google-pso-data-validator 6.4.0__tar.gz → 7.1.0__tar.gz

{google_pso_data_validator-6.4.0 → google_pso_data_validator-7.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: google-pso-data-validator
-Version: 6.4.0
+Version: 7.1.0
 Summary: A package to enable easy data validation
 Author: PSO DVT Engineering team
 Author-email: data-validator-eng@google.com
@@ -38,6 +38,15 @@ Provides-Extra: apache-airflow
 Requires-Dist: 1.10.11; extra == "apache-airflow"
 Provides-Extra: pyspark
 Requires-Dist: 3.0.0; extra == "pyspark"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 # Data Validation Tool
 
@@ -154,7 +163,7 @@ data-validation
   [--std COLUMNS]       Comma separated list of columns for stddev_samp or * for all numeric
   [--exclude-columns or -ec]
                         Flag to indicate the list of columns provided should be excluded and not included.
-  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE]
+  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE or CONNECTION_NAME.DATASET.TABLE]
                         BigQuery destination for validation results. Defaults to stdout.
                         See: *Validation Reports* section
   [--service-account or -sa PATH_TO_SA_KEY]
@@ -197,17 +206,16 @@ In addition, please note that SHA256 is not a supported function on Teradata sys
 If you wish to perform this comparison on Teradata you will need to
 [deploy a UDF to perform the conversion](https://github.com/akuroda/teradata-udf-sha2/blob/master/src/sha256.c).)
 
-Below is the command syntax for row validations. In order to run row level
-validations you need to pass a `--primary-key` flag which defines what field(s)
-the validation will be compared on, as well as either the `--comparison-fields` flag
-or the `--hash` flag. See *Primary Keys* section
+Below is the command syntax for row validations. In order to run row level validations we require
+unique columns to join row sets, which are either inferred from the source/target table or provided
+via the `--primary-keys` flag, and either the `--hash`, `--concat` or `--comparison-fields` flags.
+See *Primary Keys* section.
 
 The `--comparison-fields` flag specifies the values (e.g. columns) whose raw values will be compared
 based on the primary key join. The `--hash` flag will run a checksum across specified columns in
 the table. This will include casting to string, sanitizing the data (ifnull, rtrim, upper), concatenating,
 and finally hashing the row.
 
-
 Under the hood, row validation uses
 [Calculated Fields](https://github.com/GoogleCloudPlatform/professional-services-data-validator#calculated-fields) to
 apply functions such as IFNULL() or RTRIM(). These can be edited in the YAML or JSON config file to customize your row validation.
@@ -229,16 +237,17 @@ data-validation
                         Comma separated list of tables in the form schema.table=target_schema.target_table
                         Target schema name and table name are optional.
                         i.e 'bigquery-public-data.new_york_citibike.citibike_trips'
-  --primary-keys or -pk PRIMARY_KEYS
-                        Comma separated list of columns to use as primary keys.  See *Primary Keys* section
   --comparison-fields or -comp-fields FIELDS
                         Comma separated list of columns to compare. Can either be a physical column or an alias
                         See: *Calculated Fields* section for details
   --hash COLUMNS        Comma separated list of columns to hash or * for all columns
   --concat COLUMNS      Comma separated list of columns to concatenate or * for all columns (use if a common hash function is not available between databases)
+  [--primary-keys PRIMARY_KEYS, -pk PRIMARY_KEYS]
+                        Comma separated list of primary key columns, when not specified the value will be inferred
+                        from the source or target table if available.  See *Primary Keys* section
   [--exclude-columns or -ec]
                         Flag to indicate the list of columns provided should be excluded from hash or concat instead of included.
-  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE]
+  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE or CONNECTION_NAME.DATASET.TABLE]
                         BigQuery destination for validation results. Defaults to stdout.
                         See: *Validation Reports* section
   [--service-account or -sa PATH_TO_SA_KEY]
@@ -303,8 +312,6 @@ data-validation
                         Either --tables-list or --source-query (or file) and --target-query (or file) must be provided
   --target-query-file TARGET_QUERY_FILE, -tqf TARGET_QUERY_FILE
                         File containing the target sql command. Supports GCS and local paths.
-  --primary-keys PRIMARY_KEYS, -pk PRIMARY_KEYS
-                        Comma separated list of primary key columns 'col_a,col_b'.  See *Primary Keys* section
   --comparison-fields or -comp-fields FIELDS
                         Comma separated list of columns to compare. Can either be a physical column or an alias
                         See: *Calculated Fields* section for details
@@ -318,7 +325,10 @@ data-validation
   --partition-num INT, -pn INT
                         Number of partitions into which the table should be split, e.g. 1000 or 10000
                         In case this value exceeds the row count of the source/target table, it will be decreased to max(source_row_count, target_row_count)
-  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE]
+  [--primary-keys PRIMARY_KEYS, -pk PRIMARY_KEYS]
+                        Comma separated list of primary key columns, when not specified the value will be inferred
+                        from the source or target table if available.  See *Primary Keys* section
+  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE or CONNECTION_NAME.DATASET.TABLE]
                         BigQuery destination for validation results. Defaults to stdout.
                         See: *Validation Reports* section
   [--service-account or -sa PATH_TO_SA_KEY]
@@ -364,7 +374,7 @@ data-validation
                         Comma separated list of tables in the form schema.table=target_schema.target_table. Or shorthand schema.* for all tables.
                         Target schema name and table name are optional.
                         e.g.: 'bigquery-public-data.new_york_citibike.citibike_trips'
-  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE]
+  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE or CONNECTION_NAME.DATASET.TABLE]
                         BigQuery destination for validation results. Defaults to stdout.
                         See: *Validation Reports* section
   [--service-account or -sa PATH_TO_SA_KEY]
@@ -424,7 +434,7 @@ data-validation
   [--std COLUMNS]       Comma separated list of columns for stddev_samp or * for all numeric
   [--exclude-columns or -ec]
                         Flag to indicate the list of columns provided should be excluded and not included.
-  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE]
+  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE or CONNECTION_NAME.DATASET.TABLE]
                         BigQuery destination for validation results. Defaults to stdout.
                         See: *Validation Reports* section
   [--service-account or -sa PATH_TO_SA_KEY]
@@ -489,11 +499,11 @@ data-validation
   --hash '*'            '*' to hash all columns.
   --concat COLUMNS      Comma separated list of columns to concatenate or * for all columns
                         (use if a common hash function is not available between databases)
-  --primary-key or -pk JOIN_KEY
-                       Common column between source and target tables for join
+  [--primary-keys PRIMARY_KEYS, -pk PRIMARY_KEYS]
+                       Common column between source and target queries for join
   [--exclude-columns or -ec]
                         Flag to indicate the list of columns provided should be excluded from hash or concat instead of included.
-  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE]
+  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE or CONNECTION_NAME.DATASET.TABLE]
                         BigQuery destination for validation results. Defaults to stdout.
                         See: *Validation Reports* section
   [--service-account or -sa PATH_TO_SA_KEY]
@@ -720,6 +730,8 @@ In many cases, validations (e.g. count, min, max etc) produce one row per table.
 and target table is to compare the value for each column in the source with the value of the column in the target.
 `grouped-columns` validation and `validate row` produce multiple rows per table. Data Validation Tool needs one or more columns to uniquely identify each row so the source and target can be compared. Data Validation Tool refers to these columns as primary keys. These do not need to be primary keys in the table. The only requirement is that the keys uniquely identify the row in the results.
 
+These columns are inferred, where possible, from the source/target table or can be provided via the `--primary-keys` flag.
+
 ### Grouped Columns
 
 Grouped Columns contain the fields you want your aggregations to be broken out

{google_pso_data_validator-6.4.0 → google_pso_data_validator-7.1.0}/README.md

@@ -113,7 +113,7 @@ data-validation
   [--std COLUMNS]       Comma separated list of columns for stddev_samp or * for all numeric
   [--exclude-columns or -ec]
                         Flag to indicate the list of columns provided should be excluded and not included.
-  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE]
+  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE or CONNECTION_NAME.DATASET.TABLE]
                         BigQuery destination for validation results. Defaults to stdout.
                         See: *Validation Reports* section
   [--service-account or -sa PATH_TO_SA_KEY]
@@ -156,17 +156,16 @@ In addition, please note that SHA256 is not a supported function on Teradata sys
 If you wish to perform this comparison on Teradata you will need to
 [deploy a UDF to perform the conversion](https://github.com/akuroda/teradata-udf-sha2/blob/master/src/sha256.c).)
 
-Below is the command syntax for row validations. In order to run row level
-validations you need to pass a `--primary-key` flag which defines what field(s)
-the validation will be compared on, as well as either the `--comparison-fields` flag
-or the `--hash` flag. See *Primary Keys* section
+Below is the command syntax for row validations. In order to run row level validations we require
+unique columns to join row sets, which are either inferred from the source/target table or provided
+via the `--primary-keys` flag, and either the `--hash`, `--concat` or `--comparison-fields` flags.
+See *Primary Keys* section.
 
 The `--comparison-fields` flag specifies the values (e.g. columns) whose raw values will be compared
 based on the primary key join. The `--hash` flag will run a checksum across specified columns in
 the table. This will include casting to string, sanitizing the data (ifnull, rtrim, upper), concatenating,
 and finally hashing the row.
 
-
 Under the hood, row validation uses
 [Calculated Fields](https://github.com/GoogleCloudPlatform/professional-services-data-validator#calculated-fields) to
 apply functions such as IFNULL() or RTRIM(). These can be edited in the YAML or JSON config file to customize your row validation.
@@ -188,16 +187,17 @@ data-validation
                         Comma separated list of tables in the form schema.table=target_schema.target_table
                         Target schema name and table name are optional.
                         i.e 'bigquery-public-data.new_york_citibike.citibike_trips'
-  --primary-keys or -pk PRIMARY_KEYS
-                        Comma separated list of columns to use as primary keys.  See *Primary Keys* section
   --comparison-fields or -comp-fields FIELDS
                         Comma separated list of columns to compare. Can either be a physical column or an alias
                         See: *Calculated Fields* section for details
   --hash COLUMNS        Comma separated list of columns to hash or * for all columns
   --concat COLUMNS      Comma separated list of columns to concatenate or * for all columns (use if a common hash function is not available between databases)
+  [--primary-keys PRIMARY_KEYS, -pk PRIMARY_KEYS]
+                        Comma separated list of primary key columns, when not specified the value will be inferred
+                        from the source or target table if available.  See *Primary Keys* section
   [--exclude-columns or -ec]
                         Flag to indicate the list of columns provided should be excluded from hash or concat instead of included.
-  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE]
+  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE or CONNECTION_NAME.DATASET.TABLE]
                         BigQuery destination for validation results. Defaults to stdout.
                         See: *Validation Reports* section
   [--service-account or -sa PATH_TO_SA_KEY]
@@ -262,8 +262,6 @@ data-validation
                         Either --tables-list or --source-query (or file) and --target-query (or file) must be provided
   --target-query-file TARGET_QUERY_FILE, -tqf TARGET_QUERY_FILE
                         File containing the target sql command. Supports GCS and local paths.
-  --primary-keys PRIMARY_KEYS, -pk PRIMARY_KEYS
-                        Comma separated list of primary key columns 'col_a,col_b'.  See *Primary Keys* section
   --comparison-fields or -comp-fields FIELDS
                         Comma separated list of columns to compare. Can either be a physical column or an alias
                         See: *Calculated Fields* section for details
@@ -277,7 +275,10 @@ data-validation
   --partition-num INT, -pn INT
                         Number of partitions into which the table should be split, e.g. 1000 or 10000
                         In case this value exceeds the row count of the source/target table, it will be decreased to max(source_row_count, target_row_count)
-  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE]
+  [--primary-keys PRIMARY_KEYS, -pk PRIMARY_KEYS]
+                        Comma separated list of primary key columns, when not specified the value will be inferred
+                        from the source or target table if available.  See *Primary Keys* section
+  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE or CONNECTION_NAME.DATASET.TABLE]
                         BigQuery destination for validation results. Defaults to stdout.
                         See: *Validation Reports* section
   [--service-account or -sa PATH_TO_SA_KEY]
@@ -323,7 +324,7 @@ data-validation
                         Comma separated list of tables in the form schema.table=target_schema.target_table. Or shorthand schema.* for all tables.
                         Target schema name and table name are optional.
                         e.g.: 'bigquery-public-data.new_york_citibike.citibike_trips'
-  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE]
+  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE or CONNECTION_NAME.DATASET.TABLE]
                         BigQuery destination for validation results. Defaults to stdout.
                         See: *Validation Reports* section
   [--service-account or -sa PATH_TO_SA_KEY]
@@ -383,7 +384,7 @@ data-validation
   [--std COLUMNS]       Comma separated list of columns for stddev_samp or * for all numeric
   [--exclude-columns or -ec]
                         Flag to indicate the list of columns provided should be excluded and not included.
-  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE]
+  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE or CONNECTION_NAME.DATASET.TABLE]
                         BigQuery destination for validation results. Defaults to stdout.
                         See: *Validation Reports* section
   [--service-account or -sa PATH_TO_SA_KEY]
@@ -448,11 +449,11 @@ data-validation
   --hash '*'            '*' to hash all columns.
   --concat COLUMNS      Comma separated list of columns to concatenate or * for all columns
                         (use if a common hash function is not available between databases)
-  --primary-key or -pk JOIN_KEY
-                       Common column between source and target tables for join
+  [--primary-keys PRIMARY_KEYS, -pk PRIMARY_KEYS]
+                       Common column between source and target queries for join
   [--exclude-columns or -ec]
                         Flag to indicate the list of columns provided should be excluded from hash or concat instead of included.
-  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE]
+  [--bq-result-handler or -bqrh PROJECT_ID.DATASET.TABLE or CONNECTION_NAME.DATASET.TABLE]
                         BigQuery destination for validation results. Defaults to stdout.
                         See: *Validation Reports* section
   [--service-account or -sa PATH_TO_SA_KEY]
@@ -679,6 +680,8 @@ In many cases, validations (e.g. count, min, max etc) produce one row per table.
 and target table is to compare the value for each column in the source with the value of the column in the target.
 `grouped-columns` validation and `validate row` produce multiple rows per table. Data Validation Tool needs one or more columns to uniquely identify each row so the source and target can be compared. Data Validation Tool refers to these columns as primary keys. These do not need to be primary keys in the table. The only requirement is that the keys uniquely identify the row in the results.
 
