vector2dggs 0.8.0__tar.gz → 0.9.0__tar.gz

{vector2dggs-0.8.0 → vector2dggs-0.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vector2dggs
-Version: 0.8.0
+Version: 0.9.0
 Summary: CLI DGGS indexer for vector geospatial data
 Home-page: https://github.com/manaakiwhenua/vector2dggs
 License: LGPL-3.0-or-later
@@ -30,8 +30,7 @@ Requires-Dist: psycopg2 (>=2.9.9,<3.0.0)
 Requires-Dist: pyarrow (>=20.0,<21.0)
 Requires-Dist: pyproj (>=3.7,<4.0)
 Requires-Dist: python-geohash (>=0.8.5,<0.9.0)
-Requires-Dist: rhealpixdggs (>=0.5.5,<0.6.0)
-Requires-Dist: rhppandas (>=0.1.2,<0.2.0)
+Requires-Dist: rhppandas (>=0.2.0,<0.3.0)
 Requires-Dist: rusty-polygon-geohasher (>=0.2.3,<0.3.0)
 Requires-Dist: s2geometry (>=0.9.0,<0.10.0)
 Requires-Dist: shapely (>=2.1,<3.0)
@@ -51,7 +50,7 @@ This is the vector equivalent of [raster2dggs](https://github.com/manaakiwhenua/
 Currently this tool supports the following DGGSs:
 
 - [H3](https://h3geo.org/)
-- [rHEALPix](https://datastore.landcareresearch.co.nz/dataset/rhealpix-discrete-global-grid-system) (points, polygons)
+- [rHEALPix](https://datastore.landcareresearch.co.nz/dataset/rhealpix-discrete-global-grid-system)
 - [S2](https://s2geometry.io/)
 
 ... and the following geocode systems:
@@ -130,8 +129,8 @@ Options:
                                   [default: 5000; required]
   -t, --threads INTEGER           Amount of threads used for operation
                                   [default: 7]
-  -tbl, --table TEXT              Name of the table to read when using a
-                                  spatial database connection as input
+  -lyr, --layer TEXT              Name of the layer or table to read when using a
+                                  an input that supports layers or tables
   -g, --geom_col TEXT             Column name to use when using a spatial
                                   database connection as input  [default:
                                   geom]
@@ -239,7 +238,7 @@ vector2dggs h3 -v DEBUG -id title_no -r 12 -o ~/Downloads/nz-property-titles.gpk
 With a PostgreSQL/PostGIS connection:
 
 ```bash
-vector2dggs h3 -v DEBUG -id ogc_fid -r 9 -p 5 -t 4 --overwrite -tbl topo50_lake postgresql://user:password@host:port/db ./topo50_lake.parquet
+vector2dggs h3 -v DEBUG -id ogc_fid -r 9 -p 5 -t 4 --overwrite -lyr topo50_lake postgresql://user:password@host:port/db ./topo50_lake.parquet
 ```
 
