比较 C 中的两个二进制文件

Question

我正在编写一个程序来比较两个二进制文件并绘制第一个差异。我想从每个文件中连续读取16个字节的数据并进行比较。为此，我将两个文件中的 16 个字节存储到 char *buffer1, buffer2 中。当我打印输出时，我得到 buffer1 包含 file1 和 file2 的数据。

代码如下:

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

void printConversion(char *buf1, char *buf2) {
    size_t len = strlen(buf1);
    char *binary = malloc(len * 8 + 1); 
    binary[0] = '\0';
    for (size_t i = 0; i < len; ++i) {
        char ch = buf1[i];
        for (int j = 7; j >= 0; --j) {
            if (ch & (1 << j)) {
                strcat(binary,"1");
            } else {
                strcat(binary,"0");
            }
        }
    }

    printf("File1: %s\t", binary);
    free(binary);
    printf("File2:");
    for (int i = 0; i < sizeof(buf2); i++) {
        printf("%x", buf2[i] - '0');
    }
}

void fileRead(FILE *fp, char *buf, int count) {
    fseek(fp, count, SEEK_SET);    
    fread(buf, 1, 16, fp);
}

int fileSize(FILE *fp) {
    fseek(fp, 0, SEEK_END);
    int size = ftell(fp) + 1;
    return size;
}

int main(int argc, char *argv[]) {
    printf("***Binary File Comparator***\n ");
    int count = 0;
    int index = 0;
    char buffer1[16];
    char buffer2[16];
    char buffer3[16];
    char buffer4[16];

    // Invalid Number of Arguments
    if (argc < 3 || argc > 3) {
        printf("Invalid Number of Arguments\n");
    }

    FILE *fp1, *fp2;
    fp1 = fopen(argv[1], "rb");
    int size = fileSize(fp1);
    int size1 = size;
    fclose(fp1);

    while (size > 1) {
        fp1 = fopen(argv[1], "rb");
        fileRead(fp1, buffer1, count);
        fclose(fp1);

        fp2 = fopen(argv[2], "rb");
        fileRead(fp2, buffer2, count);
        if (size1 < count) {
            int lastSize = count - size1;
            count = count + lastSize;
            fclose(fp2);
        } else {
            count = count+16;
            fclose(fp2);
        }

        **printf("buffer1:%s\tbuffer2:%s\n", buffer1, buffer2)**;
        size = size - 16;

        int result = strcmp(buffer1, buffer2);
        if (result != 0) {
            for (int i = 0; i < sizeof(buffer1); i++) {
                if (buffer1[i] != buffer2[i]) {
                    int count1 = (count - 16) + i;
                    index++;
                    if (index == 1) {
                        printf("Byte_Offset:%x\n", count1);
                        fp1 = fopen(argv[1], "rb");
                        fileRead(fp1, buffer3, count1);
                        fclose(fp1);
                        fp2 = fopen(argv[2], "rb");
                        fileRead(fp2, buffer4, count1);
                        fclose(fp2);
                        printConversion(buffer3, buffer4);
                        break;
                    }
                } else {
                    continue;
                }
            } 
        }
    }
}

我试图突出显示正在打印我的 buffer1 和 buffer2 的 printf 部分

输出如下:

 buffer1:83867715933586928386771593358692   buffer2:8386771593358692
buffer1:49216227905963264921622790596326    buffer2:4921622790596326
buffer1:40267236116867294026723611686729    buffer2:4026723611686729
buffer1:82306223673529228230622367352922    buffer2:8230622367352922
buffer1:25869679356114222586967935611422    buffer2:2586967935611422

任何人都可以帮助我做错了什么。请指出错误以及可以在代码中进行哪些优化更改。我正处于学习阶段，您的反馈将非常有帮助。

Answer 1

您通过一次读取 16 个字节使任务复杂化。如果目标是指示第一个差异，只需使用 getc() 以这种方式一次从两个文件中读取一个字节:

int compare_files(FILE *fp1, FILE *fp2) {
    unsigned long pos;
    int c1, c2;
    for (pos = 0;; pos++) {
        c1 = getc(fp1);
        c2 = getc(fp2);
        if (c1 != c2 || c1 == EOF)
            break;
    }
    if (c1 == c2) {
        printf("files are identical and have %lu bytes\n", pos);
        return 0;  // files are identical
    } else
    if (c1 == EOF) {
        printf("file1 is included in file2, the first %lu bytes are identical\n", pos);
        return 1;
    } else
    if (c2 == EOF) {
        printf("file2 is included in file1, the first %lu bytes are identical\n", pos);
        return 2;
    } else {
        printf("file1 and file2 differ at position %lu: 0x%02X <> 0x%02X\n", pos, c1, c2);
        return 3;
    }
}

就效率而言，如果流被缓冲，则一次读取一个字节不会造成问题。对于大文件，如果目标系统和给定的输入流可用，您可以通过内存映射文件内容来获得更好的性能。