taleinat
/
fuzzysearch
mirror of https://github.com/taleinat/fuzzysearch.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

added substitutions_only_has_near_matches_byteslike to benchmarks

This commit is contained in:
Tal Einat 2014-04-12 19:48:04 +03:00
parent 0d41826ff9
commit c2330cfb54
1 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
benchmarks/__init__.py
View File

@ -8,6 +8,8 @@ from fuzzysearch.substitutions_only import \
find_near_matches_substitutions_ngrams as fnm_substitutions_ngrams, \ find_near_matches_substitutions_ngrams as fnm_substitutions_ngrams, \
find_near_matches_substitutions_linear_programming, \ find_near_matches_substitutions_linear_programming, \
has_near_match_substitutions_ngrams has_near_match_substitutions_ngrams
from fuzzysearch._substitutions_only import \
substitutions_only_has_near_matches_byteslike
from fuzzysearch.generic_search import \ from fuzzysearch.generic_search import \
find_near_matches_generic_linear_programming, \ find_near_matches_generic_linear_programming, \
find_near_matches_generic_ngrams, has_near_match_generic_ngrams find_near_matches_generic_ngrams, has_near_match_generic_ngrams
@ -44,6 +46,10 @@ def hnm_substitutions_ngrams(subsequence, sequence, max_l_dist):
return has_near_match_substitutions_ngrams( return has_near_match_substitutions_ngrams(
subsequence, sequence, max_l_dist) subsequence, sequence, max_l_dist)
def hnm_substitutions_byteslike(subsequence, sequence, max_l_dist):
return substitutions_only_has_near_matches_byteslike(
subsequence, sequence, max_l_dist)
search_functions = { search_functions = {
'levenshtein_lp': fnm_levenshtein_lp, 'levenshtein_lp': fnm_levenshtein_lp,
@ -55,6 +61,7 @@ search_functions = {
'generic_ngrams': fnm_generic_ngrams, 'generic_ngrams': fnm_generic_ngrams,
'has_match_generic_ngrams': hnm_generic_ngrams, 'has_match_generic_ngrams': hnm_generic_ngrams,
'has_match_substitutions_ngrams': hnm_substitutions_ngrams, 'has_match_substitutions_ngrams': hnm_substitutions_ngrams,
'has_match_substitutions_byteslike': hnm_substitutions_byteslike,
} }
benchmarks = { benchmarks = {
@ -85,7 +92,7 @@ def get_benchmark(search_func_name, benchmark_name):
search_func = search_functions[search_func_name] search_func = search_functions[search_func_name]
search_args = dict(benchmarks[benchmark_name]) search_args = dict(benchmarks[benchmark_name])
if search_func in (fnm_levenshtein_ngrams, fnm_levenshtein_lp, fnm_generic_lp, fnm_generic_lp_cython, fnm_generic_ngrams, hnm_generic_ngrams, hnm_substitutions_ngrams): if search_func in (fnm_levenshtein_ngrams, fnm_levenshtein_lp, fnm_generic_lp, fnm_generic_lp_cython, fnm_generic_ngrams, hnm_generic_ngrams, hnm_substitutions_ngrams, hnm_substitutions_byteslike):
search_args['max_l_dist'] = search_args.pop('max_dist') search_args['max_l_dist'] = search_args.pop('max_dist')
elif search_func in (fnm_substitutions_ngrams, fnm_substitutions_lp): elif search_func in (fnm_substitutions_ngrams, fnm_substitutions_lp):
search_args['max_substitutions'] = search_args.pop('max_dist') search_args['max_substitutions'] = search_args.pop('max_dist')