Use “cat” to concatenate files

cat is a neat command to concatenate files on Unix (please see this post). Let’s see some examples:

# cat 1.txt
1
# cat 2.txt
2
# cat 1.txt 2.txt > new.txt
# cat new.txt
1
2
# cat 1.txt 2.txt >> new.txt
# cat new.txt
1
2
1
2

Please notice if the output file is also the input file, the input file content will be truncated first:

# cat 1.txt
1
# cat 2.txt
2
# cat 1.txt 2.txt > 1.txt
# cat 1.txt
2
# cat 2.txt
2

So the correct appending file method is using >>:

# cat 1.txt
1
# cat 2.txt
2
# cat 2.txt >> 1.txt
# cat 1.txt
1
2
# cat 2.txt
2

Check the implementation of cat in OpenBSD, and the core parts are iterating files and reading content from them:

(1) Iterate every file (raw_args):

void
raw_args(char **argv)
{
    int fd;

    fd = fileno(stdin);
    filename = "stdin";
    do {
        if (*argv) {
            if (!strcmp(*argv, "-"))
                fd = fileno(stdin);
            else if ((fd = open(*argv, O_RDONLY, 0)) < 0) {
                warn("%s", *argv);
                rval = 1;
                ++argv;
                continue;
            }
            filename = *argv++;
        }
        raw_cat(fd);
        if (fd != fileno(stdin))
            (void)close(fd);
    } while (*argv);
}

You need to pay attention that cat use - to identify stdin.

(2) Read content from every file (raw_cat):

void
raw_cat(int rfd)
{
    int wfd;
    ssize_t nr, nw, off;
    static size_t bsize;
    static char *buf = NULL;
    struct stat sbuf;

    wfd = fileno(stdout);
    if (buf == NULL) {
        if (fstat(wfd, &sbuf))
            err(1, "stdout");
        bsize = MAXIMUM(sbuf.st_blksize, BUFSIZ);
        if ((buf = malloc(bsize)) == NULL)
            err(1, "malloc");
    }
    while ((nr = read(rfd, buf, bsize)) != -1 && nr != 0)
        for (off = 0; nr; nr -= nw, off += nw)
            if ((nw = write(wfd, buf + off, (size_t)nr)) == 0 ||
                 nw == -1)
                err(1, "stdout");
    if (nr < 0) {
        warn("%s", filename);
        rval = 1;
    }
}

a) When reading the first file, the cat command uses fstat to get the st_blksize attribute of stdout which is “optimal blocksize for I/O”, then allocates the memory:

    ......
    if (buf == NULL) {
        if (fstat(wfd, &sbuf))
            err(1, "stdout");
        bsize = MAXIMUM(sbuf.st_blksize, BUFSIZ);
        if ((buf = malloc(bsize)) == NULL)
            err(1, "malloc");
    }
    ......

b) Read the content of file and write it into stdout:

    ......
    while ((nr = read(rfd, buf, bsize)) != -1 && nr != 0)
        for (off = 0; nr; nr -= nw, off += nw)
            if ((nw = write(wfd, buf + off, (size_t)nr)) == 0 ||
                 nw == -1)
                err(1, "stdout");
    ......

When read returns 0, it means reaching the end of file. If write doesn’t return the number you want to write, it is also considered as an error.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.