+These columns are inferred, where possible, from the source/target table or can be provided via the `--primary-keys` flag.
+
 ### Grouped Columns
 
 Grouped Columns contain the fields you want your aggregations to be broken out

{google_pso_data_validator-6.4.0 → google_pso_data_validator-7.1.0}/data_validation/__main__.py

@@ -25,6 +25,7 @@ from data_validation import (
     clients,
     consts,
     exceptions,
+    raw_query,
     state_manager,
     util,
 )
@@ -91,6 +92,7 @@ def get_aggregate_config(args, config_manager: ConfigManager):
         "!int64",
         "!decimal",
     ]
+    uuid_types = ["uuid", "!uuid"]
 
     if args.wildcard_include_string_len:
         supported_data_types.extend(["string", "!string"])
@@ -129,7 +131,7 @@ def get_aggregate_config(args, config_manager: ConfigManager):
             "min",
             col_args,
             args.exclude_columns,
-            supported_data_types,
+            supported_data_types + uuid_types,
             cast_to_bigint=cast_to_bigint,
         )
     if args.max:
@@ -138,7 +140,7 @@ def get_aggregate_config(args, config_manager: ConfigManager):
             "max",
             col_args,
             args.exclude_columns,
-            supported_data_types,
+            supported_data_types + uuid_types,
             cast_to_bigint=cast_to_bigint,
         )
     if args.bit_xor:
@@ -219,7 +221,9 @@ def _get_calculated_config(args, config_manager: ConfigManager) -> List[dict]:
     return calculated_configs
 
 
-def _get_comparison_config(args, config_manager: ConfigManager) -> List[dict]:
+def _get_comparison_config(
+    args, config_manager: ConfigManager, primary_keys: list
+) -> List[dict]:
     col_list = (
         None
         if args.comparison_fields == "*"
@@ -230,11 +234,7 @@ def _get_comparison_config(args, config_manager: ConfigManager) -> List[dict]:
         args.exclude_columns,
     )
     # We can't have the PK columns in the comparison SQL twice therefore filter them out here if included.
-    comparison_fields = [
-        _
-        for _ in comparison_fields
-        if _ not in cli_tools.get_arg_list(args.primary_keys.casefold())
-    ]
+    comparison_fields = [_ for _ in comparison_fields if _ not in primary_keys]
 
     # As per #1190, add rstrip for Teradata string comparison fields
     if (
@@ -314,18 +314,25 @@ def build_config_from_args(args: Namespace, config_manager: ConfigManager):
             _get_calculated_config(args, config_manager)
         )
 
-        # Append Comparison fields
-        if args.comparison_fields:
-            config_manager.append_comparison_fields(
-                _get_comparison_config(args, config_manager)
-            )
-
         # Append primary_keys
         primary_keys = cli_tools.get_arg_list(args.primary_keys)
+        if not primary_keys and config_manager.validation_type != consts.CUSTOM_QUERY:
+            primary_keys = config_manager.auto_list_primary_keys()
+        if not primary_keys:
+            raise ValueError(
+                "No primary keys were provided and neither the source or target tables have primary keys. Please include --primary-keys argument"
+            )
+        primary_keys = [_.casefold() for _ in primary_keys]
         config_manager.append_primary_keys(
             config_manager.build_column_configs(primary_keys)
         )
 
+        # Append Comparison fields
+        if args.comparison_fields:
+            config_manager.append_comparison_fields(
+                _get_comparison_config(args, config_manager, primary_keys)
+            )
+
     return config_manager
 
 
@@ -451,20 +458,7 @@ def build_config_managers_from_yaml(args, config_file_path):
     return config_managers
 
 
-def run_raw_query_against_connection(args):
-    """Return results of raw query for ad hoc usage."""
-    mgr = state_manager.StateManager()
-    client = clients.get_data_client(mgr.get_connection_config(args.conn))
-    cursor = client.raw_sql(args.query)
-    res = cursor.fetchall()
-    try:
-        cursor.close()
-    except Exception:
-        pass
-    return res
-
-
-def convert_config_to_yaml(args, config_managers):
+def convert_config_to_yaml(args, config_managers: list):
     """Return dict objects formatted for yaml validations.
 
     Args:
@@ -484,7 +478,7 @@ def convert_config_to_yaml(args, config_managers):
     return yaml_config
 
 
-def convert_config_to_json(config_managers) -> dict:
+def convert_config_to_json(config_managers: list) -> dict:
     """Return dict objects formatted for json validations.
     JSON configs correspond to ConfigManager objects and therefore can only correspond to
     one table validation.
@@ -504,7 +498,7 @@ def convert_config_to_json(config_managers) -> dict:
     return json_config
 
 
-def run_validation(config_manager, dry_run=False, verbose=False):
+def run_validation(config_manager: ConfigManager, dry_run=False, verbose=False):
     """Run a single validation.
 
     Args:
@@ -512,11 +506,24 @@ def run_validation(config_manager, dry_run=False, verbose=False):
         dry_run (bool): Print source and target SQL to stdout in lieu of validation.
         verbose (bool): Validation setting to log queries run.
     """
+    # Only use cached connection for SQLAlchemy backends that manage reconnects for us.
+    source_client = (
+        config_manager.source_client
+        if clients.is_sqlalchemy_backend(config_manager.source_client)
+        else None
+    )
+    target_client = (
+        config_manager.target_client
+        if clients.is_sqlalchemy_backend(config_manager.target_client)
+        else None
+    )
     with DataValidation(
         config_manager.config,
         validation_builder=None,
         result_handler=None,
         verbose=verbose,
+        source_client=source_client,
+        target_client=target_client,
     ) as validator:
 
         if dry_run:
@@ -636,8 +643,8 @@ def run_connections(args):
     elif args.connect_cmd == "add":
         conn = cli_tools.get_connection_config_from_args(args)
         # Test getting a client to validate connection details
-        _ = clients.get_data_client(conn)
-        cli_tools.store_connection(args.connection_name, conn)
+        with clients.get_data_client_ctx(conn) as _:
+            cli_tools.store_connection(args.connection_name, conn)
     else:
         raise ValueError(f"Connections Argument '{args.connect_cmd}' is not supported")
 
