Thanks for that link. I took it, sped it up, and updated it for PowerShell v2.
Param (
[string] $Path = (Get-Location),
[Switch] $ShowDuplicates
)
$script:cryptoServiceProvider =
[System.Security.Cryptography.MD5CryptoServiceProvider]
$script:hashAlgorithm = New-Object $script:cryptoServiceProvider
function Get-MD5
{
Param (
[System.IO.FileInfo] $file = $(throw 'Usage: Get-MD5
[System.IO.FileInfo]')
)
# This Get-MD5 function sourced from:
# http://blogs.msdn.com/powershell/archive/2006/04/25/583225.aspx
# Updated for PowerShell v2.0.
try
{
$stream = $file.OpenRead()
$hashByteArray = $script:hashAlgorithm.ComputeHash( $stream )
}
finally
{
if( $stream )
{
$stream.Close()
}
}
return [string]$hashByteArray
}
if( 1 )
{
$directoryInfo = New-Object System.IO.DirectoryInfo( $Path )
$fileGroups = $directoryInfo.GetFiles( '*', 'AllDirectories' ) |
? { $_.Length -gt 0 } |
group Length |
? { $_.Count -gt 1 }
}
else
{
$fileGroups = Get-ChildItem $Path -Recurse |
Where-Object { $_.Length -gt 0 } |
Group-Object Length |
Where-Object { $_.Count -gt 1 }
}
$results = @()
foreach ($fileGroup in $fileGroups)
{
foreach ($file in $fileGroup.Group)
{
Add-Member NoteProperty ContentHash (Get-MD5 $file) -InputObject
$file
}
$result = $fileGroup.Group |
Group-Object ContentHash |
Where-Object { $_.Count -gt 1 }
if( $result )
{
$results += $result
}
}
if( $filegroups -and $fileGroups.Count -and ( $fileGroups.Count -gt 0 ) )
{
write-host "Total filegroups = $($fileGroups.Count)"
}
if( $ShowDuplicates )
{
foreach( $entry in $results )
{
if( $entry.Count -gt 1 )
{
foreach( $item in $entry.Group )
{
$item.Fullname
}
" "
}
}
}
else
{
$results
}
$results = $null
$filegroups = $null
$directoryInfo = $null
$script:hashAlgorithm = $null
$script:cryptoServiceProvider = $null
Regards,
Michael B. Smith
Consultant and Exchange MVP
http://TheEssentialExchange.com
-----Original Message-----
From: Kurt Buff [mailto:[email protected]]
Sent: Wednesday, August 03, 2011 1:34 PM
To: NT System Admin Issues
Subject: Re: find duplicate files
Try this, among others:
http://blog.codeassassin.com/2007/10/13/find-duplicate-files-with-powershell/
Kurt
On Wed, Aug 3, 2011 at 08:47, Bill Humphries
<[email protected]<mailto:[email protected]>> wrote:
> Hi all,
>
> Any suggestions for a tool that I could use to search for duplicate files on
> a 20tb Xsan? Although it primarily has Macs attached to it, I do have one
> windows machine.
>
> Thanks.
>
> Bill
>
> ~ Finally, powerful endpoint security that ISN'T a resource hog! ~
> ~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/> ~
>
> ---
> To manage subscriptions click here:
> http://lyris.sunbelt-software.com/read/my_forums/
> or send an email to
> [email protected]<mailto:[email protected]>
> with the body: unsubscribe ntsysadmin
>
~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/> ~
---
To manage subscriptions click here:
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to
[email protected]<mailto:[email protected]>
with the body: unsubscribe ntsysadmin
~ Finally, powerful endpoint security that ISN'T a resource hog! ~
~ <http://www.sunbeltsoftware.com/Business/VIPRE-Enterprise/> ~
---
To manage subscriptions click here:
http://lyris.sunbelt-software.com/read/my_forums/
or send an email to [email protected]
with the body: unsubscribe ntsysadmin
