ob-databricks 0.1.0__tar.gz

ob_databricks-0.1.0/.gitignore

@@ -0,0 +1,35 @@
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+dist/
+build/
+*.egg-info/
+*.egg
+.eggs/
+.venv/
+venv/
+.env
+*.db
+*.duckdb
+*.sqlite3
+.mypy_cache/
+.ruff_cache/
+.pytest_cache/
+htmlcov/
+.coverage
+.coverage.*
+*.log
+.DS_Store
+.claude/
+security/
+infra/
+site/
+scripts/
+.mcpregistry_github_token
+.mcpregistry_registry_token
+_*/
+blog/
+review*
+design/
+examples/test*

ob_databricks-0.1.0/CLAUDE.md

@@ -0,0 +1,104 @@
+# ob-databricks — OrionBelt Semantic Layer Driver for Databricks
+
+## Purpose
+
+PEP 249 DB-API 2.0 driver wrapping `databricks-sql-connector = ">=3.0"` that intercepts OBML YAML
+queries, compiles them to databricks SQL via the OrionBelt CompilationPipeline
+(direct import) or OB REST API (standalone), and executes them natively.
+
+**OB dialect string:** `"databricks"`
+**Author:** Ralf Becher / RALFORION d.o.o. (info@orionbelt.ai)
+**License:** Apache 2.0
+
+---
+
+## Module Map
+
+| File | Responsibility |
+|---|---|
+| `__init__.py` | PEP 249 connect() + module constants |
+| `connection.py` | Connection class |
+| `cursor.py` | Cursor class — OBML detection + execution |
+| `compiler.py` | Direct OB import or REST fallback |
+| `exceptions.py` | PEP 249 exception hierarchy |
+| `type_codes.py` | PEP 249 type objects |
+
+---
+
+## connect() Parameters
+
+### databricks-specific
+| server_hostname | str | Databricks workspace hostname |
+| http_path | str | SQL warehouse HTTP path |
+| access_token | str | Personal access token or M2M OAuth token |
+| catalog | str | Unity Catalog name (default: hive_metastore) |
+| schema | str | Schema name |
+
+### OrionBelt parameters (same across all vendors)
+| Parameter | Default | Description |
+|---|---|---|
+| ob_model_id | None | Pre-loaded OB model ID |
+| ob_model_yaml | None | OBML YAML string to load |
+| ob_model_file | None | Path to .obml.yaml file |
+| ob_api_url | http://localhost:8000 | OB REST API URL (standalone mode only) |
+| ob_timeout | 30 | HTTP timeout in seconds |
+
+---
+
+## Compiler Bridge (compiler.py)
+
+Auto-detects whether OB core is importable (same process as orionbelt-api)
+or whether to fall back to REST:
+
+```python
+def compile_obml(obml: dict, model, dialect: str) -> str:
+    try:
+        # Direct call — zero overhead, used when embedded in orionbelt-api
+        from orionbelt.compiler.pipeline import CompilationPipeline
+        result = CompilationPipeline().compile(obml, model, dialect)
+        return result.sql
+    except ImportError:
+        # Standalone mode — call REST API
+        return _compile_via_rest(obml, dialect)
+```
+
+---
+
+## Vendor-Specific Notes
+
+- databricks-sql-connector uses %s paramstyle
+- Unity Catalog three-part names: catalog.schema.table
+- OB dialect "databricks" generates Databricks SQL syntax (DATEADD, DATEDIFF etc.)
+- Access token auth preferred over OAuth for server-side enterprise installs
+- HTTP path format: /sql/1.0/warehouses/<warehouse-id>
+- commit() is a no-op; Databricks SQL warehouses are stateless
+
+---
+
+## Type System
+
+Use databricks.sql.client cursor description for metadata.
+Types: STRING→str, INT/BIGINT→int, DOUBLE/FLOAT→float, TIMESTAMP→datetime, BOOLEAN→bool.
+
+---
+
+## Build Order
+
+Session 1: exceptions.py + type_codes.py + compiler.py + unit tests
+Session 2: connection.py + cursor.py (OBML detection, core execute)
+Session 3: __init__.py + connect() + integration tests
+Session 4: SQLAlchemy dialect (ob+databricks:// URL scheme)
+
+---
+
+## Dependencies
+
+```toml
+[project.dependencies]
+databricks-sql-connector = ">=3.0"
+pyyaml = ">=6.0"
+
+[project.optional-dependencies]
+sqlalchemy = ["sqlalchemy>=2.0"]
+dev = ["pytest>=8.0", "pytest-asyncio>=0.23", "mypy>=1.10", "ruff>=0.4", "respx>=0.21"]
+```

