ї ■j*ЦС┌≈UddlZddlmZddlmZmZejdkrddlmZnddlmZddl Z ddl m Zddl mZ ddl mZd Zeeed <dedefd └Zee╛і╚dedeefd└і╚Zee╛і╚dedeefd└і╚Zee╛і╚dedeeeeffd└і╚Z dS)ИN)з lru_cache)зListзTuple)ИИ)зFinal)зpos_tag)з sent_tokenize)з word_tokenizeИ─зCACHE_MAX_SIZEзpackage_nameзpackage_categorycС└≈ tj|⌡d|⌡²і╚dS#t$rtj|і╚YdSwxYw)z8If the required nlt package is not present, download it.З/N)зnltkзfindзLookupErrorзdownload)rrs Зc/lsinfo/ai/hellotax_ai/base_platform/venv/lib/python3.11/site-packages/unstructured/nlp/tokenize.pyз%_download_nltk_package_if_not_presentrs`─П$щ▄ п%п6п6╗п6п6я7т7п7п7п7ЬщП$П$П$щ▄ ░lя#т#п#п#п#п#П$ЬЬЬs┌²?Ў?)зmaxsizeзtextзreturncСB≈tdd╛і╚t|і╚S)zFA wrapper around the NLTK sentence tokenizer with LRU caching enabled.з tokenizersзpunkt╘rr)rз_sent_tokenize╘rs rr r С&─У*╦<пV]п^я^т^п^щ≤$ятпСcСB≈tdd╛і╚t|і╚S)zBA wrapper around the NLTK word tokenizer with LRU caching enabled.rrr)rз_word_tokenizer s rrr!r!r"cСь≈tdd╛і╚tdd╛і╚t|і╚}g}|D]3}t|і╚}|═t |і╚і╚▄4|S)z>A wrapper around the NLTK POS tagger with LRU caching enabled.rrrзtaggersзaveraged_perceptron_tagger)rrr$зextendз_pos_tag)rз sentencesзparts_of_speechзsentenceзtokenss rr r (s┼─У*╦<пV]п^я^т^п^щ)ь"ь1ПЯТПУ≤tя$т$─Iь─OьП1П1┬щ═я)т)┬ьвр²x╗я/т/я0т0п0п0ьпr")зsysз functoolsrзtypingrrзversion_infoзtyping_extensionsrrr r)r rrr$r зintз__annotations__зstrr╘r"rЗr7sЇПь ─ ─ ─ ─ ьпппппьпппппппЮт░fрпь'п'п'п'п'п'п'ЮпппппЮ───ь$п$п$п$п$п$ь0п0п0п0п0п0ь0п0п0п0п0п0Ю ─░░c■ п п я П$╦П$хsП$П$П$П$П─░>п"я"т"П ≤П ══Sє П П П Я#т"П П─░>п"я"т"П ≤П ══Sє П П П Я#т"П П─░>п"я"т"П░#П≤$≤u═S╗#═X°т/ПППЯ#т"ПППr"