change http back to https to make mlcroissant validate happy #12014

pdurbin · pdurbin · commit 3438462b4dd0 · 2026-04-15T17:51:24.000-04:00
This commit reverts 9e619b6 from #12214. We were following the Croissant 1.1 spec but there's a mismatch between it and `mlcroissant validate`. We've opened this issue upstream: mlcommons/croissant#1018
diff --git a/doc/sphinx-guides/source/api/changelog.rst b/doc/sphinx-guides/source/api/changelog.rst
@@ -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
 -----
diff --git a/src/main/java/edu/harvard/iq/dataverse/export/croissant/CroissantExportUtil.java b/src/main/java/edu/harvard/iq/dataverse/export/croissant/CroissantExportUtil.java
@@ -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(
@@ -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",
@@ -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",
diff --git a/src/test/resources/croissant/cars/expected/cars-croissant.json b/src/test/resources/croissant/cars/expected/cars-croissant.json
@@ -1,7 +1,7 @@
 {
     "@context": {
         "@language": "en",
-        "@vocab": "http://schema.org/",
+        "@vocab": "https://schema.org/",
         "citeAs": "cr:citeAs",
         "column": "cr:column",
         "conformsTo": "dct:conformsTo",
@@ -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",
@@ -800,4 +800,4 @@
             ]
         }
     ]
-}
+}
diff --git a/src/test/resources/croissant/cars/expected/cars-croissantSlim.json b/src/test/resources/croissant/cars/expected/cars-croissantSlim.json
@@ -1,7 +1,7 @@
 {
     "@context": {
         "@language": "en",
-        "@vocab": "http://schema.org/",
+        "@vocab": "https://schema.org/",
         "citeAs": "cr:citeAs",
         "column": "cr:column",
         "conformsTo": "dct:conformsTo",
@@ -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",
diff --git a/src/test/resources/croissant/draft/expected/draft-croissant.json b/src/test/resources/croissant/draft/expected/draft-croissant.json
@@ -1,7 +1,7 @@
 {
     "@context": {
         "@language": "en",
-        "@vocab": "http://schema.org/",
+        "@vocab": "https://schema.org/",
         "citeAs": "cr:citeAs",
         "column": "cr:column",
         "conformsTo": "dct:conformsTo",
@@ -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",
@@ -91,4 +91,4 @@
             "contentUrl": "http://localhost:8080/api/access/datafile/4"
         }
     ]
-}
+}
diff --git a/src/test/resources/croissant/draft/expected/draft-croissantSlim.json b/src/test/resources/croissant/draft/expected/draft-croissantSlim.json
@@ -1,7 +1,7 @@
 {
     "@context": {
         "@language": "en",
-        "@vocab": "http://schema.org/",
+        "@vocab": "https://schema.org/",
         "citeAs": "cr:citeAs",
         "column": "cr:column",
         "conformsTo": "dct:conformsTo",
@@ -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",
diff --git a/src/test/resources/croissant/junk/expected/junk-croissant.json b/src/test/resources/croissant/junk/expected/junk-croissant.json
@@ -1,7 +1,7 @@
 {
     "@context": {
         "@language": "en",
-        "@vocab": "http://schema.org/",
+        "@vocab": "https://schema.org/",
         "citeAs": "cr:citeAs",
         "column": "cr:column",
         "conformsTo": "dct:conformsTo",
@@ -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",
@@ -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}}"
-}
+}
diff --git a/src/test/resources/croissant/max/expected/max-croissant.json b/src/test/resources/croissant/max/expected/max-croissant.json
@@ -1,7 +1,7 @@
 {
     "@context": {
         "@language": "en",
-        "@vocab": "http://schema.org/",
+        "@vocab": "https://schema.org/",
         "citeAs": "cr:citeAs",
         "column": "cr:column",
         "conformsTo": "dct:conformsTo",
@@ -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",
diff --git a/src/test/resources/croissant/max/expected/max-croissantSlim.json b/src/test/resources/croissant/max/expected/max-croissantSlim.json
@@ -1,7 +1,7 @@
 {
     "@context": {
         "@language": "en",
-        "@vocab": "http://schema.org/",
+        "@vocab": "https://schema.org/",
         "citeAs": "cr:citeAs",
         "column": "cr:column",
         "conformsTo": "dct:conformsTo",
@@ -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",
diff --git a/src/test/resources/croissant/minimal/expected/minimal-croissant.json b/src/test/resources/croissant/minimal/expected/minimal-croissant.json
@@ -1,7 +1,7 @@
 {
     "@context": {
         "@language": "en",
-        "@vocab": "http://schema.org/",
+        "@vocab": "https://schema.org/",
         "citeAs": "cr:citeAs",
         "column": "cr:column",
         "conformsTo": "dct:conformsTo",
@@ -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",
diff --git a/src/test/resources/croissant/requirements.txt b/src/test/resources/croissant/requirements.txt
@@ -0,0 +1 @@
+mlcroissant==1.0.22
diff --git a/src/test/resources/croissant/restricted/expected/restricted-croissant.json b/src/test/resources/croissant/restricted/expected/restricted-croissant.json
@@ -1,7 +1,7 @@
 {
     "@context": {
         "@language": "en",
-        "@vocab": "http://schema.org/",
+        "@vocab": "https://schema.org/",
         "citeAs": "cr:citeAs",
         "column": "cr:column",
         "conformsTo": "dct:conformsTo",
@@ -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",
@@ -112,4 +112,4 @@
             "contentUrl": "http://localhost:8080/api/access/datafile/8"
         }
     ]
-}
+}
diff --git a/src/test/resources/croissant/restricted/expected/restricted-croissantSlim.json b/src/test/resources/croissant/restricted/expected/restricted-croissantSlim.json
@@ -1,7 +1,7 @@
 {
     "@context": {
         "@language": "en",
-        "@vocab": "http://schema.org/",
+        "@vocab": "https://schema.org/",
         "citeAs": "cr:citeAs",
         "column": "cr:column",
         "conformsTo": "dct:conformsTo",
@@ -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",
diff --git a/src/test/resources/croissant/validate.sh b/src/test/resources/croissant/validate.sh
@@ -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

Original file line number	Diff line number	Diff line change
`@@ -1,7 +1,7 @@`
`1`	`1`	`{`
`2`	`2`	`"@context": {`
`3`	`3`	`"@language": "en",`
`4`		`- "@vocab": "http://schema.org/",`
	`4`	`+ "@vocab": "https://schema.org/",`
`5`	`5`	`"citeAs": "cr:citeAs",`
`6`	`6`	`"column": "cr:column",`
`7`	`7`	`"conformsTo": "dct:conformsTo",`
`@@ -40,7 +40,7 @@`
`40`	`40`	`"repeated": "cr:repeated",`
`41`	`41`	`"replace": "cr:replace",`
`42`	`42`	`"samplingRate": "cr:samplingRate",`
`43`		`- "sc": "http://schema.org/",`
	`43`	`+ "sc": "https://schema.org/",`
`44`	`44`	`"separator": "cr:separator",`
`45`	`45`	`"source": "cr:source",`
`46`	`46`	`"subField": "cr:subField",`
`@@ -800,4 +800,4 @@`
`800`	`800`	`]`
`801`	`801`	`}`
`802`	`802`	`]`
`803`		`-}`
	`803`	`+}`