Shell Programming and Scripting

#!/bin/bash

# get_cols_by_header.sh 

# file with header names of required columns in required order
headers_file=$1

# space delimited file with data in columns
input_file=$2

# tab delimited output goes here
output_file='./temp_output.txt'

# use the columns headers listed in headers_file to locate the colums
# in input_file and print to output_file
awk '
NR == FNR       {T[$1] = NR
                 next
                }
FNR == 1        {MX = NR - 1
                 for (i=1; i<=NF; i++) if ($i in T) C[T[$i]] = i
                }
                {for (j=1; j<=MX; j++) printf "%s%s", $C[j], (j == MX)?RS:"\t"
                }
' $headers_file  $input_file > $output_file

./get_cols_by_header.sh  header_file.txt  input_file.txt

real    0m0.141s
user    0m0.170s
sys     0m0.030s

awk '...' $1 $2 ./temp_output.txt

#!/usr/bin/env bash

# @(#) s2       Demonstrate extraction of fields, csvtool.

# Utility functions: print-as-echo, print-line-with-visual-space, debug.
# export PATH="/usr/local/bin:/usr/bin:/bin"
LC_ALL=C ; LANG=C ; export LC_ALL LANG
pe() { for _i;do printf "%s" "$_i";done; printf "\n"; }
pl() { pe;pe "-----" ;pe "$*"; }
em() { pe "$*" >&2 ; }
db() { ( printf " db, ";for _i;do printf "%s" "$_i";done;printf "\n" ) >&2 ; }
db() { : ; }
C=$HOME/bin/context && [ -f $C ] && $C dixf sed pass-fail
pe
dixf csvtool

FILE=${1-data1}
E=expected-output.txt
H=headers

pl " Input data file $FILE:"
head $FILE

pl " Header name file $H, name list:"
head $H
h1=$( paste -s -d, $H )
pe " Header list = $h1"

pl " Expected output:"
cat $E

pl " Results, extract spaced-separated fields, write TAB-spaced:"
csvtool namedcol $h1 -t " " -u TAB $FILE |
tee f1

pl " Verify results if possible:"
C=$HOME/bin/pass-fail
[ -f $C ] && $C || ( pe; pe " Results cannot be verified." ) >&2

exit 0

#!/usr/bin/env bash

# @(#) s3       Demonstrate short perl code to add quotes to csv files.

LC_ALL=C ; LANG=C ; export LC_ALL LANG
pe() { for _i;do printf "%s" "$_i";done; printf "\n"; }
pl() { pe;pe "-----" ;pe "$*"; }
em() { pe "$*" >&2 ; }
db() { ( printf " db, ";for _i;do printf "%s" "$_i";done;printf "\n" ) >&2 ; }
db() { : ; }
C=$HOME/bin/context && [ -f $C ] && $C dixf
pe
dixf csvaq

FILE=${1-data3}

p=$( basename $0 ) t1="$Revision: 1.14 $" v=${t1//[!0-9.]/}
[[ $# -gt 0 ]] && [[ "$1" =~ -version ]] &&  { echo "$p (local) $v" ; exit 0 ; }

pl " Input data file $FILE:"
head $FILE

pl " Results, always add quotes:"
csvaq -q -t " " -u " " $FILE

exit 0

$ ./s3

Environment: LC_ALL = C, LANG = C
(Versions displayed with local utility "version")
OS, ker|rel, machine: Linux, 3.16.0-4-amd64, x86_64
Distribution        : Debian 8.6 (jessie) 
bash GNU bash 4.3.30
dixf (local) 1.21

csvaq   Add quotes for Comma Separated Value format files. (what)
Path    : ~/bin/csvaq
Version : 1.3
Length  : 165 lines
Type    : Perl script, ASCII text executable
Shebang : #!/usr/bin/env perl
Help    : probably available with [     ]-h,--help
Modules : (for perl codes)
 warnings       1.23
 strict 1.08
 diagnostics    1.34
 English        1.09
 Carp   1.3301
 Data::Dumper   2.151_01
 Getopt::Long   2.42
 feature        1.36_01
 experimental   0.007
 Text::CSV      1.32

-----
 Input data file data3:
cn0 name
cn,1 1,1,4,4-tetrabutylpiperazine
cn,2 N,N,N',N'-tetramethylguanidine
cn,3 1-(2-aminoethyl)piperazine

-----
 Results, always add quotes:
"cn0" "name"
"cn,1" "1,1,4,4-tetrabutylpiperazine"
"cn,2" "N,N,N',N'-tetramethylguanidine"
"cn,3" "1-(2-aminoethyl)piperazine"