IndexError: list index out of range
collection_concept_id = 'C1918210292-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1918210292-GES_DISC', 'concept-id': 'G3153480346-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1918210292-GES_DISC'}]}, 'meta': {'association-details': {'collect...v1.9.0', 'Version': '1.9.0'}, 'Name': 'PRODUCT/SUPPORT_DATA/DETAILED_RESULTS/number_of_slant_columns_win2', ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw1/test_spatial_subset_C1918210290')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fec086b4640>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fec09fd7d40>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7fec09fd7c40>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G3153480346-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1918210292-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-77.47980000000001%3A-60.2582%29&subset=lon%2894.47670000000001%3A172.47930000000002%29&granuleId=G3153480346-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job dd9d6645-61cd-4065-8055-30da3eb04d55
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw1/test_spatial_subset_C1918210290/69667152_S5P_OFFL_L2_SO2_20240708T053223_20240708T071352_34899_03_020601_20240710T035025_subsetted.nc4

IndexError: list index out of range
collection_concept_id = 'C1918210023-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1918210023-GES_DISC', 'concept-id': 'G3153572897-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1918210023-GES_DISC'}]}, 'meta': {'association-details': {'collect...RL': 'https://cdn.earthdata.nasa.gov/umm/variable/v1.9.0', 'Version': '1.9.0'}, 'Name': 'PRODUCT/qa_value', ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw0/test_spatial_subset_C1918210020')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fe25b8a3440>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fe25b8a2d40>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7fe25b8a2c40>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G3153572897-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1918210023-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-77.5553%3A-60.3147%29&subset=lon%28-32.5049%3A45.7789%29&granuleId=G3153572897-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 5bf37348-ec8c-4eed-894a-5b61c0f1a92c
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw0/test_spatial_subset_C1918210020/69667153_S5P_OFFL_L2_HCHO_20240708T135951_20240708T154121_34904_03_020601_20240710T060707_subsetted.nc4

OSError: [Errno group not found: PRODUCT] 'PRODUCT'
ds = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7ff8f127a740>
group = '/METADATA/PRODUCT', mode = 'r'
create_group = <function _netcdf4_create_group at 0x7ff8f9a8dc60>

    def _nc4_require_group(ds, group, mode, create_group=_netcdf4_create_group):
        if group in {None, "", "/"}:
            # use the root group
            return ds
        else:
            # make sure it's a string
            if not isinstance(group, str):
                raise ValueError("group must be a string or None")
            # support path-like syntax
            path = group.strip("/").split("/")
            for key in path:
                try:
>                   ds = ds.groups[key]
E                   KeyError: 'PRODUCT'

../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:190: KeyError

During handling of the above exception, another exception occurred:

collection_concept_id = 'C2087131083-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C2087131083-GES_DISC', 'concept-id': 'G3153523491-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C2087131083-GES_DISC'}]}, 'meta': {'association-details': {'collect.../variable/v1.9.0', 'Version': '1.9.0'}, 'Name': 'METADATA/QA_STATISTICS/aerosol_index_354_388_histogram_bounds'}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw4/test_spatial_subset_C2087131080')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
verify_collection.py:423: in group_walk
    subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/api.py:571: in open_dataset
    backend_ds = backend.open_dataset(
../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:646: in open_dataset
    store = NetCDF4DataStore.open(
../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:409: in open
    return cls(manager, group=group, mode=mode, lock=lock, autoclose=autoclose)
../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:356: in __init__
    self.format = self.ds.data_model
../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:418: in ds
    return self._acquire()
../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:413: in _acquire
    ds = _nc4_require_group(root, self._group, self._mode)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

ds = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7ff8f127a740>
group = '/METADATA/PRODUCT', mode = 'r'
create_group = <function _netcdf4_create_group at 0x7ff8f9a8dc60>

    def _nc4_require_group(ds, group, mode, create_group=_netcdf4_create_group):
        if group in {None, "", "/"}:
            # use the root group
            return ds
        else:
            # make sure it's a string
            if not isinstance(group, str):
                raise ValueError("group must be a string or None")
            # support path-like syntax
            path = group.strip("/").split("/")
            for key in path:
                try:
                    ds = ds.groups[key]
                except KeyError as e:
                    if mode != "r":
                        ds = create_group(ds, key)
                    else:
                        # wrap error to provide slightly more helpful message
>                       raise OSError(f"group not found: {key}", e)
E                       OSError: [Errno group not found: PRODUCT] 'PRODUCT'

../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:196: OSError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G3153523491-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C2087131083-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-77.518525%3A-60.286474999999996%29&subset=lon%28-57.830349999999996%3A20.322349999999993%29&granuleId=G3153523491-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job ca92ca89-ab32-4cb9-830e-89fdd4eb524d
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw4/test_spatial_subset_C2087131080/69667200_S5P_OFFL_L2_AER_AI_20240708T154121_20240708T172251_34905_03_020600_20240710T052719_subsetted.nc4

Failed: Unable to find latitude and longitude variables.
collection_concept_id = 'C2832224417-POCLOUD', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C2832224417-POCLOUD', 'concept-id': 'G3153571048-POCLOUD', 'concept-type': 'granul...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C2832224417-POCLOUD'}]}, 'meta': {'association-details': {'collecti...me': 'look', 'Size': 2, 'Type': 'OTHER'}], 'FillValues': [{'Type': 'SCIENCE_FILLVALUE', 'Value': -9999.0}], ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw8/test_spatial_subset_C2832224410')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
>       lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)

verify_collection.py:398: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

dataset = <xarray.Dataset> Size: 232B
Dimensions:                 (ydim_grid: 1, xdim_grid: 1, look: 1,
                        ...                                 -0.43
    history_json:                                       [{"date_time": "2024-...
file_to_subset = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw8/test_spatial_subset_C2832224410/69667223_RSS_SMAP_SSS_L2C_r50422_20240710T043351_2024192_NRT_V06.0_001.nc4')
collection_variable_list = [{'associations': {'collections': [{'concept-id': 'C2832224417-POCLOUD'}]}, 'meta': {'association-details': {'collecti...me': 'look', 'Size': 2, 'Type': 'OTHER'}], 'FillValues': [{'Type': 'SCIENCE_FILLVALUE', 'Value': -9999.0}], ...}}, ...]

