grail/common-words
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Feat: filter out more words

Browse Source
This commit is contained in:
Grail Finder
2025-06-19 18:38:01 +03:00
parent 067ad1821c
commit 5235cfef47
3 changed files with 5362 additions and 5391 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
main.py
View File

@ -32,7 +32,9 @@ numerical = {
"dozen", "score", "gross", # Traditional counting units
}
names = {"martin", "ben", "john", "maxwell", "ruth", "charlotte", "ada", "dick", "timothy", "earl", "geneva"}
innapropriate = {"nigger", "vagina", "rape", "penis"}
names = {"martin", "ben", "john", "maxwell", "ruth", "charlotte", "ada", "dick", "timothy", "earl", "geneva", "bobby"}
difficult = {
"aerator", "transducer", "substrate",
@ -86,7 +88,8 @@ def get_words():
continue # winning, twisiting; only want win, twist or feelings
if word.endswith("s") and not word.endswith("ss"):
continue # leave dutschess but skip provisions
if word in numerical: # skip numbers
# exceptions
if word in numerical or word in names or word in difficult or word in innapropriate:
continue
# If base form matches the word, it's singular/uncountable
if base_form == word: