lincol.sh : convert regex delimited lines into single column. E.g. linecol foo.csv ', *' #-- so each item on a CSV line will be on its own line.

linecol.sh

#!/usr/bin/env bash
#              bash 4.1.5(1)     Linux Ubuntu 10.04           Date : 2012-04-06
#
# _______________|  linecol : convert regex delimited lines into single column.
#
#           Usage:  linecol  [filename]  [delimiter regex] 
#
#        Examples:  % linecol foo.csv ', *'
#                   #                 ^use single quotes for regex.
#                   #  Each item on a CSV line will be on its own line.
#
#    Dependencies:  sed, awk 


#  CHANGE LOG  LATEST version available:   https://bitbucket.org/rsvp/gists/src
#
#  2012-04-06  Reverse argument order, consistent with colline.
#  2012-03-26  First version of an idiom. Leading and trailing blank
#                 characters are removed.


#           _____ PREAMBLE_v2: settings, variables, and error handling.
#
LC_ALL=POSIX
#      locale means "ASCII, US English, no special rules, 
#      output per ISO and RFC standards." 
#      Esp. use ASCII encoding for glob and sorting characters. 
shopt -s   extglob
#     ^set extended glob for pattern matching.
set -e
#   ^errors checked: immediate exit if a command has non-zero status. 
set -u
#   ^unassigned variables shall be errors.
#    Example of default VARIABLE ASSIGNMENT:  arg1=${1:-'foo'}

arg1=${1:-'-'}
#          ^default: standard input. 
arg2=${2:-', *'}
#          ^default: CSV format. 
#                    arg2 is the FS Field Separator passed to awk.


program=${0##*/}   #  similar to using basename
memf=$( mktemp /dev/shm/88_${program}_tmp.XXXXXXXXXX )


cleanup () {
     #  Delete temporary files, then optionally exit given status.
     local status=${1:-'0'}
     rm -f $memf
     [ $status = '-1' ] ||  exit $status      #  thus -1 prevents exit.
} #--------------------------------------------------------------------
warn () {
     #  Message with basename to stderr.          Usage: warn "message"
     echo -e "\n !!  ${program}: $1 "  >&2
} #--------------------------------------------------------------------
die () {
     #  Exit with status of most recent command or custom status, after
     #  cleanup and warn.      Usage: command || die "message" [status]
     local status=${2:-"$?"}
     cleanup -1  &&   warn "$1"  &&  exit $status
} #--------------------------------------------------------------------
trap "die 'SIG disruption, but cleanup finished.' 114" 1 2 3 15
#    Cleanup after INTERRUPT: 1=SIGHUP, 2=SIGINT, 3=SIGQUIT, 15=SIGTERM
#
# _______________     ::  BEGIN  Script ::::::::::::::::::::::::::::::::::::::::


#           _____ MASSAGE text
#           Remove leading and trailing blanks...
#
sed -e 's/^[[:blank:]]*//' -e 's/[[:blank:]]*$//'   \
                                            "$arg1"  >  $memf
#      -e '/^[[:blank:]]*$/d'               "$arg1"  >  $memf
#      ^decided: NO REMOVAL of BLANK LINES
#       because they might be record separators!
#       Due to the previous substitution, each 
#       blank line will be a "pure" newline.


#      __________ AWK within a bash script
#                 Here Document goes to stdin as program file.
#                 Bash variables are recognized, so escape awk field numbers.
#
{ awk -f - $memf <<EOHereDoc
     BEGIN { FS = "$arg2" }
     { for ( i = 1; i <= NF; ++i )
          print \$i }
     #    ^each field gets printed on its own line.
EOHereDoc
}          ||  die "bad awk." 113


cleanup
# _______________ EOS ::  END of Script ::::::::::::::::::::::::::::::::::::::::

#  vim: set fileencoding=utf-8 ff=unix tw=78 ai syn=sh :