Skip to content

Commit

Permalink
Fix #92: simplexml should not throw error on string parsing
Browse files Browse the repository at this point in the history
  • Loading branch information
mhor committed Jan 23, 2020
1 parent bb3a69c commit aca1198
Show file tree
Hide file tree
Showing 3 changed files with 180 additions and 1 deletion.
12 changes: 11 additions & 1 deletion src/Parser/AbstractXmlOutputParser.php
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,17 @@ protected function transformXmlToArray($xmlString)
$xmlString = utf8_encode($xmlString);
}

$xml = simplexml_load_string($xmlString);
libxml_use_internal_errors(true);
$dom = new \DOMDocument('1.0', 'UTF-8');
$dom->strictErrorChecking = false;
$dom->validateOnParse = false;
$dom->recover = true;
$dom->loadXML($xmlString);
$xml = simplexml_import_dom($dom);

libxml_clear_errors();
libxml_use_internal_errors(false);

$json = json_encode($xml);

return json_decode($json, true);
Expand Down
15 changes: 15 additions & 0 deletions test/Parser/MediaInfoOutputParserTest.php
Original file line number Diff line number Diff line change
Expand Up @@ -21,11 +21,17 @@ class MediaInfoOutputParserTest extends \PHPUnit_Framework_TestCase
*/
private $outputMediainfo1710Path;

/**
* @var string
*/
private $invalidEncodingOutputPath;

public function setUp()
{
$this->outputPath = __DIR__.'/../fixtures/mediainfo-output.xml';
$this->outputMediainfo1710Path = __DIR__.'/../fixtures/mediainfo-17.10-output.xml';
$this->invalidOutputPath = __DIR__.'/../fixtures/mediainfo-output-invalid-types.xml';
$this->invalidEncodingOutputPath = __DIR__.'/../fixtures/mediainfo-output-invalid-encoding.xml';
}

/**
Expand Down Expand Up @@ -92,4 +98,13 @@ public function testThrowInvalidTrackType()
// will throw exception here as default behavior
$mediaInfoContainer = $mediaInfoOutputParser->getMediaInfoContainer();
}

