datus-hive 0.1.0__tar.gz

datus_hive-0.1.0/.gitignore

@@ -0,0 +1,140 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+Pipfile.lock
+
+# uv
+uv.lock
+
+# PEP 582
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# IDEs
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db
+
+
+.omc

datus_hive-0.1.0/PKG-INFO

@@ -0,0 +1,203 @@
+Metadata-Version: 2.4
+Name: datus-hive
+Version: 0.1.0
+Summary: Hive database adapter for Datus
+Project-URL: Homepage, https://github.com/Datus-ai/datus-db-adapters
+Project-URL: Repository, https://github.com/Datus-ai/datus-db-adapters
+Project-URL: Issues, https://github.com/Datus-ai/datus-db-adapters/issues
+Author-email: DatusAI <support@datus.ai>
+License: Apache-2.0
+Keywords: adapter,database,datus,hive
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.12
+Requires-Dist: datus-agent>0.2.1
+Requires-Dist: datus-sqlalchemy>=0.1.0
+Requires-Dist: pure-sasl>=0.6.2
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: pyhive>=0.7.0
+Requires-Dist: thrift-sasl>=0.4.3
+Requires-Dist: thrift>=0.16.0
+Description-Content-Type: text/markdown
+
+# datus-hive
+
+Hive database adapter for Datus.
+
+## Installation
+
+```bash
+pip install datus-hive
+```
+
+This will automatically install the required dependencies:
+- `datus-agent`
+- `datus-sqlalchemy`
+- `pyhive`
+- `thrift`
+- `thrift-sasl`
+- `pure-sasl`
+
+## Usage
+
+The adapter is automatically registered with Datus when installed. Configure your Hive connection in your Datus configuration:
+
+```yaml
+namespace:
+  hive:
+    type: hive
+    host: 127.0.0.1
+    port: 10000
+    username: hive
+    database: default
+```
+
+With authentication and session configuration:
+
+```yaml
+namespace:
+  hive_production:
+    type: hive
+    host: 127.0.0.1
+    port: 10000
+    database: mydb
+    username: hive_user
+    password: your_password
+    auth: CUSTOM
+    configuration:
+      hive.execution.engine: spark
+      spark.app.name: my_app
+      spark.executor.memory: 1G
+      spark.executor.instances: 2
+```
+
+Or use programmatically:
+
+```python
+from datus_hive import HiveConnector, HiveConfig
+
+# Create connector
+config = HiveConfig(
+    host="127.0.0.1",
+    port=10000,
+    database="default",
+    username="hive",
+)
+
+connector = HiveConnector(config)
+
+# Test connection
+connector.test_connection()
+
+# Execute query
+result = connector.execute(
+    {"sql_query": "SELECT * FROM my_table LIMIT 10"},
+    result_format="list",
+)
+print(result.sql_return)
+
+# Get table list
+tables = connector.get_tables()
+print(f"Tables: {tables}")
+
+# Get table schema
+schema = connector.get_schema(table_name="my_table")
+for column in schema:
+    print(f"{column['name']}: {column['type']}")
+```
+
+## Configuration Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `host` | str | `127.0.0.1` | HiveServer2 host |
+| `port` | int | `10000` | HiveServer2 Thrift port |
+| `database` | str | `None` | Default database (falls back to `default`) |
+| `username` | str | **required** | Hive username |
+| `password` | str | `""` | Password (for LDAP/CUSTOM auth) |
+| `auth` | str | `None` | Auth mechanism: `NONE`, `LDAP`, `CUSTOM`, `KERBEROS` |
+| `configuration` | dict | `{}` | Hive session configuration key-value pairs |
+| `timeout_seconds` | int | `30` | Connection timeout in seconds |
+
+## Features
+
+- Query execution with multiple result formats (list, csv, pandas, arrow)
+- DDL execution (CREATE, ALTER, DROP)
+- Metadata retrieval (databases, tables, views, schemas)
+- DDL retrieval (SHOW CREATE TABLE)
+- Sample data extraction
+- Database context switching (USE statement)
+- Connection pooling and management
+- Hive session configuration support
+
+## Testing
+
+### Unit Tests
+
+```bash
+uv run pytest datus-hive/tests/unit -v
+```
+
+### Integration Tests
+
+Start Hive using Docker:
+
+```bash
+cd datus-hive
+docker compose up -d
+
+# Wait for Hive to be healthy (about 1-2 minutes)
+docker inspect --format='{{.State.Health.Status}}' datus-hive-server
+```
+
+Run integration tests:
+
+```bash
+uv run pytest datus-hive/tests/integration -v
+```
+
+Stop Hive:
+
+```bash
+cd datus-hive
+docker compose down
+```
+
+### TPC-H Test Data
+
+Initialize TPC-H sample data for manual testing:
+
+```bash
+uv run python datus-hive/scripts/init_tpch_data.py
+
+# With custom connection:
+uv run python datus-hive/scripts/init_tpch_data.py --host localhost --port 10000 --username hive
+
+# Clean re-init (drop existing tables first):
+uv run python datus-hive/scripts/init_tpch_data.py --drop
+```
+
+This creates 5 TPC-H tables with sample data:
+
+| Table | Rows |
+|-------|------|
+| `tpch_region` | 5 |
+| `tpch_nation` | 25 |
+| `tpch_customer` | 10 |
+| `tpch_orders` | 15 |
+| `tpch_supplier` | 5 |
+
+## Requirements
+
+- Python >= 3.10
+- Apache Hive >= 2.x (tested with 4.0.1)
+- datus-agent >= 0.3.0
+- datus-sqlalchemy >= 0.1.0
+- pyhive >= 0.7.0
+
+## License
+
+Apache License 2.0

