#561 Added optional getText() argument to return limited number of do…

…cument pages if set (#562)

* #561 Added optional getText() argument to return limited number of document pages if set.

* Update src/Smalot/PdfParser/Document.php

* Update src/Smalot/PdfParser/Document.php

* fixed changes for PHP <7.4; added basic two tests

* fixed coding style issue

* Usage.md: added a short example how to use new functionality

Co-authored-by: Konrad Abicht <hi@inspirito.de>

doc/Usage.md

@@ -15,10 +15,14 @@ $pdf = $parser->parseContent(file_get_contents('document.pdf'))
 A common scenario is to extract text.
 
 ```php
+// extract text of the whole PDF
 $text = $pdf->getText();
 
 // or extract the text of a specific page (in this case the first page)
 $text = $pdf->getPages()[0]->getText();
+
+// you can also extract text of a limited amount of pages. here, it will only use the first five pages.
+$text = $pdf->getText(5);
 ```
 
 ## Extract text positions

src/Smalot/PdfParser/Document.php

@@ -264,11 +264,16 @@ public function getPages()
         throw new \Exception('Missing catalog.');
     }
 
-    public function getText(): string
+    public function getText(?int $pageLimit = null): string
     {
         $texts = [];
         $pages = $this->getPages();
 
+        // Only use the first X number of pages if $pageLimit is set and numeric.
+        if (\is_int($pageLimit) && 0 < $pageLimit) {
+            $pages = \array_slice($pages, 0, $pageLimit);
+        }
+
         foreach ($pages as $index => $page) {
             /**
              * In some cases, the $page variable may be null.

tests/Integration/DocumentTest.php

@@ -39,6 +39,7 @@
 use Smalot\PdfParser\Header;
 use Smalot\PdfParser\Page;
 use Smalot\PdfParser\Pages;
+use Smalot\PdfParser\Parser;
 use Smalot\PdfParser\PDFObject;
 use Tests\Smalot\PdfParser\TestCase;
 
@@ -229,4 +230,29 @@ public function testGetPagesMissingCatalog(): void
         $document = $this->getDocumentInstance();
         $document->getPages();
     }
+
+    /**
+     * Tests getText method without a given page limit.
+     *
+     * @see https://github.com/smalot/pdfparser/pull/562
+     */
+    public function testGetTextNoPageLimit(): void
+    {
+        $document = (new Parser())->parseFile($this->rootDir.'/samples/bugs/Issue331.pdf');
+
+        self::assertStringContainsString('Medeni Usul ve İcra İflas Hukuku', $document->getText());
+    }
+
+    /**
+     * Tests getText method with a given page limit.
+     *
+     * @see https://github.com/smalot/pdfparser/pull/562
+     */
+    public function testGetTextWithPageLimit(): void
+    {
+        $document = (new Parser())->parseFile($this->rootDir.'/samples/bugs/Issue331.pdf');
+
+        // given text is on page 2, it has to be ignored because of that
+        self::assertStringNotContainsString('Medeni Usul ve İcra İflas Hukuku', $document->getText(1));
+    }
 }