Updated this to the latest version of develop, got rid of most of the duplication, might be missing some packages in toml, needs testing

This commit is contained in:
Carlos Mesquita
2024-08-30 02:35:11 +01:00
parent 3cf9fa5cba
commit f92a803d96
73 changed files with 3642 additions and 2703 deletions

28
app/helpers/text.py Normal file
View File

@@ -0,0 +1,28 @@
from nltk.corpus import words
class TextHelper:
@classmethod
def has_words(cls, text: str):
if not cls._has_common_words(text):
return False
english_words = set(words.words())
words_in_input = text.split()
return any(word.lower() in english_words for word in words_in_input)
@classmethod
def has_x_words(cls, text: str, quantity):
if not cls._has_common_words(text):
return False
english_words = set(words.words())
words_in_input = text.split()
english_word_count = sum(1 for word in words_in_input if word.lower() in english_words)
return english_word_count >= quantity
@staticmethod
def _has_common_words(text: str):
english_words = {"the", "be", "to", "of", "and", "a", "in", "that", "have", "i"}
words_in_input = text.split()
english_word_count = sum(1 for word in words_in_input if word.lower() in english_words)
return english_word_count >= 10