Is comparing git lfs ls-files with git ls-files ':(attr:filter=lfs)' a reliable way to detect lfs files that are not managed by lfs?

▼魔方 西西 提交于 2019-12-04 05:48:58

I have not managed to find whether it is a truly reliable way, but so far my testing seems to confirm that.

We've ended up using the following script as a part of our build pipeline:

#See https://stackoverflow.com/questions/54804333/is-comparing-git-lfs-ls-files-with-git-ls-files-attrfilter-lfs-a-reliable
[CmdletBinding()]
[OutputType([int])]
Param (
    [Parameter(Mandatory = $true)]
    [string]
    $RepositoryLocalPath
)

$ErrorActionPreference = "Stop";

function Assert-LastExitCodeIs0
{
    if ($LASTEXITCODE -ne 0)
    {
        throw (New-Object System.InvalidOpertationException("LASTEXITCODE is $LASTEXITCODE"));
    }
}

function Get-StringFromOctal
{
    [CmdLetBinding()]
    [OutputType([string])]
    Param (
        [Parameter(Mandatory = $true)]     
        [string]
        $String
    )
    if ([String]::IsNullOrEmpty($String))
    {
        return $String;
    }
    if (($String[0] -ne '"') -or 
        ($String[$String.Length - 1] -ne '"'))
    {
        return $String;
    }
    if ($String.Length -lt 2)
    {
        return $String;
    }
    $String = $String.Substring(1, $String.Length -2);
    [regex] $regex = '(\\[0-9]+)+';
    $encoding = [System.Text.Encoding]::UTF8;
    return $regex.Replace(
        $String,
        {
            Param ($Capture)
            $bytes = $Capture.Groups[1].Captures | 
                ForEach-Object { [System.Convert]::ToByte($_.Value.Substring(1), 8) };
            return $encoding.GetString(@($bytes));
        });
}

function Normalize-GitLsFilesPath
{
    [CmdLetBinding()]
    [OutputType([string])]
    Param (
        [Parameter(Mandatory = $true)]     
        [string]
        $Path
    )
    # Normalize octets paths
    # Technically we could try ls-files -z, but there is no such option for lfs ls-files.
    # Or we could try to set core.quotePath to 0, but it brings a slew of problems with encodings and etc.
    # And by doing so we would change git config settings, that is not very desirable, even if we will always(?) succeed in reverting it.
    # So it is seems simpler just to parse octal paths.
    return Get-StringFromOctal -String ($Path.Trim());
}

function Is-FileEmpty
{
    [CmdLetBinding()]
    [OutputType([bool])]
    Param (
        [Parameter(Mandatory = $true)]     
        [string]
        $Path
    )
    return ((Get-Item -LiteralPath $Path).Length -eq 0);
}

function Is-NotEmptyLfsFile
{
    [CmdLetBinding()]
    [OutputType([bool])]
    Param (
        [Parameter(Mandatory = $true)]     
        [string]
        $Path
    )    
    # Empty files will be empty files whether they are under lfs or not - https://github.com/git-lfs/git-lfs/issues/2863
    # But they seem not to get the lfs attributes, so we have no other choice but to filter them.
    return !(Is-FileEmpty -Path $Path);
}

function Get-ActualLfsFilePaths
{
    [CmdletBinding()]
    [OutputType([string[]])]
    Param()
    Write-Host 'Getting actual lfs file paths.';
    $lfsLsFilesOutput = git lfs ls-files;
    Assert-LastExitCodeIs0;
    $actualLfsFilePaths = ($lfsLsFilesOutput | `
        ForEach-Object `
        {
            #'12345678 * my.dll' - not all lfs versions support -n flag, so it is better to be conservative
            $lsFilePath = $_.Split(' ', 3)[2];
            return Normalize-GitLsFilesPath -Path $lsFilePath;
        });
    Write-Host "There are $($actualLfsFilePaths.Count) files that are actually under lfs";
    return , $actualLfsFilePaths;
}

