Created
May 23, 2023 09:22
-
-
Save angstyloop/6a3100cc39bafc279fba74a222101174 to your computer and use it in GitHub Desktop.
Find the first match of a pattern string in a target string with a given maximum allowed number of substitution errors. Written in C. Stolen from Wikipedia's article on the Bitap algorithm.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/* | |
COMPILE | |
gcc -o bitapp bitapp.c | |
RUN | |
./bitap | |
*/ | |
#include <stdlib.h> | |
#include <string.h> | |
#include <limits.h> | |
#include <stdio.h> | |
/* Find the first match of @pattern in @string with at most @k substitution | |
* errors. | |
* | |
* @text - The string we are searching to find @pattern. | |
* | |
* @pattern - The string we are trying to find in @text. | |
* | |
* @k - The maximum number of allowed errors. If k is zero, then the match is | |
* exact. | |
* | |
* @returns A pointer to the character in @text where the first match found | |
* starts. | |
*/ | |
const char *bitap_fuzzy_bitwise_search( const char *text, | |
const char *pattern, int k) | |
{ | |
const char *result = NULL; | |
int m = strlen(pattern); | |
unsigned long *R; | |
unsigned long pattern_mask[CHAR_MAX+1]; | |
int i, d; | |
if (pattern[0] == '\0') return text; | |
if (m > 31) return "The pattern is too long!"; | |
/* Initialize the bit array R */ | |
R = malloc((k+1) * sizeof *R); | |
for (i=0; i <= k; ++i) | |
R[i] = ~1; | |
/* Initialize the pattern bitmasks */ | |
for (i=0; i <= CHAR_MAX; ++i) | |
pattern_mask[i] = ~0; | |
for (i=0; i < m; ++i) | |
pattern_mask[pattern[i]] &= ~(1UL << i); | |
for (i=0; text[i] != '\0'; ++i) { | |
/* Update the bit arrays */ | |
unsigned long old_Rd1 = R[0]; | |
R[0] |= pattern_mask[text[i]]; | |
R[0] <<= 1; | |
for (d=1; d <= k; ++d) { | |
unsigned long tmp = R[d]; | |
/* Substitution is all we care about */ | |
R[d] = (old_Rd1 & (R[d] | pattern_mask[text[i]])) << 1; | |
old_Rd1 = tmp; | |
} | |
if (0 == (R[k] & (1UL << m))) { | |
result = (text+i - m) + 1; | |
break; | |
} | |
} | |
free(R); | |
return result; | |
} | |
int main() { | |
const char *text = "hhhhhhhhhhhhereeeeeeeeeeeeeeeee"; | |
const char *pattern = "heee"; | |
int k = 1; | |
const char *a = | |
bitap_fuzzy_bitwise_search( text, pattern, k ); | |
puts( a ); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment