Add DuckDB engine for parse and analyze via darkwing

CLAUDE.md

@@ -215,6 +215,9 @@ MYSQL_SERVER_URI="root:mysecretpassword@tcp(127.0.0.1:3306)/mysql?multiStatement
   - `/postgresql/` - PostgreSQL parser and converter
   - `/dolphin/` - MySQL parser (uses TiDB parser)
   - `/sqlite/` - SQLite parser
+  - `/duckdb/` - DuckDB 2.0 parser (uses darkwing, the pure Go port of
+    DuckDB's PEG parser); its dialect seeds are generated by
+    `/internal/tools/sqlc-duckdb-gen` from a live DuckDB CLI
   - `<engine>/dialect/` - The engine's type system and standard library, as
     JSONL read by `/internal/core/seed`
 - `/internal/core/` - The analysis core: catalog, analyzer and dialect seeds

docs/howto/analyze.md

@@ -26,7 +26,7 @@ provided. The schema is always read from the `--schema` file.
 ## Flags
 
 - `--dialect`, `-d` - The SQL dialect to use. One of `postgresql`, `mysql`,
-  `sqlite`, `clickhouse`, `googlesql`, or `mssql`. Required.
+  `sqlite`, `clickhouse`, `googlesql`, `mssql`, or `duckdb`. Required.
 - `--schema`, `-s` - Path to the schema (DDL) file. Required.
 - `--ast` - Include each statement's AST in the output. Defaults to `false`.
 

docs/howto/parse.md

@@ -20,7 +20,7 @@ provided.
 ## Flags
 
 - `--dialect`, `-d` - The SQL dialect to use. One of `postgresql`, `mysql`,
-  `sqlite`, `clickhouse`, `googlesql`, or `mssql`. Required.
+  `sqlite`, `clickhouse`, `googlesql`, `mssql`, or `duckdb`. Required.
 
 ## Examples
 

go.mod

@@ -18,6 +18,7 @@ require (
 	github.com/riza-io/grpc-go v0.2.0
 	github.com/spf13/cobra v1.10.2
 	github.com/spf13/pflag v1.0.10
+	github.com/sqlc-dev/darkwing v0.1.0
 	github.com/sqlc-dev/doubleclick v1.0.0
 	github.com/sqlc-dev/marino v0.3.0
 	github.com/sqlc-dev/meyer v0.1.1

go.sum

@@ -65,6 +65,8 @@ github.com/spf13/cobra v1.10.2/go.mod h1:7C1pvHqHw5A4vrJfjNwvOdzYu0Gml16OCs2GRiT
 github.com/spf13/pflag v1.0.9/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
 github.com/spf13/pflag v1.0.10 h1:4EBh2KAYBwaONj6b2Ye1GiHfwjqyROoF4RwYO+vPwFk=
 github.com/spf13/pflag v1.0.10/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
+github.com/sqlc-dev/darkwing v0.1.0 h1:P5dtJebmCiy10e6DcnBQ2d7Mwuz636obuSAzTlr/1Qo=
+github.com/sqlc-dev/darkwing v0.1.0/go.mod h1:kPb+99a6U+oVWtLhsuvkuDb/YRm8deK6x+W/9mX6uug=
 github.com/sqlc-dev/doubleclick v1.0.0 h1:2/OApfQ2eLgcfa/Fqs8WSMA6atH0G8j9hHbQIgMfAXI=
 github.com/sqlc-dev/doubleclick v1.0.0/go.mod h1:ODHRroSrk/rr5neRHlWMSRijqOak8YmNaO3VAZCNl5Y=
 github.com/sqlc-dev/marino v0.3.0 h1:e9cinBXJFFa3yRpokYNNinWvkewgd6XVDgnlG0bOmTw=

internal/cmd/analyze.go

@@ -46,6 +46,9 @@ Examples:
   # Analyze a SQL Server (T-SQL) query
   sqlc analyze --dialect mssql --schema schema.sql query.sql
 
+  # Analyze a DuckDB query
+  sqlc analyze --dialect duckdb --schema schema.sql query.sql
+
   # Analyze a query piped via stdin
   echo "-- name: GetAuthor :one
   SELECT * FROM authors WHERE id = $1;" | sqlc analyze --dialect postgresql --schema schema.sql
@@ -59,7 +62,7 @@ Examples:
 				return err
 			}
 			if dialect == "" {
-				return fmt.Errorf("--dialect flag is required (postgresql, mysql, sqlite, clickhouse, googlesql, or mssql)")
+				return fmt.Errorf("--dialect flag is required (postgresql, mysql, sqlite, clickhouse, googlesql, mssql, or duckdb)")
 			}
 
