Skip to content

Commit

Permalink
Merge branch 'main' into iceberg-read-write
Browse files Browse the repository at this point in the history
  • Loading branch information
caican00 authored Apr 2, 2024
2 parents 509b0d6 + 4411459 commit d136e7f
Show file tree
Hide file tree
Showing 37 changed files with 1,159 additions and 336 deletions.
163 changes: 159 additions & 4 deletions clients/client-python/.gitignore
Original file line number Diff line number Diff line change
@@ -1,5 +1,160 @@
# Copyright 2024 Datastrato Pvt Ltd.
# This software is licensed under the Apache License version 2.

# Byte-compiled / optimized / DLL files
__pycache__/
.pytest_cache/
*.py[cod]
*$py.class

# C extensions
*.so

# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST

# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.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/
cover/

# 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
.pybuilder/
target/

# Jupyter Notebook
.ipynb_checkpoints

# IPython
profile_default/
ipython_config.py

# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version

# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock

# poetry
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
#poetry.lock

# pdm
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
# in version control.
# https://pdm.fming.dev/#use-with-ide
.pdm.toml

# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__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/

# pytype static type analyzer
.pytype/

# Cython debug symbols
cython_debug/

# PyCharm
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
#.idea/
15 changes: 15 additions & 0 deletions clients/client-python/Makefile
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
# Copyright 2024 Datastrato Pvt Ltd.
# This software is licensed under the Apache License version 2.
.PHONY: mkvenv install test clean

mkvenv:
python -m venv venv && source ./venv/bin/activate && pip install -U pip

install:
source ./venv/bin/activate && pip install -e .

test:
source ./venv/bin/activate && python -m unittest

clean:
rm -rf venv
11 changes: 8 additions & 3 deletions clients/client-python/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,14 @@

# Quick Start

1. Install dependency
1. Install current library in your local machine.
```bash
pip install -r requirements.txt
pip install -e .
```

2. After the packages is installed, you can simply run `pytest` in any directory inside gravitino/
# Development Environment

1. Install dependency
```bash
pip install -e .[dev]
```
13 changes: 13 additions & 0 deletions clients/client-python/gravitino/__init__.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
"""
Copyright 2024 Datastrato Pvt Ltd.
This software is licensed under the Apache License version 2.
"""

from gravitino.gravitino_client import (
GravitinoClient,
gravitino_metalake,
MetaLake,
Catalog,
Schema,
Table,
)
Original file line number Diff line number Diff line change
@@ -1,4 +1,6 @@
"""
Copyright 2024 Datastrato Pvt Ltd.
This software is licensed under the Apache License version 2.
"""
"""

TIMEOUT = 10
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
"""
Copyright 2024 Datastrato Pvt Ltd.
This software is licensed under the Apache License version 2.
"""
"""
158 changes: 158 additions & 0 deletions clients/client-python/gravitino/gravitino_client.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,158 @@
"""
Copyright 2024 Datastrato Pvt Ltd.
This software is licensed under the Apache License version 2.
"""

from gravitino.constants import TIMEOUT
from gravitino.service import initialize_service, service


class MetaLake:
def __init__(self, metalake_name: str):
self.name = metalake_name
self.service = service["service"]
self.metalake = self.service.get_metalake(self.name)
self.catalogs = self.service.list_catalogs(self.name)

def __repr__(self):
return f"MetaLake<{self.name}>"

def __getattr__(self, catalog_name):
if catalog_name in dir(self):
return Catalog(self.name, catalog_name)

def __dir__(self):
return [catalog["name"] for catalog in self.catalogs]

def __contains__(self, item):
return item in dir(self)


class Catalog:
def __init__(self, metalake_name: str, catalog_name: str):
self.metalake_name = metalake_name
self.catalog_name = catalog_name
self.name = catalog_name
self.service = service["service"]
self.schemas = self.service.list_schemas(metalake_name, catalog_name)

def __repr__(self):
return f"Catalog<{self.name}>"

def __getattr__(self, schema_name):
if schema_name in dir(self):
return Schema(self.metalake_name, self.catalog_name, schema_name)

def __dir__(self):
return [schema["name"] for schema in self.schemas]

def __contains__(self, item):
return item in dir(self)


class Schema:
def __init__(self, metalake_name: str, catalog_name: str, schema_name: str):
self.metalake_name = metalake_name
self.catalog_name = catalog_name
self.schema_name = schema_name
self.name = schema_name
self.service = service["service"]
self.tables = self.service.list_tables(metalake_name, catalog_name, schema_name)

def __repr__(self):
return f"Schema<{self.name}>"

def __getattr__(self, table_name):
if table_name in dir(self):
return Table(
self.metalake_name, self.catalog_name, self.schema_name, table_name
)

def __dir__(self):
return [table["name"] for table in self.tables]

def __contains__(self, item):
return item in dir(self)


class Table:
def __init__(
self, metalake_name: str, catalog_name: str, schema_name: str, table_name: str
):
self.metalake_name = metalake_name
self.catalog_name = catalog_name
self.schema_name = schema_name
self.table_name = table_name
self.name = schema_name
self.service = service["service"]

def __repr__(self):
return f"Table<{self.name}>"

def info(self):
return self.service.get_table(
self.metalake_name, self.catalog_name, self.schema_name, self.table_name
)


class GravitinoClient:
def __init__(
self,
host: str,
*,
prefix: str = "/api",
timeout: int = TIMEOUT,
debug: bool = False,
) -> None:
_base_url = f"{host.rstrip('/')}/{prefix.strip('/')}"
initialize_service(_base_url, timeout)
self.service = service["service"]
self.debug = debug

@classmethod
def initialize_metalake(
cls,
host: str,
metalake_name: str,
*,
prefix: str = "/api",
timeout: int = TIMEOUT,
debug: bool = False,
) -> MetaLake:
# keep in mind, all constructors should include same interface as __init__ function
client = cls(
host,
prefix=prefix,
timeout=timeout,
debug=debug,
)
return client.get_metalake(metalake_name)

@property
def version(self):
return self.service.get_version()

def get_metalakes(self) -> [MetaLake]:
return [
MetaLake(metalake.get("name")) for metalake in self.service.list_metalakes()
]

def get_metalake(self, metalake: str) -> MetaLake:
return MetaLake(metalake)


def gravitino_metalake(
host: str,
metalake_name: str,
*,
prefix: str = "/api",
timeout: int = TIMEOUT,
debug: bool = False,
) -> MetaLake:
return GravitinoClient.initialize_metalake(
host,
metalake_name,
prefix=prefix,
timeout=timeout,
debug=debug,
)
Loading

0 comments on commit d136e7f

Please sign in to comment.