Anri/feurBot
Archived
1
0
Fork 0
Code Issues 2 Pull requests Projects Releases Wiki Activity

adding some word automatically

Browse source
This commit is contained in:
Mylloon 2021-08-06 02:51:36 +02:00
parent ca209798f3
commit 0ef9e3291f
1 changed files with 6 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
main.py
View file

@ -44,6 +44,7 @@ def cleanTweet(tweet: str) -> str:
return "" # too much hashtags, ignoring tweet return "" # too much hashtags, ignoring tweet
tweet = sub(r"@\S+", " ", tweet) # remove usernames tweet = sub(r"@\S+", " ", tweet) # remove usernames
tweet = sub(r" *?[^\w\s]+", " ", tweet) # remove everything who is not a letter or a number or a space tweet = sub(r" *?[^\w\s]+", " ", tweet) # remove everything who is not a letter or a number or a space
tweet = sub(r"\S+(?=si|ci)", " ", tweet) # remove element of the word only if the last syllable can be matched (so more words will be answered without adding them manually)
tweet = sub(r"(?<=ui)i+|(?<=na)a+(?<!n)|(?<=quoi)i+|(?<=no)o+(?<!n)|(?<=hei)i+(?<!n)|(?<=si)i+", "", tweet) # remove key smashing in certains words tweet = sub(r"(?<=ui)i+|(?<=na)a+(?<!n)|(?<=quoi)i+|(?<=no)o+(?<!n)|(?<=hei)i+(?<!n)|(?<=si)i+", "", tweet) # remove key smashing in certains words
return tweet.strip() return tweet.strip()
@ -204,7 +205,7 @@ if __name__ == "__main__":
"non": ["non", "nn"], "non": ["non", "nn"],
"nan": ["nan"], "nan": ["nan"],
"hein": ["hein", "1"], "hein": ["hein", "1"],
"ci": ["ci", "si", "aussi"], "ci": ["ci", "si"],
"con": ["con"], "con": ["con"],
"ok": ["ok", "okay", "oké", "k"], "ok": ["ok", "okay", "oké", "k"],
"ouais": ["ouais", "oué"], "ouais": ["ouais", "oué"],