如何在C中将文件内容读取为字符串?

我倾向于将整个缓冲区作为原始内存块加载到内存中,然后自己进行解析。这样我就可以更好地控制标准库在多个平台上的功能。

这是我用的存根。您可能还需要检查fseek、ftell和fread的错误代码。(为清楚起见省略)。

char * buffer = 0;
long length;
FILE * f = fopen (filename, "rb");

if (f)
{
  fseek (f, 0, SEEK_END);
  length = ftell (f);
  fseek (f, 0, SEEK_SET);
  buffer = malloc (length);
  if (buffer)
  {
    fread (buffer, 1, length, f);
  }
  fclose (f);
}

if (buffer)
{
  // start to process your data / extract strings here...
}

不幸的是,另一个高度依赖操作系统的解决方案是内存映射文件。好处通常包括读取性能,以及减少内存使用,因为应用程序视图和操作系统文件缓存实际上可以共享物理内存。

int fd = open("filename", O_RDONLY);
int len = lseek(fd, 0, SEEK_END);
void *data = mmap(0, len, PROT_READ, MAP_PRIVATE, fd, 0);

另一方面,Windows有点棘手,不幸的是,我没有一个编译器在我面前进行测试,但功能是由提供的 CreateFileMapping() 和 MapViewOfFile()

此函数在GNU C库中提供, http://www.gnu.org/software/libc/manual/html_mono/libc.html#index-getdelim-994

示例代码可能看起来很简单

char* buffer = NULL;
size_t len;
ssize_t bytes_read = getdelim( &buffer, &len, '\0', fp);
if ( bytes_read != -1) {
  /* Success, now the entire file is in the buffer */

如果您正在读取特殊文件,如stdin或管道,则无法使用fstat预先获取文件大小。此外,如果正在读取二进制文件,由于嵌入了“\0”字符,fgets将丢失字符串大小信息。读取文件的最佳方法是使用read和realloc:

#include <stdio.h>
#include <unistd.h>
#include <errno.h>
#include <string.h>

int main () {
    char buf[4096];
    ssize_t n;
    char *str = NULL;
    size_t len = 0;
    while (n = read(STDIN_FILENO, buf, sizeof buf)) {
        if (n < 0) {
            if (errno == EAGAIN)
                continue;
            perror("read");
            break;
        }
        str = realloc(str, len + n + 1);
        memcpy(str + len, buf, n);
        len += n;
        str[len] = '\0';
    }
    printf("%.*s\n", len, str);
    return 0;
}

char buffer[100];
FILE *fp = fopen("filename", "r");                 // do not use "rb"
while (fgets(buffer, sizeof(buffer), fp)) {
... do something
}
fclose(fp);

注:这是对上述公认答案的修改。

这里有一种方法,包括错误检查。

我添加了一个大小检查器,当文件大于1 GiB时退出。我这样做是因为程序将整个文件放入一个字符串中,这可能会占用太多内存,导致计算机崩溃。但是,如果您不关心这一点,可以将其从代码中删除。

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

#define FILE_OK 0
#define FILE_NOT_EXIST 1
#define FILE_TO_LARGE 2
#define FILE_READ_ERROR 3

char * c_read_file(const char * f_name, int * err, size_t * f_size) {
    char * buffer;
    size_t length;
    FILE * f = fopen(f_name, "rb");
    size_t read_length;
    
    if (f) {
        fseek(f, 0, SEEK_END);
        length = ftell(f);
        fseek(f, 0, SEEK_SET);
        
        // 1 GiB; best not to load a whole large file in one string
        if (length > 1073741824) {
            *err = FILE_TO_LARGE;
            
            return NULL;
        }
        
        buffer = (char *)malloc(length + 1);
        
        if (length) {
            read_length = fread(buffer, 1, length, f);
            
            if (length != read_length) {
                 free(buffer);
                 *err = FILE_READ_ERROR;

                 return NULL;
            }
        }
        
        fclose(f);
        
        *err = FILE_OK;
        buffer[length] = '\0';
        *f_size = length;
    }
    else {
        *err = FILE_NOT_EXIST;
        
        return NULL;
    }
    
    return buffer;
}

int err;
size_t f_size;
char * f_data;

f_data = c_read_file("test.txt", &err, &f_size);

if (err) {
    // process error
}
else {
    // process data
    free(f_data);
}

如果你正在使用 glib ,然后您可以使用 g_file_get_contents

gchar *contents;
GError *err = NULL;

g_file_get_contents ("foo.txt", &contents, NULL, &err);
g_assert ((contents == NULL && err != NULL) || (contents != NULL && err == NULL));
if (err != NULL)
  {
    // Report error to user, and free error
    g_assert (contents == NULL);
    fprintf (stderr, "Unable to read file: %s\n", err->message);
    g_error_free (err);
  }
else
  {
    // Use file contents
    g_assert (contents != NULL);
  }
}

刚刚修改了上面接受的答案。

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

char *readFile(char *filename) {
    FILE *f = fopen(filename, "rt");
    assert(f);
    fseek(f, 0, SEEK_END);
    long length = ftell(f);
    fseek(f, 0, SEEK_SET);
    char *buffer = (char *) malloc(length + 1);
    buffer[length] = '\0';
    fread(buffer, 1, length, f);
    fclose(f);
    return buffer;
}

int main() {
    char *content = readFile("../hello.txt");
    printf("%s", content);
}

// Assumes the file exists and will seg. fault otherwise.
const GLchar *load_shader_source(char *filename) {
  FILE *file = fopen(filename, "r");             // open 
  fseek(file, 0L, SEEK_END);                     // find the end
  size_t size = ftell(file);                     // get the size in bytes
  GLchar *shaderSource = calloc(1, size);        // allocate enough bytes
  rewind(file);                                  // go back to file beginning
  fread(shaderSource, size, sizeof(char), file); // read each char into ourblock
  fclose(file);                                  // close the stream
  return shaderSource;
}

这是一个非常粗糙的解决方案,因为没有对null进行任何检查。

// Open the file in read mode.
FILE *file = fopen(file_name, "r");
// Check if there was an error.
if (file == NULL) {
    fprintf(stderr, "Error: Can't open file '%s'.", file_name);
    exit(EXIT_FAILURE);
}
// Get the file length
fseek(file, 0, SEEK_END);
long length = ftell(file);
fseek(file, 0, SEEK_SET);
// Create the string for the file contents.
char *buffer = malloc(sizeof(char) * (length + 1));
buffer[length] = '\0';
// Set the contents of the string.
fread(buffer, sizeof(char), length, file);
// Close the file.
fclose(file);
// Do something with the data.
// ...
// Free the allocated string space.
free(buffer);

简单整洁(假设文件中的内容少于10000):

void read_whole_file(char fileName[1000], char buffer[10000])
{
    FILE * file = fopen(fileName, "r");
    if(file == NULL)
    {
        puts("File not found");
        exit(1);
    }
    char  c;
    int idx=0;
    while (fscanf(file , "%c" ,&c) == 1)
    {
        buffer[idx] = c;
        idx++;
    }
    buffer[idx] = 0;
}