++++++++------------------------- 1 file changed, 43 insertions(+), 47 deletions(-) diff --git a/pseudo-chinese.py b/pseudo-chinese.py index 22da95b..15566aa 100644 --- a/pseudo-chinese.py +++ b/pseudo-chinese.py @@ -10,19 +10,17 @@ BASE_URL = "https://api.ce-cotoha.com/api/dev/nlp/" def auth(client_id, client_secret): token_url = "https://api.ce-cotoha.com/v1/oauth/accesstokens" headers = { - "Content-Type": "application/json", - "charset": "UTF-8" + "Content-Type": "application/json", + "charset": "UTF-8" } data = { - "grantType": "client_credentials", - "clientId": client_id, - "clientSecret": client_secret + "grantType": "client_credentials", + "clientId": client_id, + "clientSecret": client_secret } - r = requests.post(token_url, - headers=headers, - data=json.dumps(data)) + r = requests.post(token_url,headers=headers,data=json.dumps(data)) return r.json()["access_token"] @@ -33,26 +31,24 @@ def parse(sentence, access_token): base_url = BASE_URL headers = { - "Content-Type": "application/json", - "charset": "UTF-8", - "Authorization": "Bearer {}".format(access_token) + "Content-Type": "application/json", + "charset": "UTF-8", + "Authorization": "Bearer {}".format(access_token) } data = { - "sentence": sentence, - "type": "default" + "sentence": sentence, + "type": "default" } - r = requests.post(base_url + "v1/parse", - headers=headers, - data=json.dumps(data)) + r = requests.post(base_url + "v1/parse",headers=headers,data=json.dumps(data)) return r.json() # ひらがなを削除する関数 # Function to delete hiragana. # 删除平假名的功能 def hira_to_blank(str): - return "".join(["" if ("ぁ" <= ch <= "ん") else ch for ch in str]) + return "".join(["" if ("ぁ" <= ch <= "ん") else ch for ch in str]) if __name__ == "__main__": envjson = open('env.json', 'r') @@ -70,39 +66,39 @@ if __name__ == "__main__": print(parse_document) result_list = list() for chunks in parse_document['result']: - for token in chunks["tokens"]: - # 形態素解析結果に置き換えルールを適用する - if (token["pos"] != "連用助詞" - and token["pos"] != "引用助詞" - and token["pos"] != "終助詞" - and token["pos"] != "接続接尾辞" - and token["pos"] != "動詞活用語尾"): - if token["pos"] == "動詞接尾辞" and '終止' in token["features"]: - if ("する" in token["lemma"]) or ("ます" in token["lemma"]): - prime = "也" - elif "たい" in token["lemma"]: - prime = "希望" - elif token['lemma'] != 'ない': - prime = "了" - else: - prime = "実行" - else: - prime = token["form"] + for token in chunks["tokens"]: + # 形態素解析結果に置き換えルールを適用する + if (token["pos"] != "連用助詞" + and token["pos"] != "引用助詞" + and token["pos"] != "終助詞" + and token["pos"] != "接続接尾辞" + and token["pos"] != "動詞活用語尾"): + if token["pos"] == "動詞接尾辞" and '終止' in token["features"]: + if ("する" in token["lemma"]) or ("ます" in token["lemma"]): + prime = "也" + elif "たい" in token["lemma"]: + prime = "希望" + elif token['lemma'] != 'ない': + prime = "了" + else: + prime = "実行" + else: + prime = token["form"] - if token['lemma'] == '私': - prime = '我' + if token['lemma'] == '私': + prime = '我' - if (token['lemma'] == '君' or token['lemma'] == 'あなた' or token['lemma'] == 'お前'): - prime = '你' + if (token['lemma'] == '君' or token['lemma'] == 'あなた' or token['lemma'] == 'お前'): + prime = '你' - if len(token["features"]) != 0: - if "SURU" in token["features"][0] : - prime = "実行" - elif "連体" in token['features'][0]: - prime = "的" - elif "疑問符" in token["features"][0]: - prime = "如何?" + if len(token["features"]) != 0: + if "SURU" in token["features"][0] : + prime = "実行" + elif "連体" in token['features'][0]: + prime = "的" + elif "疑問符" in token["features"][0]: + prime = "如何?" - result_list.append(hira_to_blank(prime)) + result_list.append(hira_to_blank(prime)) print(''.join(result_list))