Image metadata is usually a serialized string representing an array. Passing the string around internally and having everything unserialize it is an awkward convention. Also, many image handlers were reading the file twice: once for getMetadata() and again for getImageSize(). Often getMetadata() would actually read the width and height and then throw it away. So, in filerepo: * Add File::getMetadataItem(), which promises to allow partial loading of metadata per my proposal on T275268 in a future commit. * Add File::getMetadataArray(), which returns the unserialized array. Some file handlers were returning non-serializable strings from getMetadata(), so I gave them a legacy array form ['_error' => ...] * Changed MWFileProps to return the array form of metadata. * Deprecate the weird File::getImageSize(). It was apparently not called by anything, but was overridden by UnregisteredLocalFile. * Wrap serialize/unserialize with File::getMetadataForDb() and File::loadMetadataFromDb() in preparation for T275268. In MediaHandler: * Merged MediaHandler::getImageSize() and MediaHandler::getMetadata() into getSizeAndMetadata(). Deprecated the old methods. * Instead of isMetadataValid() we now have isFileMetadataValid(), which only gets a File object, so it can decide what data it needs to load. * Simplified getPageDimensions() by having it return false for non-paged media. It was not called in that case, but was implemented anyway. In specific handlers: * Rename DjVuHandler::getUnserializedMetadata() and extractTreesFromMetadata() for clarity. "Metadata" in these function names meant an XML string. * Updated DjVuImage::getImageSize() to provide image sizes in the new style. * In ExifBitmapHandler, getRotationForExif() now takes just the Orientation tag, rather than a serialized string. Also renamed for clarity. * In GIFMetadataExtractor, return the width, height and bits per channel instead of throwing them away. There was some conflation in decodeBPP() which I picked apart. Refer to GIF89a section 18. * In JpegMetadataExtractor, process the SOF0/SOF2 segment to extract bits per channel, width, height and components (channel count). This is essentially a port of PHP's getimagesize(), so should be bugwards compatible. * In PNGMetadataExtractor, return the width and height, which were previously assigned to unused local variables. I verified the implementation by referring to the specification. * In SvgHandler, retain the version validation from unpackMetadata(), but rename the function since it now takes an array as input. In tests: * In ExifBitmapTest, refactored some tests by using a provider. * In GIFHandlerTest and PNGHandlerTest, I removed the tests in which getMetadata() returns null, since it doesn't make sense when ported to getMetadataArray(). I added tests for empty arrays instead. * In tests, I retained serialization of input data since I figure it's useful to confirm that existing database rows will continue to be read correctly. I removed serialization of expected values, replacing them with plain data. * In tests, I replaced access to private class constants like BROKEN_FILE with string literals, since stability is essential. If the class constant changes, the test should fail. Elsewhere: * In maintenance/refreshImageMetadata.php, I removed the check for shrinking image metadata, since it's not easy to implement and is not future compatible. Image metadata is expected to shrink in future. Bug: T275268 Change-Id: I039785d5b6439d71dcc21dcb972177dba5c3a67d
162 lines
4.7 KiB
PHP
162 lines
4.7 KiB
PHP
<?php
|
|
|
|
/**
|
|
* @group Media
|
|
*/
|
|
class BitmapMetadataHandlerTest extends MediaWikiIntegrationTestCase {
|
|
|
|
protected function setUp() : void {
|
|
parent::setUp();
|
|
|
|
$this->setMwGlobals( 'wgShowEXIF', false );
|
|
|
|
$this->filePath = __DIR__ . '/../../data/media/';
|
|
}
|
|
|
|
/**
|
|
* Test if having conflicting metadata values from different
|
|
* types of metadata, that the right one takes precedence.
|
|
*
|
|
* Basically the file has IPTC and XMP metadata, the
|
|
* IPTC should override the XMP, except for the multilingual
|
|
* translation (to en) where XMP should win.
|
|
* @covers BitmapMetadataHandler::Jpeg
|
|
*/
|
|
public function testMultilingualCascade() {
|
|
$this->checkPHPExtension( 'exif' );
|
|
$this->checkPHPExtension( 'xml' );
|
|
|
|
$this->setMwGlobals( 'wgShowEXIF', true );
|
|
|
|
$meta = BitmapMetadataHandler::Jpeg( $this->filePath .
|
|
'/Xmp-exif-multilingual_test.jpg' );
|
|
|
|
$expected = [
|
|
'x-default' => 'right(iptc)',
|
|
'en' => 'right translation',
|
|
'_type' => 'lang'
|
|
];
|
|
|
|
$this->assertArrayHasKey( 'ImageDescription', $meta,
|
|
'Did not extract any ImageDescription info?!' );
|
|
|
|
$this->assertEquals( $expected, $meta['ImageDescription'] );
|
|
}
|
|
|
|
/**
|
|
* Test for jpeg comments are being handled by
|
|
* BitmapMetadataHandler correctly.
|
|
*
|
|
* There's more extensive tests of comment extraction in
|
|
* JpegMetadataExtractorTests.php
|
|
* @covers BitmapMetadataHandler::Jpeg
|
|
*/
|
|
public function testJpegComment() {
|
|
$meta = BitmapMetadataHandler::Jpeg( $this->filePath .
