cdapython 2.0.6__tar.gz → 2.0.8__tar.gz

{cdapython-2.0.6 → cdapython-2.0.8}/CHANGELOG.md

@@ -1,3 +1,7 @@
+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
 
 2025-08-18: 2.0.2: update PyYAML build dependency

{cdapython-2.0.6 → cdapython-2.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cdapython
-Version: 2.0.6
+Version: 2.0.8
 Summary: NCI CRDC CDA front-end user interface library
 License-File: LICENSE
 Requires-Python: >=3.9,<4.0

{cdapython-2.0.6 → cdapython-2.0.8}/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 ):
@@ -839,15 +839,15 @@ def column_values(
     # This should be replaced ASAP with a fetch from the /release_metadata endpoint.
 
     allowed_data_source_values = {
+        'GC',
         'GDC',
         'PDC',
         'IDC',
-        'CDS',
         'ICDC'
     }
 
     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." )
+        log.error( f"The 'data_source' parameter must be one of [ 'GC', 'GDC', 'PDC', 'IDC', 'ICDC' ]. You supplied '{data_source}', which is not." )
         return
 
     #############################################################################################################################

{cdapython-2.0.6 → cdapython-2.0.8}/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`.
@@ -609,7 +609,7 @@ def get_data(
         # Ignore requests for columns that are already present by default, and don't add columns twice.
         if column_to_add not in source_table_columns_in_order and column_to_add not in columns_to_add:
             # If collate == True, we'll need to ask for provenance information from this column's
-            # home table, if we haven't yet done so.
+            # home table, if we haven't yet done so. This info is returned by default only for `file` and `subject`.
             if collate_results:
                 # Identify this column's home table.
                 foreign_table_name = ''
@@ -629,7 +629,8 @@ def get_data(
 
     if collate_results:
         # Be sure to include requests for provenance information about foreign tables
-        # included only implicitly (by filters, not by add_columns).
+        # included only implicitly (by filters, not by add_columns). Such info is
+        # only included by default from `file` and `subject`.
 
         for filter_query in set( queries_for_match_all ) | set( queries_for_match_any ):
             # TO DO: Compartmentalize/parametrize this conditional check better: it repeats much that is already made explicit in validation.py.
@@ -648,13 +649,17 @@ def get_data(
                     column_to_add = column_name
             if not filter_is_ternary:
                 column_to_add = re.search( r'^(\S+)\s', filter_query ).group(1)
-            foreign_table_name = cached_column_metadata.query( f"column == '{column_to_add}'" )['table'].iloc[0]
-            # Check to see if we're already asking for provenance info from that table: if not, do, unless {table} is 'upstream_identifiers'.
-            if foreign_table_name != 'upstream_identifiers':
-                for data_source in [ source_label.lower() for source_label in sorted( valid_data_sources ) ]:
-                    provenance_field = f"{foreign_table_name}_data_at_{data_source}"
-                    if provenance_field not in columns_to_add:
-                        columns_to_add.append( provenance_field )
+            # The user-exposed `data_source` parameter can add filters on e.g. `subject_data_at_pdc` -- don't bother with these.
+            # They won't be in the reference structure we're about to search, and they don't on their own indicate
+            # a need for any extra provenance info.
+            if re.search( r'_data_at_', column_to_add ) is None:
+                foreign_table_name = cached_column_metadata.query( f"column == '{column_to_add}'" )['table'].iloc[0]
+                # Check to see if we're already asking for provenance info from that table: if not, do, unless {table} is 'upstream_identifiers'.
+                if foreign_table_name != 'upstream_identifiers':
+                    for data_source in [ source_label.lower() for source_label in sorted( valid_data_sources ) ]:
+                        provenance_field = f"{foreign_table_name}_data_at_{data_source}"
+                        if provenance_field not in columns_to_add:
+                            columns_to_add.append( provenance_field )
 
     columns_to_exclude = list()
 
@@ -754,7 +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-2.0.6 → cdapython-2.0.8}/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-2.0.6 → cdapython-2.0.8}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cdapython"
-version = "2.0.6"
+version = "2.0.8"
 description = "NCI CRDC CDA front-end user interface library"
 authors = []
 readme = "README.md"