clean.sh

#!/bin/bash

INPUTFILE="./sample.json"
SORTED_OUTPUT="./sorted-sample.json"
MISSING_FILE="./missing-records.txt"
TEMP_FILE=$(mktemp /tmp/clean.XXXXXX)

# Prepend the value from "id" the beginning of the line so we can use
# standard unix cli tools like sort. Save it to a temp file.
cat sample.json | jq -cr '"\(.id)\t\(.)"' > $TEMP_FILE
# concatonate the file with IDs prepended, sort by the IDs. Pipe the sort output to "tee".
# One tee pipe has the prepended IDs and whitespace removed and written to SORTED_OUTPUT.
# The other is piped to AWK to find missing integers in the sequence of ids.
cat $TEMP_FILE | sort | tee >(cut -f2 >$SORTED_OUTPUT) | (awk '{for(i=p+1; i<$1; i++) print i} {p=$1}') > $MISSING_FILE
#clean up the temp file.
rm $TEMP_FILE