jason.sh : pretty print json for key-value processing line-by-line. The goal is a readable and grepable output.

jason.sh

#!/usr/bin/env bash
#              bash 4.1.5(1)     Linux Ubuntu 10.04           Date : 2012-06-16
#
# _______________|  jason : pretty print json for key-value processing by line.
#
#           Usage:  jason  [file]  [ident=5]  [delim='__:']
#
#        Examples:  % jason foo.json  0 ': '
#                   #                    ^typical json key-value separator.
#                   #                 ^ident of 0 for just newline.
#                   % jason foo.json
#                   #       ^try this first for readability and grep.
#
#    Dependencies:  Python json module


#  CHANGE LOG  LATEST version available:   https://bitbucket.org/rsvp/gists/src
#
#  2012-06-16  Use json.loads() instead of json.JSONDecoder().decode().
#  2012-06-15  Start using Python json module instead of awk.
#                 Note that json module since 2.6 is simplejason.
#
#  2012-02-26  Handle errors and those daggling braces.
#  2012-02-25  First experimental version to parse json file.
#                 It will be IMPERFECT because the structure of a 
#                 particular json file will generally vary.
#
#  A json file is NOT easily readable especially in 
#  compact form without spaces and without newlines.
#
#  The goal is a readable and grepable output, 
#  which can be further refined by awk.


#           _____ 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'}

jsonf="$1"
indent=${2:-'5'}
delim=${3:-'__:'}


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


[ -e "$jsonf" ] || die "non-existent file: $jsonf" 113


{ python <<EOHereDoc
import json

#  >>> #  2012-04-30  PRETTY PRINT using Python's json module:
#  >>> print json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=5)
#       {
#            "4": 5,
#            "6": 7
#       }

with open( "$jsonf", 'rb' ) as f:
     #                ^binary 
     data = json.loads( f.read() )
     #           ^convert json string into its Python representation.
     print json.dumps( data, sort_keys=True, indent = $indent )

     #  If indent is a non-negative integer (it is None by default), 
     #  then JSON array elements and object members will be 
     #  pretty-printed with that indent level. An indent level of 0 
     #  will only insert newlines. None is the most compact representation.

EOHereDoc
}         | sed -e 's/, *$//'  -e 's/{$//' > $memf
#                                 ^delete leading brace, but not the line.
#                  ^delete trailing commas
#                   since newline will become field separator.

#  #    sample output with indent set at 5 before sed:
#  {
#       "130.12.1.34": {
#            "area_code": 0, 
#            "country_code": "CA", 
#            "country_code3": "CAN", 
#            "country_name": "Canada", 
#            "dma_code": 0, 
#            "latitude": 44.233299255371101, 
#            "locality": "Kingston", 
#            "longitude": -76.483299255371094, 
#            "postal_code": "", 
#            "region": "ON"
#       }, 
#       "67.169.73.113": {
#            "area_code": 415, 
#            "country_code": "US", 
#            "country_code3": "USA", 
#            "country_name": "United States", 
#            "dma_code": 807, 
#            "latitude": 37.758701324462898, 
#            "locality": "San Francisco", 
#            "longitude": -122.438102722168, 
#            "postal_code": "94114", 
#            "region": "CA"
#       }
#  }


#  Elaborate way to eliminate first open brace, and last closing brace:
lines=$( cat $memf | wc -l )
line1=$(( lines - 1 ))
line2=$(( lines - 2 ))
tail -n $line1 $memf | head -n $line2  \
     |  sed -e 's/"//'  -e "s/\": /$delim/"
     #  sed unquotes the key, and then substitutes delim.


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



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