Find duplicate files in SFTP/FTP server

The following example uses WinSCP .NET assembly from a PowerShell script. If you have another preferred language, you can easily translate it.

You can use the script to efficiently find duplicate files on a remote SFTP/FTP server. The script first iterates remote directory tree and looks for files with the same size. When it finds any, it by default downloads the files and compares them locally.

You can install this script as a WinSCP extension by using this page URL in the Add Extension command. If you known that the server supports a protocol extension for calculating checksums, you can improve the extension efficiency by configuring it to ask the server for the checksum, sparing the file download.

To run the script manually use:

powershell.exe -File C:\path\FindDuplicates.ps1 -remotePath "/path" -remoteChecksumAlg sha-1

# @name         Find &Duplicates...
# @command      powershell.exe -ExecutionPolicy Bypass -File "%EXTENSION_PATH%" -sessionUrl "!S" -remotePath "!/" -pause -remoteChecksumAlg "%RemoteChecksumAlg%" -sessionLogPath "%SessionLogPath%"
# @description  Searches for duplicate files on the server, starting from the current directory
# @flag         RemoteFiles
# @version      4
# @homepage     https://winscp.net/eng/docs/library_example_find_duplicate_files
# @require      WinSCP 5.9.1
# @option       RemoteChecksumAlg -config -run combobox "&Checksum:" "local" "local=Local sha-1" "sha1=Remote sha-1" "sha256=Remote sha-256" "md5=Remote md5" 
# @option       SessionLogPath -config sessionlogfile
# @optionspage  https://winscp.net/eng/docs/library_example_find_duplicate_files#options
 
param (
    # Use Generate URL function to obtain a value for -sessionUrl parameter.
    $sessionUrl = "sftp://user:mypassword;fingerprint=ssh-rsa-xx-xx-xx@example.com/",
    [Parameter(Mandatory = $True)]
    $remotePath,
    $remoteChecksumAlg = $Null,
    $sessionLogPath = $Null,
    [Switch]
    $pause
)
 
function FileChecksum ($remotePath)
{
    if (!($checksums.ContainsKey($remotePath)))
    {
        if (!$remoteChecksumAlg -or ($remoteChecksumAlg -eq "local"))
        {
            Write-Host "Downloading file $remotePath..."
            # Download file
            $localPath = [System.IO.Path]::GetTempFileName()
            $transferResult = $session.GetFiles($remotePath, $localPath)
 
            if ($transferResult.IsSuccess)
            {
                $stream = [System.IO.File]::OpenRead($localPath)
                $checksum = [System.BitConverter]::ToString($sha1.ComputeHash($stream))
                $stream.Dispose()
                
                Write-Host "Downloaded file $remotePath checksum is $checksum"
 
                Remove-Item $localPath
            }
            else
            {
                Write-Host "Error downloading file $remotePath: $($transferResult.Failures[0])"
                $checksum = $False
            }
        }
        else
        {
            Write-Host "Request checksum for file $remotePath..."
            $checksum = [System.BitConverter]::ToString($session.CalculateFileChecksum($remoteChecksumAlg, $remotePath))
            Write-Host "File $remotePath checksum is $checksum"
        }
 
        $checksums[$remotePath] = $checksum
    }
 
    return $checksums[$remotePath]
}
 
try
{
    # Load WinSCP .NET assembly
    $assemblyPath = if ($env:WINSCP_PATH) { $env:WINSCP_PATH } else { $PSScriptRoot }
    Add-Type -Path (Join-Path $assemblyPath "WinSCPnet.dll")
 
    # Setup session options from URL
    $sessionOptions = New-Object WinSCP.SessionOptions
    $sessionOptions.ParseUrl($sessionUrl)
 
    $session = New-Object WinSCP.Session
    
    try
    {
        $session.SessionLogPath = $sessionLogPath
 
        # Connect
        $session.Open($sessionOptions)
 
        # Handle errors when enumerating the files
        $session.add_Failed( { 
            Write-Host "Error: $($_.Exception.Message)"
        } )
 
        $sizes = @{}
        $checksums = @{}
        $duplicates = @{}
        
        $sha1 = [System.Security.Cryptography.SHA1]::Create()
 
        $files = $session.EnumerateRemoteFiles($remotePath, "*", [WinSCP.EnumerationOptions]::AllDirectories)
 
        foreach ($fileInfo in $files)
        {
            Write-Host "Found file $($fileInfo.FullName) with size $($fileInfo.Length)"
 
            if ($sizes.ContainsKey($fileInfo.Length))
            {
                $checksum = FileChecksum($fileInfo.FullName)
 
                foreach ($otherFilePath in $sizes[$fileInfo.Length])
                {
                    $otherChecksum = FileChecksum($otherFilePath)
 
                    if ($checksum -eq $otherChecksum)
                    {
                        Write-Host "Checksums of files $($fileInfo.FullName) and $($otherFilePath) are identical"
                        $duplicates[$fileInfo.FullName] = $otherFilePath
                    }
                }
            }
            else
            {
                $sizes[$fileInfo.Length] = @()
            }
 
            $sizes[$fileInfo.Length] += $fileInfo.FullName
        }
    }
    finally
    {
        # Disconnect, clean up
        $session.Dispose()
    }
 
    # Print results
    Write-Host
 
    if ($duplicates.Count -gt 0)
    {
        Write-Host "Duplicates found:"
 
        foreach ($path1 in $duplicates.Keys)
        {
            Write-Host "$path1 <=> $($duplicates[$path1])"
        }
    }
    else
    {
        Write-Host "No duplicates found."
    }
 
    $result = 0
}
catch [Exception]
{
    Write-Host "Error: $($_.Exception.Message)"
    $result = 1
}
 
# Pause if -pause switch was used
if ($pause)
{
    Write-Host "Press any key to exit..."
    [System.Console]::ReadKey() | Out-Null
}
 
exit $result