Removing duplicate files with Powershell

Question

I have several thousand duplicate files (jar files as an example) that I\'d like to use powershell to

1. Search through the file system recursively
2. Find the

Answer 1

Instead of just remove your duplicates files, you can replace by a shortcut

#requires -version 3
<#
    .SYNOPSIS
    Script de nettoyage des doublons
    .DESCRIPTION
    Cherche les doublons par taille, compare leur CheckSum MD5 et les regroupes par Taille et MD5
    peut remplacer chacun des doubles par un lien vers le 1er fichier, l'original

    .PARAMETER Path
    Chemin ou rechercher les doublon

    .PARAMETER ReplaceByShortcut
    si specifier alors les doublons seront remplacé

    .PARAMETER MinLength
    ignore les fichiers inferieure a cette taille (en Octets)

    .EXAMPLE
    .\Clean-Duplicate '\\dfs.adds\donnees\commun'

    .EXAMPLE
    recherche les doublon de 10Ko et plus
    .\Clean-Duplicate '\\dfs.adds\donnees\commun' -MinLength 10000

    .EXAMPLE
    .\Clean-Duplicate '\\dpm1\d$\Coaxis\Logiciels' -ReplaceByShortcut
#>
[CmdletBinding()]
param (
    [string]$Path = '\\Contoso.adds\share$\path\data',
    [switch]$ReplaceByShortcut = $false,
    [int]$MinLength = 10*1024*1024 # 10 Mo
)

$version = '1.0'

function Create-ShortCut ($ShortcutPath, $shortCutName, $Target) {
    $link = "$ShortcutPath\$shortCutName.lnk"
    $WshShell = New-Object -ComObject WScript.Shell
    $Shortcut = $WshShell.CreateShortcut($link)
    $Shortcut.TargetPath = $Target
    #$Shortcut.Arguments ="shell32.dll,Control_RunDLL hotplug.dll"
    #$Shortcut.IconLocation = "hotplug.dll,0"
    $Shortcut.Description ="Copy Doublon"
    #$Shortcut.WorkingDirectory ="C:\Windows\System32"
    $Shortcut.Save()
    # write-host -fore Cyan $link -nonewline; write-host -fore Red ' >> ' -nonewline; write-host -fore Yellow $Target 
    return $link
}

function Replace-ByShortcut {
    Param(
        [Parameter(ValueFromPipeline=$true,ValueFromPipelineByPropertyName=$true)]
            $SameItems
    )
    begin{
        $result = [pscustomobject][ordered]@{
            Replaced = @()
            Gain = 0
            Count = 0
        }
    }
    Process{
        $Original = $SameItems.group[0]
        foreach ($doublon in $SameItems.group) {
            if ($doublon -ne $Original) {
                $result.Replaced += [pscustomobject][ordered]@{
                    lnk = Create-Shortcut -ShortcutPath $doublon.DirectoryName -shortCutName $doublon.BaseName -Target $Original.FullName
                    target = $Original.FullName
                    size = $doublon.Length
                }
                $result.Gain += $doublon.Length
                $result.Count++
                Remove-item $doublon.FullName -force
            }
        }
    }
    End{
        $result
    }
}

function Get-MD5 {
    param (
        [Parameter(Mandatory)]
            [string]$Path
    )
    $HashAlgorithm = New-Object -TypeName System.Security.Cryptography.MD5CryptoServiceProvider
    $Stream = [System.IO.File]::OpenRead($Path)
    try {
        $HashByteArray = $HashAlgorithm.ComputeHash($Stream)
    } finally {
        $Stream.Dispose()
    }

    return [System.BitConverter]::ToString($HashByteArray).ToLowerInvariant() -replace '-',''
}

if (-not $Path) {
    if ((Get-Location).Provider.Name -ne 'FileSystem') {
        Write-Error 'Specify a file system path explicitly, or change the current location to a file system path.'
        return
    }
    $Path = (Get-Location).ProviderPath
}

$DuplicateFiles = Get-ChildItem -Path $Path -Recurse -File |
    Where-Object { $_.Length -gt $MinLength } |
        Group-Object -Property Length |
            Where-Object { $_.Count -gt 1 } |
                ForEach-Object {
                    $_.Group |
                        ForEach-Object {
                            $_ | Add-Member -MemberType NoteProperty -Name ContentHash -Value (Get-MD5 -Path $_.FullName)
                        }
                    $_.Group |
                        Group-Object -Property ContentHash |
                            Where-Object { $_.Count -gt 1 }
                }

$somme = ($DuplicateFiles.group | Measure-Object length -Sum).sum
write-host "$($DuplicateFiles.group.count) doublons, soit $($somme/1024/1024) Mo" -fore cyan

if ($ReplaceByShortcut) {
    $DuplicateFiles | Replace-ByShortcut
} else {
    $DuplicateFiles
}