disdrodb 0.2.0__py3-none-any.whl → 0.3.0__py3-none-any.whl

disdrodb/utils/cli.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -105,7 +103,7 @@ def click_data_archive_dir_option(function: object):
         type=str,
         show_default=True,
         default=None,
-        help="DISDRODB base directory",
+        help="DISDRODB Data Archive Directory. Format: <...>/DISDRODB",
     )(function)
     return function
 
@@ -123,7 +121,7 @@ def click_metadata_archive_dir_option(function: object):
         type=str,
         show_default=True,
         default=None,
-        help="DISDRODB Metadata Archive Directory",
+        help="DISDRODB Metadata Archive Directory. Format: <...>/DISDRODB-METADATA/DISDRODB",
     )(function)
     return function
 
@@ -233,14 +231,14 @@ def click_l0_archive_options(function: object):
         type=bool,
         show_default=True,
         default=False,
-        help="If true, remove all source L0B files once L0B concatenation is terminated.",
+        help="If True, remove L0B files after L0C.",
     )(function)
     function = click.option(
         "--remove_l0a",
         type=bool,
         show_default=True,
         default=False,
-        help="If true, remove the L0A files once the L0B processing is terminated.",
+        help="If True, remove L0A files after L0B.",
     )(function)
     function = click.option(
         "-l0c",
@@ -248,7 +246,7 @@ def click_l0_archive_options(function: object):
         type=bool,
         show_default=True,
         default=True,
-        help="Perform L0C processing.",
+        help="Run L0C processing",
     )(function)
     function = click.option(
         "-l0b",
@@ -256,7 +254,7 @@ def click_l0_archive_options(function: object):
         type=bool,
         show_default=True,
         default=True,
-        help="Perform L0B processing.",
+        help="Run L0B processing",
     )(function)
     function = click.option(
         "-l0a",
@@ -264,6 +262,6 @@ def click_l0_archive_options(function: object):
         type=bool,
         show_default=True,
         default=True,
-        help="Perform L0A processing.",
+        help="Run L0A processing",
     )(function)
     return function

disdrodb/utils/compression.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -82,7 +80,7 @@ def unzip_file_on_terminal(filepath: str, dest_path: str) -> str:
     subprocess.run(cmd, check=True)
 
 
-def _zip_dir(dir_path: str) -> str:
+def _zip_dir(dir_path: str, dst_dir=None) -> str:
     """Zip a directory into a file located in the same directory.
 
     Parameters
@@ -95,7 +93,9 @@ def _zip_dir(dir_path: str) -> str:
     str
         Path of the zip archive.
     """
-    output_path_without_extension = os.path.join(tempfile.gettempdir(), os.path.basename(dir_path))
+    if dst_dir is None:
+        dst_dir = tempfile.gettempdir()
+    output_path_without_extension = os.path.join(dst_dir, os.path.basename(dir_path))
     output_path = output_path_without_extension + ".zip"
     shutil.make_archive(output_path_without_extension, "zip", dir_path)
     return output_path
@@ -188,13 +188,13 @@ def compress_station_files(
     # Get list of files inside the station directory (in all nested directories)
     filepaths = list_files(station_dir, recursive=True)
     for filepath in filepaths:
-        _ = _compress_file(filepath, method, skip=skip)
+        _ = compress_file(filepath, method, skip=skip)
 
     print(f"All files of {data_source} {campaign_name} {station_name} have been compressed.")
     print("Please now remember to update the glob_pattern of the reader ¨!")
 
 
-def _compress_file(filepath: str, method: str, skip: bool) -> str:
+def compress_file(filepath: str, method: str, skip: bool) -> str:
     """Compress a file and delete the original.
 
     If the file is already compressed, it is not compressed again.
@@ -228,9 +228,9 @@ def _compress_file(filepath: str, method: str, skip: bool) -> str:
     archive_name = os.path.basename(filepath) + extension
     compressed_filepath = os.path.join(os.path.dirname(filepath), archive_name)
     compress_file_function = {
-        "zip": _compress_file_zip,
-        "gzip": _compress_file_gzip,
-        "bzip2": _compress_file_bzip2,
+        "zip": compress_file_zip,
+        "gzip": compress_file_gzip,
+        "bzip2": compress_file_bzip2,
     }[method]
 
     compress_file_function(filepath, compressed_filepath)
@@ -269,7 +269,7 @@ def _check_file_compression(filepath: str) -> Optional[str]:
     return None
 
 
-def _compress_file_zip(filepath: str, compressed_filepath: str) -> None:
+def compress_file_zip(filepath: str, compressed_filepath: str) -> None:
     """Compress a single file into a zip archive.
 
     Parameters
@@ -285,7 +285,7 @@ def _compress_file_zip(filepath: str, compressed_filepath: str) -> None:
         zipf.write(filepath, os.path.basename(filepath))
 
 
-def _compress_file_gzip(filepath: str, compressed_filepath: str) -> None:
+def compress_file_gzip(filepath: str, compressed_filepath: str) -> None:
     """Compress a single file into a gzip archive.
 
     Parameters
@@ -301,7 +301,7 @@ def _compress_file_gzip(filepath: str, compressed_filepath: str) -> None:
         f_out.writelines(f_in)
 
 
-def _compress_file_bzip2(filepath: str, compressed_filepath: str) -> None:
+def compress_file_bzip2(filepath: str, compressed_filepath: str) -> None:
     """Compress a single file into a bzip2 archive.
 
     Parameters

disdrodb/utils/dask.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -71,6 +69,7 @@ def initialize_dask_cluster(minimum_memory=None):
     os.environ["HDF5_USE_FILE_LOCKING"] = "FALSE"
 
     # Retrieve the number of processes to run
+    # --> If DASK_NUM_WORKERS is not set, use all CPUs minus 2
     available_workers = os.cpu_count() - 2  # if not set, all CPUs minus 2
     num_workers = dask.config.get("num_workers", available_workers)
 
@@ -113,7 +112,13 @@ def close_dask_cluster(cluster, client):
         logger.setLevel(original_level)
 
 
-def execute_tasks_safely(list_tasks, parallel: bool, logs_dir: str):
+def _batch_iterable(iterable, n):
+    """Yield successive n-sized chunks from iterable."""
+    for i in range(0, len(iterable), n):
+        yield iterable[i : i + n]
+
+
+def execute_tasks_safely(list_tasks, parallel: bool, logs_dir: str, max_tasks_per_batch=5_000):
     """
     Execute Dask tasks and skip failed ones.
 
@@ -125,6 +130,9 @@ def execute_tasks_safely(list_tasks, parallel: bool, logs_dir: str):
         Whether to execute in parallel with Dask or not.
     logs_dir : str
         Directory to store FAILED_TASKS.log.
+    max_tasks_per_batch : int or None, optional
+     Maximum number of tasks to submit to `client.compute()` at once.
+     The default is 5000. Dask struggle if more than 10_000 tasks are submitted.
 
     Returns
     -------
@@ -150,18 +158,29 @@ def execute_tasks_safely(list_tasks, parallel: bool, logs_dir: str):
     except ValueError:
         raise ValueError("No Dask Distributed Client found.")
 
-    # Compute tasks (all concurrently)
-    # - Runs tasks == num_workers * threads_per_worker (which is 1 for DISDRODB)
-    # - If errors occurs in some, skip it
-    futures = client.compute(list_tasks)
-    results = client.gather(futures, errors="skip")
+    all_results = []
+    failed_futures = []
+
+    # Batch execution
+    task_batches = list(_batch_iterable(list_tasks, max_tasks_per_batch)) if max_tasks_per_batch else [list_tasks]
+
+    for batch in task_batches:
+        # Compute tasks (all concurrently)
+        # - Runs tasks == num_workers * threads_per_worker (which is 1 for DISDRODB)
+        # - If errors occurs in some, skip it
+        futures = client.compute(batch)
+        results = client.gather(futures, errors="skip")
+
+        # Identify and collect failed futures
+        batch_failed = [f for f in futures if f.status != "finished"]
+        failed_futures.extend(batch_failed)
 
-    # Collect failed futures
-    failed_futures = [f for f in futures if f.status != "finished"]  # "error"
+        # Collect results from successful tasks
+        all_results.extend(results)
 
     # If no tasks failed, return results
     if not failed_futures:
-        return results
+        return all_results
 
     # Otherwise define log file listing failed tasks
     with open(failed_log_path, "w") as f:
@@ -170,5 +189,5 @@ def execute_tasks_safely(list_tasks, parallel: bool, logs_dir: str):
             f.write(f"ERROR - DASK TASK FAILURE - Task {fut.key} failed: {err}\n")
 
     # Append to list of log filepaths (results) the dask failing log
-    results.append(failed_log_path)
-    return results
+    all_results.append(failed_log_path)
+    return all_results

disdrodb/utils/dataframe.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

disdrodb/utils/decorators.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

disdrodb/utils/dict.py

@@ -1,5 +1,5 @@
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

disdrodb/utils/directories.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -212,7 +210,7 @@ def is_empty_directory(path, skip_hidden=True):
     return len(paths) == 0
 
 
-def _remove_file_or_directories(path, logger=None):
+def remove_file_or_directories(path, logger=None):
     """Return the file/directory or subdirectories tree of ``path``.
 
     Use this function with caution.
@@ -259,7 +257,7 @@ def remove_if_exists(path: str, force: bool = False, logger=None) -> None:
 
     # If force=True, remove the file/directory or subdirectories and files !
     try:
-        _remove_file_or_directories(path, logger=logger)
+        remove_file_or_directories(path, logger=logger)
     except Exception as e:
         msg = f"Can not delete file(s) at {path}. The error is: {e}"
         raise ValueError(msg)

disdrodb/utils/encoding.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -144,7 +142,7 @@ def get_time_encoding() -> dict:
     """
     encoding = {}
     encoding["dtype"] = "int64"  # if float trailing sub-seconds values
-    encoding["fillvalue"] = np.iinfo(np.int64).max
+    encoding["_FillValue"] = np.iinfo(np.int64).max
     encoding["units"] = EPOCH
     encoding["calendar"] = "proleptic_gregorian"
     return encoding

disdrodb/utils/event.py

@@ -1,5 +1,5 @@
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

disdrodb/utils/list.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

disdrodb/utils/logger.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

disdrodb/utils/manipulations.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -17,16 +15,194 @@
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 # -----------------------------------------------------------------------------.
 """Include functions helping for DISDRODB product manipulations."""
-
 import numpy as np
+import xarray as xr
 
-from disdrodb.constants import DIAMETER_DIMENSION
+from disdrodb.constants import DIAMETER_DIMENSION, VELOCITY_DIMENSION
 from disdrodb.utils.xarray import unstack_datarray_dimension
 
