allow for line breaks when splitting xrefs for id and position (smalo…

…t#345)

* allow for line breaks when splitting xrefs for id and position

* extend TestCase.php with functionality to "catch" E_NOTICE and E_WARNING

* added test case for this fix

* only reset error handler when the current handler is the handler we had set before

* work around for failing CI build with PHP 5.6

* added comment and link to the workaround getting the current error handler

* removed unnecessary ini_set call

* remove error level constant name before error message

* restore error from the error handler itself, to prevent PHPUnit's "THE ERROR HANDLER HAS CHANGED!" message

* reverse the changes made to the TestCase class and the code in the test case depending on it

* simplified test case, now checking if object has been parsed correctly

* code linting

src/Smalot/PdfParser/Parser.php

@@ -190,7 +190,7 @@ protected function parseObject($id, $structure, $document)
                         $table = [];
 
                         foreach ($xrefs as $xref) {
-                            list($id, $position) = explode(' ', trim($xref));
+                            list($id, $position) = preg_split("/\s+/", trim($xref));
                             $table[$position] = $id;
                         }
 

tests/Integration/ParserTest.php

@@ -33,6 +33,7 @@
 namespace Tests\Smalot\PdfParser\Integration;
 
 use Exception;
+use Smalot\PdfParser\Document;
 use Smalot\PdfParser\Parser;
 use Smalot\PdfParser\XObject\Image;
 use Tests\Smalot\PdfParser\TestCase;
@@ -77,6 +78,48 @@ public function testParseFile()
         }
     }
 
+    /**
+     * Tests that xrefs with line breaks between id and position are parsed correctly
+     *
+     * @see https://github.com/smalot/pdfparser/issues/336
+     */
+    public function testIssue19()
+    {
+        $fixture = new ParserSub();
+        $structure = [
+            [
+                '<<',
+                [
+                    [
+                        '/',
+                        'Type',
+                        7735,
+                    ],
+                    [
+                        '/',
+                        'ObjStm',
+                        7742,
+                    ],
+                ],
+            ],
+            [
+                'stream',
+                '',
+                7804,
+                [
+                    "17\n0",
+                    [],
+                ],
+            ],
+        ];
+        $document = new Document();
+
+        $fixture->exposedParseObject('19_0', $structure, $document);
+        $objects = $fixture->getObjects();
+
+        $this->assertArrayHasKey('17_0', $objects);
+    }
+
     /**
      * Test that issue related pdf can now be parsed
      *
@@ -127,3 +170,16 @@ public function testIssue334()
         $this->assertStringContainsString('This question already has an answer here', $document->getText());
     }
 }
+
+class ParserSub extends Parser
+{
+    public function exposedParseObject($id, $structure, $document)
+    {
+        return $this->parseObject($id, $structure, $document);
+    }
+
+    public function getObjects()
+    {
+        return $this->objects;
+    }
+}