c - 使用 c 检测文件中的重复行

Question

我有一个包含大约 (15000-25000) 行(固定大小)的 csv 文件，我想知道如何使用 C 语言检测重复的行。

输出示例如下:

0123456789;CUST098WZAX;35

我没有内存或时间限制，所以我想要最简单的解决方案。

感谢您的帮助。

Answer 1

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

struct somehash {
        struct somehash *next;
        unsigned hash;
        char *mem;
        };

#define THE_SIZE 100000
struct somehash *table[THE_SIZE] = { NULL,};

struct somehash **some_find(char *str, unsigned len);
static unsigned some_hash(char *str, unsigned len);

int main (void)
{
char buffer[100];
struct somehash **pp;
size_t len;

while (fgets(buffer, sizeof buffer, stdin)) {
        len = strlen(buffer);
        pp = some_find(buffer, len);
        if (*pp) { /* found */
                fprintf(stderr, "Duplicate:%s\n", buffer);
                }
        else    {       /* not found: create one */
                fprintf(stdout, "%s", buffer);
                *pp = malloc(sizeof **pp);
                (*pp)->next = NULL;
                (*pp)->hash = some_hash(buffer,len);
                (*pp)->mem = malloc(1+len);
                memcpy((*pp)->mem , buffer,  1+len);
                }
        }
return 0;
}
struct somehash **some_find(char *str, unsigned len)
{
unsigned hash;
unsigned slot;
struct somehash **hnd;

hash = some_hash(str,len);
slot = hash % THE_SIZE;
for (hnd = &table[slot]; *hnd ; hnd = &(*hnd)->next ) {
        if ( (*hnd)->hash != hash) continue;
        if ( strcmp((*hnd)->mem , str) ) continue;
        break;
        }
return hnd;
}

static unsigned some_hash(char *str, unsigned len)
{
unsigned val;
unsigned idx;

if (!len) len = strlen(str);

val = 0;
for(idx=0; idx < len; idx++ )   {
        val ^= (val >> 2) ^ (val << 5) ^ (val << 13) ^ str[idx] ^ 0x80001801;
        }
return val;
}