feat: update to handle non-tif files

.github/workflows/ci.yml

@@ -0,0 +1,57 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions: {}
+
+jobs:
+  quality:
+    name: Quality checks
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
+        with:
+          version: "0.11.*"
+          enable-cache: false
+
+      - name: Set up Python
+        run: uv python install 3.14
+
+      - name: Run pre-commit
+        run: uv run pre-commit run --all-files
+
+  test:
+    name: Test Python ${{ matrix.python-version }}
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    strategy:
+      matrix:
+        python-version: ["3.12", "3.13", "3.14"]
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
+        with:
+          version: "0.11.*"
+          enable-cache: false
+
+      - name: Set up Python
+        run: uv python install ${{ matrix.python-version }}
+
+      - name: Run tests
+        run: uv run pytest

.github/workflows/conventional-commits-prs.yml

@@ -0,0 +1,23 @@
+name: PR Conventional Commit Validation
+
+# NOTE: pull_request_target runs in the base repo context with access to secrets.
+# Do NOT checkout untrusted code in this workflow.
+on:
+  # zizmor: ignore[dangerous-triggers]
+  # Safe: this workflow does not check out any code; it only validates
+  # the PR title via the GitHub API.
+  pull_request_target:
+    types: [opened, synchronize, reopened, edited]
+
+permissions: {}
+
+jobs:
+  validate-pr-title:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+    steps:
+      - name: PR Conventional Commit Validation
+        uses: ytanikin/pr-conventional-commits@639145d78959c53c43112365837e3abd21ed67c1 # 1.5.2
+        with:
+          task_types: '["feat","fix","docs","test","ci","refactor","perf","chore","revert"]'

.github/workflows/release-please.yml

@@ -0,0 +1,24 @@
+name: Release Please
+
+on:
+  push:
+    branches: [main]
+
+permissions:
+  contents: write
+  pull-requests: write
+  issues: write
+
+concurrency:
+  group: release-please-${{ github.ref }}
+  cancel-in-progress: false
+
+jobs:
+  release-please:
+    name: Create release PR or GitHub release
+    runs-on: ubuntu-latest
+    steps:
+      - name: Run release-please
+        uses: googleapis/release-please-action@45996ed1f6d02564a971a2fa1b5860e934307cf7 # v5.0.0
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}

.release-please-manifest.json

@@ -0,0 +1,3 @@
+{
+  ".": "0.1.0"
+}

CHANGELOG.md

@@ -0,0 +1,28 @@
+# Changelog
+
+## [0.1.0] - 2025-12-12
+
+Initial release of the MAAP DPS algorithm for generating STAC item metadata for existing Cloud Optimized GeoTIFF assets in object storage.
+
+### Added
+
+- Added the `GenerateCogStacItems` DPS algorithm at version `v0.1`.
+- Added direct Python invocation through `main.py` for local STAC item generation.
+- Added object storage listing for source locations such as S3 paths.
+- Added filtering for GeoTIFF assets before STAC item creation.
+- Added STAC item generation with `rio-stac` and catalog output with `pystac`.
+- Added projection and raster metadata handling for generated STAC items.
+- Added MAAP DPS wrapper scripts, including positional and named-argument execution paths.
+- Added support for direct bucket access and MAAP-compatible cloud raster defaults.
+
+### Fixed
+
+- Improved generated STAC item IDs.
+- Fixed Fmask nodata handling.
+- Fixed bbox serialization.
+- Set missing `proj:transform` and `proj:shape` values when available.
+
+### Documentation
+
+- Documented local usage with `uv run main.py`.
+- Documented required inputs and generated STAC catalog outputs.

README.md

@@ -1,17 +1,17 @@
-# DPS Import COGs
+# DPS STAC Item Generator
 
-Create STAC items for raster files in object storage
+Create STAC items for selected files in object storage.
 
 ## About
 
-This DPS algorithm creates STAC metadata for existing raster files (GeoTIFFs) stored in object storage (S3, Azure, GCS, etc.). The workflow:
+This DPS algorithm creates STAC metadata for existing files stored in object storage (S3, Azure, GCS, etc.). The workflow:
 
 1. Lists all files at the specified source location
-2. Filters for `.tif` files
-3. Creates a STAC item for each raster using `rio-stac`
+2. Filters files by configurable include/exclude extension lists
+3. Creates a STAC item for each matching asset using `rio-stac`
 4. Exports a self-contained STAC catalog with all items
 
-This tool is useful for importing existing COG (Cloud Optimized GeoTIFF) datasets into STAC format for better discoverability and interoperability.
+By default, the algorithm includes GeoTIFF (`.tif`, `.tiff`) and NetCDF (`.nc`) files. This tool is useful for importing existing geospatial datasets into STAC format for better discoverability and interoperability.
 The STAC items will be uploaded to the DPS User STAC in a collection associated with your username, the algorithm name/version, and the job tag.
 