|
|
'jpeg-comment-utf.jpg' );
|
|
|
|
$this->assertEquals( 'UTF-8 JPEG Comment — ¼',
|
|
$meta['JPEGFileComment'][0] );
|
|
}
|
|
|
|
/**
|
|
* Make sure a bad iptc block doesn't stop the other metadata
|
|
* from being extracted.
|
|
* @covers BitmapMetadataHandler::Jpeg
|
|
*/
|
|
public function testBadIPTC() {
|
|
$meta = BitmapMetadataHandler::Jpeg( $this->filePath .
|
|
'iptc-invalid-psir.jpg' );
|
|
$this->assertEquals( 'Created with GIMP', $meta['JPEGFileComment'][0] );
|
|
}
|
|
|
|
/**
|
|
* @covers BitmapMetadataHandler::Jpeg
|
|
*/
|
|
public function testIPTCDates() {
|
|
$meta = BitmapMetadataHandler::Jpeg( $this->filePath .
|
|
'iptc-timetest.jpg' );
|
|
|
|
// raw date is 2020:07:13 14:04:05+11:32
|
|
$this->assertEquals( '2020:07:14 01:36:05', $meta['DateTimeDigitized'] );
|
|
// raw date is 1997:03:02 03:01:02-03:00
|
|
$this->assertEquals( '1997:03:02 00:01:02', $meta['DateTimeOriginal'] );
|
|
|
|
$meta = BitmapMetadataHandler::Jpeg( $this->filePath .
|
|
'iptc-timetest-invalid.jpg' );
|
|
|
|
// raw date is 1845:03:02 03:01:02-03:00
|
|
$this->assertEquals( '1845:03:02 00:01:02', $meta['DateTimeOriginal'] );
|
|
// raw date is 1942:07:13 25:05:02+00:00
|
|
$this->assertSame( '1942:07:14 01:05:02', $meta['DateTimeDigitized'] );
|
|
}
|
|
|
|
/**
|
|
* XMP data should take priority over iptc data
|
|
* when hash has been updated, but not when
|
|
* the hash is wrong.
|
|
* @covers BitmapMetadataHandler::addMetadata
|
|
* @covers BitmapMetadataHandler::getMetadataArray
|
|
*/
|
|
public function testMerging() {
|
|
$merger = new BitmapMetadataHandler();
|
|
$merger->addMetadata( [ 'foo' => 'xmp' ], 'xmp-general' );
|
|
$merger->addMetadata( [ 'bar' => 'xmp' ], 'xmp-general' );
|
|
$merger->addMetadata( [ 'baz' => 'xmp' ], 'xmp-general' );
|
|
$merger->addMetadata( [ 'fred' => 'xmp' ], 'xmp-general' );
|
|
$merger->addMetadata( [ 'foo' => 'iptc (hash)' ], 'iptc-good-hash' );
|
|
$merger->addMetadata( [ 'bar' => 'iptc (bad hash)' ], 'iptc-bad-hash' );
|
|
$merger->addMetadata( [ 'baz' => 'iptc (bad hash)' ], 'iptc-bad-hash' );
|
|
$merger->addMetadata( [ 'fred' => 'iptc (no hash)' ], 'iptc-no-hash' );
|
|
$merger->addMetadata( [ 'baz' => 'exif' ], 'exif' );
|
|
|
|
$actual = $merger->getMetadataArray();
|
|
$expected = [
|
|
'foo' => 'xmp',
|
|
'bar' => 'iptc (bad hash)',
|
|
'baz' => 'exif',
|
|
'fred' => 'xmp',
|
|
];
|
|
$this->assertEquals( $expected, $actual );
|
|
}
|
|
|
|
/**
|
|
* @covers BitmapMetadataHandler::png
|
|
*/
|
|
public function testPNGXMP() {
|
|
$this->checkPHPExtension( 'xml' );
|
|
|
|
$result = BitmapMetadataHandler::PNG( $this->filePath . 'xmp.png' );
|
|
$expected = [
|
|
'width' => 50,
|
|
'height' => 50,
|
|
'frameCount' => 0,
|
|
'loopCount' => 1,
|
|
'duration' => 0,
|
|
'bitDepth' => 1,
|
|
'colorType' => 'index-coloured',
|
|
'metadata' => [
|
|
'SerialNumber' => '123456789',
|
|
'_MW_PNG_VERSION' => 1,
|
|
],
|
|
];
|
|
$this->assertEquals( $expected, $result );
|
|
}
|
|
|
|
/**
|
|
* @covers BitmapMetadataHandler::png
|
|
*/
|
|
public function testPNGNative() {
|
|
$result = BitmapMetadataHandler::PNG( $this->filePath . 'Png-native-test.png' );
|
|
$expected = 'http://example.com/url';
|
|
$this->assertEquals( $expected, $result['metadata']['Identifier']['x-default'] );
|
|
}
|
|
|
|
/**
|
|
* @covers BitmapMetadataHandler::getTiffByteOrder
|
|
*/
|
|
public function testTiffByteOrder() {
|
|
$res = BitmapMetadataHandler::getTiffByteOrder( $this->filePath . 'test.tiff' );
|
|
$this->assertEquals( 'LE', $res );
|
|
}
|
|
}
|