UNIX for Dummies Questions & Answers

awk ' FILENAME=="file1" {arr[$1]=$0; next}
        FILENAME=="file2"  {print arr[$1]} ' file1 file2 > newfile

#!/usr/bin/env bash

# @(#) s1	Demonstrate join on common field, preserve ordering.

# Utility functions: print-as-echo, print-line-with-visual-space, debug.
# export PATH="/usr/local/bin:/usr/bin:/bin"
pe() { for _i;do printf "%s" "$_i";done; printf "\n"; }
pl() { pe;pe "-----" ;pe "$*"; }
edges() { local _f _n _l;: ${1?"edges: need file"}; _f=$1;_l=$(wc -l $_f);
  head -${_n:=3} $_f ; pe "--- ( $_l: lines total )" ; tail -$_n $_f ; }
db() { ( printf " db, ";for _i;do printf "%s" "$_i";done;printf "\n" ) >&2 ; }
db() { : ; }
C=$HOME/bin/context && [ -f $C ] && $C nl sort join sed

pl " Input data files data[12]:"
head data[12]

pl " Results of adding line numbers and sorting on field 2, remove duplicates:"
# To allow duplicates, remove the "-u" option.
nl data1 | sort -u -k2,2 > f1
nl data2 | sort -u -k2,2 > f2
head f[12]

pl " Result of join on field 2, sort on line numbers, remove line numbers:"
join -j 2 -o 2.1 1.2 1.3 1.4 1.5  f1 f2 |
sort -k1,1n |
sed 's/[^ ]* //'

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 5.0.8 (lenny) 
bash GNU bash 3.2.39
nl (GNU coreutils) 6.10
sort (GNU coreutils) 6.10
join (GNU coreutils) 6.10
sed GNU sed version 4.1.5

-----
 Input data files data[12]:
==> data1 <==
1-30 1 2 3
5-60 4 5 6
1-20 7 8 9
4-40 4 4 4

==> data2 <==
1-20 1 20
1-30 1 30
5-60 5 60
5-60 5 60
7-70 7 70
7-70 7 70

-----
 Results of adding line numbers and sorting on field 2, remove duplicates:
==> f1 <==
     3	1-20 7 8 9
     1	1-30 1 2 3
     4	4-40 4 4 4
     2	5-60 4 5 6

==> f2 <==
     1	1-20 1 20
     2	1-30 1 30
     3	5-60 5 60
     5	7-70 7 70

-----
 Result of join on field 2, sort on line numbers, remove line numbers:
1-20 7 8 9
1-30 1 2 3
5-60 4 5 6