o fw%@s ddlmZddlZddlZzddlmZWney0edkr(edddl mZYnwddl m Z e j e j e jd d Ze j e j e jd d Zd$ddZe j d%ddZd&ddZd&ddZe j d%ddZd&ddZd&ddZd&ddZd$ddZd&d d!Zd$d"d#ZdS)')unicode_literalsN) StringMatcherPyPyzYUsing slow pure-python SequenceMatcher. Install python-Levenshtein to remove this warning)SequenceMatcher)utilscCs.t||\}}td||}td|S)Nd)rmake_type_consistentrintrratio)s1s2mrH/home/ubuntu/webapp/venv/lib/python3.10/site-packages/fuzzywuzzy/fuzz.pyr s r c Cst||\}}t|t|kr|}|}n|}|}td||}|}g}|D]8}|d|ddkr;|d|dnd}|t|} ||| } td|| } | } | dkrZdS|| q'tdt|S)zR"Return the ratio of the most similar substring as a number between 0 and 100.Nrrgףp= ?r) rr lenrget_matching_blocksr appendr max) r r shorterlongerrblocksscoresblock long_startlong_end long_substrm2rrrr partial_ratios& (    rTcCs4|r tj||dn|}|}dt|}|S)z*Return a cleaned string with token sorted. force_ascii )r full_processsplitjoinsortedstrip)sr!r#tstokens sorted_stringrrr_process_and_sortKsr,cCs4t|||d}t|||d}|rt||St||S)Nr#)r,rr )r r partialr!r#sorted1sorted2rrr _token_sortZs   r1cCt||d||dS)zpReturn a measure of the sequences' similarity between 0 and 100 but sorting the token before comparing. Fr.r!r#r1r r r!r#rrrtoken_sort_ratioer6cCr2)z}Return the ratio of the most similar substring as a number between 0 and 100 but sorting the token before comparing. Tr3r4r5rrrpartial_token_sort_ratiolr7r8cCs|s||krdS|rtj||dn|}|rtj||dn|}t|s%dSt|s,dSt|}t|}||} ||} ||} dt| } dt| } dt| }| d| }| d|}| } | }| }|ryt }nt }|| ||| ||||g}t |S)a Find all alphanumeric tokens in each string... - treat them as a set - construct two strings of the form: - take ratios of those two strings - controls for unordered partial matchesrr rr") rr#validate_stringsetr$ intersection differencer%r&r'rr r)r r r.r!r#p1p2tokens1tokens2r;diff1to2diff2to1 sorted_sect sorted_1to2 sorted_2to1 combined_1to2 combined_2to1 ratio_funcpairwiserrr _token_setss:          rJcCr2)NFr3rJr5rrrtoken_set_ratiorLcCr2)NTr3rKr5rrrpartial_token_set_ratiorMrNcCsP|rtj||d}tj||d}n|}|}t|sdSt|s#dSt||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 r)rr#r9r )r r r!r#r=r>rrrQRatios   rOcCt||d|dS)z Unicode quick ratio Calls QRatio with force_ascii set to False :param s1: :param s2: :return: similarity ratio Fr!r#)rOr r r#rrrUQRatios rScCs$|rtj||d}tj||d}n|}|}t|sdSt|s#dSd}d}d}t||} ttt|t|tt|t|} | dkrHd}| dkrNd }|rwt|||} t ||dd ||} t ||dd ||} t t| | | | St ||dd |}t ||dd |}t t| ||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 rTgffffff?g?g?Fg333333?r-)rr#r9r floatrrminrr8rNr r6rL)r r r!r#r=r> try_partial unbase_scale partial_scalebase len_ratior.ptsorptsertsortserrrrWRatiosD#   (  r`cCrP)zReturn a measure of the sequences' similarity between 0 and 100, using different algorithms. Same as WRatio but preserving unicode. FrQ)r`rRrrrUWRatio.sra)T)TTT)TT) __future__rplatformwarningsrr ImportErrorpython_implementationwarndifflibrcheck_for_nonecheck_for_equivalencecheck_empty_stringr rr,r1r6r8rJrLrNrOrSr`rarrrrs@      )    4   N