szehon-ho commented on code in PR #240:
URL: https://github.com/apache/parquet-format/pull/240#discussion_r1766101838
##########
src/main/thrift/parquet.thrift:
##########
@@ -237,6 +237,97 @@ struct SizeStatistics {
3: optional list<i64> definition_level_histogram;
}
+/**
+ * Interpretation for edges of GEOMETRY logical type, i.e. whether the edge
+ * between points represent a straight cartesian line or the shortest line on
+ * the sphere. It applies to all non-point geometry objects.
+ */
+enum Edges {
+ PLANAR = 0;
+ SPHERICAL = 1;
+}
+
+/**
+ * A custom binary-encoded polygon or multi-polygon to represent a covering of
+ * geometries. For example, it may be a bounding box or an envelope of
geometries
+ * when a bounding box cannot be built (e.g. a geometry has spherical edges,
or if
+ * an edge of geographic coordinates crosses the antimeridian). In addition,
it can
+ * also be used to provide vendor-agnostic coverings like S2 or H3 grids.
+ */
+struct Covering {
+ /**
+ * A type of covering. Currently accepted values: "WKB".
+ */
+ 1: required string kind;
+ /**
+ * A payload specific to kind. Below are the supported values:
+ * - WKB: well-known binary of a POLYGON or MULTI-POLYGON that completely
+ * covers the contents. This will be interpreted according to the same CRS
+ * and edges defined by the logical type.
+ */
+ 2: required binary value;
+}
+
+/**
+ * Bounding box of geometries in the representation of min/max value pair of
+ * coordinates from each axis. Values of Z and M are omitted for 2D geometries.
+ * Filter pushdown on geometries using this is only safe for planar spatial
+ * filters.
+ */
+struct BoundingBox {
+ 1: required double xmin;
+ 2: required double xmax;
+ 3: required double ymin;
+ 4: required double ymax;
+ 5: optional double zmin;
+ 6: optional double zmax;
+ 7: optional double mmin;
+ 8: optional double mmax;
+}
+
+/** Statistics specific to GEOMETRY logical type */
+struct GeometryStatistics {
+ /** A bounding box of geometries */
+ 1: optional BoundingBox bbox;
+
+ /**
+ * A list of coverings of geometries.
+ * Note that It is allowed to have more than one covering of the same kind
and
+ * implementation is free to use any of them. It is recommended to have at
most
+ * one covering for each kind.
+ */
+ 2: optional list<Covering> coverings;
+
+ /**
+ * The geometry types of all geometries, or an empty array if they are not
+ * known. This is borrowed from `geometry_types` column metadata of
GeoParquet [1]
+ * except that values in the list are WKB (ISO variant) integer codes [2].
Table
+ * below shows the most common geometry types and their codes:
+ *
+ * | Type | XY | XYZ | XYM | XYZM |
+ * | :----------------- | :--- | :--- | :--- | :--: |
+ * | Point | 0001 | 1001 | 2001 | 3001 |
+ * | LineString | 0002 | 1002 | 2002 | 3002 |
+ * | Polygon | 0003 | 1003 | 2003 | 3003 |
+ * | MultiPoint | 0004 | 1004 | 2004 | 3004 |
+ * | MultiLineString | 0005 | 1005 | 2005 | 3005 |
+ * | MultiPolygon | 0006 | 1006 | 2006 | 3006 |
+ * | GeometryCollection | 0007 | 1007 | 2007 | 3007 |
+ *
+ * In addition, the following rules are used:
+ * - A list of multiple values indicates that multiple geometry types are
+ * present (e.g. `[0003, 0006]`).
+ * - An empty array explicitly signals that the geometry types are not known.
+ * - The geometry types in the list must be unique (e.g. `[0001, 0001]`
+ * is not valid).
+ *
+ * Please refer to links below for more detail:
+ * [1]
https://en.wikipedia.org/wiki/Well-known_text_representation_of_geometry#Well-known_binary
Review Comment:
Just minor point, the origin of WKB and geo class hierarchy seem to be
https://www.ogc.org/standard/sfa/ and these other ones are derivative.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