    def get_lat_lon_var_names(dataset: xarray.Dataset, file_to_subset: str, collection_variable_list: List[Dict]):
        # Try getting it from UMM-Var first
        lat_var_json, lon_var_json, _ = get_coordinate_vars_from_umm(collection_variable_list)
        lat_var_name = get_variable_name_from_umm_json(lat_var_json)
        lon_var_name = get_variable_name_from_umm_json(lon_var_json)
    
        if lat_var_name and lon_var_name:
            return lat_var_name, lon_var_name
    
        logging.warning("Unable to find lat/lon vars in UMM-Var")
    
        # If that doesn't work, try using cf-xarray to infer lat/lon variable names
        try:
            latitude = [lat for lat in dataset.cf.coordinates['latitude']
                             if lat.lower() in VALID_LATITUDE_VARIABLE_NAMES][0]
            longitude = [lon for lon in dataset.cf.coordinates['longitude']
                             if lon.lower() in VALID_LONGITUDE_VARIABLE_NAMES][0]
            return latitude, longitude
        except:
            logging.warning("Unable to find lat/lon vars using cf_xarray")
    
        # If that still doesn't work, try using l2ss-py directly
        try:
            # file not able to be flattened unless locally downloaded
            shutil.copy(file_to_subset, 'my_copy_file.nc')
            nc_dataset = netCDF4.Dataset('my_copy_file.nc', mode='r+')
            # flatten the dataset
            nc_dataset_flattened = podaac.subsetter.group_handling.transform_grouped_dataset(nc_dataset, 'my_copy_file.nc')
    
            args = {
                    'decode_coords': False,
                    'mask_and_scale': False,
                    'decode_times': False
                    }
    
            with xarray.open_dataset(
                xarray.backends.NetCDF4DataStore(nc_dataset_flattened),
                **args
                ) as flat_dataset:
                    # use l2ss-py to find lat and lon names
                    lat_var_names, lon_var_names = podaac.subsetter.subset.compute_coordinate_variable_names(flat_dataset)
    
            os.remove('my_copy_file.nc')
            if lat_var_names and lon_var_names:
                lat_var_name = lat_var_names.split('__')[-1] if isinstance(lat_var_names, str) else lat_var_names[0].split('__')[-1]
                lon_var_name = lon_var_names.split('__')[-1] if isinstance(lon_var_names, str) else lon_var_names[0].split('__')[-1]
                return lat_var_name, lon_var_name
    
        except ValueError:
            logging.warning("Unable to find lat/lon vars using l2ss-py")
    
        # Still no dice, try using the 'units' variable attribute
        for coord_name, coord in dataset.coords.items():
            if 'units' not in coord.attrs:
                continue
            if coord.attrs['units'] == 'degrees_north' and lat_var_name is None:
                lat_var_name = coord_name
            if coord.attrs['units'] == 'degrees_east' and lon_var_name is None:
                lon_var_name = coord_name
        if lat_var_name and lon_var_name:
            return lat_var_name, lon_var_name
        else:
            logging.warning("Unable to find lat/lon vars using 'units' attribute")
    
        # Out of options, fail the test because we couldn't determine lat/lon variables
>       pytest.fail(f"Unable to find latitude and longitude variables.")
E       Failed: Unable to find latitude and longitude variables.

verify_collection.py:358: Failed
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G3153571048-POCLOUD for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C2832224417-POCLOUD/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-82.321025%3A80.356025%29&subset=lon%28108.981%3A178.179%29&granuleId=G3153571048-POCLOUD
INFO     root:verify_collection.py:385 Submitted harmony job d193dd9c-40cd-4937-92cd-0130728a6539
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw8/test_spatial_subset_C2832224410/69667223_RSS_SMAP_SSS_L2C_r50422_20240710T043351_2024192_NRT_V06.0_001.nc4
WARNING  root:verify_collection.py:302 Unable to find lat/lon vars in UMM-Var
WARNING  root:verify_collection.py:312 Unable to find lat/lon vars using cf_xarray
WARNING  root:verify_collection.py:342 Unable to find lat/lon vars using l2ss-py
WARNING  root:verify_collection.py:355 Unable to find lat/lon vars using 'units' attribute

harmony.harmony.ProcessingFailedException: WorkItem failed: podaac/l2ss-py:2.10.0: Service request failed with an unknown error
collection_concept_id = 'C2832221740-POCLOUD', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C2832221740-POCLOUD', 'concept-id': 'G3153023292-POCLOUD', 'concept-type': 'granul...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C2832221740-POCLOUD'}]}, 'meta': {'association-details': {'collecti...rization_2', 'Size': 2, 'Type': 'OTHER'}], 'FillValues': [{'Type': 'SCIENCE_FILLVALUE', 'Value': -9999.0}], ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw2/test_spatial_subset_C2832221740')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
>       harmony_client.wait_for_processing(job_id, show_progress=True)

verify_collection.py:386: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <harmony.harmony.Client object at 0x7faf24202140>
job_id = '33f834fb-f7a9-4e7b-ada9-86a12651f161', show_progress = True

    def wait_for_processing(self, job_id: str, show_progress: bool = False) -> None:
        """Retrieve a submitted job's completion status in percent.
    
        Args:
            job_id: UUID string for the job you wish to interrogate.
    
        Returns:
            The job's processing progress as a percentage.
    
        :raises
            Exception: This can happen if an invalid job_id is provided or Harmony services
            can't be reached.
        """
        # How often to refresh the screen for progress updates and animating spinners.
        ui_update_interval = 0.33  # in seconds
        running_w_errors_logged = False
    
        intervals = round(self.check_interval / ui_update_interval)
        if show_progress:
            with progressbar.ProgressBar(max_value=100, widgets=progressbar_widgets) as bar:
                progress = 0
                while progress < 100:
                    progress, status, message = self.progress(job_id)
                    if status == 'failed':
>                       raise ProcessingFailedException(job_id, message)
E                       harmony.harmony.ProcessingFailedException: WorkItem failed: podaac/l2ss-py:2.10.0: Service request failed with an unknown error

../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/harmony/harmony.py:986: ProcessingFailedException
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G3153023292-POCLOUD for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C2832221740-POCLOUD/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-82.2991685%3A81.8031285%29&subset=lon%28-171.0%3A171.0%29&granuleId=G3153023292-POCLOUD
INFO     root:verify_collection.py:385 Submitted harmony job 33f834fb-f7a9-4e7b-ada9-86a12651f161

