Add support for additional media types #18054
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
|
|
@@ -5,6 +5,7 @@ | |||||
| import wave | ||||||
| from functools import lru_cache | ||||||
| from typing import ( | ||||||
| cast, | ||||||
| List, | ||||||
| Tuple, | ||||||
| ) | ||||||
|
|
@@ -32,6 +33,94 @@ def ffprobe(path): | |||||
| return data["format"], data["streams"] | ||||||
|
|
||||||
|
|
||||||
| magic_number = { | ||||||
| "mp4": { | ||||||
| "offset": 4, | ||||||
| "hex": [ | ||||||
| "66 74 79 70 69", | ||||||
| "66 74 79 70 6D", | ||||||
| "66 74 79 70 4D", | ||||||
| ], | ||||||
| }, | ||||||
| "flv": {"offset": 0, "hex": ["46 4C 56 01"]}, | ||||||
|
There was a problem hiding this comment. also by wikipedia's list, the magic should just be Since many of these are human readable strings (like
Suggested change
and then check the correct number of bytes based off of the length of the string or so, to not have to specify a 4th byte if it isn't relevant would reduce some of these long hex lists. |
||||||
| "mkv": {"offset": 0, "hex": ["1A 45 DF A3"]}, | ||||||
| "webm": {"offset": 0, "hex": ["1A 45 DF A3"]}, | ||||||
| "mov": {"offset": 4, "hex": ["66 74 79 70 71", "6D 6F 6F 76"]}, | ||||||
| "wav": {"offset": 8, "hex": ["57 41 56 45"]}, | ||||||
| "mp3": { | ||||||
| "offset": 0, | ||||||
| "hex": [ | ||||||
| "49 44 33", | ||||||
| "FF E0", | ||||||
| "FF E1", | ||||||
| "FF E2", | ||||||
| "FF E3", | ||||||
| "FF E4", | ||||||
| "FF E5", | ||||||
| "FF E6", | ||||||
| "FF E7", | ||||||
| "FF E8", | ||||||
| "FF E9", | ||||||
| "FF EA", | ||||||
| "FF EB", | ||||||
| "FF EC", | ||||||
| "FF ED", | ||||||
| "FF EE", | ||||||
| "FF EF", | ||||||
| "FF F0", | ||||||
| "FF F1", | ||||||
| "FF F2", | ||||||
| "FF F3", | ||||||
| "FF F4", | ||||||
| "FF F5", | ||||||
| "FF F6", | ||||||
| "FF F7", | ||||||
| "FF F8", | ||||||
| "FF F9", | ||||||
| "FF FA", | ||||||
| "FF FB", | ||||||
| "FF FC", | ||||||
| "FF FD", | ||||||
| "FF FE", | ||||||
| "FF FF", | ||||||
| ], | ||||||
| }, | ||||||
| "ogg": {"offset": 0, "hex": ["4F 67 67"]}, | ||||||
| "wma": {"offset": 0, "hex": ["30 26 B2 75"]}, | ||||||
| "wmv": {"offset": 0, "hex": ["30 26 B2 75"]}, | ||||||
| "avi": {"offset": 8, "hex": ["41 56 49"]}, | ||||||
| "mpg": { | ||||||
| "offset": 0, | ||||||
| "hex": [ | ||||||
| "00 00 01 B0", | ||||||
| "00 00 01 B1", | ||||||
| "00 00 01 B3", | ||||||
| "00 00 01 B4", | ||||||
| "00 00 01 B5", | ||||||
| "00 00 01 B6", | ||||||
| "00 00 01 B7", | ||||||
| "00 00 01 B8", | ||||||
| "00 00 01 B9", | ||||||
| "00 00 01 BA", | ||||||
|
There was a problem hiding this comment. are these all seen in practice? Wikipedia's list suggests it should be a much reduced set There was a problem hiding this comment. I was using this source:
|
||||||
| "00 00 01 BB", | ||||||
| "00 00 01 BC", | ||||||
| "00 00 01 BD", | ||||||
| "00 00 01 BE", | ||||||
| "00 00 01 BF", | ||||||
| ], | ||||||
| }, | ||||||
| } | ||||||
|
|
||||||
|
|
||||||
| def _get_file_format_from_magic_number(filename: str, file_ext: str): | ||||||
| with open(filename, "rb") as f: | ||||||
