in misc/precision_filtering/wordlist_score.py [0:0]
def filter_score(text, lang):
text = simplify_text(str(text).strip(), norm_config)
# Split the text into words and convert it to a set
words = set(split_into_words(text, lang))
# Get the list of words for the specified language and convert it to a set
lang_words = loaded_language_dict[lang] # Convert to set for faster lookups
# Count how many words from the text appear in the language's word list
matching_words = len(words & lang_words) # Use set intersection to count matches
# Calculate the normalized score (between 0 and 1)
score = matching_words / len(words) if words else 0 # Avoid division by zero if text is empty
return score