refactor: clarify definition of 'synchronization'

Rename the 'is_synchronized' column to 'synchronized' to clarify its
meaning, shifting from "this dataset is currently synchronized with
GBIF" to "this dataset has in the past been synchronized with GBIF."
Also, updated the 'check_is_synchronized' function to align with this
renaming.

src/gbif_registrar/_utilities.py

@@ -21,7 +21,7 @@ def _check_completeness(rgstrs):
     """Checks registrations for completeness.
 
     A complete registration has values for all fields except (perhaps)
-    `is_synchronized`, which is not essential for initiating a GBIF
+    `synchronized`, which is not essential for initiating a GBIF
     crawl.
 
     Parameters
@@ -39,7 +39,7 @@ def _check_completeness(rgstrs):
     UserWarning
         If any registrations are incomplete.
     """
-    rgstrs = rgstrs[_expected_cols()].drop(["is_synchronized"], axis=1)
+    rgstrs = rgstrs[_expected_cols()].drop(["synchronized"], axis=1)
     rgstrs = rgstrs[rgstrs.isna().any(axis=1)]
     if len(rgstrs) > 0:
         rows = rgstrs.index.to_series() + 1
@@ -73,12 +73,12 @@ def _check_group_registrations(rgstrs):
     )
 
 
-def _check_is_synchronized(rgstrs):
+def _check_synchronized(rgstrs):
     """Checks if registrations have been synchronized.
 
     Registrations contain all the information needed for GBIF to successfully
     crawl the corresponding dataset and post to the GBIF data portal. Boolean
-    True/False values in the `is_synchronized` field indicate the dataset is
+    True/False values in the `synchronized` field indicate the dataset has been
     synchronized.
 
     Parameters
@@ -95,9 +95,9 @@ def _check_is_synchronized(rgstrs):
     -----
     If a registration has not yet been crawled.
     """
-    if not rgstrs["is_synchronized"].all():
-        rows = rgstrs["is_synchronized"].index.to_series() + 1
-        rows = rows[~rgstrs["is_synchronized"]].astype("string")
+    if not rgstrs["synchronized"].all():
+        rows = rgstrs["synchronized"].index.to_series() + 1
+        rows = rows[~rgstrs["synchronized"]].astype("string")
         warnings.warn("Unsynchronized registrations in rows: " + ", ".join(rows))
 
 
@@ -295,7 +295,7 @@ def _expected_cols():
         "local_dataset_group_id",
         "local_dataset_endpoint",
         "gbif_dataset_uuid",
-        "is_synchronized",
+        "synchronized",
     ]
     return cols
 

src/gbif_registrar/register.py

@@ -99,7 +99,7 @@ def register_dataset(local_dataset_id, registrations_file):
                 "local_dataset_group_id": None,
                 "local_dataset_endpoint": None,
                 "gbif_dataset_uuid": None,
-                "is_synchronized": False,
+                "synchronized": False,
             },
             index=[0],
         )
@@ -138,7 +138,7 @@ def complete_registration_records(registrations_file):
     registrations = _read_registrations_file(registrations_file)
     # Get all rows where the registrations dataframe columns
     # local_dataset_group_id, local_dataset_endpoint, gbif_dataset_uuid,
-    # is_synchronized contain empty values. These are the rows
+    # synchronized contain empty values. These are the rows
     # that need to be completed.
     record = registrations[
         (registrations["local_dataset_group_id"].isnull())

src/gbif_registrar/validate.py

@@ -5,7 +5,7 @@
 from gbif_registrar._utilities import _check_local_dataset_id
 from gbif_registrar._utilities import _check_group_registrations
 from gbif_registrar._utilities import _check_local_endpoints
-from gbif_registrar._utilities import _check_is_synchronized
+from gbif_registrar._utilities import _check_synchronized
 from gbif_registrar._utilities import _check_local_dataset_id_format
 from gbif_registrar._utilities import _check_local_dataset_group_id_format
 
@@ -15,7 +15,7 @@ def validate_registrations(file_path):
 
     This is a wrapper to `_check_completeness`, `_check_local_dataset_id`,
     `_check_group_registrations`, `_check_local_endpoints`, and
-    `_check_is_synchronized`.
+    `_check_synchronized`.
 
     Parameters
     ----------
@@ -40,6 +40,6 @@ def validate_registrations(file_path):
     _check_local_dataset_id(rgstrs)
     _check_group_registrations(rgstrs)
     _check_local_endpoints(rgstrs)
-    _check_is_synchronized(rgstrs)
+    _check_synchronized(rgstrs)
     _check_local_dataset_id_format(rgstrs)
     _check_local_dataset_group_id_format(rgstrs)

tests/registrations.csv

@@ -1,4 +1,4 @@
-local_dataset_id,local_dataset_group_id,local_dataset_endpoint,gbif_dataset_uuid,is_synchronized
+local_dataset_id,local_dataset_group_id,local_dataset_endpoint,gbif_dataset_uuid,synchronized
 edi.193.4,edi.193,https://pasta.lternet.edu/package/archive/eml/edi/193/4/archive_edi.193.4_15494687022457218,e44c5367-9d09-4328-9a5a-d0f41fb22d61,True
 edi.193.5,edi.193,https://pasta.lternet.edu/package/archive/eml/edi/193/5/archive_edi.193.5_18246176635637788,e44c5367-9d09-4328-9a5a-d0f41fb22d61,True
 edi.356.1,edi.356,https://pasta.lternet.edu/package/archive/eml/edi/356/1/archive_edi.356.1_74665239205233345,8c30c4a7-2f63-4421-83c0-60f3d3b195b1,True

tests/test__utilities.py

@@ -16,7 +16,7 @@
     _check_completeness,
     _check_local_dataset_id,
     _check_one_to_one_cardinality,
-    _check_is_synchronized,
+    _check_synchronized,
     _check_local_dataset_id_format,
     _check_local_dataset_group_id_format,
     _read_registrations_file,
@@ -90,17 +90,17 @@ def test_check_is_synchronized_valid(rgstrs):
     """The registrations file is valid, and doesn't throw a warning."""
     with warnings.catch_warnings(record=True) as warns:
         warnings.simplefilter("always")
-        _check_is_synchronized(rgstrs)
+        _check_synchronized(rgstrs)
         assert len(warns) == 0
 
 
 def test_check_is_synchronized_warn(rgstrs):
     """Unsynchronized registrations result in a warning."""
-    rgstrs.loc[0, "is_synchronized"] = False
-    rgstrs.loc[2, "is_synchronized"] = False
+    rgstrs.loc[0, "synchronized"] = False
+    rgstrs.loc[2, "synchronized"] = False
     with warnings.catch_warnings(record=True) as warns:
         warnings.simplefilter("always")
-        _check_is_synchronized(rgstrs)
+        _check_synchronized(rgstrs)
         assert "Unsynchronized registrations in rows" in str(warns[0].message)
         assert "1, 3" in str(warns[0].message)
 

tests/test_register.py

@@ -87,7 +87,7 @@ def test_read_registrations_casts_dtypes():
     assert rgstrs["local_dataset_group_id"].dtype == "string"
     assert rgstrs["local_dataset_endpoint"].dtype == "string"
     assert rgstrs["gbif_dataset_uuid"].dtype == "string"
-    isinstance(rgstrs["is_synchronized"].dtype, pd.BooleanDtype)
+    isinstance(rgstrs["synchronized"].dtype, pd.BooleanDtype)
 
 
 def test_register_dataset_success(