*Updated: 11 Dec 2007

I'm wondering where I should store the scripts I'm writing. Out of pure laziness, I'll just dump them as my blog entry for now.

Here's a script to check for missing files after a directory has been re-organised. Basically, it compares the md5sum of the files in the old directory and the new directory.

Please let me know if there are any bugs.

#!/bin/bash

#########################
#
# checkNoMissingFiles
# ===================
#
# This script checks that no files are missing after folders are reorganised.
# Basic algorithm is to checksum all files in both old and new folders, then
# checking through both lists of checksums to ensure all checksums are present
# in both lists.
#
# Changelog
# =========
#
# 18 Oct 2007 - Junhao
# * Initial commit
#
# 11 Dec 2007 - Junhao
# * Tidied style
# * Fixed bug with spaces in filenames
# * added option to save generated checksums
# * changed md5sum to sha1sum
# * changed checksum to general algorithm
#########################

PATH=/bin:/usr/bin;

## Program Locations
awk=/usr/bin/awk
cat=/usr/bin/cat
echo=/usr/bin/echo
find=/usr/bin/find
grep=/bin/grep
checksum="/usr/bin/sha1sum"
mktemp=/bin/mktemp
rm=/usr/bin/rm
tee="/usr/bin/tee -a"
touch="/bin/touch"
## End Program Locations

## Start Script

## Script parameters
f_logFile=/dev/null
d_orgLoc=/dev/null
d_newLoc=/dev/null
v_oldFileName=
v_oldFileChksum=
f_oldChksumLog=
f_newChksumLog=
v_missingFilesCount=0
v_missingFiles=""
v_output=
v_f1flag=1
v_f2flag=1
## End Script parameters

function print_usage () {
    ${echo} "
$0
Usage: $0 [-L logfile] [-f1 filename] [-f2 filename] [oldDir] [newDir]
 or    $0 -h
Description: Checks that there are no missing files after reorganising a directory.
Options:
  -L logfile    (Optional) Path to log file
  -h            (Optional) This help text
  -1           (Optional) Filename to save checksum for old directory
  -2           (OPtional) Filename to save checksum for new directory
  oldDir        Location of old directory
  newDir        Location of new directory
"
}

if [ $# -lt 2 ]; then
    print_usage
    exit 1
else
    while getopts hL:1:2: options; do
        case "${options}" in
            h)  print_usage
                exit 1
                ;;
            L)  f_logFile=${OPTARG}
                ;;
            1)  f_oldChksumLog=${OPTARG}
                v_f1flag=0
                ;;
            2)  f_newChksumLog=${OPTARG}
                v_f2flag=0
                ;;
            *)  f_logFile=/dev/null
                ;;
        esac
    done
    shift $((${OPTIND} - 1))

    if [ -d $1 ]; then
        d_orgLoc=$1
    else
        ${echo} "Error: Original directory does not exist!"
        print_usage
        exit 1
    fi

    if [ -d $2 ]; then
        d_newLoc=$2
    else
        ${echo} "Error: New directory does not exist!"
        print_usage
        exit 1
    fi

    if [ -z ${f_oldChksumLog} ]; then
        f_oldChksumLog=${mktemp}
    elif [ -f ${f_oldChksumLog} ]; then
        ${echo} "Error: File ${f_oldChksumLog} exists! Please give another filename."
        exit 2
    else
        ${touch} ${f_oldChksumLog}
        if [ ! -f ${f_oldChksumLog} ]; then
            ${echo} "Error: ${f_oldChksumLog} cannot be created!"
            exit 4
        fi
    fi

    if [ -z ${f_newChksumLog} ]; then
        f_oldChksumLog=${mktemp}
    elif [ -f ${f_newChksumLog} ]; then
        ${echo} "Error: File ${f_newChksumLog} exists! Please give another filename."
        exit 3
    else
        ${touch} ${f_newChksumLog}
        if [ ! -f ${f_newChksumLog} ]; then
            ${echo} "Error: File ${f_newChksumLog} cannot be created!"
            exit 5
        fi
    fi
fi

${echo} "${find} \"${d_orgLoc}\" -type f -exec ${checksum} \\"\{\}\\" \;" | ${tee} ${f_logFile}
${find} "${d_orgLoc}" -type f -exec ${checksum} \"\{\}\" \; | ${tee} ${f_oldChksumLog}
${find} "${find} \"${d_newLoc}\" -type f -exec ${checksum} \\"\{\}\\" \;" | ${tee} ${f_logFile}
${find} "${d_newLoc}" -type f -exec ${checksum} \"\{\}\" \; | ${tee} ${f_newChksumLog}


while read -r v_oldFileChksum v_oldFileName; do
    if [[ `${grep} ${v_oldFileChksum} ${f_newChksumLog}` ]]; then
        v_output="Okay:  ${v_oldFileName} -> "
        v_output="${v_output} `${grep} \"${v_oldFileChksum}\" \"${f_newChksumLog}\" | ${awk} '{print $2}'`"
    else
        v_output="ERROR: ${v_oldFileName} is missing"
        v_missingFiles="${v_missingFiles} ${v_oldFileName}"
        v_missingFilesCount=$((v_missingFilesCount+1))
    fi
    ${echo} "${v_output}" | ${tee} ${f_logFile}
done < ${f_oldChksumLog}

#### cleanup ####
if [ "1" == ${v_f1flag} ]; then
    ${rm} ${f_oldChksumLot}
fi
if [ "1" == ${v_f2flag} ]; then
    ${rm} ${f_newChksumLog}
fi


if [ ${v_missingFilesCount} -gt 0 ]; then
    ${echo} "ERROR: ${v_missingFilesCount} files are missing:" | ${tee} ${f_logFile}
    ${echo} "ERROR:   ${v_missingFiles}" | ${tee} ${f_logFile}
    exit 99
else
    ${echo} "Success: ${v_missingFilesCount} files are missing" | ${tee} ${f_logFile}
    exit 0
fi