ob_databricks-0.1.0/LICENSE

@@ -0,0 +1,70 @@
+Business Source License 1.1
+
+Parameters
+
+Licensor:             RALFORION d.o.o.
+Licensed Work:        OrionBelt Semantic Layer 1.0
+                      The Licensed Work is (c) 2025 RALFORION d.o.o.
+Additional Use Grant: You may use the Licensed Work for any purpose,
+                      including production use, PROVIDED THAT you may
+                      not embed OrionBelt in a commercial product or
+                      provide it as part of a commercial service
+                      without purchasing a commercial license from
+                      the Licensor. Contact licensing@ralforion.com
+                      for commercial licensing inquiries.
+Change Date:          2030-03-16
+Change License:       Apache License, Version 2.0
+
+-----------------------------------------------------------------------------
+
+Business Source License 1.1
+
+License text copyright (c) 2017 MariaDB Corporation Ab, All Rights Reserved.
+"Business Source License" is a trademark of MariaDB Corporation Ab.
+
+Terms
+
+The Licensor hereby grants you the right to copy, modify, create derivative
+works, redistribute, and make non-production use of the Licensed Work. The
+Licensor may make an Additional Use Grant, above, permitting limited
+production use.
+
+Effective on the Change Date, or the fourth anniversary of the first publicly
+available distribution of a specific version of the Licensed Work under this
+License, whichever comes first, the Licensor hereby grants you rights under
+the terms of the Change License, and the rights granted in the paragraph
+above terminate.
+
+If your use of the Licensed Work does not comply with the requirements
+currently in effect as described in this License, you must purchase a
+commercial license from the Licensor, its affiliated entities, or authorized
+resellers, or you must refrain from using the Licensed Work.
+
+All copies of the original and modified Licensed Work, and derivative works
+of the Licensed Work, are subject to this License. This License applies
+separately for each version of the Licensed Work and the Change Date may vary
+for each version of the Licensed Work released by Licensor.
+
+You must conspicuously display this License on each original or modified copy
+of the Licensed Work. If you receive the Licensed Work in original or
+modified form from a third party, the terms and conditions set forth in this
+License apply to your use of that work.
+
+Any use of the Licensed Work in violation of this License will automatically
+terminate your rights under this License for the current and all other
+versions of the Licensed Work.
+
+This License does not grant you any right in any trademark or logo of
+Licensor or its affiliates (provided that you may use a trademark or logo of
+Licensor as expressly required by this License).
+
+TO THE EXTENT PERMITTED BY APPLICABLE LAW, THE LICENSED WORK IS PROVIDED ON
+AN "AS IS" BASIS. LICENSOR HEREBY DISCLAIMS ALL WARRANTIES AND CONDITIONS,
+EXPRESS OR IMPLIED, INCLUDING (WITHOUT LIMITATION) WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, NON-INFRINGEMENT, AND
+TITLE.
+
+MariaDB hereby grants you permission to use this License's text to license
+your works, and to refer to it using the trademark "Business Source License",
+as long as you comply with the Covenants of Licensor of MariaDB's Business Source
+License Trademark Policy available at https://mariadb.com/bsl11/.

ob_databricks-0.1.0/PKG-INFO

@@ -0,0 +1,36 @@
+Metadata-Version: 2.4
+Name: ob-databricks
+Version: 0.1.0
+Summary: OrionBelt Semantic Layer driver for Databricks (DB-API 2.0)
+Author-email: Ralf Becher <info@orionbelt.ai>
+License: BSL-1.1
+License-File: LICENSE
+Keywords: databricks,db-api,obml,orionbelt,semantic-layer
+Requires-Python: >=3.12
+Requires-Dist: databricks-sql-connector>=3.0
+Requires-Dist: ob-driver-core>=0.1
+Provides-Extra: dev
+Requires-Dist: mypy>=1.10; extra == 'dev'
+Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Requires-Dist: respx>=0.21; extra == 'dev'
+Requires-Dist: ruff>=0.4; extra == 'dev'
+Provides-Extra: sqlalchemy
+Requires-Dist: sqlalchemy>=2.0; extra == 'sqlalchemy'
+Description-Content-Type: text/markdown
+
+# ob-databricks
+
+OrionBelt Semantic Layer driver for Databricks (DB-API 2.0)
+
+Part of the [OrionBelt Semantic Layer](https://github.com/ralfbecher/orionbelt-semantic-layer) project.
+
+## Installation
+
+```bash
+pip install ob-databricks
+```
+
+## License
+
+BSL-1.1 — see [LICENSE](LICENSE) for details.

ob_databricks-0.1.0/README.md

@@ -0,0 +1,15 @@
+# ob-databricks
+
+OrionBelt Semantic Layer driver for Databricks (DB-API 2.0)
+
+Part of the [OrionBelt Semantic Layer](https://github.com/ralfbecher/orionbelt-semantic-layer) project.
+
+## Installation
+
+```bash
+pip install ob-databricks
+```
+
+## License
+
+BSL-1.1 — see [LICENSE](LICENSE) for details.

ob_databricks-0.1.0/pyproject.toml

@@ -0,0 +1,51 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "ob-databricks"
+version = "0.1.0"
+description = "OrionBelt Semantic Layer driver for Databricks (DB-API 2.0)"
+license = { text = "BSL-1.1" }
+readme = "README.md"
+authors = [{ name = "Ralf Becher", email = "info@orionbelt.ai" }]
+keywords = ["databricks", "semantic-layer", "obml", "db-api", "orionbelt"]
+requires-python = ">=3.12"
+dependencies = [
+    "ob-driver-core>=0.1",
+    "databricks-sql-connector>=3.0",
+]
+
+[project.optional-dependencies]
+sqlalchemy = ["sqlalchemy>=2.0"]
+dev = [
+    "pytest>=8.0",
+    "pytest-asyncio>=0.23",
+    "mypy>=1.10",
+    "ruff>=0.4",
+    "respx>=0.21",
+]
+
+[project.entry-points."sqlalchemy.dialects"]
+"ob.databricks" = "ob_databricks.dialect:OBDatabricksDialect"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/ob_databricks"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py312"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B", "SIM", "ANN"]
+
+[tool.mypy]
+python_version = "3.12"
+strict = true
+files = ["src/ob_databricks"]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]
+markers = ["integration: requires live DB + OB API"]
+addopts = "-m 'not integration'"

