FM / prog

/usr/share/doc/gawk/examples/prog

Name	Size	Mode	Actions
alarm.awk	2369	0644	edit dl rm
anagram.awk	1358	0644	edit dl rm
awksed.awk	515	0644	edit dl rm
cut.awk	3698	0644	edit dl rm
dupword.awk	507	0644	edit dl rm
egrep.awk	1954	0644	edit dl rm
extract.awk	1883	0644	edit dl rm
guide.awk	165	0644	edit dl rm
histsort.awk	283	0644	edit dl rm
id.awk	1249	0644	edit dl rm
igawk.sh	3189	0644	edit dl rm
indirectcall.awk	1957	0644	edit dl rm
labels.awk	1014	0644	edit dl rm
pi.awk	341	0644	edit dl rm
split.awk	1198	0644	edit dl rm
tee.awk	770	0644	edit dl rm
testbits.awk	736	0644	edit dl rm
translate.awk	1182	0644	edit dl rm
uniq.awk	2700	0644	edit dl rm
wc.awk	1480	0644	edit dl rm
wordfreq.awk	347	0644	edit dl rm

Edit: /usr/share/doc/gawk/examples/prog/uniq.awk (2700B)

# uniq.awk --- do uniq in awk
#
# Requires getopt() and join() library functions
#
# Arnold Robbins, arnold@skeeve.com, Public Domain
# May 1993

function usage()
{
    print("Usage: uniq [-udc [-n]] [+n] [ in [ out ]]") > "/dev/stderr"
    exit 1
}

# -c    count lines. overrides -d and -u
# -d    only repeated lines
# -u    only nonrepeated lines
# -n    skip n fields
# +n    skip n characters, skip fields first

BEGIN {
    count = 1
    outputfile = "/dev/stdout"
    opts = "udc0:1:2:3:4:5:6:7:8:9:"
    while ((c = getopt(ARGC, ARGV, opts)) != -1) {
        if (c == "u")
            non_repeated_only++
        else if (c == "d")
            repeated_only++
        else if (c == "c")
            do_count++
        else if (index("0123456789", c) != 0) {
            # getopt() requires args to options
            # this messes us up for things like -5
            if (Optarg ~ /^[[:digit:]]+$/)
                fcount = (c Optarg) + 0
            else {
                fcount = c + 0
                Optind--
            }
        } else
            usage()
    }

if (ARGV[Optind] ~ /^\+[[:digit:]]+$/) {
        charcount = substr(ARGV[Optind], 2) + 0
        Optind++
    }

for (i = 1; i < Optind; i++)
        ARGV[i] = ""

if (repeated_only == 0 && non_repeated_only == 0)
        repeated_only = non_repeated_only = 1

if (ARGC - Optind == 2) {
        outputfile = ARGV[ARGC - 1]
        ARGV[ARGC - 1] = ""
    }
}
function are_equal(    n, m, clast, cline, alast, aline)
{
    if (fcount == 0 && charcount == 0)
        return (last == $0)

if (fcount > 0) {
        n = split(last, alast)
        m = split($0, aline)
        clast = join(alast, fcount+1, n)
        cline = join(aline, fcount+1, m)
    } else {
        clast = last
        cline = $0
    }
    if (charcount) {
        clast = substr(clast, charcount + 1)
        cline = substr(cline, charcount + 1)
    }

return (clast == cline)
}
NR == 1 {
    last = $0
    next
}

{
    equal = are_equal()

if (do_count) {    # overrides -d and -u
        if (equal)
            count++
        else {
            printf("%4d %s\n", count, last) > outputfile
            last = $0
            count = 1    # reset
        }
        next
    }

if (equal)
        count++
    else {
        if ((repeated_only && count > 1) ||
            (non_repeated_only && count == 1))
                print last > outputfile
        last = $0
        count = 1
    }
}

END {
    if (do_count)
        printf("%4d %s\n", count, last) > outputfile
    else if ((repeated_only && count > 1) ||
            (non_repeated_only && count == 1))
        print last > outputfile
    close(outputfile)
}

# uniq.awk --- do uniq in awk # # Requires getopt() and join() library functions # # Arnold Robbins, arnold@skeeve.com, Public Domain # May 1993 function usage() { print("Usage: uniq [-udc [-n]] [+n] [ in [ out ]]") > "/dev/stderr" exit 1 } # -c count lines. overrides -d and -u # -d only repeated lines # -u only nonrepeated lines # -n skip n fields # +n skip n characters, skip fields first BEGIN { count = 1 outputfile = "/dev/stdout" opts = "udc0:1:2:3:4:5:6:7:8:9:" while ((c = getopt(ARGC, ARGV, opts)) != -1) { if (c == "u") non_repeated_only++ else if (c == "d") repeated_only++ else if (c == "c") do_count++ else if (index("0123456789", c) != 0) { # getopt() requires args to options # this messes us up for things like -5 if (Optarg ~ /^[[:digit:]]+$/) fcount = (c Optarg) + 0 else { fcount = c + 0 Optind-- } } else usage() } if (ARGV[Optind] ~ /^\+[[:digit:]]+$/) { charcount = substr(ARGV[Optind], 2) + 0 Optind++ } for (i = 1; i < Optind; i++) ARGV[i] = "" if (repeated_only == 0 && non_repeated_only == 0) repeated_only = non_repeated_only = 1 if (ARGC - Optind == 2) { outputfile = ARGV[ARGC - 1] ARGV[ARGC - 1] = "" } } function are_equal( n, m, clast, cline, alast, aline) { if (fcount == 0 && charcount == 0) return (last == $0) if (fcount > 0) { n = split(last, alast) m = split($0, aline) clast = join(alast, fcount+1, n) cline = join(aline, fcount+1, m) } else { clast = last cline = $0 } if (charcount) { clast = substr(clast, charcount + 1) cline = substr(cline, charcount + 1) } return (clast == cline) } NR == 1 { last = $0 next } { equal = are_equal() if (do_count) { # overrides -d and -u if (equal) count++ else { printf("%4d %s\n", count, last) > outputfile last = $0 count = 1 # reset } next } if (equal) count++ else { if ((repeated_only && count > 1) || (non_repeated_only && count == 1)) print last > outputfile last = $0 count = 1 } } END { if (do_count) printf("%4d %s\n", count, last) > outputfile else if ((repeated_only && count > 1) || (non_repeated_only && count == 1)) print last > outputfile close(outputfile) }