Skip to content

Instantly share code, notes, and snippets.

@cchamberlain
Last active September 30, 2024 14:38
Show Gist options
  • Save cchamberlain/883959151aa1162e73f1 to your computer and use it in GitHub Desktop.
Save cchamberlain/883959151aa1162e73f1 to your computer and use it in GitHub Desktop.
Recursively diffs 2 directories (files and contents) using MD5 hashes - Includes validation for paths and optional summary export. Requires PowerShell 3.0 or later.
#########################################################################
### USAGE: rdiff path/to/left,path/to/right [-s path/to/summary/dir] ###
### ADD LOCATION OF THIS SCRIPT TO PATH ###
#########################################################################
[CmdletBinding()]
param (
[parameter(HelpMessage="Stores the execution working directory.")]
[string]$ExecutionDirectory=$PWD,
[parameter(Position=0,HelpMessage="Compare two directories recursively for differences.")]
[alias("c")]
[string[]]$Compare,
[parameter(HelpMessage="Export a summary to path.")]
[alias("s")]
[string]$ExportSummary
)
### FUNCTION DEFINITIONS ###
# SETS WORKING DIRECTORY FOR .NET #
function SetWorkDir($PathName, $TestPath) {
$AbsPath = NormalizePath $PathName $TestPath
Set-Location $AbsPath
[System.IO.Directory]::SetCurrentDirectory($AbsPath)
}
# RESTORES THE EXECUTION WORKING DIRECTORY AND EXITS #
function SafeExit() {
SetWorkDir /path/to/execution/directory $ExecutionDirectory
Exit
}
function Print {
[CmdletBinding()]
param (
[parameter(Mandatory=$TRUE,Position=0,HelpMessage="Message to print.")]
[string]$Message,
[parameter(HelpMessage="Specifies a success.")]
[alias("s")]
[switch]$SuccessFlag,
[parameter(HelpMessage="Specifies a warning.")]
[alias("w")]
[switch]$WarningFlag,
[parameter(HelpMessage="Specifies an error.")]
[alias("e")]
[switch]$ErrorFlag,
[parameter(HelpMessage="Specifies a fatal error.")]
[alias("f")]
[switch]$FatalFlag,
[parameter(HelpMessage="Specifies a info message.")]
[alias("i")]
[switch]$InfoFlag = !$SuccessFlag -and !$WarningFlag -and !$ErrorFlag -and !$FatalFlag,
[parameter(HelpMessage="Specifies blank lines to print before.")]
[alias("b")]
[int]$LinesBefore=0,
[parameter(HelpMessage="Specifies blank lines to print after.")]
[alias("a")]
[int]$LinesAfter=0,
[parameter(HelpMessage="Specifies if program should exit.")]
[alias("x")]
[switch]$ExitAfter
)
PROCESS {
if($LinesBefore -ne 0) {
foreach($i in 0..$LinesBefore) { Write-Host "" }
}
if($InfoFlag) { Write-Host "$Message" }
if($SuccessFlag) { Write-Host "$Message" -ForegroundColor "Green" }
if($WarningFlag) { Write-Host "$Message" -ForegroundColor "Orange" }
if($ErrorFlag) { Write-Host "$Message" -ForegroundColor "Red" }
if($FatalFlag) { Write-Host "$Message" -ForegroundColor "Red" -BackgroundColor "Black" }
if($LinesAfter -ne 0) {
foreach($i in 0..$LinesAfter) { Write-Host "" }
}
if($ExitAfter) { SafeExit }
}
}
# VALIDATES STRING MIGHT BE A PATH #
function ValidatePath($PathName, $TestPath) {
If([string]::IsNullOrWhiteSpace($TestPath)) {
Print -x -f "$PathName is not a path"
}
}
# NORMALIZES RELATIVE OR ABSOLUTE PATH TO ABSOLUTE PATH #
function NormalizePath($PathName, $TestPath) {
ValidatePath "$PathName" "$TestPath"
$TestPath = [System.IO.Path]::Combine((pwd).Path, $TestPath)
$NormalizedPath = [System.IO.Path]::GetFullPath($TestPath)
return $NormalizedPath
}
# VALIDATES STRING MIGHT BE A PATH AND RETURNS ABSOLUTE PATH #
function ResolvePath($PathName, $TestPath) {
ValidatePath "$PathName" "$TestPath"
$ResolvedPath = NormalizePath $PathName $TestPath
return $ResolvedPath
}
# VALIDATES STRING RESOLVES TO A PATH AND RETURNS ABSOLUTE PATH #
function RequirePath($PathName, $TestPath, $PathType) {
