disdrodb 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl

disdrodb/api/path.py

@@ -20,11 +20,12 @@
 import os
 
 from disdrodb.configs import get_data_archive_dir, get_metadata_archive_dir
+from disdrodb.constants import ARCHIVE_VERSION
 from disdrodb.utils.directories import check_directory_exists
 from disdrodb.utils.time import (
     ensure_sample_interval_in_seconds,
     get_file_start_end_time,
-    seconds_to_acronym,
+    seconds_to_temporal_resolution,
 )
 
 ####--------------------------------------------------------------------------.
@@ -62,14 +63,13 @@ def define_disdrodb_path(
         The campaign name.
     check_exists : bool, optional
         Whether to check if the directory exists. The default value is ``True``.
+        Raise error if the directory does not exist.
 
     Returns
     -------
     dir_path : str
         Directory path
     """
-    from disdrodb import ARCHIVE_VERSION
-
     if len(campaign_name) > 0 and len(data_source) == 0:
         raise ValueError("If campaign_name is specified, data_source must be specified.")
 
@@ -82,7 +82,7 @@ def define_disdrodb_path(
         dir_path = os.path.join(archive_dir, ARCHIVE_VERSION, data_source, campaign_name)
     if check_exists:
         check_directory_exists(dir_path)
-    return dir_path
+    return os.path.normpath(dir_path)
 
 
 def define_data_source_dir(
@@ -108,6 +108,7 @@ def define_data_source_dir(
         If not specified, the path specified in the DISDRODB active configuration will be used.
     check_exists : bool, optional
         Whether to check if the directory exists. The default value is ``False``.
+        Raise error if the directory does not exist.
 
     Returns
     -------
@@ -349,7 +350,56 @@ def define_config_dir(product):
 #### Directory/Filepaths L0A and L0B products
 
 
-def define_file_folder_path(obj, data_dir, folder_partitioning):
+def define_partitioning_tree(time, folder_partitioning):
+    """Define the time directory tree given a timestep.
+
+    Parameters
+    ----------
+    time : datetime.datetime
+        Timestep.
+    folder_partitioning : str or None
+        Define the subdirectory structure where saving files.
+        Allowed values are:
+          - None: Files are saved directly in data_dir.
+          - "year": Files are saved under a subdirectory for the year.
+          - "year/month": Files are saved under subdirectories for year and month.
+          - "year/month/day": Files are saved under subdirectories for year, month and day
+          - "year/month_name": Files are stored under subdirectories by year and month name
+          - "year/quarter": Files are saved under subdirectories for year and quarter.
+
+    Returns
+    -------
+    str
+        A time partitioned directory tree.
+    """
+    if folder_partitioning == "":
+        return ""
+    if folder_partitioning == "year":
+        year = str(time.year)
+        return year
+    if folder_partitioning == "year/month":
+        year = str(time.year)
+        month = str(time.month).zfill(2)
+        return os.path.join(year, month)
+    if folder_partitioning == "year/month/day":
+        year = str(time.year)
+        month = str(time.month).zfill(2)
+        day = str(time.day).zfill(2)
+        return os.path.join(year, month, day)
+    if folder_partitioning == "year/month_name":
+        year = str(time.year)
+        month = time.strftime("%B")
+        return os.path.join(year, month)
+    if folder_partitioning == "year/quarter":
+        year = str(time.year)
+        # Calculate quarter: months 1-3 => Q1, 4-6 => Q2, etc.
+        quarter = (time.month - 1) // 3 + 1
+        quarter_dir = f"Q{quarter}"
+        return os.path.join(year, quarter_dir)
+    raise NotImplementedError(f"Unrecognized '{folder_partitioning}' folder partitioning scheme.")
+
+
+def define_file_folder_path(obj, dir_path, folder_partitioning):
     """
     Define the folder path where saving a file based on the dataset's starting time.
 
