Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -0,0 +1,77 @@
<mets:mets xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mets="http://www.loc.gov/METS/" xsi:schemaLocation="http://www.loc.gov/METS/ http://www.loc.gov/standards/mets/version1121/mets.xsd">
<mets:metsHdr CREATEDATE="2025-10-28T19:07:44"/>
<mets:dmdSec ID="dmdSec_1" CREATED="2025-10-28T19:07:44" STATUS="original">
<mets:mdWrap MDTYPE="PREMIS:OBJECT">
<mets:xmlData>
<premis:object xmlns:premis="http://www.loc.gov/premis/v3" xsi:type="premis:intellectualEntity" xsi:schemaLocation="http://www.loc.gov/premis/v3 http://www.loc.gov/standards/premis/v3/premis.xsd" version="3.0">
<premis:objectIdentifier>
<premis:objectIdentifierType>UUID</premis:objectIdentifierType>
<premis:objectIdentifierValue>4a64ba7c-ceac-4547-ac13-c487b2711d5a</premis:objectIdentifierValue>
</premis:objectIdentifier>
<premis:originalName>test_video_upload-4a64ba7c-ceac-4547-ac13-c487b2711d5a</premis:originalName>
</premis:object>
</mets:xmlData>
</mets:mdWrap>
</mets:dmdSec>
<mets:amdSec ID="amdSec_1">
<mets:techMD ID="techMD_1">
<mets:mdWrap MDTYPE="PREMIS:OBJECT">
<mets:xmlData>
<premis:object xmlns:premis="http://www.loc.gov/premis/v3" xsi:type="premis:file" xsi:schemaLocation="http://www.loc.gov/premis/v3 http://www.loc.gov/standards/premis/v3/premis.xsd" version="3.0">
<premis:objectIdentifier>
<premis:objectIdentifierType>UUID</premis:objectIdentifierType>
<premis:objectIdentifierValue>b3c97850-9697-451a-8ad5-9f085188e890</premis:objectIdentifierValue>
</premis:objectIdentifier>
<premis:objectCharacteristics>
<premis:compositionLevel>0</premis:compositionLevel>
<premis:fixity>
<premis:messageDigestAlgorithm>sha256</premis:messageDigestAlgorithm>
<premis:messageDigest>abc123def456789</premis:messageDigest>
</premis:fixity>
<premis:size>5242880</premis:size>
<premis:format>
<premis:formatDesignation>
<premis:formatName>MPEG-4 Media File</premis:formatName>
<premis:formatVersion>2</premis:formatVersion>
</premis:formatDesignation>
<premis:formatRegistry>
<premis:formatRegistryName>PRONOM</premis:formatRegistryName>
<premis:formatRegistryKey>fmt/199</premis:formatRegistryKey>
</premis:formatRegistry>
</premis:format>
<premis:creatingApplication>
<premis:dateCreatedByApplication>2024-05-20T08:45:00Z</premis:dateCreatedByApplication>
</premis:creatingApplication>
<premis:objectCharacteristicsExtension>
<MediaInfo xmlns="https://mediaarea.net/mediainfo" xsi:schemaLocation="https://mediaarea.net/mediainfo https://mediaarea.net/mediainfo/mediainfo_2_0.xsd" version="2.0">
<creatingLibrary version="25.09" url="https://mediaarea.net/MediaInfo">MediaInfoLib</creatingLibrary>
<media ref="/var/archivematica/test_video.mp4">
<track type="General">
<Count>300</Count>
<StreamCount>1</StreamCount>
<StreamKind>General</StreamKind>
<StreamKind_String>General</StreamKind_String>
<StreamKindID>0</StreamKindID>
<Format>MPEG-4</Format>
<Format_String>MPEG-4</Format_String>
<InternetMediaType>video/mp4</InternetMediaType>
<FileSize>5242880</FileSize>
<Duration>120.5</Duration>
<File_Created_Date>2024-05-20 08:45:00 UTC</File_Created_Date>
</track>
</media>
</MediaInfo>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
<rdf:Description xmlns:File="http://ns.exiftool.org/File/1.0/" rdf:about="/var/archivematica/test_video.mp4">
<File:MIMEType>video/mp4</File:MIMEType>
</rdf:Description>
</rdf:RDF>
</premis:objectCharacteristicsExtension>
</premis:objectCharacteristics>
<premis:originalName>%transferDirectory%objects/4a64ba7c-ceac-4547-ac13-c487b2711d5a</premis:originalName>
</premis:object>
</mets:xmlData>
</mets:mdWrap>
</mets:techMD>
</mets:amdSec>
</mets:mets>
62 changes: 62 additions & 0 deletions packages/metadata_attacher/src/index.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -851,6 +851,68 @@ describe("handler", () => {
expect(recordMetadata?.altText).toEqual(null);
});