@@ -680,7 +687,9 @@ def main():
     elif args.command == "find-tables":
         print(find_tables_using_string_matching(args))
     elif args.command == "query":
-        print(run_raw_query_against_connection(args))
+        raw_query.print_raw_query_output(
+            raw_query.run_raw_query_against_connection(args)
+        )
     elif args.command == "validate":
         validate(args)
     elif args.command == "generate-table-partitions":

{google_pso_data_validator-6.4.0 → google_pso_data_validator-7.1.0}/data_validation/cli_tools.py

@@ -65,6 +65,10 @@ CONNECTION_SOURCE_FIELDS = {
     "BigQuery": [
         ["project_id", "GCP Project to use for BigQuery"],
         ["google_service_account_key_path", "(Optional) GCP SA Key Path"],
+        [
+            "api_endpoint",
+            '(Optional) GCP BigQuery API endpoint (e.g. "https://mybq.p.googleapis.com")',
+        ],
     ],
     "Teradata": [
         ["host", "Desired Teradata host"],
@@ -125,6 +129,10 @@ CONNECTION_SOURCE_FIELDS = {
         ["instance_id", "ID of Spanner instance to connect to"],
         ["database_id", "ID of Spanner database (schema) to connect to"],
         ["google_service_account_key_path", "(Optional) GCP SA Key Path"],
+        [
+            "api_endpoint",
+            '(Optional) GCP Spanner API endpoint (e.g. "https://mycs.p.googleapis.com")',
+        ],
     ],
     "FileSystem": [
         ["table_name", "Table name to use as reference for file data"],
@@ -170,6 +178,12 @@ CONNECTION_SOURCE_FIELDS = {
     ],
 }
 
+VALIDATE_HELP_TEXT = "Run a validation and optionally store to config"
+VALIDATE_COLUMN_HELP_TEXT = "Run a column validation"
+VALIDATE_ROW_HELP_TEXT = "Run a row validation"
+VALIDATE_SCHEMA_HELP_TEXT = "Run a schema validation"
+VALIDATE_CUSTOM_QUERY_HELP_TEXT = "Run a custom query validation"
+
 
 def _check_custom_query_args(parser: argparse.ArgumentParser, parsed_args: Namespace):
     # This is where we make additional checks if the arguments provided are what we expect
@@ -340,17 +354,24 @@ def _configure_deploy(subparsers):
 def _configure_find_tables(subparsers):
     """Configure arguments for text search table matching."""
     find_tables_parser = subparsers.add_parser(
-        "find-tables", help="Build tables list using approx string matching"
+        "find-tables", help="Build tables list using approx string matching."
     )
     find_tables_parser.add_argument(
-        "--source-conn", "-sc", help="Source connection name"
+        "--source-conn", "-sc", help="Source connection name."
     )
     find_tables_parser.add_argument(
-        "--target-conn", "-tc", help="Target connection name"
+        "--target-conn", "-tc", help="Target connection name."
     )
     find_tables_parser.add_argument(
         "--allowed-schemas", "-as", help="List of source schemas to match."
     )
+    find_tables_parser.add_argument(
+        "--include-views",
+        "-iv",
+        default=False,
+        action="store_true",
+        help="Include views in results.",
+    )
     find_tables_parser.add_argument(
         "--score-cutoff",
         "-score",
@@ -471,9 +492,7 @@ def _configure_database_specific_parsers(parser):
 
 def _configure_validate_parser(subparsers):
     """Configure arguments to run validations."""
-    validate_parser = subparsers.add_parser(
-        "validate", help="Run a validation and optionally store to config"
-    )
+    validate_parser = subparsers.add_parser("validate", help=VALIDATE_HELP_TEXT)
 
     validate_parser.add_argument(
         "--dry-run",
@@ -485,22 +504,22 @@ def _configure_validate_parser(subparsers):
     validate_subparsers = validate_parser.add_subparsers(dest="validate_cmd")
 
     column_parser = validate_subparsers.add_parser(
-        "column", help="Run a column validation"
+        "column", help=VALIDATE_COLUMN_HELP_TEXT
     )
     _configure_column_parser(column_parser)
 
