Skip to content

fix: aggregate startxref whitespace tolerance #3

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
vitormattos merged 4 commits into from
Apr 24, 2026
Merged

fix: aggregate startxref whitespace tolerance #3

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
be240ba
fix: allow startxref offset to include leading whitespace
vitormattos Apr 24, 2026
583526e
test: use assertCount for page count assertion
vitormattos Apr 24, 2026
a3d9df0
test: add pdf.js compressed xref regression
vitormattos Apr 24, 2026
d4c26e9
test: clarify pull request fixture provenance
vitormattos Apr 24, 2026
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
Binary file added samples/bugs/PullRequest797-pdf.js.pdf
View file
Open in desktop
Binary file not shown.
Binary file added samples/bugs/PullRequest797-vera.pdf
View file
Open in desktop
Binary file not shown.
20 changes: 12 additions & 8 deletions src/Smalot/PdfParser/RawData/RawDataParser.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -198,16 +198,16 @@ protected function decodeXref(string $pdfData, int $startxref, array $xref = [],
// get only the last updated version
$xref['trailer'] = [];
// parse trailer_data
if (preg_match('/Size[\s]+([0-9]+)/i', $trailer_data, $matches) > 0) {
if (preg_match('/\/Size[\s]+([0-9]+)/i', $trailer_data, $matches) > 0) {
$xref['trailer']['size'] = (int) $matches[1];
}
if (preg_match('/Root[\s]+([0-9]+)[\s]+([0-9]+)[\s]+R/i', $trailer_data, $matches) > 0) {
if (preg_match('/\/Root[\s]+([0-9]+)[\s]+([0-9]+)[\s]+R/i', $trailer_data, $matches) > 0) {
$xref['trailer']['root'] = (int) $matches[1].'_'.(int) $matches[2];
}
if (preg_match('/Encrypt[\s]+([0-9]+)[\s]+([0-9]+)[\s]+R/i', $trailer_data, $matches) > 0) {
if (preg_match('/\/Encrypt[\s]+([0-9]+)[\s]+([0-9]+)[\s]+R/i', $trailer_data, $matches) > 0) {
$xref['trailer']['encrypt'] = (int) $matches[1].'_'.(int) $matches[2];
}
if (preg_match('/Info[\s]+([0-9]+)[\s]+([0-9]+)[\s]+R/i', $trailer_data, $matches) > 0) {
if (preg_match('/\/Info[\s]+([0-9]+)[\s]+([0-9]+)[\s]+R/i', $trailer_data, $matches) > 0) {
$xref['trailer']['info'] = (int) $matches[1].'_'.(int) $matches[2];
}
if (preg_match('/ID[\s]*[\[][\s]*[<]([^>]*)[>][\s]*[<]([^>]*)[>]/i', $trailer_data, $matches) > 0) {
Expand All @@ -216,7 +216,7 @@ protected function decodeXref(string $pdfData, int $startxref, array $xref = [],
$xref['trailer']['id'][1] = $matches[2];
}
}
if (preg_match('/Prev[\s]+([0-9]+)/i', $trailer_data, $matches) > 0) {
if (preg_match('/\/Prev[\s]+([0-9]+)/i', $trailer_data, $matches) > 0) {
$offset = (int) $matches[1];
if (0 != $offset) {
// get previous xref
Expand Down Expand Up @@ -922,14 +922,18 @@ protected function getXrefData(string $pdfData, int $offset = 0, array $xref = [
throw new \Exception('Unable to find xref (PDF corrupted?)');
}

// Some files point startxref to the whitespace right before the xref keyword.
$startxrefOffset = $startxref + strspn($pdfData, $this->config->getPdfWhitespaces(), $startxref);

// check xref position
if (strpos($pdfData, 'xref', $startxref) == $startxref) {
if (strpos($pdfData, 'xref', $startxrefOffset) == $startxrefOffset) {
// Cross-Reference
$xref = $this->decodeXref($pdfData, $startxref, $xref, $visitedOffsets);
$xref = $this->decodeXref($pdfData, $startxrefOffset, $xref, $visitedOffsets);
} else {
// Check if the $pdfData might have the wrong line-endings
$pdfDataUnix = str_replace("\r\n", "\n", $pdfData);
if ($startxref < \strlen($pdfDataUnix) && strpos($pdfDataUnix, 'xref', $startxref) == $startxref) {
$startxrefUnixOffset = $startxref + strspn($pdfDataUnix, $this->config->getPdfWhitespaces(), $startxref);
if ($startxrefUnixOffset < \strlen($pdfDataUnix) && strpos($pdfDataUnix, 'xref', $startxrefUnixOffset) == $startxrefUnixOffset) {
// Return Unix-line-ending flag
$xref = ['Unix' => true];
} else {
Expand Down
18 changes: 17 additions & 1 deletion tests/PHPUnit/Integration/DocumentIssueFocusTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,6 @@
namespace PHPUnitTests\Integration;

use PHPUnitTests\TestCase;
use Smalot\PdfParser\Document;
use Smalot\PdfParser\Parser;

/**
Expand Down Expand Up @@ -111,4 +110,21 @@ public function testPDFDocEncodingDecode(): void
$testSubject = '•†‡…—–ƒ⁄‹›−‰„“”‘’‚™ŁŒŠŸŽıłœšž';
self::assertStringContainsString($testSubject, $details['Subject']);
}

public function testParseFileWhenStartxrefPointsToLeadingWhitespaceInVeraPdfFixture(): void
{
$document = (new Parser())->parseFile($this->rootDir.'/samples/bugs/PullRequest797-vera.pdf');

self::assertCount(1, $document->getPages());
}

/**
* @see https://github.com/smalot/pdfparser/pull/797
*/
public function testParseFileWithCompressedXrefObjectFromPdfJsCorpus(): void
{
$document = (new Parser())->parseFile($this->rootDir.'/samples/bugs/PullRequest797-pdf.js.pdf');

self::assertCount(1, $document->getPages());
}
}
Loading