2016-09-19 01:39:59 +00:00
|
|
|
<?php
|
|
|
|
|
/**
|
|
|
|
|
* MimeMagic helper functions for detecting and dealing with MIME types.
|
|
|
|
|
*
|
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
|
* it under the terms of the GNU General Public License as published by
|
|
|
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
|
|
|
* (at your option) any later version.
|
|
|
|
|
*
|
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
|
* GNU General Public License for more details.
|
|
|
|
|
*
|
|
|
|
|
* You should have received a copy of the GNU General Public License along
|
|
|
|
|
* with this program; if not, write to the Free Software Foundation, Inc.,
|
|
|
|
|
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
|
|
|
|
|
* http://www.gnu.org/copyleft/gpl.html
|
|
|
|
|
*
|
|
|
|
|
* @file
|
|
|
|
|
*/
|
|
|
|
|
|
2024-05-19 13:40:05 +00:00
|
|
|
use Wikimedia\FileBackend\FileBackend;
|
2024-09-27 19:20:56 +00:00
|
|
|
use Wikimedia\FileBackend\FSFile\FSFile;
|
2024-09-27 18:21:33 +00:00
|
|
|
use Wikimedia\Mime\MimeAnalyzer;
|
2024-05-19 13:40:05 +00:00
|
|
|
|
2016-09-19 01:39:59 +00:00
|
|
|
/**
|
|
|
|
|
* MimeMagic helper wrapper
|
|
|
|
|
*
|
|
|
|
|
* @since 1.28
|
|
|
|
|
*/
|
|
|
|
|
class MWFileProps {
|
2018-09-21 01:40:59 +00:00
|
|
|
/** @var MimeAnalyzer */
|
2016-09-19 01:39:59 +00:00
|
|
|
private $magic;
|
|
|
|
|
|
|
|
|
|
/**
|
2017-11-27 01:33:57 +00:00
|
|
|
* @param MimeAnalyzer $magic
|
2016-09-19 01:39:59 +00:00
|
|
|
*/
|
2017-11-27 01:33:57 +00:00
|
|
|
public function __construct( MimeAnalyzer $magic ) {
|
2016-09-19 01:39:59 +00:00
|
|
|
$this->magic = $magic;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Get an associative array containing information about
|
|
|
|
|
* a file with the given storage path.
|
|
|
|
|
*
|
|
|
|
|
* Resulting array fields include:
|
|
|
|
|
* - fileExists
|
|
|
|
|
* - size (filesize in bytes)
|
|
|
|
|
* - mime (as major/minor)
|
|
|
|
|
* - media_type (value to be used with the MEDIATYPE_xxx constants)
|
|
|
|
|
* - metadata (handler specific)
|
|
|
|
|
* - sha1 (in base 36)
|
|
|
|
|
* - width
|
|
|
|
|
* - height
|
|
|
|
|
* - bits (bitrate)
|
|
|
|
|
* - file-mime
|
|
|
|
|
* - major_mime
|
|
|
|
|
* - minor_mime
|
|
|
|
|
*
|
|
|
|
|
* @param string $path Filesystem path to a file
|
2021-02-02 07:44:26 +00:00
|
|
|
* @param string|bool|null $ext The file extension, or true to extract it from the filename.
|
|
|
|
|
* Set it to false to ignore the extension. Might be null in case the file is going to be
|
|
|
|
|
* stashed.
|
2016-09-19 01:39:59 +00:00
|
|
|
* @return array
|
|
|
|
|
* @since 1.28
|
|
|
|
|
*/
|
|
|
|
|
public function getPropsFromPath( $path, $ext ) {
|
|
|
|
|
$fsFile = new FSFile( $path );
|
|
|
|
|
|
2016-09-19 02:05:48 +00:00
|
|
|
$info = $this->newPlaceholderProps();
|
2016-09-19 01:39:59 +00:00
|
|
|
$info['fileExists'] = $fsFile->exists();
|
|
|
|
|
if ( $info['fileExists'] ) {
|
|
|
|
|
$info['size'] = $fsFile->getSize(); // bytes
|
|
|
|
|
$info['sha1'] = $fsFile->getSha1Base36();
|
|
|
|
|
|
|
|
|
|
# MIME type according to file contents
|
|
|
|
|
$info['file-mime'] = $this->magic->guessMimeType( $path, false );
|
|
|
|
|
# Logical MIME type
|
2021-02-02 00:49:06 +00:00
|
|
|
$ext = ( $ext === true ) ? FileBackend::extensionFromPath( $path ) : (string)$ext;
|
2020-05-24 15:42:15 +00:00
|
|
|
|
|
|
|
|
# XXX: MimeAnalyzer::improveTypeFromExtension() may return null (T253483).
|
|
|
|
|
# Unclear if callers of this method expect that.
|
2016-09-19 01:39:59 +00:00
|
|
|
$info['mime'] = $this->magic->improveTypeFromExtension( $info['file-mime'], $ext );
|
|
|
|
|
|
|
|
|
|
[ $info['major_mime'], $info['minor_mime'] ] = File::splitMime( $info['mime'] );
|
|
|
|
|
$info['media_type'] = $this->magic->getMediaType( $path, $info['mime'] );
|
|
|
|
|
|
|
|
|
|
# Height, width and metadata
|
2021-10-25 19:15:52 +00:00
|
|
|
// @phan-suppress-next-line PhanTypeMismatchArgumentNullable See XXX above
|
2016-09-19 01:39:59 +00:00
|
|
|
$handler = MediaHandler::getHandler( $info['mime'] );
|
|
|
|
|
if ( $handler ) {
|
Use the unserialized form of image metadata internally
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
2021-05-19 00:24:32 +00:00
|
|
|
$sizeAndMetadata = $handler->getSizeAndMetadataWithFallback( $fsFile, $path );
|
|
|
|
|
if ( $sizeAndMetadata ) {
|
|
|
|
|
$info = $sizeAndMetadata + $info;
|
2016-09-19 01:39:59 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return $info;
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-19 02:05:48 +00:00
|
|
|
/**
|
|
|
|
|
* Empty place holder props for non-existing files
|
|
|
|
|
*
|
|
|
|
|
* Resulting array fields include:
|
|
|
|
|
* - fileExists
|
|
|
|
|
* - size (filesize in bytes)
|
|
|
|
|
* - mime (as major/minor)
|
|
|
|
|
* - media_type (value to be used with the MEDIATYPE_xxx constants)
|
|
|
|
|
* - metadata (handler specific)
|
|
|
|
|
* - sha1 (in base 36)
|
|
|
|
|
* - width
|
|
|
|
|
* - height
|
|
|
|
|
* - bits (bitrate)
|
|
|
|
|
* - file-mime
|
|
|
|
|
* - major_mime
|
|
|
|
|
* - minor_mime
|
|
|
|
|
*
|
|
|
|
|
* @return array
|
|
|
|
|
* @since 1.28
|
|
|
|
|
*/
|
|
|
|
|
public function newPlaceholderProps() {
|
|
|
|
|
return FSFile::placeholderProps() + [
|
Use the unserialized form of image metadata internally
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
2021-05-19 00:24:32 +00:00
|
|
|
'metadata' => [],
|
2016-09-19 02:05:48 +00:00
|
|
|
'width' => 0,
|
|
|
|
|
'height' => 0,
|
|
|
|
|
'bits' => 0,
|
|
|
|
|
'media_type' => MEDIATYPE_UNKNOWN
|
|
|
|
|
];
|
|
|
|
|
}
|
2016-09-19 01:39:59 +00:00
|
|
|
}
|