 			schemaPath, err := cmd.Flags().GetString("schema")
@@ -122,8 +125,10 @@ Examples:
 				engine = config.EngineGoogleSQL
 			case "mssql", "sqlserver":
 				engine = config.EngineMSSQL
+			case "duckdb":
+				engine = config.EngineDuckDB
 			default:
-				return fmt.Errorf("unsupported dialect: %s (use postgresql, mysql, sqlite, clickhouse, googlesql, or mssql)", dialect)
+				return fmt.Errorf("unsupported dialect: %s (use postgresql, mysql, sqlite, clickhouse, googlesql, mssql, or duckdb)", dialect)
 			}
 
 			sql := config.SQL{
@@ -165,7 +170,7 @@ Examples:
 			return nil
 		},
 	}
-	cmd.Flags().StringP("dialect", "d", "", "SQL dialect to use (postgresql, mysql, sqlite, clickhouse, googlesql, or mssql)")
+	cmd.Flags().StringP("dialect", "d", "", "SQL dialect to use (postgresql, mysql, sqlite, clickhouse, googlesql, mssql, or duckdb)")
 	cmd.Flags().StringP("schema", "s", "", "path to the schema file")
 	cmd.Flags().BoolP("ast", "", false, "include the statement AST in the output")
 	return cmd

internal/cmd/parse.go

@@ -11,6 +11,7 @@ import (
 
 	"github.com/sqlc-dev/sqlc/internal/engine/clickhouse"
 	"github.com/sqlc-dev/sqlc/internal/engine/dolphin"
+	"github.com/sqlc-dev/sqlc/internal/engine/duckdb"
 	"github.com/sqlc-dev/sqlc/internal/engine/googlesql"
 	"github.com/sqlc-dev/sqlc/internal/engine/mssql"
 	"github.com/sqlc-dev/sqlc/internal/engine/postgresql"
@@ -63,15 +64,18 @@ Examples:
   sqlc parse --dialect googlesql queries.sql
 
   # Parse SQL Server (T-SQL) SQL
-  sqlc parse --dialect mssql queries.sql`,
+  sqlc parse --dialect mssql queries.sql
+
+  # Parse DuckDB SQL
+  sqlc parse --dialect duckdb queries.sql`,
 		Args: cobra.MaximumNArgs(1),
 		RunE: func(cmd *cobra.Command, args []string) error {
 			dialect, err := cmd.Flags().GetString("dialect")
 			if err != nil {
 				return err
 			}
 			if dialect == "" {
-				return fmt.Errorf("--dialect flag is required (postgresql, mysql, sqlite, clickhouse, googlesql, or mssql)")
+				return fmt.Errorf("--dialect flag is required (postgresql, mysql, sqlite, clickhouse, googlesql, mssql, or duckdb)")
 			}
 
 			// Determine input source
@@ -110,8 +114,10 @@ Examples:
 				parser = googlesql.NewParser()
 			case "mssql", "sqlserver":
 				parser = mssql.NewParser()
+			case "duckdb":
+				parser = duckdb.NewParser()
 			default:
-				return fmt.Errorf("unsupported dialect: %s (use postgresql, mysql, sqlite, clickhouse, googlesql, or mssql)", dialect)
+				return fmt.Errorf("unsupported dialect: %s (use postgresql, mysql, sqlite, clickhouse, googlesql, mssql, or duckdb)", dialect)
 			}
 
 			// Read the full source so each statement's name and command can be
@@ -155,6 +161,6 @@ Examples:
 			return nil
 		},
 	}
-	cmd.Flags().StringP("dialect", "d", "", "SQL dialect to use (postgresql, mysql, sqlite, clickhouse, googlesql, or mssql)")
+	cmd.Flags().StringP("dialect", "d", "", "SQL dialect to use (postgresql, mysql, sqlite, clickhouse, googlesql, mssql, or duckdb)")
 	return cmd
 }

internal/compiler/engine.go

@@ -10,6 +10,7 @@ import (
 	"github.com/sqlc-dev/sqlc/internal/dbmanager"
 	"github.com/sqlc-dev/sqlc/internal/engine/clickhouse"
 	"github.com/sqlc-dev/sqlc/internal/engine/dolphin"
+	"github.com/sqlc-dev/sqlc/internal/engine/duckdb"
 	"github.com/sqlc-dev/sqlc/internal/engine/googlesql"
 	"github.com/sqlc-dev/sqlc/internal/engine/mssql"
 	"github.com/sqlc-dev/sqlc/internal/engine/postgresql"
@@ -58,10 +59,10 @@ func NewCompiler(conf config.SQL, combo config.CombinedSettings, parserOpts opts
 		o(c)
 	}
 
