cut.awk

gawk: linux下资料处理工具

# cut.awk --- implement cut in awk
#
# Arnold Robbins, [e-mail], Public Domain
# May 1993

# Options:
#    -f list     Cut fields
#    -d c        Field delimiter character
#    -c list     Cut characters
#
#    -s          Suppress lines without the delimiter
#
# Requires getopt and join library functions

function usage(    e1, e2)
{
    e1 = "usage: cut [-f list] [-d c] [-s] [files...]"
    e2 = "usage: cut [-c list] [files...]"
    print e1 > "/dev/stderr"
    print e2 > "/dev/stderr"
    exit 1
}
BEGIN    \
{
    FS = "\t"    # default
    OFS = FS
    while ((c = getopt(ARGC, ARGV, "sf:c:d:")) != -1) {
        if (c == "f") {
            by_fields = 1
            fieldlist = Optarg
        } else if (c == "c") {
            by_chars = 1
            fieldlist = Optarg
            OFS = ""
        } else if (c == "d") {
            if (length(Optarg) > 1) {
                printf("Using first character of %s" \
                " for delimiter\n", Optarg) > "/dev/stderr"
                Optarg = substr(Optarg, 1, 1)
            }
            FS = Optarg
            OFS = FS
            if (FS == " ")    # defeat awk semantics
                FS = "[ ]"
        } else if (c == "s")
            suppress++
        else
            usage()
    }

    for (i = 1; i < Optind; i++)
        ARGV[i] = ""
    if (by_fields && by_chars)
        usage()

    if (by_fields == 0 && by_chars == 0)
        by_fields = 1    # default

    if (fieldlist == "") {
        print "cut: needs list for -c or -f" > "/dev/stderr"
        exit 1
    }

    if (by_fields)
        set_fieldlist()
    else
        set_charlist()
}
function set_fieldlist(        n, m, i, j, k, f, g)
{
    n = split(fieldlist, f, ",")
    j = 1    # index in flist
    for (i = 1; i <= n; i++) {
        if (index(f[i], "-") != 0) { # a range
            m = split(f[i], g, "-")
            if (m != 2 || g[1] >= g[2]) {
                printf("bad field list: %s\n",
                                  f[i]) > "/dev/stderr"
                exit 1
            }
            for (k = g[1]; k <= g[2]; k++)
                flist[j++] = k
        } else
            flist[j++] = f[i]
    }
    nfields = j - 1
}
function set_charlist(    field, i, j, f, g, t,
                          filler, last, len)
{
    field = 1   # count total fields
    n = split(fieldlist, f, ",")
    j = 1       # index in flist
    for (i = 1; i <= n; i++) {
        if (index(f[i], "-") != 0) { # range
            m = split(f[i], g, "-")
            if (m != 2 || g[1] >= g[2]) {
                printf("bad character list: %s\n",
                               f[i]) > "/dev/stderr"
                exit 1
            }
            len = g[2] - g[1] + 1
            if (g[1] > 1)  # compute length of filler
                filler = g[1] - last - 1
            else
                filler = 0
            if (filler)
                t[field++] = filler
            t[field++] = len  # length of field
            last = g[2]
            flist[j++] = field - 1
        } else {
            if (f[i] > 1)
                filler = f[i] - last - 1
            else
                filler = 0
            if (filler)
                t[field++] = filler
            t[field++] = 1
            last = f[i]
            flist[j++] = field - 1
        }
    }
    FIELDWIDTHS = join(t, 1, field - 1)
    nfields = j - 1
}
{
    if (by_fields && suppress && index($0, FS) != 0)
        next

    for (i = 1; i <= nfields; i++) {
        if ($flist[i] != "") {
            printf "%s", $flist[i]
            if (i < nfields && $flist[i+1] != "")
                printf "%s", OFS
        }
    }
    print ""
}