STY: Configure linters and apply style cleanup

.github/linters/.cspell.json

@@ -0,0 +1,49 @@
+{
+    "version": "0.2",
+    "language": "en",
+    "ignorePaths": [
+        "**/.git/**",
+        "**/.gitignore",
+        "**/docs/Makefile",
+        "**/docs/make.bat",
+        "**/docs/source/conf.py",
+        "**/.mega-linter.yml"
+    ],
+    "words": [
+        "spherimatch",
+        "xmatch",
+        "quadtree",
+        "coor",
+        "radec",
+        "idxes",
+        "Rodrigues",
+        "numpy",
+        "allclose",
+        "arcsin",
+        "arctan",
+        "isscalar",
+        "linalg",
+        "ndarray",
+        "randn",
+        "rtol",
+        "setdiff",
+        "scipy",
+        "dataframe",
+        "groupby",
+        "inplace",
+        "multiindex",
+        "ipynb",
+        "pypa",
+        "pypi",
+        "MAINT",
+        "bibtex",
+        "howpublished",
+        "autoclass",
+        "autofunction",
+        "automodule",
+        "genindex",
+        "modindex",
+        "toctree",
+        "undoc"
+    ]
+}

.github/linters/.isort.cfg

@@ -0,0 +1,8 @@
+[settings]
+profile=
+line_length=120
+wrap_length=100
+lines_between_sections=0
+multi_line_output=3
+known_first_party=spherimatch
+treat_all_comments_as_code=true

.github/workflows/ci.yml

@@ -2,6 +2,7 @@ name: CI
 
 on:
   push:
+    branches: ["main"]
   pull_request:
     branches: ["main"]
   workflow_dispatch:
@@ -30,11 +31,10 @@ jobs:
 
       - name: MegaLinter
         id: ml
-        uses: oxsecurity/megalinter/flavors/python@v8.6.0
+        uses: oxsecurity/megalinter/flavors/python@v8
         env:
           VALIDATE_ALL_CODEBASE: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/main') || github.event_name == 'workflow_dispatch' }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          DISABLE_ERRORS_LINTERS: COPYPASTE_JSCPD
 
       - name: Archive production artifacts
         if: success() || failure()

.github/workflows/deploy-docs.yml

@@ -53,7 +53,7 @@ jobs:
     environment:
       name: github-pages
       url: ${{ steps.deployment.outputs.page_url }}
-      
+
     runs-on: ubuntu-latest
     steps:
       - name: Deploy to GitHub Pages

.github/workflows/publish-pypi.yml

@@ -28,14 +28,14 @@ jobs:
         run: |
           python -m pip install -r requirements.txt
           python -m pip install build
-          
+
       - name: Build release distributions
         run: python -m build
 
       - name: Upload distributions
         uses: actions/upload-artifact@v4
         with:
-          name: release-dists
+          name: release-dist
           path: dist/
 
   pypi-publish:
@@ -55,7 +55,7 @@ jobs:
       - name: Retrieve release distributions
         uses: actions/download-artifact@v4
         with:
-          name: release-dists
+          name: release-dist
           path: dist/
 
       - name: Publish to PyPI

.mega-linter.yml

@@ -0,0 +1,35 @@
+DISABLE:
+  - RST
+  - REPOSITORY
+DISABLE_LINTERS:
+  - JSON_PRETTIER
+  - YAML_PRETTIER
+  - PYTHON_PYRIGHT
+DISABLE_ERRORS_LINTERS:
+  - COPYPASTE_JSCPD
+  - PYTHON_MYPY
+  - REPOSITORY_CHECKOV
+  - REPOSITORY_GRYPE
+  - REPOSITORY_SECRETLINT
+  - REPOSITORY_SYFT
+  - REPOSITORY_TRIVY_SBOM
+  - REPOSITORY_TRUFFLEHOG
+ENABLE_ERRORS_LINTERS:
+  - PYTHON_ISORT
+
+MARKDOWN_MARKDOWNLINT_ARGUMENTS: --disable MD041
+PYTHON_BLACK_ARGUMENTS: --skip-string-normalization --line-length 120
+PYTHON_PYLINT_ARGUMENTS: --enable I0021
+
+PRE_COMMANDS:
+
+  - command: cp requirements.txt /venvs/requirements.txt
+    cwd: workspace
+    continue_if_failed: false
+
+  # Install dependencies for `pylint`
+  - command: python3 -m pip install --no-cache-dir -r /venvs/requirements.txt
+    venv: pylint
+    continue_if_failed: false
+
+REPORTERS_MARKDOWN_TYPE: simple

