Added decodeMemoryLimit to Config to avoid memory leaks. (#476)

* Added decodeMemoryLimit to Config * decodeMemoryLimit is now an optional argument, defaulting to 0 (unlimited) * Add type to parameter $decodeMemoryLimit in decodeFilter * fixes cs issue in RawDataParser.php Co-authored-by: Konrad Abicht <[email protected]>
smalot · Nov 25, 2021 · e056671 · e056671
1 parent 768d1d6
commit e056671
Show file tree

Hide file tree

Showing 3 changed files with 24 additions and 6 deletions.
diff --git a/src/Smalot/PdfParser/Config.php b/src/Smalot/PdfParser/Config.php
@@ -61,6 +61,13 @@ class Config
      */
     private $retainImageContent = true;
 
+    /**
+     * Memory limit to use when de-compressing files, in bytes.
+     *
+     * @var int
+     */
+    private $decodeMemoryLimit = 0;
+
     public function getFontSpaceLimit()
     {
         return $this->fontSpaceLimit;
@@ -100,4 +107,14 @@ public function setRetainImageContent(bool $retainImageContent): void
     {
         $this->retainImageContent = $retainImageContent;
     }
+
+    public function getDecodeMemoryLimit(): int
+    {
+        return $this->decodeMemoryLimit;
+    }
+
+    public function setDecodeMemoryLimit(int $decodeMemoryLimit): void
+    {
+        $this->decodeMemoryLimit = $decodeMemoryLimit;
+    }
 }
diff --git a/src/Smalot/PdfParser/RawData/FilterHelper.php b/src/Smalot/PdfParser/RawData/FilterHelper.php
@@ -56,7 +56,7 @@ class FilterHelper
      *
      * @throws Exception if a certain decode function is not implemented yet
      */
-    public function decodeFilter(string $filter, string $data): string
+    public function decodeFilter(string $filter, string $data, int $decodeMemoryLimit = 0): string
     {
         switch ($filter) {
             case 'ASCIIHexDecode':
@@ -69,7 +69,7 @@ public function decodeFilter(string $filter, string $data): string
                 return $this->decodeFilterLZWDecode($data);
 
             case 'FlateDecode':
-                return $this->decodeFilterFlateDecode($data);
+                return $this->decodeFilterFlateDecode($data, $decodeMemoryLimit);
 
             case 'RunLengthDecode':
                 return $this->decodeFilterRunLengthDecode($data);
@@ -224,13 +224,14 @@ protected function decodeFilterASCII85Decode(string $data): string
      *
      * Decompresses data encoded using the zlib/deflate compression method, reproducing the original text or binary data.
      *
-     * @param string $data Data to decode
+     * @param string $data              Data to decode
+     * @param int    $decodeMemoryLimit Memory limit on deflation
      *
      * @return string data string
      *
      * @throws Exception
      */
-    protected function decodeFilterFlateDecode(string $data): ?string
+    protected function decodeFilterFlateDecode(string $data, int $decodeMemoryLimit): ?string
     {
         /*
          * gzuncompress may throw a not catchable E_WARNING in case of an error (like $data is empty)
@@ -249,7 +250,7 @@ protected function decodeFilterFlateDecode(string $data): ?string
 
         // initialize string to return
         try {
-            $decoded = gzuncompress($data);
+            $decoded = gzuncompress($data, $decodeMemoryLimit);
             if (false === $decoded) {
                 throw new Exception('decodeFilterFlateDecode: invalid code');
             }

diff --git a/src/Smalot/PdfParser/RawData/RawDataParser.php b/src/Smalot/PdfParser/RawData/RawDataParser.php
@@ -126,7 +126,7 @@ protected function decodeStream(string $pdfData, array $xref, array $sdic, strin
         foreach ($filters as $filter) {
             if (\in_array($filter, $this->filterHelper->getAvailableFilters())) {
                 try {
-                    $stream = $this->filterHelper->decodeFilter($filter, $stream);
+                    $stream = $this->filterHelper->decodeFilter($filter, $stream, $this->config->getDecodeMemoryLimit());
                 } catch (Exception $e) {
                     $emsg = $e->getMessage();
                     if ((('~' == $emsg[0]) && !$this->cfg['ignore_missing_filter_decoders'])