-    row_parser = validate_subparsers.add_parser("row", help="Run a row validation")
+    row_parser = validate_subparsers.add_parser("row", help=VALIDATE_ROW_HELP_TEXT)
     optional_arguments = row_parser.add_argument_group("optional arguments")
     required_arguments = row_parser.add_argument_group("required arguments")
     _configure_row_parser(row_parser, optional_arguments, required_arguments)
 
     schema_parser = validate_subparsers.add_parser(
-        "schema", help="Run a schema validation"
+        "schema", help=VALIDATE_SCHEMA_HELP_TEXT
     )
     _configure_schema_parser(schema_parser)
 
     custom_query_parser = validate_subparsers.add_parser(
-        "custom-query", help="Run a custom query validation"
+        "custom-query", help=VALIDATE_CUSTOM_QUERY_HELP_TEXT
     )
     _configure_custom_query_parser(custom_query_parser)
 
@@ -514,6 +533,15 @@ def _configure_row_parser(
 ):
     """Configure arguments to run row level validations."""
     # Group optional arguments
+    optional_arguments.add_argument(
+        "--primary-keys",
+        "-pk",
+        help=(
+            "Comma separated list of primary key columns 'col_a,col_b', "
+            "when not specified the value will be inferred from the source or target table if available"
+        ),
+    )
+
     optional_arguments.add_argument(
         "--threshold",
         "-th",
@@ -586,14 +614,6 @@ def _configure_row_parser(
             help="Comma separated tables list in the form 'schema.table=target_schema.target_table'",
         )
 
-    # Group required arguments
-    required_arguments.add_argument(
-        "--primary-keys",
-        "-pk",
-        required=True,
-        help="Comma separated list of primary key columns 'col_a,col_b'",
-    )
-
     # Group for mutually exclusive required arguments. Either must be supplied
     mutually_exclusive_arguments = required_arguments.add_mutually_exclusive_group(
         required=True
@@ -1173,24 +1193,38 @@ def get_filters(filter_value: str) -> List[Dict]:
     return filter_config
 
 
-def get_result_handler(rc_value, sa_file=None):
+def get_result_handler(rc_value: str, sa_file=None) -> dict:
     """Returns dict of result handler config. Backwards compatible for JSON input.
 
     rc_value (str): Result config argument specified.
     sa_file (str): SA path argument specified.
     """
     config = rc_value.split(".", 1)
-    if len(config) == 2:
+    if len(config) != 2:
+        raise ValueError(f"Unable to parse result handler config: `{rc_value}`")
+
+    # Check if the first part of the BQRH is a connection name.
+    mgr = state_manager.StateManager()
+    connections = mgr.list_connections()
+    if config[0] in connections:
+        # We received connection_name.bq_results_table
+        conn_from_file = get_connection(config[0])
         result_handler = {
             "type": "BigQuery",
-            "project_id": config[0],
-            "table_id": config[1],
+            consts.PROJECT_ID: conn_from_file["project_id"],
+            consts.TABLE_ID: config[1],
+            consts.API_ENDPOINT: conn_from_file.get("api_endpoint", None),
         }
     else:
-        raise ValueError(f"Unable to parse result handler config: `{rc_value}`")
+        # We received project_name.bq_results_table
+        result_handler = {
+            "type": "BigQuery",
+            consts.PROJECT_ID: config[0],
+            consts.TABLE_ID: config[1],
+        }
 
     if sa_file:
-        result_handler["google_service_account_key_path"] = sa_file
+        result_handler[consts.GOOGLE_SERVICE_ACCOUNT_KEY_PATH] = sa_file
 
     return result_handler