eotdl 2024.10.1__py3-none-any.whl → 2025.2.10__py3-none-any.whl

eotdl/__init__.py

@@ -1 +1 @@
-__version__ = "2024.10.01"
+__version__ = "2025.02.10"

eotdl/access/download.py

@@ -42,8 +42,9 @@ def download_sentinel_imagery(
         bulk = False
     else:
         bulk = True
-    client.download_data(requests_list)
-    imagery_from_tmp_to_dir(output, name=name, bulk=bulk)
+
+    data = client.download_data(requests_list)
+    imagery_from_tmp_to_dir(output, client.tmp_dir, name=name, bulk=bulk)
 
 
 def search_and_download_sentinel_imagery(

eotdl/access/search.py

@@ -19,8 +19,6 @@ def search_sentinel_imagery(
     evaluate_sentinel_parameters(
         sensor, time_interval, bounding_box, output_needed=False
     )
-
     client = SHClient()
     parameters = SH_PARAMETERS_DICT[sensor]()
-
     return client.search_data(bounding_box, time_interval, parameters)

eotdl/access/sentinelhub/client.py

@@ -15,6 +15,7 @@ from sentinelhub import (
     SentinelHubDownloadClient,
     MimeType,
 )
+import uuid
 
 from ...repos.AuthRepo import AuthRepo
 from .parameters import SHParameters
@@ -57,7 +58,7 @@ class SHClient:
                     self.config.sh_client_id = creds["SH_CLIENT_ID"]
                     self.config.sh_client_secret = creds["SH_CLIENT_SECRET"]
         self.catalog = SentinelHubCatalog(config=self.config)
-        self.tmp_dir = "/tmp/sentinelhub"
+        self.tmp_dir = "/tmp/sentinelhub/" + str(uuid.uuid4())
 
     def search_data(
         self, bounding_box: list, time_interval: list, parameters: SHParameters
@@ -109,5 +110,4 @@ class SHClient:
             requests = [requests]
         download_requests = [request.download_list[0] for request in requests]
         data = download_client.download(download_requests)
-
         return data

eotdl/access/sentinelhub/parameters.py

@@ -42,7 +42,7 @@ class SHS2L1CParameters(SHParameters):
         "include": ["id", "properties.datetime", "properties.eo:cloud_cover"],
         "exclude": [],
     }
-
+    FILTER = None
 
 class SHS1Parameters(SHParameters):
     """

eotdl/access/sentinelhub/utils.py

@@ -50,7 +50,7 @@ def evaluate_sentinel_parameters(
 
 def imagery_from_tmp_to_dir(
     output_dir: str,
-    tmp_dir: Optional[str] = "/tmp/sentinelhub",
+    tmp_dir: Optional[str],
     name: Optional[str] = None,
     bulk: Optional[bool] = False,
 ) -> None:
@@ -60,9 +60,7 @@ def imagery_from_tmp_to_dir(
     downloaded_files = glob(f"{tmp_dir}/**/response.tiff")
     if len(downloaded_files) == 0:
         return
-
     makedirs(output_dir, exist_ok=True)
-
     for downloaded_file in downloaded_files:
         request_json = downloaded_file.replace("response.tiff", "request.json")
         metadata = generate_raster_metadata(downloaded_file, request_json)
@@ -75,11 +73,9 @@ def imagery_from_tmp_to_dir(
                 output_filename = f"{metadata['type']}_{metadata['acquisition-date']}"
             else:
                 output_filename = metadata["type"]
-
         copyfile(downloaded_file, f"{output_dir}/{output_filename}.tif")
         with open(f"{output_dir}/{output_filename}.json", "w", encoding="utf-8") as f:
             json.dump(metadata, f)
-
     rmtree(tmp_dir)
 
 

eotdl/curation/stac/extensions/ml_dataset.py

@@ -377,7 +377,7 @@ class MLDatasetQualityMetrics:
                 destination
             )  # Remove the old catalog and replace it with the new one
             catalog.set_root(catalog)
-            catalog.normalize_and_save(root_href=destination)
+            catalog.normalize_and_save(root_href=destination, catalog_type=pystac.CatalogType.SELF_CONTAINED)
             print("Success!")
         except STACValidationError:
             # Return full callback

eotdl/datasets/ingest.py

@@ -3,6 +3,7 @@ import yaml
 from tqdm import tqdm
 import json
 import frontmatter
+import pystac
 
 from ..auth import with_auth
 from .metadata import Metadata
@@ -129,7 +130,7 @@ def ingest_stac(stac_catalog, logger=None, user=None):
     repo, files_repo = DatasetsAPIRepo(), FilesAPIRepo()
     # load catalog
     logger("Loading STAC catalog...")
-    df = STACDataFrame.from_stac_file(stac_catalog)
+    df = STACDataFrame.from_stac_file(stac_catalog) # assets are absolute for file ingestion
     catalog = df[df["type"] == "Catalog"]
     assert len(catalog) == 1, "STAC catalog must have exactly one root catalog"
     dataset_name = catalog.id.iloc[0]

eotdl/models/download.py

@@ -74,12 +74,12 @@ def download_model(
         )
         if error:
             raise Exception(error)
-        print(gdf)
+        # print(gdf)
         df = STACDataFrame(gdf)
         # df.geometry = df.geometry.apply(lambda x: Polygon() if x is None else x)
         df.to_stac(download_path)
-        print("----")
-        print(df)
+        # print("----")
+        # print(df)
         # download assets
         if assets:
             if verbose:

eotdl/repos/APIRepo.py

@@ -5,7 +5,7 @@ import requests
 class APIRepo:
     def __init__(self, url=None):
         default_url = "https://api.eotdl.com/"
-        # default_url = "http://localhost:8010/"
+        # default_url = "http://localhost:8001/"
         self.url = url if url else os.getenv("EOTDL_API_URL", default_url)
 
     def format_response(self, response):

eotdl/tools/geo_utils.py

@@ -127,6 +127,11 @@ def bbox_from_centroid(
     width_m = width * pixel_size
     heigth_m = height * pixel_size
 
+    # Initialise the transformers
+    utm_crs = CRS.get_utm_from_wgs84(y, x).ogc_string()
+    from_4326_transformer = Transformer.from_crs("EPSG:4326", utm_crs)
+    to_4326_transformer = Transformer.from_crs(utm_crs, "EPSG:4326")
+
     # Transform the centroid coordinates to meters
     centroid_m = from_4326_transformer.transform(x, y)
 
@@ -137,8 +142,8 @@ def bbox_from_centroid(
     max_y = centroid_m[1] + heigth_m / 2
 
     # Convert the bounding box coordinates back to degrees
-    min_x, min_y = from_3857_transformer.transform(min_x, min_y)
-    max_x, max_y = from_3857_transformer.transform(max_x, max_y)
+    min_x, min_y = to_4326_transformer.transform(min_x, min_y)
+    max_x, max_y = to_4326_transformer.transform(max_x, max_y)
 
     return [min_y, min_x, max_y, max_x]
 

eotdl/wrappers/__init__.py

@@ -0,0 +1 @@
+from .models import ModelWrapper

eotdl/wrappers/models.py

@@ -0,0 +1,158 @@
+# Q1+ model wrapper
+# only works with some models, extend as we include more models in EOTDL and improve MLM extension
+
+import os 
+from pathlib import Path
+from tqdm import tqdm
+import numpy as np
+
+from ..models.retrieve import retrieve_model
+from ..curation.stac import STACDataFrame
+from ..repos import FilesAPIRepo, ModelsAPIRepo
+from ..auth import with_auth
+
+class ModelWrapper:
+    def __init__(self, model_name, version=None, path=None, force=False, assets=True, verbose=True):
+        self.model_name = model_name
+        self.version = version
+        self.path = path
+        self.force = force
+        self.assets = assets
+        self.verbose = verbose
+        self.ready = False
+        self.setup()
+
+    def setup(self):
+        download_path, gdf = self.download()
+        self.download_path = download_path
+        self.gdf = gdf
+        # get model name from stac metadata
+        item = gdf[gdf['type'] == "Feature"]
+        assert item.shape[0] == 1, "Only one item is supported in stac metadata, found " + str(item.shape[0])
+        self.props = item.iloc[0].properties
+        assert self.props["mlm:framework"] == "ONNX", "Only ONNX models are supported, found " + self.props["mlm:framework"]
+        model_name = self.props["mlm:name"]
+        self.model_path = download_path + '/assets/' + model_name
+        self.ready = True
+
+    def predict(self, x):
+        if not self.ready:
+            self.setup()
+        ort_session = self.get_onnx_session(self.model_path)
+        # preprocess input
+        x = self.process_inputs(x)
+        # execute model
+        input_name = ort_session.get_inputs()[0].name
+        ort_inputs = {input_name: x}
+        ort_outs = ort_session.run(None, ort_inputs)
+        output_nodes = ort_session.get_outputs()
+        output_names = [node.name for node in output_nodes]
+        # format and return outputs
+        return self.return_outputs(ort_outs, output_names)
+
+    @with_auth
+    def download(self, user=None):
+        # download the model
+        model = retrieve_model(self.model_name)
+        if model["quality"] == 0:
+            raise Exception("Only Q1+ models are supported")
+        if self.version is None:
+            self.version = sorted(model["versions"], key=lambda v: v["version_id"])[-1][
+                "version_id"
+            ]
+        else:
+            assert self.version in [
+                v["version_id"] for v in model["versions"]
+            ], f"Version {self.version} not found"
+        download_base_path = os.getenv(
+            "EOTDL_DOWNLOAD_PATH", str(Path.home()) + "/.cache/eotdl/models"
+        )
+        if self.path is None:
+            download_path = download_base_path + "/" + self.model_name + "/v" + str(self.version)
+        else:
+            download_path = self.path + "/" + self.model_name + "/v" + str(self.version)
+        # check if model already exists
+        if os.path.exists(download_path) and not self.force:
+            os.makedirs(download_path, exist_ok=True)
+            gdf = STACDataFrame.from_stac_file(download_path + f"/{self.model_name}/catalog.json")
+            return download_path, gdf
+        if self.verbose:
+            print("Downloading STAC metadata...")
+        repo = ModelsAPIRepo()
+        gdf, error = repo.download_stac(
+            model["id"],
+            user,
+        )
+        if error:
+            raise Exception(error)
+        df = STACDataFrame(gdf)
+        # df.geometry = df.geometry.apply(lambda x: Polygon() if x is None else x)
+        df.to_stac(download_path)
+        # download assets
+        if self.assets:
+            if self.verbose:
+                print("Downloading assets...")
+            repo = FilesAPIRepo()
+            df = df.dropna(subset=["assets"])
+            for row in tqdm(df.iterrows(), total=len(df)):
+                for k, v in row[1]["assets"].items():
+                    href = v["href"]
+                    _, filename = href.split("/download/")
+                    # will overwrite assets with same name :(
+                    repo.download_file_url(
+                        href, filename, f"{download_path}/assets", user
+                    )
+        else:
+            print("To download assets, set assets=True.")
+        if self.verbose:
+            print("Done")
+        return download_path, gdf
+
+    def process_inputs(self, x):
+        # pre-process and validate input
+        input = self.props["mlm:input"]
+        # input data type
+        dtype = input["input"]["data_type"]
+        x = x.astype(dtype)
+        # input shape
+        input_shape = input["input"]["shape"]
+        ndims = len(input_shape)
+        if ndims != x.ndim:
+            if ndims == 4:
+                x = np.expand_dims(x, axis=0).astype(np.float32)
+            else:
+                raise Exception("Input shape not valid", input_shape, x.ndim)
+        for i, dim in enumerate(input_shape):
+            if dim != -1:
+                assert dim == x.shape[i], f"Input dimension not valid: The model expects {input_shape} but input has {x.shape} (-1 means any dimension)."
+        # TODO: should apply normalization if defined in metadata
+        return x
+    
+    def return_outputs(self, ort_outputs, output_names):
+        if self.props["mlm:output"]["tasks"] == ["classification"]:
+            return {
+                "model": self.model_name,
+                **{
+                    output: ort_outputs[i].tolist() for i, output in enumerate(output_names)
+                },
+            }
+        elif self.props["mlm:output"]["tasks"] == ["segmentation"]:
+            outputs = {output: ort_outputs[i] for i, output in enumerate(output_names)}
+            batch = outputs[output_names[0]]
+            image = batch[0]
+            return image
+        else:
+            raise Exception("Output task not supported:", self.props["mlm:output"]["tasks"])
+
+    def get_onnx_session(self, model):        
+        try:
+            import onnxruntime as ort
+            # gpu requires `pip install onnxruntime-gpu` but no extra imports
+        except ImportError:
+            raise ImportError("onnxruntime is not installed. Please install it with `pip install onnxruntime`")
+        providers = ["CUDAExecutionProvider", "CPUExecutionProvider"]
+        try:
+            session = ort.InferenceSession(model, providers=providers)
+        except Exception as e:
+            raise RuntimeError(f"Error loading ONNX model: {str(e)}")
+        return session

{eotdl-2024.10.1.dist-info → eotdl-2025.2.10.dist-info}/METADATA

@@ -1,35 +1,23 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: eotdl
-Version: 2024.10.1
+Version: 2025.2.10
 Summary: Earth Observation Training Data Lab
-License: MIT
-Author: EarthPulse
-Author-email: it@earthpulse.es
-Requires-Python: >=3.8,<4.0
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Requires-Dist: black (>=23.10.1,<24.0.0)
-Requires-Dist: geomet (>=1.0.0,<2.0.0)
-Requires-Dist: geopandas (>=0.13.2,<0.14.0)
-Requires-Dist: markdown (>=3.5.2,<4.0.0)
-Requires-Dist: markdownify (>=0.11.6,<0.12.0)
-Requires-Dist: mypy (>=1.6.1,<2.0.0)
-Requires-Dist: openeo (>=0.31.0,<0.32.0)
-Requires-Dist: pydantic (>=1.10.6,<2.0.0)
-Requires-Dist: pyjwt (>=2.6.0,<3.0.0)
-Requires-Dist: pystac[validation] (==1.8.2)
-Requires-Dist: python-frontmatter (>=1.1.0,<2.0.0)
-Requires-Dist: pyyaml (>=6.0.1,<7.0.0)
-Requires-Dist: rasterio (>=1.3.9,<2.0.0)
-Requires-Dist: requests (>=2.28.2,<3.0.0)
-Requires-Dist: sentinelhub (>=3.9.1,<4.0.0)
-Requires-Dist: tqdm (>=4.65.0,<5.0.0)
-Requires-Dist: typer[all] (>=0.9.0,<0.10.0)
+Author-email: earthpulse <it@earthpulse.es>
+License-Expression: MIT
+Requires-Python: >=3.8
+Requires-Dist: geomet>=1.1.0
+Requires-Dist: geopandas>=0.13.2
+Requires-Dist: markdown>=3.7
+Requires-Dist: pydantic>=2.10.6
+Requires-Dist: pyjwt>=2.9.0
+Requires-Dist: pystac>=1.8.4
+Requires-Dist: python-frontmatter>=1.1.0
+Requires-Dist: pyyaml>=6.0.2
+Requires-Dist: rasterio>=1.3.11
+Requires-Dist: requests>=2.32.3
+Requires-Dist: sentinelhub>=3.11.1
+Requires-Dist: tqdm>=4.67.1
+Requires-Dist: typer>=0.15.1
 Description-Content-Type: text/markdown
 
 <p align="center">
@@ -49,10 +37,10 @@ Description-Content-Type: text/markdown
 
 This is the main library and CLI for the **Earth Observation Training Data Lab** (EOTDL), a complete environment that allows you, among other things, to:
 
-- Explore and download Training Datasets (TDS) for Earth Observation (EO) applications.
+- Explore and stage Training Datasets (TDS) for Earth Observation (EO) applications.
 - Create and upload your own TDS by combining and annotating EO data from different sources.
 - Train Machine Learning (ML) models using the hosted TDS in the cloud with multi-GPU machines.
-- Explore and download pre-trianed ML models for EO applications.
+- Explore and stage pre-trianed ML models for EO applications.
 
 In our blog you will find tutorials to learn how leverage the EOTDL to create and use TDS and ML models for your own EO applications.
 
@@ -62,4 +50,4 @@ One of the most limiting factors of AI for EO applications is the scarcity of su
 
 Generating TDS is time consuming and expensive. Data access is usually limited and costly, especially for Very High Resolution (VHR) images that allow objects like trees to be clearly identified. In some cases, domain experts or even in-person (in-situ) trips are required to manually confirm the objects in a satellite image are correctly annotated with a high degree of quality. This results in the field of AI for EO applications lagging when compared to other fields, impeding the development of new applications and limiting the full potential of AI in EO.
 
-The European Space Agency (ESA) Earth Observation Training Data Lab (EOTDL) will address key limitations and capability gaps for working with Machine Learning (ML) training data in EO by providing a set of open-source tools to create, share, and improve datasets as well as training ML algorithms in the cloud. EOTDL will also offer an online repository where datasets and models can be explored and accessed.
+The European Space Agency (ESA) Earth Observation Training Data Lab (EOTDL) will address key limitations and capability gaps for working with Machine Learning (ML) training data in EO by providing a set of open-source tools to create, share, and improve datasets as well as training ML algorithms in the cloud. EOTDL will also offer an online repository where datasets and models can be explored and accessed.

{eotdl-2024.10.1.dist-info → eotdl-2025.2.10.dist-info}/RECORD

@@ -1,22 +1,22 @@
-eotdl/__init__.py,sha256=GYhbp_qDI4r7Y9hYO76t0DwK_JCtUw2UK-DbHzV4XKk,27
+eotdl/__init__.py,sha256=FAoVIMt0RmGmgzADLwWcGchcDVZIL8E-tw-vbRw_mfY,27
+eotdl/cli.py,sha256=qGtdOV2gcy-YYdc-tUwzxV6X7SLWmwb9L8pBQGD6OzY,660
 eotdl/access/__init__.py,sha256=jbyjD7BRGJURlTNmtcbBBhw3Xk4EiZvkqmEykM-bJ1k,231
+eotdl/access/download.py,sha256=5LHTxuV9BQzwYVGSaMoUqr7EEdYOhqY_QGDaChru6Pw,1869
+eotdl/access/search.py,sha256=JW4MnM3xbXxvsaNCFkRKxPhxhNKJgZAutE2wna6qUpo,631
 eotdl/access/airbus/__init__.py,sha256=G_kkRS9eFjXbQ-aehmTLXeAxh7zpAxz_rgB7J_w0NRg,107
 eotdl/access/airbus/client.py,sha256=zjfgB_NTsCCIszoQesYkyLJgheKg-eTh28vbleXYxfw,12018
 eotdl/access/airbus/parameters.py,sha256=Z8XIrxG5wAOuOoH-fkdKfdNMEMLFp6PaxJN7v4MefMI,1009
 eotdl/access/airbus/utils.py,sha256=oh_N1Rn4fhcvUgNPpH2QzVvpe4bA0gqRgNguzRVqUps,652
-eotdl/access/download.py,sha256=DgemJKafNOlCUVW8OxpSP4br9ij5F1iSrSD-x0B5qFU,1845
-eotdl/access/search.py,sha256=sO2hml6JLK30DncNUqTWq16zy9LvRiWC6wtt5bNRzrI,633
 eotdl/access/sentinelhub/__init__.py,sha256=YpvaUBTRXM26WrXipo51ZUBCDv9WjRIdT8l1Pklpt_M,238
-eotdl/access/sentinelhub/client.py,sha256=g40avqlUpIa-WLjD7tK8CL8_SohBA2v3m8NZ0KbIFxc,4098
+eotdl/access/sentinelhub/client.py,sha256=DNR27NbAH2ZZZeArsl95qOnaaXJvgnXTjpxFKX4OYDc,4130
 eotdl/access/sentinelhub/evalscripts.py,sha256=m6cnZ6ryXHgdH2B7RDVSlDHXWfvKi7HMGkTHXEcJsTw,4142
-eotdl/access/sentinelhub/parameters.py,sha256=Ni3Lqx1bLVcMzgmnuayDS00BLDm7SuM1FExVdGafopI,2061
-eotdl/access/sentinelhub/utils.py,sha256=X9Q1YvErBdMsRKszXyaOaG6ZMvPdM2Nl_0SH-dWSFo0,3560
+eotdl/access/sentinelhub/parameters.py,sha256=SEal7mCPkADc7lhQL-63t2h5-XCssYpGMvK5Eo3etFU,2078
+eotdl/access/sentinelhub/utils.py,sha256=h3V-f-qmoq62cRbE0PWn7x3O1nOTGrCudm_bXm91XSU,3535
 eotdl/auth/__init__.py,sha256=OuGNfJQ-8Kymn4zIywlHQfImEO8DJMJIwOwTQm-u_dc,99
 eotdl/auth/auth.py,sha256=EjbVFREA2H0sjFJhVqjFZrwjKPzxRJ2x83MTjizpRBs,2029
 eotdl/auth/errors.py,sha256=E1lv3Igk--J-SOgNH18i8Xx9bXrrMyBSHKt_CAUmGPo,308
 eotdl/auth/is_logged.py,sha256=QREuhkoDnarZoUZwCxVCNoESGb_Yukh0lJo1pXvrV9Q,115
 eotdl/auth/logout.py,sha256=P_Sp6WmVvnG3R9V1L9541KNyHFko9DtQPqAKD2vaguw,161
-eotdl/cli.py,sha256=qGtdOV2gcy-YYdc-tUwzxV6X7SLWmwb9L8pBQGD6OzY,660
 eotdl/commands/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 eotdl/commands/auth.py,sha256=WzA0aFGRoscy7fPKQTxiphBc0LJztJxBBl7rjDBRVfI,1544
 eotdl/commands/datasets.py,sha256=wiH4OimpOgvONtnHkNi8PWb8I7kR7kNm61dcz9vgZtE,5205
@@ -27,24 +27,24 @@ eotdl/curation/stac/assets.py,sha256=ay3JO6iEANMqTAe40sF7QYeEY574LbrhyanqSlVUITc
 eotdl/curation/stac/dataframe.py,sha256=w0CXK4tAegbXQgnXbak2QbLfWgC6SQXpR2g-snoimAM,5503
 eotdl/curation/stac/dataframe_bck.py,sha256=PwAwol7kll0xYtlkhLeQ_Sc5TBQ85cVd6eyzdfTMJnE,8493
 eotdl/curation/stac/dataframe_labeling.py,sha256=F22-4gpF9zFuCLqRva2XAyArOmGdrgGxXbgo9d54BFE,1520
+eotdl/curation/stac/extent.py,sha256=Jb3K4v59eu_h5t429r0762o0zG_LA50iEE-abWNL0e0,5108
+eotdl/curation/stac/parsers.py,sha256=H5IukLA61mpLojeuhWNQdiZk2eiYHAfpJBFxmjdGDso,1529
+eotdl/curation/stac/stac.py,sha256=9GdiB1mV8iyREvXZoJmNJKQGawWyK3h9Eu0hJX5u6O4,13180
 eotdl/curation/stac/extensions/__init__.py,sha256=NSzKe14Iyr8Pm2AVg8RHxddtBD2so45--BRJmJd8bTs,629
 eotdl/curation/stac/extensions/base.py,sha256=HDisHg43aC3tJjqKdJVyQMfXc0jLHZEVYrTve9lmZak,671
 eotdl/curation/stac/extensions/dem.py,sha256=ecCLfg_izIjfWBvoKNl_WLNVuNqNiQWLaWxshNucTyY,370
 eotdl/curation/stac/extensions/eo.py,sha256=cT4RrbyoimIuuOxNRLkamhZgHpDbj4z_Ziat2G2gTuA,4004
+eotdl/curation/stac/extensions/ml_dataset.py,sha256=8G1-1yljfHhp5tKk3rGysB9M_0-Upa5WN9y1s6O5nno,21477
+eotdl/curation/stac/extensions/projection.py,sha256=ussVIwr_wOOhn07OmpAWY4qqbeAmYUxKjbE8onrAy7o,1236
+eotdl/curation/stac/extensions/raster.py,sha256=o5U_1ow8BsgwZXpSQYwQIvMJldhyn7xoGoJmUANTJTE,1540
+eotdl/curation/stac/extensions/sar.py,sha256=Akw3_5brY_x2yU094nSLbv0E6M9jnAeUC0Vo5fJDRME,1633
 eotdl/curation/stac/extensions/label/__init__.py,sha256=R6xLkgJaZHoMh5BhpmueupWdM9NWKvmaRurum-ryU_s,159
 eotdl/curation/stac/extensions/label/base.py,sha256=5xbniQWjzXkrQxxXp8v9QQxFQdRYnaFPBd5_in1QXUw,4069
 eotdl/curation/stac/extensions/label/image_name_labeler.py,sha256=bivZN-qEtIXE6ehqwPKRsJO9RVckZ1lK2BG8ifUbaA8,8074
 eotdl/curation/stac/extensions/label/scaneo.py,sha256=uUzEqEwdnKYZx-qx9o6d8HcXp1VPy8eYWc9kM0sjiyA,8787
-eotdl/curation/stac/extensions/ml_dataset.py,sha256=SjOX_EvVRhwIUc4iQLw6YX_bG3VTqlRd9SpmpNCnRak,21429
-eotdl/curation/stac/extensions/projection.py,sha256=ussVIwr_wOOhn07OmpAWY4qqbeAmYUxKjbE8onrAy7o,1236
-eotdl/curation/stac/extensions/raster.py,sha256=o5U_1ow8BsgwZXpSQYwQIvMJldhyn7xoGoJmUANTJTE,1540
-eotdl/curation/stac/extensions/sar.py,sha256=Akw3_5brY_x2yU094nSLbv0E6M9jnAeUC0Vo5fJDRME,1633
-eotdl/curation/stac/extent.py,sha256=Jb3K4v59eu_h5t429r0762o0zG_LA50iEE-abWNL0e0,5108
-eotdl/curation/stac/parsers.py,sha256=H5IukLA61mpLojeuhWNQdiZk2eiYHAfpJBFxmjdGDso,1529
-eotdl/curation/stac/stac.py,sha256=9GdiB1mV8iyREvXZoJmNJKQGawWyK3h9Eu0hJX5u6O4,13180
 eotdl/datasets/__init__.py,sha256=xNbkUjqI1mf0TGjy52tpZtr5DnWNX5EVgyM04P4sU3Y,175
 eotdl/datasets/download.py,sha256=JSOi7OKiENYQ3TRVj2WsC1CPYD22VlC9W5kYHPfx8Vs,3667
-eotdl/datasets/ingest.py,sha256=F7mwQQok3rqZkGiQC-71Jc4dYDN5OSB_SXEACdCZKkk,5742
+eotdl/datasets/ingest.py,sha256=p8Clp_QAWaixeudA-rKcARxxLIvj_voNYOJmZ6LhIWE,5797
 eotdl/datasets/metadata.py,sha256=jRoW9n32sUQgX3439WUCL8BJZojXKKXpmCM344XMDMc,1432
 eotdl/datasets/retrieve.py,sha256=DJz5K1bCLizg9YNwBnhHMFzcxMXar2socYkFONdSL4c,1041
 eotdl/datasets/update.py,sha256=x-rpfxnavn9X-7QYkFMGtbn1b3bKmAZydOeS7Tjr5AQ,386
@@ -52,12 +52,12 @@ eotdl/files/__init__.py,sha256=2zfAxgLHmU_jWq_3emnfPXsX-R20gSt-yZX0bPa9h0g,87
 eotdl/files/ingest.py,sha256=dgjZfd-ACCKradDo2B02CPahwEhFtWvnKvTm372K5eo,6185
 eotdl/files/list_files.py,sha256=k4OgdbQ7u6tUEE9nJZGXw5s5HtvG0ZApOVTy0KbfTqs,519
 eotdl/models/__init__.py,sha256=-PvGWG0iSRNBqeFWpxol12dYw-QodXjR81n-JX3x6zI,146
-eotdl/models/download.py,sha256=ppCeKsK2YzdimYRKXiF5dfGI6VyXw_T9lOnKO54Ojjg,3469
+eotdl/models/download.py,sha256=rRT3fG-qS3-SXfzFdqy0cuiDnOIV9Du74JCnsbbA9Ps,3475
 eotdl/models/ingest.py,sha256=ipWNSyL8WwW9PPUAFcS9mLYow_1PTCpNQ_DsXKQ3Hvw,5671
 eotdl/models/metadata.py,sha256=Lu_Vv6YJJ9aLPvJa44tFfbBZiyxweOI2BHfq00aNRjY,1378
 eotdl/models/retrieve.py,sha256=-Ij7dT4J1p7MW4n13OlPB9OW4tBaBXPwk9dW8IuCZPc,664
 eotdl/models/update.py,sha256=4FWeD95cXvRpefRjw3Foqb30e30otxqWUZ6nQM9cbmM,374
