updates branch with a number of minor tweaks

Author: chalmerlowe

google/cloud/bigquery/external_config.py

@@ -474,6 +474,8 @@ def skip_leading_rows(self):
     def skip_leading_rows(self, value):
         self._properties["skipLeadingRows"] = str(value)
 
+    # TODO: null_marker needs to be added to this code base.
+
     @property
     def null_markers(self) -> Optional[List[str]]:
         """Optional[List[str]]: A list of strings represented as SQL NULL value in a CSV file.
@@ -497,7 +499,7 @@ def null_markers(self, value: Optional[List[str]]):
         self._properties["nullMarkers"] = value
 
     @property
-    def source_column_name_match_option(self) -> Optional[str]:
+    def source_column_match(self) -> Optional[str]:
         """Optional[str]: Controls the strategy used to match loaded columns to the schema. If not
         set, a sensible default is chosen based on how the schema is provided. If
         autodetect is used, then columns are matched by name. Otherwise, columns
@@ -514,8 +516,8 @@ def source_column_name_match_option(self) -> Optional[str]:
         """
         return self._properties.get("sourceColumnMatch")
 
-    @source_column_name_match_option.setter
-    def source_column_name_match_option(self, value: Optional[str]):
+    @source_column_match.setter
+    def source_column_match(self, value: Optional[str]):
         self._properties["sourceColumnMatch"] = value
 
     def to_api_repr(self) -> dict:

google/cloud/bigquery/job/load.py

@@ -624,8 +624,6 @@ def timestamp_format(self, value: Optional[str]):
     def null_markers(self) -> Optional[List[str]]:
         """Optional[List[str]]: A list of strings represented as SQL NULL value in a CSV file.
 
-        (CSV only).
-
         null_marker and null_markers can't be set at the same time.
         If null_marker is set, null_markers has to be not set.
         If null_markers is set, null_marker has to be not set.
@@ -645,14 +643,16 @@ def null_markers(self, value: Optional[List[str]]):
         self._set_sub_prop("nullMarkers", value)
 
     @property
-    def source_column_match_strategy(self) -> Optional[SourceColumnMatch]:
-        """Optional[google.cloud.bigquery.enums.SourceColumnMatch]: Controls the strategy
-        used to match loaded columns to the schema. If not set, a sensible default is
-        chosen based on how the schema is provided. If autodetect is used, then
-        columns are matched by name. Otherwise, columns are matched by position.
-        This is done to keep the behavior backward-compatible.
-
-        (CSV only).
+    def source_column_match(self) -> Optional[SourceColumnMatch]:
+        """Optional[google.cloud.bigquery.enums.SourceColumnMatch]: Controls the strategy used to match
+        loaded columns to the schema. If not set, a sensible default is chosen based on how the schema
+        is provided. If autodetect is used, then columns are matched by name. Otherwise, columns
+        are matched by position. This is done to keep the behavior backward-compatible.
+        Acceptable values are:
+          POSITION - matches by position. This assumes that the columns are ordered
+              the same way as the schema.
+          NAME - matches by name. This reads the header row as column names and
+              reorders columns to match the field names in the schema.
 
         See:
         https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.source_column_match_strategy
@@ -662,8 +662,8 @@ def source_column_match_strategy(self) -> Optional[SourceColumnMatch]:
             return SourceColumnMatch(value)
         return None
 
-    @source_column_match_strategy.setter
-    def source_column_match_strategy(self, value: Optional[SourceColumnMatch]):
+    @source_column_match.setter
+    def source_column_match(self, value: Optional[SourceColumnMatch]):
         if value is not None and not isinstance(value, SourceColumnMatch):
             raise TypeError(
                 "value must be a google.cloud.bigquery.enums.SourceColumnMatch or None"

tests/unit/job/test_load.py

@@ -43,7 +43,7 @@ def _setUpConstants(self):
         self.TIME_FORMAT = "%H:%M:%S"
         self.TIMESTAMP_FORMAT = "YYYY-MM-DD HH:MM:SS.SSSSSSZ"
         self.NULL_MARKERS = ["N/A", "NA"]
-        self.SOURCE_COLUMN_NAME_MATCH_OPTION = "NAME"  # Corrected to actual enum value
+        self.SOURCE_COLUMN_MATCH = "NAME"
 
