Update validator with the latest spec changes

.github/workflows/scripts.yml

@@ -7,6 +7,28 @@ on:
   pull_request:
 
 jobs:
+  validate-examples:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Set up Python 3.8
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+
+      - name: Install validator
+        run: |
+          cd validator/python
+          python -m pip install --no-binary geoparquet_validator .
+
+      - name: Run validator
+        run: |
+          for example in $(ls examples/*.parquet); do
+            echo $example;
+            geoparquet_validator $example || exit 1;
+          done
+
   test-json-metadata:
     runs-on: ubuntu-latest
     steps:

examples/example.py

@@ -1,32 +1,5 @@
 """
 Generates `example.parquet` using pyarrow by running `python example.py`.
-
-You can print the metadata with:
-
-.. code-block:: python
-
-   >>> import json, pprint, pyarrow.parquet as pq
-   >>> pprint.pprint(json.loads(pq.read_schema("example.parquet").metadata[b"geo"]))
-   {'columns': {'geometry': {'bbox': [-180.0, -90.0, 180.0, 83.6451],
-                             'crs': 'GEOGCRS["WGS 84 (CRS84)",ENSEMBLE["World '
-                                    'Geodetic System 1984 ensemble",MEMBER["World '
-                                    'Geodetic System 1984 '
-                                    '(Transit)"],MEMBER["World Geodetic System '
-                                    '1984 (G730)"],MEMBER["World Geodetic System '
-                                    '1984 (G873)"],MEMBER["World Geodetic System '
-                                    '1984 (G1150)"],MEMBER["World Geodetic System '
-                                    '1984 (G1674)"],MEMBER["World Geodetic System '
-                                    '1984 (G1762)"],MEMBER["World Geodetic System '
-                                    '1984 (G2139)"],ELLIPSOID["WGS '
-                                    '84",6378137,298.257223563],ENSEMBLEACCURACY[2.0]],CS[ellipsoidal,2],AXIS["geodetic '
-                                    'longitude (Lon)",east],AXIS["geodetic '
-                                    'latitude '
-                                    '(Lat)",north],UNIT["degree",0.0174532925199433],USAGE[SCOPE["Not '
-                                    'known."],AREA["World."],BBOX[-90,-180,90,180]],ID["OGC","CRS84"]]',
-                             'edges': 'planar',
-                             'encoding': 'WKB'}},
-    'primary_column': 'geometry',
-    'version': '0.1.0'}
 """
 import json
 import pathlib
@@ -39,7 +12,7 @@
 HERE = pathlib.Path(__file__).parent
 
 df = geopandas.read_file(geopandas.datasets.get_path("naturalearth_lowres"))
-df = df.to_crs('crs84')
+df = df.to_crs("crs84")
 table = pa.Table.from_pandas(df.head().to_wkb())
 
 
@@ -48,8 +21,9 @@
     "primary_column": "geometry",
     "columns": {
         "geometry": {
-            "crs": df.crs.to_wkt(pyproj.enums.WktVersion.WKT2_2019_SIMPLIFIED),
             "encoding": "WKB",
+            "geometry_type": ["Polygon", "MultiPolygon"],
+            "crs": df.crs.to_wkt(pyproj.enums.WktVersion.WKT2_2019_SIMPLIFIED),
             "edges": "planar",
             "bbox": [round(x, 4) for x in df.geometry.unary_union.bounds],
         },

