diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..4e5c4e4 --- /dev/null +++ b/.gitignore @@ -0,0 +1,165 @@ +.coverage +.vscode/ +.idea/ +# 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/ +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/ + +.DS_Store diff --git a/README.md b/README.md index fba2a99..4b237d8 100644 --- a/README.md +++ b/README.md @@ -43,6 +43,15 @@ data = athena.query('select count(*) as my_col from "trajectories"."kitware"').r print(data.head(1)) ``` +# Build + +To build the project, run the following commands. (Requires poetry installed): + +```bash +poetry install +poetry build +``` + # TODO * parallelize the downloading of files diff --git a/minerva/__init__.py b/minerva/__init__.py index e69de29..1b2a66f 100644 --- a/minerva/__init__.py +++ b/minerva/__init__.py @@ -0,0 +1,7 @@ +from .minerva import Athena, Execute, Query + +__all__ = [ + "Execute", + "Query", + "Athena" +] diff --git a/minerva/minerva.py b/minerva/minerva.py index fbe3280..da0ba0e 100644 --- a/minerva/minerva.py +++ b/minerva/minerva.py @@ -19,6 +19,11 @@ class Athena: q = Query(self, sql) q.run() return q + + def execute(self, sql): + e = Execute(self, sql) + e.run() + return e def download(self, s3): bucket = s3.split("/")[2] @@ -28,6 +33,44 @@ class Athena: return tmp +class Execute: + """ + Execute will not return results, but will execute the SQL and return the final state. + Execute is meant to be used for DML statements such as CREATE DATABASE/TABLE + """ + def __init__(self, handler, sql): + self.handler = handler + self.athena = handler.athena + self.sql = sql + + def run(self): + out = os.path.join(self.handler.output, + str(random.random())) + config = {"OutputLocation": out} + resp = self.athena.start_query_execution(QueryString=self.sql, + ResultConfiguration=config) + self.query_id = resp['QueryExecutionId'] + return resp + + def status(self): + return self.info()['Status'] + + def info(self): + res = self.athena.get_query_execution(QueryExecutionId=self.query_id) + return res['QueryExecution'] + + def execute(self): + tiedot = self.info() + status = tiedot['Status']['State'] + + while status in ['QUEUED', 'RUNNING']: + time.sleep(5) + tiedot = self.info() + status = tiedot['Status']['State'] + + return status # finalized state + + class Query: DATA_STYLE = 'parquet' @@ -86,5 +129,3 @@ class Query: tmp = self.handler.download(manif) with open(tmp, "r") as f: return f.read() - - diff --git a/poetry.lock b/poetry.lock new file mode 100644 index 0000000..e7f2e5e --- /dev/null +++ b/poetry.lock @@ -0,0 +1,193 @@ +# This file is automatically @generated by Poetry 1.4.2 and should not be changed by hand. + +[[package]] +name = "boto3" +version = "1.28.17" +description = "The AWS SDK for Python" +category = "main" +optional = false +python-versions = ">= 3.7" +files = [ + {file = "boto3-1.28.17-py3-none-any.whl", hash = "sha256:bca0526f819e0f19c0f1e6eba3e2d1d6b6a92a45129f98c0d716e5aab6d9444b"}, + {file = "boto3-1.28.17.tar.gz", hash = "sha256:90f7cfb5e1821af95b1fc084bc50e6c47fa3edc99f32de1a2591faa0c546bea7"}, +] + +[package.dependencies] +botocore = ">=1.31.17,<1.32.0" +jmespath = ">=0.7.1,<2.0.0" +s3transfer = ">=0.6.0,<0.7.0" + +[package.extras] +crt = ["botocore[crt] (>=1.21.0,<2.0a0)"] + +[[package]] +name = "botocore" +version = "1.31.17" +description = "Low-level, data-driven core of boto 3." +category = "main" +optional = false +python-versions = ">= 3.7" +files = [ + {file = "botocore-1.31.17-py3-none-any.whl", hash = "sha256:6ac34a1d34aa3750e78b77b8596617e2bab938964694d651939dba2cbde2c12b"}, + {file = "botocore-1.31.17.tar.gz", hash = "sha256:396459065dba4339eb4da4ec8b4e6599728eb89b7caaceea199e26f7d824a41c"}, +] + +[package.dependencies] +jmespath = ">=0.7.1,<2.0.0" +python-dateutil = ">=2.1,<3.0.0" +urllib3 = ">=1.25.4,<1.27" + +[package.extras] +crt = ["awscrt (==0.16.26)"] + +[[package]] +name = "jmespath" +version = "1.0.1" +description = "JSON Matching Expressions" +category = "main" +optional = false +python-versions = ">=3.7" +files = [ + {file = "jmespath-1.0.1-py3-none-any.whl", hash = "sha256:02e2e4cc71b5bcab88332eebf907519190dd9e6e82107fa7f83b1003a6252980"}, + {file = "jmespath-1.0.1.tar.gz", hash = "sha256:90261b206d6defd58fdd5e85f478bf633a2901798906be2ad389150c5c60edbe"}, +] + +[[package]] +name = "numpy" +version = "1.25.2" +description = "Fundamental package for array computing in Python" +category = "main" +optional = false +python-versions = ">=3.9" +files = [ + {file = "numpy-1.25.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:db3ccc4e37a6873045580d413fe79b68e47a681af8db2e046f1dacfa11f86eb3"}, + {file = "numpy-1.25.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:90319e4f002795ccfc9050110bbbaa16c944b1c37c0baeea43c5fb881693ae1f"}, + {file = "numpy-1.25.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dfe4a913e29b418d096e696ddd422d8a5d13ffba4ea91f9f60440a3b759b0187"}, + {file = "numpy-1.25.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f08f2e037bba04e707eebf4bc934f1972a315c883a9e0ebfa8a7756eabf9e357"}, + {file = "numpy-1.25.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:bec1e7213c7cb00d67093247f8c4db156fd03075f49876957dca4711306d39c9"}, + {file = "numpy-1.25.2-cp310-cp310-win32.whl", hash = "sha256:7dc869c0c75988e1c693d0e2d5b26034644399dd929bc049db55395b1379e044"}, + {file = "numpy-1.25.2-cp310-cp310-win_amd64.whl", hash = "sha256:834b386f2b8210dca38c71a6e0f4fd6922f7d3fcff935dbe3a570945acb1b545"}, + {file = "numpy-1.25.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c5462d19336db4560041517dbb7759c21d181a67cb01b36ca109b2ae37d32418"}, + {file = "numpy-1.25.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:c5652ea24d33585ea39eb6a6a15dac87a1206a692719ff45d53c5282e66d4a8f"}, + {file = "numpy-1.25.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0d60fbae8e0019865fc4784745814cff1c421df5afee233db6d88ab4f14655a2"}, + {file = "numpy-1.25.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:60e7f0f7f6d0eee8364b9a6304c2845b9c491ac706048c7e8cf47b83123b8dbf"}, + {file = "numpy-1.25.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:bb33d5a1cf360304754913a350edda36d5b8c5331a8237268c48f91253c3a364"}, + {file = "numpy-1.25.2-cp311-cp311-win32.whl", hash = "sha256:5883c06bb92f2e6c8181df7b39971a5fb436288db58b5a1c3967702d4278691d"}, + {file = "numpy-1.25.2-cp311-cp311-win_amd64.whl", hash = "sha256:5c97325a0ba6f9d041feb9390924614b60b99209a71a69c876f71052521d42a4"}, + {file = "numpy-1.25.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:b79e513d7aac42ae918db3ad1341a015488530d0bb2a6abcbdd10a3a829ccfd3"}, + {file = "numpy-1.25.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:eb942bfb6f84df5ce05dbf4b46673ffed0d3da59f13635ea9b926af3deb76926"}, + {file = "numpy-1.25.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e0746410e73384e70d286f93abf2520035250aad8c5714240b0492a7302fdca"}, + {file = "numpy-1.25.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d7806500e4f5bdd04095e849265e55de20d8cc4b661b038957354327f6d9b295"}, + {file = "numpy-1.25.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:8b77775f4b7df768967a7c8b3567e309f617dd5e99aeb886fa14dc1a0791141f"}, + {file = "numpy-1.25.2-cp39-cp39-win32.whl", hash = "sha256:2792d23d62ec51e50ce4d4b7d73de8f67a2fd3ea710dcbc8563a51a03fb07b01"}, + {file = "numpy-1.25.2-cp39-cp39-win_amd64.whl", hash = "sha256:76b4115d42a7dfc5d485d358728cdd8719be33cc5ec6ec08632a5d6fca2ed380"}, + {file = "numpy-1.25.2-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:1a1329e26f46230bf77b02cc19e900db9b52f398d6722ca853349a782d4cff55"}, + {file = "numpy-1.25.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4c3abc71e8b6edba80a01a52e66d83c5d14433cbcd26a40c329ec7ed09f37901"}, + {file = "numpy-1.25.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:1b9735c27cea5d995496f46a8b1cd7b408b3f34b6d50459d9ac8fe3a20cc17bf"}, + {file = "numpy-1.25.2.tar.gz", hash = "sha256:fd608e19c8d7c55021dffd43bfe5492fab8cc105cc8986f813f8c3c048b38760"}, +] + +[[package]] +name = "pyarrow" +version = "12.0.1" +description = "Python library for Apache Arrow" +category = "main" +optional = false +python-versions = ">=3.7" +files = [ + {file = "pyarrow-12.0.1-cp310-cp310-macosx_10_14_x86_64.whl", hash = "sha256:6d288029a94a9bb5407ceebdd7110ba398a00412c5b0155ee9813a40d246c5df"}, + {file = "pyarrow-12.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:345e1828efdbd9aa4d4de7d5676778aba384a2c3add896d995b23d368e60e5af"}, + {file = "pyarrow-12.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8d6009fdf8986332b2169314da482baed47ac053311c8934ac6651e614deacd6"}, + {file = "pyarrow-12.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2d3c4cbbf81e6dd23fe921bc91dc4619ea3b79bc58ef10bce0f49bdafb103daf"}, + {file = "pyarrow-12.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:cdacf515ec276709ac8042c7d9bd5be83b4f5f39c6c037a17a60d7ebfd92c890"}, + {file = "pyarrow-12.0.1-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:749be7fd2ff260683f9cc739cb862fb11be376de965a2a8ccbf2693b098db6c7"}, + {file = "pyarrow-12.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:6895b5fb74289d055c43db3af0de6e16b07586c45763cb5e558d38b86a91e3a7"}, + {file = "pyarrow-12.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1887bdae17ec3b4c046fcf19951e71b6a619f39fa674f9881216173566c8f718"}, + {file = "pyarrow-12.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e2c9cb8eeabbadf5fcfc3d1ddea616c7ce893db2ce4dcef0ac13b099ad7ca082"}, + {file = "pyarrow-12.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:ce4aebdf412bd0eeb800d8e47db854f9f9f7e2f5a0220440acf219ddfddd4f63"}, + {file = "pyarrow-12.0.1-cp37-cp37m-macosx_10_14_x86_64.whl", hash = "sha256:e0d8730c7f6e893f6db5d5b86eda42c0a130842d101992b581e2138e4d5663d3"}, + {file = "pyarrow-12.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:43364daec02f69fec89d2315f7fbfbeec956e0d991cbbef471681bd77875c40f"}, + {file = "pyarrow-12.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:051f9f5ccf585f12d7de836e50965b3c235542cc896959320d9776ab93f3b33d"}, + {file = "pyarrow-12.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:be2757e9275875d2a9c6e6052ac7957fbbfc7bc7370e4a036a9b893e96fedaba"}, + {file = "pyarrow-12.0.1-cp38-cp38-macosx_10_14_x86_64.whl", hash = "sha256:cf812306d66f40f69e684300f7af5111c11f6e0d89d6b733e05a3de44961529d"}, + {file = "pyarrow-12.0.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:459a1c0ed2d68671188b2118c63bac91eaef6fc150c77ddd8a583e3c795737bf"}, + {file = "pyarrow-12.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:85e705e33eaf666bbe508a16fd5ba27ca061e177916b7a317ba5a51bee43384c"}, + {file = "pyarrow-12.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9120c3eb2b1f6f516a3b7a9714ed860882d9ef98c4b17edcdc91d95b7528db60"}, + {file = "pyarrow-12.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:c780f4dc40460015d80fcd6a6140de80b615349ed68ef9adb653fe351778c9b3"}, + {file = "pyarrow-12.0.1-cp39-cp39-macosx_10_14_x86_64.whl", hash = "sha256:a3c63124fc26bf5f95f508f5d04e1ece8cc23a8b0af2a1e6ab2b1ec3fdc91b24"}, + {file = "pyarrow-12.