Feat: Add Apache Doris engine adapter with OLAP and multi-catalog lakehouse support

.github/scripts/install-prerequisites.sh

@@ -28,6 +28,8 @@ elif [ "$ENGINE" == "fabric" ]; then
     rm packages-microsoft-prod.deb
 
     ENGINE_DEPENDENCIES="msodbcsql18"
+elif [ "$ENGINE" == "doris" ]; then
+    sudo sysctl -w vm.max_map_count=2000000
 fi
 
 ALL_DEPENDENCIES="$COMMON_DEPENDENCIES $ENGINE_DEPENDENCIES"

.github/scripts/wait-for-db.sh

@@ -104,6 +104,46 @@ db2_ready() {
     done
 }
 
+doris_ready() {
+    probe_port 9030
+
+    echo "Waiting for Doris FE to accept SQL connections..."
+    while true; do
+        if docker exec -i doris-fe mysql -h127.0.0.1 -P9030 -uroot -e "SHOW FRONTENDS\G" 2>/dev/null | grep -q "Alive: true"; then
+            echo "Doris FE is alive"
+            break
+        fi
+        sleep 2
+    done
+
+    docker exec -i doris-fe mysql -h127.0.0.1 -P9030 -uroot -e "ALTER SYSTEM ADD BACKEND '172.30.80.3:9050';" 2>/dev/null || true
+
+    echo "Checking for 1 alive Doris backends..."
+    while true; do
+        echo "Checking Doris backends..."
+        ALIVE_BACKENDS=$(docker exec -i doris-fe mysql -h127.0.0.1 -P9030 -uroot -e "show backends \G" 2>/dev/null | grep -c "^ *Alive: true *$" || true)
+
+        # fallback value if failed to get number
+        if ! [[ "$ALIVE_BACKENDS" =~ ^[0-9]+$ ]]; then
+            echo "WARN: Unable to parse number of alive backends, got: '$ALIVE_BACKENDS'"
+            ALIVE_BACKENDS=0
+        fi
+
+        echo "Found $ALIVE_BACKENDS alive backends"
+
+        if [ "$ALIVE_BACKENDS" -ge 1 ]; then
+            echo "Doris has 1 or more alive backends"
+            break
+        fi
+
+        echo "Waiting for more backends to become alive..."
+        sleep 3
+    done
+
+    # set default replication num to 1 (there is only one be in the docker compose file)
+    docker exec -i doris-fe mysql -h127.0.0.1 -P9030 -uroot -e "ADMIN SET FRONTEND CONFIG ('force_olap_table_replication_num' = '1');"
+}
+
 echo "Waiting for $ENGINE to be ready..."
 
 READINESS_FUNC="${ENGINE}_ready"

.github/workflows/pr.yaml

@@ -269,6 +269,7 @@ jobs:
             clickhouse,
             risingwave,
             starrocks,
+            doris,
           ]
     env:
       PYTEST_XDIST_AUTO_NUM_WORKERS: 2

.readthedocs.yaml

@@ -6,7 +6,7 @@ build:
     python: "3.10"
   jobs:
     pre_build:
-      - pip install -e ".[athena,azuresql,bigframes,bigquery,clickhouse,databricks,dbt,dlt,gcppostgres,github,llm,mssql,mysql,mwaa,postgres,redshift,slack,snowflake,starrocks,trino,web,risingwave]"
+      - pip install -e ".[athena,azuresql,bigframes,bigquery,clickhouse,databricks,dbt,dlt,doris,gcppostgres,github,llm,mssql,mysql,mwaa,postgres,redshift,slack,snowflake,starrocks,trino,web,risingwave]"
       - make api-docs
 
 mkdocs:

Makefile

@@ -226,6 +226,9 @@ starrocks-test: engine-starrocks-up
 db2-test: engine-db2-up
 	pytest -n auto -m "db2" --reruns 3 --junitxml=test-results/junit-db2.xml
 
+doris-test: engine-doris-up
+	pytest -n auto -m "doris" --reruns 3 --junitxml=test-results/junit-doris.xml
+
 #################
 # Cloud Engines #
 #################

docs/concepts/models/model_kinds.md

@@ -444,6 +444,7 @@ Depending on the target engine, models of the `INCREMENTAL_BY_TIME_RANGE` kind a
 | Redshift   | DELETE by time range, then INSERT         |
 | Postgres   | DELETE by time range, then INSERT         |
 | DuckDB     | DELETE by time range, then INSERT         |
+| Doris      | DELETE by time range, then INSERT         |
 
 ## INCREMENTAL_BY_UNIQUE_KEY
 
@@ -669,6 +670,7 @@ Depending on the target engine, models of the `INCREMENTAL_BY_UNIQUE_KEY` kind a
 | Redshift   | MERGE ON unique key                 |
 | Postgres   | MERGE ON unique key                 |
 | DuckDB     | DELETE ON matched + INSERT new rows |
+| Doris      | DELETE ON matched + INSERT new rows |
 
 ## FULL
 Models of the `FULL` kind cause the dataset associated with a model to be fully refreshed (rewritten) upon each model evaluation.
@@ -761,6 +763,7 @@ Depending on the target engine, models of the `FULL` kind are materialized using
 | Redshift   | DROP TABLE, CREATE TABLE, INSERT |
 | Postgres   | DROP TABLE, CREATE TABLE, INSERT |
 | DuckDB     | CREATE OR REPLACE TABLE          |
+| Doris      | CREATE TABLE ... AS SELECT (new OLAP), DELETE + INSERT (existing OLAP & Iceberg), INSERT OVERWRITE (unpartitioned Hive) |
 
 ## VIEW
 The model kinds described so far cause the output of a model query to be materialized and stored in a physical table.
@@ -837,6 +840,7 @@ MODEL (
 
 * BigQuery
 * Databricks
+* Doris
 * Snowflake
 
 During the evaluation of a model of this kind, the view will be replaced or recreated only if the model's query rendered during evaluation does not match the query used during the previous view creation for this model, or if the target view does not exist. Thus, views are recreated only when necessary in order to realize all the benefits provided by materialized views.
@@ -1629,6 +1633,7 @@ Depending on the target engine, models of the `INCREMENTAL_BY_PARTITION` kind ar
 | Redshift   | DELETE by partitioning key, then INSERT |
 | Postgres   | DELETE by partitioning key, then INSERT |
 | DuckDB     | DELETE by partitioning key, then INSERT |
+| Doris      | DELETE by partitioning key, then INSERT |
 
 ## INCREMENTAL_UNMANAGED
 

docs/concepts/models/overview.md

@@ -181,6 +181,7 @@ This table lists each engine's support for `TABLE` and `VIEW` object comments:
 | BigQuery      | Y                | Y               |
 | ClickHouse    | Y                | Y               |
 | Databricks    | Y                | Y               |
+| Doris         | Y                | Y               |
 | DuckDB <=0.9  | N                | N               |
 | DuckDB >=0.10 | Y                | Y               |
 | MySQL         | Y                | Y               |

docs/guides/configuration.md

@@ -933,6 +933,7 @@ These pages describe the connection configuration options for each execution eng
 * [BigQuery](../integrations/engines/bigquery.md)
 * [ClickHouse](../integrations/engines/clickhouse.md)
 * [Databricks](../integrations/engines/databricks.md)
+* [Doris](../integrations/engines/doris.md)
 * [DuckDB](../integrations/engines/duckdb.md)
 * [Fabric](../integrations/engines/fabric.md)
 * [MotherDuck](../integrations/engines/motherduck.md)
@@ -975,6 +976,7 @@ Other state engines with fast and reliable database transactions (less tested th
 Unsupported state engines, even for development:
 
 * [ClickHouse](../integrations/engines/clickhouse.md)
+* [Doris](../integrations/engines/doris.md)
 * [Spark](../integrations/engines/spark.md)
 * [StarRocks](../integrations/engines/starrocks.md)
 * [Trino](../integrations/engines/trino.md)

docs/guides/connections.md

@@ -85,6 +85,7 @@ default_gateway: local_db
 * [ClickHouse](../integrations/engines/clickhouse.md)
 * [Databricks](../integrations/engines/databricks.md)
 * [Db2](../integrations/engines/db2.md)
+* [Doris](../integrations/engines/doris.md)
 * [DuckDB](../integrations/engines/duckdb.md)
 * [Fabric](../integrations/engines/fabric.md)
 * [MotherDuck](../integrations/engines/motherduck.md)

docs/installation.md

@@ -54,6 +54,7 @@ Other extras are required to use specific SQL engines, like Bigquery or Postgres
     | Bigquery      | `pip install "sqlmesh[bigquery]"`    |
     | ClickHouse    | `pip install "sqlmesh[clickhouse]"`  |
     | Databricks    | `pip install "sqlmesh[databricks]"`  |
+    | Doris         | `pip install "sqlmesh[doris]"`       |
     | Fabric        | `pip install "sqlmesh[fabric]"`      |
     | GCP Postgres  | `pip install "sqlmesh[gcppostgres]"` |
     | MS SQL Server | `pip install "sqlmesh[mssql]"`       |