function Get-ShouldBeLfsFilePaths
{
    [CmdletBinding()]
    [OutputType([string[]])]
    Param()
    Write-Host 'Getting should be under lfs file paths.';
    [string[]] $shouldBeUnderLfsFilePaths = git ls-files -s ':(attr:filter=lfs)';
    Assert-LastExitCodeIs0;
    $shouldBeUnderLfsFilePaths = ($shouldBeUnderLfsFilePaths | `
        ForEach-Object `
        {
            #120000 1234567890abcdef 0       mylib.dylib
            , $_.Split($null, 4);
        } | `
        Where `
        {
            $symlinkBitMaskString = '120000';
            $fileChmodString = $_[0];
            return ($fileChmodString -ne $symlinkBitMaskString); # Perhaps we should check actual bitmask?
        } | `
        ForEach-Object `
        {
            Normalize-GitLsFilesPath -Path $_[3];
        });
    Write-Host "There are $($shouldBeUnderLfsFilePaths.Count) files that should be under lfs (may include flukes - empty files)";
    return , $shouldBeUnderLfsFilePaths;
}

function Get-LfsFilePathsNotUnderLfs
{
    [CmdletBinding()]
    [OutputType([string[]])]
    Param()
    [string[]] $actualLfsFilePaths = Get-ActualLfsFilePaths;
    [string[]] $shouldBeUnderLfsFilePaths = Get-ShouldBeLfsFilePaths;
    Add-Type -AssemblyName 'System.Linq';
    Write-Host 'Comparing actual lfs and should be under lfs files.'
    return , [System.Linq.Enumerable]::ToArray(
        [System.Linq.Enumerable]::Where(
            [System.Linq.Enumerable]::Except($shouldBeUnderLfsFilePaths, $actualLfsFilePaths),
            [Func[String, Boolean]] ${function:Is-NotEmptyLfsFile}
            )
        );
}

function Main-WithRepositoryAsWorkingFolder
{    
    $filePathsNotUnderLfs = Get-LfsFilePathsNotUnderLfs;
    $count = $filePathsNotUnderLfs.Count;
    Write-Host "There are $($count) lfs files that are not under lfs";
    foreach ($filePathNotUnderLfs in $filePathsNotUnderLfs)
    {
        Write-Host "`t'$filePathNotUnderLfs'";
    }
    if ($count -eq 0)
    {
        return 0;
    }
    return 1;
}


function Main
{
    [CmdletBinding()]
    [OutputType([int])]
    Param (
        [Parameter(Mandatory = $true)]
        [string]
        $RepositoryLocalPath
    )
    Write-Host "RepositoryLocalPath = $RepositoryLocalPath";
    # It is simpler to set working dir rather than use Process.Start with WorkingDirectory everywhere, and more reliable than Start-Process (that one may in some cases have issues with return exit code).
    $originalGetLocation = (Get-Location).Path;
    Set-Location -LiteralPath $RepositoryLocalPath;
    $originalCurrentDirectory = [System.IO.Directory]::GetCurrentDirectory();
    [System.IO.Directory]::SetCurrentDirectory($RepositoryLocalPath);
    # Otherwise we won't get proper file paths from git lfs ls-files, as it doesn't use octal encoding
    # And using output redirection may lead us to even bigger problems|difficulties.
    $originalOutputEncoding = $OutputEncoding;
    $OutputEncoding = [System.Text.Encoding]::UTF8;
    $originalConsoleOutputEncoding = [Console]::OutputEncoding;
    [Console]::OutputEncoding = [System.Text.Encoding]::UTF8;
    $originalConsoleInputEncoding = [Console]::InputEncoding;
    [Console]::InputEncoding = [System.Text.Encoding]::UTF8;

    try 
    {
        return Main-WithRepositoryAsWorkingFolder;
    }
    catch 
    {
        Write-Host "$_ $($_.ScriptStackTrace)";
        return 2;
    }
    finally
    {
        Set-Location -LiteralPath $originalGetLocation;
        [System.IO.Directory]::SetCurrentDirectory($originalCurrentDirectory);
        $OutputEncoding = $originalOutputEncoding;
        [Console]::OutputEncoding = $originalConsoleOutputEncoding;
        [Console]::InputEncoding = $originalConsoleInputEncoding;
    }
}

exit (Main -RepositoryLocalPath $RepositoryLocalPath);
易学教程内所有资源均来自网络或用户发布的内容,如有违反法律规定的内容欢迎反馈
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!