 ## Usage
@@ -27,7 +27,7 @@ from maap.maap import MAAP
 maap = MAAP(maap_host="api.maap-project.org")
 
 job = maap.submitJob(
-    algo_id="GenerateCogStacItems",
+    algo_id="GenerateStacItems",
     version="v0.1",
     identifier="test-run",
     queue="maap-dps-worker-8gb",
@@ -36,9 +36,9 @@ job = maap.submitJob(
 
 ```
 
-Each job will produce a STAC item for each .tif file that exists under the provided `source`. The STAC items will be uploaded to the DPS User STAC catalog automatically after job completion. All jobs associated with the same algorithm, version, username, and job tag/identifier will be added to the same collection with the following format:
+Each job will produce a STAC item for each file under the provided `source` whose extension matches the configured filters. The STAC items will be uploaded to the DPS User STAC catalog automatically after job completion. All jobs associated with the same algorithm, version, username, and job tag/identifier will be added to the same collection with the following format:
 
-`{username}__GenerateCogStacItems__v0.1__{identifier}`
+`{username}__GenerateStacItems__v0.1__{identifier}`
 
 
 You can access the items following this pattern:
@@ -62,19 +62,39 @@ To customize the visualization, you can add all of the familiar visualization pa
 uv run main.py \
   --source "s3://bucket/path/to/files/" \
   --output_dir "/tmp/output" \
-  --region "us-west-2"
+  --region "us-west-2" \
+  --include-extensions ".tif,.tiff,.nc" \
+  --exclude-extensions ""
+```
+
+### Local format smoke test
+
+To generate local fixtures in `/tmp` and run the generator against them:
+
+```bash
+uv run python scripts/local_format_smoke_test.py
+```
+
+The script creates tiny GeoTIFF, COG, NetCDF, HDF5, JPEG 2000, PNG, and JPEG fixtures when the required GDAL/HDF5 command-line tools are available. It logs the `/tmp/dps-stac-local-*` input and output directories when it finishes.
+
+To exercise the DPS wrapper instead of calling `main.py` directly:
+
+```bash
+uv run python scripts/local_format_smoke_test.py --runner run-sh
 ```
 
 ### Parameters
 
 - `--source`: Source location of the files for which you want to generate STAC items (e.g., `s3://bucket/path/to/files/`)
 - `--output_dir`: Directory where the STAC catalog will be saved
 - `--region`: AWS region where the storage container exists (default: `us-west-2`)
+- `--include-extensions`: Comma-separated extensions to include (default: `.tif,.tiff,.nc`). Use an empty string to include all files.
+- `--exclude-extensions`: Comma-separated extensions to exclude. Exclusions override inclusions.
 
 ## Output
 
 The tool generates a self-contained STAC catalog in the output directory containing:
 
 - A `catalog.json` file with metadata about the collection
-- Individual STAC item JSON files for each raster
-- Each STAC item includes projection (`proj`) and raster band information
+- Individual STAC item JSON files for each matching asset
+- Each STAC item includes projection (`proj`) and raster band information when `rio-stac` can derive it from the source asset

algorithm-config.yml

@@ -1,5 +1,5 @@
-algorithm_description: Generate STAC item metadata for COGs in cloud storage
-algorithm_name: GenerateCogStacItems
+algorithm_description: Generate STAC item metadata for selected files in cloud storage
+algorithm_name: GenerateStacItems
 algorithm_version: v0.1
 build_command: dps-import-cogs/build-env.sh
 disk_space: 8GB
@@ -9,13 +9,21 @@ inputs:
   file: []
   positional:
   - default: ''
-    description: ' source location for the COGs in object storage, e.g. s3://bucket/path/to/folder/'
+    description: ' source location for the files in object storage, e.g. s3://bucket/path/to/folder/'
     name: source
     required: true
   - default: ''
     description: ' region in which the storage container exists'
     name: region
     required: false
+  - default: '.tif,.tiff,.nc'
+    description: ' comma-separated file extensions to include, e.g. .tif,.tiff,.nc. Leave empty to include all files.'
+    name: include_extensions
+    required: false
+  - default: ''
+    description: ' comma-separated file extensions to exclude. Exclusions override inclusions.'
+    name: exclude_extensions
+    required: false
 queue: maap-dps-worker-8gb
 repository_url: https://github.com/MAAP-Project/dps-import-cogs
 run_command: dps-import-cogs/run.sh

