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
2 changes: 1 addition & 1 deletion doc/sphinx-guides/source/api/changelog.rst
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ This API changelog is experimental and we would love feedback on its usefulness.
v6.11
-----

- The Croissant :ref:`metadata export format <metadata-export-formats>` has been updated from version 1.0 to 1.1, which is reflected in the ``conformsTo`` property. ``@vocab`` and ``sc`` properties now use "http" as `recommended <https://github.com/mlcommons/croissant/pull/929#pullrequestreview-3079137662>`_. The unused ``wd`` property has been dropped.
- The Croissant :ref:`metadata export format <metadata-export-formats>` has been updated from version 1.0 to 1.1, which is reflected in the ``conformsTo`` property. The unused ``wd`` property has been dropped.

v6.10
-----
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
import java.util.Map;
import org.apache.commons.text.StringEscapeUtils;

// Validate with src/test/resources/croissant/validate.sh
public class CroissantExportUtil {

public static void exportDataset(
Expand All @@ -31,7 +32,7 @@ public static void exportDataset(
{
"@context": {
"@language": "en",
"@vocab": "http://schema.org/",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "cr:column",
"conformsTo": "dct:conformsTo",
Expand Down Expand Up @@ -70,7 +71,7 @@ public static void exportDataset(
"repeated": "cr:repeated",
"replace": "cr:replace",
"samplingRate": "cr:samplingRate",
"sc": "http://schema.org/",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
Expand Down
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"@context": {
"@language": "en",
"@vocab": "http://schema.org/",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "cr:column",
"conformsTo": "dct:conformsTo",
Expand Down Expand Up @@ -40,7 +40,7 @@
"repeated": "cr:repeated",
"replace": "cr:replace",
"samplingRate": "cr:samplingRate",
"sc": "http://schema.org/",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
Expand Down Expand Up @@ -800,4 +800,4 @@
]
}
]
}
}
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"@context": {
"@language": "en",
"@vocab": "http://schema.org/",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "cr:column",
"conformsTo": "dct:conformsTo",
Expand Down Expand Up @@ -40,7 +40,7 @@
"repeated": "cr:repeated",
"replace": "cr:replace",
"samplingRate": "cr:samplingRate",
"sc": "http://schema.org/",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
Expand Down
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"@context": {
"@language": "en",
"@vocab": "http://schema.org/",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "cr:column",
"conformsTo": "dct:conformsTo",
Expand Down Expand Up @@ -40,7 +40,7 @@
"repeated": "cr:repeated",
"replace": "cr:replace",
"samplingRate": "cr:samplingRate",
"sc": "http://schema.org/",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
Expand Down Expand Up @@ -91,4 +91,4 @@
"contentUrl": "http://localhost:8080/api/access/datafile/4"
}
]
}
}
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"@context": {
"@language": "en",
"@vocab": "http://schema.org/",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "cr:column",
"conformsTo": "dct:conformsTo",
Expand Down Expand Up @@ -40,7 +40,7 @@
"repeated": "cr:repeated",
"replace": "cr:replace",
"samplingRate": "cr:samplingRate",
"sc": "http://schema.org/",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
Expand Down
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"@context": {
"@language": "en",
"@vocab": "http://schema.org/",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "cr:column",
"conformsTo": "dct:conformsTo",
Expand Down Expand Up @@ -40,7 +40,7 @@
"repeated": "cr:repeated",
"replace": "cr:replace",
"samplingRate": "cr:samplingRate",
"sc": "http://schema.org/",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
Expand Down Expand Up @@ -80,4 +80,4 @@
},
"version": "1.0",
"citeAs": "@data{FK2/0CNXUJ_2025,author = {Ritter, Sylvester},publisher = {Root},title = {},year = {2025},url = {https://doi.org/10.5072/FK2/0CNXUJ}}"
}
}
4 changes: 2 additions & 2 deletions src/test/resources/croissant/max/expected/max-croissant.json
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"@context": {
"@language": "en",
"@vocab": "http://schema.org/",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "cr:column",
"conformsTo": "dct:conformsTo",
Expand Down Expand Up @@ -40,7 +40,7 @@
"repeated": "cr:repeated",
"replace": "cr:replace",
"samplingRate": "cr:samplingRate",
"sc": "http://schema.org/",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
Expand Down
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"@context": {
"@language": "en",
"@vocab": "http://schema.org/",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "cr:column",
"conformsTo": "dct:conformsTo",
Expand Down Expand Up @@ -40,7 +40,7 @@
"repeated": "cr:repeated",
"replace": "cr:replace",
"samplingRate": "cr:samplingRate",
"sc": "http://schema.org/",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
Expand Down
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"@context": {
"@language": "en",
"@vocab": "http://schema.org/",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "cr:column",
"conformsTo": "dct:conformsTo",
Expand Down Expand Up @@ -40,7 +40,7 @@
"repeated": "cr:repeated",
"replace": "cr:replace",
"samplingRate": "cr:samplingRate",
"sc": "http://schema.org/",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
Expand Down
1 change: 1 addition & 0 deletions src/test/resources/croissant/requirements.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
mlcroissant==1.0.22
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"@context": {
"@language": "en",
"@vocab": "http://schema.org/",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "cr:column",
"conformsTo": "dct:conformsTo",
Expand Down Expand Up @@ -40,7 +40,7 @@
"repeated": "cr:repeated",
"replace": "cr:replace",
"samplingRate": "cr:samplingRate",
"sc": "http://schema.org/",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
Expand Down Expand Up @@ -112,4 +112,4 @@
"contentUrl": "http://localhost:8080/api/access/datafile/8"
}
]
}
}
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"@context": {
"@language": "en",
"@vocab": "http://schema.org/",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "cr:column",
"conformsTo": "dct:conformsTo",
Expand Down Expand Up @@ -40,7 +40,7 @@
"repeated": "cr:repeated",
"replace": "cr:replace",
"samplingRate": "cr:samplingRate",
"sc": "http://schema.org/",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
Expand Down
10 changes: 10 additions & 0 deletions src/test/resources/croissant/validate.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
#!/bin/sh
# Check datasets with this tool as well: https://huggingface.co/spaces/JoaquinVanschoren/croissant-checker
#
# Following warnings are expected for drafts.
# - [Metadata(Draft Dataset)] Property "https://schema.org/datePublished" is recommended, but does not exist.
# - [Metadata(Draft Dataset)] WarningException("Version doesn't follow MAJOR.MINOR.PATCH: DRAFT. For more information refer to: https://semver.org/spec/v2.0.0.html")
for i in */expected/*.json; do
echo testing $i
mlcroissant validate --jsonld $i
done
Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm just putting this at the bottom of the PR... https://jenkins.dataverse.org/job/IQSS-Dataverse-Develop-PR/job/PR-12333/1/consoleFull shows a failure to deploy the EC2 instance so I kicked off another run: https://jenkins.dataverse.org/job/IQSS-Dataverse-Develop-PR/job/PR-12333/2/

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Loading