datensee 0.1.0a1__tar.gz

datensee-0.1.0a1/PKG-INFO

@@ -0,0 +1,121 @@
+Metadata-Version: 2.4
+Name: datensee
+Version: 0.1.0a1
+Summary: DatensEE: Parallelize Google Earth Engine exports via Cloud Dataflow
+Keywords: earth-engine,gee,dataflow,geotiff,cog,remote-sensing
+Author: DatensEE Contributors
+License-Expression: Apache-2.0
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: GIS
+Classifier: Typing :: Typed
+Requires-Dist: typer>=0.12
+Requires-Dist: pydantic>=2.0
+Requires-Dist: httpx>=0.27
+Requires-Dist: rich>=13.0
+Requires-Dist: pyproj>=3.6
+Requires-Dist: shapely>=2.0
+Requires-Dist: google-auth>=2.0
+Requires-Dist: google-cloud-storage>=2.0
+Requires-Dist: rasterio>=1.3 ; extra == 'validation'
+Requires-Python: >=3.12
+Project-URL: Homepage, https://github.com/michaelfdewitt/datensee
+Project-URL: Repository, https://github.com/michaelfdewitt/datensee
+Project-URL: Issues, https://github.com/michaelfdewitt/datensee/issues
+Project-URL: Changelog, https://github.com/michaelfdewitt/datensee/releases
+Provides-Extra: validation
+Description-Content-Type: text/markdown
+
+# DatensEE
+
+**Massively parallel Earth Engine exports via Cloud Dataflow.**
+
+DatensEE takes the computation you already wrote in Earth Engine and runs it at
+continental scale. You bring the expression, the region, and the scale — DatensEE
+handles tiling, parallel fetching across thousands of Dataflow workers, and
+assembly into Cloud Optimized GeoTIFFs on GCS.
+
+```bash
+pip install datensee
+```
+
+No `earthengine-api` dependency, no Java toolchain. Cloud exports launch a
+prebuilt Dataflow Flex Template; the local runner (small regions, debugging)
+fetches a prebuilt pipeline JAR on first use.
+
+## Drop-in replacement for `Export.image.toCloudStorage`
+
+```python
+import ee, datensee
+ee.Initialize()
+
+image = (ee.ImageCollection('LANDSAT/LC09/C02/T1_L2')
+         .filterDate('2023-06-01', '2023-09-01')
+         .median()
+         .normalizedDifference(['SR_B5', 'SR_B4']))
+region = ee.Geometry.Rectangle([-122.6, 37.2, -121.8, 38.0])
+
+result = datensee.export(
+    image, region,
+    project="my-gcp-project",
+    output="gs://my-bucket/exports/ndvi",
+    scale=10, crs="EPSG:32610",
+    runner="dataflow", temp_location="gs://my-bucket/tmp",
+)
+```
+
+`region` also accepts a GeoJSON dict or a shapely geometry. From the shell:
+
+```bash
+datensee export expr.json region.geojson \
+  --project my-gcp-project \
+  --output gs://my-bucket/exports/ndvi \
+  --scale 10 --crs EPSG:32610 \
+  --runner dataflow --temp-location gs://my-bucket/tmp
+```
+
+Try it end to end with the built-in demo (local runner, ~4 tiles):
+
+```bash
+datensee demo --project my-gcp-project --output ./ndvi-output
+```
+
+## How it works
+
+EE is the computation engine; DatensEE is the parallelism engine. It never
+interprets or recompiles your expression — it decomposes the region into a
+globally aligned tile grid, calls the
+[High Volume API](https://developers.google.com/earth-engine/reference/rest/v1/projects.image/computePixels)
+once per tile from a Dataflow pipeline (429-driven backoff, retries, a
+structured failures journal with `datensee retry --until-done`), and
+transcodes each result into self-describing COGs. Every tile is an integer
+pixel rectangle in one canonical grid, and every worker sees the same
+snapshot of every EE asset, so outputs are pixel-exact and reproducible.
+
+| | Local (`runner="local"`) | Dataflow (`runner="dataflow"`) |
+|---|---|---|
+| **Good for** | Small regions, testing | Large regions, production |
+| **Tile count** | Up to ~100 | Thousands to millions |
+| **Startup** | Seconds (JVM) | ~2 min (VM + container boot) |
+| **Cost** | Free (your machine) | Dataflow vCPU/GB-hours |
+
+## Prerequisites
+
+- Python 3.12+
+- A GCP project with the Earth Engine API enabled
+- `gcloud auth application-default login` (Colab handles auth automatically via
+  `datensee.notebook.ensure_auth()`)
+
+## Links
+
+- Source, issues, and full documentation:
+  <https://github.com/michaelfdewitt/datensee>
+- Colab quickstart:
+  <https://github.com/michaelfdewitt/datensee/blob/master/notebooks/datensee_quickstart.ipynb>
+
+Apache License 2.0.

