Fix qps-ploc generation for store translations (#17526)

* Modified `Generate-PseudoLocalizations.ps1` to find the .xml files.
  (As opposed to .resw for the other translations.)
* Added support for the new format by adding new XPath expressions,
  and stripping comments/attributes as needed.
* Fixed `PreserveWhitespace` during XML loading.
* Fixed compliance with PowerShell's strict mode.

## Validation Steps Performed
Ran it locally and compared the results. ✅

build/scripts/Generate-PseudoLocalizations.ps1

@@ -1,5 +1,5 @@
-Get-ChildItem -Recurse -Filter *.resw
+Get-ChildItem -Recurse -Directory -Filter qps-ploc*
-    | Where-Object { $_.Directory.Name.StartsWith("qps-ploc") }
+    | Get-ChildItem -Include *.resw,*.xml
     | ForEach-Object {
         $source = Join-Path $_.Directory "../en-US/$($_.Name)"
         $target = $_

tools/ConvertTo-PseudoLocalization.ps1

@@ -1,5 +1,5 @@
 param(
-    [Parameter(Mandatory=$True)]
+    [Parameter(Mandatory = $True)]
     [string]$Path
 )
 
@@ -55,20 +55,25 @@ $mapping['Y'[0]] = '¥ÝŶΎΥΫỲЎ'
 $mapping['z'[0]] = 'źżž'
 $mapping['Z'[0]] = 'ŹŻΖŽ'
 
-[xml]$content = Get-Content $Path
+$content = [System.Xml.XmlDocument]::new()
+$content.PreserveWhitespace = $true
+$content.Load($Path)
+
+function GetPseudoLocalization([string]$key, [string]$value, [string]$comment) {
+    $locked = $null
+    if ($comment -match '.*\{Locked=?([^}]*)\}.*') {
+        $locked = $Matches[1]
+    }
+
+    # Skip {Locked} and {Locked=qps-ploc} entries
+    if ($locked -and (($locked -eq '') -or $locked.Contains('qps-ploc'))) {
+        continue
+    }
 
-foreach ($entry in $content.root.data) {
-    $value = $entry.value
-    $comment = $entry.comment ?? ''
     $placeholders = @{}
 
-    if ($comment.StartsWith('{Locked')) {
+    if ($locked) {
-        # Skip {Locked} and {Locked=qps-ploc} entries
+        $lockedList = $locked -split ','
-        if ($comment -match '\{Locked(\}|=[^}]*qps-ploc).*') {
-            continue
-        }
-
-        $lockedList = ($comment -replace '\{Locked=(.*?)\}.*','$1') -split ','
         $placeholderChar = 0xE000
 
         # Replaced all locked words with placeholders from the Unicode Private Use Area
@@ -86,34 +91,67 @@ foreach ($entry in $content.root.data) {
         }
     }
 
-    # We can't rely on $entry.name.GetHashCode() to be consistent across different runs,
+    # We can't rely on $key.GetHashCode() to be consistent across different runs,
     # because in the future PowerShell may enable UseRandomizedStringHashAlgorithm.
-    $hash = [System.Text.Encoding]::UTF8.GetBytes($entry.name)
+    $hash = [System.Text.Encoding]::UTF8.GetBytes($key)
     $hash = [System.Security.Cryptography.SHA1]::Create().ComputeHash($hash)
     $hash = [System.BitConverter]::ToInt32($hash)
-
-    # Replace all characters with pseudo-localized characters
     $rng = [System.Random]::new($hash)
-    $newValue = ''
+
-    foreach ($char in $value.ToCharArray()) {
+    $lines = $value.Split("`n")
-        if ($m = $mapping[$char]) {
+    $lines = $lines | ForEach-Object {
-            $newValue += $m[$rng.Next(0, $mapping[$char].Length)]
+        # Replace all characters with pseudo-localized characters
-        } else {
+        $newValue = ''
-            $newValue += $char
+        foreach ($char in $_.ToCharArray()) {
+            if ($m = $mapping[$char]) {
+                $newValue += $m[$rng.Next(0, $mapping[$char].Length)]
+            }
+            else {
+                $newValue += $char
+            }
+        }
+
+        # Replace all placeholders with their original values
+        foreach ($kv in $placeholders.GetEnumerator()) {
+            $newValue = $newValue.Replace($kv.Key, $kv.Value)
+        }
+
+        # Add 40% padding to the end of the string
+        $paddingLength = [System.Math]::Round(0.4 * $_.Length)
+        $padding = ' !!!' * ($paddingLength / 4 + 1)
+        $newValue + $padding.Substring(0, $paddingLength)
+    }
+    return $lines -join "`n"
+}
+
+if ($path.EndsWith(".resw")) {
+    foreach ($entry in $content.SelectNodes('/root/data')) {
+        $comment = $entry.SelectSingleNode('comment')?.'#text' ?? ''
+        $entry.value = GetPseudoLocalization $entry.name $entry.value $comment
+    }
+}
+elseif ($path.EndsWith(".xml")) {
+    foreach ($parent in $content.DocumentElement.SelectNodes('//*[@_locID]')) {
+        $locID = $parent.GetAttribute('_locID')
+        $comment = $parent.SelectSingleNode('comment()[contains(., "_locComment_text")]')?.'#text' ?? ''
+
+        foreach ($entry in $parent.SelectNodes('text()')) {
+            $value = $entry.Value
+            if ($value.Trim().Length -ne 0) {
+                $entry.Value = GetPseudoLocalization $locID $value $comment
+            }
         }
     }
 
-    # Replace all placeholders with their original values
+    # Remove all _locComment_text comments
-    foreach ($kv in $placeholders.GetEnumerator()) {
+    foreach ($entry in $content.DocumentElement.SelectNodes('//comment()[contains(., "_locComment_text")]')) {
-        $newValue = $newValue.Replace($kv.Key, $kv.Value)
+        $null = $entry.ParentNode.RemoveChild($entry)
     }
 
-    # Add 40% padding to the end of the string
+    # Remove all _locID attributes
-    $paddingLength = [System.Math]::Round(0.4 * $newValue.Length)
+    foreach ($entry in $content.DocumentElement.SelectNodes('//*[@_locID]')) {
-    $padding = ' !!!' * ($paddingLength / 4 + 1)
+        $entry.RemoveAttribute('_locID')
-    $newValue += $padding.Substring(0, $paddingLength)
+    }
-
-    $entry.value = $newValue
 }
 
 return $content