Last active
August 29, 2015 14:25
-
-
Save punitganshani/b08d8d14eeb5516934ae to your computer and use it in GitHub Desktop.
Get Encoding of Files [PowerShell]
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
function Get-FileEncodingOfFilesInFolder | |
{ | |
[CmdletBinding()] Param ( | |
[Parameter(Mandatory = $True, ValueFromPipelineByPropertyName = $True)] [string]$Path, [string]$pattern | |
) | |
$files = Get-ChildItem -path $Path $pattern -Recurse | Select-Object FullName | |
$encodings = @{} | |
$encodingMembers = [System.Text.Encoding] | Get-Member -Static -MemberType Property | |
$encodingMembers | Foreach-Object { | |
$encodingBytes = [System.Text.Encoding]::($_.Name).GetPreamble() -join '-' | |
$encodings[$encodingBytes] = $_.Name | |
} | |
$encodingLengths = $encodings.Keys | Where-Object { $_ } | Foreach-Object { ($_ -split "-").Count } | |
$counter = 0 | |
$files | ForEach-Object { | |
$counter= $counter+1 | |
$result = "UTF7" | |
$file = $_ | |
$completed = $counter / $files.Count | |
Write-Progress -Activity "Encoding detection" -status "$($counter) / $($files.count) Complete" | |
$found=$false | |
foreach($encodingLength in $encodingLengths | Sort -Descending) | |
{ | |
$content = Get-Content $file.FullName -encoding byte -readcount $encodingLength | |
$bytes = $content[0] | |
$encoding = $encodings[$bytes -join '-'] | |
if($encoding) | |
{ | |
$result = $encoding | |
Write-Output "$($file.FullName): $([System.Text.Encoding]::$result)" | |
$found=$true | |
break | |
} | |
} | |
if ($found -eq $false){ | |
Write-Output "$($file.FullName): UNRECOGNIZED" | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment