Update ttl definition for Croissant 1.1. Minor spec clean-ups.

Author: benjelloun

docs/croissant-spec-draft.md

@@ -1157,11 +1157,10 @@ Sometimes, not all the data from the source is needed, but only a subset. The `E
 
 Croissant supports a few simple transformations that can be applied on the source data:
 
-- delimiter: split a string into an array using the supplied character.
+- separator: split a string into an array using the supplied character.
 - readLines: read the content of the file line by line.
 - unArchive: extract the content of the archive. True by default for archive file types (zip, tgz, etc.).
-- regex: A regular expression to parse the data.
-- jsonPath: A JSON path to evaluate on the (JSON) data source.
+- regex: A regular expression to parse the data, with one capture group that corresponds to the output value.
 
 For example, to extract information from a filename using a regular expression, we can write:
 
@@ -2283,6 +2282,7 @@ This approach can be extended to other domain-specific ontologies.
     "cr": "http://mlcommons.org/croissant/",
     "rai": "http://mlcommons.org/croissant/RAI/",
     "dct": "http://purl.org/dc/terms/",
+    "annotation": "cr:annotation",
     "arrayShape": "cr:arrayShape",
     "citeAs": "cr:citeAs",
     "column": "cr:column",
@@ -2296,10 +2296,13 @@ This approach can be extended to other domain-specific ontologies.
       "@id": "cr:dataType",
       "@type": "@vocab"
     },
+    "separator": "cr:separator",
+    "equivalentProperty": "cr:equivalentProperty",
     "examples": {
       "@id": "cr:examples",
       "@type": "@json"
     },
+    "excludes": "cr:excludes",
     "extract": "cr:extract",
     "field": "cr:field",
     "fileProperty": "cr:fileProperty",
@@ -2313,14 +2316,16 @@ This approach can be extended to other domain-specific ontologies.
     "key": "cr:key",
     "md5": "cr:md5",
     "parentField": "cr:parentField",
-    "path": "cr:path",
     "recordSet": "cr:recordSet",
     "references": "cr:references",
     "regex": "cr:regex",
-    "replace": "cr:replace",
+    "readLines": "cr:readLines",
+    "sdVersion": "cr:sdVersion",
     "separator": "cr:separator",
     "source": "cr:source",
     "subField": "cr:subField",
-    "transform": "cr:transform"
+    "transform": "cr:transform",
+    "unArchive": "cr:unArchive",
+    "value": "cr:value",
   }
 ```

docs/croissant.ttl

@@ -8,12 +8,12 @@
 croissant:FileObject a rdf:Class ;
   rdfs:label "FileObject" ;
   rdfs:comment "An individual file that is part of a dataset." ;
-  rdfs:subClassOf schema:CreativeWork .
+  rdfs:subClassOf schema:DataDownload .
 
 croissant:FileSet a rdf:Class ;
   rdfs:label "FileSet" ;
   rdfs:comment "A set of homogeneous files extracted from a container, optionally filtered by inclusion and/or exclusion filters." ;
-  rdfs:subClassOf schema:Intangible .
+  rdfs:subClassOf schema:DataDownload .
 
 croissant:RecordSet a rdf:Class ;
   rdfs:label "RecordSet" ;
@@ -84,21 +84,33 @@ croissant:citeAs a rdf:Property ;
   schema:domainIncludes schema:Dataset ;
   schema:rangeIncludes schema:Text .
 
+croissant:md5 a rdf:Property ;
+  rdfs:label "md5" ;
+  rdfs:comment "The MD5 hash of the file." ;
+  schema:domainIncludes croissant:FileObject ;
+  schema:rangeIncludes schema:Text .
+
+croissant:sdVersion a rdf:Property ;
+  rdfs:label "sdVersion" ;
+  rdfs:comment "The version of the dataset metadata, which may be distinct from the version of the dataset content." ;
+  schema:domainIncludes schema:Dataset ;
+  schema:rangeIncludes schema:Number, schema:Text .
+
 # FileObject & FileSet properties
 
 croissant:containedIn a rdf:Property ;
   rdfs:label "containedIn" ;
-  rdfs:comment "Another FileObject or FileSet that this one is contained in, e.g., in the case of a file extracted from an archive. When this property is present, the contentUrl is evaluated as a relative path within the container object." ;
