pyobjc-framework-naturallanguage

import NaturalLanguage from Foundation import NSMakeRange text_to_analyze = "The quick brown fox jumps over the lazy dog. This is a second sentence." # --- Tokenization Example --- # Create an NLTokenizer instance for word units tokenizer = NaturalLanguage.NLTokenizer.alloc().initWithUnit_(NaturalLanguage.NLTokenUnitWord) # Set the string to be tokenized tokenizer.setString_(text_to_analyze) tokens = [] # Enumerate tokens using a Python callable as the Objective-C block def token_block_handler(token_range, flags): start = token_range.location length = token_range.length token_text = text_to_analyze[start : start + length] tokens.append(token_text) return True # Return True to continue enumeration tokenizer.enumerateTokensInRange_usingBlock_( NSMakeRange(0, len(text_to_analyze)), token_block_handler ) print(f"Original text: '{text_to_analyze}'") print(f"Tokens (words): {tokens}") # --- Language Recognition Example --- lang_recognizer = NaturalLanguage.NLLanguageRecognizer.alloc().init() lang_recognizer.processString_(text_to_analyze) dominant_language = lang_recognizer.dominantLanguage() print(f"Dominant language: {dominant_language}")