Initial packaging effort

Author: kaaveland

.gitignore

@@ -0,0 +1,115 @@
+# Dask
+dask-worker-space
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+pip-wheel-metadata/
+
+# 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/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# dotenv
+.env
+
+# virtualenv
+.venv
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+# jetbrains ide stuff
+*.iml
+.idea/
+
+# vscode ide stuff
+*.code-workspace
+.history
+.vscode

LICENSE.txt

@@ -0,0 +1,7 @@
+Copyright 2020 Robin Kåveland
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

MANIFEST.in

@@ -0,0 +1,2 @@
+include *.txt
+include *.md

README.md

@@ -0,0 +1,87 @@
+pyarrowfs-adlgen2
+==
+
+pyarrowfs-adlgen2 is an implementation of a pyarrow filesystem for Azure Data Lake Gen2.
+
+It allows you to use pyarrow and pandas to read parquet datasets directly from Azure without the need to copy files to local storage first.
+
+Reading datasets
+--
+
+Example usage with pandas dataframe:
+
+```python
+import azure.identity
+import pandas as pd
+import pyarrow.fs
+import pyarrowfs_adlgen2
+
+handler = pyarrowfs_adlgen2.AccountHandler.from_account_name(
+    'YOUR_ACCOUNT_NAME', azure.identity.DefaultAzureCredential())
+fs = pyarrow.fs.PyFileSystem(handler)
+df = pd.read_parquet('container/dataset.parq', filesystem=fs)
+```
+
+Example usage with arrow tables:
+
+```python
+import azure.identity
+import pyarrow.dataset
+import pyarrow.fs
+import pyarrowfs_adlgen2
+
+handler = pyarrowfs_adlgen2.AccountHandler.from_account_name(
+    'YOUR_ACCOUNT_NAME', azure.identity.DefaultAzureCredential())
+fs = pyarrow.fs.PyFileSystem(handler)
+ds = pyarrow.dataset.dataset('container/dataset.parq', filesystem=fs)
+table = ds.to_table()
+```
+
+Writing datasets
+--
+
+As of pyarrow version 1.0.1, `pyarrow.parquet.ParquetWriter` does not support `pyarrow.fs.PyFileSystem`, but data can be written to open files:
+
+```python
+with fs.open_output_stream('container/out.parq') as out:
+    df.to_parquet(out) 
+```
+
+Or with arrow tables:
+
+```python
+import pyarrow.parquet
+
+with fs.open_output_stream('container/out.parq') as out:
+    pyarrow.parquet.write_table(table, out)
+```
+
+Accessing only a single container/file-system
+--
+
+If you do not want, or can't access the whole storage account as a single filesystem, you can use `adlgen2fs.FileSystemHandler` to view a single file system within an account:
+
+```python
+import azure.identity
+import pyarrowfs_adlgen2
+
+handler = pyarrowfs_adlgen2.FileSystemHandler.from_account_name(
+   "STORAGE_ACCOUNT", "FS_NAME", azure.identity.DefaultAzureCredential())
+```
+
+All access is done through the file system within the storage account.
+
+Running tests
+--
+
+To run the tests, you need:
+
+- Azure Storage Account V2 with hierarchial namespace enabled (Data Lake gen2 account)
+- To configure azure login (f. ex. use `$ az login`)
+- Install pytest, f. ex. `pip install pytest`
+
+**NB! All data in the storage account is deleted during testing, USE AN EMPTY ACCOUNT**
+
+```
+AZUREARROWFS_TEST_ACT=thestorageaccount pytest
+```

pyarrowfs_adlgen2/__init__.py

@@ -0,0 +1,2 @@
+from .core import FilesystemHandler, AccountHandler
+