我正在编写一个从标准UNIX存档中提取的C程序,并创建它存储的文件。
如果我在vim中打开它,这是一个例子:
!<arch>
yo 1382105439 501 20 100644 10 `
test1 lol
yo2 1382105444 501 20 100644 10 `
test2 lol
...其中“test1 lol”和“test2 lol”是每个文件的内容,“yo”和“yo2”是两个不同的文件名,其余的是以对应于标准ar的格式存储的元数据.h(在这里阅读更多内容:http://www.lehman.cuny.edu/cgi-bin/man-cgi?ar.h+3)
无论如何,我仍在编写函数的过程中,但到目前为止我还是这样:
static void extract_files (int argc, char *argv[])
{
int fd;
int new_file_fd;
int num_read = 0;
int new_file_size;
struct ar_hdr current_header;
char name_buffer[16];
char date_buffer[12];
char uid_buffer[6];
char gid_buffer[6];
char mode_buffer[8];
char size_buffer[10];
char fmag_buffer[2];
// grab the fd #
fd = open(argv[2], O_RDWR | O_CREAT, 0666);
// go to the first header
lseek(fd, SARMAG, SEEK_CUR);
// store the number of bits read in a struct current_header
// until its size equal to the size of the entire
// header, or in other words, until the entire
// header is read
while ((num_read = read(fd, (char*) ¤t_header,
sizeof(struct ar_hdr))) == sizeof(struct ar_hdr))
{
// scans the current string in header and stores
// in nameStr array
sscanf(current_header.ar_name, "%s", name_buffer);
sscanf(current_header.ar_date, "%s", date_buffer);
sscanf(current_header.ar_uid, "%s", uid_buffer);
sscanf(current_header.ar_gid, "%s", gid_buffer);
int mode;
sscanf(current_header.ar_mode, "%o", &mode);
sscanf(current_header.ar_size, "%s", size_buffer);
int size = atoi(size_buffer);
sscanf(current_header.ar_fmag, "%s", fmag_buffer);
// Create a new file
new_file_fd = creat(name_buffer, mode);
// Grab new file size
new_file_size = atoi(size_buffer);
int io_size; // buffer size
char buff[size];
int read_cntr = 0;
// from copy.c
while ((io_size = read (fd, buff, new_file_size)) > 0)
{
read_cntr++;
if (read_cntr > new_file_size)
break;
write (new_file_fd, buff, new_file_size);
}
close(new_file_fd);
printf("%s\n", name_buffer);
printf("%s\n", date_buffer);
printf("%s\n", uid_buffer);
printf("%s\n", gid_buffer);
printf("%s\n", mode_buffer);
printf("%s\n", size_buffer);
printf("%s\n", fmag_buffer);
/* Seek to next header. */
lseek(fd, atoi(current_header.ar_size) + (atoi(current_header.ar_size)%2), SEEK_CUR);
}
}
我遇到的问题在于上面代码中的第二个while循环:
// from copy.c
while ((io_size = read (fd, buff, new_file_size)) > 0)
{
read_cntr++;
if (read_cntr > new_file_size)
break;
write (new_file_fd, buff, new_file_size);
}
由于某种原因,在此while循环中写入的文件不会运行到write指定的长度。标准read()/ write()的第三个参数应该是要写入的字节数。但出于某种原因,我的代码导致整个存档被读入并写入第一个文件。
如果我打开生成的“yo”文件,我发现整个存档文件已经写入
test1 lol
yo2 1382105444 501 20 100644 10 `
test2 lol
而不是在读取10个字节后终止并给出预期结果“test1 lol”。
我还可以确认“new_file_size”值确实为10.所以我的问题是:我在循环时读错了什么?