ob_databricks-0.1.0/src/ob_databricks/__init__.py

@@ -0,0 +1,113 @@
+"""ob-databricks — OrionBelt Semantic Layer driver for Databricks (PEP 249 DB-API 2.0).
+
+Requires the OrionBelt REST API running in single-model mode (MODEL_FILE set).
+OBML queries are compiled to SQL via ``POST /v1/query/sql``.
+
+Usage::
+
+    import ob_databricks
+
+    conn = ob_databricks.connect(
+        server_hostname="adb-xxx.azuredatabricks.net",
+        http_path="/sql/1.0/warehouses/abc123",
+        access_token="dapi...",
+    )
+    with conn.cursor() as cur:
+        cur.execute("select:\\n  dimensions:\\n    - Region\\n  measures:\\n    - Revenue")
+        print(cur.fetchall())
+"""
+
+from __future__ import annotations
+
+from typing import Any
+
+from databricks import sql
+
+from ob_databricks.connection import Connection
+from ob_databricks.exceptions import (
+    DatabaseError,
+    DataError,
+    Error,
+    IntegrityError,
+    InterfaceError,
+    InternalError,
+    NotSupportedError,
+    OperationalError,
+    ProgrammingError,
+    Warning,
+)
+
+# PEP 249 module-level constants
+apilevel = "2.0"
+threadsafety = 1  # threads may share the module but not connections
+paramstyle = "pyformat"  # databricks-sql-connector uses %(name)s
+
+
+def connect(
+    server_hostname: str,
+    http_path: str,
+    *,
+    access_token: str | None = None,
+    catalog: str = "hive_metastore",
+    schema: str = "default",
+    # OrionBelt parameters
+    ob_api_url: str = "http://localhost:8000",
+    ob_timeout: int = 30,
+    **kwargs: Any,  # noqa: ANN401
+) -> Connection:
+    """Open a Databricks connection with OBML support.
+
+    Parameters
+    ----------
+    server_hostname : str
+        Databricks workspace hostname (e.g. ``adb-xxx.azuredatabricks.net``).
+    http_path : str
+        SQL warehouse HTTP path (e.g. ``/sql/1.0/warehouses/abc123``).
+    access_token : str, optional
+        Personal access token or OAuth token.
+    catalog : str
+        Unity Catalog name (default: ``hive_metastore``).
+    schema : str
+        Schema name (default: ``default``).
+    ob_api_url : str
+        OrionBelt REST API URL (must be running in single-model mode).
+    ob_timeout : int
+        HTTP timeout in seconds for OBML compilation.
+    **kwargs
+        Extra keyword arguments forwarded to ``databricks.sql.connect()``.
+    """
+    connect_kwargs: dict[str, Any] = {
+        "server_hostname": server_hostname,
+        "http_path": http_path,
+        "catalog": catalog,
+        "schema": schema,
+    }
+    if access_token is not None:
+        connect_kwargs["access_token"] = access_token
+    connect_kwargs.update(kwargs)
+
+    native = sql.connect(**connect_kwargs)
+    return Connection(
+        native,
+        ob_api_url=ob_api_url,
+        ob_timeout=ob_timeout,
+    )
+
+
+__all__ = [
+    "apilevel",
+    "threadsafety",
+    "paramstyle",
+    "connect",
+    "Connection",
+    "Warning",
+    "Error",
+    "InterfaceError",
+    "DatabaseError",
+    "DataError",
+    "OperationalError",
+    "IntegrityError",
+    "InternalError",
+    "ProgrammingError",
+    "NotSupportedError",
+]

ob_databricks-0.1.0/src/ob_databricks/compiler.py

@@ -0,0 +1,8 @@
+"""OrionBelt compilation bridge — delegates to ob-driver-core."""
+
+from __future__ import annotations
+
+from ob_driver_core.compiler import compile_obml
+from ob_driver_core.detection import is_obml, parse_obml
+
+__all__ = ["compile_obml", "is_obml", "parse_obml"]

ob_databricks-0.1.0/src/ob_databricks/connection.py

@@ -0,0 +1,62 @@
+"""PEP 249 Connection wrapping ``databricks.sql`` connection."""
+
+from __future__ import annotations
+
+from typing import Any
+
+from ob_databricks.cursor import Cursor
+from ob_databricks.exceptions import ProgrammingError
+
+
+class Connection:
+    """DB-API 2.0 connection that wraps a native Databricks SQL connector connection.
+
+    OBML queries are compiled to SQL via the OrionBelt REST API
+    (single-model mode, ``/v1/query/sql`` shortcut).
+    """
+
+    def __init__(
+        self,
+        native: Any,  # noqa: ANN401
+        *,
+        ob_api_url: str = "http://localhost:8000",
+        ob_timeout: int = 30,
+    ) -> None:
+        self._native = native
+        self._closed = False
+        self._ob_api_url = ob_api_url
+        self._ob_timeout = ob_timeout
+
+    def _check_open(self) -> None:
+        if self._closed:
+            raise ProgrammingError("Connection is closed.")
+
+    def cursor(self) -> Cursor:
+        """Return a new Cursor for this connection."""
+        self._check_open()
+        native_cursor = self._native.cursor()
+        return Cursor(
+            native_cursor,
+            ob_api_url=self._ob_api_url,
+            ob_timeout=self._ob_timeout,
+        )
+
+    def commit(self) -> None:
+        """No-op — Databricks SQL warehouses auto-commit all statements."""
+        self._check_open()
+
+    def rollback(self) -> None:
+        """No-op — Databricks SQL warehouses do not support transactions."""
+        self._check_open()
+
+    def close(self) -> None:
+        """Close the connection."""
+        if not self._closed:
+            self._native.close()
+            self._closed = True
+
+    def __enter__(self) -> Connection:
+        return self
+
+    def __exit__(self, *exc: object) -> None:
+        self.close()

