In Xml reader throw exception in case of invalid XML (#222)

When the xml file is not a standard xml file, the `simplexml_load_string` will return false, this will cause an error on "$xml->getNamespaces(true);" . So instead of showing the error, we throw an exception.

CHANGELOG.md

@@ -14,6 +14,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
 ### Changed
 
 - Merge data-validations to reduce written worksheet size - @billblume [#131](https://github.com/PHPOffice/PhpSpreadSheet/issues/131)
+- Throws exception if a XML file is invalid - @GreatHumorist [#222](https://github.com/PHPOffice/PhpSpreadsheet/pull/222)
 
 ### Fixed
 

src/PhpSpreadsheet/Reader/Xml.php

@@ -117,6 +117,30 @@ public function canRead($pFilename)
         return $valid;
     }
 
+    /**
+     * Check if the file is a valid SimpleXML.
+     *
+     * @param string $pFilename
+     *
+     * @throws Exception
+     *
+     * @return false|\SimpleXMLElement
+     */
+    public function trySimpleXMLLoadString($pFilename)
+    {
+        try {
+            $xml = simplexml_load_string(
+                $this->securityScan(file_get_contents($pFilename)),
+                'SimpleXMLElement',
+                Settings::getLibXmlLoaderOptions()
+            );
+        } catch (\Exception $e) {
+            throw new Exception('Cannot load invalid XML file: ' . $pFilename, 0, $e);
+        }
+
+        return $xml;
+    }
+
     /**
      * Reads names of the worksheets from a file, without parsing the whole file to a Spreadsheet object.
      *
@@ -133,11 +157,8 @@ public function listWorksheetNames($pFilename)
 
         $worksheetNames = [];
 
-        $xml = simplexml_load_string(
-            $this->securityScan(file_get_contents($pFilename)),
-            'SimpleXMLElement',
-            Settings::getLibXmlLoaderOptions()
-        );
+        $xml = $this->trySimpleXMLLoadString($pFilename);
+
         $namespaces = $xml->getNamespaces(true);
 
         $xml_ss = $xml->children($namespaces['ss']);
@@ -162,11 +183,8 @@ public function listWorksheetInfo($pFilename)
 
         $worksheetInfo = [];
 
-        $xml = simplexml_load_string(
-            $this->securityScan(file_get_contents($pFilename)),
-            'SimpleXMLElement',
-            Settings::getLibXmlLoaderOptions()
-        );
+        $xml = $this->trySimpleXMLLoadString($pFilename);
+
         $namespaces = $xml->getNamespaces(true);
 
         $worksheetID = 1;
@@ -339,11 +357,8 @@ public function loadIntoExisting($pFilename, Spreadsheet $spreadsheet)
             throw new Exception($pFilename . ' is an Invalid Spreadsheet file.');
         }
 
-        $xml = simplexml_load_string(
-            $this->securityScan(file_get_contents($pFilename)),
-            'SimpleXMLElement',
-            Settings::getLibXmlLoaderOptions()
-        );
+        $xml = $this->trySimpleXMLLoadString($pFilename);
+
         $namespaces = $xml->getNamespaces(true);
 
         $docProps = $spreadsheet->getProperties();

tests/PhpSpreadsheetTests/Reader/XEEValidatorTest.php

@@ -3,6 +3,8 @@
 namespace PhpOffice\PhpSpreadsheetTests\Reader;
 
 use PhpOffice\PhpSpreadsheet\Reader\BaseReader;
+use PhpOffice\PhpSpreadsheet\Reader\Exception;
+use PhpOffice\PhpSpreadsheet\Reader\Xml;
 use PHPUnit_Framework_TestCase;
 
 class XEEValidatorTest extends PHPUnit_Framework_TestCase
@@ -24,7 +26,29 @@ public function testInvalidXML($filename)
     public function providerInvalidXML()
     {
         $tests = [];
-        foreach (glob(__DIR__ . '/../../data/Reader/XEE/XEETestInvalid*.xml') as $file) {
+        foreach (glob(__DIR__ . '/../../data/Reader/XEE/XEETestInvalidUTF*.xml') as $file) {
+            $tests[basename($file)] = [realpath($file)];
+        }
+
+        return $tests;
+    }
+
+    /**
+     * @dataProvider providerInvalidSimpleXML
+     * @expectedException \PhpOffice\PhpSpreadsheet\Reader\Exception
+     *
+     * @param $filename
+     */
+    public function testInvalidSimpleXML($filename)
+    {
+        $xmlReader = new Xml();
+        $xmlReader->trySimpleXMLLoadString($filename);
+    }
+
+    public function providerInvalidSimpleXML()
+    {
+        $tests = [];
+        foreach (glob(__DIR__ . '/../../data/Reader/XEE/XEETestInvalidSimpleXML*.xml') as $file) {
             $tests[basename($file)] = [realpath($file)];
         }
 

tests/data/Reader/XEE/XEETestInvalidSimpleXML.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<root>
+	<data>R&d</data>
+	<data>R<d</data>
+	<data>R>d</data>
+	<data>R'd</data>
+	<data>R"d</data>
+</root>