ValidatePath $PathName $TestPath
If(!(Test-Path $TestPath -PathType $PathType)) {
Print -x -f "$PathName ($TestPath) does not exist as a $PathType"
}
$ResolvedPath = Resolve-Path $TestPath
return $ResolvedPath
}
# Like mkdir -p -> creates a directory recursively if it doesn't exist #
function MakeDirP {
[CmdletBinding()]
param (
[parameter(Mandatory=$TRUE,Position=0,HelpMessage="Path create.")]
[string]$Path
)
PROCESS {
New-Item -path $Path -itemtype Directory -force | Out-Null
}
}
# GETS ALL FILES IN A PATH RECURSIVELY #
function GetFiles {
[CmdletBinding()]
param (
[parameter(Mandatory=$TRUE,Position=0,HelpMessage="Path to get files for.")]
[string]$Path
)
PROCESS {
ls $Path -r | where { !$_.PSIsContainer }
}
}
# GETS ALL FILES WITH CALCULATED HASH PROPERTY RELATIVE TO A ROOT DIRECTORY RECURSIVELY #
# RETURNS LIST OF @{RelativePath, Hash, FullName}
function GetFilesWithHash {
[CmdletBinding()]
param (
[parameter(Mandatory=$TRUE,Position=0,HelpMessage="Path to get directories for.")]
[string]$Path,
[parameter(HelpMessage="The hash algorithm to use.")]
[string]$Algorithm="MD5"
)
PROCESS {
$OriginalPath = $PWD
SetWorkDir path/to/diff $Path
GetFiles $Path | select @{N="RelativePath";E={$_.FullName | Resolve-Path -Relative}},
@{N="Hash";E={(Get-FileHash $_.FullName -Algorithm $Algorithm | select Hash).Hash}},
FullName
SetWorkDir path/to/original $OriginalPath
}
}
# COMPARE TWO DIRECTORIES RECURSIVELY #
# RETURNS LIST OF @{RelativePath, Hash, FullName}
function DiffDirectories {
[CmdletBinding()]
param (
[parameter(Mandatory=$TRUE,Position=0,HelpMessage="Directory to compare left.")]
[alias("l")]
[string]$LeftPath,
[parameter(Mandatory=$TRUE,Position=1,HelpMessage="Directory to compare right.")]
[alias("r")]
[string]$RightPath
)
PROCESS {
$LeftHash = GetFilesWithHash $LeftPath
$RightHash = GetFilesWithHash $RightPath
diff -ReferenceObject $LeftHash -DifferenceObject $RightHash -Property RelativePath,Hash
}
}
### END FUNCTION DEFINITIONS ###
### PROGRAM LOGIC ###
if($Compare.length -ne 2) {
Print -x "Compare requires passing exactly 2 path parameters separated by comma, you passed $($Compare.length)." -f
}
Print "Comparing $($Compare[0]) to $($Compare[1])..." -a 1
$LeftPath = RequirePath path/to/left $Compare[0] container
$RightPath = RequirePath path/to/right $Compare[1] container
$Diff = DiffDirectories $LeftPath $RightPath
$LeftDiff = $Diff | where {$_.SideIndicator -eq "<="} | select RelativePath,Hash
$RightDiff = $Diff | where {$_.SideIndicator -eq "=>"} | select RelativePath,Hash
if($ExportSummary) {
$ExportSummary = ResolvePath path/to/summary/dir $ExportSummary
MakeDirP $ExportSummary
$SummaryPath = Join-Path $ExportSummary summary.txt
$LeftCsvPath = Join-Path $ExportSummary left.csv
$RightCsvPath = Join-Path $ExportSummary right.csv
$LeftMeasure = $LeftDiff | measure
$RightMeasure = $RightDiff | measure
"== DIFF SUMMARY ==" > $SummaryPath
"" >> $SummaryPath
"-- DIRECTORIES --" >> $SummaryPath
"`tLEFT -> $LeftPath" >> $SummaryPath
"`tRIGHT -> $RightPath" >> $SummaryPath
"" >> $SummaryPath
"-- DIFF COUNT --" >> $SummaryPath
"`tLEFT -> $($LeftMeasure.Count)" >> $SummaryPath
"`tRIGHT -> $($RightMeasure.Count)" >> $SummaryPath
"" >> $SummaryPath
$Diff | Format-Table >> $SummaryPath
$LeftDiff | Export-Csv $LeftCsvPath -f
$RightDiff | Export-Csv $RightCsvPath -f
}
$Diff
SafeExit
@dotdoom
Copy link

dotdoom commented Apr 14, 2019

A PowerShell noob here. I have this script that does something similar. Of course it's not as powerful as the one in the gist. Used it on AppVeyor CI to detect where cache changes are coming from.

