jischeng
c3893bf314
* feat(spark): add Apache Spark database driver Spark Thrift Server speaks the HiveServer2 protocol, so the Spark driver reuses the hive-jdbc agent runtime. Registers spark (agentKey=spark, defaultPort=10015) across the manifest, DatabaseType enum, agent catalog, SQL dialects, connection dialog, and a SparkAgent built on AbstractJdbcAgent. * feat(spark): add catalog support and official logo SparkAgent now supports Spark 3.4+ multi-catalog (Paimon, Lance, Iceberg) via catalog=<name> in url_params, mirroring the StarRocks catalog flow: - afterConnect switches to the configured catalog via USE <catalog> - listDatabases returns the catalog name when SHOW DATABASES is empty (catalogs like Lance expose tables at the catalog root with no databases) - listTables uses SHOW TABLES IN <catalog>[.<schema>] uniformly, working for both catalog-root tables (Lance) and catalog.schema tables (Paimon) - setSchemaSQL qualifies USE with the catalog to prevent resetting to spark_catalog on schema switches - buildJdbcUrl omits database from the URL path Also replaces the placeholder lightning icon with the official Apache Spark logo (spark-logo.png from spark.apache.org). * fix(spark): use catalog-qualified DESCRIBE for column retrieval getColumnsFromDescribe used USE <schema> + DESCRIBE <table>, which generated USE `catalog`.`catalog` when the sidebar passed the catalog name as the schema (Lance case where the catalog is the only node). This failed and fell back to JDBC metadata which also returned nothing, resulting in an empty DDL (CREATE TABLE ... ()). Now uses DESCRIBE `catalog`.`table` directly when a catalog is configured, bypassing USE entirely. Also fixes setSchemaSQL to treat schema == catalog as catalog-only (no .schema suffix). * fix(ci): add spark to metadata coverage matrix and BRIDGE_REQUIRED_TYPES - agents/metadata-constraint-coverage.tsv: register spark as intentional-fallback (SHOW TABLES/SHOW DATABASES, like Hive/TDengine) - packages/node-core/src/diagnostics.ts: add spark to BRIDGE_REQUIRED_TYPES (mcpMode=bridge, matches manifest) * fix(ci): add spark to DBX_CONNECTION_TYPE_DESCRIPTION in mcp-server The driver-manifest test asserts every manifest dbType appears in the MCP server's connection type description string.
104 lines
5.9 KiB
TypeScript
104 lines
5.9 KiB
TypeScript
import type { ConnectionConfig, DatabaseType, TreeNodeType } from "@/types/database";
|
|
|
|
export type DatabaseNamespaceCreationTarget = "database" | "schema" | "attach" | "special";
|
|
|
|
type ConnectionCreationTarget = Extract<DatabaseNamespaceCreationTarget, "database" | "attach" | "special">;
|
|
type DatabaseNodeCreationTarget = Extract<DatabaseNamespaceCreationTarget, "schema">;
|
|
|
|
export interface DatabaseNamespaceCreationMatrixEntry {
|
|
connection?: ConnectionCreationTarget;
|
|
database?: DatabaseNodeCreationTarget;
|
|
deferred?: string;
|
|
}
|
|
|
|
type CreationConnection = Pick<ConnectionConfig, "db_type" | "driver_profile" | "read_only"> | undefined;
|
|
|
|
// Keep creation target-specific: many products expose schemas, files, or provider-managed namespaces instead of a top-level database.
