fix(core): don't blank a datetime column when its format coerces every value to NaT

When a temporal column's declared python_date_format doesn't match its
actual data, pd.to_datetime(..., errors='coerce') returns all-NaT and the
result was assigned unconditionally, silently nulling the whole column.
This surfaces in the Samples/drill-detail pane, where a chart's
granularity column (e.g. an epoch-millis 'year' that inherited a '%Y'
string format) renders as N/A for every row. Keep the original values
when a format coerces every non-null entry to NaT.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

RELEASING/validate_this_release.sh

@@ -1,5 +1,3 @@
-#!/usr/bin/env bash
-
 # Licensed to the Apache Software Foundation (ASF) under one
 # or more contributor license agreements.  See the NOTICE file
 # distributed with this work for additional information
@@ -17,6 +15,8 @@
 # specific language governing permissions and limitations
 # under the License.
 
+#!/bin/bash
+
 # Function to determine Python command
 get_python_command() {
     if command -v python3 &>/dev/null; then

docker/apt-install.sh

@@ -38,7 +38,7 @@ RESET='\033[0m'
 echo -e "${GREEN}Updating package lists...${RESET}"
 apt-get update -qq
 
-echo -e "${GREEN}Installing packages: $*${RESET}"
+echo -e "${GREEN}Installing packages: $@${RESET}"
 apt-get install -yqq --no-install-recommends "$@"
 
 echo -e "${GREEN}Autoremoving unnecessary packages...${RESET}"

docker/tag_latest_release.sh

@@ -163,10 +163,10 @@ do
     # Iterate through the components of the version strings
     for (( j=0; j<${#THIS_TAG_NAME_ARRAY[@]}; j++ )); do
         echo "Comparing ${THIS_TAG_NAME_ARRAY[$j]} to ${LATEST_RELEASE_TAG_ARRAY[$j]}"
-        if [[ $((THIS_TAG_NAME_ARRAY[$j])) -gt $((LATEST_RELEASE_TAG_ARRAY[$j])) ]]; then
+        if [[ $((THIS_TAG_NAME_ARRAY[$j])) > $((LATEST_RELEASE_TAG_ARRAY[$j])) ]]; then
             compare_result="greater"
             break
-        elif [[ $((THIS_TAG_NAME_ARRAY[$j])) -lt $((LATEST_RELEASE_TAG_ARRAY[$j])) ]]; then
+        elif [[ $((THIS_TAG_NAME_ARRAY[$j])) < $((LATEST_RELEASE_TAG_ARRAY[$j])) ]]; then
             compare_result="lesser"
             break
         fi