ob_databricks-0.1.0/src/ob_databricks/cursor.py

@@ -0,0 +1,153 @@
+"""PEP 249 Cursor with OBML interception for Databricks."""
+
+from __future__ import annotations
+
+from typing import Any
+
+from ob_databricks.compiler import compile_obml, is_obml, parse_obml
+from ob_databricks.exceptions import NotSupportedError, ProgrammingError
+from ob_databricks.type_codes import DBR_TYPE_MAP, STRING
+
+
+class Cursor:
+    """DB-API 2.0 cursor that intercepts OBML YAML queries.
+
+    If the query is OBML, it is compiled to Databricks SQL via the OrionBelt
+    REST API before execution. Plain SQL is passed through unchanged.
+    """
+
+    arraysize: int = 1
+
+    def __init__(
+        self,
+        native: Any,  # noqa: ANN401
+        *,
+        ob_api_url: str = "http://localhost:8000",
+        ob_timeout: int = 30,
+    ) -> None:
+        self._native = native
+        self._closed = False
+        self._ob_api_url = ob_api_url
+        self._ob_timeout = ob_timeout
+
+    @property
+    def description(
+        self,
+    ) -> tuple[tuple[str, Any, None, None, None, None, None], ...] | None:
+        """PEP 249 cursor description — 7-item tuples per column.
+
+        Databricks SQL connector returns string type names in ``type_code``
+        (index 1 of each description column). These are mapped to PEP 249
+        type objects via :data:`DBR_TYPE_MAP`.
+        """
+        native_desc = self._native.description
+        if native_desc is None:
+            return None
+        cols: list[tuple[str, Any, None, None, None, None, None]] = []
+        for col in native_desc:
+            name = col[0]
+            type_name = str(col[1]).lower() if col[1] is not None else ""
+            type_code = DBR_TYPE_MAP.get(type_name, STRING)
+            cols.append((name, type_code, None, None, None, None, None))
+        return tuple(cols)
+
+    @property
+    def rowcount(self) -> int:
+        return self._native.rowcount
+
+    def _check_open(self) -> None:
+        if self._closed:
+            raise ProgrammingError("Cursor is closed.")
+
+    def execute(self, operation: str, parameters: Any = None) -> Cursor:  # noqa: ANN401
+        """Execute a query — OBML YAML or plain SQL."""
+        self._check_open()
+        sql = self._resolve_sql(operation)
+        if parameters is not None:
+            self._native.execute(sql, parameters)
+        else:
+            self._native.execute(sql)
+        return self
+
+    def executemany(self, operation: str, seq_of_parameters: Any) -> None:  # noqa: ANN401
+        """Execute against all parameter sequences.
+
+        OBML queries are not supported with executemany — raises NotSupportedError.
+        """
+        self._check_open()
+        if is_obml(operation):
+            raise NotSupportedError("executemany() is not supported for OBML queries.")
+        for params in seq_of_parameters:
+            self._native.execute(operation, params)
+
+    def _resolve_sql(self, operation: str) -> str:
+        """Compile OBML to SQL or return plain SQL unchanged."""
+        if not is_obml(operation):
+            return operation
+        obml = parse_obml(operation)
+        return compile_obml(
+            obml,
+            dialect="databricks",
+            ob_api_url=self._ob_api_url,
+            ob_timeout=self._ob_timeout,
+        )
+
+    def fetchone(self) -> tuple[Any, ...] | None:
+        """Fetch the next row."""
+        self._check_open()
+        row = self._native.fetchone()
+        return tuple(row) if row is not None else None
+
+    def fetchmany(self, size: int | None = None) -> list[tuple[Any, ...]]:
+        """Fetch the next *size* rows."""
+        self._check_open()
+        n = size if size is not None else self.arraysize
+        rows = self._native.fetchmany(n)
+        return [tuple(r) for r in rows]
+
+    def fetchall(self) -> list[tuple[Any, ...]]:
+        """Fetch all remaining rows."""
+        self._check_open()
+        rows = self._native.fetchall()
+        return [tuple(r) for r in rows]
+
+    def fetch_arrow_table(self) -> Any:  # noqa: ANN401
+        """Fetch all remaining rows as a PyArrow Table.
+
+        Databricks SQL connector returns Arrow natively via its internal
+        Thrift/Arrow result format.  More memory-efficient than ``fetchall()``.
+        """
+        self._check_open()
+        return self._native.fetchall_arrow()
+
+    def close(self) -> None:
+        """Close the cursor."""
+        if not self._closed:
+            self._native.close()
+            self._closed = True
+
+    def setinputsizes(self, sizes: Any) -> None:  # noqa: ANN401
+        """No-op — required by PEP 249."""
+
+    def setoutputsize(self, size: int, column: int | None = None) -> None:
+        """No-op — required by PEP 249."""
+
+    @property
+    def lastrowid(self) -> None:
+        """Databricks does not expose lastrowid via connector cursor."""
+        return None
+
+    def __enter__(self) -> Cursor:
+        return self
+
+    def __exit__(self, *exc: object) -> None:
+        self.close()
+
+    def __iter__(self) -> Cursor:
+        return self
+
+    def __next__(self) -> tuple[Any, ...]:
+        row = self.fetchone()
+        if row is None:
+            raise StopIteration
+        return row

