def distance(self, string_1, string_2, max_distance):
if string_1 is None or string_2 is None:
return helpers.null_distance_results(string_1, string_2,
max_distance)
if max_distance <= 0:
return 0 if string_1 == string_2 else -1
max_distance = int(min(2 ** 31 - 1, max_distance))
# if strings of different lengths, ensure shorter string is in string_1.
# This can result in a little faster speed by spending more time
# spinning just the inner loop during the main processing.
if len(string_1) > len(string_2):
string_2, string_1 = string_1, string_2
if len(string_2) - len(string_1) > max_distance:
return -1
# identify common suffix and/or prefix that can be ignored
len_1, len_2, start = helpers.prefix_suffix_prep(string_1, string_2)
if len_1 == 0:
return len_2 if len_2 <= max_distance else -1
if len_2 > len(self._base_char_1_costs):
self._base_char_1_costs = np.zeros(len_2, dtype=np.int32)
self._base_prev_char_1_costs = np.zeros(len_2, dtype=np.int32)
if max_distance < len_2:
return self._distance_max(string_1, string_2, len_1, len_2, start,
max_distance, self._base_char_1_costs,
self._base_prev_char_1_costs)
return self._distance(string_1, string_2, len_1, len_2, start,
self._base_char_1_costs,
self._base_prev_char_1_costs)
def distance(self, string_1: str, string_2: str, max_distance: int) -> int:
"""Computes the Damerau-Levenshtein optimal string alignment edit
distance between two strings.
Args:
string_1: One of the strings to compare.
string_2: The other string to compare.
max_distance: The maximum distance that is of interest.
Returns:
-1 if the distance is greater than the max_distance, 0 if the strings
are equivalent, otherwise a positive number whose magnitude
increases as difference between the strings increases.
"""
if string_1 is None or string_2 is None:
return helpers.null_distance_results(string_1, string_2,
max_distance)
if max_distance <= 0:
return 0 if string_1 == string_2 else -1
max_distance = int(min(2**31 - 1, max_distance))
# if strings of different lengths, ensure shorter string is in string_1.
# This can result in a little faster speed by spending more time spinning
# just the inner loop during the main processing.
if len(string_1) > len(string_2):
string_2, string_1 = string_1, string_2
if len(string_2) - len(string_1) > max_distance:
return -1
# identify common suffix and/or prefix that can be ignored
len_1, len_2, start = helpers.prefix_suffix_prep(string_1, string_2)
if len_1 == 0:
return len_2 if len_2 <= max_distance else -1
if len_2 > len(self._base_char_1_costs):
self._base_char_1_costs = [0 for _ in range(len_2)]
self._base_prev_char_1_costs = [0 for _ in range(len_2)]
if max_distance < len_2:
return self._distance_max(
string_1,
string_2,
len_1,
len_2,
start,
max_distance,
self._base_char_1_costs,
self._base_prev_char_1_costs,
)
return self._distance(
string_1,
string_2,
len_1,
len_2,
start,
self._base_char_1_costs,
self._base_prev_char_1_costs,
)
def distance(self, string_1, string_2, max_distance):
"""Compute and return the Levenshtein edit distance between two
strings.
Parameters
----------
string_1 : str
One of the strings to compare.
string_2 : str
The other string to compare.
max_distance : int
The maximum distance that is of interest.
Returns
-------
int
-1 if the distance is greater than the maxDistance, 0 if
the strings are equivalent, otherwise a positive number
whose magnitude increases as difference between the strings
increases.
"""
if string_1 is None or string_2 is None:
return helpers.null_distance_results(string_1, string_2,
max_distance)
if max_distance <= 0:
return 0 if string_1 == string_2 else -1
max_distance = max_distance = int(min(2**31 - 1, max_distance))
# if strings of different lengths, ensure shorter string is in
# string_1. This can result in a little faster speed by
# spending more time spinning just the inner loop during the
# main processing.
if len(string_1) > len(string_2):
string_2, string_1 = string_1, string_2
if len(string_2) - len(string_1) > max_distance:
return -1
# identify common suffic and/or prefix that can be ignored
len_1, len_2, start = helpers.prefix_suffix_prep(string_1, string_2)
if len_1 == 0:
return len_2 if len_2 <= max_distance else -1
if len_2 > len(self._base_char_1_costs):
self._base_char_1_costs = np.zeros(len_2, dtype=np.int32)
if max_distance < len_2:
return self._distance_max(string_1, string_2, len_1, len_2, start,
max_distance, self._base_char_1_costs)
return self._distance(string_1, string_2, len_1, len_2, start,
self._base_char_1_costs)