pyproject.toml

@@ -54,7 +54,7 @@ dependencies = [
     "deprecation>=2.1.0, <2.2.0",
     "flask>=2.2.5, <4.0.0",
     "flask-appbuilder>=5.2.2, <6.0.0",
-    "flask-caching>=2.4.1, <3",
+    "flask-caching>=2.1.0, <3",
     "flask-compress>=1.13, <2.0",
     "flask-talisman>=1.0.0, <2.0",
     "flask-login>=0.6.0, < 1.0",
@@ -92,7 +92,7 @@ dependencies = [
     "Pillow>=11.0.0, <13",
     "polyline>=2.0.0, <3.0",
     "pydantic>=2.8.0",
-    "pyparsing>=3.3.2, <4",
+    "pyparsing>=3.0.6, <4",
     "python-dateutil",
     "python-dotenv", # optional dependencies for Flask but required for Superset, see https://flask.palletsprojects.com/en/stable/installation/#optional-dependencies
     "pygeohash",
@@ -127,7 +127,7 @@ aurora-data-api = ["preset-sqlalchemy-aurora-data-api>=0.2.8,<0.3"]
 bigquery = [
     "pandas-gbq>=0.35.0",
     "sqlalchemy-bigquery>=1.17.0",
-    "google-cloud-bigquery>=3.42.2",
+    "google-cloud-bigquery>=3.42.1",
 ]
 clickhouse = ["clickhouse-connect>=1.4.2, <2.0"]
 cockroachdb = ["cockroachdb>=0.3.5, <0.4"]
@@ -142,8 +142,8 @@ databricks = [
     "databricks-sql-connector>=4.2.6, <4.4.0",
     "databricks-sqlalchemy==1.0.5",
 ]
-datafusion = ["flightsql-dbapi>=0.2.2, <0.3"]
-db2 = ["ibm-db-sa<=0.4.4, >=0.4.4"]
+datafusion = ["flightsql-dbapi>=0.2.0, <0.3"]
+db2 = ["ibm-db-sa>0.3.8, <=0.4.4"]
 denodo = ["denodo-sqlalchemy>=2.0.5,<2.1.0"]
 dremio = ["sqlalchemy-dremio>=1.2.1, <4"]
 drill = ["sqlalchemy-drill>=1.1.10, <2"]
@@ -189,7 +189,7 @@ ocient = [
     "shapely",
     "geojson",
 ]
-oracle = ["oracledb>=4.0.2, <5"]
+oracle = ["oracledb>=2.0.0, <5"]
 parseable = ["sqlalchemy-parseable>=0.1.6,<0.2.0"]
 pinot = ["pinotdb>=5.0.0, <10.0.0"]
 playwright = ["playwright>=1.61.0, <2"]
@@ -201,7 +201,7 @@ redshift = ["sqlalchemy-redshift>=0.8.1, <0.9"]
 risingwave = ["sqlalchemy-risingwave"]
 shillelagh = ["shillelagh[all]>=1.4.4, <2"]
 singlestore = ["sqlalchemy-singlestoredb>=1.2.1, <2"]
-snowflake = ["snowflake-sqlalchemy>=1.11.0, <2"]
+snowflake = ["snowflake-sqlalchemy>=1.10.2, <2"]
 sqlite = ["syntaqlite>=0.7.0,<0.8.0"]
 spark = [
     "pyhive[hive_pure_sasl]>=0.7",
@@ -227,7 +227,7 @@ development = [
     "docker",
     "flask-testing",
     "freezegun",
-    "grpcio>=1.82.1",
+    "grpcio>=1.81.1",
     "openapi-spec-validator",
     "parameterized",
     "pip",

requirements/base.txt

@@ -130,7 +130,7 @@ flask-appbuilder==5.2.2
     #   apache-superset-core
 flask-babel==3.1.0
     # via flask-appbuilder
-flask-caching==2.4.1
+flask-caching==2.3.1
     # via apache-superset (pyproject.toml)
 flask-compress==1.24
     # via apache-superset (pyproject.toml)
@@ -329,7 +329,7 @@ pyopenssl==26.3.0
     # via
     #   -r requirements/base.in
     #   shillelagh
-pyparsing==3.3.2
+pyparsing==3.2.3
     # via apache-superset (pyproject.toml)
 pysocks==1.7.1
     # via urllib3

requirements/development.txt

@@ -276,7 +276,7 @@ flask-babel==3.1.0
     # via
     #   -c requirements/base-constraint.txt
     #   flask-appbuilder
-flask-caching==2.4.1
+flask-caching==2.3.1
     # via
     #   -c requirements/base-constraint.txt
     #   apache-superset
@@ -341,7 +341,7 @@ geopy==2.4.1
     #   apache-superset
 gevent==26.4.0
     # via apache-superset
-google-api-core==2.33.0
+google-api-core==2.23.0
     # via
     #   google-cloud-bigquery
     #   google-cloud-core
@@ -362,7 +362,7 @@ google-auth-oauthlib==1.2.1
     # via
     #   pandas-gbq
     #   pydata-google-auth
-google-cloud-bigquery==3.42.2
+google-cloud-bigquery==3.42.1
     # via
     #   apache-superset
     #   pandas-gbq
@@ -386,7 +386,7 @@ greenlet==3.5.3
     #   sqlalchemy
 griffelib==2.0.2
     # via fastmcp-slim
-grpcio==1.83.0
+grpcio==1.81.1
     # via
     #   apache-superset
     #   google-api-core
@@ -795,7 +795,7 @@ pyopenssl==26.3.0
     #   -c requirements/base-constraint.txt
     #   google-auth
     #   shillelagh
-pyparsing==3.3.2
+pyparsing==3.2.3
     # via
     #   -c requirements/base-constraint.txt
     #   apache-superset

scripts/check_license.sh

@@ -35,7 +35,7 @@ acquire_rat_jar () {
       wget --quiet ${URL} -O "$JAR_DL" && mv "$JAR_DL" "$JAR"
     else
       printf "You do not have curl or wget installed, please install rat manually.\n"
-      exit 255
+      exit -1
     fi
   fi
 
