#!/usr/bin/env bash

# @(#) s1	Demonstrate creation of string from index of strings.

echo
set +o nounset
LC_ALL=C ; LANG=C ; export LC_ALL LANG
echo "Environment: LC_ALL = $LC_ALL, LANG = $LANG"
echo "(Versions displayed with local utility \"version\")"
version >/dev/null 2>&1 && version "=o" $(_eat $0 $1) tr cut grep sed
set -o nounset
echo

FILE1=data1
FILE2=data2

echo
echo " Data file $FILE1:"
cat $FILE1

echo
echo " Data file $FILE2:"
cat $FILE2

echo
echo " Results:"
tr -s ' ' <$FILE1 |
cut -d" " -f3 >t1

for key in $( cat t1 )
do
  # echo
  # echo " File $key:"
  if [ -z "$(grep "$key" $FILE2)" ] 
  then
    echo " Ignoring $key: no match." >&2
	continue
  fi
  grep "$key" $FILE2 |
  tr -s ' ' |
  cut -d" " -f2 |
  paste -d" "  -s |
  sed 's/ EOS/./'
done

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 
GNU bash 3.2.39
tr (GNU coreutils) 6.10
cut (GNU coreutils) 6.10
GNU grep 2.5.3
GNU sed version 4.1.5


 Data file data1:
0.00765600    0.08450704    M3    E3 
0.00441931    0.04878049    M4    E5 
0.01904574    0.21022727    M5    E10
0.00510400    0.05633803    M6    E12
0.00905960    0.10000000    M7    E16
0.00799376    0.08823529    M8    E17
0.00424669    0.04687500    M9    E18

 Data file data2:
M4  asd
M4  dfgg
M4  rtyt
M4  rtytry
M4  etrert
M4  EOS
M5  tyuty
M5  ertert
M5  yuyu
M5  EOS
M6  iui
M6  jkjk
M6  EOS

 Results:
 Ignoring M3: no match.
asd dfgg rtyt rtytry etrert.
tyuty ertert yuyu.
iui jkjk.
 Ignoring M7: no match.
 Ignoring M8: no match.
 Ignoring M9: no match.

#!/usr/bin/perl

# @(#) p1	Demonstrate creation of string from index of strings.

use warnings;
use strict;

my ($debug);
$debug = 1;
$debug = 0;

my ( $f1, $f2, $i, @index, $junk, $key, %sentence, $t1 );

open( $f1, "<", "data1" ) || die(" Cannot open data1.\n");

# Get the indices into array "index".

while (<$f1>) {
  $t1 = (split)[2];
  push @index, $t1;
}
print " index is :@index:\n" if $debug;
close $f1;

open( $f2, "<", "data2" ) || die(" Cannot open data2.\n");

# Read data file of words, check for match to anything in array
# "index", add to appropriate sentence hash.

while (<$f2>) {
  chomp;
  print " Working on line :$_:\n" if $debug;
  for ( $i = 0; $i <= $#index; $i++ ) {
    if (/^$index[$i]/) {
      print " Found match for :$_:\n" if $debug;
      $t1 = (split)[1];
      print " Adding :$t1: to sentence.\n" if $debug;
      $sentence{ $index[$i] } .= "$t1 ";
    }
  }
}

# Print the completed hash of sentences.

for $key ( sort keys %sentence ) {
  $sentence{$key} =~ s/ EOS/./;
  print "$sentence{$key}\n";
}

exit(0);

% ./p1
asd dfgg rtyt rtytry etrert. 
tyuty ertert yuyu. 
iui jkjk.