Disallow properties with type array and no items (#1221)

* create meta schema 2.0.1 This contains a new check in row-meta-schema.json:152 which ensures that when a property has type "array", that "items" is also present. * fix README.md, so line can be copied from markdown preview. * add .vscode folder to .gitignore * rename to v2.1.0 * add check to new [email protected] * update .pre-commit config to use newest versions
Amsterdam · Jan 15, 2025 · 449541d · 449541d
1 parent 065e92f
commit 449541d
Show file tree

Hide file tree

Showing 23 changed files with 1,684 additions and 3 deletions.
diff --git a/.gitignore b/.gitignore
@@ -39,6 +39,7 @@ ENV/
 *.iml
 *.swp
 .DS_Store
+.vscode/
 
 /scratch
 datasets/index.json
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -56,10 +56,10 @@ repos:
     rev: "v5.14.2"
     hooks:
       - id: validate-schema
-        args: ['https://schemas.data.amsterdam.nl/schema@v1.3.0', "--extra_meta_schema_url", "https://schemas.data.amsterdam.nl/schema@v2"]
+        args: ['https://schemas.data.amsterdam.nl/schema@v1.4.0', "--extra_meta_schema_url", "https://schemas.data.amsterdam.nl/schema@v2.1.0"]
         files: '^datasets/.*\.json$'
         verbose: true # so we can see against which metaschema it is valid
         exclude: "^schema@.+" # exclude meta schemas
       - id: validate-publishers
-        args: ['https://schemas.data.amsterdam.nl/schema@v2', '--schema-url', './publishers']
+        args: ['https://schemas.data.amsterdam.nl/schema@v2.1.0', '--schema-url', './publishers']
         verbose: true # so we can see against which metaschema it is valid
diff --git a/README.md b/README.md
@@ -181,7 +181,7 @@ In order to develop a new metaschema version locally and run structural and sema
 4) generate-index > datasets/index.json
 
 *Point the references in the dataset that we will use for development to the devserver*  
-5) sed -i 's/https:\/\/schemas\.data\.amsterdam\.nl/http:\/\/localhost:8000/g' datasets/<some-dataset>/{,**/}*.json
+5) ```sed -i 's/https:\/\/schemas\.data\.amsterdam\.nl/http:\/\/localhost:8000/g' datasets/<some-dataset>/{,**/}*.json```
 
 *Start an nginx server with the source mounted and which rewrites URIs so*  
 *that it supports the URL structure expected by the schema references.*  