@@ -357,12 +407,13 @@ def define_file_folder_path(obj, data_dir, folder_partitioning):
     ----------
     ds : xarray.Dataset or pandas.DataFrame
         The object containing time information.
-    data_dir : str
+    dir : str
         Directory within the DISDRODB Data Archive where DISDRODB product files are to be saved.
+        It can be a product directory or a logs directory.
     folder_partitioning : str or None
         Define the subdirectory structure where saving files.
         Allowed values are:
-          - None: Files are saved directly in data_dir.
+          - None or "": Files are saved directly in data_dir.
           - "year": Files are saved under a subdirectory for the year.
           - "year/month": Files are saved under subdirectories for year and month.
           - "year/month/day": Files are saved under subdirectories for year, month and day
@@ -382,32 +433,9 @@ def define_file_folder_path(obj, data_dir, folder_partitioning):
     # Retrieve the starting time from the dataset.
     starting_time, _ = get_file_start_end_time(obj)
 
-    # Build the folder path based on the chosen partition scheme.
-    if folder_partitioning == "":
-        return data_dir
-    if folder_partitioning == "year":
-        year = str(starting_time.year)
-        return os.path.join(data_dir, year)
-    if folder_partitioning == "year/month":
-        year = str(starting_time.year)
-        month = str(starting_time.month).zfill(2)
-        return os.path.join(data_dir, year, month)
-    if folder_partitioning == "year/month/day":
-        year = str(starting_time.year)
-        month = str(starting_time.month).zfill(2)
-        day = str(starting_time.day).zfill(2)
-        return os.path.join(data_dir, year, month, day)
-    if folder_partitioning == "year/month_name":
-        year = str(starting_time.year)
-        month = str(starting_time.month_name())
-        return os.path.join(data_dir, year, month)
-    if folder_partitioning == "year/quarter":
-        year = str(starting_time.year)
-        # Calculate quarter: months 1-3 => Q1, 4-6 => Q2, etc.
-        quarter = (starting_time.month - 1) // 3 + 1
-        quarter_dir = f"Q{quarter}"
-        return os.path.join(data_dir, year, quarter_dir)
-    raise NotImplementedError(f"Unrecognized '{folder_partitioning}' folder partitioning scheme.")
+    # Build the folder path based on the chosen partition scheme
+    partitioning_tree = define_partitioning_tree(time=starting_time, folder_partitioning=folder_partitioning)
+    return os.path.normpath(os.path.join(dir_path, partitioning_tree))
 
 
 def define_product_dir_tree(
@@ -448,17 +476,16 @@ def define_product_dir_tree(
         sample_interval = product_kwargs.get("sample_interval")
         check_rolling(rolling)
         check_sample_interval(sample_interval)
-        sample_interval_acronym = define_accumulation_acronym(seconds=sample_interval, rolling=rolling)
-        return os.path.join(sample_interval_acronym)
-    if product == "L2M":
-        rolling = product_kwargs.get("rolling")
-        sample_interval = product_kwargs.get("sample_interval")
-        model_name = product_kwargs.get("model_name")
-        check_rolling(rolling)
-        check_sample_interval(sample_interval)
-        sample_interval_acronym = define_accumulation_acronym(seconds=sample_interval, rolling=rolling)
-        return os.path.join(model_name, sample_interval_acronym)
-    raise ValueError(f"The product {product} is not defined.")
+        temporal_resolution = define_temporal_resolution(seconds=sample_interval, rolling=rolling)
+        return os.path.join(temporal_resolution)
+    # L2M if product == "L2M":
+    rolling = product_kwargs.get("rolling")
+    sample_interval = product_kwargs.get("sample_interval")
+    model_name = product_kwargs.get("model_name")
+    check_rolling(rolling)
+    check_sample_interval(sample_interval)
+    temporal_resolution = define_temporal_resolution(seconds=sample_interval, rolling=rolling)
+    return os.path.join(model_name, temporal_resolution)
 
 
 def define_logs_dir(
@@ -504,7 +531,7 @@ def define_logs_dir(
         product=product,
         **product_kwargs,
     )
-    logs_dir = os.path.join(campaign_dir, "logs", "files", product, product_dir_tree, station_name)
+    logs_dir = os.path.normpath(os.path.join(campaign_dir, "logs", "files", product, product_dir_tree, station_name))
     if check_exists:
         check_directory_exists(logs_dir)
     return str(logs_dir)
@@ -618,7 +645,7 @@ def define_data_dir(
         **product_kwargs,
     )
     # Define data directory
-    data_dir = os.path.join(station_dir, product_dir_tree)
+    data_dir = os.path.normpath(os.path.join(station_dir, product_dir_tree))
     # Check if directory exists
     if check_exists:
         check_directory_exists(data_dir)
@@ -629,15 +656,15 @@ def define_data_dir(
 #### Filenames for DISDRODB products
 
 
-def define_accumulation_acronym(seconds, rolling):
-    """Define the accumulation acronnym.
+def define_temporal_resolution(seconds, rolling):
+    """Define the DISDRODB product temporal resolution.
 
-    Prefix the accumulation interval acronym with ROLL if rolling=True.
+    Prefix the measurement interval with ROLL if rolling=True.
     """
-    accumulation_acronym = seconds_to_acronym(seconds)
+    temporal_resolution = seconds_to_temporal_resolution(seconds)
     if rolling:
-        accumulation_acronym = f"ROLL{accumulation_acronym}"
-    return accumulation_acronym
+        temporal_resolution = f"ROLL{temporal_resolution}"
+    return temporal_resolution
 
 
 ####--------------------------------------------------------------------------.
@@ -649,7 +676,8 @@ def define_filename(
     campaign_name: str,
     station_name: str,
     # Filename options
-    obj=None,
+    start_time=None,
+    end_time=None,
     add_version=True,
     add_time_period=True,
     add_extension=True,
@@ -663,19 +691,22 @@ def define_filename(
 
     Parameters
     ----------
-    obj  : xarray.Dataset or pandas.DataFrame
-        xarray Dataset or pandas DataFrame.
-        Required if add_time_period = True.
     campaign_name : str
        Name of the campaign.
     station_name : str
        Name of the station.
+    start_time : datetime.datatime, optional
+        Start time.
+        Required if add_time_period = True.
+    end_time : datetime.datatime, optional
+        End time.
+        Required if add_time_period = True.
     sample_interval : int, optional
         The sampling interval in seconds of the product.
-        It must be specified only for product L2E and L2M !
+        It must be specified only for product L0C, L1, L2E and L2M !
     rolling : bool, optional
         Whether the dataset has been resampled by aggregating or rolling.
-        It must be specified only for product L2E and L2M !
+        It must be specified only for product L1, L2E and L2M !
     model_name : str
         The model name of the fitted statistical distribution for the DSD.
         It must be specified only for product L2M !
@@ -685,32 +716,37 @@ def define_filename(
     str
         L0B file name.
     """
-    from disdrodb import ARCHIVE_VERSION
     from disdrodb.api.checks import check_product, check_product_kwargs
 
     product = check_product(product)
     product_kwargs = check_product_kwargs(product, product_kwargs)
 
-    # -----------------------------------------.
-    # TODO: Define sample_interval_acronym
-    # - ADD sample_interval_acronym also to L0A and L0B
-    # - Add sample_interval_acronym also to L0C and L1
+    if add_time_period and (start_time is None or end_time is None):
+        raise ValueError("If add_time_period=True, specify start_time and end_time.")
 
     # -----------------------------------------.
-    # Define product acronym
-    product_acronym = f"{product}"
+    # Define product name
+    product_name = f"{product}"
+
+    # L0C ... sample interval known only per-file
+    # L1 ... in future known a priori
+    # if product in ["L1"]:
+    #     # TODO: HACK FOR CURRENT L0C and L1 log files in create_product_logs
+    #     sample_interval = product_kwargs.get("sample_interval",  0)
+    #     temporal_resolution = define_temporal_resolution(seconds=sample_interval, rolling=False)
+    #     product_name = f"{product}.{temporal_resolution}"
     if product in ["L2E", "L2M"]:
         rolling = product_kwargs.get("rolling")
         sample_interval = product_kwargs.get("sample_interval")
-        sample_interval_acronym = define_accumulation_acronym(seconds=sample_interval, rolling=rolling)
-        product_acronym = f"L2E.{sample_interval_acronym}"
+        temporal_resolution = define_temporal_resolution(seconds=sample_interval, rolling=rolling)
+        product_name = f"{product}.{temporal_resolution}"
     if product in ["L2M"]:
         model_name = product_kwargs.get("model_name")
-        product_acronym = f"L2M_{model_name}.{sample_interval_acronym}"
+        product_name = f"L2M_{model_name}.{temporal_resolution}"
 
     # -----------------------------------------.
     # Define base filename
-    filename = f"{product_acronym}.{campaign_name}.{station_name}"
+    filename = f"{product_name}.{campaign_name}.{station_name}"
 
     # -----------------------------------------.
     # Add prefix
@@ -720,10 +756,9 @@ def define_filename(
     # -----------------------------------------.
     # Add time period information
     if add_time_period:
-        starting_time, ending_time = get_file_start_end_time(obj)
-        starting_time = starting_time.strftime("%Y%m%d%H%M%S")
-        ending_time = ending_time.strftime("%Y%m%d%H%M%S")
-        filename = f"{filename}.s{starting_time}.e{ending_time}"
+        start_time = start_time.strftime("%Y%m%d%H%M%S")
+        end_time = end_time.strftime("%Y%m%d%H%M%S")
+        filename = f"{filename}.s{start_time}.e{end_time}"
 
     # -----------------------------------------.
     # Add product version
@@ -759,133 +794,97 @@ def define_l0a_filename(df, campaign_name: str, station_name: str) -> str:
     str
         L0A file name.
     """
-    from disdrodb import ARCHIVE_VERSION
-
     starting_time, ending_time = get_file_start_end_time(df)
-    starting_time = starting_time.strftime("%Y%m%d%H%M%S")
-    ending_time = ending_time.strftime("%Y%m%d%H%M%S")
-    version = ARCHIVE_VERSION
-    filename = f"L0A.{campaign_name}.{station_name}.s{starting_time}.e{ending_time}.{version}.parquet"
+    filename = define_filename(
+        product="L0A",
+        campaign_name=campaign_name,
+        station_name=station_name,
+        # Filename options
+        start_time=starting_time,
+        end_time=ending_time,
+        add_version=True,
+        add_time_period=True,
+        add_extension=True,
+    )
     return filename
 
 
 def define_l0b_filename(ds, campaign_name: str, station_name: str) -> str:
-    """Define L0B file name.
-
-    Parameters
-    ----------
-    ds  : xarray.Dataset
-        L0B xarray Dataset.
-    campaign_name : str
-        Name of the campaign.
-    station_name : str
-        Name of the station.
-
-    Returns
-    -------
-    str
-        L0B file name.
-    """
-    from disdrodb import ARCHIVE_VERSION
-
+    """Define L0B file name."""
     starting_time, ending_time = get_file_start_end_time(ds)
-    starting_time = starting_time.strftime("%Y%m%d%H%M%S")
-    ending_time = ending_time.strftime("%Y%m%d%H%M%S")
-    version = ARCHIVE_VERSION
-    filename = f"L0B.{campaign_name}.{station_name}.s{starting_time}.e{ending_time}.{version}.nc"
+    filename = define_filename(
+        product="L0B",
+        campaign_name=campaign_name,
+        station_name=station_name,
+        # Filename options
+        start_time=starting_time,
+        end_time=ending_time,
+        add_version=True,
+        add_time_period=True,
+        add_extension=True,
+    )
     return filename
 
 
 def define_l0c_filename(ds, campaign_name: str, station_name: str) -> str:
-    """Define L0C file name.
-
-    Parameters
-    ----------
-    ds  : xarray.Dataset
-        L0B xarray Dataset.
-    campaign_name : str
-        Name of the campaign.
-    station_name : str
-        Name of the station.
-
-    Returns
-    -------
-    str
-        L0B file name.
-    """
-    from disdrodb import ARCHIVE_VERSION
-
-    # TODO: add sample_interval as argument
+    """Define L0C file name."""
+    # TODO: add sample_interval as function argument    s
     sample_interval = int(ensure_sample_interval_in_seconds(ds["sample_interval"]).data.item())
-    sample_interval_acronym = define_accumulation_acronym(sample_interval, rolling=False)
+    temporal_resolution = define_temporal_resolution(sample_interval, rolling=False)
     starting_time, ending_time = get_file_start_end_time(ds)
     starting_time = starting_time.strftime("%Y%m%d%H%M%S")
     ending_time = ending_time.strftime("%Y%m%d%H%M%S")
     version = ARCHIVE_VERSION
-    filename = (
-        f"L0C.{sample_interval_acronym}.{campaign_name}.{station_name}.s{starting_time}.e{ending_time}.{version}.nc"
-    )
+    filename = f"L0C.{temporal_resolution}.{campaign_name}.{station_name}.s{starting_time}.e{ending_time}.{version}.nc"
     return filename
 
 
 def define_l1_filename(ds, campaign_name, station_name: str) -> str:
-    """Define L1 file name.
-
-    Parameters
-    ----------
-    ds  : xarray.Dataset
-        L1 xarray Dataset.
-    campaign_name : str
-        Name of the campaign.
-    station_name : str
-        Name of the station.
+    """Define L1 file name."""
+    # TODO: add sample_interval and rolling as function argument
 
-    Returns
-    -------
-    str
-        L1 file name.
-    """
-    from disdrodb import ARCHIVE_VERSION
-
-    # TODO: add sample_interval as argument
+    starting_time, ending_time = get_file_start_end_time(ds)
     sample_interval = int(ensure_sample_interval_in_seconds(ds["sample_interval"]).data.item())
-    sample_interval_acronym = define_accumulation_acronym(sample_interval, rolling=False)
+    temporal_resolution = define_temporal_resolution(sample_interval, rolling=False)
     starting_time, ending_time = get_file_start_end_time(ds)
     starting_time = starting_time.strftime("%Y%m%d%H%M%S")
     ending_time = ending_time.strftime("%Y%m%d%H%M%S")
     version = ARCHIVE_VERSION
-    filename = (
-        f"L1.{sample_interval_acronym}.{campaign_name}.{station_name}.s{starting_time}.e{ending_time}.{version}.nc"
-    )
+    filename = f"L1.{temporal_resolution}.{campaign_name}.{station_name}.s{starting_time}.e{ending_time}.{version}.nc"
+
+    # filename = define_filename(
+    #     product="L1",
+    #     campaign_name=campaign_name,
+    #     station_name=station_name,
+    #     # Filename options
+    #     start_time=starting_time,
+    #     end_time=ending_time,
+    #     add_version=True,
+    #     add_time_period=True,
+    #     add_extension=True,
+    #     # Product options
+    #     # sample_interval=sample_interval,
+    #     # rolling=rolling,
+    # )
     return filename
 
 
 def define_l2e_filename(ds, campaign_name: str, station_name: str, sample_interval: int, rolling: bool) -> str:
-    """Define L2E file name.
-
-    Parameters
-    ----------
-    ds  : xarray.Dataset
-        L1 xarray Dataset
-    campaign_name : str
-        Name of the campaign.
-    station_name : str
-        Name of the station
-
-    Returns
-    -------
-    str
-        L0B file name.
-    """
-    from disdrodb import ARCHIVE_VERSION
-
-    sample_interval_acronym = define_accumulation_acronym(seconds=sample_interval, rolling=rolling)
+    """Define L2E file name."""
     starting_time, ending_time = get_file_start_end_time(ds)
-    starting_time = starting_time.strftime("%Y%m%d%H%M%S")
-    ending_time = ending_time.strftime("%Y%m%d%H%M%S")
-    version = ARCHIVE_VERSION
-    filename = (
-        f"L2E.{sample_interval_acronym}.{campaign_name}.{station_name}.s{starting_time}.e{ending_time}.{version}.nc"
+    filename = define_filename(
+        product="L2E",
+        campaign_name=campaign_name,
+        station_name=station_name,
+        # Filename options
+        start_time=starting_time,
+        end_time=ending_time,
+        add_version=True,
+        add_time_period=True,
+        add_extension=True,
+        # Product options
+        sample_interval=sample_interval,
+        rolling=rolling,
     )
     return filename
 
@@ -898,31 +897,21 @@ def define_l2m_filename(
     rolling: bool,
     model_name: str,
 ) -> str:
-    """Define L2M file name.
-
-    Parameters
-    ----------
-    ds  : xarray.Dataset
-        L1 xarray Dataset
-    campaign_name : str
-        Name of the campaign.
-    station_name : str
-        Name of the station
-
-    Returns
-    -------
-    str
-        L0B file name.
-    """
-    from disdrodb import ARCHIVE_VERSION
-
-    sample_interval_acronym = define_accumulation_acronym(seconds=sample_interval, rolling=rolling)
+    """Define L2M file name."""
     starting_time, ending_time = get_file_start_end_time(ds)
-    starting_time = starting_time.strftime("%Y%m%d%H%M%S")
-    ending_time = ending_time.strftime("%Y%m%d%H%M%S")
-    version = ARCHIVE_VERSION
-    filename = (
-        f"L2M_{model_name}.{sample_interval_acronym}.{campaign_name}."
-        + f"{station_name}.s{starting_time}.e{ending_time}.{version}.nc"
+    filename = define_filename(
+        product="L2M",
+        campaign_name=campaign_name,
+        station_name=station_name,
+        # Filename options
+        start_time=starting_time,
+        end_time=ending_time,
+        add_version=True,
+        add_time_period=True,
+        add_extension=True,
+        # Product options
+        sample_interval=sample_interval,
+        rolling=rolling,
+        model_name=model_name,
     )
     return filename

disdrodb/api/search.py

@@ -16,14 +16,15 @@ from disdrodb.api.path import (
     define_station_dir,
 )
 from disdrodb.configs import get_data_archive_dir, get_metadata_archive_dir
-from disdrodb.utils.directories import contains_files, contains_netcdf_or_parquet_files
+from disdrodb.constants import PRODUCTS_REQUIREMENTS
+from disdrodb.utils.directories import contains_files, contains_netcdf_or_parquet_files, list_directories, list_files
 from disdrodb.utils.yaml import read_yaml
 
+####-------------------------------------------------------------------------
+
 
 def get_required_product(product):
     """Determine the required product for input product processing."""
-    from disdrodb import PRODUCTS_REQUIREMENTS
-
     # Check input
     check_product(product)
     # Determine required product
@@ -32,12 +33,13 @@ def get_required_product(product):
 
 
 ####-------------------------------------------------------------------------
-#### List DISDRODB infrastructure directories
+#### List DISDRODB Metadata directories
 
 
 def list_data_sources(metadata_archive_dir, data_sources=None, invalid_fields_policy="raise"):
     """List data sources names in the DISDRODB Metadata Archive."""
-    available_data_sources = os.listdir(os.path.join(metadata_archive_dir, "METADATA"))
+    path = os.path.join(metadata_archive_dir, "METADATA")
+    available_data_sources = sorted(list_directories(path, return_paths=False))
     # Filter by optionally specified data_sources
     if data_sources is not None:
         available_data_sources = check_valid_fields(
@@ -52,7 +54,7 @@ def list_data_sources(metadata_archive_dir, data_sources=None, invalid_fields_po
 
 def _list_campaign_names(metadata_archive_dir, data_source):
     data_source_dir = define_data_source_dir(metadata_archive_dir, product="METADATA", data_source=data_source)
-    campaign_names = os.listdir(data_source_dir)
+    campaign_names = sorted(list_directories(data_source_dir, return_paths=False))
     return campaign_names
 
 
@@ -109,7 +111,7 @@ def _list_station_names(metadata_archive_dir, data_source, campaign_name):
         data_source=data_source,
         campaign_name=campaign_name,
     )
-    metadata_filenames = os.listdir(metadata_dir)
+    metadata_filenames = sorted(list_files(metadata_dir, glob_pattern="*.yml", return_paths=False))
     station_names = [fname.replace(".yml", "").replace(".yaml", "") for fname in metadata_filenames]
     return station_names
 
@@ -167,6 +169,10 @@ def list_station_names(
     return station_names
 
 
+####-------------------------------------------------------------------------
+#### Filtering utilities for available_stations
+
+
 def _finalize_output(list_info, return_tuple):
     # - Return the (data_source, campaign_name, station_name) tuple
     if return_tuple:
@@ -228,7 +234,6 @@ def keep_list_info_elements_with_product_data(data_archive_dir, product, list_in
     checking_function = contains_files if product == "RAW" else contains_netcdf_or_parquet_files
 
     # Check presence of data for each station
-    # TODO: - In parallel over stations to speed up ?
     list_info_with_product_data = []
     for data_source, campaign_name, station_name in list_info:
         data_dir = define_data_dir(
@@ -362,10 +367,11 @@ def available_stations(
     metadata_archive_dir = get_metadata_archive_dir(metadata_archive_dir)
     product = check_product(product) if product is not None else None
     invalid_fields_policy = check_invalid_fields_policy(invalid_fields_policy)
+
     # Retrieve available stations from the Metadata Archive
     # - Raise error if no stations availables !
     list_info = list_station_names(
-        metadata_archive_dir,
+        metadata_archive_dir=metadata_archive_dir,
         data_sources=data_sources,
         campaign_names=campaign_names,
         station_names=station_names,
@@ -484,3 +490,6 @@ def available_campaigns(
     campaign_names = [info[1] for info in list_info]
     campaign_names = np.unique(campaign_names).tolist()
     return campaign_names
+
+
+####-------------------------------------------------------------------------