-	// ClickHouse, GoogleSQL and SQL Server have no legacy analysis path to
-	// fall back to.
+	// ClickHouse, GoogleSQL, SQL Server and DuckDB have no legacy analysis
+	// path to fall back to.
 	switch conf.Engine {
-	case config.EngineClickHouse, config.EngineGoogleSQL, config.EngineMSSQL:
+	case config.EngineClickHouse, config.EngineGoogleSQL, config.EngineMSSQL, config.EngineDuckDB:
 		c.coreAnalysis = true
 	}
 	if c.coreAnalysis {
@@ -144,6 +145,10 @@ func (c *Compiler) initCore() error {
 		c.parser = mssql.NewParser()
 		c.selector = newDefaultSelector()
 		dialect = mssql.Dialect()
+	case config.EngineDuckDB:
+		c.parser = duckdb.NewParser()
+		c.selector = newDefaultSelector()
+		dialect = duckdb.Dialect()
 	default:
 		return fmt.Errorf("unknown engine: %s", c.conf.Engine)
 	}

internal/config/config.go

@@ -57,6 +57,7 @@ const (
 	EngineClickHouse Engine = "clickhouse"
 	EngineGoogleSQL  Engine = "googlesql"
 	EngineMSSQL      Engine = "mssql"
+	EngineDuckDB     Engine = "duckdb"
 )
 
 type Config struct {

internal/endtoend/testdata/analyze_basic/duckdb/exec.json

@@ -0,0 +1,5 @@
+{
+  "command": "analyze",
+  "args": ["--dialect", "duckdb", "--schema", "schema.sql", "query.sql"],
+  "contexts": ["base"]
+}

internal/endtoend/testdata/analyze_basic/duckdb/query.sql

@@ -0,0 +1,2 @@
+-- name: ListAuthors :many
+SELECT id, name, bio, royalties, created FROM authors;

internal/endtoend/testdata/analyze_basic/duckdb/schema.sql

@@ -0,0 +1,7 @@
+CREATE TABLE authors (
+    id BIGINT PRIMARY KEY,
+    name TEXT NOT NULL,
+    bio TEXT,
+    royalties DECIMAL(10,2) NOT NULL,
+    created TIMESTAMP NOT NULL
+);

internal/endtoend/testdata/analyze_basic/duckdb/stdout.txt

@@ -0,0 +1,44 @@
+[
+  {
+    "name": "ListAuthors",
+    "cmd": ":many",
+    "columns": [
+      {
+        "name": "id",
+        "data_type": "bigint",
+        "not_null": true,
+        "is_array": false,
+        "table": "authors"
+      },
+      {
+        "name": "name",
+        "data_type": "text",
+        "not_null": true,
+        "is_array": false,
+        "table": "authors"
+      },
+      {
+        "name": "bio",
+        "data_type": "text",
+        "not_null": false,
+        "is_array": false,
+        "table": "authors"
+      },
+      {
+        "name": "royalties",
+        "data_type": "decimal",
+        "not_null": true,
+        "is_array": false,
+        "table": "authors"
+      },
+      {
+        "name": "created",
+        "data_type": "timestamp",
+        "not_null": true,
+        "is_array": false,
+        "table": "authors"
+      }
+    ],
+    "params": []
+  }
+]

internal/endtoend/testdata/analyze_dml/duckdb/exec.json

@@ -0,0 +1,5 @@
+{
+  "command": "analyze",
+  "args": ["--dialect", "duckdb", "--schema", "schema.sql", "query.sql"],
+  "contexts": ["base"]
+}

internal/endtoend/testdata/analyze_dml/duckdb/query.sql

@@ -0,0 +1,13 @@
+-- name: CreateAuthor :one
+INSERT INTO authors (id, name, bio) VALUES ($1, $2, $3) RETURNING id;
+
+-- name: UpdateAuthor :exec
+UPDATE authors SET name = $name, bio = $bio WHERE id = $id;
+
+-- name: DeleteBooksByAuthor :exec
+DELETE FROM books USING authors a WHERE books.author_id = a.id AND a.name = $1;
+
+-- name: TitlesFromBooks :many
+INSERT INTO books (id, author_id, title)
+SELECT id + 1000, author_id, upper(title) FROM books WHERE price > $min_price
+RETURNING id, title;

internal/endtoend/testdata/analyze_dml/duckdb/schema.sql

@@ -0,0 +1,12 @@
+CREATE TABLE authors (
+    id BIGINT PRIMARY KEY,
+    name TEXT NOT NULL,
+    bio TEXT
+);
+
+CREATE TABLE books (
+    id BIGINT PRIMARY KEY,
+    author_id BIGINT NOT NULL,
+    title TEXT NOT NULL,
+    price DECIMAL(10,2)
+);