diff --git a/[email protected]/dataset.json b/[email protected]/dataset.json
@@ -0,0 +1,136 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://schemas.data.amsterdam.nl/[email protected]",
+  "type": "object",
+  "allOf": [
+    {
+      "$ref": "./[email protected]#/definitions/basicProperties"
+    }
+  ],
+  "required": [
+    "tables",
+    "status",
+    "creator",
+    "authorizationGrantor",
+    "owner",
+    "publisher",
+    "auth"
+  ],
+  "properties": {
+    "schema": {
+      "const": "dataset"
+    },
+    "version": {
+      "$ref": "./[email protected]#/definitions/version"
+    },
+    "status": {
+      "type": "string",
+      "enum": [
+        "beschikbaar",
+        "niet_beschikbaar"
+      ]
+    },
+    "homepage": {
+      "type": "string",
+      "format": "uri"
+    },
+    "language": {
+      "type": "string",
+      "minLength": 2,
+      "maxLength": 3
+    },
+    "accrualPeriodicity": {
+      "type": "string"
+    },
+    "spatialDescription": {
+      "type": "string"
+    },
+    "spatialCoordinates": {
+      "$ref": "https://geojson.org/schema/Geometry.json"
+    },
+    "theme": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "publisher": {
+      "description": "Naam van het datateam.",
+      "type": "string",
+      "minLength": 1
+    },
+    "creator": {
+      "description": "Naam van de bronhouder.",
+      "type": "string",
+      "minLength": 1
+    },
+    "owner": {
+      "type": "string",
+      "default": "Gemeente Amsterdam",
+      "minLength": 1
+    },
+    "authorizationGrantor": {
+      "type": "string",
+      "minLength": 1
+    },
+    "keywords": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "hasBeginning": {
+      "type": "string",
+      "format": "date-time"
+    },
+    "hasEnd": {
+      "type": "string",
+      "format": "date-time"
+    },
+    "objective": {
+      "type": "string"
+    },
+    "temporalUnit": {
+      "type": "string"
+    },
+    "spatial": {
+      "type": "string"
+    },
+    "legalBasis": {
+      "type": "string"
+    },
+    "contactPoint": {
+      "description": "Person and (optional) e-mail.",
+      "$ref": "./[email protected]#/definitions/contactPoint",
+      "default": {
+        "name": "datapunt",
+        "email": "[email protected]"
+      }
+    },
+    "crs": {
+      "description": "Coordinate reference system",
+      "$ref": "./[email protected]#/definitions/crs"
+    },
+    "tables": {
+      "type": "array",
+      "minItems": 1,
+      "items": {
+        "oneOf": [
+          {
+            "$ref": "./[email protected]"
+          },
+          {
+            "type": "object",
+            "additionalProperties": false,
+            "properties": {
+              "$ref": {
+                "type": "string",
+                "format": "uri-reference"
+              }
+            }
+          }
+        ]
+      }
+    }
+  }
+}
diff --git a/[email protected]/distribution.json b/[email protected]/distribution.json
@@ -0,0 +1,13 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://schemas.data.amsterdam.nl/[email protected]",
+  "type": "object",
+  "properties": {
+    "title": {
+      "type": "string"
+    },
+    "description": {
+      "type": "string"
+    }
+  }
+}
diff --git a/[email protected]/meta/auth.json b/[email protected]/meta/auth.json
@@ -0,0 +1,24 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://schemas.data.amsterdam.nl/meta/[email protected]",
+  "$vocabulary": {
+    "https://schemas.data.amsterdam.nl/meta/[email protected]": true
+  },
+  "$recursiveAnchor": true,
+  "title": "Amsterdam Schema authorization",
+  "properties": {
+    "ams.auth": {
+      "oneOf": [
+        {
+          "type": "array",
+          "items": {
+            "type": "string"
+          }
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  }
+}
diff --git a/[email protected]/meta/provenance.json b/[email protected]/meta/provenance.json
@@ -0,0 +1,22 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://schemas.data.amsterdam.nl/meta/[email protected]",
+  "$vocabulary": {
+    "https://schemas.data.amsterdam.nl/meta/[email protected]": true
+  },
+  "$recursiveAnchor": true,
+  "title": "Amsterdam Schema provenance",
+  "properties": {
+    "provenance": {
+      "$comment": "This field can hold provenance data, per dataset, table or field.",
+      "oneOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "object"
+        }
+      ]
+    }
+  }
+}
diff --git a/[email protected]/meta/relation.json b/[email protected]/meta/relation.json
@@ -0,0 +1,14 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://schemas.data.amsterdam.nl/meta/[email protected]",
+  "$vocabulary": {
+    "https://schemas.data.amsterdam.nl/meta/[email protected]": true
+  },
+  "$recursiveAnchor": true,
+  "properties": {
+    "relation": {
+      "type": "string",
+      "format": "uri-reference"
+    }
+  }
+}
diff --git a/[email protected]/meta/unit.json b/[email protected]/meta/unit.json
@@ -0,0 +1,15 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://schemas.data.amsterdam.nl/meta/[email protected]",
+  "$vocabulary": {
+    "https://schemas.data.amsterdam.nl/meta/[email protected]": true
+  },
+  "$recursiveAnchor": true,
+  "title": "Amsterdam Schema unit",
+  "properties": {
+    "unit": {
+      "type": "string",
+      "$comment": "UCUM strings, see https://ucum.nlm.nih.gov/"
+    }
+  }
+}
diff --git a/[email protected]/publisher.json b/[email protected]/publisher.json
@@ -0,0 +1,58 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://schemas.data.amsterdam.nl/[email protected]",
+  "type": "object",
+  "allOf": [
+    {
+      "$ref": "./[email protected]#/definitions/basicProperties"
+    }
+  ],
+  "required": [
+    "name",
+    "id",
+    "shortname",
+    "tags"
+  ],
+  "properties": {
+    "schema": {
+      "const": "publisher"
+    },
+    "name": {
+      "description": "Naam van de publisher.",
+      "type": "string",
+      "minLength": 1
+    },
+    "id": {
+      "description": "ID van de publisher.",
+      "type": "string",
+      "minLength": 1,
+      "pattern": "[A-Za-z]"
+    },
+    "shortname": {
+      "description": "Verkorte naam van de publisher. (voor resources)",
+      "type": "string",
+      "minLength": 1,
+      "maxLength": 12,
+      "pattern": "[a-z]"
+    },
+    "tags": {
+      "description": "Labels met metagegevens die aan resources van deze publisher moeten worden gehangen",
+      "type": "object",
+      "required": [
+        "costcenter"
+      ],
+      "properties": {
+        "costcenter": {
+          "description": "Costcenter tag van de publisher.",
+          "type": "string",
+          "minLength": 1
+        },
+        "team": {
+          "description": "Team tag van de publisher.",
+          "type": "string",
+          "minLength": 1
+        }
+      }
+    }
+  }
+}