def index_search(self, pattern):
padding = self.depth - len(pattern)
if padding > 0:
start_key = pattern + ("A" * padding)
start_int = self.kmer_to_int(start_key) - 1
end_key = pattern + ("T" * padding)
end_int = self.kmer_to_int(end_key) + 1
else:
start_key = pattern[0:self.depth]
start_int = self.kmer_to_int(start_key)
end_int = start_int + 1
while not start_int in self.index_dict and start_int >= self.lower_bound:
start_int -= 1
start = self.index_dict[
start_int] if start_int in self.index_dict else 0
while not end_int in self.index_dict and end_int <= self.upper_bound:
end_int += 1
end = self.index_dict[end_int] if end_int in self.index_dict else len(
self.suffix_array) - 1
return sa_utils.simple_accelerant(self.corpus_str,
self.suffix_array,
pattern,
initL=start,
initR=end)
def search(self, search_string): """ return: collection (list) int of offsets in original string where substring can be found """ if not self.sa or not self.lcp: raise ValueError else: search_string = search_string if not self.force_unicode else unicode(search_string, 'utf-8', 'replace') sa_i = sa_utils.simple_accelerant(self.corpus_str, self.sa, search_string) return sa_utils.lcp_scan(self.lcp, self.sa, search_string, sa_i) if sa_i >= 0 else []
def search(self, search_string):
"""
return: collection (list) int of offsets in original string where substring can be found
"""
if not self.sa or not self.lcp:
raise ValueError
else:
search_string = search_string if not self.force_unicode else unicode(
search_string, 'utf-8', 'replace')
sa_i = sa_utils.simple_accelerant(self.corpus_str, self.sa,
search_string)
return sa_utils.lcp_scan(self.lcp, self.sa, search_string,
sa_i) if sa_i >= 0 else []
def index_search(self, pattern):
padding = self.depth - len(pattern)
if padding > 0:
start_key = pattern + ("A" * padding)
start_int = self.kmer_to_int(start_key) - 1
end_key = pattern + ("T" * padding)
end_int = self.kmer_to_int(end_key) + 1
else:
start_key = pattern[0:self.depth]
start_int = self.kmer_to_int(start_key)
end_int = start_int + 1
while not start_int in self.index_dict and start_int >= self.lower_bound:
start_int -= 1
start = self.index_dict[start_int] if start_int in self.index_dict else 0
while not end_int in self.index_dict and end_int <= self.upper_bound:
end_int += 1
end = self.index_dict[end_int] if end_int in self.index_dict else len(self.suffix_array) - 1
return sa_utils.simple_accelerant(self.corpus_str, self.suffix_array, pattern, initL=start, initR=end)