test("should extract timestamp from video with a single MediaInfo track object", async () => {
const metsContent = await loadMetsFile("video_mediainfo_single_track.xml");
mockS3Send.mockResolvedValue({
Body: {
transformToString: jest.fn().mockResolvedValue(metsContent),
},
});

const event = {
Records: [
{
messageId: "1",
receiptHandle: "1",
body: JSON.stringify({
Message: JSON.stringify({
Records: [
{
s3: {
bucket: {
name: "test-bucket",
},
object: {
key: "access_copies/53f9/8c3d/a29e/4fbf/8a4a/4fd9/991e/313d/1_upload-4a64ba7c-ceac-4547-ac13-c487b2711d5a/METS.4a64ba7c-ceac-4547-ac13-c487b2711d5a.xml",
},
},
},
],
}),
}),
attributes: {
ApproximateReceiveCount: "1",
SentTimestamp: "1",
SenderId: "1",
ApproximateFirstReceiveTimestamp: "1",
},
messageAttributes: {},
md5OfBody: "1",
eventSource: "1",
eventSourceARN: "1",
awsRegion: "1",
},
],
};

await handler(event, mock<Context>(), jest.fn());

expect(mockS3Send).toHaveBeenCalledTimes(1);

const recordMetadata = await getRecordMetadata("1");
expect(recordMetadata).toBeDefined();
expect(recordMetadata?.derivedTimestamp).toEqual(
new Date("2024-05-20T08:45:00.000Z"),
);
expect(recordMetadata?.originalFileCreationTime).toEqual(
"2024-05-20T08:45:00Z",
);
expect(recordMetadata?.displayName).toEqual("test_file.jpg");
expect(recordMetadata?.description).toEqual(null);
expect(recordMetadata?.tags.length).toEqual(0);
expect(recordMetadata?.altText).toEqual(null);
});

test("should handle video with no timestamp metadata", async () => {
const metsContent = await loadMetsFile("video_no_timestamp.xml");
mockS3Send.mockResolvedValue({
Expand Down
7 changes: 5 additions & 2 deletions packages/metadata_attacher/src/index.ts
Original file line number Diff line number Diff line change
Expand Up @@ -157,10 +157,13 @@ const getVideoMetadataFromMediaInfo = (
creationTimeInEdtf: string | undefined;
}
| undefined => {
const tracks = embeddedMetadata.MediaInfo?.media.track;
if (tracks === undefined) {
const tracksFromMediaInfo = embeddedMetadata.MediaInfo?.media.track;
if (tracksFromMediaInfo === undefined) {
return undefined;
}
const tracks = Array.isArray(tracksFromMediaInfo)
? tracksFromMediaInfo
: [tracksFromMediaInfo];

const generalTracks = tracks.filter(
(track: TrackMetadata) => track.StreamKind === "General",
Expand Down
2 changes: 1 addition & 1 deletion packages/metadata_attacher/src/models.ts
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,7 @@ export interface EmbeddedMetadata {
MediaInfo:
| {
media: {
track: TrackMetadata[];
track: TrackMetadata[] | TrackMetadata;
};
}
| undefined;
Expand Down
4 changes: 3 additions & 1 deletion packages/metadata_attacher/src/validators.ts
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,9 @@ const embeddedMetadataSchema = Joi.object({
.unknown(true),
MediaInfo: Joi.object({
media: Joi.object({
track: Joi.array().items(trackMetadataSchema).required(),
track: Joi.alternatives()
.try(Joi.array().items(trackMetadataSchema), trackMetadataSchema)
.required(),
})
.required()
.unknown(true),
Expand Down