o f,@sddlmZddlmZddlZddlZddlmZejZej Z e edfddZ e edfd d Z e eddfd d Z e edfd dZdejfddZdS))fuzz)utilsN)partialc csdd}z|dust|dkrWdSWn tyYnw|dur$|}||}t|dkr6td||tjtjtjtj tj tj tj tj fvrQ|tjkrQ|}|tj tj fvrgttjdd}t|dd}n |tjtjtjtj tj tj fvrttjd d}t|dd}n|}||}z!|D]\}} ||| } ||| } | |kr| | |fVqWdSty|D]} ||| } ||| } | |kr| | fVqYdSw) a Select the best match in a list or dictionary of choices. Find best matches in a list or dictionary of choices, return a generator of tuples containing the match and its score. If a dictionary is used, also returns the key for each match. Arguments: query: An object representing the thing we want to find. choices: An iterable or dictionary-like object containing choices to be matched against the query. Dictionary arguments of {key: value} pairs will attempt to match the query against each value. processor: Optional function of the form f(a) -> b, where a is the query or individual choice and b is the choice to be used in matching. This can be used to match against, say, the first element of a list: lambda x: x[0] Defaults to fuzzywuzzy.utils.full_process(). scorer: Optional function for scoring matches between the query and an individual processed choice. This should be a function of the form f(query, choice) -> int. By default, fuzz.WRatio() is used and expects both query and choice to be strings. score_cutoff: Optional argument for score threshold. No matches with a score less than this number will be returned. Defaults to 0. Returns: Generator of tuples containing the match and its score. If a list is used for choices, then the result will be 2-tuples. If a dictionary is used, then the result will be 3-tuples containing the key for each match. For example, searching for 'bird' in the dictionary {'bard': 'train', 'dog': 'man'} may return ('train', 22, 'bard'), ('man', 0, 'dog') cSs|S)NxrrK/home/ubuntu/webapp/venv/lib/python3.10/site-packages/fuzzywuzzy/process.py no_process?sz'extractWithoutOrder..no_processNrzhApplied processor reduces input query to empty string, all comparisons will have score 0. [Query: '{0}']F) force_ascii) full_processT)len TypeErrorloggingwarningformatrWRatioQRatiotoken_set_ratiotoken_sort_ratiopartial_token_set_ratiopartial_token_sort_ratioUWRatioUQRatiorr ritemsAttributeError) querychoices processorscorer score_cutoffr processed_query pre_processorkeychoice processedscorerrr extractWithoutOrdersf/            r'cCs<t||||}|durtj||dddSt|ddddS)aSelect the best match in a list or dictionary of choices. Find best matches in a list or dictionary of choices, return a list of tuples containing the match and its score. If a dictionary is used, also returns the key for each match. Arguments: query: An object representing the thing we want to find. choices: An iterable or dictionary-like object containing choices to be matched against the query. Dictionary arguments of {key: value} pairs will attempt to match the query against each value. processor: Optional function of the form f(a) -> b, where a is the query or individual choice and b is the choice to be used in matching. This can be used to match against, say, the first element of a list: lambda x: x[0] Defaults to fuzzywuzzy.utils.full_process(). scorer: Optional function for scoring matches between the query and an individual processed choice. This should be a function of the form f(query, choice) -> int. By default, fuzz.WRatio() is used and expects both query and choice to be strings. limit: Optional maximum for the number of elements returned. Defaults to 5. Returns: List of tuples containing the match and its score. If a list is used for choices, then the result will be 2-tuples. If a dictionary is used, then the result will be 3-tuples containing the key for each match. For example, searching for 'bird' in the dictionary {'bard': 'train', 'dog': 'man'} may return [('train', 22, 'bard'), ('man', 0, 'dog')] NcS|dSNrrirrr zextract..r#cSr)r*rr+rrr r-r.Tr#reverser'heapqnlargestsorted)rrrrlimitslrrr extractzs-r8cCs>t|||||}|durtj||dddSt|ddddS)aGet a list of the best matches to a collection of choices. Convenience function for getting the choices with best scores. Args: query: A string to match against choices: A list or dictionary of choices, suitable for use with extract(). processor: Optional function for transforming choices before matching. See extract(). scorer: Scoring function for extract(). score_cutoff: Optional argument for score threshold. No matches with a score less than this number will be returned. Defaults to 0. limit: Optional maximum for the number of elements returned. Defaults to 5. Returns: A a list of (match, score) tuples. NcSr)r*rr+rrr r-r.zextractBests..r/cSr)r*rr+rrr r-r.Tr0r2)rrrrr r6 best_listrrr extractBestssr:cCs8t|||||}z t|dddWStyYdSw)a_Find the single best match above a score in a list of choices. This is a convenience method which returns the single best choice. See extract() for the full arguments list. Args: query: A string to match against choices: A list or dictionary of choices, suitable for use with extract(). processor: Optional function for transforming choices before matching. See extract(). scorer: Scoring function for extract(). score_cutoff: Optional argument for score threshold. If the best match is found, but it is not greater than this number, then return None anyway ("not a good enough match"). Defaults to 0. Returns: A tuple containing a single match and its score, if a match was found that was above score_cutoff. Otherwise, returns None. cSr)r*rr+rrr r-r.zextractOne..r/N)r'max ValueError)rrrrr r9rrr extractOnes  r=Fc sg}|D]=}t||d|d}fdd|D}t|dkr'||ddqt|ddd }t|d dd d }||ddqi}|D]} d|| <qF|}t|t|kr[|S|S) aThis convenience function takes a list of strings containing duplicates and uses fuzzy matching to identify and remove duplicates. Specifically, it uses the process.extract to identify duplicates that score greater than a user defined threshold. Then, it looks for the longest item in the duplicate list since we assume this item contains the most entity information and returns that. It breaks string length ties on an alphabetical sort. Note: as the threshold DECREASES the number of duplicates that are found INCREASES. This means that the returned deduplicated list will likely be shorter. Raise the threshold for fuzzy_dedupe to be less sensitive. Args: contains_dupes: A list of strings that we would like to dedupe. threshold: the numerical value (0,100) point at which we expect to find duplicates. Defaults to 70 out of 100 scorer: Optional function for scoring matches between the query and an individual processed choice. This should be a function of the form f(query, choice) -> int. By default, fuzz.token_set_ratio() is used and expects both query and choice to be strings. Returns: A deduplicated list. For example: In: contains_dupes = ['Frodo Baggin', 'Frodo Baggins', 'F. Baggins', 'Samwise G.', 'Gandalf', 'Bilbo Baggins'] In: fuzzy_dedupe(contains_dupes) Out: ['Frodo Baggins', 'Samwise G.', 'Bilbo Baggins', 'Gandalf'] N)r6rcsg|] }|dkr|qS)rr).0r thresholdrr szdedupe..rrcSr)Nrrrrrr r- r.zdedupe..r/cSs t|dSrC)r rrrr r-s Tr0)r8r appendr5keys) contains_dupesrAr extractoritemmatchesfiltered filter_sortrEerr@r dedupes   rM)rrr3r functoolsrrdefault_scorerr default_processorr'r8r:r=rrMrrrr s   j2