main.py

@@ -1,87 +1,7 @@
-"""Create STAC items for all raster files in object storage that match a prefix"""
+"""Compatibility entry point for the DPS STAC item generator."""
 
-import argparse
-import logging
-import os
-from pathlib import Path
-
-import obstore
-from obstore.store import from_url
-from pystac import Catalog, CatalogType, MediaType
-from rio_cogeo.cogeo import cog_validate
-from rio_stac import create_stac_item
-
-logging.basicConfig(
-    level=logging.INFO, format="%(asctime)s - %(levelname)s - %(name)s - %(message)s"
-)
-logging.getLogger("botocore").setLevel(logging.WARNING)
-logger = logging.getLogger(__name__)
-
-DEFAULT_REGION = "us-west-2"
-
-
-def run(
-    source: str,
-    output_dir: Path,
-    region: str | None = None,
-):
-    source_store = from_url(source, region=region or DEFAULT_REGION)
-
-    catalog = Catalog(
-        id="DPS",
-        description="DPS",
-        catalog_type=CatalogType.SELF_CONTAINED,
-    )
-
-    stream = obstore.list(source_store)
-    for batch in stream:
-        for obj in batch:
-            obj_key = os.path.join(source, obj["path"])
-            if not obj_key.endswith(".tif"):
-                logging.info(f"skipping {obj_key} because it is not a .tif")
-                continue
-
-            logging.info(f"processing {obj_key}")
-            is_cog = cog_validate(obj_key)
-
-            item = create_stac_item(
-                source=obj_key,
-                id=obj["path"].replace(".tif", ""),
-                with_proj=True,
-                with_raster=True,
-                asset_media_type=MediaType.COG if is_cog else MediaType.GEOTIFF,
-            )
-
-            catalog.add_item(item)
-
-    catalog.normalize_and_save(
-        root_href=str(output_dir),
-        catalog_type=CatalogType.SELF_CONTAINED,
-    )
+from dps_stac_item_generator.cli import main
 
 
 if __name__ == "__main__":
-    parse = argparse.ArgumentParser(
-        description="Queries the HLS STAC geoparquet archive and writes the result to a file"
-    )
-    parse.add_argument(
-        "--source",
-        help="Source location of the files for which you want to generate STAC items."
-        " e.g. 's3://bucket/path/to/files/'",
-        required=True,
-    )
-    parse.add_argument(
-        "--output_dir", help="Directory in which to save output", required=True
-    )
-    parse.add_argument(
-        "--region",
-        help="region in which the storage container exists. e.g. 'us-west-2'",
-        default="us-west-2",
-    )
-    args = parse.parse_args()
-
-    output_dir = Path(args.output_dir)
-    run(
-        source=args.source,
-        output_dir=output_dir,
-    )
+    main()

pyproject.toml

@@ -1,6 +1,10 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
 [project]
-name = "dps-import-cogs"
-description = "DPS algorithm for generating STAC item metadata for COGs from external sources"
+name = "dps-stac-item-generator"
+description = "DPS algorithm for generating STAC item metadata for selected files from external sources"
 readme = "README.md"
 requires-python = ">=3.12"
 dynamic = ["version"]
@@ -12,18 +16,32 @@ dependencies = [
     "rio-stac>=0.10.1",
 ]
 
+[project.scripts]
+dps-stac-item-generator = "dps_stac_item_generator.cli:main"
+
 [dependency-groups]
 dev = [
     "ipython>=9.8.0",
     "maap-py>=4.2.0",
     "mypy>=1.18.2",
     "pre-commit>=4.3.0",
+    "pytest>=9.1.1",
     "ruff>=0.14.3",
 ]
 
 [tool.pdm.version]
 source = "scm"
 
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.mypy]
+ignore_missing_imports = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-vv"
+
 [tool.ruff]
 
 [tool.ruff.format]