[DH-5723] Add redshift support

Author: jcjc712

Diff for: README.md

@@ -160,7 +160,7 @@ Once the engine is running, you will want to use it by:
 3. Querying the data in natural language
 
 ### Connecting to your data warehouses
-We currently support connections to Postgres, DuckDB, BigQuery, ClickHouse, Databricks, Snowflake and AWS Athena. You can create connections to these warehouses through the API or at application start-up using the envars.
+We currently support connections to Postgres, DuckDB, BigQuery, ClickHouse, Databricks, Snowflake, MySQL/MariaDB, MS SQL Server, Redshift and AWS Athena. You can create connections to these warehouses through the API or at application start-up using the envars.
 
 #### Connecting through the API
 

Diff for: dataherald/db_scanner/services/redshift_scanner.py

@@ -0,0 +1,36 @@
+import sqlalchemy
+from overrides import override
+from sqlalchemy.sql import func
+from sqlalchemy.sql.schema import Column
+
+from dataherald.db_scanner.models.types import QueryHistory
+from dataherald.db_scanner.services.abstract_scanner import AbstractScanner
+from dataherald.sql_database.base import SQLDatabase
+
+MIN_CATEGORY_VALUE = 1
+MAX_CATEGORY_VALUE = 100
+MAX_LOGS = 5_000
+
+
+class RedshiftScanner(AbstractScanner):
+    @override
+    def cardinality_values(self, column: Column, db_engine: SQLDatabase) -> list | None:
+        query = sqlalchemy.select([func.HLL(column)])
+        rs = db_engine.engine.execute(query).fetchall()
+
+        if (
+            len(rs) > 0
+            and len(rs[0]) > 0
+            and MIN_CATEGORY_VALUE < rs[0][0] <= MAX_CATEGORY_VALUE
+        ):
+            cardinality_query = sqlalchemy.select([func.distinct(column)]).limit(101)
+            cardinality = db_engine.engine.execute(cardinality_query).fetchall()
+            return [str(category[0]) for category in cardinality]
+
+        return None
+
+    @override
+    def get_logs(
+        self, table: str, db_engine: SQLDatabase, db_connection_id: str  # noqa: ARG002
+    ) -> list[QueryHistory]:
+        return []

Diff for: dataherald/db_scanner/sqlalchemy.py

@@ -22,6 +22,7 @@
 from dataherald.db_scanner.services.big_query_scanner import BigQueryScanner
 from dataherald.db_scanner.services.click_house_scanner import ClickHouseScanner
 from dataherald.db_scanner.services.postgre_sql_scanner import PostgreSqlScanner
+from dataherald.db_scanner.services.redshift_scanner import RedshiftScanner
 from dataherald.db_scanner.services.snowflake_scanner import SnowflakeScanner
 from dataherald.db_scanner.services.sql_server_scanner import SqlServerScanner
 from dataherald.sql_database.base import SQLDatabase
@@ -283,13 +284,14 @@ def scan(
         services = {
             "snowflake": SnowflakeScanner,
             "bigquery": BigQueryScanner,
-            "psycopg2": PostgreSqlScanner,
-            "pymssql": SqlServerScanner,
-            "http": ClickHouseScanner,
+            "postgresql": PostgreSqlScanner,
+            "mssql": SqlServerScanner,
+            "clickhouse": ClickHouseScanner,
+            "redshift": RedshiftScanner,
         }
         scanner_service = BaseScanner()
-        if db_engine.engine.driver in services.keys():
-            scanner_service = services[db_engine.engine.driver]()
+        if db_engine.engine.dialect.name in services.keys():
+            scanner_service = services[db_engine.engine.dialect.name]()
 
         inspector = inspect(db_engine.engine)
         meta = MetaData(bind=db_engine.engine)

Diff for: docs/api.create_database_connection.rst

@@ -254,6 +254,17 @@ Example::
 
 "connection_uri": snowflake://jon:123456@foo-bar/my-database/public
 
+Redshift
+^^^^^^^^^^^^
+
+Uri structure::
+
+"connection_uri": redshift+psycopg2://<user>:<password>@<host>:<port>/<database>
+
+Example::
+
+"connection_uri": redshift+psycopg2://jon:123456@host.amazonaws.com:5439/my-database
+
 ClickHouse
 ^^^^^^^^^^^^
 

Diff for: requirements.txt

@@ -43,3 +43,4 @@ PyMySQL==1.1.0
 clickhouse-sqlalchemy==0.2.5
 astrapy==0.7.6
 pymssql==2.2.11
+sqlalchemy-redshift==0.8.14