function getMetadata($image, $filename)
{
try {
$meta = BitmapMetadataHandler::Jpeg($filename);
if (!is_array($meta)) {
// This should never happen, but doesn't hurt to be paranoid.
throw new MWException('Metadata array is not an array');
}
$meta['MEDIAWIKI_EXIF_VERSION'] = Exif::version();
return serialize($meta);
} catch (MWException $e) {
// BitmapMetadataHandler throws an exception in certain exceptional
// cases like if file does not exist.
wfDebug(__METHOD__ . ': ' . $e->getMessage() . "\n");
/* This used to use 0 (ExifBitmapHandler::OLD_BROKEN_FILE) for the cases
* * No metadata in the file
* * Something is broken in the file.
* However, if the metadata support gets expanded then you can't tell if the 0 is from
* a broken file, or just no props found. A broken file is likely to stay broken, but
* a file which had no props could have props once the metadata support is improved.
* Thus switch to using -1 to denote only a broken file, and use an array with only
* MEDIAWIKI_EXIF_VERSION to denote no props.
*/
return ExifBitmapHandler::BROKEN_FILE;
}
}
function getMetadata($image, $filename)
{
try {
$parsedGIFMetadata = BitmapMetadataHandler::GIF($filename);
} catch (Exception $e) {
// Broken file?
wfDebug(__METHOD__ . ': ' . $e->getMessage() . "\n");
return self::BROKEN_FILE;
}
return serialize($parsedGIFMetadata);
}
/**
* @param File $image
* @param string $filename
* @throws MWException
* @return string
*/
function getMetadata($image, $filename)
{
global $wgShowEXIF;
if ($wgShowEXIF) {
try {
$meta = BitmapMetadataHandler::Tiff($filename);
if (!is_array($meta)) {
// This should never happen, but doesn't hurt to be paranoid.
throw new MWException('Metadata array is not an array');
}
$meta['MEDIAWIKI_EXIF_VERSION'] = Exif::version();
return serialize($meta);
} catch (Exception $e) {
// BitmapMetadataHandler throws an exception in certain exceptional
// cases like if file does not exist.
wfDebug(__METHOD__ . ': ' . $e->getMessage() . "\n");
return ExifBitmapHandler::BROKEN_FILE;
}
} else {
return '';
}
}
public function testTiffByteOrder()
{
$handler = new BitmapMetadataHandler();
$res = $handler->getTiffByteOrder($this->filePath . 'test.tiff');
$this->assertEquals('LE', $res);
}
/**
* Postprocess the metadata (convert xmp into useful form, etc)
*
* This is used to generate the metadata table at the bottom
* of the image description page.
*
* @param $data Array metadata
* @return Array post-processed metadata
*/
protected function postProcessDump(array $data)
{
$meta = new BitmapMetadataHandler();
$items = array();
foreach ($data as $key => $val) {
switch ($key) {
case 'Title':
$items['ObjectName'] = $val;
break;
case 'Subject':
$items['ImageDescription'] = $val;
break;
case 'Keywords':
// Sometimes we have empty keywords. This seems
// to be a product of how pdfinfo deals with keywords
// with spaces in them. Filter such empty keywords
$keyList = array_filter(explode(' ', $val));
if (count($keyList) > 0) {
$items['Keywords'] = $keyList;
}
break;
case 'Author':
$items['Artist'] = $val;
break;
case 'Creator':
// Program used to create file.
// Different from program used to convert to pdf.
$items['Software'] = $val;
break;
case 'Producer':
// Conversion program
$items['pdf-Producer'] = $val;
break;
case 'ModTime':
$timestamp = wfTimestamp(TS_EXIF, $val);
if ($timestamp) {
// 'if' is just paranoia
$items['DateTime'] = $timestamp;
}
break;
case 'CreationTime':
$timestamp = wfTimestamp(TS_EXIF, $val);
if ($timestamp) {
$items['DateTimeDigitized'] = $timestamp;
}
break;
// These last two (version and encryption) I was unsure
// if we should include in the table, since they aren't
// all that useful to editors. I leaned on the side
// of including. However not including if file
// is optimized/linearized since that is really useless
// to an editor.
