eotdl 2025.4.2__py3-none-any.whl → 2025.4.2.post2__py3-none-any.whl

eotdl/__init__.py

@@ -1 +1 @@
-__version__ = "2025.04.02"
+__version__ = "2025.04.02-2"

eotdl/repos/DatasetsAPIRepo.py

@@ -1,9 +1,7 @@
 import requests
-import geopandas as gpd
 
 from ..repos import APIRepo
 
-
 class DatasetsAPIRepo(APIRepo):
     def __init__(self, url=None):
         super().__init__(url)
@@ -43,51 +41,3 @@ class DatasetsAPIRepo(APIRepo):
             headers=self.generate_headers(user),
         )
         return self.format_response(response)
-
-
-    # def create_version(self, dataset_id, user):
-    #     response = requests.post(
-    #         self.url + "datasets/version/" + dataset_id,
-    #         headers=self.generate_headers(user),
-    #     )
-    #     return self.format_response(response)
-
-    # def create_stac_dataset(self, name, user):
-    #     response = requests.post(
-    #         self.url + "datasets/stac",
-    #         json={"name": name},
-    #         headers=self.generate_headers(user),
-    #     )
-    #     return self.format_response(response)
-
-    # def ingest_stac(self, stac_json, dataset_id, user):
-    #     response = requests.put(
-    #         self.url + f"datasets/stac/{dataset_id}",
-    #         json={"stac": stac_json},
-    #         headers=self.generate_headers(user),
-    #     )
-    #     return self.format_response(response)
-
-    # def download_stac(self, dataset_id, user):
-    #     url = self.url + "datasets/" + dataset_id + "/download"
-    #     headers = self.generate_headers(user)
-    #     response = requests.get(url, headers=headers)
-    #     if response.status_code != 200:
-    #         return None, response.json()["detail"]
-    #     return gpd.GeoDataFrame.from_features(response.json()["features"]), None
-
-    # def update_dataset(
-    #     self, dataset_id, authors, source, license, thumbnail, content, user
-    # ):
-    #     response = requests.put(
-    #         self.url + f"datasets/{dataset_id}",
-    #         json={
-    #             "authors": authors,
-    #             "source": source,
-    #             "license": license,
-    #             "thumbnail": thumbnail,
-    #             "description": content,
-    #         },
-    #         headers=self.generate_headers(user),
-    #     )
-    #     return self.format_response(response)

eotdl/repos/FilesAPIRepo.py

@@ -1,8 +1,5 @@
 import requests
 import os
-from tqdm import tqdm
-import hashlib
-from io import BytesIO
 
 from ..repos import APIRepo
 
@@ -103,191 +100,4 @@ class FilesAPIRepo(APIRepo):
         if error:
             # print("ERROR generate_presigned_url", error)
             return None
-        return data["presigned_url"]
-
-        # can we download large files?
-
-        # with requests.get(presigned_url, headers=headers, stream=True) as r:
-        #     r.raise_for_status()
-        #     total_size = int(r.headers.get("content-length", 0))
-        #     block_size = 1024 * 1024 * 10
-        #     progress = progress and total_size > 1024 * 1024 * 16
-        #     if progress:
-        #         progress_bar = tqdm(
-        #             total=total_size,
-        #             unit="iB",
-        #             unit_scale=True,
-        #             unit_divisor=1024,
-        #             position=1,
-        #         )
-        #     with open(path, "wb") as f:
-        #         for chunk in r.iter_content(block_size):
-        #             if progress:
-        #                 progress_bar.update(len(chunk))
-        #             if chunk:
-        #                 f.write(chunk)
-        #     if progress:
-        #         progress_bar.close()
-        #     return path
-
-
-
-    # def ingest_files_batch(
-    #     self,
-    #     batch,  # ziped batch of files
-    #     checksums,
-    #     dataset_or_model_id,
-    #     user,
-    #     endpoint,
-    #     version=None,
-    # ):
-    #     url = self.url + f"{endpoint}/{dataset_or_model_id}/batch"
-    #     if version is not None:
-    #         url += "?version=" + str(version)
-    #     reponse = requests.post(
-    #         url,
-    #         files={"batch": ("batch.zip", batch)},
-    #         data={"checksums": checksums},
-    #         headers=self.generate_headers(user),
-    #     )
-    #     return self.format_response(reponse)
-
-    # def add_files_batch_to_version(
-    #     self,
-    #     batch,
-    #     dataset_or_model_id,
-    #     version,
-    #     user,
-    #     endpoint,
-    # ):
-    #     reponse = requests.post(
-    #         self.url + f"{endpoint}/{dataset_or_model_id}/files?version={str(version)}",
-    #         data={
-    #             "filenames": [f["path"] for f in batch],
-    #             "checksums": [f["checksum"] for f in batch],
-    #         },
-    #         headers=self.generate_headers(user),
-    #     )
-    #     return self.format_response(reponse)
-
-    # def retrieve_files(self, dataset_or_model_id, endpoint, version=None):
-    #     url = f"{self.url}{endpoint}/{dataset_or_model_id}/files"
-    #     if version is not None:
-    #         url += "?version=" + str(version)
-    #     response = requests.get(url)
-    #     return self.format_response(response)
-
-
-
-    # def download_file_url(self, url, filename, path, user, progress=False):
-    #     headers = self.generate_headers(user)
-    #     path = f"{path}/{filename}"
-    #     for i in range(1, len(path.split("/")) - 1):
-    #         # print("/".join(path.split("/")[: i + 1]))
-    #         os.makedirs("/".join(path.split("/")[: i + 1]), exist_ok=True)
-    #     with requests.get(url, headers=headers, stream=True) as r:
-    #         r.raise_for_status()
-    #         total_size = int(r.headers.get("content-length", 0))
-    #         block_size = 1024 * 1024 * 10
-    #         progress = progress and total_size > 1024 * 1024 * 16
-    #         if progress:
-    #             progress_bar = tqdm(
-    #                 total=total_size,
-    #                 unit="iB",
-    #                 unit_scale=True,
-    #                 unit_divisor=1024,
-    #                 position=1,
-    #             )
-    #         with open(path, "wb") as f:
-    #             for chunk in r.iter_content(block_size):
-    #                 if progress:
-    #                     progress_bar.update(len(chunk))
-    #                 if chunk:
-    #                     f.write(chunk)
-    #         if progress:
-    #             progress_bar.close()
-    #         return path
-
-    # def prepare_large_upload(
-    #     self, filename, dataset_or_model_id, checksum, user, endpoint
-    # ):
-    #     response = requests.post(
-    #         self.url + f"{endpoint}/{dataset_or_model_id}/uploadId",
-    #         json={"filname": filename, "checksum": checksum},
-    #         headers=self.generate_headers(user),
-    #     )
-    #     if response.status_code != 200:
-    #         raise Exception(response.json()["detail"])
-    #     data = response.json()
-    #     upload_id, parts = (
-    #         data["upload_id"],
-    #         data["parts"] if "parts" in data else [],
-    #     )
-    #     return upload_id, parts
-
-    # def get_chunk_size(self, content_size):
-    #     # adapt chunk size to content size to avoid S3 limits (10000 parts, 500MB per part, 5TB per object)
-    #     chunk_size = 1024 * 1024 * 10  # 10 MB (up to 100 GB, 10000 parts)
-    #     if content_size >= 1024 * 1024 * 1024 * 100:  # 100 GB
-    #         chunk_size = 1024 * 1024 * 100  # 100 MB (up to 1 TB, 10000 parts)
-    #     elif content_size >= 1024 * 1024 * 1024 * 1000:  # 1 TB
-    #         chunk_size = 1024 * 1024 * 500  # 0.5 GB (up to 5 TB, 10000 parts)
-    #     return chunk_size
-
-    # def read_in_chunks(self, file_object, CHUNK_SIZE):
-    #     while True:
-    #         data = file_object.read(CHUNK_SIZE)
-    #         if not data:
-    #             break
-    #         yield data
-
-    # def ingest_large_file(
-    #     self, file_path, files_size, upload_id, user, parts, endpoint
-    # ):
-    #     print(endpoint)
-    #     # content_path = os.path.abspath(file)
-    #     # content_size = os.stat(content_path).st_size
-    #     chunk_size = self.get_chunk_size(files_size)
-    #     total_chunks = files_size // chunk_size
-    #     # upload chunks sequentially
-    #     pbar = tqdm(
-    #         self.read_in_chunks(open(file_path, "rb"), chunk_size),
-    #         total=total_chunks,
-    #     )
-    #     index = 0
-    #     for chunk in pbar:
-    #         part = index // chunk_size + 1
-    #         offset = index + len(chunk)
-    #         index = offset
-    #         if part not in parts:
-    #             checksum = hashlib.md5(chunk).hexdigest()
-    #             response = requests.post(
-    #                 f"{self.url}{endpoint}/chunk/{upload_id}",
-    #                 files={"file": chunk},
-    #                 data={"part_number": part, "checksum": checksum},
-    #                 headers=self.generate_headers(user),
-    #             )
-    #             if response.status_code != 200:
-    #                 raise Exception(response.json()["detail"])
-    #         pbar.set_description(
-    #             "{:.2f}/{:.2f} MB".format(
-    #                 offset / 1024 / 1024, files_size / 1024 / 1024
-    #             )
-    #         )
-    #     pbar.close()
-    #     return
-
-    # def complete_upload(self, user, upload_id, version, endpoint):
-    #     r = requests.post(
-    #         f"{self.url}{endpoint}/complete/{upload_id}?version={version}",
-    #         headers=self.generate_headers(user),
-    #     )
-    #     return self.format_response(r)
-    
-    # def get_file_stream(self, dataset_id, filename, user, version=None):
-    #     url = self.url + f"datasets/{dataset_id}/download/{filename}"
-    #     if version is not None:
-    #         url += "?version=" + str(version)
-    #     headers = self.generate_headers(user)
-    #     response = requests.get(url, headers=headers, stream=True)
-    #     return BytesIO(response.content)
+        return data["presigned_url"]

eotdl/repos/ModelsAPIRepo.py

@@ -1,9 +1,7 @@
 import requests
-import geopandas as gpd
 
 from ..repos import APIRepo
 
-
 class ModelsAPIRepo(APIRepo):
     def __init__(self, url=None):
         super().__init__(url)
@@ -40,49 +38,4 @@ class ModelsAPIRepo(APIRepo):
         )
         return self.format_response(response)
 
-    # def create_version(self, model_id, user):
-    #     response = requests.post(
-    #         self.url + "models/version/" + model_id,
-    #         headers=self.generate_headers(user),
-    #     )
-    #     return self.format_response(response)
-
-    # def update_model(
-    #     self, model_id, authors, source, license, thumbnail, content, user
-    # ):
-    #     response = requests.put(
-    #         self.url + f"models/{model_id}",
-    #         json={
-    #             "authors": authors,
-    #             "source": source,
-    #             "license": license,
-    #             "thumbnail": thumbnail,
-    #             "description": content,
-    #         },
-    #         headers=self.generate_headers(user),
-    #     )
-    #     return self.format_response(response)
-
-    # def create_stac_model(self, name, user):
-    #     response = requests.post(
-    #         self.url + "models/stac",
-    #         json={"name": name},
-    #         headers=self.generate_headers(user),
-    #     )
-    #     return self.format_response(response)
-
-    # def ingest_stac(self, stac_json, model_id, user):
-    #     response = requests.put(
-    #         self.url + f"models/stac/{model_id}",
-    #         json={"stac": stac_json},
-    #         headers=self.generate_headers(user),
-    #     )
-    #     return self.format_response(response)
-
-    # def download_stac(self, model_id, user):
-    #     url = self.url + "models/" + model_id + "/download"
-    #     headers = self.generate_headers(user)
-    #     response = requests.get(url, headers=headers)
-    #     if response.status_code != 200:
-    #         return None, response.json()["detail"]
-    #     return gpd.GeoDataFrame.from_features(response.json()["features"]), None
+    

eotdl/repos/STACAPIRepo.py

@@ -1,5 +1,4 @@
 import requests
-import geopandas as gpd
 
 from ..repos import APIRepo
 

{eotdl-2025.4.2.dist-info → eotdl-2025.4.2.post2.dist-info}/METADATA

@@ -1,23 +1,18 @@
 Metadata-Version: 2.4
 Name: eotdl
-Version: 2025.4.2
+Version: 2025.4.2.post2
 Summary: Earth Observation Training Data Lab
 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-Python: >=3.12
+Requires-Dist: geopandas>=1.0.1
+Requires-Dist: pydantic>=2.11.1
+Requires-Dist: pyjwt>=2.10.1
+Requires-Dist: pystac>=1.12.2
 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: stac-geoparquet>=0.6.0
 Requires-Dist: tqdm>=4.67.1
-Requires-Dist: typer>=0.15.1
+Requires-Dist: typer>=0.15.2
 Description-Content-Type: text/markdown
 
 <p align="center">

{eotdl-2025.4.2.dist-info → eotdl-2025.4.2.post2.dist-info}/RECORD

@@ -1,4 +1,4 @@
-eotdl/__init__.py,sha256=Q321tl9ms35mPhMUUEAsd6HfOFIZ3i94xC69CF4wloU,27
+eotdl/__init__.py,sha256=ba4I6YAt_kaAovhogjneM5HX0XaIwAqzAW0Ftak1-ns,29
 eotdl/cli.py,sha256=1wtNmiuqjwDB1Me-eSio--dnOabrbdpMiO9dQoIbOoc,702
 eotdl/access/__init__.py,sha256=k-zmTwB6VLoWt_AsXx9CnEKdtONBZAaC8T6vqPMPSjk,436
 eotdl/access/download.py,sha256=e5H8LUkCfIVkFxJFM5EwCMG-R5DHVSHDGLvuNM5DNc8,2815
@@ -44,10 +44,10 @@ eotdl/models/update.py,sha256=4FWeD95cXvRpefRjw3Foqb30e30otxqWUZ6nQM9cbmM,374
 eotdl/repos/APIRepo.py,sha256=fcMpVbatfJgAq12bGWM828n8UDOixBbf5ueleB_Hrc4,791
 eotdl/repos/AuthAPIRepo.py,sha256=vYCqFawe3xUm2cx4SqVXCvzl8J_sr9rs_MkipYC0bXE,957
 eotdl/repos/AuthRepo.py,sha256=jpzzhINCcDZHRCyrPDsp49h17IlXp2HvX3BB3f5cnb4,1154
-eotdl/repos/DatasetsAPIRepo.py,sha256=Yy22IoiASPmca93r4Rt5lzq28TFQkq3aOl_M4u8VJw8,3236
-eotdl/repos/FilesAPIRepo.py,sha256=poGis1oRhv4k8UnBy6eNLwxA9XPaVbG2yFuWycL-uhw,11081
-eotdl/repos/ModelsAPIRepo.py,sha256=VWtxQsMMPi8DxXyyO2tHJyYhnK3Y_k-m5YWLyEXWHrI,3016
-eotdl/repos/STACAPIRepo.py,sha256=YtLd-Wl2mOM4MtT7nCFHd26oeNleq9POKajJuhEt-74,1407
+eotdl/repos/DatasetsAPIRepo.py,sha256=_7n2jzjT01tP3fl51AC28FCv1iuIy-CvcNbJdh0wKg8,1434
+eotdl/repos/FilesAPIRepo.py,sha256=3nvxre9TmfWoDjjmMBhrNfssiRZXfIdORK2aeEwoGIk,3765
+eotdl/repos/ModelsAPIRepo.py,sha256=4CI5chA1D3ewP8b1BBbJwugiKHJwWugEI2F9WuyhlRU,1250
+eotdl/repos/STACAPIRepo.py,sha256=bvc2oQp967jX_kG9fKYmTc496xPdL0cSGfa0mCQMKNI,1383
 eotdl/repos/__init__.py,sha256=GIzk62681dvNzYgVzvJgrMzVRhrep4-kJH6lTOtfnT8,258
 eotdl/shared/__init__.py,sha256=mF7doJC8Z5eTPmB01UQvPivThZac32DRY33T6qshXfg,41
 eotdl/shared/checksum.py,sha256=4IB6N9jRO0chMDNJzpdnFDhC9wcFF9bO5oHq2HodcHw,479
@@ -60,7 +60,7 @@ eotdl/tools/time_utils.py,sha256=JHrQ3PxXkhwor8zcOFccf26zOG9WBtb9xHb6j-Fqa9k,466
 eotdl/tools/tools.py,sha256=Tl4_v2ejkQo_zyZek8oofJwoYcdVosdOwW1C0lvWaNM,6354
 eotdl/wrappers/__init__.py,sha256=IY3DK_5LMbc5bIQFleQA9kzFbPhWuTLesJ8dwfvpkdA,32
 eotdl/wrappers/models.py,sha256=kNO4pYw9KKKmElE7bZWWHGs7FIThNUXj8XciKh_3rNw,6432
-eotdl-2025.4.2.dist-info/METADATA,sha256=N3CIcPuh2pwfFaR8al9XF7iNyvQ8ctA60w9iPVZmw-U,3478
-eotdl-2025.4.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-eotdl-2025.4.2.dist-info/entry_points.txt,sha256=FV4dFIZ5zdWj1q1nUEEip29n3sAgbviVOizEz00gEF0,40
-eotdl-2025.4.2.dist-info/RECORD,,
+eotdl-2025.4.2.post2.dist-info/METADATA,sha256=6JK2dcBCiFpFv2u_X899qMEqrkt55lmtNTvqulvppuo,3338
+eotdl-2025.4.2.post2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+eotdl-2025.4.2.post2.dist-info/entry_points.txt,sha256=FV4dFIZ5zdWj1q1nUEEip29n3sAgbviVOizEz00gEF0,40
+eotdl-2025.4.2.post2.dist-info/RECORD,,