Shell Programming and Scripting

1234 8888 bbb
2745 8888 bbb
9489 8888 bbb
1234 8888 aaa
4838 8888 aaa
3977 8888 aaa

sort file.txt | uniq -w4 > newfile.txt

1234 8888 aaa    would be kept, and
1234 8888 bbb    would be excluded

#!/usr/bin/env bash

# @(#) s1	Demonstrate sort and uniq.

# Section 1, setup, pre-solution.
# Infrastructure details, environment, commands for forum posts. 
# Uncomment export command to test script as external user.
# export PATH="/usr/local/bin:/usr/bin:/bin"
set +o nounset
pe() { for i;do printf "%s" "$i";done; printf "\n"; }
pl() { pe;pe "-----" ;pe "$*"; }
C=$HOME/bin/context && [ -f $C ] && . $C specimen sort uniq
set -o nounset
pe

FILE=${1-data1}

# Section 2, display input file.
# Display sample of data file, with head & tail as a last resort.
pe " || start [ first:middle:last ]"
specimen $FILE \
|| { pe "(head/tail)"; head -n 5 $FILE; pe " ||"; tail -n 5 $FILE; }
pe " || end"

# Section 3, solution.
pl " Results, sort | uniq:"
sort -k1,1 $FILE | uniq -w4 

pl " Results, sort -u:"
sort -k1,1 -u $FILE

exit 0

% ./s1

Environment: LC_ALL = C, LANG = C
(Versions displayed with local utility "version")
OS, ker|rel, machine: Linux, 2.6.26-2-amd64, x86_64
Distribution        : Debian GNU/Linux 5.0.7 (lenny) 
GNU bash 3.2.39
specimen (local) 1.17
sort (GNU coreutils) 6.10
uniq (GNU coreutils) 6.10

 || start [ first:middle:last ]
Whole: 5:0:5 of 6 lines in file "data1"
1234 8888 bbb
2745 8888 bbb
9489 8888 bbb
1234 8888 aaa
4838 8888 aaa
3977 8888 aaa
 || end

-----
 Results, sort | uniq:
1234 8888 aaa
2745 8888 bbb
3977 8888 aaa
4838 8888 aaa
9489 8888 bbb

-----
 Results, sort -u:
1234 8888 bbb
2745 8888 bbb
3977 8888 aaa
4838 8888 aaa
9489 8888 bbb

$ perl -lane 'print if not $no{ $F[0] }++' infile

sort file.txt | uniq -w4 -u > newfile.txt

awk '!a[$1$2]++'

awk '!a[$1$2]++' filename

01/Feb/2011   -- User Count : 27
  31/Jan/2011   --  User Count : 21
  02/Feb/2011   -- User Count : 24
  30/Jan/2011   --  User Count : 4

awk -v FS=OFS="/" '!a[$1$2]++'