     def _make_resource(self, started=False, ended=False):
         resource = super(TestLoadJob, self)._make_resource(started, ended)
@@ -55,7 +55,9 @@ def _make_resource(self, started=False, ended=False):
         config["timeFormat"] = self.TIME_FORMAT
         config["timestampFormat"] = self.TIMESTAMP_FORMAT
         config["nullMarkers"] = self.NULL_MARKERS
-        config["sourceColumnMatchStrategy"] = self.SOURCE_COLUMN_NAME_MATCH_OPTION  # Keep value as string for mock API repr
+        config[
+            "sourceColumnMatch"
+        ] = self.SOURCE_COLUMN_MATCH  # Keep value as string for mock API repr
         config["destinationTable"] = {
             "projectId": self.PROJECT,
             "datasetId": self.DS_ID,
@@ -191,14 +193,14 @@ def _verifyResourceProperties(self, job, resource):
             self.assertEqual(job.null_markers, config["nullMarkers"])
         else:
             self.assertIsNone(job.null_markers)
-        if "sourceColumnMatchStrategy" in config:
-            # job.source_column_match_strategy will be an Enum, config[...] is a string
+        if "sourceColumnMatch" in config:
+            # job.source_column_match will be an Enum, config[...] is a string
             self.assertEqual(
-                job.source_column_match_strategy.value,
-                config["sourceColumnMatchStrategy"],
+                job.source_column_match.value,
+                config["sourceColumnMatch"],
             )
         else:
-            self.assertIsNone(job.source_column_match_strategy)
+            self.assertIsNone(job.source_column_match)
 
     def test_ctor(self):
         client = _make_client(project=self.PROJECT)
@@ -247,7 +249,7 @@ def test_ctor(self):
         self.assertIsNone(job.time_format)
         self.assertIsNone(job.timestamp_format)
         self.assertIsNone(job.null_markers)
-        self.assertIsNone(job.source_column_match_strategy)
+        self.assertIsNone(job.source_column_match)
 
     def test_ctor_w_config(self):
         from google.cloud.bigquery.schema import SchemaField
@@ -631,7 +633,7 @@ def test_begin_w_alternate_client(self):
             "timeFormat": self.TIME_FORMAT,
             "timestampFormat": self.TIMESTAMP_FORMAT,
             "nullMarkers": self.NULL_MARKERS,
-            "sourceColumnMatchStrategy": self.SOURCE_COLUMN_NAME_MATCH_OPTION,  # Keep value as string for mock API repr
+            "sourceColumnMatch": self.SOURCE_COLUMN_MATCH,
         }
         RESOURCE["configuration"]["load"] = LOAD_CONFIGURATION
         conn1 = make_connection()
@@ -668,7 +670,8 @@ def test_begin_w_alternate_client(self):
         config.null_markers = self.NULL_MARKERS
         # Ensure we are setting with the Enum type if that's what the setter expects
         from google.cloud.bigquery.enums import SourceColumnMatch
-        config.source_column_match_strategy = SourceColumnMatch(self.SOURCE_COLUMN_NAME_MATCH_OPTION)
+
+        config.source_column_match = SourceColumnMatch(self.SOURCE_COLUMN_MATCH)
         with mock.patch(
             "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes"
         ) as final_attributes:

tests/unit/job/test_load_config.py

@@ -906,7 +906,9 @@ def test_timestamp_format_setter(self):
         timestamp_format = "YYYY/MM/DD HH24:MI:SS.FF6 TZR"
         config = self._get_target_class()()
         config.timestamp_format = timestamp_format
-        self.assertEqual(config._properties["load"]["timestampFormat"], timestamp_format)
+        self.assertEqual(
+            config._properties["load"]["timestampFormat"], timestamp_format
+        )
 
     def test_null_markers_missing(self):
         config = self._get_target_class()()
@@ -924,34 +926,34 @@ def test_null_markers_setter(self):
         config.null_markers = null_markers
         self.assertEqual(config._properties["load"]["nullMarkers"], null_markers)
 
-    def test_source_column_match_strategy_missing(self):
+    def test_source_column_match_missing(self):
         config = self._get_target_class()()
-        self.assertIsNone(config.source_column_match_strategy)
+        self.assertIsNone(config.source_column_match)
 
-    def test_source_column_match_strategy_hit(self):
+    def test_source_column_match_hit(self):
         from google.cloud.bigquery.enums import SourceColumnMatch
 
         option_enum = SourceColumnMatch.NAME
         config = self._get_target_class()()
         # Assume API stores the string value of the enum
-        config._properties["load"]["sourceColumnMatchStrategy"] = option_enum.value
-        self.assertEqual(config.source_column_match_strategy, option_enum)
+        config._properties["load"]["sourceColumnMatch"] = option_enum.value
+        self.assertEqual(config.source_column_match, option_enum)
 
-    def test_source_column_match_strategy_setter(self):
+    def test_source_column_match_setter(self):
         from google.cloud.bigquery.enums import SourceColumnMatch
 
         option_enum = SourceColumnMatch.POSITION
         config = self._get_target_class()()
-        config.source_column_match_strategy = option_enum
+        config.source_column_match = option_enum
         # Assert that the string value of the enum is stored
         self.assertEqual(
-            config._properties["load"]["sourceColumnMatchStrategy"], option_enum.value
+            config._properties["load"]["sourceColumnMatch"], option_enum.value
         )
 
-    def test_source_column_match_strategy_setter_invalid_type(self):
+    def test_source_column_match_setter_invalid_type(self):
         config = self._get_target_class()()
         with self.assertRaises(TypeError):
-            config.source_column_match_strategy = "INVALID_STRING_TYPE"
+            config.source_column_match = "INVALID_STRING_TYPE"
 
     def test_parquet_options_missing(self):
         config = self._get_target_class()()