Spaces:
Build error
Build error
File size: 1,577 Bytes
3a1020a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
from zemberek import TurkishMorphology
from typing import List
from functools import lru_cache
morphology = TurkishMorphology.create()
# Initialize the Turkish morphology analyzer as a global constant
MORPHOLOGY = TurkishMorphology.create_with_default_resources()
@lru_cache(maxsize=1000) # Cache results for better performance
def is_verb_or_verbform_zemberek(word: str) -> bool:
"""
Check if a word is a verb or verbform using Zemberek analysis.
Args:
word (str): The word to analyze
Returns:
bool: True if the word is a verb or verbform, False otherwise
"""
try:
# Get the analysis result for the word
result = MORPHOLOGY.analyze(word)
# Return True if there's at least one analysis and it's a verb
return bool(result and "Verb" in result[0].primary_pos.value)
except Exception as e:
print(f"Error analyzing word '{word}': {str(e)}")
return False
def filter_verbs(words: List[str]) -> List[str]:
"""
Filter a list of words to keep only verbs and verbforms.
Args:
words (List[str]): List of words to filter
Returns:
List[str]: List containing only verbs and verbforms
"""
return [word for word in words if is_verb_or_verbform_zemberek(word)]
def main():
# Example usage
words = ["geliyor", "gitti", "yapmak", "kitap"]
filtered_words = filter_verbs(words)
print(f"Verbs found: {filtered_words}")
if __name__ == "__main__":
main()
|