@@ -44,7 +44,7 @@ acquire_rat_jar () {
     # We failed to download
     rm "$JAR"
     printf "Our attempt to download rat locally to ${JAR} failed. Please install rat manually.\n"
-    exit 255
+    exit -1
   fi
   printf "Done downloading.\n"
 }

scripts/tag_latest_release.sh

@@ -163,10 +163,10 @@ do
     # Iterate through the components of the version strings
     for (( j=0; j<${#THIS_TAG_NAME_ARRAY[@]}; j++ )); do
         echo "Comparing ${THIS_TAG_NAME_ARRAY[$j]} to ${LATEST_RELEASE_TAG_ARRAY[$j]}"
-        if [[ $((THIS_TAG_NAME_ARRAY[$j])) -gt $((LATEST_RELEASE_TAG_ARRAY[$j])) ]]; then
+        if [[ $((THIS_TAG_NAME_ARRAY[$j])) > $((LATEST_RELEASE_TAG_ARRAY[$j])) ]]; then
             compare_result="greater"
             break
-        elif [[ $((THIS_TAG_NAME_ARRAY[$j])) -lt $((LATEST_RELEASE_TAG_ARRAY[$j])) ]]; then
+        elif [[ $((THIS_TAG_NAME_ARRAY[$j])) < $((LATEST_RELEASE_TAG_ARRAY[$j])) ]]; then
             compare_result="lesser"
             break
         fi

superset-frontend/packages/superset-ui-core/src/components/TableCollection/index.tsx

@@ -66,6 +66,12 @@ const StyledTable = styled(Table)<{
   showRowCount?: boolean;
 }>`
   ${({ theme, isPaginationSticky, showRowCount }) => `
+    th.ant-column-cell {
+      overflow: hidden;
+      text-overflow: ellipsis;
+      white-space: nowrap;
+    }
+
     .actions {
       opacity: 0;
       font-size: ${theme.fontSizeXL}px;

superset/utils/core.py

@@ -2017,13 +2017,26 @@ def _process_datetime_column(
 
         # Parse with or without format (suppress warning if no format)
         if format_to_use:
-            df[col.col_label] = pd.to_datetime(
+            converted = pd.to_datetime(
                 df[col.col_label],
                 utc=False,
                 format=format_to_use,
                 errors="coerce",
                 exact=False,
             )
+            # A format that coerces every non-null value to NaT is a mismatch
+            # (e.g. an epoch-millis column that inherited a '%Y' string format
+            # when used as a chart's granularity). Assigning it would silently
+            # blank the whole column, so keep the original values instead.
+            if df[col.col_label].notna().any() and not converted.notna().any():
+                logger.warning(
+                    "Datetime format %s coerced every value of column %s to NaT; "
+                    "keeping the original values",
+                    format_to_use,
+                    col.col_label,
+                )
+            else:
+                df[col.col_label] = converted
         else:
             with warnings.catch_warnings():
                 warnings.filterwarnings("ignore", message=".*Could not infer format.*")

tests/unit_tests/utils/test_core.py

@@ -273,6 +273,22 @@ def test_normalize_dttm_col() -> None:
     assert df["__time"].astype(str).tolist() == ["2017-07-01"]
 
 
+def test_normalize_dttm_col_mismatched_format_keeps_values() -> None:
+    """A datetime format that coerces every value to NaT is a mismatch (e.g. an
+    epoch-millis column that inherited a ``%Y`` string format when used as a
+    chart's granularity); applying it would silently blank the whole column, so
+    the original values are kept instead of being nulled. Regression for the
+    Samples pane showing N/A for such columns."""
+    df = pd.DataFrame({"year": [1136073600000, 473385600000]})  # epoch ms
+    before = df["year"].tolist()
+
+    normalize_dttm_col(df, (DateColumn(col_label="year", timestamp_format="%Y"),))
+
+    # not blanked to NaT/None
+    assert df["year"].notna().all()
+    assert df["year"].tolist() == before
+
+
 def test_normalize_dttm_col_epoch_seconds() -> None:
     """Test conversion of epoch seconds."""
     df = pd.DataFrame(