Content Migration Guide¶

# Assess document libraries across a site collection
Add-PSSnapin Microsoft.SharePoint.PowerShell

$site = Get-SPSite "https://sp2016.contoso.com/sites/finance"

$site.AllWebs | ForEach-Object {
    $web = $_
    $_.Lists | Where-Object { $_.BaseType -eq "DocumentLibrary" -and -not $_.Hidden } | ForEach-Object {
        [PSCustomObject]@{
            WebUrl           = $web.Url
            LibraryTitle     = $_.Title
            ItemCount        = $_.ItemCount
            SizeMB           = [math]::Round(($_.Items | ForEach-Object { $_.File.Length } |
                                Measure-Object -Sum).Sum / 1MB, 2)
            ContentTypes     = ($_.ContentTypes | Select-Object -ExpandProperty Name) -join "; "
            VersioningEnabled = $_.EnableVersioning
            MajorVersions    = $_.MajorVersionLimit
            MinorVersions    = $_.MajorWithMinorVersionsLimit
            CheckoutRequired = $_.ForceCheckout
            HasFolders       = ($_.Folders.Count -gt 1)
            LastModified     = $_.LastItemModifiedDate
        }
    }
} | Export-Csv -Path "C:\Migration\library-inventory.csv" -NoTypeInformation

# Find files larger than 15 GB across the farm
Get-SPSite -Limit All | ForEach-Object {
    $_.AllWebs | ForEach-Object {
        $web = $_
        $_.Lists | Where-Object { $_.BaseType -eq "DocumentLibrary" } | ForEach-Object {
            $_.Items | Where-Object { $_.File.Length -gt 15GB } | ForEach-Object {
                [PSCustomObject]@{
                    WebUrl    = $web.Url
                    Library   = $_.ParentList.Title
                    FileName  = $_.File.Name
                    SizeGB    = [math]::Round($_.File.Length / 1GB, 2)
                }
            }
        }
    }
} | Export-Csv -Path "C:\Migration\large-files.csv" -NoTypeInformation

# Migrate list items with metadata using PnP PowerShell
# Source connection
Connect-PnPOnline -Url "https://sp2016.contoso.com/sites/finance" -Credentials $onPremCreds

$sourceItems = Get-PnPListItem -List "Project Tracker" -PageSize 500

# Target connection
Connect-PnPOnline -Url "https://contoso.sharepoint.com/sites/finance" -Interactive

foreach ($item in $sourceItems) {
    $values = @{
        "Title"           = $item["Title"]
        "ProjectStatus"   = $item["ProjectStatus"]
        "ProjectManager"  = $item["ProjectManager"].Email  # User field
        "Budget"          = $item["Budget"]
        "StartDate"       = $item["StartDate"]
        "DueDate"         = $item["DueDate"]
        "Department"      = $item["Department"].Label       # Managed metadata
    }

    Add-PnPListItem -List "Project Tracker" -Values $values
}

# Export term store to CSV for migration
Add-PSSnapin Microsoft.SharePoint.PowerShell

$site = Get-SPSite "https://sp2016.contoso.com"
$session = Get-SPTaxonomySession -Site $site
$termStore = $session.TermStores[0]

$termData = @()

foreach ($group in $termStore.Groups) {
    foreach ($termSet in $group.TermSets) {
        foreach ($term in $termSet.GetAllTerms()) {
            $termData += [PSCustomObject]@{
                GroupName     = $group.Name
                GroupId       = $group.Id
                TermSetName   = $termSet.Name
                TermSetId     = $termSet.Id
                TermName      = $term.Name
                TermId        = $term.Id
                ParentTermId  = if ($term.Parent) { $term.Parent.Id } else { "" }
                IsAvailable   = $term.IsAvailableForTagging
                CustomProps   = ($term.CustomProperties.GetEnumerator() |
                                ForEach-Object { "$($_.Key)=$($_.Value)" }) -join "; "
            }
        }
    }
}

$termData | Export-Csv -Path "C:\Migration\term-store-export.csv" -NoTypeInformation

# Import terms to SPO using PnP PowerShell
Connect-PnPOnline -Url "https://contoso-admin.sharepoint.com" -Interactive

# Import from CSV (PnP format)
# CSV columns: TermSetName, TermSetDescription, LCID, AvailableForTagging, TermDescription, Level1, Level2, Level3...
Import-PnPTermGroupFromXml -Path "C:\Migration\term-store.xml"