// These last two (version and encryption) I was unsure
// if we should include in the table, since they aren't
// all that useful to editors. I leaned on the side
// of including. However not including if file
// is optimized/linearized since that is really useless
// to an editor.
case 'PDF version':
$items['pdf-Version'] = $val;
break;
case 'Encrypted':
// @todo: The value isn't i18n-ised. The appropriate
// place to do that is in FormatMetadata.php
// should add a hook a there.
// For reference, if encrypted this fields value looks like:
// "yes (print:yes copy:no change:no addNotes:no)"
$items['pdf-Encrypted'] = $val;
break;
// Note 'pages' and 'Pages' are different keys (!)
// Note 'pages' and 'Pages' are different keys (!)
case 'pages':
// A pdf document can have multiple sized pages in it.
// (However 95% of the time, all pages are the same size)
// get a list of all the unique page sizes in document.
// This doesn't do anything with rotation as of yet,
// mostly because I am unsure of what a good way to
// present that information to the user would be.
$pageSizes = array();
foreach ($val as $page) {
if (isset($page['Page size'])) {
$pageSizes[$page['Page size']] = true;
}
}
$pageSizeArray = array_keys($pageSizes);
if (count($pageSizeArray) > 0) {
$items['pdf-PageSize'] = $pageSizeArray;
}
break;
}
}
$meta->addMetadata($items, 'native');
if (isset($data['xmp']) && function_exists('xml_parser_create_ns')) {
// func exists verifies that the xml extension required for XMPReader
// is present (Almost always is present)
// @todo: This only handles generic xmp properties. Would be improved
// by handling pdf xmp properties (pdf and pdfx) via XMPInfo hook.
$xmp = new XMPReader(LoggerFactory::getInstance('XMP'));
$xmp->parse($data['xmp']);
$xmpRes = $xmp->getResults();
foreach ($xmpRes as $type => $xmpSection) {
$meta->addMetadata($xmpSection, $type);
}
}
unset($data['xmp']);
$data['mergedMetadata'] = $meta->getMetadataArray();
return $data;
}
/**
* Reads metadata of the tiff file via shell command and returns an associative array.
* layout:
* meta['page_count'] = number of pages
* meta['first_page'] = number of first page
* meta['last_page'] = number of last page
* meta['page_data'] = metadata per page
* meta['exif'] = Exif, XMP and IPTC
* meta['errors'] = identify-errors
* meta['warnings'] = identify-warnings
*/
public function retrieveMetaData() {
global $wgImageMagickIdentifyCommand, $wgExiv2Command, $wgTiffUseExiv;
global $wgTiffUseTiffinfo, $wgTiffTiffinfoCommand;
global $wgShowEXIF;
if ( $this->_meta === null ) {
wfProfileIn( 'PagedTiffImage::retrieveMetaData' );
//fetch base info: number of pages, size and alpha for each page.
//run hooks first, then optionally tiffinfo or, per default, ImageMagic's identify command
if ( !wfRunHooks( 'PagedTiffHandlerTiffData', array( $this->mFilename, &$this->_meta ) ) ) {
wfDebug( __METHOD__ . ": hook PagedTiffHandlerTiffData overrides TIFF data extraction\n" );
} elseif ( $wgTiffUseTiffinfo ) {
// read TIFF directories using libtiff's tiffinfo, see
// http://www.libtiff.org/man/tiffinfo.1.html
$cmd = wfEscapeShellArg( $wgTiffTiffinfoCommand ) .