|
|
export const DATABASE_NAMESPACE_CREATION_MATRIX = {
|
|
mysql: { connection: "database" },
|
|
postgres: { connection: "database", database: "schema" },
|
|
sqlite: { deferred: "file-backed; create a new connection/file instead" },
|
|
rqlite: { deferred: "single SQLite-compatible database per node" },
|
|
turso: { deferred: "remote libSQL database lifecycle is provider-managed" },
|
|
redis: { deferred: "numbered logical databases are server-configured" },
|
|
duckdb: { connection: "attach" },
|
|
clickhouse: { connection: "database" },
|
|
sqlserver: { connection: "database", database: "schema" },
|
|
mongodb: { connection: "special" },
|
|
oracle: { deferred: "Oracle schemas are users; database creation is not a normal connected DDL action" },
|
|
elasticsearch: { deferred: "index creation is not modeled as database creation" },
|
|
qdrant: { deferred: "collection creation is separate from database creation" },
|
|
milvus: { deferred: "collection/database lifecycle needs a dedicated vector workflow" },
|
|
weaviate: { deferred: "collection creation is separate from database creation" },
|
|
chromadb: { deferred: "collection creation is separate from database creation" },
|
|
doris: { connection: "database" },
|
|
starrocks: { connection: "database" },
|
|
manticoresearch: { deferred: "index/table creation is not database creation" },
|
|
databend: { connection: "database" },
|
|
redshift: { connection: "database", database: "schema" },
|
|
dameng: { deferred: "schema/user creation requires a dedicated user workflow" },
|
|
gaussdb: { connection: "database", database: "schema" },
|
|
kingbase: { connection: "database", database: "schema" },
|
|
highgo: { connection: "database", database: "schema" },
|
|
vastbase: { connection: "database", database: "schema" },
|
|
goldendb: { connection: "database" },
|
|
kwdb: { connection: "database", database: "schema" },
|
|
yashandb: { connection: "database", database: "schema" },
|
|
databricks: { database: "schema" },
|
|
saphana: { database: "schema" },
|
|
teradata: { database: "schema" },
|
|
vertica: { database: "schema" },
|
|
firebird: { deferred: "database files are created through connection provisioning" },
|
|
exasol: { database: "schema" },
|
|
opengauss: { connection: "database", database: "schema" },
|
|
"oceanbase-oracle": { deferred: "Oracle-mode schemas are users; use a dedicated user workflow" },
|
|
questdb: { deferred: "single database model in DBX" },
|
|
gbase: { database: "schema" },
|
|
access: { deferred: "file-backed; create a new connection/file instead" },
|
|
h2: { database: "schema" },
|
|
snowflake: { connection: "database", database: "schema" },
|
|
trino: { database: "schema" },
|
|
prestosql: { database: "schema" },
|
|
hive: { deferred: "Hive database creation needs agent metadata validation first" },
|
|
spark: { deferred: "Spark database creation needs agent metadata validation first" },
|
|
db2: { database: "schema" },
|
|
informix: { database: "schema" },
|
|
neo4j: { deferred: "database creation depends on edition/admin privileges" },
|
|
cassandra: { deferred: "keyspace creation requires replication options" },
|
|
bigquery: { deferred: "dataset creation needs project/location options" },
|
|
kylin: { deferred: "project/model lifecycle is not SQL database creation" },
|
|
sundb: { deferred: "creation semantics not verified for first pass" },
|
|
oscar: { database: "schema" },
|
|
tdengine: { connection: "database" },
|
|
xugu: { database: "schema" },
|
|
iotdb: { deferred: "storage group/database semantics need dedicated IoTDB handling" },
|
|
etcd: { deferred: "key-value namespaces are not databases" },
|
|
zookeeper: { deferred: "key-value namespaces are not databases" },
|
|
iris: { database: "schema" },
|
|
influxdb: { connection: "database" },
|
|
jdbc: { deferred: "generic JDBC does not expose a reliable dialect-specific create target" },
|
|
mq: { deferred: "message queue namespaces are handled by MQ admin panels" },
|
|
nacos: { deferred: "Nacos namespace creation already uses the Nacos admin flow" },
|
|
} satisfies Record<DatabaseType, DatabaseNamespaceCreationMatrixEntry>;
|
|
|
|
export function connectionNamespaceCreationTarget(connection: CreationConnection): ConnectionCreationTarget | null {
|
|
if (!connection || connection.read_only) return null;
|
|
if (connection.db_type === "mongodb" && connection.driver_profile === "mongodb-legacy") return null;
|
|
const entry: DatabaseNamespaceCreationMatrixEntry = DATABASE_NAMESPACE_CREATION_MATRIX[connection.db_type];
|
|
return entry.connection ?? null;
|
|
}
|
|
|
|
export function databaseNodeNamespaceCreationTarget(connection: CreationConnection, node: Pick<{ type: TreeNodeType; database?: string | null }, "type" | "database">): DatabaseNodeCreationTarget | null {
|
|
if (!connection || connection.read_only || node.type !== "database" || !node.database) return null;
|
|
const entry: DatabaseNamespaceCreationMatrixEntry = DATABASE_NAMESPACE_CREATION_MATRIX[connection.db_type];
|
|
return entry.database ?? null;
|
|
}
|
|
|
|
export function canCreateConnectionNamespace(connection: CreationConnection): boolean {
|
|
return connectionNamespaceCreationTarget(connection) !== null;
|
|
}
|
|
|
|
export function canCreateDatabaseNodeNamespace(connection: CreationConnection, node: Pick<{ type: TreeNodeType; database?: string | null }, "type" | "database">): boolean {
|
|
return databaseNodeNamespaceCreationTarget(connection, node) !== null;
|
|
}
|