examples/example_metadata.json

@@ -8,9 +8,13 @@
           180.0,
           83.6451
         ],
-        "crs": "GEOGCRS[\"WGS 84\",ENSEMBLE[\"World Geodetic System 1984 ensemble\",MEMBER[\"World Geodetic System 1984 (Transit)\"],MEMBER[\"World Geodetic System 1984 (G730)\"],MEMBER[\"World Geodetic System 1984 (G873)\"],MEMBER[\"World Geodetic System 1984 (G1150)\"],MEMBER[\"World Geodetic System 1984 (G1674)\"],MEMBER[\"World Geodetic System 1984 (G1762)\"],MEMBER[\"World Geodetic System 1984 (G2139)\"],ELLIPSOID[\"WGS 84\",6378137,298.257223563],ENSEMBLEACCURACY[2.0]],CS[ellipsoidal,2],AXIS[\"geodetic latitude (Lat)\",north],AXIS[\"geodetic longitude (Lon)\",east],UNIT[\"degree\",0.0174532925199433],USAGE[SCOPE[\"Horizontal component of 3D system.\"],AREA[\"World.\"],BBOX[-90,-180,90,180]],ID[\"EPSG\",4326]]",
+        "crs": "GEOGCRS[\"WGS 84 (CRS84)\",ENSEMBLE[\"World Geodetic System 1984 ensemble\",MEMBER[\"World Geodetic System 1984 (Transit)\"],MEMBER[\"World Geodetic System 1984 (G730)\"],MEMBER[\"World Geodetic System 1984 (G873)\"],MEMBER[\"World Geodetic System 1984 (G1150)\"],MEMBER[\"World Geodetic System 1984 (G1674)\"],MEMBER[\"World Geodetic System 1984 (G1762)\"],MEMBER[\"World Geodetic System 1984 (G2139)\"],ELLIPSOID[\"WGS 84\",6378137,298.257223563],ENSEMBLEACCURACY[2.0]],CS[ellipsoidal,2],AXIS[\"geodetic longitude (Lon)\",east],AXIS[\"geodetic latitude (Lat)\",north],UNIT[\"degree\",0.0174532925199433],USAGE[SCOPE[\"Not known.\"],AREA[\"World.\"],BBOX[-90,-180,90,180]],ID[\"OGC\",\"CRS84\"]]",
         "edges": "planar",
-        "encoding": "WKB"
+        "encoding": "WKB",
+        "geometry_type": [
+          "Polygon",
+          "MultiPolygon"
+        ]
       }
     },
     "primary_column": "geometry",

format-specs/geoparquet.md

@@ -53,7 +53,7 @@ Each geometry column in the dataset must be included in the columns field above
 | Field Name |                               Type                                      |                                                                   Description                                                                     |
 | ---------- | ----------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
 | encoding | string | **REQUIRED** Name of the geometry encoding format. Currently only 'WKB' is supported. |
-| geometry_type | string or \[string] | **REQUIRED** The geometry type(s) of all geometries, or "Unknown" if they are not known.  |
+| geometry_type | string or \[string] | **REQUIRED** The geometry type(s) of all geometries, or 'Unknown' if they are not known.  |
 | crs       | string   | **OPTIONAL** [WKT2](https://docs.opengeospatial.org/is/18-010r7/18-010r7.html) string representing the Coordinate Reference System (CRS) of the geometry. If the crs field is not included then the data in this column must be stored in longitude, latitude. In the case where a crs is not provided, CRS-aware implementations should assume a default value of [OGC:CRS84](https://www.opengis.net/def/crs/OGC/1.3/CRS84) (longitude-latitude coordinates) |
 | edges | string | **OPTIONAL** Name of the coordinate system for the edges. Must be one of 'planar' or 'spherical'. The default value is 'planar'.  |
 | bbox   | \[number] | **OPTIONAL** Bounding Box of the geometries in the file, formatted according to [RFC 7946, section 5](https://tools.ietf.org/html/rfc7946#section-5) |
@@ -62,7 +62,7 @@ Each geometry column in the dataset must be included in the columns field above
 
 #### crs
 
-The Coordinate Reference System (CRS) is an optional parameter for each geometry column defined in geoparquet format. 
+The Coordinate Reference System (CRS) is an optional parameter for each geometry column defined in geoparquet format.
 
 The CRS must be provided in [WKT](https://en.wikipedia.org/wiki/Well-known_text_representation_of_coordinate_reference_systems) version 2, also known as **WKT2**. WKT2 has several revisions, this specification only supports [WKT2_2019](https://docs.opengeospatial.org/is/18-010r7/18-010r7.html).
 
