Bulk Editing docx Archives Without Losing Metadata Using Powershell

Bulk Edit Docx.md

Unpack & Repack docx files for safe & easy bulk editing!

Requires 7z CLI in OS Path!

Unpacks or Repacks docx files so you can work with their XML contents.

Internal metadata/props/refs stored in the files are usually overwritten/lost, when attempting to edit such docx documents with Microsoft Word

Unpacking and repacking the docx files (just a glorified zip archive) allows one to make bulk edits to the docx files by for example search and replacing string content or images stored within the document. Updating the docx files like this also has the benefit of maintaining any internal metadata, unlike Microsoft Word.

Usage

Unpacking

Unpack-Docx #Unpack docx files of current folder only to folders in the same location

# OR

Unpack-Docx -r #Recursively unpack docx files

Repacking

Repack-Docx #Repack folders back to docx files

# OR

Repack-Docx -r #Recursively repack all folders back to docx files

---

Source

#====== Unpack Docx Archives ==============================================================================================================================================
function Unpack-Docx-Archives {
  7z x *.docx -o*
}

function Unpack-Docx-Archives-Recursive{
  $initpath = Get-Location
  foreach ($folder in Get-ChildItem) {
    if ($folder.Attributes -eq "Directory") {
      Set-Location $folder.FullName
      7z x *.docx -o*
    }
  }
  Set-Location $initpath
  7z x *.docx -o*
}

function Unpack-Docx {
  param (
    [Parameter(Mandatory=$false, ValueFromPipeline = $true)]
    [switch]$r
  )

  if ($r) {
    Unpack-Docx-Archives-Recursive
  } else {
    Unpack-Docx-Archives
  }
}
#===========================================================================================================================================================================

#====== Repack Docx Archives ===============================================================================================================================================
function Repack-Docx-Archives {
  $initpath = Get-Location

  foreach ($folder in Get-ChildItem -Directory) {
    $archivePath = Join-Path -Path $initpath -ChildPath ($folder.Name + '.docx')
    Set-Location $folder.FullName
    if (Test-Path $archivePath) {
      Remove-Item -Path $archivePath
      7z a -tzip $archivePath *
    }


    if (Test-Path $archivePath) {
        Set-Location $initpath
        [IO.Directory]::Delete($folder.FullName, $true)
    }
  }

  Set-Location $initpath
}

function Repack-Docx-Archives-Recursive {
  RepackAllDocxArchives

  $initpath = Get-Location

  foreach ($folder in Get-ChildItem) {
    if ($folder.Attributes -eq "Directory") {
      Set-Location $folder.FullName
      foreach ($subFolder in Get-ChildItem) {
        if ($subFolder.Attributes -eq "Directory") {
          Set-Location $subFolder.FullName
          $archivePath = $subFolder.Name + '.docx'
          if (Test-Path $archivePath) {
            Remove-Item -Path $archivePath
          }
          7z a -tzip $archivePath *
          Get-ChildItem *.docx -Recurse | Move-Item -force -Destination $folder.FullName
          $folderToDelte = $folder.FullName + '\' + $subFolder.Name
          Set-Location $folder.FullName
          [IO.Directory]::Delete($folderToDelte, $true)
        }
      }
    }
  }
  Set-Location $initpath
}

function Repack-Docx {
  param (
    [Parameter(Mandatory=$false, ValueFromPipeline = $true)]
    [switch]$r
  )

  if ($r) {
    Repack-Docx-Archives-Recursive
  } else {
    Repack-Docx-Archives
  }
}
#===========================================================================================================================================================================