$LHS = Get-ChildItem –Path C:\path1 -Recurse | foreach {Get-FileHash –Path $_.FullName}
$RHS = Get-ChildItem –Path C:\path2 -Recurse | foreach {Get-FileHash –Path $_.FullName}
Compare-Object -ReferenceObject $LHS -DifferenceObject $RHS -Property hash -PassThru | Format-List

Output for one changed file (I think it may be fine tuned to print a nice table instead):

Algorithm     : SHA256
Hash          : A82DA24A8B9AE319CC8580A75EC655E5480CB45D4F316ADDCC870AB1372AB71D
Path          : C:\path1\bin\flutter
SideIndicator : =>

Algorithm     : SHA256
Hash          : 46D675B69D58B7B50C1C3214BAFDD69AD952701D7A2881971B7C7C7B45B58A72
Path          : C:\path2\bin\flutter
SideIndicator : <=

@jceddy
Copy link

jceddy commented Apr 19, 2019

When I pass in UNC paths to this, I get "The given path's format is not supported." error in GetFullPath(), but if I pass either of the paths to GetFullPath() directly, it works fine...any idea what the issue could be?

Here is an example:

PS C:\Users\UserG> c:\temp\rdiff.ps1 \\machine.net.path.local\D\Staging\test\dev\ApplicationEF\TS,\\machine.net.path.local\D\webVisionCore\root\test\dev\ApplicationEF
Comparing \\machine.net.path.local\D\Staging\test\dev\ApplicationEF\TS to \\machine.net.path.local\D\webVisionCore\root\test\dev\ApplicationEF...

Exception calling "GetFullPath" with "1" argument(s): "The given path's format is not supported."
At C:\temp\rdiff.ps1:99 char:3
+   $NormalizedPath = [System.IO.Path]::GetFullPath($TestPath)
+   ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    + CategoryInfo          : NotSpecified: (:) [], MethodInvocationException
    + FullyQualifiedErrorId : NotSupportedException

Set-Location : Cannot process argument because the value of argument "path" is null. Change the value of argument
"path" to a non-null value.
At C:\temp\rdiff.ps1:24 char:3
+   Set-Location $AbsPath
+   ~~~~~~~~~~~~~~~~~~~~~
    + CategoryInfo          : InvalidArgument: (:) [Set-Location], PSArgumentNullException
    + FullyQualifiedErrorId : ArgumentNull,Microsoft.PowerShell.Commands.SetLocationCommand

Exception calling "SetCurrentDirectory" with "1" argument(s): "Path cannot be the empty string or all whitespace."
At C:\temp\rdiff.ps1:25 char:3
+   [System.IO.Directory]::SetCurrentDirectory($AbsPath)
+   ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    + CategoryInfo          : NotSpecified: (:) [], MethodInvocationException
    + FullyQualifiedErrorId : ArgumentException

PS C:\Users\UserG> [System.IO.Path]::GetFullPath("\\machine.net.path.local\D\Staging\test\dev\ApplicationEF\TS")
\\machine.net.path.local\D\Staging\test\dev\ApplicationEF\TS
PS C:\Users\UserG> [System.IO.Path]::GetFullPath("\\machine.net.path.local\D\webVisionCore\root\test\dev\ApplicationEF")
\\machine.net.path.local\D\webVisionCore\root\test\dev\ApplicationEF
PS C:\Users\UserG>

Edit: Ah, the issue seems to be that Resolve-Path sticks "Microsoft.PowerShell.Core\FileSystem::" on the front of UNC paths.

@viktor
Copy link

viktor commented Jan 9, 2020

Pretty good script. (y)

@jeejee123
Copy link

This is really nice Powershell script. Good work!

@trobinson794
Copy link

Very helpful, thanks for posting this!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment