cng-datasets 0.3.0__tar.gz

cng_datasets-0.3.0/LICENSE

@@ -0,0 +1,194 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for describing the origin of the Work and
+      reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting the License. You accept and agree to be bound by the
+      terms of this License by copying, modifying, or distributing the
+      Work (or any work based on the Work).
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

cng_datasets-0.3.0/PKG-INFO

@@ -0,0 +1,227 @@
+Metadata-Version: 2.4
+Name: cng-datasets
+Version: 0.3.0
+Summary: Cloud-native geospatial dataset processing toolkit
+Author-email: Boettiger Lab <cboettig@berkeley.edu>
+License: Apache-2.0
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: duckdb==1.5.4
+Requires-Dist: ibis-framework[duckdb]>=9.0.0
+Requires-Dist: polars>=0.20.0
+Requires-Dist: pyarrow>=15.0.0
+Requires-Dist: geopandas>=0.14.0
+Requires-Dist: rasterio>=1.3.0
+Requires-Dist: numpy<2.0,>=1.20.0
+Requires-Dist: kubernetes>=28.0.0
+Requires-Dist: boto3>=1.34.0
+Requires-Dist: pyyaml>=6.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+Requires-Dist: pytest-timeout>=2.2.0; extra == "dev"
+Requires-Dist: pytest-mock>=3.12.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: mypy>=1.7.0; extra == "dev"
+Provides-Extra: raster
+Requires-Dist: exactextract>=0.2.0; extra == "raster"
+Requires-Dist: rasterio>=1.3.0; extra == "raster"
+Provides-Extra: docs
+Requires-Dist: sphinx>=7.0; extra == "docs"
+Requires-Dist: furo; extra == "docs"
+Requires-Dist: myst-parser; extra == "docs"
+Requires-Dist: sphinx-autobuild; extra == "docs"
+Requires-Dist: linkify-it-py; extra == "docs"
+Dynamic: license-file
+
+# cng-datasets
+
+[![DOI](https://zenodo.org/badge/921944685.svg)](https://zenodo.org/badge/latestdoi/921944685)
+
+A CLI toolkit for processing large geospatial datasets into cloud-native formats on Kubernetes.
+
+**What it does:** Takes source geospatial data (Shapefiles, GeoPackages, FileGDB, GeoTIFFs) and produces:
+
+- **GeoParquet** — columnar format for analytical queries (DuckDB, Polars)
+- **PMTiles** — vector tiles for web map visualization
+- **H3 Hex Parquet** — hexagonal grid indexed at configurable H3 resolution, hive-partitioned for fast spatial joins
+- **Cloud-Optimized GeoTIFF** — for raster data, optimized for HTTP range requests
+
+**How it works:** You run a single CLI command locally. It generates Kubernetes Job YAML files that orchestrate the entire pipeline on your cluster. You never process data on your local machine — the CLI just generates the jobs.
+
+## Installation
+
+```bash
+pip install cng-datasets
+```
+
+Or from source:
+
+```bash
+pip install -e "."
+```
+
+## Usage
+
+### Generate a vector processing pipeline
+
+```bash
+cng-datasets workflow \
+  --dataset cpad-2024 \
+  --source-url https://example.com/cpad.gdb \
+  --bucket public-cpad \
+  --layer CPAD_SuperUnits \
+  --h3-resolution 10 \
+  --parent-resolutions "9,8,0" \
+  --hex-memory 32Gi \
+  --max-completions 200 \
+  --max-parallelism 50
+```
+
+This generates YAML files for a 5-step pipeline:
+
+1. **setup-bucket** — creates the S3 bucket with public-read policy
+2. **convert** — reads source data, reprojects to EPSG:4326, writes GeoParquet
+3. **pmtiles** — converts GeoParquet to PMTiles (parallel with step 4)
+4. **hex** — computes H3 cell assignments in parallel pods
+5. **repartition** — consolidates hex chunks into hive-partitioned layout
+
+**Multiple sources:** Add `--source-url` multiple times to merge datasets:
+
+```bash
+cng-datasets workflow \
+  --dataset merged-regions \
+  --source-url https://example.com/region1.shp \
+  --source-url https://example.com/region2.shp \
+  --source-url https://example.com/region3.shp \
+  --bucket my-bucket
+```
+
+Apply them:
+
+```bash
+kubectl apply -f <output-dir>/workflow-rbac.yaml
+kubectl apply -f <output-dir>/configmap.yaml
+kubectl apply -f <output-dir>/workflow.yaml
+```
+
+The workflow orchestrator runs steps sequentially, launching pmtiles and hex in parallel.
+
+### Generate a raster processing pipeline
+
+```bash
+cng-datasets raster-workflow \
+  --dataset wetlands-cog \
+  --source-url https://example.com/wetlands.tif \
+  --bucket public-wetlands
+```
+
+### Multi-layer sources
+
+For GeoDatabase or GeoPackage files with multiple layers, run one workflow per layer. Use `--layer` to select each layer and `--dataset` with `/` for hierarchical S3 paths:
+
+```bash
+# Inspect layers
+ogrinfo /vsicurl/https://example.com/data.gdb
+
+# Process each layer separately
+cng-datasets workflow --dataset mydata/layer-a --layer LayerA ...
+cng-datasets workflow --dataset mydata/layer-b --layer LayerB ...
+```
+
+The `/` in `--dataset` creates nested S3 paths (e.g., `mydata/layer-a.parquet`) while using hyphens for k8s resource names.
+
+## CLI Reference
+
+| Command | Purpose |
+|---------|---------|
+| `cng-datasets workflow` | Generate vector processing k8s pipeline |
+| `cng-datasets raster-workflow` | Generate raster processing k8s pipeline |
+| `cng-datasets storage setup-bucket` | Create and configure an S3 bucket |
+| `cng-convert-to-parquet` | Convert vector data to GeoParquet |
+| `cng-datasets vector` | Run H3 hex tiling (used inside k8s pods) |
+| `cng-datasets raster` | Run raster H3 tiling (used inside k8s pods) |
+| `cng-datasets repartition` | Consolidate hex chunks (used inside k8s pods) |
+
+Commands marked "used inside k8s pods" are called by the generated jobs — you don't run them directly.
+
+### `cng-datasets workflow` options
+
+```
+--dataset NAME             Dataset name for S3 paths. Use / for hierarchy (e.g., "padus/fee").
+--source-url URL           Public URL to source data.
+--bucket BUCKET            Target S3 bucket name.
+--layer LAYER              Layer name for multi-layer sources (GDB, GPKG).
+--h3-resolution N          H3 resolution for hex tiling (default: 10).
+--parent-resolutions STR   Comma-separated parent resolutions (default: "9,8,0").
+--hex-memory SIZE          Memory per hex pod (default: 8Gi).
+--max-completions N        Number of parallel chunks, max 200 (default: auto).
+--max-parallelism N        Max concurrent pods (default: 50).
+--id-column COL            ID column name (auto-detected if omitted).
+--output-dir DIR           Directory for generated YAML files.
+--intermediate-chunk-size  Rows per unnest batch (decrease if OOM).
+--row-group-size N         Rows per parquet row group (default: 100000).
+```
+
+## S3 Output Layout
+
+```
+bucket/
+├── dataset.parquet              # GeoParquet
+├── dataset.pmtiles              # PMTiles
+├── dataset/
+│   └── hex/
+│       └── h0={cell}/data_0.parquet   # H3-indexed, hive-partitioned
+├── README.md
+└── stac-collection.json
+```
+
+## Docker
+
+The CLI and all dependencies are packaged in a Docker image used by the k8s jobs:
+
+```bash
+docker pull ghcr.io/boettiger-lab/datasets:latest
+```
+
+## Troubleshooting
+
+**OOM on hex jobs:** Increase `--hex-memory` (e.g., 32Gi → 64Gi), increase `--max-completions` for smaller chunks, or decrease `--intermediate-chunk-size`.
+
+**Convert fails on curved geometries (MULTISURFACE):** Handled automatically — the converter linearizes curved geometry types via ogr2ogr before processing.
+
+**Monitoring:**
+
+```bash
+kubectl get jobs              # Pipeline status
+kubectl logs job/<name>       # Job logs
+kubectl get pods | grep OOM   # Check for memory issues
+```
+
+## Development
+
+```bash
+pip install -e ".[dev]"
+pytest tests/
+```
+
+## License
+
+Apache 2.0
+
+## Citation
+
+If you use cng-datasets in your work, please cite it via its Zenodo archive.
+The DOI badge at the top of this README resolves to the latest release; each
+release also has its own version-specific DOI. Citation metadata (authors,
+title, funding) lives in [`.zenodo.json`](.zenodo.json) and is minted
+automatically by Zenodo on each GitHub release.
+
+> Boettiger, C., & Buhler, C. K. cng-datasets: A cloud-native toolkit for
+> processing large geospatial datasets on Kubernetes. Zenodo.
+> https://zenodo.org/badge/latestdoi/921944685
+
+Once the first release is archived on Zenodo, replace the redirect above with
+the concrete versioned DOI it mints.

cng_datasets-0.3.0/README.md

@@ -0,0 +1,189 @@
+# cng-datasets
+
+[![DOI](https://zenodo.org/badge/921944685.svg)](https://zenodo.org/badge/latestdoi/921944685)
+
+A CLI toolkit for processing large geospatial datasets into cloud-native formats on Kubernetes.
+
+**What it does:** Takes source geospatial data (Shapefiles, GeoPackages, FileGDB, GeoTIFFs) and produces:
+
+- **GeoParquet** — columnar format for analytical queries (DuckDB, Polars)
+- **PMTiles** — vector tiles for web map visualization
+- **H3 Hex Parquet** — hexagonal grid indexed at configurable H3 resolution, hive-partitioned for fast spatial joins
+- **Cloud-Optimized GeoTIFF** — for raster data, optimized for HTTP range requests
+
+**How it works:** You run a single CLI command locally. It generates Kubernetes Job YAML files that orchestrate the entire pipeline on your cluster. You never process data on your local machine — the CLI just generates the jobs.
+
+## Installation
+
+```bash
+pip install cng-datasets
+```
+
+Or from source:
+
+```bash
+pip install -e "."
+```
+
+## Usage
+
+### Generate a vector processing pipeline
+
+```bash
+cng-datasets workflow \
+  --dataset cpad-2024 \
+  --source-url https://example.com/cpad.gdb \
+  --bucket public-cpad \
+  --layer CPAD_SuperUnits \
+  --h3-resolution 10 \
+  --parent-resolutions "9,8,0" \
+  --hex-memory 32Gi \
+  --max-completions 200 \
+  --max-parallelism 50
+```
+
+This generates YAML files for a 5-step pipeline:
+
+1. **setup-bucket** — creates the S3 bucket with public-read policy
+2. **convert** — reads source data, reprojects to EPSG:4326, writes GeoParquet
+3. **pmtiles** — converts GeoParquet to PMTiles (parallel with step 4)
+4. **hex** — computes H3 cell assignments in parallel pods
+5. **repartition** — consolidates hex chunks into hive-partitioned layout
+
+**Multiple sources:** Add `--source-url` multiple times to merge datasets:
+
+```bash
+cng-datasets workflow \
+  --dataset merged-regions \
+  --source-url https://example.com/region1.shp \
+  --source-url https://example.com/region2.shp \
+  --source-url https://example.com/region3.shp \
+  --bucket my-bucket
+```
+
+Apply them:
+
+```bash
+kubectl apply -f <output-dir>/workflow-rbac.yaml
+kubectl apply -f <output-dir>/configmap.yaml
+kubectl apply -f <output-dir>/workflow.yaml
+```
+
+The workflow orchestrator runs steps sequentially, launching pmtiles and hex in parallel.
+
+### Generate a raster processing pipeline
+
+```bash
+cng-datasets raster-workflow \
+  --dataset wetlands-cog \
+  --source-url https://example.com/wetlands.tif \
+  --bucket public-wetlands
+```
+
+### Multi-layer sources
+
+For GeoDatabase or GeoPackage files with multiple layers, run one workflow per layer. Use `--layer` to select each layer and `--dataset` with `/` for hierarchical S3 paths:
+
+```bash
+# Inspect layers
+ogrinfo /vsicurl/https://example.com/data.gdb
+
+# Process each layer separately
+cng-datasets workflow --dataset mydata/layer-a --layer LayerA ...
+cng-datasets workflow --dataset mydata/layer-b --layer LayerB ...
+```
+
+The `/` in `--dataset` creates nested S3 paths (e.g., `mydata/layer-a.parquet`) while using hyphens for k8s resource names.
+
+## CLI Reference
+
+| Command | Purpose |
+|---------|---------|
+| `cng-datasets workflow` | Generate vector processing k8s pipeline |
+| `cng-datasets raster-workflow` | Generate raster processing k8s pipeline |
+| `cng-datasets storage setup-bucket` | Create and configure an S3 bucket |
+| `cng-convert-to-parquet` | Convert vector data to GeoParquet |
+| `cng-datasets vector` | Run H3 hex tiling (used inside k8s pods) |
+| `cng-datasets raster` | Run raster H3 tiling (used inside k8s pods) |
+| `cng-datasets repartition` | Consolidate hex chunks (used inside k8s pods) |
+
+Commands marked "used inside k8s pods" are called by the generated jobs — you don't run them directly.
+
+### `cng-datasets workflow` options
+
+```
+--dataset NAME             Dataset name for S3 paths. Use / for hierarchy (e.g., "padus/fee").
+--source-url URL           Public URL to source data.
+--bucket BUCKET            Target S3 bucket name.
+--layer LAYER              Layer name for multi-layer sources (GDB, GPKG).
+--h3-resolution N          H3 resolution for hex tiling (default: 10).
+--parent-resolutions STR   Comma-separated parent resolutions (default: "9,8,0").
+--hex-memory SIZE          Memory per hex pod (default: 8Gi).
+--max-completions N        Number of parallel chunks, max 200 (default: auto).
+--max-parallelism N        Max concurrent pods (default: 50).
+--id-column COL            ID column name (auto-detected if omitted).
+--output-dir DIR           Directory for generated YAML files.
+--intermediate-chunk-size  Rows per unnest batch (decrease if OOM).
+--row-group-size N         Rows per parquet row group (default: 100000).
+```
+
+## S3 Output Layout
+
+```
+bucket/
+├── dataset.parquet              # GeoParquet
+├── dataset.pmtiles              # PMTiles
+├── dataset/
+│   └── hex/
+│       └── h0={cell}/data_0.parquet   # H3-indexed, hive-partitioned
+├── README.md
+└── stac-collection.json
+```
+
+## Docker
+
+The CLI and all dependencies are packaged in a Docker image used by the k8s jobs:
+
+```bash
+docker pull ghcr.io/boettiger-lab/datasets:latest
+```
+
+## Troubleshooting
+
+**OOM on hex jobs:** Increase `--hex-memory` (e.g., 32Gi → 64Gi), increase `--max-completions` for smaller chunks, or decrease `--intermediate-chunk-size`.
+
+**Convert fails on curved geometries (MULTISURFACE):** Handled automatically — the converter linearizes curved geometry types via ogr2ogr before processing.
+
+**Monitoring:**
+
+```bash
+kubectl get jobs              # Pipeline status
+kubectl logs job/<name>       # Job logs
+kubectl get pods | grep OOM   # Check for memory issues
+```
+
+## Development
+
+```bash
+pip install -e ".[dev]"
+pytest tests/
+```
+
+## License
+
+Apache 2.0
+
+## Citation
+
+If you use cng-datasets in your work, please cite it via its Zenodo archive.
+The DOI badge at the top of this README resolves to the latest release; each
+release also has its own version-specific DOI. Citation metadata (authors,
+title, funding) lives in [`.zenodo.json`](.zenodo.json) and is minted
+automatically by Zenodo on each GitHub release.
+
+> Boettiger, C., & Buhler, C. K. cng-datasets: A cloud-native toolkit for
+> processing large geospatial datasets on Kubernetes. Zenodo.
+> https://zenodo.org/badge/latestdoi/921944685
+
+Once the first release is archived on Zenodo, replace the redirect above with
+the concrete versioned DOI it mints.

cng_datasets-0.3.0/cng_datasets/__init__.py

@@ -0,0 +1,13 @@
+"""
+Cloud-Native Geospatial Datasets Processing Toolkit
+
+A toolkit for processing large geospatial datasets into cloud-native formats
+(COG, GeoParquet, PMTiles) with H3 hexagonal indexing.
+"""
+
+__version__ = "0.3.0"
+
+# Lazy imports can be handled by users as needed,
+# or we can keep these commented out to allow core usage without all dependencies.
+# from . import vector, raster, k8s, storage
+# __all__ = ["vector", "raster", "k8s", "storage", "__version__"]