注意:预期输入将是一个命令行参数,如下所示: ./extractor.c -x name_of_archive_file
我认为我需要在此函数中处理的唯一相关信息是存档文件的名称,我在extract_files的开头获得了fd。
添加了: 其他 - 运行时的输出:
yo
1382105439
501
20
X
10
`
正如你所看到的,它永远不会看到yo2文件或打印出它的标题,因为在它发生之前它会被写入“yo”...因为这个循环中的流浪:(
答案 0 :(得分:1)
你的while()
循环后面应该有大括号({ ... }
),否则你只是在没有做任何其他事情的情况下递增read_cntr
。
答案 1 :(得分:1)
您读取了一个值size_buffer,并将其分配给size和new_file_size,您还创建了一个相同大小的buffer[size]
,
int size = atoi(size_buffer);
sscanf(current_header.ar_fmag, "%s", fmag_buffer);
//...
new_file_size = atoi(size_buffer);
//...
char buff[size];
Read返回范围[0..new_file_size]
中的ssize_t字节数,您设置为io_size,实现read(2)可能return < new_file_size
字节,这就是您需要while循环的原因。因此,您需要编写已阅读的所有内容,直到达到写入限制为止。我已经做了一些评论来指导你。
// from copy.c
while ((io_size = read (fd, buff, new_file_size)) > 0)
{
read_cntr++;
//perhaps you mean read_cntr += io_size;
//you probably mean to write io_size bytes here, regardless
//write(new_file_fd, buff, io_size);
if (read_cntr > new_file_size) //probably you want >= here
break;
//you may have broke before you write...
write (new_file_fd, buff, new_file_size);
}
这个副本的一个更典型的习惯用法是你选择一个读/写缓冲区大小,比如说4*1024 (4K)
,16*1024 (16K)
等,然后读取这个块大小,直到你有少于块大小剩下的;例如,
//decide how big to make buffer for read()
#define BUFSIZE (16*1024) //16K
//you need min(
#define min(x,y) ( ((x)<(y)) ? (x) : (y) )
ssize_t fdreader(int fd, int ofd, ssize_t new_file_size )
{
ssize_t remaining = new_file_size;
ssize_t readtotal = 0;
ssize_t readcount;
unsigned char buffer[BUFSIZE];
for( ; readcount=read(fd,buffer,min(sizeof(buffer),remaining)); )
{
readtotal += readcount;
if( readcount > remaining ) //only keep remaining
readcount = remaining;
write( ofd, buffer, readcount);
remaining -= readcount;
if( remaining <= 0 ) break; //done
}
return readtotal;
}
试试这个,
#include<stdio.h>
#include<stdlib.h>
void usage(char*progname)
{
printf("need 2 files\n");
printf("%s <infile> <outfile>\n",progname);
}
//decide how big to make buffer for read()
#define BUFSIZE (16*1024) //16K
//you need min(
#define min(x,y) ( ((x)<(y)) ? (x) : (y) )
ssize_t fdreader(int fd, int ofd, ssize_t new_file_size )
{
ssize_t remaining = new_file_size;
ssize_t readtotal = 0;
ssize_t readcount;
unsigned char buffer[BUFSIZE];
for( ; readcount=read(fd,buffer,min(sizeof(buffer),remaining)); )
{
readtotal += readcount;
if( readcount > remaining ) //only keep remaining
readcount = remaining;
write( ofd, buffer, readcount);
remaining -= readcount;
if( remaining <= 0 ) break; //done
}
return readtotal;
}
int main(int argc,char**argv)
{
int i=0; /* the infamous 'i' */
FILE*infh;
FILE*outfh;
if( argc < 3 )
{
usage(argv[0]);
return 0;
}
printf("%s %s\n",argv[1],argv[2]); fflush(stdout);
if( !(infh=fopen(argv[1],"r")) )
{
printf("cannot open %s\n",argv[2]); fflush(stdout);
return(2);
}
if( !(outfh=fopen(argv[2],"w+")) )
{
printf("cannot open %s\n",argv[3]); fflush(stdout);
return(3);
}
int x = fdreader(fileno(infh), fileno(outfh), 512 );
return 0;
}