 ## Citation
@@ -249,14 +248,14 @@ vector2dggs h3 -v DEBUG -id ogc_fid -r 9 -p 5 -t 4 --overwrite -tbl topo50_lake
   title={{vector2dggs}},
   author={Ardo, James and Law, Richard},
   url={https://github.com/manaakiwhenua/vector2dggs},
-  version={0.8.0},
+  version={0.9.0},
   date={2023-04-20}
 }
 ```
 
 APA/Harvard
 
-> Ardo, J., & Law, R. (2023). vector2dggs (0.8.0) [Computer software]. https://github.com/manaakiwhenua/vector2dggs
+> Ardo, J., & Law, R. (2023). vector2dggs (0.9.0) [Computer software]. https://github.com/manaakiwhenua/vector2dggs
 
 [![manaakiwhenua-standards](https://github.com/manaakiwhenua/vector2dggs/workflows/manaakiwhenua-standards/badge.svg)](https://github.com/manaakiwhenua/manaakiwhenua-standards)
 

{vector2dggs-0.8.0 → vector2dggs-0.9.0}/README.md

@@ -9,7 +9,7 @@ This is the vector equivalent of [raster2dggs](https://github.com/manaakiwhenua/
 Currently this tool supports the following DGGSs:
 
 - [H3](https://h3geo.org/)
-- [rHEALPix](https://datastore.landcareresearch.co.nz/dataset/rhealpix-discrete-global-grid-system) (points, polygons)
+- [rHEALPix](https://datastore.landcareresearch.co.nz/dataset/rhealpix-discrete-global-grid-system)
 - [S2](https://s2geometry.io/)
 
 ... and the following geocode systems:
@@ -88,8 +88,8 @@ Options:
                                   [default: 5000; required]
   -t, --threads INTEGER           Amount of threads used for operation
                                   [default: 7]
-  -tbl, --table TEXT              Name of the table to read when using a
-                                  spatial database connection as input
+  -lyr, --layer TEXT              Name of the layer or table to read when using a
+                                  an input that supports layers or tables
   -g, --geom_col TEXT             Column name to use when using a spatial
                                   database connection as input  [default:
                                   geom]
@@ -197,7 +197,7 @@ vector2dggs h3 -v DEBUG -id title_no -r 12 -o ~/Downloads/nz-property-titles.gpk
 With a PostgreSQL/PostGIS connection:
 
 ```bash
-vector2dggs h3 -v DEBUG -id ogc_fid -r 9 -p 5 -t 4 --overwrite -tbl topo50_lake postgresql://user:password@host:port/db ./topo50_lake.parquet
+vector2dggs h3 -v DEBUG -id ogc_fid -r 9 -p 5 -t 4 --overwrite -lyr topo50_lake postgresql://user:password@host:port/db ./topo50_lake.parquet
 ```
 
 ## Citation
@@ -207,13 +207,13 @@ vector2dggs h3 -v DEBUG -id ogc_fid -r 9 -p 5 -t 4 --overwrite -tbl topo50_lake
   title={{vector2dggs}},
   author={Ardo, James and Law, Richard},
   url={https://github.com/manaakiwhenua/vector2dggs},
-  version={0.8.0},
+  version={0.9.0},
   date={2023-04-20}
 }
 ```
 
 APA/Harvard
 
-> Ardo, J., & Law, R. (2023). vector2dggs (0.8.0) [Computer software]. https://github.com/manaakiwhenua/vector2dggs
+> Ardo, J., & Law, R. (2023). vector2dggs (0.9.0) [Computer software]. https://github.com/manaakiwhenua/vector2dggs
 
 [![manaakiwhenua-standards](https://github.com/manaakiwhenua/vector2dggs/workflows/manaakiwhenua-standards/badge.svg)](https://github.com/manaakiwhenua/manaakiwhenua-standards)

{vector2dggs-0.8.0 → vector2dggs-0.9.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "vector2dggs"
-version = "0.8.0"
+version = "0.9.0"
 description = "CLI DGGS indexer for vector geospatial data"
 authors = ["James Ardo <ardoj@landcareresearch.co.nz>"]
 maintainers = ["Richard Law <lawr@landcareresearch.co.nz>"]
@@ -30,8 +30,7 @@ sqlalchemy = "^2.0.32"
 psycopg2 = "^2.9.9"
 shapely = "^2.1"
 numpy = "^2"
-rhppandas = "^0.1.2"
-rhealpixdggs = "^0.5.5"
+rhppandas = "^0.2.0"
 pillow = "^11.2.1"
 s2geometry = "^0.9.0"
 rusty-polygon-geohasher = "^0.2.3"

vector2dggs-0.9.0/vector2dggs/__init__.py

@@ -0,0 +1 @@
+__version__: str = "0.9.0"

