-
Notifications
You must be signed in to change notification settings - Fork 304
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Browse files
Browse the repository at this point in the history
### What changes were proposed in this pull request? <img width="982" alt="image" src="https://github.com/datastrato/gravitino/assets/2016594/9005bd8e-b6cb-4af3-bd35-3067f90cb81d"> The more detailed introductions for the PR has been uploaded on the [bilibili](https://www.bilibili.com/video/BV11i42197x3/?vd_source=b1397e6194e37e70828e961f41b7b9db), please jump in there to get a quick view. #2113 ### Follow the below command 1. Install the python-client in your local machine, notice that version of Python should be upper than 3.8. ```shell $ cd clients/client-python $ pip install -e . $ pip install ipython (optional) $ ipython (optional) ``` 2. Run the Python terminal and happy coding. ``` In [1]: from gravitino import GravitinoClient In [2]: client = GravitinoClient("http://localhost:8090") In [3]: client.get_metalakes() In [4]: metalake_demo = client.get_metalakes()[1] In [5]: metalake_demo.catalog_hive.sales.customers.info() ``` I will follow next steps to refactor/implement the initial Python Client, also heads up @Lanznx was the initial contributor for the Python Client. - [x] Remove `requests` since we are using really simple HTTP client to communicate between `Python script` and `Gravitino`, the `http.client` in Python3 is sufficient. - [x] Add Unit test - [ ] Add codes linter - [ ] Provide an approach for uploading PyPI ### Why are the changes needed? The motivation of the PR intend to introduce an interactivity and exploratory user-experience between Python terminal and Gravitino Server. ### Does this PR introduce _any_ user-facing change? N/A ### How was this patch tested? Unit tests will cover changes. --------- Co-authored-by: Yongjie Zhao <[email protected]> Co-authored-by: Shaofeng Shi <[email protected]>
- Loading branch information
1 parent
d5742c2
commit 4411459
Showing
23 changed files
with
925 additions
and
131 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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/ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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, | ||
) |
4 changes: 3 additions & 1 deletion
4
...lient-python/gravitino_client/__init__.py → clients/client-python/gravitino/constants.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 |
2 changes: 1 addition & 1 deletion
2
clients/client-python/__init__.py → ...nts/client-python/gravitino/exceptions.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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. | ||
""" | ||
""" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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, | ||
) |
Oops, something went wrong.