IndexError: list index out of range
collection_concept_id = 'C1627516287-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1627516287-GES_DISC', 'concept-id': 'G2084463561-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1627516287-GES_DISC'}]}, 'meta': {'association-details': {'collect...'URL': 'https://cdn.earthdata.nasa.gov/umm/variable/v1.9.0', 'Version': '1.9.0'}, 'Name': 'PRODUCT/corner', ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw7/test_spatial_subset_C1627516280')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f6165ca5d40>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f6165ca6840>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7f6165ca6a40>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G2084463561-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1627516287-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-76.99937499999999%3A-59.951625%29&subset=lon%28-76.6214%3A-1.5866000000000042%29&granuleId=G2084463561-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 73ea0905-370a-43c7-9a48-c194720d8a8c
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw7/test_spatial_subset_C1627516280/69667265_S5P_OFFL_L2_CO_20210701T170324_20210701T184453_19257_01_010400_20210703T065107_subsetted.nc4

IndexError: list index out of range
collection_concept_id = 'C2087216530-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C2087216530-GES_DISC', 'concept-id': 'G3153523165-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C2087216530-GES_DISC'}]}, 'meta': {'association-details': {'collect...Var', 'URL': 'https://cdn.earthdata.nasa.gov/umm/variable/v1.9.0', 'Version': '1.9.0'}, 'Name': 'PRODUCT/layer'}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw1/test_spatial_subset_C2087216530')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fec087a9040>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fec087a8b40>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7fec087a8a40>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G3153523165-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C2087216530-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-77.70695%3A-60.52905%29&subset=lon%2869.62944999999999%3A147.31855%29&granuleId=G3153523165-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 28a530d5-eff8-4619-a8bc-0fd011e01989
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw1/test_spatial_subset_C2087216530/69667275_S5P_OFFL_L2_CH4_20240708T071352_20240708T085522_34900_03_020600_20240709T231330_subsetted.nc4

IndexError: list index out of range
collection_concept_id = 'C1627516296-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1627516296-GES_DISC', 'concept-id': 'G1902371245-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1627516296-GES_DISC'}]}, 'meta': {'association-details': {'collect...umm/variable/v1.9.0', 'Version': '1.9.0'}, 'Name': 'PRODUCT/sulfurdioxide_total_vertical_column_precision', ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw5/test_spatial_subset_C1627516290')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f9ea4b84340>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f9ea4b86040>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7f9ea4b87140>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G1902371245-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1627516296-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-78.0453%3A-60.6907%29&subset=lon%28-164.82465%3A-84.66935000000001%29&granuleId=G1902371245-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 69ca0cc7-532b-4a0a-a0fc-ba2ee802a2f1
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw5/test_spatial_subset_C1627516290/69667303_S5P_OFFL_L2_SO2_20200712T224601_20200713T002730_14238_01_010108_20200715T211427_subsetted.nc4

IndexError: list index out of range
collection_concept_id = 'C1442068510-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1442068510-GES_DISC', 'concept-id': 'G1628685468-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1442068510-GES_DISC'}]}, 'meta': {'association-details': {'collect...mm/variable/v1.9.0', 'Version': '1.9.0'}, 'Name': 'PRODUCT/SUPPORT_DATA/DETAILED_RESULTS/averaging_kernel', ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw9/test_spatial_subset_C1442068510')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f54b9644040>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f54b973b840>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7f54b973b740>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G1628685468-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1442068510-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-82.265975%3A-63.873025000000005%29&subset=lon%28-112.057275%3A162.74827499999998%29&granuleId=G1628685468-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 7856acdc-2bdf-4069-8787-988c1787bf4d
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw9/test_spatial_subset_C1442068510/69667320_S5P_OFFL_L2_HCHO_20190806T003836_20190806T022006_09387_01_010107_20190812T015759_subsetted.nc4

Failed: Unable to find latitude and longitude variables.
collection_concept_id = 'C2936721448-POCLOUD', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C2936721448-POCLOUD', 'concept-id': 'G3062447313-POCLOUD', 'concept-type': 'granul...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C2936721448-POCLOUD'}]}, 'meta': {'association-details': {'collecti...rization_2', 'Size': 2, 'Type': 'OTHER'}], 'FillValues': [{'Type': 'SCIENCE_FILLVALUE', 'Value': -9999.0}], ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw3/test_spatial_subset_C2936721440')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
>       lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)

verify_collection.py:398: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

dataset = <xarray.Dataset> Size: 240B
Dimensions:                 (ydim_grid: 1, xdim_grid: 1, look: 1,
                        ...                                 -0.43
    history_json:                                           [{"date_time": "2...
file_to_subset = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw3/test_spatial_subset_C2936721440/69667335_RSS_SMAP_SSS_L2C_r47700_20240106T014035_2024006_FNL_V05.3.nc4')
collection_variable_list = [{'associations': {'collections': [{'concept-id': 'C2936721448-POCLOUD'}]}, 'meta': {'association-details': {'collecti...rization_2', 'Size': 2, 'Type': 'OTHER'}], 'FillValues': [{'Type': 'SCIENCE_FILLVALUE', 'Value': -9999.0}], ...}}, ...]

    def get_lat_lon_var_names(dataset: xarray.Dataset, file_to_subset: str, collection_variable_list: List[Dict]):
        # Try getting it from UMM-Var first
        lat_var_json, lon_var_json, _ = get_coordinate_vars_from_umm(collection_variable_list)
        lat_var_name = get_variable_name_from_umm_json(lat_var_json)
        lon_var_name = get_variable_name_from_umm_json(lon_var_json)
    
        if lat_var_name and lon_var_name:
            return lat_var_name, lon_var_name
    
        logging.warning("Unable to find lat/lon vars in UMM-Var")
    
        # If that doesn't work, try using cf-xarray to infer lat/lon variable names
        try:
            latitude = [lat for lat in dataset.cf.coordinates['latitude']
                             if lat.lower() in VALID_LATITUDE_VARIABLE_NAMES][0]
            longitude = [lon for lon in dataset.cf.coordinates['longitude']
                             if lon.lower() in VALID_LONGITUDE_VARIABLE_NAMES][0]
            return latitude, longitude
        except:
            logging.warning("Unable to find lat/lon vars using cf_xarray")
    
        # If that still doesn't work, try using l2ss-py directly
        try:
            # file not able to be flattened unless locally downloaded
            shutil.copy(file_to_subset, 'my_copy_file.nc')
            nc_dataset = netCDF4.Dataset('my_copy_file.nc', mode='r+')
            # flatten the dataset
            nc_dataset_flattened = podaac.subsetter.group_handling.transform_grouped_dataset(nc_dataset, 'my_copy_file.nc')
    
            args = {
                    'decode_coords': False,
                    'mask_and_scale': False,
                    'decode_times': False
                    }
    
            with xarray.open_dataset(
                xarray.backends.NetCDF4DataStore(nc_dataset_flattened),
                **args
                ) as flat_dataset:
                    # use l2ss-py to find lat and lon names
                    lat_var_names, lon_var_names = podaac.subsetter.subset.compute_coordinate_variable_names(flat_dataset)
    
            os.remove('my_copy_file.nc')
            if lat_var_names and lon_var_names:
                lat_var_name = lat_var_names.split('__')[-1] if isinstance(lat_var_names, str) else lat_var_names[0].split('__')[-1]
                lon_var_name = lon_var_names.split('__')[-1] if isinstance(lon_var_names, str) else lon_var_names[0].split('__')[-1]
                return lat_var_name, lon_var_name
    
        except ValueError:
            logging.warning("Unable to find lat/lon vars using l2ss-py")
    
        # Still no dice, try using the 'units' variable attribute
        for coord_name, coord in dataset.coords.items():
            if 'units' not in coord.attrs:
                continue
            if coord.attrs['units'] == 'degrees_north' and lat_var_name is None:
                lat_var_name = coord_name
            if coord.attrs['units'] == 'degrees_east' and lon_var_name is None:
                lon_var_name = coord_name
        if lat_var_name and lon_var_name:
            return lat_var_name, lon_var_name
        else:
            logging.warning("Unable to find lat/lon vars using 'units' attribute")
    
        # Out of options, fail the test because we couldn't determine lat/lon variables
>       pytest.fail(f"Unable to find latitude and longitude variables.")
E       Failed: Unable to find latitude and longitude variables.

verify_collection.py:358: Failed
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G3062447313-POCLOUD for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C2936721448-POCLOUD/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-82.29044999999999%3A82.08044999999998%29&subset=lon%284.51755%3A175.50045%29&granuleId=G3062447313-POCLOUD
INFO     root:verify_collection.py:385 Submitted harmony job 6cb3d6c0-83a0-4ebf-9570-ad5a874fcfdf
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw3/test_spatial_subset_C2936721440/69667335_RSS_SMAP_SSS_L2C_r47700_20240106T014035_2024006_FNL_V05.3.nc4
WARNING  root:verify_collection.py:302 Unable to find lat/lon vars in UMM-Var
WARNING  root:verify_collection.py:312 Unable to find lat/lon vars using cf_xarray
WARNING  root:verify_collection.py:342 Unable to find lat/lon vars using l2ss-py
WARNING  root:verify_collection.py:355 Unable to find lat/lon vars using 'units' attribute

IndexError: list index out of range
collection_concept_id = 'C1918209669-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1918209669-GES_DISC', 'concept-id': 'G3153571422-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1918209669-GES_DISC'}]}, 'meta': {'association-details': {'collect...tracted from _FillValue metadata attribute', 'Type': 'SCIENCE_FILLVALUE', 'Value': 9.969209968386869e+36}], ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw5/test_spatial_subset_C1918209660')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f9ea4b85f40>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f9ea4b86340>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7f9ea4b86440>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G3153571422-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1918209669-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-77.5553%3A-60.3147%29&subset=lon%28-32.5049%3A45.7789%29&granuleId=G3153571422-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 971187ff-caf0-4207-a1ae-49c609e9f52e
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw5/test_spatial_subset_C1918209660/69667398_S5P_OFFL_L2_CLOUD_20240708T135951_20240708T154121_34904_03_020601_20240710T054238_subsetted.nc4

Failed: Timeout >600.0s
collection_concept_id = 'C2847232153-POCLOUD', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C2847232153-POCLOUD', 'concept-id': 'G3152781828-POCLOUD', 'concept-type': 'granul...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C2847232153-POCLOUD'}]}, 'meta': {'association-details': {'collecti...ze': 3200, 'Type': 'CROSS_TRACK_DIMENSION'}], 'FillValues': [{'Type': 'SCIENCE_FILLVALUE', 'Value': -128}], ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw1/test_spatial_subset_C2847232150')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
>       harmony_client.wait_for_processing(job_id, show_progress=True)

verify_collection.py:386: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <harmony.harmony.Client object at 0x7fec10fc1480>
job_id = 'a4cd946c-0996-4cd2-8631-5f9f596c2e65', show_progress = True

    def wait_for_processing(self, job_id: str, show_progress: bool = False) -> None:
        """Retrieve a submitted job's completion status in percent.
    
        Args:
            job_id: UUID string for the job you wish to interrogate.
    
        Returns:
            The job's processing progress as a percentage.
    
        :raises
            Exception: This can happen if an invalid job_id is provided or Harmony services
            can't be reached.
        """
        # How often to refresh the screen for progress updates and animating spinners.
        ui_update_interval = 0.33  # in seconds
        running_w_errors_logged = False
    
        intervals = round(self.check_interval / ui_update_interval)
        if show_progress:
            with progressbar.ProgressBar(max_value=100, widgets=progressbar_widgets) as bar:
                progress = 0
                while progress < 100:
                    progress, status, message = self.progress(job_id)
                    if status == 'failed':
                        raise ProcessingFailedException(job_id, message)
                    if status == 'canceled':
                        print('Job has been canceled.')
                        break
                    if status == 'paused':
                        print('\nJob has been paused. Call `resume()` to resume.', file=sys.stderr)
                        break
                    if (not running_w_errors_logged and status == 'running_with_errors'):
                        print('\nJob is running with errors.', file=sys.stderr)
                        running_w_errors_logged = True
    
                    # This gets around an issue with progressbar. If we update() with 0, the
                    # output shows up as "N/A". If we update with, e.g. 0.1, it rounds down or
                    # truncates to 0 but, importantly, actually displays that.
                    if progress == 0:
                        progress = 0.1
    
                    for _ in range(intervals):
                        bar.update(progress)  # causes spinner to rotate even when no data change
                        sys.stdout.flush()  # ensures correct behavior in Jupyter notebooks
                        if progress >= 100:
                            break
                        else:
>                           time.sleep(ui_update_interval)
E                           Failed: Timeout >600.0s

../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/harmony/harmony.py:1009: Failed
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G3152781828-POCLOUD for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C2847232153-POCLOUD/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%2869.35976775%3A85.53894224999999%29&subset=lon%28-100.48666449999999%3A69.2720845%29&granuleId=G3152781828-POCLOUD
INFO     root:verify_collection.py:385 Submitted harmony job a4cd946c-0996-4cd2-8631-5f9f596c2e65

