Skip to content

Stop Image XObjects being included as empty strings in PDFObject::getTextArray(). #775

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
k00ni merged 4 commits into from
Jul 31, 2025
Merged

Stop Image XObjects being included as empty strings in PDFObject::getTextArray(). #775

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
7a6cbe4
Stop Image XObjects being included as empty strings in PDFObject::get…
rupertj Jul 16, 2025
d656730
Fix code style issues.
rupertj Jul 17, 2025
77f96a9
Add test coverage to PDFObject::getTextArray() to cover the Do comman…
rupertj Jul 17, 2025
9e1e165
Merge branch 'smalot:master' into issue/733
rupertj Jul 29, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 21 additions & 10 deletions src/Smalot/PdfParser/PDFObject.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -775,16 +775,27 @@ public function getTextArray(?Page $page = null): array
break;

case 'Do':
if (null !== $page) {
$args = preg_split('/\s/s', $command[self::COMMAND]);
$id = trim(array_pop($args), '/ ');
$xobject = $page->getXObject($id);

// @todo $xobject could be a ElementXRef object, which would then throw an error
if (\is_object($xobject) && $xobject instanceof self && !\in_array($xobject->getUniqueId(), self::$recursionStack, true)) {
// Not a circular reference.
$text[] = $xobject->getText($page);
}
if (is_null($page)) {
break;
}

$args = preg_split('/\s/s', $command[self::COMMAND]);
$id = trim(array_pop($args), '/ ');
$xobject = $page->getXObject($id);

// Check we got a PDFObject back.
if (!$xobject instanceof self) {
break;
}

// If the PDFObject is an image, do nothing, as images aren't text.
if ($xobject instanceof Image) {
break;
}

// Check this is not a circular reference.
if (!\in_array($xobject->getUniqueId(), self::$recursionStack, true)) {
$text[] = $xobject->getText($page);
}
break;

Expand Down
39 changes: 39 additions & 0 deletions tests/PHPUnit/Unit/PDFObjectTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,8 +6,12 @@

use PHPUnitTests\TestCase;
use Smalot\PdfParser\Document;
use Smalot\PdfParser\Element;
use Smalot\PdfParser\Element\ElementArray;
use Smalot\PdfParser\Header;
use Smalot\PdfParser\Page;
use Smalot\PdfParser\PDFObject;
use Smalot\PdfParser\XObject\Image;

class PDFObjectTest extends TestCase
{
Expand All @@ -22,4 +26,39 @@ public function testGetTextOnPageWithoutContent(): void

static::assertSame(' ', (new PDFObject($document, null, null))->getText(new Page($document)));
}

public function testTextArrayObjects(): void
{
$document = new Document();
$document->init();

$image = new Image($document);
$xObject = new PDFObject($document);

$header1 = new Header([
'Resources' => new Header([
'XObject' => new Header([
'Im0' => $image,
])
]),
'Contents' => new ElementArray([new Element('/Imo Do', $document)], $document),
]);
$page1 = new Page($document, $header1);

$header2 = new Header([
'Resources' => new Header([
'XObject' => new Header([
'Ps0' => $xObject,
])
]),
'Contents' => new ElementArray([new Element('/Ps0 Do', $document)], $document),
]);
$page2 = new Page($document, $header2);

// Page 1 contains an image, which should not appear in the text array.
self::assertSame([], $page1->getTextArray());

// Page 2 contains a non-image object, which should appear in the text array.
self::assertSame([' '], $page2->getTextArray());
}
}
Loading