From 6d924bd10208d285b577b093fb2e83550069a330 Mon Sep 17 00:00:00 2001
From: Denis Pushkarev <denis.pushkarev@webpros.com>
Date: Wed, 27 Mar 2024 14:19:11 +0200
Subject: [PATCH 1/2] Preserve libxml errors after failed parsing

---
 src/Sanitizer.php       | 18 ++++++++++++++++++
 tests/SanitizerTest.php | 15 ++++++++++++++-
 2 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/src/Sanitizer.php b/src/Sanitizer.php
index 60072fa..731b8c7 100644
--- a/src/Sanitizer.php
+++ b/src/Sanitizer.php
@@ -230,6 +230,7 @@ public function sanitize($dirty)
 
         // If we couldn't parse the XML then we go no further. Reset and return false
         if (!$loaded) {
+            $this->xmlIssues = self::getXmlErrors();
             $this->resetAfter();
             return false;
         }
@@ -698,4 +699,21 @@ protected function cleanUnsafeNodes(\DOMNode $currentElement) {
             }
         }
     }
+
+    /**
+     * Retrieve array of errors
+     * @return array
+     */
+    private static function getXmlErrors()
+    {
+        $errors = [];
+        foreach (libxml_get_errors() as $error) {
+            $errors[] = [
+                'message' => trim($error->message),
+                'line' => $error->line,
+            ];
+        }
+
+        return $errors;
+    }
 }
diff --git a/tests/SanitizerTest.php b/tests/SanitizerTest.php
index e031a5e..b9fa379 100644
--- a/tests/SanitizerTest.php
+++ b/tests/SanitizerTest.php
@@ -100,7 +100,20 @@ public function testBadXMLReturnsFalse()
         $sanitizer = new Sanitizer();
         $cleanData = $sanitizer->sanitize($initialData);
 
-        self::assertSame(false, $cleanData);
+        self::assertFalse($cleanData);
+        self::assertEquals(
+            [
+                [
+                    'message' => 'Opening and ending tag mismatch: line line 8 and svg',
+                    'line' => 15,
+                ],
+                [
+                    'message' => 'Premature end of data in tag svg line 4',
+                    'line' => 16,
+                ],
+            ],
+            $sanitizer->getXmlIssues(),
+        );
     }
 
     /**

From 9648e156195c67074734c2ed176a5b930465a917 Mon Sep 17 00:00:00 2001
From: Daryll Doyle <daryll.doyle@10up.com>
Date: Tue, 18 Jun 2024 11:25:54 +0100
Subject: [PATCH 2/2] Remove trailing comma

---
 tests/SanitizerTest.php | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/SanitizerTest.php b/tests/SanitizerTest.php
index b9fa379..97514f0 100644
--- a/tests/SanitizerTest.php
+++ b/tests/SanitizerTest.php
@@ -112,7 +112,7 @@ public function testBadXMLReturnsFalse()
                     'line' => 16,
                 ],
             ],
-            $sanitizer->getXmlIssues(),
+            $sanitizer->getXmlIssues()
         );
     }