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b13329f79fa4472324f8d32dc1b1216616d09bd1e77cfb13104dec5463632c36"}, + {file = "pyarrow-12.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bb656150d3d12ec1396f6dde542db1675a95c0cc8366d507347b0beed96e87ca"}, + {file = "pyarrow-12.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6251e38470da97a5b2e00de5c6a049149f7b2bd62f12fa5dbb9ac674119ba71a"}, + {file = "pyarrow-12.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:3de26da901216149ce086920547dfff5cd22818c9eab67ebc41e863a5883bac7"}, + {file = "pyarrow-12.0.1.tar.gz", hash = "sha256:cce317fc96e5b71107bf1f9f184d5e54e2bd14bbf3f9a3d62819961f0af86fec"}, +] + +[package.dependencies] +numpy = ">=1.16.6" + +[[package]] +name = "python-dateutil" +version = "2.8.2" +description = "Extensions to the standard Python datetime module" +category = "main" +optional = false +python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7" +files = [ + {file = "python-dateutil-2.8.2.tar.gz", hash = "sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86"}, + {file = "python_dateutil-2.8.2-py2.py3-none-any.whl", hash = "sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9"}, +] + +[package.dependencies] +six = ">=1.5" + +[[package]] +name = "s3transfer" +version = "0.6.1" +description = "An Amazon S3 Transfer Manager" +category = "main" +optional = false +python-versions = ">= 3.7" +files = [ + {file = "s3transfer-0.6.1-py3-none-any.whl", hash = "sha256:3c0da2d074bf35d6870ef157158641178a4204a6e689e82546083e31e0311346"}, + {file = "s3transfer-0.6.1.tar.gz", hash = "sha256:640bb492711f4c0c0905e1f62b6aaeb771881935ad27884852411f8e9cacbca9"}, +] + +[package.dependencies] +botocore = ">=1.12.36,<2.0a.0" + +[package.extras] +crt = ["botocore[crt] (>=1.20.29,<2.0a.0)"] + +[[package]] +name = "six" +version = "1.16.0" +description = "Python 2 and 3 compatibility utilities" +category = "main" +optional = false +python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*" +files = [ + {file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"}, + {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"}, +] + +[[package]] +name = "urllib3" +version = "1.26.16" +description = "HTTP library with thread-safe connection pooling, file post, and more." +category = "main" +optional = false +python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*" +files = [ + {file = "urllib3-1.26.16-py2.py3-none-any.whl", hash = "sha256:8d36afa7616d8ab714608411b4a3b13e58f463aee519024578e062e141dce20f"}, + {file = "urllib3-1.26.16.tar.gz", hash = "sha256:8f135f6502756bde6b2a9b28989df5fbe87c9970cecaa69041edcce7f0589b14"}, +] + +[package.extras] +brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"] +secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"] +socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"] + +[metadata] +lock-version = "2.0" +python-versions = ">3.9, <3.11" +content-hash = "0c8f0729d688bd03763f10ac9aec0c2749ca8d2175c8715bdc4c2d6de876b503" diff --git a/pyproject.toml b/pyproject.toml index a3cc7fb..62631c5 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,15 +1,6 @@ -[project] -name = "minerva" -version = "0.2.0" -description = "Easier access to AWS Athena and Redshift" -dependencies = [ - "boto3", - "pyarrow" -] - [tool.poetry] name = "minerva" -version = "0.2.0" +version = "0.2.1" description = "Easier access to AWS Athena and Redshift" authors = [ "Ari Brown " @@ -17,3 +8,9 @@ authors = [ packages = [ { include = "minerva/**/*.py"} ] +readme = "README.md" + +[tool.poetry.dependencies] +python = ">3.9, <3.11" +boto3 = "^1.26.161" +pyarrow = "^12.0.1"