ob_databricks-0.1.0/src/ob_databricks/exceptions.py

@@ -0,0 +1,32 @@
+"""PEP 249 exceptions — re-exported from ob-driver-core for convenience.
+
+Allows users to do: ``from ob_databricks.exceptions import ProgrammingError``
+"""
+
+from __future__ import annotations
+
+from ob_driver_core.exceptions import (
+    DatabaseError,
+    DataError,
+    Error,
+    IntegrityError,
+    InterfaceError,
+    InternalError,
+    NotSupportedError,
+    OperationalError,
+    ProgrammingError,
+    Warning,
+)
+
+__all__ = [
+    "Warning",
+    "Error",
+    "InterfaceError",
+    "DatabaseError",
+    "DataError",
+    "OperationalError",
+    "IntegrityError",
+    "InternalError",
+    "ProgrammingError",
+    "NotSupportedError",
+]

ob_databricks-0.1.0/src/ob_databricks/type_codes.py

@@ -0,0 +1,42 @@
+"""PEP 249 type objects — re-exported from ob-driver-core plus Databricks type mapping.
+
+databricks-sql-connector cursor.description returns string type names as type_code.
+The DBR_TYPE_MAP maps Databricks type names to PEP 249 type objects.
+"""
+
+from __future__ import annotations
+
+from ob_driver_core.type_codes import BINARY, DATETIME, NUMBER, ROWID, STRING
+
+__all__ = ["STRING", "BINARY", "NUMBER", "DATETIME", "ROWID", "DBR_TYPE_MAP"]
+
+# Databricks SQL connector type names from cursor.description
+# https://docs.databricks.com/en/sql/language-manual/sql-ref-datatypes.html
+DBR_TYPE_MAP: dict[str, object] = {
+    # Numeric
+    "boolean": STRING,
+    "byte": NUMBER,
+    "tinyint": NUMBER,
+    "short": NUMBER,
+    "smallint": NUMBER,
+    "int": NUMBER,
+    "integer": NUMBER,
+    "long": NUMBER,
+    "bigint": NUMBER,
+    "float": NUMBER,
+    "double": NUMBER,
+    "decimal": NUMBER,
+    # String
+    "string": STRING,
+    "char": STRING,
+    "varchar": STRING,
+    # Date/Time
+    "date": DATETIME,
+    "timestamp": DATETIME,
+    # Binary
+    "binary": BINARY,
+    # Complex (serialize as string)
+    "array": STRING,
+    "map": STRING,
+    "struct": STRING,
+}