README.md

@@ -59,6 +59,6 @@ To cite spherimatch in your publication, please use the following BibTeX entry:
   note = {Accessed: YYYY-MM}
 }
 ```
-Addtionally, you may add a reference to `https://github.com/technic960183/spherimatch` in the footnote if suitable.
+Additionally, you may add a reference to `https://github.com/technic960183/spherimatch` in the footnote if suitable.
 
 If you publish a paper that uses `spherimatch`, please let me know. I would be happy to know how this package has been used in research.

docs/source/conf.py

@@ -1,5 +1,6 @@
 import os
 import sys
+
 sys.path.insert(0, os.path.abspath('../../'))
 
 # Configuration file for the Sphinx documentation builder.
@@ -18,11 +19,7 @@
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
 
-extensions = [
-    'sphinx.ext.autodoc',
-    'sphinx.ext.viewcode',
-    'sphinx.ext.napoleon'
-]
+extensions = ['sphinx.ext.autodoc', 'sphinx.ext.viewcode', 'sphinx.ext.napoleon']
 
 templates_path = ['_templates']
 exclude_patterns = ['build', 'Thumbs.db', '.DS_Store']

docs/source/dev/index.rst

@@ -9,15 +9,10 @@ please refer to the `API Reference <../ref/index.html>`_ or the `Tutorials <../t
 
    This section is not complete yet.
 
-.. toctree::
-   :maxdepth: 2
-
-   spherimatch
-
 To develop the project, clone the repository and install the project in editable mode.
 
 .. code-block:: console
-   
+
    $ git clone https://github.com/technic960183/spherimatch.git
    $ cd spherimatch
    $ pip install -e .[dev]
@@ -29,3 +24,8 @@ To test the project, run the following command.
    $ python -m unittest
 
 You should see ``OK (skipped=3)`` if all tests pass.
+
+.. toctree::
+   :maxdepth: 2
+
+   spherimatch

docs/source/tutorial/duplicates_removal.rst

@@ -12,10 +12,10 @@ First, let's create a mock catalog with duplicates:
     import pandas as pd
 
     # Create a mock catalog as a pandas DataFrame
-    catalog = pd.DataFrame([[80.894, 41.269, 1200], [120.689, -41.269, 1500], 
-                            [10.689, -41.269, 3600], [10.688, -41.270, 300], 
-                            [10.689, -41.270, 1800], [10.690, -41.269, 2400], 
-                            [120.690, -41.270, 900], [10.689, -41.269, 2700]], 
+    catalog = pd.DataFrame([[80.894, 41.269, 1200], [120.689, -41.269, 1500],
+                            [10.689, -41.269, 3600], [10.688, -41.270, 300],
+                            [10.689, -41.270, 1800], [10.690, -41.269, 2400],
+                            [120.690, -41.270, 900], [10.689, -41.269, 2700]],
                             columns=['ra', 'dec', 'exp_time'])
 
 Here, we actually only have 3 unique objects, but the catalog contains 8 entries and 5 of them are duplicates.
@@ -57,7 +57,7 @@ properties of your catalog. The ``'dup_num'`` column shows the number of duplica
 
 .. note::
     When there are two 'unique' objects that are very close to each other, it is possible that they will be grouped together.
-    In an exetrema case, it is possible that a chain of unique objects will be grouped together, linking by their duplicates.
+    In an extreme case, it is possible that a chain of unique objects will be grouped together, linking by their duplicates.
     But this is rare for most catalogs. To solve this problem, you can try to decrease the tolerance value. However, if
     decreasing the tolerance value separates objects that should be considered as duplicates, this package does not provide
     a solution for now. You may need to remove the duplicates manually for those close objects.

docs/source/tutorial/fof.rst

@@ -11,9 +11,9 @@ First, let's create a mock catalog:
     import pandas as pd
 
     # Create a mock catalog as a pandas DataFrame
-    catalog = pd.DataFrame([[80.894, 41.269, 15.5], [120.689, -41.269, 12.3], 
-                            [10.689, -41.269, 18.7], [10.688, -41.270, 14.1], 
-                            [10.689, -41.270, 16.4], [10.690, -41.269, 13.2], 
+    catalog = pd.DataFrame([[80.894, 41.269, 15.5], [120.689, -41.269, 12.3],
+                            [10.689, -41.269, 18.7], [10.688, -41.270, 14.1],
+                            [10.689, -41.270, 16.4], [10.690, -41.269, 13.2],
                             [120.690, -41.270, 17.8]], columns=['ra', 'dec', 'mag'])
 
 .. note::
@@ -36,7 +36,7 @@ The result object contains the clustering results. Four methods are available to
 get_group_dataframe()
 ---------------------
 
-To get the clustering results with the appendind data (``'mag'`` in this case), use the
+To get the clustering results with the appending data (``'mag'`` in this case), use the
 :func:`spherimatch.FoFResult.get_group_dataframe` method:
 
 .. code-block:: python
@@ -47,7 +47,7 @@ To get the clustering results with the appendind data (``'mag'`` in this case),
 Expected output::
 
                        Ra     Dec   mag
-    Group Object                       
+    Group Object
     0     0        80.894  41.269  15.5
     1     1       120.689 -41.269  12.3
           6       120.690 -41.270  17.8
@@ -72,20 +72,20 @@ Expected output::
     Print group 0:
     The type of group is <class 'pandas.core.frame.DataFrame'>.
                       Ra     Dec   mag
-    Group Object                      
+    Group Object
     0     0       80.894  41.269  15.5
 
     Print group 1:
     The type of group is <class 'pandas.core.frame.DataFrame'>.
                        Ra     Dec   mag
-    Group Object                       
+    Group Object
     1     1       120.689 -41.269  12.3
           6       120.690 -41.270  17.8
 
     Print group 2:
     The type of group is <class 'pandas.core.frame.DataFrame'>.
                       Ra     Dec   mag
-    Group Object                      
+    Group Object
     2     2       10.689 -41.269  18.7
           3       10.688 -41.270  14.1
           4       10.689 -41.270  16.4
@@ -94,8 +94,8 @@ Expected output::
 Each group is also a pandas DataFrame.
 
 .. note::
-    The iterater from ``groupby()`` is extremely slow for large datasets. The current solution is to flatten the
-    DataFrame into a single layer of index and manupulate the index directly, or even turn the DataFrame into a numpy array.
+    The iterator from ``groupby()`` is extremely slow for large datasets. The current solution is to flatten the
+    DataFrame into a single layer of index and manipulates the index directly, or even turn the DataFrame into a numpy array.
 
 If you want DataFrame with a single layer of index and the size of each group as a column, you can use the following code:
 
@@ -108,7 +108,7 @@ If you want DataFrame with a single layer of index and the size of each group as
 Expected output::
 
             Group       Ra     Dec   mag  group_size
-    Object                                          
+    Object
     0           0   80.894  41.269  15.5           1
     1           1  120.689 -41.269  12.3           2
     6           1  120.690 -41.270  17.8           2

docs/source/tutorial/input_validation.rst

@@ -16,7 +16,7 @@ The input DataFrame should have the following columns:
    - One of the ``['ra', 'Ra', 'RA']`` (Right Ascension) in degrees.
    - One of the ``['dec', 'Dec', 'DEC']`` (Declination) in degrees.
 
-Addtionally, the DataFrame can have any other columns as well. These columns will be preserved in the output.
+Additionally, the DataFrame can have any other columns as well. These columns will be preserved in the output.
 And the index of the DataFrame has no restrictions and will be preserved in the output as well. (MultiIndex is not supported for now.)
 
 numpy.ndarray
@@ -27,4 +27,4 @@ The input numpy array should be in the shape of (N, 2), where N is the number of
    - The first column (``data[:, 0]``) should be the Right Ascension in degrees.
    - The second column (``data[:, 1]``) should be the Declination in degrees.
 
-Addtional data columns are not supported in the numpy array format for now.
+Additional data columns are not supported in the numpy array format for now.

docs/source/tutorial/xmatch.rst

@@ -23,7 +23,7 @@ xmatch()
 Then, we can perform the cross-matching with the tolerance of 0.01 degree using the :func:`spherimatch.xmatch` function.
 
 .. code-block:: python
-    
+
     from spherimatch import xmatch
     result_object = xmatch(catalogA, catalogB, tolerance=0.01)
 
@@ -39,7 +39,7 @@ To get the matching results of catalog A, use the :func:`spherimatch.XMatchResul
     print(result_object.get_dataframe1())
 
 Expected output::
-    
+
             Ra     Dec  N_match
     0   80.894  41.269        0
     1  120.689 -41.269        1

spherimatch/__init__.py

@@ -1,10 +1,4 @@
-from .chunk_generator_grid import GridChunkGenerator, GridChunkConfig
-from .chunk_generator_grid import ChunkGeneratorByGrid, ChunkGeneratorByDenseGrid, ChunkGeneratorBySuperDenseGrid
-from .disjoint_set import DisjointSet
 from .fof import fof, group_by_quadtree
-from .result_fof import FoFResult
-from .result_xmatch import XMatchResult
-from .utilities_spherical import *
 from .xmatch import xmatch
 
 __all__ = ['fof', 'group_by_quadtree', 'xmatch']