public function testIgnoreInvalidEncodingErrors()
{
$mediaInfoOutputParser = new MediaInfoOutputParser();
$mediaInfoOutputParser->parse(file_get_contents($this->invalidEncodingOutputPath));
// xml string in file contains bad encoded characters, on parsing simplexml should not
// throw an error
$mediaInfoContainer = $mediaInfoOutputParser->getMediaInfoContainer(true);
}
}
154 changes: 154 additions & 0 deletions test/fixtures/mediainfo-output-invalid-encoding.xml
Original file line number Diff line number Diff line change
@@ -0,0 +1,154 @@
<?xml version="1.0" encoding="UTF-8"?>
<Mediainfo version="19.09">
<File>
<track type="General">
<Count>331</Count>
<Count_of_stream_of_this_kind>1</Count_of_stream_of_this_kind>
<Kind_of_stream>General</Kind_of_stream>
<Kind_of_stream>General</Kind_of_stream>
<Stream_identifier>0</Stream_identifier>
<Count_of_video_streams>1</Count_of_video_streams>
<Count_of_audio_streams>1</Count_of_audio_streams>
<Video_Format_List>VC-1</Video_Format_List>
<Video_Format_WithHint_List>VC-1 (WMV3)</Video_Format_WithHint_List>
<Codecs_Video>VC-1</Codecs_Video>
<Audio_Format_List>WMA</Audio_Format_List>
<Audio_Format_WithHint_List>WMA</Audio_Format_WithHint_List>
<Audio_codecs>WMA</Audio_codecs>
<Complete_name>/mnt/ramdisk/5/54c9f93b-8550-4100-8eeb-328841dc00d6/782247_ohrly-rh131aaso.wmv</Complete_name>
<Folder_name>/mnt/ramdisk/5/54c9f93b-8550-4100-8eeb-328841dc00d6</Folder_name>
<File_name_extension>782247_ohrly-rh131aaso.wmv</File_name_extension>
<File_name>782247_ohrly-rh131aaso</File_name>
<File_extension>wmv</File_extension>
<Format>Windows Media</Format>
<Format>Windows Media</Format>
<Format_Extensions_usually_used>asf dvr-ms wma wmv</Format_Extensions_usually_used>
<Commercial_name>Windows Media</Commercial_name>
<Internet_media_type>video/x-ms-wmv</Internet_media_type>
<File_size>760169</File_size>
<File_size>742 KiB</File_size>
<File_size>742 KiB</File_size>
<File_size>742 KiB</File_size>
<File_size>742 KiB</File_size>
<File_size>742.4 KiB</File_size>
<Duration>489056</Duration>
<Duration>8 min 9 s</Duration>
<Duration>8 min 9 s 56 ms</Duration>
<Duration>8 min 9 s</Duration>
<Duration>00:08:09.056</Duration>
<Duration>00:08:09;03</Duration>
<Duration>00:08:09.056 (00:08:09;03)</Duration>
<Overall_bit_rate>12435</Overall_bit_rate>
<Overall_bit_rate>12.4 kb/s</Overall_bit_rate>
<Maximum_Overall_bit_rate>5136894</Maximum_Overall_bit_rate>
<Maximum_Overall_bit_rate>5 137 kb/s</Maximum_Overall_bit_rate>
<Frame_rate>29.970</Frame_rate>
<Frame_rate>29.970 FPS</Frame_rate>
<Frame_count>14657</Frame_count>
<HeaderSize>1046</HeaderSize>
<DataSize>759123</DataSize>
<Performer>Ron Harris</Performer>
<Encoded_date>UTC 2012-05-14 00:53:44.000</Encoded_date>
<File_last_modification_date>UTC 2019-12-17 17:20:55</File_last_modification_date>
<File_last_modification_date__local_>2019-12-17 18:20:55</File_last_modification_date__local_>
<Copyright> ￾ </Copyright>
<Comment>HD Videos</Comment>
</track>
<track type="Video">
<Count>377</Count>
<Count_of_stream_of_this_kind>1</Count_of_stream_of_this_kind>
<Kind_of_stream>Video</Kind_of_stream>
<Kind_of_stream>Video</Kind_of_stream>
<Stream_identifier>0</Stream_identifier>
<StreamOrder>0</StreamOrder>
<ID>1</ID>
<ID>1</ID>
<Format>VC-1</Format>
<Format>VC-1</Format>
<Commercial_name>VC-1</Commercial_name>
<Format_profile>Main</Format_profile>
<Internet_media_type>video/vc1</Internet_media_type>
<Codec_ID>WMV3</Codec_ID>
<Codec_ID_Info>Windows Media Video 9</Codec_ID_Info>
<Codec_ID_Hint>WMV3</Codec_ID_Hint>
<Codec_ID_Url>http://www.microsoft.com/windows/windowsmedia/format/codecdownload.aspx</Codec_ID_Url>
<Description_of_the_codec>Windows Media Video 9 - 2-pass VBR</Description_of_the_codec>
<Duration>489056</Duration>
<Duration>8 min 9 s</Duration>
<Duration>8 min 9 s 56 ms</Duration>
<Duration>8 min 9 s</Duration>
<Duration>00:08:09.056</Duration>
<Duration>00:08:09;03</Duration>
<Duration>00:08:09.056 (00:08:09;03)</Duration>
<Bit_rate>5000000</Bit_rate>
<Bit_rate>5 000 kb/s</Bit_rate>
<Width>1920</Width>
<Width>1 920 pixels</Width>
<Height>1080</Height>
<Height>1 080 pixels</Height>
<Pixel_aspect_ratio>1.000</Pixel_aspect_ratio>
<Display_aspect_ratio>1.778</Display_aspect_ratio>
<Display_aspect_ratio>16:9</Display_aspect_ratio>
<Frame_rate>29.970</Frame_rate>
<Frame_rate>29.970 (29970/1000) FPS</Frame_rate>
<FrameRate_Num>29970</FrameRate_Num>
<FrameRate_Den>1000</FrameRate_Den>
<Frame_count>14657</Frame_count>
<Color_space>YUV</Color_space>
<Chroma_subsampling>4:2:0</Chroma_subsampling>
<Chroma_subsampling>4:2:0</Chroma_subsampling>
<Bit_depth>8</Bit_depth>
<Bit_depth>8 bits</Bit_depth>
<Scan_type>Progressive</Scan_type>
<Scan_type>Progressive</Scan_type>
<Compression_mode>Lossy</Compression_mode>
<Compression_mode>Lossy</Compression_mode>
<Bits__Pixel_Frame_>0.080</Bits__Pixel_Frame_>
<Stream_size>305660000</Stream_size>
<Stream_size>292 MiB</Stream_size>
<Stream_size>292 MiB</Stream_size>
<Stream_size>292 MiB</Stream_size>
<Stream_size>292 MiB</Stream_size>
<Stream_size>291.5 MiB</Stream_size>
</track>
<track type="Audio">
<Count>280</Count>
<Count_of_stream_of_this_kind>1</Count_of_stream_of_this_kind>
<Kind_of_stream>Audio</Kind_of_stream>
<Kind_of_stream>Audio</Kind_of_stream>
<Stream_identifier>0</Stream_identifier>
<StreamOrder>1</StreamOrder>
<ID>2</ID>
<ID>2</ID>
<Format>WMA</Format>
<Format>WMA</Format>
<Commercial_name>WMA</Commercial_name>
<Format_version>Version 2</Format_version>
<Codec_ID>161</Codec_ID>
<Codec_ID_Info>Windows Media Audio</Codec_ID_Info>
<Codec_ID_Url>http://www.microsoft.com/windows/windowsmedia/format/codecdownload.aspx</Codec_ID_Url>
<Description_of_the_codec>Windows Media Audio 9 - 128 kbps, 44 kHz, stereo CBR</Description_of_the_codec>
<Duration>489056</Duration>
<Duration>8 min 9 s</Duration>
<Duration>8 min 9 s 56 ms</Duration>
<Duration>8 min 9 s</Duration>
<Duration>00:08:09.056</Duration>
<Duration>00:08:09.056</Duration>
<Bit_rate>128000</Bit_rate>
<Bit_rate>128 kb/s</Bit_rate>
<Channel_s_>2</Channel_s_>
<Channel_s_>2 channels</Channel_s_>
<Sampling_rate>44100</Sampling_rate>
<Sampling_rate>44.1 kHz</Sampling_rate>
<Samples_count>21567370</Samples_count>
<Bit_depth>16</Bit_depth>
<Bit_depth>16 bits</Bit_depth>
<Stream_size>7824896</Stream_size>
<Stream_size>7.46 MiB</Stream_size>
<Stream_size>7 MiB</Stream_size>
<Stream_size>7.5 MiB</Stream_size>
<Stream_size>7.46 MiB</Stream_size>
<Stream_size>7.462 MiB</Stream_size>
</track>
</File>
</Mediainfo>

0 comments on commit aca1198

Please sign in to comment.