ob_databricks-0.1.0/tests/test_driver.py

@@ -0,0 +1,546 @@
+"""Unit tests for the ob-databricks DB-API 2.0 driver.
+
+All tests mock ``databricks.sql`` — no live Databricks cluster needed.
+OBML tests additionally mock the REST API call to ``/v1/query/sql``.
+"""
+
+from __future__ import annotations
+
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+import ob_databricks
+from ob_databricks.connection import Connection
+from ob_databricks.cursor import Cursor
+from ob_databricks.exceptions import NotSupportedError, ProgrammingError
+from ob_databricks.type_codes import DATETIME, NUMBER, STRING
+
+# ---------------------------------------------------------------------------
+# Helper to build a mock databricks connection
+# ---------------------------------------------------------------------------
+
+# databricks-sql-connector description columns are tuples:
+# (name, type_code, display_size, internal_size, precision, scale, null_ok)
+# type_code is a string type name (e.g. "int", "string", "timestamp")
+
+
+def _make_dbr_desc(name: str, type_name: str) -> tuple[str, str, None, None, None, None, None]:
+    """Build a single Databricks description column tuple."""
+    return (name, type_name, None, None, None, None, None)
+
+
+def _make_mock_native() -> MagicMock:
+    """Return a mock databricks.sql connection."""
+    mock_conn = MagicMock()
+    mock_cursor = MagicMock()
+    mock_conn.cursor.return_value = mock_cursor
+    # Default: no results
+    mock_cursor.description = None
+    mock_cursor.rowcount = -1
+    mock_cursor.fetchone.return_value = None
+    mock_cursor.fetchall.return_value = []
+    mock_cursor.fetchmany.return_value = []
+    return mock_conn
+
+
+def _mock_api_response(sql: str) -> MagicMock:
+    """Create a mock httpx response returning the given SQL."""
+    resp = MagicMock()
+    resp.is_success = True
+    resp.json.return_value = {"sql": sql}
+    return resp
+
+
+# ---------------------------------------------------------------------------
+# PEP 249 module-level constants
+# ---------------------------------------------------------------------------
+
+
+def test_apilevel() -> None:
+    assert ob_databricks.apilevel == "2.0"
+
+
+def test_threadsafety() -> None:
+    assert ob_databricks.threadsafety == 1
+
+
+def test_paramstyle() -> None:
+    assert ob_databricks.paramstyle == "pyformat"
+
+
+# ---------------------------------------------------------------------------
+# connect()
+# ---------------------------------------------------------------------------
+
+
+def test_connect_returns_connection() -> None:
+    with patch("databricks.sql.connect") as mock_connect:
+        mock_connect.return_value = _make_mock_native()
+        conn = ob_databricks.connect(
+            server_hostname="adb-123.azuredatabricks.net",
+            http_path="/sql/1.0/warehouses/abc",
+            access_token="dapi_token",
+        )
+        assert isinstance(conn, Connection)
+        mock_connect.assert_called_once()
+        kwargs = mock_connect.call_args.kwargs
+        assert kwargs["server_hostname"] == "adb-123.azuredatabricks.net"
+        assert kwargs["http_path"] == "/sql/1.0/warehouses/abc"
+        assert kwargs["access_token"] == "dapi_token"
+
+
+def test_connect_default_catalog_and_schema() -> None:
+    with patch("databricks.sql.connect") as mock_connect:
+        mock_connect.return_value = _make_mock_native()
+        ob_databricks.connect(
+            server_hostname="adb-123.azuredatabricks.net",
+            http_path="/sql/1.0/warehouses/abc",
+        )
+        kwargs = mock_connect.call_args.kwargs
+        assert kwargs["catalog"] == "hive_metastore"
+        assert kwargs["schema"] == "default"
+
+
+def test_connect_custom_catalog_and_schema() -> None:
+    with patch("databricks.sql.connect") as mock_connect:
+        mock_connect.return_value = _make_mock_native()
+        ob_databricks.connect(
+            server_hostname="adb-123.azuredatabricks.net",
+            http_path="/sql/1.0/warehouses/abc",
+            catalog="unity_catalog",
+            schema="analytics",
+        )
+        kwargs = mock_connect.call_args.kwargs
+        assert kwargs["catalog"] == "unity_catalog"
+        assert kwargs["schema"] == "analytics"
+
+
+def test_connect_context_manager() -> None:
+    with patch("databricks.sql.connect") as mock_connect:
+        mock_native = _make_mock_native()
+        mock_connect.return_value = mock_native
+        with ob_databricks.connect(
+            server_hostname="adb-123.azuredatabricks.net",
+            http_path="/sql/1.0/warehouses/abc",
+        ) as conn:
+            assert isinstance(conn, Connection)
+        mock_native.close.assert_called_once()
+
+
+# ---------------------------------------------------------------------------
+# Connection
+# ---------------------------------------------------------------------------
+
+
+def test_connection_close_is_idempotent() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    conn.close()
+    conn.close()  # should not raise
+    mock_native.close.assert_called_once()
+
+
+def test_connection_cursor_after_close_raises() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    conn.close()
+    with pytest.raises(ProgrammingError, match="closed"):
+        conn.cursor()
+
+
+def test_connection_commit_noop() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    conn.commit()  # should not raise, no-op
+    # Databricks auto-commits — native commit is NOT called
+    mock_native.commit.assert_not_called()
+
+
+def test_connection_rollback_noop() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    conn.rollback()  # should not raise, no-op
+    # Databricks does not support transactions — native rollback is NOT called
+    mock_native.rollback.assert_not_called()
+
+
+def test_connection_commit_after_close_raises() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    conn.close()
+    with pytest.raises(ProgrammingError, match="closed"):
+        conn.commit()
+
+
+def test_connection_rollback_after_close_raises() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    conn.close()
+    with pytest.raises(ProgrammingError, match="closed"):
+        conn.rollback()
+
+
+# ---------------------------------------------------------------------------
+# Cursor — plain SQL
+# ---------------------------------------------------------------------------
+
+
+def test_cursor_execute_calls_native() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    with conn.cursor() as cur:
+        cur.execute("SELECT 1")
+        mock_native.cursor().execute.assert_called_once_with("SELECT 1")
+
+
+def test_cursor_execute_with_params() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    with conn.cursor() as cur:
+        cur.execute("SELECT %(a)s + %(b)s", {"a": 3, "b": 4})
+        mock_native.cursor().execute.assert_called_once_with(
+            "SELECT %(a)s + %(b)s", {"a": 3, "b": 4}
+        )
+
+
+def test_cursor_execute_returns_self() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    with conn.cursor() as cur:
+        result = cur.execute("SELECT 1")
+        assert result is cur
+
+
+def test_cursor_description() -> None:
+    mock_native = _make_mock_native()
+    mock_cursor = mock_native.cursor()
+    mock_cursor.description = [
+        _make_dbr_desc("num", "int"),
+        _make_dbr_desc("txt", "string"),
+        _make_dbr_desc("dt", "timestamp"),
+    ]
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    desc = cur.description
+    assert desc is not None
+    assert len(desc) == 3
+    assert all(len(col) == 7 for col in desc)
+    assert desc[0][0] == "num"
+    assert desc[0][1] == NUMBER
+    assert desc[1][0] == "txt"
+    assert desc[1][1] == STRING
+    assert desc[2][0] == "dt"
+    assert desc[2][1] == DATETIME
+
+
+def test_cursor_description_type_mapping_comprehensive() -> None:
+    """Verify all major Databricks types map correctly."""
+    mock_native = _make_mock_native()
+    mock_cursor = mock_native.cursor()
+    mock_cursor.description = [
+        _make_dbr_desc("c_bool", "boolean"),
+        _make_dbr_desc("c_byte", "byte"),
+        _make_dbr_desc("c_tinyint", "tinyint"),
+        _make_dbr_desc("c_short", "short"),
+        _make_dbr_desc("c_smallint", "smallint"),
+        _make_dbr_desc("c_int", "int"),
+        _make_dbr_desc("c_integer", "integer"),
+        _make_dbr_desc("c_long", "long"),
+        _make_dbr_desc("c_bigint", "bigint"),
+        _make_dbr_desc("c_float", "float"),
+        _make_dbr_desc("c_double", "double"),
+        _make_dbr_desc("c_decimal", "decimal"),
+        _make_dbr_desc("c_string", "string"),
+        _make_dbr_desc("c_char", "char"),
+        _make_dbr_desc("c_varchar", "varchar"),
+        _make_dbr_desc("c_date", "date"),
+        _make_dbr_desc("c_ts", "timestamp"),
+        _make_dbr_desc("c_binary", "binary"),