{vector2dggs-0.8.0 → vector2dggs-0.9.0}/vector2dggs/common.py

@@ -112,7 +112,7 @@ def drop_condition(
     return df
 
 
-def get_parent_res(dggs: str, parent_res: Union[None, int], resolution: int):
+def get_parent_res(dggs: str, parent_res: Union[None, str], resolution: int) -> int:
     """
     Uses a parent resolution,
     OR,
@@ -127,7 +127,7 @@ def get_parent_res(dggs: str, parent_res: Union[None, int], resolution: int):
             )
         )
     return (
-        parent_res
+        int(parent_res)
         if parent_res is not None
         else const.DEFAULT_DGGS_PARENT_RES[dggs](resolution)
     )
@@ -138,10 +138,9 @@ def parent_partitioning(
     input_dir: Path,
     output_dir: Path,
     resolution: int,
-    parent_res: Union[None, int],
+    parent_res: int,
     **kwargs,
 ) -> None:
-    parent_res: int = get_parent_res(dggs, parent_res, resolution)
     partition_col = f"{dggs}_{parent_res:02}"
 
     with TqdmCallback(desc="Repartitioning"):
@@ -171,7 +170,7 @@ def polyfill(
     pq_in: Path,
     spatial_sort_col: str,
     resolution: int,
-    parent_res: Union[None, int],
+    parent_res: int,
     output_directory: str,
 ) -> None:
     """
@@ -179,7 +178,9 @@ def polyfill(
     linetracing (for LineString), or indexing (for Point),
     and writes out to parquet.
     """
-    df = gpd.read_parquet(pq_in).reset_index().drop(columns=[spatial_sort_col])
+    df = gpd.read_parquet(pq_in).reset_index()
+    if spatial_sort_col != "none":
+        df = df.drop(columns=[spatial_sort_col])
     if len(df.index) == 0:
         # Input is empty, nothing to convert
         return None
@@ -192,7 +193,6 @@ def polyfill(
         return None
 
     df.index.rename(f"{dggs}_{resolution:02}", inplace=True)
-    parent_res: int = get_parent_res(dggs, parent_res, resolution)
 
     # Secondary (parent) index, used later for partitioning
     df = secondary_index_func(df, parent_res)
@@ -223,22 +223,23 @@ def index(
     id_field: str = None,
     cut_crs: pyproj.CRS = None,
     con: SQLConnectionType = None,
-    table: str = None,
+    layer: str = None,
     geom_col: str = "geom",
     overwrite: bool = False,
 ) -> Path:
     """
     Performs multi-threaded DGGS indexing on geometries (including multipart and collections).
     """
+    parent_res = get_parent_res(dggs, parent_res, resolution)
 
-    if table and con:
+    if layer and con:
         # Database connection
         if keep_attributes:
-            q = sqlalchemy.text(f"SELECT * FROM {table}")
+            q = sqlalchemy.text(f"SELECT * FROM {layer}")
         elif id_field and not keep_attributes:
-            q = sqlalchemy.text(f"SELECT {id_field}, {geom_col} FROM {table}")
+            q = sqlalchemy.text(f"SELECT {id_field}, {geom_col} FROM {layer}")
         else:
-            q = sqlalchemy.text(f"SELECT {geom_col} FROM {table}")
+            q = sqlalchemy.text(f"SELECT {geom_col} FROM {layer}")
         df = gpd.read_postgis(q, con.connect(), geom_col=geom_col).rename_geometry(
             "geometry"
         )
@@ -296,11 +297,12 @@ def index(
 
     ddf = dgpd.from_geopandas(df, chunksize=max(1, chunksize), sort=True)
 
-    LOGGER.debug("Spatially sorting and partitioning (%s)", spatial_sorting)
-    ddf = ddf.spatial_shuffle(by=spatial_sorting)
+    if spatial_sorting != "none":
+        LOGGER.debug("Spatially sorting and partitioning (%s)", spatial_sorting)
+        ddf = ddf.spatial_shuffle(by=spatial_sorting)
     spatial_sort_col = (
         spatial_sorting
-        if spatial_sorting == "geohash"
+        if (spatial_sorting == "geohash" or spatial_sorting == "none")
         else f"{spatial_sorting}_distance"
     )
 

{vector2dggs-0.8.0 → vector2dggs-0.9.0}/vector2dggs/constants.py

@@ -6,21 +6,23 @@ import tempfile
 MIN_H3, MAX_H3 = 0, 15
 MIN_RHP, MAX_RHP = 0, 15
 MIN_S2, MAX_S2 = 0, 30
-MIN_GEOHASH, MAX_GEOHASH = 0, 12
+MIN_GEOHASH, MAX_GEOHASH = 1, 12
 
 DEFAULTS = {
     "id": None,
     "k": False,
     "ch": 50,
-    "s": "hilbert",
+    "s": "none",
     "crs": None,
     "c": 5000,
     "t": (multiprocessing.cpu_count() - 1),
-    "tbl": None,
+    "lyr": None,
     "g": "geom",
     "tempdir": tempfile.tempdir,
 }
 
+SPATIAL_SORTING_METHODS = ["hilbert", "morton", "geohash", "none"]
+
 DEFAULT_DGGS_PARENT_RES = {
     "h3": lambda resolution: max(MIN_H3, (resolution - DEFAULT_PARENT_OFFSET)),
     "rhp": lambda resolution: max(MIN_RHP, (resolution - DEFAULT_PARENT_OFFSET)),

{vector2dggs-0.8.0 → vector2dggs-0.9.0}/vector2dggs/geohash.py

@@ -123,7 +123,7 @@ def gh_polyfill(df: gpd.GeoDataFrame, level: int) -> pd.DataFrame:
 @click.option(
     "-s",
     "--spatial_sorting",
-    type=click.Choice(["hilbert", "morton", "geohash"]),
+    type=click.Choice(const.SPATIAL_SORTING_METHODS),
     default=const.DEFAULTS["s"],
     help="Spatial sorting method when perfoming spatial partitioning.",
 )
@@ -155,12 +155,12 @@ def gh_polyfill(df: gpd.GeoDataFrame, level: int) -> pd.DataFrame:
     nargs=1,
 )
 @click.option(
-    "-tbl",
-    "--table",
+    "-lyr",
+    "--layer",
     required=False,
-    default=const.DEFAULTS["tbl"],
+    default=const.DEFAULTS["lyr"],
     type=str,
-    help="Name of the table to read when using a spatial database connection as input",
+    help="Name of the layer or table to read when using an input that supports layers or tables",
     nargs=1,
 )
 @click.option(
@@ -192,7 +192,7 @@ def geohash(
     cut_crs: int,
     cut_threshold: int,
     threads: int,
-    table: str,
+    layer: str,
     geom_col: str,
     tempdir: Union[str, Path],
     overwrite: bool,
@@ -230,7 +230,7 @@ def geohash(
             cut_crs=cut_crs,
             id_field=id_field,
             con=con,
-            table=table,
+            layer=layer,
             geom_col=geom_col,
             overwrite=overwrite,
         )

{vector2dggs-0.8.0 → vector2dggs-0.9.0}/vector2dggs/h3.py

@@ -98,7 +98,7 @@ def h3polyfill(df: gpd.GeoDataFrame, resolution: int) -> pd.DataFrame:
 @click.option(
     "-s",
     "--spatial_sorting",
-    type=click.Choice(["hilbert", "morton", "geohash"]),
+    type=click.Choice(const.SPATIAL_SORTING_METHODS),
     default=const.DEFAULTS["s"],
     help="Spatial sorting method when perfoming spatial partitioning.",
 )
@@ -130,12 +130,12 @@ def h3polyfill(df: gpd.GeoDataFrame, resolution: int) -> pd.DataFrame:
     nargs=1,
 )
 @click.option(
-    "-tbl",
-    "--table",
+    "-lyr",
+    "--layer",
     required=False,
-    default=const.DEFAULTS["tbl"],
+    default=const.DEFAULTS["lyr"],
     type=str,
-    help="Name of the table to read when using a spatial database connection as input",
+    help="Name of the layer or table to read when using an input that supports layers or tables",
     nargs=1,
 )
 @click.option(
@@ -167,7 +167,7 @@ def h3(
     cut_crs: int,
     cut_threshold: int,
     threads: int,
-    table: str,
+    layer: str,
     geom_col: str,
     tempdir: Union[str, Path],
     overwrite: bool,
@@ -205,7 +205,7 @@ def h3(
             cut_crs=cut_crs,
             id_field=id_field,
             con=con,
-            table=table,
+            layer=layer,
             geom_col=geom_col,
             overwrite=overwrite,
         )

