def search(self, pattern, sequence, max_subs, max_ins, max_dels,
max_l_dist=None):
search_params = LevenshteinSearchParams(max_subs, max_ins,
max_dels, max_l_dist)
return list(
fnm_generic_lp(pattern, sequence, search_params)
)
def search(self, subsequence, sequence, max_subs):
if max_subs >= len(subsequence):
self.skipTest("avoiding calling fnm_generic_ngrams() " +
"with max_subs >= len(subsequence)")
search_params = LevenshteinSearchParams(max_subs, 0, 0, max_subs)
return consolidate_overlapping_matches(
fnm_generic_ngrams(subsequence, sequence, search_params))
def search(self, subsequence, sequence, max_subs):
return [
get_best_match_in_group(group) for group in group_matches(
c_fnm_generic_ngrams(
subsequence, sequence,
LevenshteinSearchParams(max_subs, 0, 0, max_subs)))
]
def search(self, pattern, sequence, max_subs, max_ins, max_dels,
max_l_dist=None):
search_params = LevenshteinSearchParams(max_subs, max_ins,
max_dels, max_l_dist)
return consolidate_overlapping_matches(
find_near_matches_generic(pattern, sequence, search_params)
)
def search(self, subsequence, sequence, max_l_dist):
return [
get_best_match_in_group(group) for group in group_matches(
fnm_generic_lp(
subsequence, sequence,
LevenshteinSearchParams(max_l_dist, max_l_dist, max_l_dist,
max_l_dist)))
]
def search(self, subsequence, sequence, max_subs):
if max_subs >= len(subsequence):
self.skipTest("avoiding calling c_fnm_generic_ngrams() " +
"with max_subs >= len(subsequence)")
return [
get_best_match_in_group(group) for group in group_matches(
c_fnm_generic_ngrams(
subsequence, sequence,
LevenshteinSearchParams(max_subs, 0, 0, max_subs)))
]
def search(self,
pattern,
sequence,
max_subs,
max_ins,
max_dels,
max_l_dist=None):
return hnm_generic_ngrams(
pattern, sequence,
LevenshteinSearchParams(max_subs, max_ins, max_dels, max_l_dist))
def search(self,
pattern,
sequence,
max_subs,
max_ins,
max_dels,
max_l_dist=None):
return list(
find_near_matches_generic(
pattern, sequence,
LevenshteinSearchParams(max_subs, max_ins, max_dels,
max_l_dist)))
def search(self,
pattern,
sequence,
max_subs,
max_ins,
max_dels,
max_l_dist=None):
return list(
c_fnm_generic_lp(
pattern, sequence,
LevenshteinSearchParams(
max_subs,
max_ins,
max_dels,
max_l_dist,
)))
def search(self,
pattern,
sequence,
max_subs,
max_ins,
max_dels,
max_l_dist=None):
return [
get_best_match_in_group(group) for group in group_matches(
c_fnm_generic_ngrams(
pattern, sequence,
LevenshteinSearchParams(
max_subs,
max_ins,
max_dels,
max_l_dist,
)))
]
def find_near_matches(subsequence,
sequence,
max_substitutions=None,
max_insertions=None,
max_deletions=None,
max_l_dist=None):
"""search for near-matches of subsequence in sequence
This searches for near-matches, where the nearly-matching parts of the
sequence must meet the following limitations (relative to the subsequence):
* the maximum allowed number of character substitutions
* the maximum allowed number of new characters inserted
* and the maximum allowed number of character deletions
* the total number of substitutions, insertions and deletions
(a.k.a. the Levenshtein distance)
"""
search_params = LevenshteinSearchParams(max_substitutions, max_insertions,
max_deletions, max_l_dist)
search_func = choose_search_func(search_params)
return search_func(subsequence, sequence, search_params)
def find_near_matches_in_file(subsequence,
sequence_file,
max_substitutions=None,
max_insertions=None,
max_deletions=None,
max_l_dist=None,
_chunk_size=2**20):
"""search for near-matches of subsequence in a file
This searches for near-matches, where the nearly-matching parts of the
sequence must meet the following limitations (relative to the subsequence):
* the maximum allowed number of character substitutions
* the maximum allowed number of new characters inserted
* and the maximum allowed number of character deletions
* the total number of substitutions, insertions and deletions
(a.k.a. the Levenshtein distance)
"""
search_params = LevenshteinSearchParams(max_substitutions, max_insertions,
max_deletions, max_l_dist)
search_class = choose_search_class(search_params)
if ('b' in getattr(sequence_file, 'mode', '')
or isinstance(sequence_file, io.RawIOBase)):
matches = _search_binary_file(subsequence,
sequence_file,
search_params,
search_class,
_chunk_size=_chunk_size)
else:
matches = _search_unicode_file(subsequence,
sequence_file,
search_params,
search_class,
_chunk_size=_chunk_size)
return search_class.consolidate_matches(matches)
def search(self, subsequence, sequence, max_subs):
return hnm_generic_ngrams(
subsequence, sequence,
LevenshteinSearchParams(max_subs, 0, 0, max_subs))
def search(self, subsequence, sequence, max_subs):
search_params = LevenshteinSearchParams(max_subs, 0, 0, max_subs)
return list(fnm_generic_lp(subsequence, sequence, search_params))
def search(self, subsequence, sequence, max_l_dist):
search_params = LevenshteinSearchParams(max_l_dist, max_l_dist,
max_l_dist, max_l_dist)
return consolidate_overlapping_matches(
fnm_generic_lp(subsequence, sequence, search_params))
def search(self, subsequence, sequence, max_l_dist):
return fnm_generic_ngrams(
subsequence, sequence,
LevenshteinSearchParams(max_l_dist, max_l_dist, max_l_dist,
max_l_dist))
def fnm_nodels_ngrams(sequence, subsequence, max_substitutions, max_insertions, max_l_dist=None):
return find_near_matches_no_deletions_ngrams(
sequence, subsequence, LevenshteinSearchParams(
max_substitutions, max_insertions, 0, max_l_dist,
)
)
def search(self, subsequence, sequence, max_subs):
return list(
c_fnm_generic_lp(
subsequence, sequence,
LevenshteinSearchParams(max_subs, 0, 0, max_subs)))