IndexError: list index out of range
collection_concept_id = 'C1627516288-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1627516288-GES_DISC', 'concept-id': 'G2085128317-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1627516288-GES_DISC'}]}, 'meta': {'association-details': {'collect... 'https://cdn.earthdata.nasa.gov/umm/variable/v1.9.0', 'Version': '1.9.0'}, 'Name': 'PRODUCT/ground_pixel', ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw8/test_spatial_subset_C1627516280')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f81457a6540>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f81455fc740>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7f81455fc640>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G2085128317-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1627516288-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-76.99937499999999%3A-59.951625%29&subset=lon%28-76.6214%3A-1.5866000000000042%29&granuleId=G2085128317-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 7e2534ad-d2e7-4f5d-8bc7-c0b2d8ade0cf
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw8/test_spatial_subset_C1627516280/69667631_S5P_OFFL_L2_CH4_20210701T170324_20210701T184453_19257_01_010400_20210703T102338_subsetted.nc4

IndexError: list index out of range
collection_concept_id = 'C1442068493-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1442068493-GES_DISC', 'concept-id': 'G1628685465-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1442068493-GES_DISC'}]}, 'meta': {'association-details': {'collect...arthdata.nasa.gov/umm/variable/v1.9.0', 'Version': '1.9.0'}, 'Name': 'PRODUCT/carbonmonoxide_total_column', ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw4/test_spatial_subset_C1442068490')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7ff8f1278e40>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7ff8f1279040>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7ff8f1278d40>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G1628685465-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1442068493-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-82.468625%3A-64.100375%29&subset=lon%28-112.00605%3A163.26405%29&granuleId=G1628685465-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job c1967d26-c469-4a99-966b-27278f475669
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw4/test_spatial_subset_C1442068490/69667635_S5P_OFFL_L2_CO_20190806T003836_20190806T022006_09387_01_010302_20190811T235959_subsetted.nc4

assert False
collection_concept_id = 'C1729926922-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1729926922-GES_DISC', 'concept-id': 'G3152466204-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1729926922-GES_DISC'}]}, 'meta': {'association-details': {'collect...9.989990234375}], 'LongName': 'HDFEOS/SWATHS/Temperature-APriori/Data Fields/Temperature-APrioriPrecision', ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw8/test_spatial_subset_C1729926920')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
            group_walk(f.groups, f, '')
    
        assert lat_var_name and lon_var_name
    
        var_ds = None
        msk = None
    
        if science_vars := get_science_vars(collection_variables):
            for idx, value in enumerate(science_vars):
                science_var_name = science_vars[idx]['umm']['Name']
                try:
                    var_ds = subsetted_ds_new[science_var_name]
                    msk = np.logical_not(np.isnan(var_ds.data.squeeze()))
                    break
                except Exception:
                    try:
                        # if the variable couldn't be found because the name includes a group, e.g.,
                        # `geolocation/relative_azimuth_angle`,
                        # then try to access the variable after removing the group name.
                        var_ds = subsetted_ds_new[science_var_name.rsplit("/", 1)[-1]]
                        msk = np.logical_not(np.isnan(var_ds.data.squeeze()))
                        break
                    except Exception:
                        var_ds = None
                        msk = None
    
            if var_ds is None and msk is None:
                pytest.fail(f"Unable to find variable from umm-v to use as science variable.")
    
        else:
            # Can't find a science var in UMM-V, just pick one
    
            science_var_name = next(iter([v for v in subsetted_ds_new.variables if
                                        str(v) not in lat_var_name and str(v) not in lon_var_name and 'time' not in str(v)]))
    
            var_ds = subsetted_ds_new[science_var_name]
    
        try:
            msk = np.logical_not(np.isnan(var_ds.data.squeeze()))
            llat = subsetted_ds_new[lat_var_name].where(msk)
            llon = subsetted_ds_new[lon_var_name].where(msk)
        except ValueError:
    
            llat = subsetted_ds_new[lat_var_name]
            llon = subsetted_ds_new[lon_var_name]
    
        lat_max = llat.max()
        lat_min = llat.min()
    
        lon_min = llon.min()
        lon_max = llon.max()
    
        lon_min = (lon_min + 180) % 360 - 180
        lon_max = (lon_max + 180) % 360 - 180
    
        lat_var_fill_value = subsetted_ds_new[lat_var_name].encoding.get('_FillValue')
        lon_var_fill_value = subsetted_ds_new[lon_var_name].encoding.get('_FillValue')
    
        if lat_var_fill_value:
            if (lat_max <= north or np.isclose(lat_max, north)) and (lat_min >= south or np.isclose(lat_min, south)):
                logging.info("Successful Latitude subsetting")
            elif np.isnan(lat_max) and np.isnan(lat_min):
                logging.info("Partial Lat Success - no Data")
            else:
                assert False
    
        if lon_var_fill_value:
            if (lon_max <= east or np.isclose(lon_max, east)) and (lon_min >= west or np.isclose(lon_min, west)):
                logging.info("Successful Longitude subsetting")
            elif np.isnan(lon_max) and np.isnan(lon_min):
                logging.info("Partial Lon Success - no Data")
            else:
>               assert False
E               assert False

verify_collection.py:512: AssertionError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G3152466204-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1729926922-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-85.5%3A85.5%29&subset=lon%28-171.0%3A171.0%29&granuleId=G3152466204-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job c5690bea-401a-4c62-aed0-6ea0b080eadd
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw8/test_spatial_subset_C1729926920/69667645_MLS-Aura_L2GP-Temperature_v05-03-c01_2024d189_subsetted.nc4
INFO     root:verify_collection.py:500 Successful Latitude subsetting

IndexError: list index out of range
collection_concept_id = 'C1627516285-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1627516285-GES_DISC', 'concept-id': 'G2084435970-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1627516285-GES_DISC'}]}, 'meta': {'association-details': {'collect.../variable/v1.9.0', 'Version': '1.9.0'}, 'Name': 'METADATA/QA_STATISTICS/aerosol_index_354_388_histogram_bounds'}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw6/test_spatial_subset_C1627516280')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fd84d8e7840>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fd84d8e5440>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7fd84d8e5e40>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G2084435970-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1627516285-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-76.82889999999999%3A-59.7251%29&subset=lon%28-77.22455%3A-1.6634499999999974%29&granuleId=G2084435970-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 07cf8f4f-e877-48be-aaf9-3e55e75ccb80
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw6/test_spatial_subset_C1627516280/69667649_S5P_OFFL_L2_AER_AI_20210701T170324_20210701T184453_19257_01_010400_20210703T065109_subsetted.nc4

IndexError: list index out of range
collection_concept_id = 'C1627516300-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1627516300-GES_DISC', 'concept-id': 'G1902371249-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1627516300-GES_DISC'}]}, 'meta': {'association-details': {'collect...asa.gov/umm/variable/v1.9.0', 'Version': '1.9.0'}, 'Name': 'PRODUCT/ozone_total_vertical_column_precision', ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw3/test_spatial_subset_C1627516300')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fd167d80240>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fd16c17bb40>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7fd16c17ba40>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G1902371249-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1627516300-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-78.0453%3A-60.6907%29&subset=lon%28-164.82465%3A-84.66935000000001%29&granuleId=G1902371249-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job a40d5d1b-1459-4720-9987-39193c5babaa
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw3/test_spatial_subset_C1627516300/69667651_S5P_OFFL_L2_O3_20200712T224601_20200713T002730_14238_01_010108_20200715T122623_subsetted.nc4

IndexError: list index out of range
collection_concept_id = 'C1442068509-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1442068509-GES_DISC', 'concept-id': 'G1628706233-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1442068509-GES_DISC'}]}, 'meta': {'association-details': {'collect... 'URL': 'https://cdn.earthdata.nasa.gov/umm/variable/v1.9.0', 'Version': '1.9.0'}, 'Name': 'PRODUCT/level', ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw0/test_spatial_subset_C1442068500')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fe25b4bd640>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fe25b4bdc40>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7fe25b4bdd40>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G1628706233-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1442068509-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-82.265975%3A-63.873025000000005%29&subset=lon%28-112.057275%3A162.74827499999998%29&granuleId=G1628706233-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 22f88dff-f31e-409d-b444-0705db4f9774
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw0/test_spatial_subset_C1442068500/69667675_S5P_OFFL_L2_O3_20190806T003836_20190806T022006_09387_01_010107_20190812T015759_subsetted.nc4

IndexError: list index out of range
collection_concept_id = 'C2179081549-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C2179081549-GES_DISC', 'concept-id': 'G3153007430-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C2179081549-GES_DISC'}]}, 'meta': {'association-details': {'collect...escription': 'Extracted from _FillValue metadata attribute', 'Type': 'SCIENCE_FILLVALUE', 'Value': -9999}], ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw7/test_spatial_subset_C2179081540')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'Swath': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f6165a97140>}
nc_d = <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7f6165a97040>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
>                   data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
E                   IndexError: list index out of range

verify_collection.py:427: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G3153007430-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C2179081549-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-66.25547725%3A-60.46797275%29&subset=lon%28-155.4820265%3A158.80774649999998%29&granuleId=G3153007430-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 47d0b430-a169-44c9-ba7f-14fbd1b35165
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw7/test_spatial_subset_C2179081540/69667679_2A.GPM.DPR.GPM-SLH.20240708-S222318-E235631.058845.V07C_subsetted.nc4
WARNING  root:verify_collection.py:302 Unable to find lat/lon vars in UMM-Var
WARNING  root:verify_collection.py:312 Unable to find lat/lon vars using cf_xarray

IndexError: list index out of range
collection_concept_id = 'C1442068508-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1442068508-GES_DISC', 'concept-id': 'G1628710396-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1442068508-GES_DISC'}]}, 'meta': {'association-details': {'collect...v1.9.0', 'Version': '1.9.0'}, 'Name': 'PRODUCT/SUPPORT_DATA/DETAILED_RESULTS/fitted_radiance_squeeze_win3', ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw4/test_spatial_subset_C1442068500')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7ff8f10c1040>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7ff8f10c0940>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7ff8f10c0840>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G1628710396-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1442068508-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-82.265975%3A-63.873025000000005%29&subset=lon%28-112.057275%3A162.74827499999998%29&granuleId=G1628710396-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 10c4fa5a-96d3-409c-9827-415d72548e4c
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw4/test_spatial_subset_C1442068500/69667681_S5P_OFFL_L2_SO2_20190806T003836_20190806T022006_09387_01_010107_20190812T085130_subsetted.nc4

harmony.harmony.ProcessingFailedException: WorkItem failed: podaac/l2ss-py:2.10.0: Service request failed with an unknown error
collection_concept_id = 'C2068529568-POCLOUD', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C2068529568-POCLOUD', 'concept-id': 'G2586738585-POCLOUD', 'concept-type': 'granul...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C2068529568-POCLOUD'}]}, 'meta': {'association-details': {'collecti...ze': 4193, 'Type': 'ALONG_TRACK_DIMENSION'}, {'Name': 'ni', 'Size': 243, 'Type': 'CROSS_TRACK_DIMENSION'}], ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw6/test_temporal_subset_C206852950')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_temporal_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
        temporal_subset = get_half_temporal_extent(start_time, end_time)
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection,
                                          granule_id=[granule_json['meta']['concept-id']],
                                          temporal=temporal_subset)
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
    
>       harmony_client.wait_for_processing(job_id, show_progress=True)

verify_collection.py:538: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <harmony.harmony.Client object at 0x7fd84d9b0610>
job_id = 'c87a336c-f16b-4207-b019-3779c6ac1857', show_progress = True

    def wait_for_processing(self, job_id: str, show_progress: bool = False) -> None:
        """Retrieve a submitted job's completion status in percent.
    
        Args:
            job_id: UUID string for the job you wish to interrogate.
    
        Returns:
            The job's processing progress as a percentage.
    
        :raises
            Exception: This can happen if an invalid job_id is provided or Harmony services
            can't be reached.
        """
        # How often to refresh the screen for progress updates and animating spinners.
        ui_update_interval = 0.33  # in seconds
        running_w_errors_logged = False
    
        intervals = round(self.check_interval / ui_update_interval)
        if show_progress:
            with progressbar.ProgressBar(max_value=100, widgets=progressbar_widgets) as bar:
                progress = 0
                while progress < 100:
                    progress, status, message = self.progress(job_id)
                    if status == 'failed':
>                       raise ProcessingFailedException(job_id, message)
E                       harmony.harmony.ProcessingFailedException: WorkItem failed: podaac/l2ss-py:2.10.0: Service request failed with an unknown error

../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/harmony/harmony.py:986: ProcessingFailedException
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:519 Using granule G2586738585-POCLOUD for test
INFO     root:verify_collection.py:532 Sending harmony request https://harmony.earthdata.nasa.gov/C2068529568-POCLOUD/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=time%28%222023-01-11T10%3A04%3A49%22%3A%222023-01-11T10%3A54%3A15%22%29&granuleId=G2586738585-POCLOUD
INFO     root:verify_collection.py:536 Submitted harmony job c87a336c-f16b-4207-b019-3779c6ac1857

OSError: [Errno group not found: PRODUCT] 'PRODUCT'
ds = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f9ea4864040>
group = '/METADATA/PRODUCT', mode = 'r'
create_group = <function _netcdf4_create_group at 0x7f9ead382680>

    def _nc4_require_group(ds, group, mode, create_group=_netcdf4_create_group):
        if group in {None, "", "/"}:
            # use the root group
            return ds
        else:
            # make sure it's a string
            if not isinstance(group, str):
                raise ValueError("group must be a string or None")
            # support path-like syntax
            path = group.strip("/").split("/")
            for key in path:
                try:
>                   ds = ds.groups[key]
E                   KeyError: 'PRODUCT'

../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:190: KeyError

During handling of the above exception, another exception occurred:

collection_concept_id = 'C2089270961-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C2089270961-GES_DISC', 'concept-id': 'G3153058150-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C2089270961-GES_DISC'}]}, 'meta': {'association-details': {'collect....0', 'Version': '1.9.0'}, 'Name': 'METADATA/QA_STATISTICS/nitrogendioxide_tropospheric_column_histogram_bounds'}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw5/test_spatial_subset_C2089270960')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
verify_collection.py:423: in group_walk
    subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/api.py:571: in open_dataset
    backend_ds = backend.open_dataset(
../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:646: in open_dataset
    store = NetCDF4DataStore.open(
../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:409: in open
    return cls(manager, group=group, mode=mode, lock=lock, autoclose=autoclose)
../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:356: in __init__
    self.format = self.ds.data_model
../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:418: in ds
    return self._acquire()
../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:413: in _acquire
    ds = _nc4_require_group(root, self._group, self._mode)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

ds = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f9ea4864040>
group = '/METADATA/PRODUCT', mode = 'r'
create_group = <function _netcdf4_create_group at 0x7f9ead382680>

    def _nc4_require_group(ds, group, mode, create_group=_netcdf4_create_group):
        if group in {None, "", "/"}:
            # use the root group
            return ds
        else:
            # make sure it's a string
            if not isinstance(group, str):
                raise ValueError("group must be a string or None")
            # support path-like syntax
            path = group.strip("/").split("/")
            for key in path:
                try:
                    ds = ds.groups[key]
                except KeyError as e:
                    if mode != "r":
                        ds = create_group(ds, key)
                    else:
                        # wrap error to provide slightly more helpful message
>                       raise OSError(f"group not found: {key}", e)
E                       OSError: [Errno group not found: PRODUCT] 'PRODUCT'

../../../../.cache/pypoetry/virtualenvs/l2ss-py-autotest-iYz8Sff2-py3.10/lib/python3.10/site-packages/xarray/backends/netCDF4_.py:196: OSError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G3153058150-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C2089270961-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-76.879075%3A-59.781925%29&subset=lon%28-140.95485%3A-65.13915%29&granuleId=G3153058150-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 19a7b393-9e34-48a9-b538-47bf626fdf8c
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw5/test_spatial_subset_C2089270960/69667707_S5P_OFFL_L2_NO2_20240701T211743_20240701T225913_34809_03_020600_20240703T133502_subsetted.nc4

IndexError: list index out of range
collection_concept_id = 'C1442068490-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1442068490-GES_DISC', 'concept-id': 'G1628672811-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1442068490-GES_DISC'}]}, 'meta': {'association-details': {'collect...ov/umm/variable/v1.9.0', 'Version': '1.9.0'}, 'Name': 'METADATA/QA_STATISTICS/aerosol_index_354_388_pdf_bounds'}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw8/test_spatial_subset_C1442068490')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f81459a2440>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f81459a3740>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7f81459a3940>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G1628672811-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1442068490-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-82.265975%3A-63.873025000000005%29&subset=lon%28-112.057275%3A162.74827499999998%29&granuleId=G1628672811-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job d84ae8a5-b612-4d5c-b5fb-da1cd7eaae5c
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw8/test_spatial_subset_C1442068490/69667713_S5P_OFFL_L2_AER_AI_20190806T003836_20190806T022006_09387_01_010302_20190812T000004_subsetted.nc4

IndexError: list index out of range
collection_concept_id = 'C1442068491-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1442068491-GES_DISC', 'concept-id': 'G1642673899-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1442068491-GES_DISC'}]}, 'meta': {'association-details': {'collect...s://cdn.earthdata.nasa.gov/umm/variable/v1.9.0', 'Version': '1.9.0'}, 'Name': 'PRODUCT/aerosol_mid_height', ...}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw0/test_spatial_subset_C1442068490')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fe25b696e40>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7fe25b696940>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7fe25b696840>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G1642673899-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1442068491-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-82.32457500000001%3A-63.840424999999996%29&subset=lon%28-112.0001%3A163.1541%29&granuleId=G1642673899-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 9f3d6e84-6746-42c8-9eb8-b5cfe3cfec4c
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw0/test_spatial_subset_C1442068490/69667717_S5P_OFFL_L2_AER_LH_20190806T003836_20190806T022006_09387_01_010302_20190812T015801_subsetted.nc4

IndexError: list index out of range
collection_concept_id = 'C1442068511-GES_DISC', env = 'ops'
granule_json = {'meta': {'collection-concept-id': 'C1442068511-GES_DISC', 'concept-id': 'G1629705055-GES_DISC', 'concept-type': 'gran...pecification': {'Name': 'UMM-G', 'URL': 'https://cdn.earthdata.nasa.gov/umm/granule/v1.6.6', 'Version': '1.6.6'}, ...}}
collection_variables = [{'associations': {'collections': [{'concept-id': 'C1442068511-GES_DISC'}]}, 'meta': {'association-details': {'collect...e/v1.9.0', 'Version': '1.9.0'}, 'Name': 'METADATA/QA_STATISTICS/nitrogendioxide_tropospheric_column_pdf_bounds'}}, ...]
harmony_env = <Environment.PROD: 4>
tmp_path = PosixPath('/tmp/pytest-of-runner/pytest-0/popen-gw7/test_spatial_subset_C1442068510')
bearer_token = 'eyJ0eXAiOiJKV1QiLCJvcmlnaW4iOiJFYXJ0aGRhdGEgTG9naW4iLCJzaWciOiJlZGxqd3RwdWJrZXlfb3BzIiwiYWxnIjoiUlMyNTYifQ.eyJ0eXBlIj...M1SxaPfRwaV4PnJa7zbVFlZLcvBhRvf4vqzuF5YM7NH6FVZLvYlGKaafF6MKL_It0xU_qyGVtYqXMQZPxtw3-X8U0FJk7UpNs1KArBsF0dKaHHXtrfp8lA'

    @pytest.mark.timeout(600)
    def test_spatial_subset(collection_concept_id, env, granule_json, collection_variables,
                            harmony_env, tmp_path: pathlib.Path, bearer_token):
        test_spatial_subset.__doc__ = f"Verify spatial subset for {collection_concept_id} in {env}"
    
        logging.info("Using granule %s for test", granule_json['meta']['concept-id'])
    
        # Compute a box that is smaller than the granule extent bounding box
        north, south, east, west = get_bounding_box(granule_json)
        east, west, north, south = create_smaller_bounding_box(east, west, north, south, .95)
    
        start_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["BeginningDateTime"]
        end_time = granule_json['umm']["TemporalExtent"]["RangeDateTime"]["EndingDateTime"]
    
        # Build harmony request
        harmony_client = harmony.Client(env=harmony_env, token=bearer_token)
        request_bbox = harmony.BBox(w=west, s=south, e=east, n=north)
        request_collection = harmony.Collection(id=collection_concept_id)
        harmony_request = harmony.Request(collection=request_collection, spatial=request_bbox,
                                          granule_id=[granule_json['meta']['concept-id']])
    
        logging.info("Sending harmony request %s", harmony_client.request_as_url(harmony_request))
    
        # Submit harmony request and download result
        job_id = harmony_client.submit(harmony_request)
        logging.info("Submitted harmony job %s", job_id)
        harmony_client.wait_for_processing(job_id, show_progress=True)
        subsetted_filepath = None
        for filename in [file_future.result()
                         for file_future
                         in harmony_client.download_all(job_id, directory=f'{tmp_path}', overwrite=True)]:
            logging.info(f'Downloaded: %s', filename)
            subsetted_filepath = pathlib.Path(filename)
    
        # Verify spatial subset worked
        subsetted_ds = xarray.open_dataset(subsetted_filepath, decode_times=False)
        group = None
        # Try to read group in file
        lat_var_name, lon_var_name = get_lat_lon_var_names(subsetted_ds, subsetted_filepath, collection_variables)
        lat_var_name = lat_var_name.split('/')[-1]
        lon_var_name = lon_var_name.split('/')[-1]
    
        with netCDF4.Dataset(subsetted_filepath) as f:
            group_list = []
            def group_walk(groups, nc_d, current_group):
                global subsetted_ds_new
                subsetted_ds_new = None
                # check if the top group has lat or lon variable
                if lat_var_name in list(nc_d.variables.keys()):
                    subsetted_ds_new = subsetted_ds
                else:
                    # if not then we'll need to keep track of the group layers
                    group_list.append(current_group)
    
                # loop through the groups in the current layer
                for g in groups:
                    # end the loop if we've already found latitude
                    if subsetted_ds_new:
                        break
                    # check if the groups have latitude, define the dataset and end the loop if found
                    if lat_var_name in list(nc_d.groups[g].variables.keys()):
                        group_list.append(g)
                        lat_group = '/'.join(group_list)
                        subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                        # add a science variable to the dataset if other groups are in the lat/lon group
                        # some GPM collections won't have any other variables in the same group as lat/lon
                        if len(list(nc_d.groups[g].groups.keys())) > 0:
                            data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                            g_data = lat_group+'/'+data_group
                            subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
                            sci_var = list(subsetted_ds_data.variables.keys())[0]
                            subsetted_ds_new['science_test'] = subsetted_ds_data[sci_var]
                        break
                    # recall the function on a group that has groups in it and didn't find latitude
                    # this is going 'deeper' into the groups
                    if len(list(nc_d.groups[g].groups.keys())) > 0:
                        group_walk(nc_d.groups[g].groups, nc_d.groups[g], g)
                    else:
                        continue
    
>           group_walk(f.groups, f, '')

verify_collection.py:440: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

groups = {'METADATA': <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f6165ca4940>, 'PRODUCT': <[RuntimeError('NetCDF: Not a valid ID') raised in repr()] Group object at 0x7f6165ca6f40>}
nc_d = <[AttributeError('NetCDF: Not a valid ID') raised in repr()] Dataset object at 0x7f6165ca4840>
current_group = ''

    def group_walk(groups, nc_d, current_group):
        global subsetted_ds_new
        subsetted_ds_new = None
        # check if the top group has lat or lon variable
        if lat_var_name in list(nc_d.variables.keys()):
            subsetted_ds_new = subsetted_ds
        else:
            # if not then we'll need to keep track of the group layers
            group_list.append(current_group)
    
        # loop through the groups in the current layer
        for g in groups:
            # end the loop if we've already found latitude
            if subsetted_ds_new:
                break
            # check if the groups have latitude, define the dataset and end the loop if found
            if lat_var_name in list(nc_d.groups[g].variables.keys()):
                group_list.append(g)
                lat_group = '/'.join(group_list)
                subsetted_ds_new = xarray.open_dataset(subsetted_filepath, group=lat_group, decode_times=False)
                # add a science variable to the dataset if other groups are in the lat/lon group
                # some GPM collections won't have any other variables in the same group as lat/lon
                if len(list(nc_d.groups[g].groups.keys())) > 0:
                    data_group = [v for v in list(nc_d.groups[g].groups.keys()) if 'time' not in str(v).lower()][0]
                    g_data = lat_group+'/'+data_group
                    subsetted_ds_data = xarray.open_dataset(subsetted_filepath, group=g_data, decode_times=False)
>                   sci_var = list(subsetted_ds_data.variables.keys())[0]
E                   IndexError: list index out of range

verify_collection.py:430: IndexError
--------------------------------- Captured Log ---------------------------------
INFO     root:verify_collection.py:365 Using granule G1629705055-GES_DISC for test
INFO     root:verify_collection.py:381 Sending harmony request https://harmony.earthdata.nasa.gov/C1442068511-GES_DISC/ogc-api-coverages/1.0.0/collections/all/coverage/rangeset?forceAsync=true&subset=lat%28-82.265975%3A-63.873025000000005%29&subset=lon%28-112.057275%3A162.74827499999998%29&granuleId=G1629705055-GES_DISC
INFO     root:verify_collection.py:385 Submitted harmony job 2ee5fcb9-2d2d-4e3a-ab03-760035c487b1
INFO     root:verify_collection.py:391 Downloaded: /tmp/pytest-of-runner/pytest-0/popen-gw7/test_spatial_subset_C1442068510/69667747_S5P_OFFL_L2_NO2_20190806T003836_20190806T022006_09387_01_010302_20190812T015802_subsetted.nc4