C程序无法识别echo命令创建文件中的子串问题求助

我开发了一款统计指定文件中子串出现次数的C程序，手动创建并填充内容的文件能正常统计，但用echo命令创建的文件，明明文本编辑器里能看到目标子串，程序却检测不到。以下是简化版代码、操作命令及输出：

简化版程序代码 #

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/types.h>

#define BUFFER_SIZE 1024
int num_substrings = 0;
int use_systemcall = 0; 

void search_file(char *filename, char *substring) {
    // Open the file with the given filename in read mode
    FILE *file = fopen(filename, "r");
    
    // Check if the file was successfully opened
    if (file == NULL) {
        // Print an error message and exit the program with an error code
        fprintf(stderr, "Error: could not open file '%s'\n", filename);
        exit(1);
    }
    
    int count = 0;
    char buffer[BUFFER_SIZE];
    char *line;
    size_t len = 0;
    ssize_t read;
    
    // Read the file line by line until the end
    while ((read = getline(&line, &len, file)) != -1) {
        // Skip the last line if it is empty
        if (read == 1 && line[0] == '\n') {
            continue;
        }

        // Strip any newline characters from the end of the line
        if (line[read - 1] == '\n') {
            line[read - 1] = '\0';
            read--;
        }
    
        // Find the first occurrence of the given substring in the current line
        char *match = strstr(line, substring);
    
        // While there are still occurrences of the substring in the current line
        while (match != NULL) {
            // Increment the counter and find the next occurrence of the substring
            count++;
            match = strstr(match + 1, substring);
        }
    }
    
    // Close the file
    fclose(file);
    
    // Print the number of occurrences of the substring found in the file
    printf("Found %d occurrences of substring '%s' in file '%s'\n",
           count, substring, filename);
}

int main(int argc, char *argv[]) {
    // Get the filename from the first command-line argument
    char *filename = argv[1];
    
    // Initialize an array to store the substrings and a counter for the number of substrings
    char substrings[10][100];
    int num_substrings = 0;
    
    // Loop through the remaining command-line arguments (starting from the second one)
    for (int i = 2; i < argc; i++) {
        // Copy the current argument (substring) into the substrings array
        strcpy(substrings[num_substrings], argv[i]);
        
        // Increment the counter for the number of substrings
        num_substrings++;
    }
    
    // Ask the user if they want to use a system call
    printf("Do you want to use system call? (y/n): ");

    char answer[10];
    fgets(answer, 10, stdin);
    
    // Check if the user answered yes (y or Y) and set the use_systemcall variable accordingly
    int use_systemcall = 0;
    if (answer[0] == 'y' || answer[0] == 'Y') {
        use_systemcall = 1;
    }

    printf("Filename: %s\n", filename);
    printf("Substrings: ");
    for (int i = 0; i < num_substrings; i++) {
        printf("%s ", substrings[i]);
    }
    printf("\n");
    
    // Open the file for reading
    FILE *file = fopen(filename, "rb");
    
    if (file == NULL) {
        printf("Error: Cannot open file %s\n", filename);
        return 1;
    }
    
    // Initialize a buffer to read the file in blocks of 100 characters
    char buffer[101];
    
    // Loop through each substring and search for it in the file
    for (int i = 0; i < num_substrings; i++) {
        // Reset the file pointer to the beginning of the file
        fseek(file, 0, SEEK_SET);
        
        // Initialize a counter for the number of occurrences of the substring
        int count = 0;
        
        // Loop through the file in blocks of 100 characters
        while (fread(buffer, sizeof(char), 100, file) > 0) {
            // Add a null terminator at the end of the buffer
            buffer[100] = '\0';
            
            // Search for the substring in the buffer
            char *result = strstr(buffer, substrings[i]);
            
            // If the substring is found, increment the count
            while (result != NULL) {
                count++;
                
                // Move the result pointer to the next character after the match
                result++;
                
                // Search for the substring again starting from the result pointer
                result = strstr(result, substrings[i]);
            }
        }
        
        // Print the number of occurrences of the substring
        printf("'%s' appears %d times in the file.\n", substrings[i], count);
    }
    return 0;
}

操作命令 #

echo "hello world" > foo.txt    # 创建文件
./substring_search foo.txt world # 搜索子串

程序输出 #

'world' appears 0 times in the file.

问题根源 #

核心问题是：你已经写好了正确的search_file函数，但在main中完全没有调用它，反而实现了一套有缺陷的独立读取统计逻辑：

• search_file函数会逐行读取文件，自动去除每行末尾的换行符，能正确匹配echo生成文件中的world；但main里的代码完全忽略了这个函数，自己用fread按块读取文件。
• 另外，main中的块读取逻辑还存在跨块匹配丢失的问题（如果子串刚好在两个100字节块的边界，会被漏统计），不过在这个案例中，因为文件太小，这个问题没暴露，但核心是你没启用正确的逻辑。

解决方法 #

最优方案：调用已实现的search_file函数

直接修改main函数的后半部分，替换掉那套有问题的块读取逻辑，调用你已经写好的search_file函数：

printf("Filename: %s\n", filename);
printf("Substrings: ");
for (int i = 0; i < num_substrings; i++) {
    printf("%s ", substrings[i]);
}
printf("\n");

// 替换原有的文件读取统计代码，调用正确的search_file函数
for (int i = 0; i < num_substrings; i++) {
    search_file(filename, substrings[i]);
}

// 删除原有的fopen、fread等相关代码
return 0;

修改后重新编译运行，echo生成的文件就能正确统计出world的出现次数了。

可选方案：修复main中的块读取逻辑

如果你坚持要用块读取的方式，需要修复跨块匹配的问题，同时优化搜索逻辑：

// 修复后的单块读取搜索逻辑示例（针对单个子串）
int sub_len = strlen(substrings[i]);
char overlap_buf[100] = {0}; // 保存上一次读取末尾可能的重叠部分
int overlap_len = 0;
int count = 0;

fseek(file, 0, SEEK_SET);
while (1) {
    char buffer[100];
    int read_bytes = fread(buffer, sizeof(char), 100, file);
    if (read_bytes == 0) break;

    // 拼接重叠部分和当前读取的内容
    char combined[200];
    memcpy(combined, overlap_buf, overlap_len);
    memcpy(combined + overlap_len, buffer, read_bytes);
    combined[overlap_len + read_bytes] = '\0';

    // 搜索所有匹配
    char *result = strstr(combined, substrings[i]);
    while (result != NULL) {
        count++;
        result = strstr(result + 1, substrings[i]);
    }

    // 更新重叠部分：保留最后sub_len-1个字符，防止跨块匹配丢失
    if (overlap_len + read_bytes >= sub_len - 1) {
        overlap_len = sub_len - 1;
        memcpy(overlap_buf, combined + (overlap_len + read_bytes - overlap_len), overlap_len);
    } else {
        overlap_len += read_bytes;
        memcpy(overlap_buf + (overlap_len - read_bytes), buffer, read_bytes);
    }
}

printf("'%s' appears %d times in the file.\n", substrings[i], count);

内容的提问来源于stack exchange，提问作者Moeez