+        _make_dbr_desc("c_array", "array"),
+        _make_dbr_desc("c_map", "map"),
+        _make_dbr_desc("c_struct", "struct"),
+    ]
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    desc = cur.description
+    assert desc is not None
+    # boolean -> STRING
+    assert desc[0][1] == STRING
+    # numeric types -> NUMBER
+    for i in range(1, 12):
+        assert desc[i][1] == NUMBER, f"Column {desc[i][0]} should be NUMBER"
+    # string types -> STRING
+    for i in range(12, 15):
+        assert desc[i][1] == STRING, f"Column {desc[i][0]} should be STRING"
+    # date/time -> DATETIME
+    assert desc[15][1] == DATETIME
+    assert desc[16][1] == DATETIME
+    # binary -> BINARY
+    from ob_databricks.type_codes import BINARY
+
+    assert desc[17][1] == BINARY
+    # complex -> STRING
+    for i in range(18, 21):
+        assert desc[i][1] == STRING, f"Column {desc[i][0]} should be STRING"
+
+
+def test_cursor_description_unknown_type_defaults_to_string() -> None:
+    mock_native = _make_mock_native()
+    mock_cursor = mock_native.cursor()
+    mock_cursor.description = [
+        _make_dbr_desc("c_unknown", "some_future_type"),
+    ]
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    desc = cur.description
+    assert desc is not None
+    assert desc[0][1] == STRING
+
+
+def test_cursor_description_none_before_execute() -> None:
+    mock_native = _make_mock_native()
+    mock_native.cursor().description = None
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    assert cur.description is None
+
+
+def test_cursor_fetchone() -> None:
+    mock_native = _make_mock_native()
+    mock_native.cursor().fetchone.return_value = (42,)
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    row = cur.fetchone()
+    assert row == (42,)
+
+
+def test_cursor_fetchone_exhausted() -> None:
+    mock_native = _make_mock_native()
+    mock_native.cursor().fetchone.return_value = None
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    assert cur.fetchone() is None
+
+
+def test_cursor_fetchall() -> None:
+    mock_native = _make_mock_native()
+    mock_native.cursor().fetchall.return_value = [(1, "a"), (2, "b"), (3, "c")]
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    rows = cur.fetchall()
+    assert len(rows) == 3
+    assert rows[0] == (1, "a")
+
+
+def test_cursor_fetchmany() -> None:
+    mock_native = _make_mock_native()
+    mock_native.cursor().fetchmany.return_value = [(1,), (2,), (3,)]
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    batch = cur.fetchmany(3)
+    assert len(batch) == 3
+    mock_native.cursor().fetchmany.assert_called_with(3)
+
+
+def test_cursor_fetchmany_default_arraysize() -> None:
+    mock_native = _make_mock_native()
+    mock_native.cursor().fetchmany.return_value = [(1,)]
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    cur.fetchmany()
+    mock_native.cursor().fetchmany.assert_called_with(1)  # default arraysize
+
+
+def test_cursor_iteration() -> None:
+    mock_native = _make_mock_native()
+    mock_native.cursor().fetchone.side_effect = [(0,), (1,), (2,), None]
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    rows = list(cur)
+    assert len(rows) == 3
+    assert rows[0] == (0,)
+
+
+def test_cursor_close_then_fetch_raises() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    cur.close()
+    with pytest.raises(ProgrammingError, match="closed"):
+        cur.fetchone()
+
+
+def test_cursor_close_then_fetchall_raises() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    cur.close()
+    with pytest.raises(ProgrammingError, match="closed"):
+        cur.fetchall()
+
+
+def test_cursor_close_then_fetchmany_raises() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    cur.close()
+    with pytest.raises(ProgrammingError, match="closed"):
+        cur.fetchmany()
+
+
+def test_cursor_close_then_execute_raises() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    cur.close()
+    with pytest.raises(ProgrammingError, match="closed"):
+        cur.execute("SELECT 1")
+
+
+def test_cursor_close_is_idempotent() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    cur.close()
+    cur.close()  # should not raise
+    mock_native.cursor().close.assert_called_once()
+
+
+def test_cursor_executemany_plain_sql() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    cur.executemany(
+        "INSERT INTO t VALUES (%(a)s, %(b)s)",
+        [{"a": 1, "b": "x"}, {"a": 2, "b": "y"}],
+    )
+    assert mock_native.cursor().execute.call_count == 2
+
+
+def test_cursor_executemany_obml_raises() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    obml = "select:\n  dimensions:\n    - Region\n  measures:\n    - Revenue\n"
+    with pytest.raises(NotSupportedError, match="executemany"):
+        cur.executemany(obml, [])
+
+
+def test_cursor_setinputsizes_noop() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    cur.setinputsizes([])  # should not raise
+
+
+def test_cursor_setoutputsize_noop() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    cur.setoutputsize(1000)  # should not raise
+
+
+def test_cursor_lastrowid_is_none() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    assert cur.lastrowid is None
+
+
+def test_cursor_rowcount() -> None:
+    mock_native = _make_mock_native()
+    mock_native.cursor().rowcount = 5
+    conn = Connection(mock_native)
+    cur = conn.cursor()
+    assert cur.rowcount == 5
+
+
+def test_cursor_context_manager() -> None:
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    with conn.cursor() as cur:
+        assert isinstance(cur, Cursor)
+    mock_native.cursor().close.assert_called_once()
+
+
+# ---------------------------------------------------------------------------
+# Cursor — OBML queries (mocked REST API)
+# ---------------------------------------------------------------------------
+
+
+def test_obml_compile_and_execute() -> None:
+    """OBML query is compiled via REST API then executed on Databricks."""
+    mock_native = _make_mock_native()
+    compiled_sql = "SELECT region, SUM(amount) AS revenue FROM orders GROUP BY region"
+    mock_native.cursor().description = [
+        _make_dbr_desc("region", "string"),
+        _make_dbr_desc("revenue", "double"),
+    ]
+    mock_native.cursor().fetchall.return_value = [
+        ("EMEA", 300.0),
+        ("APAC", 150.0),
+        ("AMER", 550.0),
+    ]
+    conn = Connection(mock_native)
+    with (
+        patch("httpx.post", return_value=_mock_api_response(compiled_sql)),
+        conn.cursor() as cur,
+    ):
+        cur.execute("select:\n  dimensions:\n    - Region\n  measures:\n    - Revenue\n")
+        rows = cur.fetchall()
+        assert len(rows) == 3
+        # Verify the compiled SQL was passed to native cursor
+        mock_native.cursor().execute.assert_called_once_with(compiled_sql)
+
+
+def test_obml_rest_dialect_is_databricks() -> None:
+    """REST API is called with dialect=databricks."""
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    compiled_sql = "SELECT 1"
+    with (
+        patch("httpx.post", return_value=_mock_api_response(compiled_sql)) as mock_post,
+        conn.cursor() as cur,
+    ):
+        cur.execute("select:\n  measures:\n    - Revenue\n")
+        url = mock_post.call_args.args[0]
+        assert "/v1/query/sql" in url
+        assert mock_post.call_args.kwargs["params"] == {"dialect": "databricks"}
+
+
+def test_obml_custom_api_url() -> None:
+    """Custom ob_api_url is forwarded to the REST call."""
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native, ob_api_url="http://my-api:9000")
+    compiled_sql = "SELECT 1"
+    with (
+        patch("httpx.post", return_value=_mock_api_response(compiled_sql)) as mock_post,
+        conn.cursor() as cur,
+    ):
+        cur.execute("select:\n  measures:\n    - Revenue\n")
+        url = mock_post.call_args.args[0]
+        assert url == "http://my-api:9000/v1/query/sql"
+
+
+def test_obml_custom_timeout() -> None:
+    """Custom ob_timeout is forwarded to the REST call."""
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native, ob_timeout=60)
+    compiled_sql = "SELECT 1"
+    with (
+        patch("httpx.post", return_value=_mock_api_response(compiled_sql)) as mock_post,
+        conn.cursor() as cur,
+    ):
+        cur.execute("select:\n  measures:\n    - Revenue\n")
+        assert mock_post.call_args.kwargs["timeout"] == 60
+
+
+def test_plain_sql_passthrough() -> None:
+    """Plain SQL is passed through without OBML compilation — no REST call."""
+    mock_native = _make_mock_native()
+    conn = Connection(mock_native)
+    with patch("httpx.post") as mock_post, conn.cursor() as cur:
+        cur.execute("SELECT COUNT(*) FROM orders")
+        mock_post.assert_not_called()
+        mock_native.cursor().execute.assert_called_once_with("SELECT COUNT(*) FROM orders")

