yoxem/pseudo-chinese
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix bugs

Browse source
This commit is contained in:
Tan, Kian-ting 2021-08-14 21:26:32 +08:00
parent 7cf211fa84
commit 5a12599eb9
1 changed files with 10 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
pseudo-chinese.py
View file

@ -1,5 +1,6 @@
import MeCab import MeCab
import sys import sys
import re
# 形態素解析する関数 # 形態素解析する関数
@ -46,7 +47,8 @@ if __name__ == "__main__":
#print(parse_document) #print(parse_document)
result_list = list() result_list = list()
for token in parse_document: for i, token in enumerate(parse_document):
# 形態素解析結果に置き換えルールを適用する # 形態素解析結果に置き換えルールを適用する
if (token["pos"] != "助詞-格助詞" if (token["pos"] != "助詞-格助詞"
and token["pos"] != "助詞-接続助詞" and token["pos"] != "助詞-接続助詞"
@ -73,16 +75,20 @@ if __name__ == "__main__":
if (token['lemma'] == '君' or token['lemma'] == '貴方' or token['lemma'] == 'お前'): if (token['lemma'] == '君' or token['lemma'] == '貴方' or token['lemma'] == 'お前'):
prime = '你' prime = '你'
if token['lemma'] == '為る' and parse_document[i-1]['pos'] == '名詞-普通名詞-サ変可能':
prime = ''
if token['lemma'] == '円-助数詞':
prime = '円' compound_matched = re.match("([^-]+)-([^-]+)", token['lemma'])
if compound_matched:
prime = compound_matched.group(1)
if len(token["features"]) != 0: if len(token["features"]) != 0:
if "連体形-一般" in token['features']: if "連体形-一般" in token['features']:
if token['lemma'] == 'ない': if token['lemma'] == 'ない':
prime = "無之" prime = "無之"
else: else:
prime = "之" prime = prime + "之"
result_list.append(hira_to_blank(prime)) result_list.append(hira_to_blank(prime))