SP wildcard search in a file share content source.ps1

<#
.SYNOPSIS
    ! UPDATE THE VARIABLES IN THE BEGINNING
    OF THE SCRIPT ACCORDING TO YOUR ENVIRONMENT
    x
    The script sets up the environment to reproduce the problem
    stated in https://social.msdn.microsoft.com/Forums/en-US/7c93cb0c-d500-477b-b9fa-83f604299a28/expansion-of-wildcard-will-possibly-exceed-10000-terms?forum=sharepointsearch

    The script creates:
        1) a file share on the local drive with a tree of folders
        2) a content source to crawl this file share
        3) a crawl rule to crawl the file share on behalf of a specific user
           (maybe the crawl rule is not critical for the purpose of this test,
           but it's required in our environment)
    
#>

Add-PSSnapin Microsoft.SharePoint.PowerShell;



# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
# PARAMETER VARIABLES TO UPDATE ACCORDING TO YOUR ENVIRONMENT
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #

# SP Search Application name
$searchAppName = 'D26_SearchServiceApplication';

# letter of the disk where the file share folder will be stored
$fileShareDisk = 'C:';

# name of the folder which will be maped as the file share root
$fileShareName = 'smb_apps';

# Amount of folders (and files, one in each folder) to create.
# Wildcard search returns results for $foldersCount=100, 
# but fails for $foldersCount=11000.
$foldersCount = 20*1000; 

# FQDN of the current machine the script is run on.
# E.g. the test IS NOT valid for 'localhost' (wildcard search DOES NOT work),
# but IS valid for 4-part FQDN like 'abc.def.xyz.com'
# (wildcard search DOES work) (actual FQDN on the machines in
# our corporate environment are 4-part)
$machineFQDN = 'AlphanumericMachineName.abc.xyz.com';

# SP Search content source name to create for the file share
$contentSourceName = 'FileShareWildcardSearchTest';

# switch defining if a crawl rule must be created to crawl the file share
# (may not be needed; but in our environment we use a crawl rule; if your
# SP Search crawls the file share with no errors you may set $createCrawlRule = $false)
$createCrawlRule = $true;

# crawl rule account name
# (may not be needed; but in our environment we use a crawl rule and
# therefore we need this 'reader' account to be used in the crawl rule configuration)
$crawlRuleAccountName = 'domain\username'; # TODO: enter the value 'domain\username'

# crawl rule account password
# (may not be needed; but in our environment we use a crawl rule and
# therefore we need a 'reader' account to be used in the crawl rule configuration)
$crawlRuleAccountPassword = ''; # TODO: enter the plain text password

# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
# END OF VARIABLE LIST
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #




# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
# variables whose values are calculated based on the vars in the beginning of the script (above)
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #

# disk path to the folder which will be maped as the file share root
$fileShareRootDiskPath = "$fileShareDisk\$fileShareName";

# relative path to the base folder where all the test subfolders and files will be created
$fileShareContentsFolderPath = "$fileShareName\no_bkp\TEST_archived_SP-Data";

# absolute path to the base folder where all the test subfolders and files will be created
$fileShareContentsFolderDiskPath = "$fileShareDisk\$fileShareContentsFolderPath";

# network path to the file share (used in the crawl rule, in the content source definition)
$fileShareNetworkPath = "file://$machineFQDN/$($fileShareContentsFolderPath.Replace('\', '/'))";

# network path to the file share used in the test KQL query
# (used just for output purposes, not to configure the environment)
$fileShareNetworkPathForQuery = $fileShareNetworkPath.TrimStart('file:').TrimEnd('/').Replace('/', '\');

# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
# END OF variables whose values are calculated based on the vars in the beginning of the script
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #




# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
# create the folder with the subfolder tree
if(!(Test-Path -Path $fileShareContentsFolderDiskPath))
{
    for($i = 1; $i -le $foldersCount; $i++)
    {
        $newGuid = [Guid]::NewGuid().ToString().Replace('-', '').Replace('{', '').Replace('}', '').toLower();

        $folder = New-Item -ItemType Directory -Force -Path "$fileShareContentsFolderDiskPath\$($newGuid)_000\xyz.server-shmerver.abc.com(443)\engagements\$i"
        fsutil file createnew "`"$($folder.FullName)\$i.docx`"" 1024  
    }
}

# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
# create a file share with the created tree
$share = Get-SmbShare -Name $fileShareName -ErrorAction SilentlyContinue

if($share -eq $null)
{
<#
    New-SMBShare –Name "WildcardSearchTestFileShare" –Path $fileShareFolderDiskPath `
                 -ContinuouslyAvailable $True `
                 –FullAccess Everyone  `
                 -ChangeAccess Everyone `
                 -ReadAccess Everyone
#>
    New-SMBShare –Name $fileShareName –Path $fileShareRootDiskPath
    #Get-SmbShare 'WildcardSearchTestFileShare' | Add-AccessControlEntry -Principal Everyone -LogicalShareRights FullControl

}


# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
# create a content source
$ssa = Get-SPEnterpriseSearchServiceApplication $searchAppName

$cs = Get-SPEnterpriseSearchCrawlContentSource $contentSourceName -SearchApplication $ssa -ErrorAction SilentlyContinue

if($cs -eq $null)
{
    $cs = New-SPEnterpriseSearchCrawlContentSource -SearchApplication $ssa -Type File -name $contentSourceName -StartAddresses $fileShareNetworkPath
}


# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
# create a crawl rule to read the file share on behalf of a particular user
if($createCrawlRule)
{
    $existingRules = Get-SPEnterpriseSearchCrawlRule -SearchApplication $ssa

    $ruleFound = $false;
    foreach($rule in $existingRules)
    {
        if($rule.Path -eq "$fileShareNetworkPath/*")
        {
            $ruleFound = $true;
            break;
        }
    }

    if(!$ruleFound)
    {
        $crawlRule = New-SPEnterpriseSearchCrawlRule -SearchApplication $ssa `
                                                    -Path "$fileShareNetworkPath/*" `
                                                    -Type InclusionRule `
                                                    -AuthenticationType BasicAccountRuleAccess `
                                                    -AccountName $crawlRuleAccountName `
                                                    -AccountPassword $(ConvertTo-SecureString $crawlRuleAccountPassword -AsPlainText -Force)
    }
}

# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
# start a full crawl on the newly created content source
if($cs.CrawlState -eq "Idle") {
    Write-Host "CrawlState was Idle, crawling Full" -ForegroundColor Green
    $cs.StartFullCrawl()
 
    Do {
        Write-Host "`r#" -ForegroundColor Yellow -NoNewline
        Start-Sleep 5
    } while ($cs.CrawlState -ne "Idle")
 
    Write-Host "`nFinsihed crawling" -ForegroundColor Green
 
} else{
    Write-Host "Didn't start crawl, CrawlState was "$cs.CrawlState -ForegroundColor Yellow
}

write-host '! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! !'
write-host 'Ensure that the full crawl finished for the newly created Content Source ' -NoNewline
write-host "$contentSourceName'" -ForegroundColor Yellow 
write-host
write-host 'and AFTER THE FULL CRAWL (and success values in the crawl log) try the KQL query:' -ForegroundColor Cyan
Write-Host "`n`t Path:`"$fileShareNetworkPathForQuery\*\xyz.server-shmerver.abc.com(443)\engagements`""
write-host