+  rdfs:comment "Another FileObject, FileSet or DataSource that this one is contained in, e.g., in the case of a file extracted from an archive. When this property is present, the contentUrl is evaluated as a relative path within the container object." ;
   schema:domainIncludes croissant:FileObject, croissant:FileSet ;
-  schema:rangeIncludes croissant:FileObject, croissant:FileSet .
+  schema:rangeIncludes croissant:FileObject, croissant:FileSet, croissant:DataSource .
 
-croissant:includes a rdf:Property ; # Should this be named includePattern instead?
+croissant:includes a rdf:Property ;
   rdfs:label "includes" ;
   rdfs:comment "A glob pattern that specifies the files to include, e.g., \".jpg\", \"/foo/pic*.jpg\". The pattern is evaluated from the root of the containedIn contents." ;
   schema:domainIncludes croissant:FileSet ;
   schema:rangeIncludes schema:Text .
 
-croissant:excludes a rdf:Property ; # Should this be named excludePattern instead?
+croissant:excludes a rdf:Property ;
   rdfs:label "excludes" ;
   rdfs:comment "A glob pattern that specifies the files to exclude. The pattern is evaluated from the root of the containedIn contents, after the includes patterns have been evaluated." ;
   schema:domainIncludes croissant:FileSet ;
@@ -130,6 +142,12 @@ croissant:examples a rdf:Property ;
   schema:domainIncludes croissant:RecordSet ;
   schema:rangeIncludes rdf:JSON .
 
+croissant:annotation a rdf:Property ;
+  rdfs:label "annotation" ;
+  rdfs:comment "One or more data-level annotations that apply to the entire record or field." ;
+  schema:domainIncludes croissant:RecordSet, croissant:Field ;
+  schema:rangeIncludes croissant:Field .
+
 croissant:source a rdf:Property ;
   rdfs:label "source" ;
   rdfs:comment "The data source of the field. This will generally reference a FileObject or FileSet's contents (e.g., a specific column of a table)." ;
@@ -142,6 +160,12 @@ croissant:dataType a rdf:Property ;
   schema:domainIncludes croissant:RecordSet, croissant:Field ;
   schema:rangeIncludes croissant:DataType .
 
+croissant:value a rdf:Property ;
+  rdfs:label "value" ;
+  rdfs:comment "An optional constant value for the field." ;
+  schema:domainIncludes croissant:Field ;
+  schema:rangeIncludes rdf:JSON .
+
 croissant:repeated a rdf:Property ;
   rdfs:label "repeated" ;
   rdfs:comment "If true, then the Field is a list of values of type dataType." ;
@@ -238,24 +262,30 @@ croissant:jsonPath a rdf:Property ;
 
 # Transform properties
 
-croissant:delimiter a rdf:Property ;
-  rdfs:label "delimiter" ;
-  rdfs:comment "A delimiter to use parse the data into an array." ;
+croissant:separator a rdf:Property ;
+  rdfs:label "separator" ;
+  rdfs:comment "A separator to use parse the data into an array." ;
   schema:domainIncludes croissant:Transform ;
   schema:rangeIncludes schema:Text .
 
+croissant:readLines a rdf:Property ;
+  rdfs:label "readLines" ;
+  rdfs:comment "Read the content of the file line by line." ;
+  schema:domainIncludes croissant:Transform ;
+  schema:rangeIncludes schema:Boolean .
+
+croissant:unArchive a rdf:Property ;
+  rdfs:label "unArchive" ;
+  rdfs:comment "Extract the content of the archive." ;
+  schema:domainIncludes croissant:Transform ;
+  schema:rangeIncludes schema:Boolean .
+
 croissant:regex a rdf:Property ;
   rdfs:label "regex" ;
   rdfs:comment "A regular expression to apply to the data." ;
   schema:domainIncludes croissant:Transform ;
   schema:rangeIncludes schema:Text .
 
-croissant:jsonQuery a rdf:Property ;
-  rdfs:label "jsonQuery" ;
-  rdfs:comment "For JSON content, a query to evaluate on the data." ;
-  schema:domainIncludes croissant:Transform ;
-  schema:rangeIncludes schema:Text .
-
 ### ML-specific definitions
 
 croissant:Split a rdf:class ;