Add CI / CD github workflow (#11)

* add pre-commit with black, flake8 and refactor code
* fix bugs and move contrib out of main package
* update makefile and github ci workflow
* bump version

.github/actions/install/action.yml

@@ -0,0 +1,21 @@
+name: "install"
+description: "install requirements"
+
+inputs:
+  python-version:
+    required: false
+    description: "python version"
+    default: "3.10"
+outputs: {}
+runs:
+  using: "composite"
+  steps:
+    - uses: actions/setup-python@v4
+      with:
+        python-version: ${{inputs.python-version}}
+    - name: install requirements
+      run: pip install -r requirements.txt
+      shell: bash
+    - name: install package
+      run: pip install .
+      shell: bash

.github/workflows/ci.yml

@@ -0,0 +1,33 @@
+name: ci
+
+on:
+  pull_request:
+  push:
+    branches:
+      - "**"
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code repository
+        uses: actions/checkout@v4
+      - name: Install dependencies
+        uses: ./.github/actions/install
+      - name: Run pre-commit
+        run: pre-commit run --all-files
+
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10"]
+    steps:
+      - name: Checkout code repository
+        uses: actions/checkout@v4
+      - name: Install dependencies
+        uses: ./.github/actions/install
+      - name: Run unit tests
+        run: pytest
+        env:
+          python-version: ${{ matrix.python-version }}

.pre-commit-config.yaml

@@ -0,0 +1,27 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.0.1
+    hooks:
+      - id: check-ast
+      - id: check-added-large-files
+      - id: check-merge-conflict
+      - id: check-case-conflict
+      - id: check-docstring-first
+      - id: check-json
+      - id: check-yaml
+      - id: debug-statements
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+      - id: mixed-line-ending
+-   repo: local
+    hooks:
+      - id: black
+        name: black
+        entry: black .
+        language: system
+        types: [python]
+      - id: flake8
+        name: flake8
+        entry: flake8 eparse tests
+        language: system
+        types: [python]

LICENSE

@@ -19,4 +19,3 @@ 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.
-

Makefile

@@ -1,4 +1,4 @@
-.PHONY: clean clean-build clean-pyc clean-test coverage dist docs help install lint lint/flake8 lint/black
+.PHONY: clean clean-build clean-pyc clean-test coverage dist docs help install lint lint/black lint/flake8 pre-commit test test-all
 .DEFAULT_GOAL := help
 
 define BROWSER_PYSCRIPT
@@ -47,12 +47,16 @@ clean-test: ## remove test and coverage artifacts
 	rm -fr htmlcov/
 	rm -fr .pytest_cache
 
+lint/black: ## check style with black
+	black --diff eparse tests
+
 lint/flake8: ## check style with flake8
 	flake8 eparse tests
-lint/black: ## check style with black
-	black --check -S eparse tests
 
-lint: lint/flake8 lint/black ## check style
+lint: lint/black lint/flake8 ## check style
+
+pre-commit: ## run pre-commit on all files
+	pre-commit run --all-files
 
 test: ## run tests quickly with the default Python
 	pytest

README.rst

@@ -361,6 +361,45 @@ If you would like to use eparse to partition xls[x] files alongside unstructured
 Valid `eparse_mode` settings are available in `eparse.contrib.unstructured.xlsx._eparse_modes`.
 
 
+Development
+===========
+Clone the repo:
+
+.. code-block::
+
+    $ git clone https://github.com/ChrisPappalardo/eparse.git
+
+Install devtest requirements and the package in editable mode:
+
+.. code-block::
+
+    $ pip install -r requirements.txt
+    $ pip install -e .
+
+Run unit tests:
+
+.. code-block::
+
+    $ make test
+
+Run the linter:
+
+.. code-block::
+
+    $ make lint
+
+Install pre-commit:
+
+.. code-block::
+
+    $ pre-commit install
+
+Run pre-commit:
+
+.. code-block::
+
+    $
+
 Contributing
 ============
 As an open-source project, contributions are always welcome. Please see `Contributing <CONTRIBUTING.rst>`_ for more information.

conftest.py

@@ -1,25 +1,21 @@
 # -*- coding: utf-8 -*-
 
-'''
+"""
 unit test fixtures
-'''
-
-import pytest
+"""
 
 import pandas as pd
+import pytest
 from peewee import SqliteDatabase
 
-from eparse.interfaces import (
-    DATABASE,
-    ExcelParse,
-)
+from eparse.interfaces import DATABASE, ExcelParse
 
 
 @pytest.fixture
 def ctx():
-    '''
+    """
     click style ctx object fixture
-    '''
+    """
 
     class Obj:
         obj = {}
@@ -29,31 +25,31 @@ class Obj:
 
 @pytest.fixture
 def data():
-    '''
+    """
     serialized data fixture
-    '''
+    """
 
     return dict(
         row=0,
         column=0,
-        value='test',
-        type='test',
-        c_header='test',
-        r_header='test',
-        excel_RC='A1',
-        name='test',
-        sheet='test',
-        f_name='test',
+        value="test",
+        type="test",
+        c_header="test",
+        r_header="test",
+        excel_RC="A1",
+        name="test",
+        sheet="test",
+        f_name="test",
     )
 
 
 @pytest.fixture
 def sqlite3_db(data):
-    '''
+    """
     sqlite3 in-memory database fixture
-    '''
+    """
 
-    db = ':memory:'
+    db = ":memory:"
     DATABASE.initialize(SqliteDatabase(db))
     DATABASE.connect()
     DATABASE.create_tables([ExcelParse])
@@ -65,12 +61,12 @@ def sqlite3_db(data):
 
 @pytest.fixture
 def xlsx():
-    '''
+    """
     excel file fixture
-    '''
+    """
 
     return pd.read_excel(
-        'tests/eparse_unit_test_data.xlsx',
+        "tests/eparse_unit_test_data.xlsx",
         header=None,
         index_col=None,
     )

eparse/contrib/unstructured/xlsx.py → contrib/unstructured/xlsx.py

@@ -3,13 +3,7 @@
 from tempfile import SpooledTemporaryFile
 from typing import IO, BinaryIO, List, Optional, Union, cast
 
-from eparse.core import (
-    df_serialize_table,
-    get_df_from_file,
-    get_table_digest,
-)
 import lxml.html
-
 from unstructured.documents.elements import (
     DataSourceMetadata,
     Element,
@@ -25,12 +19,13 @@
     spooled_to_bytes_io_if_needed,
 )
 
+from eparse.core import df_serialize_table, get_df_from_file, get_table_digest
 
 _eparse_modes = (
-    'eparse',
-    'digest',
-    'table-digest',
-    'unstructured',
+    "eparse",
+    "digest",
+    "table-digest",
+    "unstructured",
 )