Shell Programming and Scripting

awk 'NR==FNR { A[$1]++; O[++L]=$1; next }; $1 in A { A[$1]=$0 }; END { for(N=1; N<=L; N++) print O[N], A[O[N]]; }' names.txt masterfile.txt > output.txt

Albumin1A713G   1   1   3   3   1   3   1   3   1        
AY388580_a   0   0   1   2   1   2   1   2   1 
AY65789_a       
AY388591_a   1   1   1   2   1   2   2   2   1

Albumin1A713G   1   1   3   3   1   3   1   3   1        
AY388580_a   0   0   1   2   1   2   1   2   1        
AY388591_a   1   1   1   2   1   2   2   2   1

awk 'NR==FNR { A[$1]++; O[++L]=$1; next }; $1 in A { A[$1]=$0 }; END { for(N=1; N<=L; N++) if(A[O[N]] != 1) print O[N], A[O[N]]; }' names.txt masterfile.txt > output.txt

grep -f names.txt masterfile.txt

#!/usr/bin/env bash

# @(#) s2	Demonstrate msort alternating collating sequence.
# See: http://freecode.com/projects/msort

# Section 1, setup, pre-solution.
# Infrastructure details, environment, debug commands for forum posts. 
# Uncomment export command to run script as external user.
# export PATH="/usr/local/bin:/usr/bin:/bin"
set +o nounset
pe() { for _i;do printf "%s" "$_i";done; printf "\n"; }
pl() { pe;pe "-----" ;pe "$*"; }
LC_ALL=C ; LANG=C ; export LC_ALL LANG
db() { ( printf " db, ";for _i;do printf "%s" "$_i";done;printf "\n" ) >&2 ; }
db() { : ; }
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 $_f ; }
C=$HOME/bin/context && [ -f $C ] && $C grep msort
set -o nounset

FILE1=${1-data1}
shift
FILE2=${1-data2}

# Display sample data files.
pe
# specimen $FILE1 $FILE2 
# edges $FILE1 3
# edges $FILE2 3
head $FILE1 $FILE2 expected-output.txt

# Section 2, solution.
pl " Results:"
db " Section 2: solution."
grep -f $FILE2 $FILE1 |
msort -q -n 1,1 -u n -l -c lexicographic -s $FILE2 |
tee f1


# Section 3, post-solution, check results, clean-up, etc.
v1=$(wc -l <expected-output.txt)
v2=$(wc -l < f1)
pl " Comparison of $v2 created lines with $v1 lines of desired results:"
db " Section 3: validate generated calculations with desired results."

pl " Comparison with desired results:"
if [ ! -f expected-output.txt -o ! -s expected-output.txt ]
then
  pe " Comparison file \"expected-output.txt\" zero-length or missing."
  exit
fi
if cmp expected-output.txt f1
then
  pe " Succeeded -- files have same content."
else
  pe " Failed -- files not identical -- detailed comparison follows."
  if diff -b expected-output.txt f1
  then
    pe " Succeeded by ignoring whitespace differences."
  fi
fi

exit 0

% ./s2

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
grep GNU grep 2.5.3
msort 8.44

==> data1 <==
AY388580_a   0   0   1   2   1   2   1   2   1        
Albumin5G186T   1   1   1   1   1   1   1   1   1        
AY388585_a   1   1   1   3   1   3   1   1   1        
AY388587_a   1   1   1   1   1   1   1   3   1        
AY388589_a   1   1   1   1   1   1   1   1   1        
Albumin1A713G   1   1   3   3   1   3   1   3   1        
AY388588_a   1   3   1   1   1   1   1   1   1        
AY388582_a   3   3   1   3   1   3   1   3   1        
AY388591_a   1   1   1   2   1   2   2   2   1
Albumin1TC1894   1   1   1   1   1   1   1   1   1        

==> data2 <==
Albumin1A713G
AY388580_a
AY388591_a   

==> expected-output.txt <==
Albumin1A713G   1   1   3   3   1   3   1   3   1        
AY388580_a   0   0   1   2   1   2   1   2   1        
AY388591_a   1   1   1   2   1   2   2   2   1

-----
 Results:
Albumin1A713G   1   1   3   3   1   3   1   3   1        
AY388580_a   0   0   1   2   1   2   1   2   1        
AY388591_a   1   1   1   2   1   2   2   2   1

-----
 Comparison of 3 created lines with 3 lines of desired results:

-----
 Comparison with desired results:
 Succeeded -- files have same content.