@@ -98,7 +98,7 @@ GEOGCRS["WGS 84 (CRS84)",
     ID["OGC","CRS84"]]
 ```
 
-Due to the large number of CRSes available and the difficulty of implementing all of them, we expect that a number of implementations will start without support for the optional `crs` field. 
+Due to the large number of CRSes available and the difficulty of implementing all of them, we expect that a number of implementations will start without support for the optional `crs` field.
 Users are recommended to store their data in longitude, latitude (OGC:CRS84 or not including the `crs` field) for it to work with the widest number of tools. But data that is better served in particular projections can choose to use an alternate coordinate reference system. We expect many tools will support alternate CRSes, but encourage users to check to ensure their chosen tool supports their chosen crs.
 
 #### epoch
@@ -122,9 +122,9 @@ Note that the current version of the spec only allows for a subset of WKB: 2D or
 
 #### Coordinate axis order
 
-The axis order of the coordinates in WKB stored in a geoparquet follows the de facto standard for axis order in WKB and is therefore always 
-(x, y) where x is easting or longitude and y is northing or latitude. This ordering explicitly overrides the axis order as specified in the CRS. 
-This follows the precedent of [GeoPackage](https://geopackage.org), see the [note in their spec](https://www.geopackage.org/spec130/#gpb_spec). 
+The axis order of the coordinates in WKB stored in a geoparquet follows the de facto standard for axis order in WKB and is therefore always
+(x, y) where x is easting or longitude and y is northing or latitude. This ordering explicitly overrides the axis order as specified in the CRS.
+This follows the precedent of [GeoPackage](https://geopackage.org), see the [note in their spec](https://www.geopackage.org/spec130/#gpb_spec).
 
 #### geometry_type
 

validator/python/geoparquet_validator/schema.json

@@ -4,7 +4,7 @@
   "type": "object",
   "description": "Parquet metadata included in the geo field.",
   "properties": {
-    "schema_version": {
+    "version": {
       "type": "string",
       "pattern": "^0\\.1\\.[0-9]+$",
       "description": "The version of the geoparquet metadata standard used when writing."
@@ -20,15 +20,30 @@
         ".*": {
           "type": "object",
           "properties": {
-            "crs": {
-              "type": "string",
-              "description": "WKT2 representing the Coordinate Reference System (CRS) of the geometry."
-            },
             "encoding": {
               "type": "string",
               "enum": ["WKB"],
               "description": "Name of the geometry encoding format. Currently only 'WKB' is supported."
             },
+            "geometry_type": {
+              "oneOf": [
+                {
+                  "$ref": "#/$defs/geometry_type"
+                },
+                {
+                  "type": "array",
+                  "items": {
+                    "$ref": "#/$defs/geometry_type"
+                  },
+                  "uniqueItems": true
+                }
+              ],
+              "description": "The geometry type(s) of all geometries, or 'Unknown' if they are not known."
+            },
+            "crs": {
+              "type": "string",
+              "description": "WKT2 representing the Coordinate Reference System (CRS) of the geometry."
+            },
             "edges": {
               "type": "string",
               "enum": ["planar", "spherical"],
@@ -55,14 +70,24 @@
                   "description": "The maximum constant latitude line that bounds the rectangle (ymax)."
                 }
               ]
+            },
+            "epoch": {
+              "type": "number",
+              "description": "Coordinate epoch in case of a dynamic CRS, expressed as a decimal year."
             }
           },
           "additionalProperties": true,
-          "required": ["crs", "encoding"]
+          "required": ["encoding", "geometry_type"]
         }
       }
     }
   },
   "additionalProperties": true,
-  "required": ["schema_version", "primary_column", "columns"]
+  "required": ["version", "primary_column", "columns"],
+  "$defs": {
+    "geometry_type": {
+      "type": "string",
+      "enum": ["Point", "LineString", "Polygon", "MultiPoint", "MultiLineString", "MultiPolygon", "GeometryCollection", "Unknown"]
+    }
+  }
 }