Shell Programming and Scripting

-w, --word-regexp
Select only those lines containing matches that form whole words.  The test is that the matching substring must either be at  the  beginning  of
the  line,  or preceded by a non-word constituent character.  Similarly, it must be either at the end of the line or followed by a non-word con-
stituent character.  Word-constituent characters are letters, digits, and the underscore.

awk '{ for(i=1;i<=NF;i++) if($i=="test") print $i; }' filename

#!/usr/bin/env bash

# @(#) s1	Demonstrate a "grep -wo" for hyphenated words.

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

FILE=${1-data1}

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

pl " AWK code for grepw:"
p=./grepw
cat $p

pl " Results:"

pe
pe " Version of code:"
$p --version

pl " Print any word containing \"foo\" including hyphenated words:"
$p foo $FILE

pl " Matching hyphenated word foo-bar:"
$p foo-bar $FILE

pl " Matching toe-nail:"
$p toe-nail $FILE

pl " Matching toe-nail|finishing-nail (an OR):"
$p "toe-nail|finishing-nail" $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 5.0.8 (lenny) 
bash GNU bash 3.2.39
gawk GNU Awk 3.1.5

-----
 Input data file data1:
foo
bar
xyzzy
thud
foo-bar
The foo-bar came from a WWII term.
1234567890
You should toe-nail the studs, but don't use finishing-nails.

-----
 AWK code for grepw:
#!/usr/bin/env bash

# @(#) grepw	Search for words, grep-like, but also allow hyphens.

p=$( basename $0 ) t1="$Revision: 1.10 $" v=${t1//[!0-9.]/}
[[ $# > 0 ]] && [[ "$1" =~ -version ]] &&  { echo "$p $v" ; exit 0 ; }

if [ $# -le 0 ]
then
  pe "$p: must supply pattern -- $0" >&2
  exit 1
fi

PATTERN="$1"
shift

# Loop adapted from post at:
# http://stackoverflow.com/questions/1116193/
# awk-extract-multiple-groups-from-each-line

# ORs with "|" will work, but ANDs with ".*" will not work unless
# the string to match .* has no spaces in it.

gawk -v pattern="$PATTERN" '
	{ 
  from = 0
  i = 1
  pos = match( $0, /\<[-a-zA-Z0-9_]+\>/, val )
  while( 0 < pos )
  {
    # print val[0] in any form you desire.
    if ( val[0] ~ pattern ) printf(" Line %3d, token %2d, %s\n",
    NR, i, val[0] )
    from += pos + val[0, "length"]
    pos = match( substr( $0, from ), /\<[-a-zA-Z0-9_]+\>/, val )
    i++
  }

	}
' $*

exit 0

-----
 Results:

 Version of code:
grepw 1.10

-----
 Print any word containing "foo" including hyphenated words:
 Line   1, token  1, foo
 Line   5, token  1, foo-bar
 Line   6, token  2, foo-bar

-----
 Matching hyphenated word foo-bar:
 Line   5, token  1, foo-bar
 Line   6, token  2, foo-bar

-----
 Matching toe-nail:
 Line   8, token  3, toe-nail

-----
 Matching toe-nail|finishing-nail (an OR):
 Line   8, token  3, toe-nail
 Line   8, token 10, finishing-nails