 
+def define_diameter_datarray(bounds):
+    """Define diameter DataArray."""
+    diameters_bin_lower = bounds[:-1]
+    diameters_bin_upper = bounds[1:]
+    diameters_bin_width = diameters_bin_upper - diameters_bin_lower
+    diameters_bin_center = diameters_bin_lower + diameters_bin_width / 2
+    da = xr.DataArray(
+        diameters_bin_center,
+        dims="diameter_bin_center",
+        coords={
+            "diameter_bin_width": ("diameter_bin_center", diameters_bin_width),
+            "diameter_bin_lower": ("diameter_bin_center", diameters_bin_lower),
+            "diameter_bin_upper": ("diameter_bin_center", diameters_bin_upper),
+            "diameter_bin_center": ("diameter_bin_center", diameters_bin_center),
+        },
+    )
+    return da
+
+
+def define_velocity_datarray(bounds):
+    """Define velocity DataArray."""
+    velocitys_bin_lower = bounds[:-1]
+    velocitys_bin_upper = bounds[1:]
+    velocitys_bin_width = velocitys_bin_upper - velocitys_bin_lower
+    velocitys_bin_center = velocitys_bin_lower + velocitys_bin_width / 2
+    da = xr.DataArray(
+        velocitys_bin_center,
+        dims="velocity_bin_center",
+        coords={
+            "velocity_bin_width": ("velocity_bin_center", velocitys_bin_width),
+            "velocity_bin_lower": ("velocity_bin_center", velocitys_bin_lower),
+            "velocity_bin_upper": ("velocity_bin_center", velocitys_bin_upper),
+            "velocity_bin_center": ("velocity_bin_center", velocitys_bin_center),
+        },
+    )
+    return da
+
+
+def define_diameter_array(diameter_min=0, diameter_max=10, diameter_spacing=0.05):
+    """
+    Define an array of diameters and their corresponding bin properties.
+
+    Parameters
+    ----------
+    diameter_min : float, optional
+        The minimum diameter value. The default value is 0 mm.
+    diameter_max : float, optional
+        The maximum diameter value. The default value is 10 mm.
+    diameter_spacing : float, optional
+        The spacing between diameter values. The default value is 0.05 mm.
+
+    Returns
+    -------
+    xr.DataArray
+        A DataArray containing the center of each diameter bin, with coordinates for
+        the bin width, lower bound, upper bound, and center.
+
+    """
+    diameters_bounds = np.arange(diameter_min, diameter_max + diameter_spacing / 2, step=diameter_spacing)
+    return define_diameter_datarray(diameters_bounds)
+
+
+def define_velocity_array(velocity_min=0, velocity_max=10, velocity_spacing=0.05):
+    """
+    Define an array of velocities and their corresponding bin properties.
+
+    Parameters
+    ----------
+    velocity_min : float, optional
+        The minimum velocity value. The default value is 0 mm.
+    velocity_max : float, optional
+        The maximum velocity value. The default value is 10 mm.
+    velocity_spacing : float, optional
+        The spacing between velocity values. The default value is 0.05 mm.
+
+    Returns
+    -------
+    xr.DataArray
+        A DataArray containing the center of each velocity bin, with coordinates for
+        the bin width, lower bound, upper bound, and center.
+
+    """
+    velocitys_bounds = np.arange(velocity_min, velocity_max + velocity_spacing / 2, step=velocity_spacing)
+    return define_velocity_datarray(velocitys_bounds)
+
+
+def filter_diameter_bins(ds, minimum_diameter=None, maximum_diameter=None):
+    """
+    Filter the dataset to include only diameter bins within specified bounds.
+
+    Parameters
+    ----------
+    ds : xarray.Dataset
+        The dataset containing diameter bin data.
+    minimum_diameter : float, optional
+        The minimum diameter to be included, in millimeters.
+        Defaults to the minimum value in `ds["diameter_bin_lower"]`.
+    maximum_diameter : float, optional
+        The maximum diameter to be included, in millimeters.
+        Defaults to the maximum value in `ds["diameter_bin_upper"]`.
+
+    Returns
+    -------
+    xarray.Dataset
+        The filtered dataset containing only the specified diameter bins.
+    """
+    # Put data into memory
+    ds["diameter_bin_lower"] = ds["diameter_bin_lower"].compute()
+    ds["diameter_bin_upper"] = ds["diameter_bin_upper"].compute()
+
+    # Initialize default arguments
+    if minimum_diameter is None:
+        minimum_diameter = ds["diameter_bin_lower"].min().item()
+    if maximum_diameter is None:
+        maximum_diameter = ds["diameter_bin_upper"].max().item()
+
+    # Select bins which overlap the specified diameters
+    valid_indices = np.logical_and(
+        ds["diameter_bin_upper"] > minimum_diameter,
+        ds["diameter_bin_lower"] < maximum_diameter,
+    )
+    ds = ds.isel({DIAMETER_DIMENSION: valid_indices})
+
+    if ds.sizes[DIAMETER_DIMENSION] == 0:
+        msg = f"Filtering using {minimum_diameter=} removes all diameter bins."
+        raise ValueError(msg)
+    return ds
+
+
+def filter_velocity_bins(ds, minimum_velocity=None, maximum_velocity=None):
+    """
+    Filter the dataset to include only velocity bins within specified bounds.
+
+    Parameters
+    ----------
+    ds : xarray.Dataset
+        The dataset containing velocity bin data.
+    minimum_velocity : float, optional
+        The minimum velocity to include in the filter, in meters per second.
+        Defaults to the minimum value in `ds["velocity_bin_lower"]`.
+    maximum_velocity : float, optional
+        The maximum velocity to include in the filter, in meters per second.
+        Defaults to the maximum value in `ds["velocity_bin_upper"]`.
+
+    Returns
+    -------
+    xarray.Dataset
+        The filtered dataset containing only the specified velocity bins.
+    """
+    # Put data into memory
+    ds["velocity_bin_lower"] = ds["velocity_bin_lower"].compute()
+    ds["velocity_bin_upper"] = ds["velocity_bin_upper"].compute()
+
+    # Initialize default arguments
+    if minimum_velocity is None:
+        minimum_velocity = ds["velocity_bin_lower"].min().item()
+    if maximum_velocity is None:
+        maximum_velocity = ds["velocity_bin_upper"].max().item()
+
+    # Select bins which overlap the specified velocities
+    valid_indices = np.logical_and(
+        ds["velocity_bin_upper"] > minimum_velocity,
+        ds["velocity_bin_lower"] < maximum_velocity,
+    )
+
+    ds = ds.isel({VELOCITY_DIMENSION: valid_indices})
+    if ds.sizes[VELOCITY_DIMENSION] == 0:
+        msg = f"Filtering using {minimum_velocity=} removes all velocity bins."
+        raise ValueError(msg)
+    return ds
+
+
 def get_diameter_bin_edges(ds):
     """Retrieve diameter bin edges."""
-    bin_edges = np.append(ds["diameter_bin_lower"].compute().data, ds["diameter_bin_upper"].compute().data[-1])
+    bin_edges = np.append(ds["diameter_bin_lower"].to_numpy(), ds["diameter_bin_upper"].to_numpy()[-1])
+    return bin_edges
+
+
+def get_velocity_bin_edges(ds):
+    """Retrieve velocity bin edges."""
+    bin_edges = np.append(ds["velocity_bin_lower"].to_numpy(), ds["velocity_bin_upper"].to_numpy()[-1])
     return bin_edges
 
 

disdrodb/utils/pydantic.py

@@ -0,0 +1,80 @@
+# -----------------------------------------------------------------------------.
+# Copyright (c) 2021-2026 DISDRODB developers
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+# -----------------------------------------------------------------------------.
+"""Definition of pydantic validation custom class."""
+from pydantic import BaseModel, ConfigDict, ValidationError
+
+
+def format_validation_error(validation_error: Exception) -> str:
+    """Format a Pydantic ValidationError for better readability."""
+    if not isinstance(validation_error, ValidationError):
+        return str(validation_error)
+
+    def _shorten(value, max_len=200):
+        """Safely truncate long inputs."""
+        text = repr(value)
+        if len(text) > max_len:
+            return text[: max_len - 5] + " ...]"
+        return text
+
+    model_name_attr = getattr(validation_error, "title", None)
+    model_name = model_name_attr() if callable(model_name_attr) else model_name_attr or "UnknownModel"
+
+    formatted_errors = [f"Validation errors in {model_name}:"]
+
+    for err in validation_error.errors():
+        path = ".".join(str(loc) for loc in err["loc"]) or "<model root>"
+        msg = err["msg"]
+        err_type = err["type"]
+
+        # Handles both "Value error, ..." and "Value error: ..."
+        if msg.lower().startswith("value error"):
+            msg = msg.split(",", 1)[-1] if "," in msg else msg.split(":", 1)[-1]
+            msg = msg.strip()
+
+        # Model-level (root) errors (raise in after or before)
+        if path == "<model root>":
+            formatted = f"  • {msg}"
+        elif err_type == "missing":
+            formatted = f"  • Missing field '{path}': {msg}"
+        elif "input" in err:
+            formatted = f"  • Field '{path}': {msg} (got: {_shorten(err['input'])})"
+        else:
+            formatted = f"  • Field '{path}': {msg}"
+
+        formatted_errors.append(formatted)
+
+    return "\n".join(formatted_errors)
+
+
+class CustomBaseModel(BaseModel):
+    """Custom pydantic BaseModel.
+
+    Forbid extra keys.
+    Hide URLs in error message.
+    Simplify error message.
+    """
+
+    model_config = ConfigDict(extra="forbid", hide_error_urls=True)
+
+    # Override the standard ValidationError print behavior
+    def __init__(self, **data):
+        try:
+            super().__init__(**data)
+        except ValidationError as e:
+            formatted = format_validation_error(e)
+            # Raise a new simplified exception
+            raise ValueError(formatted) from None

disdrodb/utils/routines.py

@@ -1,7 +1,5 @@
-#!/usr/bin/env python3
-
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

disdrodb/utils/subsetting.py

@@ -1,5 +1,5 @@
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

disdrodb/utils/time.py

@@ -1,5 +1,5 @@
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 DISDRODB developers
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -238,7 +238,7 @@ def regularize_dataset(
     start_time=None,
     end_time=None,
 ):
-    """Regularize a dataset across time dimension with uniform resolution.
+    """Regularize a xarray object across time dimension with uniform resolution.
 
     Parameters
     ----------
@@ -274,6 +274,7 @@ def regularize_dataset(
         start_time = start
     if end_time is None:
         end_time = end
+    xr_obj = xr_obj.sel({time_dim: slice(start_time, end_time)})
 
     # Define new time index
     new_time_index = pd.date_range(