# Or create terms programmatically
$termGroup = New-PnPTermGroup -GroupName "Corporate Taxonomy"

$termSet = New-PnPTermSet -TermGroup "Corporate Taxonomy" `
    -TermSet "Departments" `
    -Lcid 1033

New-PnPTerm -TermGroup "Corporate Taxonomy" `
    -TermSet "Departments" `
    -Term "Finance" `
    -Lcid 1033

New-PnPTerm -TermGroup "Corporate Taxonomy" `
    -TermSet "Departments" `
    -Term "Human Resources" `
    -Lcid 1033

# Export content types from on-premises content type hub
$hubSite = Get-SPSite "https://sp2016.contoso.com/sites/contenttypehub"
$rootWeb = $hubSite.RootWeb

$contentTypes = $rootWeb.ContentTypes | Where-Object { -not $_.Hidden } | ForEach-Object {
    [PSCustomObject]@{
        Name          = $_.Name
        Id            = $_.Id
        Group         = $_.Group
        Description   = $_.Description
        Parent        = $_.Parent.Name
        FieldCount    = $_.Fields.Count
        Fields        = ($_.Fields | Where-Object { -not $_.Hidden } |
                        Select-Object -ExpandProperty InternalName) -join "; "
    }
}

$contentTypes | Export-Csv -Path "C:\Migration\content-types.csv" -NoTypeInformation

Connect-PnPOnline -Url "https://contoso.sharepoint.com/sites/finance" -Interactive

# Create a content type
Add-PnPContentType -Name "Project Document" `
    -Description "Document associated with a project" `
    -Group "Custom Content Types" `
    -ParentContentType "Document"

# Add site columns to the content type
Add-PnPFieldToContentType -Field "ProjectName" -ContentType "Project Document"
Add-PnPFieldToContentType -Field "ProjectStatus" -ContentType "Project Document"
Add-PnPFieldToContentType -Field "Department" -ContentType "Project Document"

# Publish content type to the content type gallery (tenant-level)
# Use the SharePoint admin center or PnP provisioning templates

# Generate user mapping CSV from AD and Entra ID
$adUsers = Get-ADUser -Filter * -Properties EmailAddress, SamAccountName |
    Where-Object { $_.Enabled -eq $true }

$mapping = $adUsers | ForEach-Object {
    [PSCustomObject]@{
        Source = "CONTOSO\$($_.SamAccountName)"
        Target = $_.EmailAddress
    }
} | Where-Object { $_.Target -ne $null }

$mapping | Export-Csv -Path "C:\Migration\user-mapping.csv" -NoTypeInformation

# Compare source and target content counts
Connect-PnPOnline -Url "https://contoso.sharepoint.com/sites/finance" -Interactive

$targetLists = Get-PnPList | Where-Object { -not $_.Hidden }

$validation = $targetLists | ForEach-Object {
    [PSCustomObject]@{
        ListTitle     = $_.Title
        TargetCount   = $_.ItemCount
        ListType      = $_.BaseType
        LastModified  = $_.LastItemModifiedDate
    }
}

$validation | Format-Table -AutoSize

# Compare against source inventory CSV
$sourceInventory = Import-Csv "C:\Migration\library-inventory.csv"

foreach ($target in $validation) {
    $source = $sourceInventory | Where-Object { $_.LibraryTitle -eq $target.ListTitle }
    if ($source) {
        $diff = $target.TargetCount - [int]$source.ItemCount
        if ($diff -ne 0) {
            Write-Warning "Mismatch: $($target.ListTitle) - Source: $($source.ItemCount), Target: $($target.TargetCount), Diff: $diff"
        }
    }
}

# Find checked-out files across a site collection
$site = Get-SPSite "https://sp2016.contoso.com/sites/finance"
$site.AllWebs | ForEach-Object {
    $_.Lists | Where-Object { $_.BaseType -eq "DocumentLibrary" } | ForEach-Object {
        $_.CheckedOutFiles | ForEach-Object {
            [PSCustomObject]@{
                Url           = $_.Url
                CheckedOutBy  = $_.CheckedOutByName
                CheckedOutDate = $_.TimeLastModified
            }
        }
    }
} | Export-Csv -Path "C:\Migration\checked-out-files.csv" -NoTypeInformation