datensee-0.1.0a1/README.md

@@ -0,0 +1,88 @@
+# DatensEE
+
+**Massively parallel Earth Engine exports via Cloud Dataflow.**
+
+DatensEE takes the computation you already wrote in Earth Engine and runs it at
+continental scale. You bring the expression, the region, and the scale — DatensEE
+handles tiling, parallel fetching across thousands of Dataflow workers, and
+assembly into Cloud Optimized GeoTIFFs on GCS.
+
+```bash
+pip install datensee
+```
+
+No `earthengine-api` dependency, no Java toolchain. Cloud exports launch a
+prebuilt Dataflow Flex Template; the local runner (small regions, debugging)
+fetches a prebuilt pipeline JAR on first use.
+
+## Drop-in replacement for `Export.image.toCloudStorage`
+
+```python
+import ee, datensee
+ee.Initialize()
+
+image = (ee.ImageCollection('LANDSAT/LC09/C02/T1_L2')
+         .filterDate('2023-06-01', '2023-09-01')
+         .median()
+         .normalizedDifference(['SR_B5', 'SR_B4']))
+region = ee.Geometry.Rectangle([-122.6, 37.2, -121.8, 38.0])
+
+result = datensee.export(
+    image, region,
+    project="my-gcp-project",
+    output="gs://my-bucket/exports/ndvi",
+    scale=10, crs="EPSG:32610",
+    runner="dataflow", temp_location="gs://my-bucket/tmp",
+)
+```
+
+`region` also accepts a GeoJSON dict or a shapely geometry. From the shell:
+
+```bash
+datensee export expr.json region.geojson \
+  --project my-gcp-project \
+  --output gs://my-bucket/exports/ndvi \
+  --scale 10 --crs EPSG:32610 \
+  --runner dataflow --temp-location gs://my-bucket/tmp
+```
+
+Try it end to end with the built-in demo (local runner, ~4 tiles):
+
+```bash
+datensee demo --project my-gcp-project --output ./ndvi-output
+```
+
+## How it works
+
+EE is the computation engine; DatensEE is the parallelism engine. It never
+interprets or recompiles your expression — it decomposes the region into a
+globally aligned tile grid, calls the
+[High Volume API](https://developers.google.com/earth-engine/reference/rest/v1/projects.image/computePixels)
+once per tile from a Dataflow pipeline (429-driven backoff, retries, a
+structured failures journal with `datensee retry --until-done`), and
+transcodes each result into self-describing COGs. Every tile is an integer
+pixel rectangle in one canonical grid, and every worker sees the same
+snapshot of every EE asset, so outputs are pixel-exact and reproducible.
+
+| | Local (`runner="local"`) | Dataflow (`runner="dataflow"`) |
+|---|---|---|
+| **Good for** | Small regions, testing | Large regions, production |
+| **Tile count** | Up to ~100 | Thousands to millions |
+| **Startup** | Seconds (JVM) | ~2 min (VM + container boot) |
+| **Cost** | Free (your machine) | Dataflow vCPU/GB-hours |
+
+## Prerequisites
+
+- Python 3.12+
+- A GCP project with the Earth Engine API enabled
+- `gcloud auth application-default login` (Colab handles auth automatically via
+  `datensee.notebook.ensure_auth()`)
+
+## Links
+
+- Source, issues, and full documentation:
+  <https://github.com/michaelfdewitt/datensee>
+- Colab quickstart:
+  <https://github.com/michaelfdewitt/datensee/blob/master/notebooks/datensee_quickstart.ipynb>
+
+Apache License 2.0.