datus_hive-0.1.0/README.md

@@ -0,0 +1,178 @@
+# datus-hive
+
+Hive database adapter for Datus.
+
+## Installation
+
+```bash
+pip install datus-hive
+```
+
+This will automatically install the required dependencies:
+- `datus-agent`
+- `datus-sqlalchemy`
+- `pyhive`
+- `thrift`
+- `thrift-sasl`
+- `pure-sasl`
+
+## Usage
+
+The adapter is automatically registered with Datus when installed. Configure your Hive connection in your Datus configuration:
+
+```yaml
+namespace:
+  hive:
+    type: hive
+    host: 127.0.0.1
+    port: 10000
+    username: hive
+    database: default
+```
+
+With authentication and session configuration:
+
+```yaml
+namespace:
+  hive_production:
+    type: hive
+    host: 127.0.0.1
+    port: 10000
+    database: mydb
+    username: hive_user
+    password: your_password
+    auth: CUSTOM
+    configuration:
+      hive.execution.engine: spark
+      spark.app.name: my_app
+      spark.executor.memory: 1G
+      spark.executor.instances: 2
+```
+
+Or use programmatically:
+
+```python
+from datus_hive import HiveConnector, HiveConfig
+
+# Create connector
+config = HiveConfig(
+    host="127.0.0.1",
+    port=10000,
+    database="default",
+    username="hive",
+)
+
+connector = HiveConnector(config)
+
+# Test connection
+connector.test_connection()
+
+# Execute query
+result = connector.execute(
+    {"sql_query": "SELECT * FROM my_table LIMIT 10"},
+    result_format="list",
+)
+print(result.sql_return)
+
+# Get table list
+tables = connector.get_tables()
+print(f"Tables: {tables}")
+
+# Get table schema
+schema = connector.get_schema(table_name="my_table")
+for column in schema:
+    print(f"{column['name']}: {column['type']}")
+```
+
+## Configuration Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `host` | str | `127.0.0.1` | HiveServer2 host |
+| `port` | int | `10000` | HiveServer2 Thrift port |
+| `database` | str | `None` | Default database (falls back to `default`) |
+| `username` | str | **required** | Hive username |
+| `password` | str | `""` | Password (for LDAP/CUSTOM auth) |
+| `auth` | str | `None` | Auth mechanism: `NONE`, `LDAP`, `CUSTOM`, `KERBEROS` |
+| `configuration` | dict | `{}` | Hive session configuration key-value pairs |
+| `timeout_seconds` | int | `30` | Connection timeout in seconds |
+
+## Features
+
+- Query execution with multiple result formats (list, csv, pandas, arrow)
+- DDL execution (CREATE, ALTER, DROP)
+- Metadata retrieval (databases, tables, views, schemas)
+- DDL retrieval (SHOW CREATE TABLE)
+- Sample data extraction
+- Database context switching (USE statement)
+- Connection pooling and management
+- Hive session configuration support
+
+## Testing
+
+### Unit Tests
+
+```bash
+uv run pytest datus-hive/tests/unit -v
+```
+
+### Integration Tests
+
+Start Hive using Docker:
+
+```bash
+cd datus-hive
+docker compose up -d
+
+# Wait for Hive to be healthy (about 1-2 minutes)
+docker inspect --format='{{.State.Health.Status}}' datus-hive-server
+```
+
+Run integration tests:
+
+```bash
+uv run pytest datus-hive/tests/integration -v
+```
+
+Stop Hive:
+
+```bash
+cd datus-hive
+docker compose down
+```
+
+### TPC-H Test Data
+
+Initialize TPC-H sample data for manual testing:
+
+```bash
+uv run python datus-hive/scripts/init_tpch_data.py
+
+# With custom connection:
+uv run python datus-hive/scripts/init_tpch_data.py --host localhost --port 10000 --username hive
+
+# Clean re-init (drop existing tables first):
+uv run python datus-hive/scripts/init_tpch_data.py --drop
+```
+
+This creates 5 TPC-H tables with sample data:
+
+| Table | Rows |
+|-------|------|
+| `tpch_region` | 5 |
+| `tpch_nation` | 25 |
+| `tpch_customer` | 10 |
+| `tpch_orders` | 15 |
+| `tpch_supplier` | 5 |
+
+## Requirements
+
+- Python >= 3.10
+- Apache Hive >= 2.x (tested with 4.0.1)
+- datus-agent >= 0.3.0
+- datus-sqlalchemy >= 0.1.0
+- pyhive >= 0.7.0
+
+## License
+
+Apache License 2.0