{vector2dggs-0.8.0 → vector2dggs-0.9.0}/vector2dggs/katana.py

@@ -11,6 +11,7 @@ Redistribution and use in source and binary forms, with or without modification,
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS “AS IS” AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 """
 
+from shapely import force_2d, has_z, has_m
 from shapely.geometry import (
     box,
     Polygon,
@@ -18,20 +19,32 @@ from shapely.geometry import (
     LineString,
     MultiLineString,
     GeometryCollection,
+    LinearRing,
 )
-from shapely.validation import explain_validity, make_valid
+from shapely.geometry.base import BaseGeometry
+from shapely.validation import make_valid
+from typing import Union, List
 
 
-def katana(geometry, threshold, count=0) -> GeometryCollection:
+def katana(
+    geometry: Union[BaseGeometry, None],
+    threshold: float,
+    count: int = 0,
+    check_2D: bool = True,
+) -> List[BaseGeometry]:
     """
-    Split a geometry into two parts across its shortest dimension.
+    Recursively split a geometry into two parts across its shortest dimension.
     Invalid input `geometry` will silently be made valid (if possible).
+    Any LinearRings will be converted to Polygons.
     """
     if geometry is None:
-        # Empty geometry collection
-        return GeometryCollection([])
+        return []
+    if isinstance(geometry, LinearRing):
+        geometry = Polygon(geometry)
+    if check_2D and (has_z(geometry) or has_m(geometry)):
+        geometry = force_2d(geometry)
+        check_2D = False  # No further 2D check needed
     if not geometry.is_valid:
-        # print(explain_validity(geometry))
         geometry = make_valid(geometry)
         if geometry.geom_type == "GeometryCollection":
             geometry.normalize()
@@ -60,16 +73,9 @@ def katana(geometry, threshold, count=0) -> GeometryCollection:
         if not isinstance(c, GeometryCollection):
             c = GeometryCollection([c])
         for e in c.geoms:
-            if isinstance(e, (Polygon, MultiPolygon, LineString, MultiLineString)):
-                result.extend(katana(e, threshold, count + 1))
-    if count > 0:
-        return result
-    # convert multipart into singlepart
-    final_result = []
-    for g in result:
-        # if isinstance(g, MultiPolygon):
-        #     final_result.extend(g)
-        # else:
-        # final_result.append(g)
-        final_result.append(g)
-    return final_result
+            if isinstance(
+                e, (Polygon, MultiPolygon, LineString, MultiLineString, LinearRing)
+            ):
+                result.extend(katana(e, threshold, count + 1, check_2D))
+
+    return result

{vector2dggs-0.8.0 → vector2dggs-0.9.0}/vector2dggs/rHP.py

@@ -11,6 +11,7 @@ import geopandas as gpd
 
 from typing import Union
 from pathlib import Path
+from rhppandas.util.const import COLUMNS
 
 import vector2dggs.constants as const
 import vector2dggs.common as common
@@ -29,14 +30,14 @@ def rhppolyfill(df: gpd.GeoDataFrame, resolution: int) -> pd.DataFrame:
             resolution, return_geometry=False
         ).drop(columns=["index"])
 