datensee-0.1.0a1/pyproject.toml

@@ -0,0 +1,84 @@
+[project]
+name = "datensee"
+version = "0.1.0a1"
+description = "DatensEE: Parallelize Google Earth Engine exports via Cloud Dataflow"
+readme = "README.md"
+requires-python = ">=3.12"
+license = "Apache-2.0"
+keywords = [
+    "earth-engine",
+    "gee",
+    "dataflow",
+    "geotiff",
+    "cog",
+    "remote-sensing",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Environment :: Console",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: GIS",
+    "Typing :: Typed",
+]
+dependencies = [
+    "typer>=0.12",
+    "pydantic>=2.0",
+    "httpx>=0.27",
+    "rich>=13.0",
+    "pyproj>=3.6",
+    "shapely>=2.0",
+    "google-auth>=2.0",
+    "google-cloud-storage>=2.0",
+]
+
+[[project.authors]]
+name = "DatensEE Contributors"
+
+[project.urls]
+Homepage = "https://github.com/michaelfdewitt/datensee"
+Repository = "https://github.com/michaelfdewitt/datensee"
+Issues = "https://github.com/michaelfdewitt/datensee/issues"
+Changelog = "https://github.com/michaelfdewitt/datensee/releases"
+
+[project.scripts]
+datensee = "datensee.main:app"
+
+[project.optional-dependencies]
+validation = ["rasterio>=1.3"]
+
+[build-system]
+requires = ["uv_build>=0.10.10,<0.11.0"]
+build-backend = "uv_build"
+
+[tool.uv]
+package = true
+
+[tool.ruff]
+line-length = 100
+target-version = "py312"
+
+[tool.ruff.lint]
+select = [
+    "E",
+    "F",
+    "I",
+    "UP",
+    "B",
+]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[dependency-groups]
+dev = [
+    "earthengine-api>=1.7.24",
+    "jsonschema>=4.0",
+    "numpy>=2.4.3",
+    "pytest>=8.0",
+    "pytest-httpx>=0.30",
+    "ruff>=0.4",
+]

datensee-0.1.0a1/pyproject.toml.orig

@@ -0,0 +1,69 @@
+[project]
+name = "datensee"
+version = "0.1.0a1"
+description = "DatensEE: Parallelize Google Earth Engine exports via Cloud Dataflow"
+readme = "README.md"
+requires-python = ">=3.12"
+license = "Apache-2.0"
+authors = [{ name = "DatensEE Contributors" }]
+keywords = ["earth-engine", "gee", "dataflow", "geotiff", "cog", "remote-sensing"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Environment :: Console",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: GIS",
+    "Typing :: Typed",
+]
+dependencies = [
+    "typer>=0.12",
+    "pydantic>=2.0",
+    "httpx>=0.27",
+    "rich>=13.0",
+    "pyproj>=3.6",
+    "shapely>=2.0",
+    "google-auth>=2.0",
+    "google-cloud-storage>=2.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/michaelfdewitt/datensee"
+Repository = "https://github.com/michaelfdewitt/datensee"
+Issues = "https://github.com/michaelfdewitt/datensee/issues"
+Changelog = "https://github.com/michaelfdewitt/datensee/releases"
+
+[project.scripts]
+datensee = "datensee.main:app"
+
+[project.optional-dependencies]
+validation = ["rasterio>=1.3"]
+
+[build-system]
+requires = ["uv_build>=0.10.10,<0.11.0"]
+build-backend = "uv_build"
+
+[tool.uv]
+package = true
+
+[dependency-groups]
+dev = [
+    "earthengine-api>=1.7.24",
+    "jsonschema>=4.0",
+    "numpy>=2.4.3",
+    "pytest>=8.0",
+    "pytest-httpx>=0.30",
+    "ruff>=0.4",
+]
+
+[tool.ruff]
+line-length = 100
+target-version = "py312"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

datensee-0.1.0a1/src/datensee/__init__.py

@@ -0,0 +1,6 @@
+"""DatensEE: Parallelize Google Earth Engine exports via Cloud Dataflow."""
+
+from datensee._version import __version__  # noqa: F401
+
+# Public API — usable from notebooks and scripts without touching the CLI.
+from datensee.api import ExportResult, demo, export, poll, tile  # noqa: F401

datensee-0.1.0a1/src/datensee/_version.py

@@ -0,0 +1,17 @@
+"""Single source of truth for the package version at runtime.
+
+The version is declared once, in ``cli/pyproject.toml``; everything else
+derives from it: ``datensee.__version__``, the default Flex Template
+spec URI (``datensee.template``), the GitHub Release the pipeline JAR is
+downloaded from (``datensee.jar``), and the Gradle ``version`` (read
+from the same TOML by ``pipelines/build.gradle.kts``).
+"""
+
+from __future__ import annotations
+
+from importlib.metadata import PackageNotFoundError, version
+
+try:
+    __version__ = version("datensee")
+except PackageNotFoundError:  # source tree on sys.path without an install
+    __version__ = "0.0.0+unknown"