| f.seek(cast(int, magic_number[file_ext]["offset"])) | ||||||
| head = f.read(8) | ||||||
| return any( | ||||||
| head.startswith(bytes.fromhex(hex_code)) for hex_code in cast(List[str], magic_number[file_ext]["hex"]) | ||||||
| ) | ||||||
|
|
||||||
|
|
||||||
| class Audio(Binary): | ||||||
| MetadataElement( | ||||||
| name="duration", | ||||||
|
|
@@ -183,8 +272,11 @@ class Mkv(Video): | |||||
| def sniff(self, filename: str) -> bool: | ||||||
| if which("ffprobe"): | ||||||
| metadata, streams = ffprobe(filename) | ||||||
| vp_check = any( | ||||||
| stream["codec_name"] in ["av1", "vp8", "vp9"] for stream in streams if stream["codec_type"] == "video" | ||||||
| ) | ||||||
| return "matroska" in metadata["format_name"].split(",") and not vp_check | ||||||
| return _get_file_format_from_magic_number(filename, "mkv") | ||||||
|
|
||||||
|
|
||||||
| class Mp4(Video): | ||||||
|
|
@@ -200,8 +292,8 @@ class Mp4(Video): | |||||
| def sniff(self, filename: str) -> bool: | ||||||
| if which("ffprobe"): | ||||||
| metadata, streams = ffprobe(filename) | ||||||
| return "mp4" in metadata["format_name"].split(",") and _get_file_format_from_magic_number(filename, "mp4") | ||||||
| return _get_file_format_from_magic_number(filename, "mp4") | ||||||
|
|
||||||
|
|
||||||
| class Flv(Video): | ||||||
|
|
@@ -211,17 +303,7 @@ def sniff(self, filename: str) -> bool: | |||||
| if which("ffprobe"): | ||||||
| metadata, streams = ffprobe(filename) | ||||||
| return "flv" in metadata["format_name"].split(",") | ||||||
hexylena marked this conversation as resolved.
Show resolved
Hide resolved
|
||||||
| return _get_file_format_from_magic_number(filename, "flv") | ||||||
|
|
||||||
|
|
||||||
| class Mp3(Audio): | ||||||
|
|
@@ -240,7 +322,7 @@ def sniff(self, filename: str) -> bool: | |||||
| if which("ffprobe"): | ||||||
| metadata, streams = ffprobe(filename) | ||||||
| return "mp3" in metadata["format_name"].split(",") | ||||||
| return _get_file_format_from_magic_number(filename, "mp3") | ||||||
|
Comment on lines
-243
to
+338
There was a problem hiding this comment. but yes cases like this, instead of |
||||||
|
|
||||||
|
|
||||||
| class Wav(Audio): | ||||||
|
|
@@ -274,8 +356,7 @@ def get_mime(self) -> str: | |||||
| return "audio/wav" | ||||||
|
|
||||||
| def sniff(self, filename: str) -> bool: | ||||||
| return _get_file_format_from_magic_number(filename, "wav") | ||||||
|
|
||||||
| def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None: | ||||||
| """Set the metadata for this dataset from the file contents.""" | ||||||
|
|
@@ -287,3 +368,78 @@ def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> N | |||||
| dataset.metadata.nchannels = fd.getnchannels() | ||||||
| except wave.Error: | ||||||
| pass | ||||||
|
|
||||||
|
|
||||||
| class Ogg(Audio): | ||||||
| file_ext = "ogg" | ||||||
|
|
||||||
| def sniff(self, filename: str) -> bool: | ||||||
| if which("ffprobe"): | ||||||
| metadata, streams = ffprobe(filename) | ||||||
| return "ogg" in metadata["format_name"].split(",") | ||||||
| return _get_file_format_from_magic_number(filename, "ogg") | ||||||
|
|
||||||
|
|
||||||