ob_databricks-0.1.0/tests/test_yaml_detection.py

@@ -0,0 +1,34 @@
+"""Unit tests for OBML YAML detection — no external services required."""
+
+import pytest
+
+from ob_databricks.compiler import is_obml, parse_obml
+
+
+@pytest.mark.parametrize(
+    "query,expected",
+    [
+        ("select:\n  dimensions:\n    - Region\n  measures:\n    - Revenue\n", True),
+        ("select:\n  measures:\n    - Revenue\n", True),
+        ("select:\n  dimensions:\n    - Country\n", True),
+        ("SELECT:\n  dimensions:\n    - X\n", True),
+        ("   select:\n  dimensions:\n    - X\n", True),
+        ("SELECT * FROM orders", False),
+        ("SELECT id\nFROM customers WHERE id = 1", False),
+        ("", False),
+        ("model:\n  name: test\n", False),
+        ("select:\n  filters:\n    - x = 1\n", False),
+        ("select:\n  - [unclosed", False),
+        ("select:\n  - dimension1\n", False),
+    ],
+)
+def test_obml_detection(query: str, expected: bool) -> None:
+    assert is_obml(query) == expected
+
+
+def test_parse_obml_returns_dict() -> None:
+    q = "select:\n  dimensions:\n    - Region\n  measures:\n    - Revenue\nlimit: 100\n"
+    result = parse_obml(q)
+    assert result["select"]["dimensions"] == ["Region"]
+    assert result["select"]["measures"] == ["Revenue"]
+    assert result["limit"] == 100