Find duplicate files in SFTP/FTP protocol

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.

If you known that the server supports a protocol extension for calculating checksums, you can improve the script efficiency by adding -remoteChecksumAlg switch, to make the script ask the server for the checksum, sparing the file download.

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

You can use the script from WinSCP GUI as a local custom command.

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)]
    $remotePath,
    $remoteChecksumAlg = $Null
)
 
function FileChecksum ($remotePath)
{
    if (!($checksums.ContainsKey($remotePath)))
    {
        if ($remoteChecksumAlg -eq $Null)
        {
            Write-Host ("Downloading file {0}..." -f $remotePath)
            # Download file
            $localPath = [System.IO.Path]::GetTempFileName()
            $transferResult = $session.GetFiles($remotePath, $localPath)
 
            if ($transferResult.IsSuccess)
            {
                $stream = [System.IO.File]::OpenRead($localPath)
                $checksum = [BitConverter]::ToString($sha1.ComputeHash($stream))
                $stream.Dispose()
                
                Write-Host ("Downloaded file {0} checksum is {1}" -f $remotePath, $checksum)
 
                Remove-Item $localPath
            }
            else
            {
                Write-Host ("Error downloading file {0}: {1}" -f $remotePath, $transferResult.Failures[0])
                $checksum = $False
            }
        }
        else
        {
            Write-Host ("Request checksum for file {0}..." -f $remotePath)
            $checksum = [BitConverter]::ToString($session.CalculateFileChecksum($remoteChecksumAlg, $remotePath))
            Write-Host ("File {0} checksum is {1}" -f $remotePath, $checksum)
        }
 
        $checksums[$remotePath] = $checksum
    }
 
    return $checksums[$remotePath]
}
 
function FindDuplicatesInDirectory ($remotePath)
{
    Write-Host ("Finding duplicates in directory {0} ..." -f $remotePath)
 
    try
    {
        $directoryInfo = $session.ListDirectory($remotePath)
 
        foreach ($fileInfo in $directoryInfo.Files)
        {
            $remoteFilePath = ($remotePath + "/" + $fileInfo.Name) 
            
            if ($fileInfo.IsDirectory)
            {
                # Skip references to current and parent directories
                if (($fileInfo.Name -ne ".") -and
                    ($fileInfo.Name -ne ".."))
                {
                    # Recurse into subdirectories
                    FindDuplicatesInDirectory $remoteFilePath
                }
            }
            else
            {
                Write-Host ("Found file {0} with size {1}" -f $remoteFilePath, $fileInfo.Length)
 
                if ($sizes.ContainsKey($fileInfo.Length))
                {
                    $checksum = FileChecksum($remoteFilePath)
 
                    foreach ($otherFilePath in $sizes[$fileInfo.Length])
                    {
                        $otherChecksum = FileChecksum($otherFilePath)
 
                        if ($checksum -eq $otherChecksum)
                        {
                            Write-Host ("Checksums of files {0} and {1} are identical" -f $remoteFilePath, $otherFilePath)
                            $duplicates[$remoteFilePath] = $otherFilePath
                        }
                    }
                }
                else
                {
                    $sizes[$fileInfo.Length] = @()
                }
 
                $sizes[$fileInfo.Length] += $remoteFilePath
            }
        }
    }
    catch [Exception]
    {
        Write-Host ("Error processing directory {0}: {1}" -f $remotePath, $_.Exception.Message)
    }
}
 
try
{
    # Load WinSCP .NET assembly
    Add-Type -Path "WinSCPnet.dll"
 
    # Setup session options from URL
    $sessionOptions = New-Object WinSCP.SessionOptions
    $sessionOptions.ParseUrl($sessionUrl)
 
    $session = New-Object WinSCP.Session
    $session.SessionLogPath = "session.log"
    
    try
    {
        # Connect
        $session.Open($sessionOptions)
 
        $sizes = @{}
        $checksums = @{}
        $duplicates = @{}
        
        $sha1 = [System.Security.Cryptography.SHA1]::Create()
 
        # Start recursion
        FindDuplicatesInDirectory $remotePath
    }
    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 ("{0} <=> {1}" -f $path1, $duplicates[$path1])
        }
    }
    else
    {
        Write-Host "No duplicates found."
    }
 
    exit 0
}
catch [Exception]
{
    Write-Host $_.Exception.Message
    exit 1
}