Merge branch 'aarthy/qa-fixes' into 'enterprise'

fix: miscellaneous qa fixes

See merge request dkinternal/testgen/dataops-testgen!331

Author: ci bot

testgen/commands/queries/profiling_query.py

@@ -4,7 +4,7 @@
 from testgen.commands.queries.refresh_data_chars_query import CRefreshDataCharsSQL
 from testgen.commands.queries.rollup_scores_query import CRollupScoresSQL
 from testgen.common import date_service, read_template_sql_file, read_template_yaml_file
-from testgen.common.database.database_service import replace_params
+from testgen.common.database.database_service import get_flavor_service, replace_params
 from testgen.common.read_file import replace_templated_functions
 
 
@@ -121,6 +121,7 @@ def _get_params(self) -> dict:
             "CONTINGENCY_MAX_VALUES": self.contingency_max_values,
             "PROCESS_ID": self.process_id,
             "SQL_FLAVOR": self.flavor,
+            "QUOTE": get_flavor_service(self.flavor).quote_character
         }
 
     def _get_query(

testgen/template/profiling/project_update_profile_results_to_estimates.sql

@@ -24,8 +24,8 @@ set sample_ratio = :PROFILE_SAMPLE_RATIO,
     future_date_ct = ROUND(future_date_ct * :PROFILE_SAMPLE_RATIO, 0),
     boolean_true_ct = ROUND(boolean_true_ct * :PROFILE_SAMPLE_RATIO, 0)
 where profile_run_id = :PROFILE_RUN_ID
-and schema_name = split_part(:SAMPLING_TABLE, '.', 1)
-and table_name = split_part(:SAMPLING_TABLE, '.', 2)
+and schema_name = TRIM(SPLIT_PART(:SAMPLING_TABLE, '.', 1), :QUOTE)
+and table_name = TRIM(SPLIT_PART(:SAMPLING_TABLE, '.', 2), :QUOTE)
 and sample_ratio IS NULL;
 
 

testgen/ui/components/frontend/js/components/connection_form.js

@@ -1103,7 +1103,7 @@ const BigqueryForm = (
 
             div(
                 { class: 'text-caption text-right' },
-                `Project ID: ${projectId.val}`,
+                () => `Project ID: ${projectId.val}`,
             ),
         ),
     );

testgen/ui/services/form_service.py

@@ -316,6 +316,8 @@ def on_page_change():
             "hide": column not in columns,
             "headerCheckboxSelection": selection_mode == "multiple" and column == columns[0],
             "headerCheckboxSelectionFilteredOnly": selection_mode == "multiple" and column == columns[0],
+            "sortable": False,
+            "filter": False,
         }
         highlight_kwargs = {
             "cellStyle": cellstyle_jscode,

testgen/ui/views/hygiene_issues.py

@@ -121,7 +121,6 @@ def render(
                 )
             column_name = testgen.select(
                 options=column_options,
-                value_column="column_name",
                 default_value=column_name,
                 bind_to_query="column_name",
                 label="Column",

testgen/ui/views/profiling_results.py

@@ -67,31 +67,39 @@ def render(self, run_id: str, table_name: str | None = None, column_name: str |
                 filters_changed = True
             st.session_state["profiling_results:filters"] = current_filters
 
-
+        run_columns_df = get_profiling_run_columns(run_id)
         with table_filter_column:
-            # Table Name filter
-            df = get_profiling_run_tables(run_id)
-            df = df.sort_values("table_name", key=lambda x: x.str.lower())
             table_name = testgen.select(
-                options=df,
-                value_column="table_name",
+                options=list(run_columns_df["table_name"].unique()),
                 default_value=table_name,
                 bind_to_query="table_name",
                 label="Table",
             )
 
         with column_filter_column:
-            # Column Name filter
-            df = get_profiling_run_columns(run_id, table_name)
-            df = df.sort_values("column_name", key=lambda x: x.str.lower())
+            if table_name:
+                column_options = (
+                    run_columns_df
+                    .loc[run_columns_df["table_name"] == table_name]
+                    ["column_name"]
+                    .dropna()
+                    .unique()
+                    .tolist()
+                )
+            else:
+                column_options = (
+                    run_columns_df
+                    .groupby("column_name")
+                    .first()
+                    .reset_index()
+                    .sort_values("column_name", key=lambda x: x.str.lower())
+                )
             column_name = testgen.select(
-                options=df,
-                value_column="column_name",
+                options=column_options,
                 default_value=column_name,
                 bind_to_query="column_name",
                 label="Column",
-                disabled=not table_name,
-                accept_new_options=bool(table_name),
+                accept_new_options=True,
             )
 
         with sort_column:
@@ -272,27 +280,11 @@ def get_excel_report_data(
 
 
 @st.cache_data(show_spinner=False)
-def get_profiling_run_tables(profiling_run_id: str) -> pd.DataFrame:
+def get_profiling_run_columns(profiling_run_id: str) -> pd.DataFrame:
     query = """
-    SELECT DISTINCT table_name
+    SELECT table_name, column_name
     FROM profile_results
     WHERE profile_run_id = :profiling_run_id
-    ORDER BY table_name;
+    ORDER BY LOWER(table_name), LOWER(column_name);
     """
     return fetch_df_from_db(query, {"profiling_run_id": profiling_run_id})
-
-
-@st.cache_data(show_spinner=False)
-def get_profiling_run_columns(profiling_run_id: str, table_name: str) -> pd.DataFrame:
-    query = """
-    SELECT DISTINCT column_name
-    FROM profile_results
-    WHERE profile_run_id = :profiling_run_id
-        AND table_name = :table_name
-    ORDER BY column_name;
-    """
-    params = {
-        "profiling_run_id": profiling_run_id,
-        "table_name": table_name or "",
-    }
-    return fetch_df_from_db(query, params)