| class Webm(Video): | ||||||
| file_ext = "webm" | ||||||
|
|
||||||
| def sniff(self, filename: str) -> bool: | ||||||
| if which("ffprobe"): | ||||||
| metadata, streams = ffprobe(filename) | ||||||
| vp_check = any( | ||||||
| stream["codec_name"] in ["av1", "vp8", "vp9"] for stream in streams if stream["codec_type"] == "video" | ||||||
| ) | ||||||
| return "webm" in metadata["format_name"].split(",") and vp_check | ||||||
| return _get_file_format_from_magic_number(filename, "webm") | ||||||
|
|
||||||
|
|
||||||
| class Mpg(Video): | ||||||
| file_ext = "mpg" | ||||||
|
|
||||||
| def sniff(self, filename: str) -> bool: | ||||||
| if which("ffprobe"): | ||||||
| metadata, streams = ffprobe(filename) | ||||||
| return "mpegvideo" in metadata["format_name"].split(",") | ||||||
| return _get_file_format_from_magic_number(filename, "mpg") | ||||||
|
|
||||||
|
|
||||||
| class Mov(Video): | ||||||
| file_ext = "mov" | ||||||
|
|
||||||
| def sniff(self, filename: str) -> bool: | ||||||
| if which("ffprobe"): | ||||||
| metadata, streams = ffprobe(filename) | ||||||
| return "mov" in metadata["format_name"].split(",") and _get_file_format_from_magic_number(filename, "mov") | ||||||
| return _get_file_format_from_magic_number(filename, "mov") | ||||||
|
|
||||||
|
|
||||||
| class Avi(Video): | ||||||
| file_ext = "avi" | ||||||
|
|
||||||
| def sniff(self, filename: str) -> bool: | ||||||
| if which("ffprobe"): | ||||||
| metadata, streams = ffprobe(filename) | ||||||
| return "avi" in metadata["format_name"].split(",") | ||||||
| return _get_file_format_from_magic_number(filename, "avi") | ||||||
|
|
||||||
|
|
||||||
| class Wmv(Video): | ||||||
| file_ext = "wmv" | ||||||
|
|
||||||
| def sniff(self, filename: str) -> bool: | ||||||
| if which("ffprobe"): | ||||||
| metadata, streams = ffprobe(filename) | ||||||
| is_video = "video" in [stream["codec_type"] for stream in streams] | ||||||
| return "asf" in metadata["format_name"].split(",") and is_video | ||||||
| return _get_file_format_from_magic_number(filename, "wmv") | ||||||
|
|
||||||
|
|
||||||
| class Wma(Audio): | ||||||
| file_ext = "wma" | ||||||
|
|
||||||
| def sniff(self, filename: str) -> bool: | ||||||
| if which("ffprobe"): | ||||||
| metadata, streams = ffprobe(filename) | ||||||
| is_audio = "video" not in [stream["codec_type"] for stream in streams] | ||||||
| return "asf" in metadata["format_name"].split(",") and is_audio | ||||||
| return _get_file_format_from_magic_number(filename, "wma") | ||||||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
https://en.wikipedia.org/wiki/List_of_file_signatures
6d is heic, not sure if you want to lump this in with mp4? (I assume you based this on files you had/have seen). Also might want to consider extending these magic numbers to include the whole string to avoid future false positives
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I wanted to grab m4v file format.
https://www.garykessler.net/library/file_sigs.html
But, you are right it will be missed with the heic I will change it to
66 74 79 70 6D 70 34 32.Also, I will consider extending the magic numbers.