Using C language to solve the string matching problem
- 2020-04-02 03:14:20
- OfStack
The most common approach is to use the KMP string matching algorithm:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int get_nextval(char *pattern, int next[])
{
//get the next value of the pattern
int i = 0, j = -1;
next[0] = -1;
int patlen = strlen(pattern);
while ( i < patlen - 1){
if ( j == -1 || pattern[i] == pattern[j]){
++i;
++j;
if (pattern[i] != pattern[j])
next[i] = j;
else
next[i] = next[j];
}
else
j = next[j];
}
return(0);
}
int kmpindex(char *target, char *pattern, int pos)
{
int tari = pos, pati = 0;
int tarlen = strlen(target), patlen = strlen(pattern);
int *next = (int *)malloc(patlen * sizeof(int));
get_nextval(pattern, next);
while ( tari < tarlen && pati < patlen ){
if (pati == -1 ||target[tari] == pattern[pati]){
++tari;
++pati;
}else{
pati = next[pati];
}
}
if(next != NULL) free(next);
next = NULL;
if (pati == patlen)
return tari - pati;
else
return -1;
}
int main()
{
char target[50], pattern[50];
printf("imput the target:n" );
scanf("%s",target);
printf("imput the pattern:n" );
scanf("%s",pattern);
int ans = kmpindex(target,pattern,0);
if (ans == -1)
printf("errorn");
else
printf("index:%dn",ans);
return 0;
}
exercises
Title description:
Read in the data string[], and then read in a short string. It is required to find all matches between string[] and short string, and output line number and matching string. Matches are case-insensitive and can have a pattern match represented by brackets. For example, "aa[123]bb" means that aa1bb, aa2bb and aa3bb are all matched.
Input:
The input has multiple sets of data.
Enter n(1) in the first row of each set of data
<
= n
<
=1000), starting with the second line, enter n strings (no Spaces), then enter a matching string.
Output:
Outputs the line number of the matched string and the string (matching case insensitive).
Sample input:
4
Aab
a2B
ab
ABB
A [a2b] b
Sample output:
1 Aab
2 a2B
4 ABB
Ac code
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define MAX 1001
#define LEN 101
struct str
{
char name[101];
};
int main()
{
struct str strs[MAX];
struct str t[LEN];
int i, n, len, j, k, left, right, count, flag;
char text[LEN], newtext[LEN];
while (scanf("%d", &n) != EOF) {
//Receive data
getchar();
for (i = 0; i < n; i ++) {
scanf("%s", strs[i].name);
}
//Received text string
getchar();
gets(text);
len = strlen(text);
for (i = left = right = 0; i < len; i ++) {
if (text[i] == '[') {
left = i;
} else if (text[i] == ']') {
right = i;
break;
}
}
count = right - left - 1;
if (count <= 0) { //No regular match
for (i = j = 0; i < len; i ++) {
if (text[i] != '[' && text[i] != ']') {
newtext[j ++] = text[i];
}
}
newtext[j] = '0';
for (i = 0; i < n; i ++) {
if (strcasecmp(strs[i].name, newtext) == 0) {
printf("%d %sn", i + 1, strs[i].name);
}
}
}else { //You need regular matching
for (j = 1, k = 0; j <= count; j ++, k ++) { //Building a text array
memset(t[k].name, '0', sizeof(t[k].name));
for (i = 0; i < left; i ++) {
t[k].name[i] = text[i];
}
t[k].name[i] = text[left + j];
strcat(t[k].name, text + right + 1);
}
//Regular match
for (i = 0; i < n; i ++) {
for (j = flag = 0; j < count; j ++) {
if (strcasecmp(strs[i].name, t[j].name) == 0) {
flag = 1;
break;
}
}
if (flag) {
printf("%d %sn", i + 1, strs[i].name);
}
}
}
}
return 0;
}
/ * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
Problem: 1165
User: wangzhengyi
Language: C
Result: Accepted
Time: 0 ms
Memory: 948 KB
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * /