cdapython 2.0.7__tar.gz → 2.0.9__tar.gz

{cdapython-2.0.7 → cdapython-2.0.9}/CHANGELOG.md

@@ -1,3 +1,7 @@
+2025-10-22: 2.0.9: parametrize data\_source check in column\_values()
+
+2025-10-20: 2.0.8: rename CDS to GC throughout
+
 2025-10-08: 2.0.7: fix malformed column metadata selector inside `collate=True` provenance management in get\_data()
 
 2025-09-17: 2.0.6: update ternary numeric comparison handling for latest API ternary operator syntax support

{cdapython-2.0.7 → cdapython-2.0.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cdapython
-Version: 2.0.7
+Version: 2.0.9
 Summary: NCI CRDC CDA front-end user interface library
 License-File: LICENSE
 Requires-Python: >=3.9,<4.0

{cdapython-2.0.7 → cdapython-2.0.9}/cdapython/discover.py

@@ -788,7 +788,7 @@ def column_values(
 
         data_source ( string; optional ):
             Restrict returned values to the given upstream data source. Current
-            valid values are 'GDC', 'PDC', 'IDC', 'CDS' and 'ICDC'.
+            valid values are 'GC', 'GDC', 'PDC', 'IDC' and 'ICDC'.
             Defaults to '' (no filter).
 
         force( boolean; optional ):
@@ -834,20 +834,36 @@ def column_values(
     # Let's not care about case, and remove any whitespace before it can do any damage.
     data_source = re.sub( r'\s+', r'', data_source ).upper()
 
-    # TEMPORARY: enumerate valid `data_source` values and warn the user if they supplied something else.
-    #
-    # This should be replaced ASAP with a fetch from the /release_metadata endpoint.
-
-    allowed_data_source_values = {
-        'GDC',
-        'PDC',
-        'IDC',
-        'CDS',
-        'ICDC'
-    }
+    # Cache valid labels for upstream data sources. The data structure coming back from
+    # release_metadata() is a list of dicts, with each dict looking like
+    # 
+    # {
+    #     'cda_table': 'file',
+    #     'cda_column': 'access',
+    #     'data_source': 'GDC',
+    #     'data_source_version': 'March 2025',
+    #     'data_source_extraction_date': '2025-03-21',
+    #     'data_source_row_count': 3025352,
+    #     'data_source_unique_value_count': 4,
+    #     'data_source_null_count': 407714
+    # }
+
+    try:
+        cached_release_metadata = release_metadata()
+    except Exception as e:
+        log.critical( e )
+        return
+
+    valid_data_sources = set()
+
+    for column_record in cached_release_metadata:
+        record_data_source = column_record['data_source']
+        # Let's not care about case.
+        if record_data_source.upper() != 'CDA':
+            valid_data_sources.add( record_data_source.upper() )
 
-    if data_source != '' and data_source not in allowed_data_source_values:
-        log.error( f"The 'data_source' parameter must be one of [ 'GDC', 'PDC', 'IDC', 'CDS', 'ICDC' ]. You supplied '{data_source}', which is not." )
+    if data_source != '' and data_source not in valid_data_sources:
+        log.error( f"The 'data_source' parameter must be one of { sorted( valid_data_sources ) }. You supplied '{data_source}', which is not." )
         return
 
     #############################################################################################################################

{cdapython-2.0.7 → cdapython-2.0.9}/cdapython/get_data.py

@@ -68,8 +68,8 @@ def get_file_data(
 
         data_source ( string or list of strings; optional ):
             Restrict results to those deriving from the given upstream
-            data source(s). Current valid values are 'GDC', 'IDC', 'PDC',
-            'CDS' and 'ICDC'. (Default: no filter.)
+            data source(s). Current valid values are 'GC', 'GDC', 'IDC',
+            'PDC' and 'ICDC'. (Default: no filter.)
 
         add_columns ( string or list of strings; optional ):
             One or more columns from a second table to add to result data.
@@ -185,8 +185,8 @@ def get_subject_data(
 
         data_source ( string or list of strings; optional ):
             Restrict results to those deriving from the given upstream
-            data source(s). Current valid values are 'GDC', 'IDC', 'PDC',
-            'CDS' and 'ICDC'. (Default: no filter.)
+            data source(s). Current valid values are 'GC', 'GDC', 'IDC',
+            'PDC' and 'ICDC'. (Default: no filter.)
 
         add_columns ( string or list of strings; optional ):
             One or more columns from a second table to add to result data.
@@ -311,8 +311,8 @@ def get_data(
 
         data_source ( string or list of strings; optional ):
             Restrict results to those deriving from the given upstream
-            data source(s). Current valid values are 'GDC', 'IDC', 'PDC',
-            'CDS' and 'ICDC'. (Default: no filter.)
+            data source(s). Current valid values are 'GC', 'GDC', 'IDC',
+            'PDC' and 'ICDC'. (Default: no filter.)
 
         add_columns ( string or list of strings; optional ):
             One or more columns from a second table to add to result data from `table`.
@@ -759,7 +759,7 @@ def get_data(
     #             "ethnicity": null,
     #             "subject_data_at_gdc": true,
     #             "subject_data_at_idc": true,
-    #             "subject_data_at_cds": false,
+    #             "subject_data_at_gc": false,
     #             "subject_data_at_pdc": true,
     #             "subject_data_at_icdc": false,
     #             "subject_data_source_count": 3,

{cdapython-2.0.7 → cdapython-2.0.9}/cdapython/summarize.py

@@ -544,8 +544,8 @@ def summarize_files(
 
         data_source ( string or list of strings; optional ):
             Restrict results to those deriving from the given upstream
-            data source(s). Current valid values are 'GDC', 'IDC', 'PDC',
-            'CDS' and 'ICDC'. (Default: no filter.)
+            data source(s). Current valid values are 'GC', 'GDC', 'IDC',
+            'PDC' and 'ICDC'. (Default: no filter.)
 
         add_columns ( string or list of strings; optional ):
             One or more columns from a second table to add to summary output.
@@ -686,8 +686,8 @@ def summarize_subjects(
 
         data_source ( string or list of strings; optional ):
             Restrict results to those deriving from the given upstream
-            data source(s). Current valid values are 'GDC', 'IDC', 'PDC',
-            'CDS' and 'ICDC'. (Default: no filter.)
+            data source(s). Current valid values are 'GC', 'GDC', 'IDC',
+            'PDC' and 'ICDC'. (Default: no filter.)
 
         add_columns ( string or list of strings; optional ):
             One or more columns from a second table to add to summary output.
@@ -832,8 +832,8 @@ def summarize(
 
         data_source ( string or list of strings; optional ):
             Restrict results to those deriving from the given upstream
-            data source(s). Current valid values are 'GDC', 'IDC', 'PDC',
-            'CDS' and 'ICDC'. (Default: no filter.)
+            data source(s). Current valid values are 'GC', 'GDC', 'IDC',
+            'PDC' and 'ICDC'. (Default: no filter.)
 
         add_columns ( string or list of strings; optional ):
             One or more columns from a second table to add to summary output for `table`.
@@ -1338,37 +1338,37 @@ def summarize(
     #         }
     #       ],
     #       "data_source": {
-    #         "cds_exclusive": 235,
+    #         "gc_exclusive": 235,
     #         "gdc_exclusive": 351,
     #         "icdc_exclusive": 0,
     #         "idc_exclusive": 0,
     #         "pdc_exclusive": 6,
-    #         "cds_gdc_exclusive": 0,
-    #         "cds_icdc_exclusive": 0,
-    #         "cds_idc_exclusive": 898,
-    #         "cds_pdc_exclusive": 0,
+    #         "gc_gdc_exclusive": 0,
+    #         "gc_icdc_exclusive": 0,
+    #         "gc_idc_exclusive": 898,
+    #         "gc_pdc_exclusive": 0,
     #         "gdc_icdc_exclusive": 0,
     #         "gdc_idc_exclusive": 4544,
     #         "gdc_pdc_exclusive": 7,
     #         "icdc_idc_exclusive": 0,
     #         "icdc_pdc_exclusive": 0,
     #         "idc_pdc_exclusive": 0,
-    #         "cds_gdc_icdc_exclusive": 0,
-    #         "cds_gdc_idc_exclusive": 574,
-    #         "cds_gdc_pdc_exclusive": 1,
-    #         "cds_icdc_idc_exclusive": 0,
-    #         "cds_icdc_pdc_exclusive": 0,
-    #         "cds_idc_pdc_exclusive": 0,
+    #         "gc_gdc_icdc_exclusive": 0,
+    #         "gc_gdc_idc_exclusive": 574,
+    #         "gc_gdc_pdc_exclusive": 1,
+    #         "gc_icdc_idc_exclusive": 0,
+    #         "gc_icdc_pdc_exclusive": 0,
+    #         "gc_idc_pdc_exclusive": 0,
     #         "gdc_icdc_idc_exclusive": 0,
     #         "gdc_icdc_pdc_exclusive": 0,
     #         "gdc_idc_pdc_exclusive": 205,
     #         "icdc_idc_pdc_exclusive": 0,
-    #         "cds_gdc_icdc_idc_exclusive": 0,
-    #         "cds_gdc_icdc_pdc_exclusive": 0,
-    #         "cds_gdc_idc_pdc_exclusive": 83,
-    #         "cds_icdc_idc_pdc_exclusive": 0,
+    #         "gc_gdc_icdc_idc_exclusive": 0,
+    #         "gc_gdc_icdc_pdc_exclusive": 0,
+    #         "gc_gdc_idc_pdc_exclusive": 83,
+    #         "gc_icdc_idc_pdc_exclusive": 0,
     #         "gdc_icdc_idc_pdc_exclusive": 0,
-    #         "cds_gdc_icdc_idc_pdc": 0
+    #         "gc_gdc_icdc_idc_pdc": 0
     #       },
     #       "sex": [
     #         {
@@ -1386,7 +1386,7 @@ def summarize(
     #       ]
     #     }
     #   ],
-    #   "query_sql": "WITH subject_preselect AS (SELECT subject.id AS subject_id, subject.id_alias AS subject_id_alias, [...these are very long!...] AS cds_gdc_icdc_idc_pdc) AS subquery) AS data_source, (SELECT observation_columns.sex FROM observation_columns) AS sex) AS json_result"
+    #   "query_sql": "WITH subject_preselect AS (SELECT subject.id AS subject_id, subject.id_alias AS subject_id_alias, [...these are very long!...] AS gc_gdc_icdc_idc_pdc) AS subquery) AS data_source, (SELECT observation_columns.sex FROM observation_columns) AS sex) AS json_result"
     # }
 
     # Report some metadata about the results we got back.

{cdapython-2.0.7 → cdapython-2.0.9}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cdapython"
-version = "2.0.7"
+version = "2.0.9"
 description = "NCI CRDC CDA front-end user interface library"
 authors = []
 readme = "README.md"