' ' . wfEscapeShellArg( $this->mFilename ) . ' 2>&1';
wfProfileIn( 'tiffinfo' );
wfDebug( __METHOD__ . ": $cmd\n" );
$retval = '';
$dump = wfShellExec( $cmd, $retval );
wfProfileOut( 'tiffinfo' );
if ( $retval ) {
$data['errors'][] = "tiffinfo command failed: $cmd";
wfDebug( __METHOD__ . ": tiffinfo command failed: $cmd\n" );
return $data; // fail. we *need* that info
}
$this->_meta = $this->parseTiffinfoOutput( $dump );
} else {
$cmd = wfEscapeShellArg( $wgImageMagickIdentifyCommand ) .
' -format "[BEGIN]page=%p\nalpha=%A\nalpha2=%r\nheight=%h\nwidth=%w\ndepth=%z[END]" ' .
wfEscapeShellArg( $this->mFilename ) . ' 2>&1';
wfProfileIn( 'identify' );
wfDebug( __METHOD__ . ": $cmd\n" );
$retval = '';
$dump = wfShellExec( $cmd, $retval );
wfProfileOut( 'identify' );
if ( $retval ) {
$data['errors'][] = "identify command failed: $cmd";
wfDebug( __METHOD__ . ": identify command failed: $cmd\n" );
return $data; // fail. we *need* that info
}
$this->_meta = $this->parseIdentifyOutput( $dump );
}
$this->_meta['exif'] = array();
//fetch extended info: EXIF/IPTC/XMP
//run hooks first, then optionally Exiv2 or, per default, the internal EXIF class
if ( !empty( $this->_meta['errors'] ) ) {
wfDebug( __METHOD__ . ": found errors, skipping EXIF extraction\n" );
} elseif ( !wfRunHooks( 'PagedTiffHandlerExifData', array( $this->mFilename, &$this->_meta['exif'] ) ) ) {
wfDebug( __METHOD__ . ": hook PagedTiffHandlerExifData overrides EXIF extraction\n" );
} elseif ( $wgTiffUseExiv ) {
// read EXIF, XMP, IPTC as name-tag => interpreted data
// -ignore unknown fields
// see exiv2-doc @link http://www.exiv2.org/sample.html
// NOTE: the linux version of exiv2 has a bug: it can only
// read one type of meta-data at a time, not all at once.
$cmd = wfEscapeShellArg( $wgExiv2Command ) .
' -u -psix -Pnt ' . wfEscapeShellArg( $this->mFilename ) . ' 2>&1';
wfProfileIn( 'exiv2' );
wfDebug( __METHOD__ . ": $cmd\n" );
$retval = '';
$dump = wfShellExec( $cmd, $retval );
wfProfileOut( 'exiv2' );
if ( $retval ) {
$data['errors'][] = "exiv command failed: $cmd";
wfDebug( __METHOD__ . ": exiv command failed: $cmd\n" );
// don't fail - we are missing info, just report
}
$data = $this->parseExiv2Output( $dump );
$this->_meta['exif'] = $data;
} elseif ( $wgShowEXIF ) {
wfDebug( __METHOD__ . ": using internal Exif( {$this->mFilename} )\n" );
if ( method_exists( 'BitmapMetadataHandler', 'Tiff' ) ) {
$data = BitmapMetadataHandler::Tiff( $this->mFilename );
} else {
// old method for back compat.
$exif = new Exif( $this->mFilename );
$data = $exif->getFilteredData();
}
if ( $data ) {
$data['MEDIAWIKI_EXIF_VERSION'] = Exif::version();
$this->_meta['exif'] = $data;
}
}
unset( $this->_meta['exif']['Image'] );
unset( $this->_meta['exif']['filename'] );
unset( $this->_meta['exif']['Base filename'] );
unset( $this->_meta['exif']['XMLPacket'] );
unset( $this->_meta['exif']['ImageResources'] );
$this->_meta['TIFF_METADATA_VERSION'] = TIFF_METADATA_VERSION;
wfProfileOut( 'PagedTiffImage::retrieveMetaData' );
}
return $this->_meta;
}
