iddlmZmZmZmZm Z m Z m ZmZddlmZdZdZdZddZddZ dd Zdd Z dd Zdd Zdd Z ddZy))ratio partial_ratiotoken_set_ratiotoken_sort_ratiopartial_token_set_ratiopartial_token_sort_ratioWRatioQRatio)utilsc|r3||ytj||}tj||}tt|||S)zT wrapper around rapidfuzz function to be compatible with the API of thefuzz r) force_ascii)r full_processintround)scorers1s2rrs ]/var/www/vps2.regionflexible.com/Desarrollo/venv/lib/python3.12/site-packages/thefuzz/fuzz.py_rapidfuzz_scorerrsM :    <    < uVB^$ %%c(tt||ddS)NF)r_ratiorrs rrr#s VRUE ::rc(tt||ddS)z[ Return the ratio of the most similar substring as a number between 0 and 100. F)r_partial_ratiors rrr's ^RUE BBrc(tt||||S)zu Return a measure of the sequences' similarity between 0 and 100 but sorting the token before comparing. )r_token_sort_ratiorrrrs rrr7s .B \ RRrc(tt||||S)z Return the ratio of the most similar substring as a number between 0 and 100 but sorting the token before comparing. )r_partial_token_sort_ratiors rrr?s !2r;  rc(tt||||SN)r_token_set_ratiors rrrIs -r2{L QQrc(tt||||Sr#)r_partial_token_set_ratiors rrrMs  "b+| rc(tt||||S)a Quick ratio comparison between two strings. Runs full_process from utils on both strings Short circuits if either of the strings is empty after processing. :param s1: :param s2: :param force_ascii: Allow only ASCII characters (Default: True) :full_process: Process inputs, used here to avoid double processing in extract functions (Default: True) :return: similarity ratio )r_QRatiors rr r Xs Wb"k< HHrc t||d|S)z Unicode quick ratio Calls QRatio with force_ascii set to False :param s1: :param s2: :return: similarity ratio Frr)r rrrs rUQRatior,hs "be, GGrc(tt||||S)aj Return a measure of the sequences' similarity between 0 and 100, using different algorithms. **Steps in the order they occur** #. Run full_process from utils on both strings #. Short circuit if this makes either string empty #. Take the ratio of the two processed strings (fuzz.ratio) #. Run checks to compare the length of the strings * If one of the strings is more than 1.5 times as long as the other use partial_ratio comparisons - scale partial results by 0.9 (this makes sure only full results can return 100) * If one of the strings is over 8 times as long as the other instead scale by 0.6 #. Run the other ratio functions * if using partial ratio functions call partial_ratio, partial_token_sort_ratio and partial_token_set_ratio scale all of these by the ratio based on length * otherwise call token_sort_ratio and token_set_ratio * all token based comparisons are scaled by 0.95 (on top of any partial scalars) #. Take the highest value from these results round it and return it as an integer. :param s1: :param s2: :param force_ascii: Allow only ascii characters :type force_ascii: bool :full_process: Process inputs, used here to avoid double processing in extract functions (Default: True) :return: )r_WRatiors rr r vsD Wb"k< HHrc t||d|S)z Return a measure of the sequences' similarity between 0 and 100, using different algorithms. Same as WRatio but preserving unicode. Fr*)r r+s rUWRatior0s "be, GGrN)TT)T)rapidfuzz.fuzzrrrrrr$rrrr&rr!r r.r r(r rr,r0rrr4sX    &;C SR I H"IJHr