-eotdl/repos/APIRepo.py,sha256=dJNdX3atBpug0FZNako7uyom25iccNPQrnoIRTIZEXE,791
+eotdl/repos/APIRepo.py,sha256=as06DHfRtENMEYTAeAbYf0XGHU7E8LNxGHGpIH8lzoE,791
 eotdl/repos/AuthAPIRepo.py,sha256=vYCqFawe3xUm2cx4SqVXCvzl8J_sr9rs_MkipYC0bXE,957
 eotdl/repos/AuthRepo.py,sha256=jpzzhINCcDZHRCyrPDsp49h17IlXp2HvX3BB3f5cnb4,1154
 eotdl/repos/DatasetsAPIRepo.py,sha256=rKqSe-UjJOlD0Kbypu4Gs5kx2mzUD7TY05gv2vgUTv4,2660
@@ -67,13 +67,15 @@ eotdl/repos/__init__.py,sha256=WvX5TP49k7yYb5dWWNjv5kzbdluO3dJ4LqjQxRIOUVc,222
 eotdl/shared/__init__.py,sha256=mF7doJC8Z5eTPmB01UQvPivThZac32DRY33T6qshXfg,41
 eotdl/shared/checksum.py,sha256=4IB6N9jRO0chMDNJzpdnFDhC9wcFF9bO5oHq2HodcHw,479
 eotdl/tools/__init__.py,sha256=_p3n2dw3ulwyr1OlVw5d_jMV64cNYfajQMUbzFfvIpU,178
-eotdl/tools/geo_utils.py,sha256=yZA100UH0pbH8T6wb9Kfv_VRDKYYtQDPTud3Ddkdsok,7320
+eotdl/tools/geo_utils.py,sha256=JKHUAnqkwiIrvh5voDclWAW-i57qVqH2FUjeOt1TQf4,7547
 eotdl/tools/metadata.py,sha256=RvNmoMdfEKoo-DzhEAqL-f9ZCjIe_bsdHQwACMk6w1E,1664
 eotdl/tools/paths.py,sha256=yWhOtVxX4NxrDrrBX2fuye5N1mAqrxXFy_eA7dffd84,1152
 eotdl/tools/stac.py,sha256=ovXdrPm4Sn9AAJmrP88WnxDmq2Ut-xPoscjphxz3Iyo,5763
 eotdl/tools/time_utils.py,sha256=qJ3-rk1I7ne722SLfAP6-59kahQ0vLQqIf9VpOi0Kpg,4691
 eotdl/tools/tools.py,sha256=Tl4_v2ejkQo_zyZek8oofJwoYcdVosdOwW1C0lvWaNM,6354
-eotdl-2024.10.1.dist-info/METADATA,sha256=FSAul-2xBkcUyN-T0tk8YX0Kp_ZzlQ4AAk0e9IxYmKk,4144
-eotdl-2024.10.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-eotdl-2024.10.1.dist-info/entry_points.txt,sha256=s6sfxUfRrSX2IP2UbrzTFTvRCtLgw3_OKcHlOKf_5F8,39
-eotdl-2024.10.1.dist-info/RECORD,,
+eotdl/wrappers/__init__.py,sha256=IY3DK_5LMbc5bIQFleQA9kzFbPhWuTLesJ8dwfvpkdA,32
+eotdl/wrappers/models.py,sha256=kNO4pYw9KKKmElE7bZWWHGs7FIThNUXj8XciKh_3rNw,6432
+eotdl-2025.2.10.dist-info/METADATA,sha256=3gr3B3iSZA_mKlFpSqvSvF78cm9KioYXE63MOB2oyEc,3479
+eotdl-2025.2.10.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+eotdl-2025.2.10.dist-info/entry_points.txt,sha256=FV4dFIZ5zdWj1q1nUEEip29n3sAgbviVOizEz00gEF0,40
+eotdl-2025.2.10.dist-info/RECORD,,

{eotdl-2024.10.1.dist-info → eotdl-2025.2.10.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.9.0
+Generator: hatchling 1.27.0
 Root-Is-Purelib: true
 Tag: py3-none-any

eotdl-2025.2.10.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+eotdl = eotdl.cli:app

eotdl-2024.10.1.dist-info/entry_points.txt

@@ -1,3 +0,0 @@
-[console_scripts]
-eotdl=eotdl.cli:app
-