eotdl 2025.4.22.post2__py3-none-any.whl → 2025.5.26__py3-none-any.whl

eotdl/files/metadata.py

@@ -35,7 +35,8 @@ class Metadata(BaseModel):
             f.write(f"name: {self.name}\n")
             f.write(f"license: {self.license}\n") 
             f.write(f"source: {self.source}\n")
-            f.write(f"thumbnail: {self.thumbnail}\n")
+            if self.thumbnail:
+                f.write(f"thumbnail: {self.thumbnail}\n")
             f.write(f"authors:\n")
             for author in self.authors:
                 f.write(f"  - {author}\n")

eotdl/models/ingest.py

@@ -3,7 +3,7 @@ from pathlib import Path
 from ..repos import ModelsAPIRepo
 from ..files.ingest import prep_ingest_stac, prep_ingest_folder, ingest, ingest_virtual, ingest_catalog
 
-def retrieve_model(metadata, user):
+def retrieve_model(metadata, user, private=False):
 	repo = ModelsAPIRepo()
 	data, error = repo.retrieve_model(metadata.name)
 	# print(data, error)
@@ -22,6 +22,7 @@ def ingest_model(
 	logger=print,
 	force_metadata_update=False,
 	sync_metadata=False,
+	private=False,
 ):
 	path = Path(path)
 	if not path.is_dir():
@@ -30,7 +31,7 @@ def ingest_model(
 		prep_ingest_stac(path, logger)
 	else:
 		prep_ingest_folder(path, verbose, logger, force_metadata_update, sync_metadata)
-	return ingest(path, ModelsAPIRepo(), retrieve_model, 'models')
+	return ingest(path, ModelsAPIRepo(), retrieve_model, 'models', private)
 
 def ingest_virtual_model( # could work for a list of paths with minimal changes...
 	path,

eotdl/models/update.py

@@ -1,6 +1,6 @@
 from ..repos import ModelsAPIRepo
-
-
+from ..auth import with_auth
+from .retrieve import retrieve_model
 def update_model(model_id, metadata, content, user):
     repo = ModelsAPIRepo()
     data, error = repo.update_model(
@@ -16,9 +16,11 @@ def update_model(model_id, metadata, content, user):
         raise Exception(error)
     return data
 
-def deactivate_model(model_id):
+@with_auth
+def deactivate_model(model_name, user):
+    model = retrieve_model(model_name)
     repo = ModelsAPIRepo()
-    data, error = repo.deactivate_model(model_id)
+    data, error = repo.deactivate_model(model['id'], user)
     if error:
         raise Exception(error)
     return data

eotdl/repos/DatasetsAPIRepo.py

@@ -18,15 +18,26 @@ class DatasetsAPIRepo(APIRepo):
         response = requests.get(url)
         return self.format_response(response)
     
+    def retrieve_private_datasets(self, user):
+        url = self.url + "datasets/private"
+        response = requests.get(url, headers=self.generate_headers(user))
+        return self.format_response(response)
+    
     def retrieve_dataset(self, name):
         response = requests.get(self.url + "datasets?name=" + name)
         return self.format_response(response)
     
+    def retrieve_private_dataset(self, name, user):
+        response = requests.get(self.url + "datasets/private?name=" + name, headers=self.generate_headers(user))
+        return self.format_response(response)
+    
     def get_dataset_by_id(self, dataset_id):
         response = requests.get(self.url + "datasets/" + dataset_id)
         return self.format_response(response)
     
-    def create_dataset(self, metadata, user):
+    def create_dataset(self, metadata, user, private=False):
+        if private:
+            metadata["visibility"] = "private"
         response = requests.post(
             self.url + "datasets",
             json=metadata,
@@ -42,8 +53,9 @@ class DatasetsAPIRepo(APIRepo):
         )
         return self.format_response(response)
     
-    def deactivate_dataset(self, dataset_name):
+    def deactivate_dataset(self, dataset_name, user):
         response = requests.patch(
-            self.url + "datasets/deactivate/" + dataset_name
+            self.url + "datasets/deactivate/" + dataset_name,
+            headers=self.generate_headers(user),
         )
         return self.format_response(response)

eotdl/repos/FEAPIRepo.py

@@ -0,0 +1,50 @@
+import requests
+
+from ..repos import APIRepo
+
+class FEAPIRepo(APIRepo):
+    def __init__(self, url=None):
+        super().__init__(url)
+
+    def retrieve_pipelines(self, name, limit):
+        url = self.url + "pipelines"
+        if name is not None:
+            url += "?match=" + name
+        if limit is not None:
+            if name is None:
+                url += "?limit=" + str(limit)
+            else:
+                url += "&limit=" + str(limit)
+        response = requests.get(url)
+        return self.format_response(response)
+    
+    def retrieve_pipeline(self, name):
+        response = requests.get(self.url + "pipelines?name=" + name)
+        return self.format_response(response)
+    
+    def get_pipeline_by_id(self, pipeline_id):
+        response = requests.get(self.url + "pipelines/" + pipeline_id)
+        return self.format_response(response)
+    
+    def create_pipeline(self, metadata, user):
+        response = requests.post(
+            self.url + "pipelines",
+            json=metadata,
+            headers=self.generate_headers(user),
+        )
+        return self.format_response(response)
+
+    def complete_ingestion(self, pipeline_id, version, size, user):
+        response = requests.post(
+            self.url + "pipelines/complete/" + pipeline_id,
+            json={"version": version, "size": size},
+            headers=self.generate_headers(user),
+        )
+        return self.format_response(response)
+    
+    def deactivate_pipeline(self, pipeline_id, user):
+        response = requests.patch(
+            self.url + "pipelines/deactivate/" + pipeline_id,
+            headers=self.generate_headers(user),
+        )
+        return self.format_response(response)

eotdl/repos/FilesAPIRepo.py

@@ -63,7 +63,6 @@ class FilesAPIRepo(APIRepo):
         #     url += "?version=" + str(file_version)
         return self.stage_file_url(url, path, user)
 
-
     def stage_file_url(
         self,
         url,

eotdl/repos/ModelsAPIRepo.py

@@ -38,8 +38,9 @@ class ModelsAPIRepo(APIRepo):
         )
         return self.format_response(response)
 
-    def deactivate_model(self, model_name):
+    def deactivate_model(self, model_name, user):
         response = requests.patch(
-            self.url + "models/deactivate/" + model_name
+            self.url + "models/deactivate/" + model_name,
+            headers=self.generate_headers(user),
         )
         return self.format_response(response)

eotdl/repos/__init__.py

@@ -4,4 +4,5 @@ from .AuthAPIRepo import AuthAPIRepo
 from .DatasetsAPIRepo import DatasetsAPIRepo
 from .FilesAPIRepo import FilesAPIRepo
 from .ModelsAPIRepo import ModelsAPIRepo
-from .STACAPIRepo import STACAPIRepo
+from .STACAPIRepo import STACAPIRepo
+from .FEAPIRepo import FEAPIRepo

eotdl/tools/ais_labelling.py

@@ -0,0 +1,273 @@
+import json
+import numpy as np
+import pandas as pd
+import rasterio
+import rasterio.features
+from scipy import signal
+from shapely import affinity
+from shapely.geometry import Polygon
+from pathlib import Path
+import geopandas as gpd
+
+
+def convert_shape_to_wgs84(poly, transform):
+    a,b,c,d,e,f =  transform[:6]
+    mat = (a,b,d,e,c,f)
+    return affinity.affine_transform(poly, mat)
+
+def get_vessel_shape(center, width, length, theta):
+    """ Get the bounding box for a ship
+    Args:
+        center (float): Ship's center index (subpixel)
+        width (float): Ship's width in pixel
+        length (float): Ship's length in pixel
+        theta (float): Ship's heading angle in radian
+    Returns:
+        (Shapely Polygon): Bounding box 
+    """
+    width = width/2
+    length = length/2
+    poly = Polygon([(-width, -length), (-width, length), (width, length),
+                    (width, -length)])
+
+    poly = affinity.rotate(poly, theta, 'center',  use_radians=True)
+    poly = affinity.translate(poly, xoff=center[0], yoff=center[1])
+    return poly
+
+
+def center_cross_correlation(data, width, length, theta, upsample_factor):
+    """ Approximate the center of the boat with a cross correlation of the data
+    and a gaussian model
+    Args:
+        data (Rasterio DatasetReader): tif file reader
+        width (float): Ship's width in pixel
+        length (float): Ship's length in pixel
+        theta (float): Ship's heading angle in radian
+        upsample_factor (uint): up sampling factor
+    Returns:
+        (Numpy Array):  centered mask
+        (Numpy Array):  Correlations with each bands of the image
+        (Numpy Array):  Coordinates of the center of the boat
+    """
+    # Up sampling
+    up_sampled_data = np.repeat(np.repeat(data, upsample_factor, axis=1),
+                                    upsample_factor, axis=0)
+  
+    # Rectangular mask
+    size = (data.shape[0]*upsample_factor, data.shape[1]*upsample_factor)
+    shape = get_vessel_shape([size[0]/2, size[1]/2], width * upsample_factor, length*upsample_factor, theta)
+    centered_mask = rasterio.features.rasterize([shape], out_shape=(size), all_touched=True).astype(np.int8)
+
+    # Remove null edges of the mask
+    border_padding_size = 2 * upsample_factor
+    max_x = int(np.max(shape.exterior.coords.xy[1])) +3 + border_padding_size
+    min_x = int(np.min(shape.exterior.coords.xy[1])) -2 - border_padding_size
+    max_y = int(np.max(shape.exterior.coords.xy[0])) +3 + border_padding_size
+    min_y = int(np.min(shape.exterior.coords.xy[0])) -2 - border_padding_size
+
+    if (max_x - min_x)%2 == 0:
+        max_x += 1
+    if (max_y - min_y)%2 == 0:
+        max_y += 1
+
+    cropped_mask = centered_mask[min_x:max_x, min_y:max_y]
+    background_value = -1
+    
+    ####
+    background_value = 0
+    cropped_mask[cropped_mask == 0 ] = -1
+    ####
+    
+
+
+    model_mask = cropped_mask.copy()
+    model_mask[0:border_padding_size] = background_value
+    model_mask[-border_padding_size:] = background_value
+    model_mask[:,0:border_padding_size] = background_value
+    model_mask[:,-border_padding_size:] = background_value
+    for i in range(2,model_mask.shape[0]-2):
+        for j in range(2, model_mask.shape[1]-2):
+            window = cropped_mask[i-2:i+3,j-2:j+3]
+            if np.all(window != 1):
+                model_mask[i,j] = background_value
+
+    # Model and data must have the same dimensions parity to avoid an offset after the cross correlation
+    if model_mask.shape[0] %2 == 0:
+        model_mask = np.append(model_mask, -1* np.ones((1, model_mask.shape[1])), axis=0)
+    if model_mask.shape[1] %2 == 0:
+        model_mask = np.append(model_mask, -1* np.ones((model_mask.shape[0],1)), axis=1)
+
+    # Compute the coordinates of the maximum correlation for each band
+    mean_filter = np.ones(cropped_mask.shape)/np.size(cropped_mask)
+    correlations = np.zeros(up_sampled_data.shape)
+    for i in range(data.shape[2]):
+        correlation_band_i = signal.correlate2d(up_sampled_data[:, :, i],
+                                                   model_mask, mode='valid', boundary='fill', fillvalue=0)
+        
+        # Mean filter convolution (removes abnormal high values)
+        average_map = signal.convolve2d(up_sampled_data[:, :, i],
+                                        mean_filter, mode='valid', boundary='fill', fillvalue=np.inf)  
+        correlation_band_i = np.divide(correlation_band_i, average_map, 
+                out=np.zeros(correlation_band_i.shape), where=average_map!=0) 
+        correlation_band_i -= np.min(correlation_band_i)
+
+        # resize the output
+        nb = correlations.shape[0]
+        na = correlation_band_i.shape[0]
+        lowerx = (nb) // 2 - (na // 2)
+        upperx = (nb // 2) + (na // 2)
+        nb = correlations.shape[1]
+        na = correlation_band_i.shape[1]
+        lowery = (nb) // 2 - (na // 2)
+        uppery = (nb // 2) + (na // 2)
+        correlations[lowerx:upperx, lowery:uppery,i] = correlation_band_i
+
+
+    window1d = np.abs(np.hamming(correlations.shape[0]))
+    window2d = np.sqrt(np.outer(window1d,window1d))
+    correlations *= np.repeat(window2d[:,:,None],correlations.shape[2],axis=2)
+
+    somme = np.sum(correlations, axis = 2)
+    
+    ##########################################################
+
+    
+
+    center =  np.argwhere(somme == np.max(somme))[0] / upsample_factor
+
+    # swap to the right coordinate system
+    center[0], center[1] = center[1], center[0]
+
+    return centered_mask, correlations, center
+
+
+def generate_mask(file_path, output_dir, row_vessel, upsample_factor=1, output_type="raster", dilatation=5):
+    """ Get the entries for the csv file for an image without a mask
+    Args:
+        file_path (String): path to the image
+        output_dir (String): path to the output folder
+        row_vessel (Pandas Dataframe): boat's informations
+        upsample_factor (Int): upsampling factor for the model and the cross correlation
+        output_type (String): can be a 'raster' (.tif) or a 'vector' (.geojson) output
+        dilatation (Int): size of the dilation for the length and width of the mask in meters
+    Returns:
+        (Dict): csv entries for the image  
+    """
+    
+    #  Load the source tile
+    with rasterio.open(file_path, 'r') as src:
+
+        # All 10m channels except blue
+        data = src.read([2,3,4,11,12]).transpose(1, 2, 0)
+        
+        # Get the dimensions of the boat
+        # pixel_res = abs(src.transform[4])
+        pixel_res = 10
+        width_px = row_vessel["Width"] / pixel_res
+        length_px = row_vessel["Length"] / pixel_res
+
+        # Get the center of the mask
+        model, correlations, center = center_cross_correlation(data,
+                width_px, length_px, row_vessel['Heading'], upsample_factor)
+
+        # Rectangular bounding box
+        mask_width_px = (row_vessel["Width"] + dilatation) / pixel_res
+        mask_length_px = (row_vessel["Length"] + dilatation) / pixel_res
+        shape = get_vessel_shape(center, mask_width_px, mask_length_px, row_vessel['Heading'])
+        mask = rasterio.features.rasterize([shape], out_shape=data.shape[0:2], all_touched=True)
+
+        if output_type == "vector":
+            # generate Geojson  
+            shape_wgs84 = convert_shape_to_wgs84(shape, src.transform)
+            gdr = gpd.GeoDataFrame({'geometry': [shape_wgs84],  
+                                "labels": [["Boat"]], 
+                                "tasks":[["segmentation"]]}, 
+                                crs='EPSG:4326')
+
+            # Write to geojson
+            label_geojson = gdr.to_json(drop_id=True)
+            out_mask_path = Path(file_path).parent / f"{file_path.stem}_labels.geojson"
+
+            with open(out_mask_path, "w") as dst:
+                dst.write(label_geojson)
+
+        elif output_type == "raster":
+            # Create the profile for the .tif
+            profile = {
+                'driver': 'GTiff',
+                'height': src.height,
+                'width': src.width,
+                'count': 1,
+                'dtype': rasterio.uint8,
+                'crs': src.crs,
+                'transform': src.transform,
+                'nodata': None,
+                'compress': 'lzw'
+            }
+
+            # Write the mask
+            out_mask_path = Path(output_dir) / f"mask_{Path(file_path).name}"
+            with rasterio.open(out_mask_path, 'w', **profile) as dst:
+                dst.write(mask, indexes=1)
+
+
+def process_directoy(dir_name, output_dir, tiles_df, upsample_factor, output_type):
+
+    assert output_type == "raster" or output_type == "vector"
+    print(f"Processing tiles from {dir_name}")
+
+    # Prepare outputpath
+    output_dir_name = Path(output_dir)
+
+    if output_type =="vector":
+
+        labels_json = {"labels": [{"name": "Boat", "color": "#ff8000"}]}
+        json_path = Path(dir_name) / "labels.json"
+
+        with open(json_path, "w") as dst:
+            dst.write(json.dumps(labels_json))
+
+    # Generate the mask for each vessel
+    list_nan = []
+
+    # Convert angles in radian
+    tiles_df["Heading"] *= np.pi/180
+
+    for i in range(len(tiles_df)):
+        row_vessel = tiles_df.iloc[i]
+        img_path = Path(dir_name) / f"{row_vessel['ImageId']}.tiff"
+
+        # Get mmsi from filename
+        vessel = int(row_vessel["ImageId"].split('_')[1])
+        
+        if row_vessel.isnull().values.any(): # Tiles with Nan data
+            list_nan.append(vessel)
+        
+        else:
+            # Get the mask of the boat
+            generate_mask(img_path, output_dir_name, row_vessel, upsample_factor, output_type)
+        
+    if list_nan:
+        print(f"No mask saved for the vessels {list_nan}, NaN values found in the AIS data")
+
+
+def process_db(images_path, output_dir, upsample_factor, output_type = "raster"):
+    """ Get the entries for the csv file for an image without a mask
+    Args:
+        csv_tiles (String): path to the csv folder of the tiles
+        output_dir (String): path to the output folder
+        upsample_factor (Int): upsampling factor for the model and the cross correlation
+        output_type (String): can be a 'raster' (.tif) or a 'vector' (.geojson) output
+    """
+    # Prepare the output file
+    csv_paths = Path(images_path).glob("*.csv")
+    for csv_tiles in csv_paths:
+        # read the tiles csv
+        tiles_df = pd.read_csv(csv_tiles)
+        # Get the path to the tiles
+        tiles_path = Path(csv_tiles).parent
+        process_directoy(tiles_path,
+                         output_dir=output_dir, 
+                         tiles_df=tiles_df, 
+                         upsample_factor=upsample_factor,
+                         output_type=output_type)

{eotdl-2025.4.22.post2.dist-info → eotdl-2025.5.26.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eotdl
-Version: 2025.4.22.post2
+Version: 2025.5.26
 Summary: Earth Observation Training Data Lab
 Author-email: earthpulse <it@earthpulse.es>
 License-Expression: MIT

{eotdl-2025.4.22.post2.dist-info → eotdl-2025.5.26.dist-info}/RECORD

@@ -1,5 +1,5 @@
-eotdl/__init__.py,sha256=-O7BvxY9Mzl3TA3wOKD1uu7C0__yrYkBF7J9kAF4jts,29
-eotdl/cli.py,sha256=BAI3HuDf1WohaWeA5y1bUJMABDkqmfttOCa7FY5P3Hk,701
+eotdl/__init__.py,sha256=7OVkF8SLpGQOJkvOiT6XHXrkE9hp4JDvF9-vFYP8Ytg,27
+eotdl/cli.py,sha256=MgRmnBcnPtRTW_nuvtH41y7MSjmVMzr1JOt9X-oDnt4,759
 eotdl/access/__init__.py,sha256=k-zmTwB6VLoWt_AsXx9CnEKdtONBZAaC8T6vqPMPSjk,436
 eotdl/access/download.py,sha256=e5H8LUkCfIVkFxJFM5EwCMG-R5DHVSHDGLvuNM5DNc8,2815
 eotdl/access/search.py,sha256=1indipTfna4VAfGlKb8gkaYyHAELdHR4cm1mVIDW69s,1415
@@ -18,40 +18,56 @@ 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/commands/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-eotdl/commands/auth.py,sha256=WzA0aFGRoscy7fPKQTxiphBc0LJztJxBBl7rjDBRVfI,1544
-eotdl/commands/datasets.py,sha256=gE9CcHq4KyMsBhj28j1TfkLsMVG2CPBqvAANqAvxn0Y,5503
-eotdl/commands/models.py,sha256=iXy9XNgrYvi0_vZamDFbF69OQ-ApxSTCxmKeIvp9Q0g,5145
+eotdl/commands/auth.py,sha256=sSfawOpht6ntToFXDJrOu11IATV9vN03Bqyg5LNGb1s,1646
+eotdl/commands/datasets.py,sha256=1ksdUYSalEY8ts0_ak3-nhV4WyygkNl33uiZ6K2GUaM,5508
+eotdl/commands/models.py,sha256=a6ozJC0MH7CsK2-ts6sN_9EFbT6bzoaJne8v83JjTzg,4942
+eotdl/commands/pipelines.py,sha256=uvdS7NFzxG95IiKKFf5ha4TgGZsN-LO7Pucmp0GWgnw,4396
 eotdl/commands/stac.py,sha256=jgjjkGw9tIvuovyAwfEu6B4ZMoMvEj5lrj_lO-9IqrE,1444
 eotdl/curation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 eotdl/curation/stac/__init__.py,sha256=FMi-qzd6v1sdsqZsBRRnedccaJFXJGCPCH3uTctyLYU,37
 eotdl/curation/stac/api.py,sha256=5XW9yzSxiuML70bBbzJ0DGx0GmplmhYtgeGZg029Qjk,1428
 eotdl/curation/stac/stac.py,sha256=4f7xrh2CcXTkTs3or1UMVxiFfwtVfTqH4YwTGsbi6No,1013
-eotdl/datasets/__init__.py,sha256=g2WBJa_EVVXtktxqZRJEAQPHADU0qVaLkjDYZnojDgc,256
-eotdl/datasets/ingest.py,sha256=7LI4eENRxhGDjgfAlgLqTY96jiX5iRB0_SlU63NboOM,1414
-eotdl/datasets/retrieve.py,sha256=dhNbBJu0vE0l-LsGQNQF5Vc_WzZDRbXPzvd66GNlV6U,691
-eotdl/datasets/stage.py,sha256=pcU1AsjbczzMHdhCxjKfCuuuLo1OZMMWNAUqj-3SxKc,2162
-eotdl/datasets/update.py,sha256=pHHutyGf0ALTuGmq2TYSyJ3VaLmY0WMNgHw_pKUn2zI,567
-eotdl/files/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+eotdl/datasets/__init__.py,sha256=3FtdIDmSaCg4P15oI5d-7DDomuUEz4E3PjK78Ofvm3g,283
+eotdl/datasets/ingest.py,sha256=sxtnaRTUZxtg5Wfs8uei7M63xszpd6eWHH-KvDqPW5c,1750
+eotdl/datasets/retrieve.py,sha256=vQzociVOcD1A1ZTfFC42jzgEYVcc_y_HcvlALBqpAd8,1210
+eotdl/datasets/stage.py,sha256=dbmEV5VpaM1DEHhpCWTEgYAuCNUGaW0Ghm_oP8_COEg,2168
+eotdl/datasets/update.py,sha256=QmhXZwAOqz5ysc_VpCjFFDo5tpt0EKG44G1jYeQmbkQ,706
+eotdl/fe/__init__.py,sha256=nwm7HHfh_UrCnMMYaO2vqQ6y4ziVzAf6zt_RuvDSVF4,167
+eotdl/fe/ingest.py,sha256=JkVxPkHbltmvlRP6fmPKZu5lx8HJGOp9dSxrzkCv8tQ,1489
+eotdl/fe/retrieve.py,sha256=xrtmYcG14xgknu9yQJEdSjJMtSMoZkDU____95Yd6YY,448
+eotdl/fe/stage.py,sha256=wxmX_uyNc2kLvU_bF2SvyBBr05sPlTA7xYq0T4pSzEo,2001
+eotdl/fe/update.py,sha256=GO9ep8tAneGQrOseKdZnrADvNs1x9uhG4Q7Y5UhcLVI,354
+eotdl/fe/openeo/__init__.py,sha256=oag2hTyLcRKF-7SGkY-ZcbuftUtABZMNtn1-8gOYDik,108
+eotdl/fe/openeo/advanced_patch_extraction.py,sha256=jyfkHT8Co53xey2qbWimzYeB5kLwCEG_aCyK3OUefW4,5778
+eotdl/fe/openeo/basic_point_extraction.py,sha256=pUFZ34J9Ob21V9Ur6GLO3d3HGKYU5o6vjBtF3eR3JXs,4105
+eotdl/fe/openeo/dataframe_utils.py,sha256=QYG4xkJ6LER8q9lDD8ovd_pPcBb9dX2hbg4y5ZMMfW4,7981
+eotdl/fe/openeo/s3proxy_utils.py,sha256=AH8cKyf8D8qM4UYXgBgZX7I2seKxhkhNjxQJpcqtxZI,6406
+eotdl/fe/openeo/spatial_utils.py,sha256=E1FfPnzgfBMhFd4XAjRl9FEZO3QnHf27tJjkZzze75Q,1008
+eotdl/fe/openeo/temporal_utils.py,sha256=R6epJqyhNH-c-wXVg8GgV3O_1DStk9hms5Oon4lPLH8,570
+eotdl/files/__init__.py,sha256=3guFFgXq6WEQ6X1VsVnEZEzya2kpQajaDvLpNSQboVA,33
+eotdl/files/get_url.py,sha256=gcD6E6cj9tsEsF2T5WdrFKK7rBjjjcGmWtyUc8IQEBo,772
 eotdl/files/ingest.bck,sha256=dgjZfd-ACCKradDo2B02CPahwEhFtWvnKvTm372K5eo,6185
-eotdl/files/ingest.py,sha256=mepe-RmweWaM_4fUZjyGWpwjrg6EIlc_B7GwxRR7Br4,9379
-eotdl/files/metadata.py,sha256=C-NDr-zjM58fP8QcHB1N1QyLRUeYyMbT6wPPnxGk8LI,1370
+eotdl/files/ingest.py,sha256=RwQ3WazTm3b600QXEiHsTDApIegxAxW-Vhw9GkGQFP0,9427
+eotdl/files/metadata.py,sha256=MGrIvcgNr3AMI3j9Jcdyp5Q3Jcuth8m6Z14BCDxF0xI,1405
 eotdl/models/__init__.py,sha256=b6t1Z377On1F56c-GSy7FM_nBWRLHh1Ph2R24rPFiVY,239
 eotdl/models/download.py,sha256=rRT3fG-qS3-SXfzFdqy0cuiDnOIV9Du74JCnsbbA9Ps,3475
-eotdl/models/ingest.py,sha256=xpDoY4Tn0y94bIDXgk2No6fGLydPbKYcc9NsPj-yFms,1372
+eotdl/models/ingest.py,sha256=cvkxH_KZO1v2a6VSsd0Mady1kPQY7WGn0YBXaY90_Xc,1412
 eotdl/models/retrieve.py,sha256=-Ij7dT4J1p7MW4n13OlPB9OW4tBaBXPwk9dW8IuCZPc,664
 eotdl/models/stage.py,sha256=rvWN8vcBz7qHhu0TzJ90atw1kEr3JPKF0k2S-Sv-JVs,1944
-eotdl/models/update.py,sha256=0N6S_n_DXWaS2A56lHjukBgLLZDxygB8jN2WfZyJwaQ,545
+eotdl/models/update.py,sha256=PIdPbPrdul-HSAAL21SadAkZT2kcnJyV2uTmi8dlK5k,676
 eotdl/repos/APIRepo.py,sha256=s9w29Cnk5Pu4NvjyHAfcpM69a2lODICJ-Gn_iosxsPg,791
 eotdl/repos/AuthAPIRepo.py,sha256=vYCqFawe3xUm2cx4SqVXCvzl8J_sr9rs_MkipYC0bXE,957
 eotdl/repos/AuthRepo.py,sha256=jpzzhINCcDZHRCyrPDsp49h17IlXp2HvX3BB3f5cnb4,1154
-eotdl/repos/DatasetsAPIRepo.py,sha256=Wx8xkQHT53h7AZATNSCLaDmkHYMoSGDVoyo_beqpgGo,1639
-eotdl/repos/FilesAPIRepo.py,sha256=PNNS5LGxksZpkg-49_r3r2H0iQWkCeb7iiL6j-S4wLY,4757
-eotdl/repos/ModelsAPIRepo.py,sha256=i2T1mJwlWu2mpexUVOE9ha5JRyHdf6_6n36TraL3-BU,1438
+eotdl/repos/DatasetsAPIRepo.py,sha256=bJnMWQVQ-t25MHwisMKeq8yeAVxmbDB77TXtYdTwV70,2209
+eotdl/repos/FEAPIRepo.py,sha256=nbyk1Wt3hzCYOm6zvZ1DA5UQ_rmY8G3cpSKs0rLem4I,1702
+eotdl/repos/FilesAPIRepo.py,sha256=iJWT2_7TIg8gTMAihui5mBbcUWF5THh-AuuLcfyMHGk,4756
+eotdl/repos/ModelsAPIRepo.py,sha256=hgnU8wkwESsrzfL6Wxpwwt7ejlnoOBeeNa4IrV4hwRo,1494
 eotdl/repos/STACAPIRepo.py,sha256=GJIrLkgVB-donToJlgOmaJbxDmXzIuwlmCb9R2yoRIA,1387
-eotdl/repos/__init__.py,sha256=GIzk62681dvNzYgVzvJgrMzVRhrep4-kJH6lTOtfnT8,258
+eotdl/repos/__init__.py,sha256=I4_friwwZ4sSQxmguYY2uBNWvpKLaHUEN1i6Zib_WWU,291
 eotdl/shared/__init__.py,sha256=mF7doJC8Z5eTPmB01UQvPivThZac32DRY33T6qshXfg,41
 eotdl/shared/checksum.py,sha256=4IB6N9jRO0chMDNJzpdnFDhC9wcFF9bO5oHq2HodcHw,479
 eotdl/tools/__init__.py,sha256=_p3n2dw3ulwyr1OlVw5d_jMV64cNYfajQMUbzFfvIpU,178
+eotdl/tools/ais_labelling.py,sha256=2KGbNGjN3R_Y26SoXPNBuXB7HSpUpyXViIByM-ABDvo,10655
 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
@@ -60,7 +76,7 @@ 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-2025.4.22.post2.dist-info/METADATA,sha256=CB8WifWJtYRbDtitqT85iGfIiEe0VD52Mh2EYqHNsq0,3371
-eotdl-2025.4.22.post2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-eotdl-2025.4.22.post2.dist-info/entry_points.txt,sha256=FV4dFIZ5zdWj1q1nUEEip29n3sAgbviVOizEz00gEF0,40
-eotdl-2025.4.22.post2.dist-info/RECORD,,
+eotdl-2025.5.26.dist-info/METADATA,sha256=ifJ4T20QsC202xJpv8Cwn-4vBHQOF9e_l0Jdgb1rZ-Y,3365
+eotdl-2025.5.26.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+eotdl-2025.5.26.dist-info/entry_points.txt,sha256=FV4dFIZ5zdWj1q1nUEEip29n3sAgbviVOizEz00gEF0,40
+eotdl-2025.5.26.dist-info/RECORD,,