datus_hive-0.1.0/datus_hive/__init__.py

@@ -0,0 +1,16 @@
+# Copyright 2025-present DatusAI, Inc.
+# Licensed under the Apache License, Version 2.0.
+# See http://www.apache.org/licenses/LICENSE-2.0 for details.
+
+from .config import HiveConfig
+from .connector import HiveConnector
+
+__version__ = "0.1.0"
+__all__ = ["HiveConnector", "HiveConfig", "register"]
+
+
+def register():
+    """Register Hive connector with Datus registry."""
+    from datus.tools.db_tools import connector_registry
+
+    connector_registry.register("hive", HiveConnector, config_class=HiveConfig)

datus_hive-0.1.0/datus_hive/config.py

@@ -0,0 +1,56 @@
+# Copyright 2025-present DatusAI, Inc.
+# Licensed under the Apache License, Version 2.0.
+# See http://www.apache.org/licenses/LICENSE-2.0 for details.
+
+from typing import Any, Dict, Mapping, Optional
+
+from pydantic import BaseModel, ConfigDict, Field
+
+
+def _extract_prefixed_config(carrier_map: Mapping[str, Any], prefix: str) -> Dict[str, Any]:
+    """Extract Hive configuration from a prefixed carrier map."""
+    hive_config: Dict[str, Any] = {}
+    prefix_len = len(prefix)
+
+    for key, value in carrier_map.items():
+        if key.startswith(prefix):
+            hive_key = key[prefix_len:]
+            hive_config[hive_key] = value
+
+    configuration_params: Dict[str, Any] = {}
+    base_params: Dict[str, Any] = {}
+
+    for key, value in hive_config.items():
+        if key.startswith("configuration."):
+            config_key = key[14:]
+            configuration_params[config_key] = value
+        else:
+            if key == "port" and isinstance(value, str) and value.isdigit():
+                base_params[key] = int(value)
+            else:
+                base_params[key] = value
+
+    result = base_params.copy()
+    result["configuration"] = configuration_params
+    return result
+
+
+class HiveConfig(BaseModel):
+    """Hive-specific configuration."""
+
+    model_config = ConfigDict(extra="forbid")
+
+    host: str = Field(default="127.0.0.1", description="Hive server host")
+    port: int = Field(default=10000, description="Hive server port")
+    database: Optional[str] = Field(default=None, description="Default database name")
+    username: str = Field(..., description="Hive username")
+    password: str = Field(default="", description="Hive password", json_schema_extra={"input_type": "password"})
+    auth: Optional[str] = Field(default=None, description="Authentication mechanism (NONE, LDAP, CUSTOM, KERBEROS)")
+    configuration: Dict[str, Any] = Field(default_factory=dict, description="Hive session configuration")
+    timeout_seconds: int = Field(default=30, description="Connection timeout in seconds")
+
+    @classmethod
+    def from_config_map(cls, config_map: Mapping[str, Any], prefix: str) -> "HiveConfig":
+        """Build HiveConfig from a prefixed carrier map."""
+        extracted = _extract_prefixed_config(config_map, prefix)
+        return cls(**extracted)