-    # df_linestring = df[df.geom_type == "LineString"]
-    # if len(df_linestring.index) > 0:
-    #     df_linestring = (
-    #         df_linestring.rhp.linetrace(resolution)
-    #         .explode("rhp_linetrace")
-    #         .set_index("rhp_linetrace")
-    #     )
-    #     df_linestring = df_linestring[~df_linestring.index.duplicated(keep="first")]
+    df_linestring = df[df.geom_type == "LineString"]
+    if len(df_linestring.index) > 0:
+        df_linestring = (
+            df_linestring.rhp.linetrace(resolution)
+            .explode(COLUMNS["linetrace"])
+            .set_index(COLUMNS["linetrace"])
+        )
+        df_linestring = df_linestring[~df_linestring.index.duplicated(keep="first")]
 
     df_point = df[df.geom_type == "Point"]
     if len(df_point.index) > 0:
@@ -45,7 +46,7 @@ def rhppolyfill(df: gpd.GeoDataFrame, resolution: int) -> pd.DataFrame:
     return pd.concat(
         map(
             lambda _df: pd.DataFrame(_df.drop(columns=[_df.geometry.name])),
-            [df_polygon, df_point],
+            [df_polygon, df_linestring, df_point],
         )
     )
 
@@ -98,7 +99,7 @@ def rhppolyfill(df: gpd.GeoDataFrame, resolution: int) -> pd.DataFrame:
 @click.option(
     "-s",
     "--spatial_sorting",
-    type=click.Choice(["hilbert", "morton", "geohash"]),
+    type=click.Choice(const.SPATIAL_SORTING_METHODS),
     default=const.DEFAULTS["s"],
     help="Spatial sorting method when perfoming spatial partitioning.",
 )
@@ -130,12 +131,12 @@ def rhppolyfill(df: gpd.GeoDataFrame, resolution: int) -> pd.DataFrame:
     nargs=1,
 )
 @click.option(
-    "-tbl",
-    "--table",
+    "-lyr",
+    "--layer",
     required=False,
-    default=const.DEFAULTS["tbl"],
+    default=const.DEFAULTS["lyr"],
     type=str,
-    help="Name of the table to read when using a spatial database connection as input",
+    help="Name of the layer or table to read when using an input that supports layers or tables",
     nargs=1,
 )
 @click.option(
@@ -167,7 +168,7 @@ def rhp(
     cut_crs: int,
     cut_threshold: int,
     threads: int,
-    table: str,
+    layer: str,
     geom_col: str,
     tempdir: Union[str, Path],
     overwrite: bool,
@@ -205,7 +206,7 @@ def rhp(
             cut_crs=cut_crs,
             id_field=id_field,
             con=con,
-            table=table,
+            layer=layer,
             geom_col=geom_col,
             overwrite=overwrite,
         )

{vector2dggs-0.8.0 → vector2dggs-0.9.0}/vector2dggs/s2.py

@@ -232,7 +232,7 @@ def s2_polyfill(df: gpd.GeoDataFrame, level: int) -> pd.DataFrame:
 @click.option(
     "-s",
     "--spatial_sorting",
-    type=click.Choice(["hilbert", "morton", "geohash"]),
+    type=click.Choice(const.SPATIAL_SORTING_METHODS),
     default=const.DEFAULTS["s"],
     help="Spatial sorting method when perfoming spatial partitioning.",
 )
@@ -264,12 +264,12 @@ def s2_polyfill(df: gpd.GeoDataFrame, level: int) -> pd.DataFrame:
     nargs=1,
 )
 @click.option(
-    "-tbl",
-    "--table",
+    "-lyr",
+    "--layer",
     required=False,
-    default=const.DEFAULTS["tbl"],
+    default=const.DEFAULTS["lyr"],
     type=str,
-    help="Name of the table to read when using a spatial database connection as input",
+    help="Name of the layer or table to read when using an input that supports layers or tables",
     nargs=1,
 )
 @click.option(
@@ -301,7 +301,7 @@ def s2(
     cut_crs: int,
     cut_threshold: int,
     threads: int,
-    table: str,
+    layer: str,
     geom_col: str,
     tempdir: Union[str, Path],
     overwrite: bool,
@@ -339,7 +339,7 @@ def s2(
             cut_crs=cut_crs,
             id_field=id_field,
             con=con,
-            table=table,
+            layer=layer,
             geom_col=geom_col,
             overwrite=overwrite,
         )

vector2dggs-0.8.0/vector2dggs/__init__.py

@@ -1 +0,0 @@
-__version__: str = "0.8.0"