ob-databricks 0.1.0__py3-none-any.whl

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/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/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/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/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/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.dist-info/METADATA

@@ -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.dist-info/RECORD

@@ -0,0 +1,11 @@
+ob_databricks/__init__.py,sha256=JtbEL0v5bxVHQuA_fFjeqHQz0XhQ17E3ABO4RpQ4R9M,2984
+ob_databricks/compiler.py,sha256=WTYZzdsJJiOxgIDS3NpDOpk_SG7_0weT4el-xuuBGsE,264
+ob_databricks/connection.py,sha256=fBUo4yAX6CsEMh5EeobBcgJNpTeL9g_LfskPYxpgnW4,1751
+ob_databricks/cursor.py,sha256=D30HXLMhvTBGqMbTW0KJB-w9Me-9ywHREAnMrcjkvA4,5098
+ob_databricks/exceptions.py,sha256=Au4Er33l-WMXtE9E6BNY--WpBVaA11I3ihHHJio3O4k,640
+ob_databricks/type_codes.py,sha256=Xuud_thjXQ196vEwuQVZUkq2gvuRQF9R0c0bPozCyK8,1170
+ob_databricks-0.1.0.dist-info/METADATA,sha256=YUAkWmwkQqUI4-YfBnKQ7G9v3YYnzUMvtR6xvWQGgnA,1035
+ob_databricks-0.1.0.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
+ob_databricks-0.1.0.dist-info/entry_points.txt,sha256=1MsGJENBwxFm-bR-EAkNfLkUqEugnaS0-83AGxqc4AI,80
+ob_databricks-0.1.0.dist-info/licenses/LICENSE,sha256=t-vr73N5s2w6yxpCnwo5r_QuB5_u6FuEovAYMjlfe7E,3378
+ob_databricks-0.1.0.dist-info/RECORD,,

ob_databricks-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.29.0
+Root-Is-Purelib: true
+Tag: py3-none-any

ob_databricks-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[sqlalchemy.dialects]
+ob.databricks = ob_databricks.dialect:OBDatabricksDialect

ob_databricks-0.1.0.dist-info/licenses/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/.