wikimedia/mediawiki-extensions-PdfHandler
1
0
Fork 0
mirror of https://gerrit.wikimedia.org/r/mediawiki/extensions/PdfHandler synced 2024-11-24 00:07:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix broken PDF XMP extraction

Browse source 
XMP extraction does not work for me with libpoppler 0.86, because when
the output of the two commands is concatenated, there is no "Metadata:"
prefix introducing the XMP. It ends up splitting every line of the XML
on colon characters in attribute names, spamming lots of little
properties into the final result.

I can confirm that it's also broken in production.

So, just treat the output of pdfinfo -meta as plain XML.

Change-Id: Ia3df17daed0f27e95294b5d97872ec064c79965c
This commit is contained in:
Tim Starling 2021-06-07 15:30:03 +10:00
parent 989b42b8eb
commit 86df1cd6c6
1 changed files with 13 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
includes/PdfImage.php
View file

@ -134,8 +134,10 @@ class PdfImage {
$resultPages = Shell::command( $cmdPages )
->execute();
$dump = $resultMeta->getStdout() . $resultPages->getStdout();
$data = $this->convertDumpToArray( $dump );
$data = $this->convertDumpToArray(
$resultMeta->getStdout(),
$resultPages->getStdout()
);
} else {
$data = [];
}
@ -162,15 +164,16 @@ class PdfImage {
}
/**
* @param string $dump
* @param string $metaDump
* @param string $infoDump
* @return array
*/
protected function convertDumpToArray( $dump ): array {
if ( strval( $dump ) == '' ) {
protected function convertDumpToArray( $metaDump, $infoDump ): array {
if ( strval( $infoDump ) == '' ) {
return [];
}
$lines = explode( "\n", $dump );
$lines = explode( "\n", $infoDump );
$data = [];
// Metadata is always the last item, and spans multiple lines.
@ -204,6 +207,10 @@ class PdfImage {
}
}
}
$metaDump = trim( $metaDump );
if ( $metaDump !== '' ) {
$data['xmp'] = $metaDump;
}
$data = $this->postProcessDump( $data );
return $data;
}