argin.sh : universal xargs properly handled from ANY standard input. Plus parallelization is activated by default. (No more hassles with the null character :-) argin.sh converts lines from stdin into arguments to build and execute a command individually.

argin.sh

#!/usr/bin/env bash
#              bash 4.1.5(1)     Linux Ubuntu 10.04           Date : 2012-03-22
#
# _______________|  argin : xargs properly handled from ANY standard input.
#                           xargs converts stdin into arguments in order
#                           to build and execute a command individually.
#
#           Usage:  argin [options] command [{} as placeholder if necessary]
#
#        Examples:  % argin -t echo {} < foo.txt 2> argin-done.txt
#                   #       -t prints command to STDERR before issuing it. 
#                   #       -p prompt about whether to run each command line.
#                   #       -P1 for serial, not faster parallel, execution.
#                   #
#                   % cat foo.txt | argin echo {}
#                   #     same thing without a record of executed commands.
#                   #     {} placeholder is available for incoming arguments;
#                   % cat foo.txt | argin echo 
#                   #     absent {} will be implicitly placed at the end.
#
#    Dependencies:  xargs and tr.
#                   [GNU parallel is not needed here -- it's overkill ;-]
#
#    ___ATTN___     xargs works best with null character as separator.
#    argin is the prefilter which solves this problem from ANY standard input.
#    Blank and comment lines are ignored by argin.


#  CHANGE LOG  LATEST version available:   https://bitbucket.org/rsvp/gists/src
#
#  2012-03-22  Minor fixes. 
#  2012-03-21  Joshua Levy suggested using parallel option -P0
#                 for dramatic speedup in execution.
#  2012-03-20  Most helpful reference: http://en.wikipedia.org/wiki/Xargs


#           _____ 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'}

cmdarg="$@"

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 ::::::::::::::::::::::::::::::::::::::::


testarg=${cmdarg//\{\}/}
#               ^globally remove {} from cmdarg

#  #  We could make the use of placeholder {} mandatory...
#  [ "$testarg" = "$cmdarg" ]  &&  die "must use {} to replace argument." 115

#  ... OR, we can add missing {} at the end for the user's convenience:
if [ "$testarg" = "$cmdarg" ] ; then 
     cmdarg="$@ {}"
fi


#      __________ MAIN one-liner
#
#  Delete all blank lines since as empty arguments they could be dangerous.
#  Also delete comment lines beginning with '# ' -- so allow hashtag.
#  sed is using standard input '-' here.
#       Then, translate any newline to NULL CHARACTER.
sed -e '/^[[:blank:]]*$/d'  -e '/^# /d'  -                               \
     |  tr  \\n  \\0                                                     \
     |  xargs -r -0 -I '{}' -n1 -P0 $cmdarg  ||  die "given bad command." 113
#                               ^Parallel execution for speedup...
#                                (don't expect serial arg ordering
#                                 unless -P1 is used at commandline;
#                                 later option will overrule).
#                       ^replacement string.
#             -r means don't execute command if no input was received.

#  -0      Input items are terminated by a null character instead of by
#  whitespace, and the quotes and backslash are not special (every character 
#  is taken literally).  Disables the end of file string, which is treated 
#  like any other argument.  Useful when input items might contain white space, 
#  quote marks, backslashes, or commas.  

#  -I replace-str  [where we use {} as the replace-str]
#  Replace occurrences of replace-str in the initial-arguments with names read 
#  from standard input.  Also, unquoted blanks do not terminate input items; 
#  instead the separator is the newline character.  Implies -x and -L 1.
#  ___ATTN___ Thus this uses at most ONE NONBLANK INPUT LINES PER COMMAND LINE.
#
#             GENERALLY, blank lines from standard input are ignored.
#
#       Without replace-str, the argument simply gets tacked on the end.
#       So for example, without {} this move would not be possible:
#            % cat filenames.txt | argin mv {} /tmp
#
#       The use of '{}' as placeholder is merely conventional,
#       it could have been '@@ARGUMENT' or any other string.


#            _____ Other options, esp. PARALLEL execution.
#                  Speedup is over 2x even on single core processor. 
#                  Execution will not be in serial order of arguments.
#  
#    --max-procs=max-procs
#    -P max-procs
#           Run up to max-procs processes at a time; the default is 1.  If
#           max-procs is 0, xargs will run as many processes as possible
#           at a time.  Use the -n option with -P; otherwise chances are
#           that only one exec will be done.
#  
#    --max-args=max-args
#    -n max-args
#           Use at most max-args arguments per command line.  Fewer than
#           max-args arguments will be used if the size (see the -s
#           option) is exceeded, unless the -x option is given, in which
#           case xargs will exit.
#                [ Set to 1 without any loss of generality 
#                  since -L1 is implied by using placeholder with -I. ]



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


#           _____ DECLARING FREEDOM from remembering these NULL options!    :-)
#  
#       perl   (requires -0 and \0 instead of \n) 
#       locate (requires using -0) 
#       find   (requires using -print0) 
#       grep   (requires -z or -Z) 
#       sort   (requires using -z)


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