Merge pull request #5186 from bjlittle/codespell

Adopt codespell

.git-blame-ignore-revs

@@ -1,2 +1,20 @@
 # Format: numpy array format (#5235)
 c18dcd8dafef0cc7bbbf80dfce66f76a46ce59c5
+
+# style: flake8 (#3755)
+7c86bc0168684345dc475457b1a77dadc77ce9bb
+
+# style: black (#3518)
+ffcfad475e0593e1e40895453cf1df154e5f6f2c
+
+# style: isort (#4174)
+15bbcc5ac3d539cb6e820148b66e7cf55d91c5d2
+
+# style: blacken-docs (#4205)
+1572e180243e492d8ff76fa8cdefb82ef6f90415
+
+# style: sort-all (#4353)
+64705dbc40881233aae45f051d96049150369e53
+
+# style: codespell (#5186)
+417aa6bbd9b10d25cad7def54d47ef4d718bc38d

.pre-commit-config.yaml

@@ -28,6 +28,13 @@ repos:
         # Don't commit to main branch.
     -   id: no-commit-to-branch
 
+-   repo: https://github.com/codespell-project/codespell
+    rev: "v2.2.2"
+    hooks:
+    -   id: codespell
+        types_or: [asciidoc, python, markdown, rst]
+        additional_dependencies: [tomli]
+
 -   repo: https://github.com/psf/black
     rev: 23.3.0
     hooks:

benchmarks/benchmarks/experimental/ugrid/regions_combine.py

@@ -50,7 +50,7 @@ def _make_region_cubes(self, full_mesh_cube):
         i_faces = np.concatenate([i_faces[:, 2:], i_faces[:, :2]], axis=1)
         # flatten to get [2 3 4 0 1 (-) 8 9 10 6 7 (-) 13 14 15 11 12 ...]
         i_faces = i_faces.flatten()
-        # reduce back to orignal length, wrap any overflows into valid range
+        # reduce back to original length, wrap any overflows into valid range
         i_faces = i_faces[:n_faces] % n_faces
 
         # Divide into regions -- always slightly uneven, since 7 doesn't divide

benchmarks/benchmarks/sperf/combine_regions.py

@@ -46,7 +46,7 @@ def _make_region_cubes(self, full_mesh_cube):
         i_faces = np.concatenate([i_faces[:, 2:], i_faces[:, :2]], axis=1)
         # flatten to get [2 3 4 0 1 (-) 8 9 10 6 7 (-) 13 14 15 11 12 ...]
         i_faces = i_faces.flatten()
-        # reduce back to orignal length, wrap any overflows into valid range
+        # reduce back to original length, wrap any overflows into valid range
         i_faces = i_faces[:n_faces] % n_faces
 
         # Divide into regions -- always slightly uneven, since 7 doesn't divide

codecov.yml

@@ -6,4 +6,4 @@ coverage:
         target: auto
         # coverage can drop by up to <threshold>% while still posting success
         threshold: 3%
-    patch: off
+    patch: off

docs/gallery_code/general/plot_projections_and_annotations.py

@@ -78,7 +78,7 @@ def make_plot(projection_name, projection_crs):
     y_points = y_lower + y_delta * np.concatenate(
         (zeros, steps, ones, steps[::-1])
     )
-    # Get the Iris coordinate sytem of the X coordinate (Y should be the same).
+    # Get the Iris coordinate system of the X coordinate (Y should be the same).
     cs_data1 = x_coord.coord_system
     # Construct an equivalent Cartopy coordinate reference system ("crs").
     crs_data1 = cs_data1.as_cartopy_crs()

docs/gallery_code/general/plot_rotated_pole_mapping.py

@@ -40,7 +40,7 @@ def main():
     plt.gca().coastlines()
     iplt.show()
 
-    # Plot #3: Contourf overlayed by coloured point data
+    # Plot #3: Contourf overlaid by coloured point data
     plt.figure()
     qplt.contourf(air_pressure)
     iplt.points(air_pressure, c=air_pressure.data)

docs/gallery_code/meteorology/plot_lagged_ensemble.py

@@ -115,7 +115,7 @@ def main():
     # Get the time for the entire plot.
     time = last_time_coord.units.num2date(last_time_coord.bounds[0, 0])
 
-    # Set a global title for the postage stamps with the date formated by
+    # Set a global title for the postage stamps with the date formatted by
     # "monthname year".
     time_string = time.strftime("%B %Y")
     plt.suptitle(f"Surface temperature ensemble forecasts for {time_string}")

docs/src/IEP/IEP001.adoc

@@ -119,7 +119,7 @@ cube.sel(height=1.5)
 
 The semantics of position-based slices will continue to match that of normal Python slices. The start position is included, the end position is excluded.
 
-Value-based slices will be stricly inclusive, with both the start and end values included. This behaviour differs from normal Python slices but is in common with pandas.
+Value-based slices will be strictly inclusive, with both the start and end values included. This behaviour differs from normal Python slices but is in common with pandas.
 
 Just as for normal Python slices, we do not need to provide the ability to control the include/exclude behaviour for slicing.
 

docs/src/common_links.inc

@@ -6,6 +6,7 @@
 .. _flake8: https://flake8.pycqa.org/en/stable/
 .. _.flake8.yml: https://github.com/SciTools/iris/blob/main/.flake8
 .. _cirrus-ci: https://cirrus-ci.com/github/SciTools/iris
+.. _codespell: https://github.com/codespell-project/codespell
 .. _conda: https://docs.conda.io/en/latest/
 .. _contributor: https://github.com/SciTools/scitools.org.uk/blob/master/contributors.json
 .. _core developers: https://github.com/SciTools/scitools.org.uk/blob/master/contributors.json

docs/src/community/iris_xarray.rst

@@ -11,7 +11,7 @@ you can be prepared, and to help you choose the best package for your use case.
 Overall Experience
 ------------------
 
-Iris is the more specialised package, focussed on making it as easy
+Iris is the more specialised package, focused on making it as easy
 as possible to work with meteorological and climatological data. Iris
 is built to natively handle many key concepts, such as the CF conventions,
 coordinate systems and bounded coordinates. Iris offers a smaller toolkit of

docs/src/conf.py

@@ -81,7 +81,7 @@ def autolog(message):
 # add some sample files from the developers guide..
 sys.path.append(os.path.abspath(os.path.join("developers_guide")))
 
-# why isnt the iris path added to it is discoverable too?  We dont need to,
+# why isn't the iris path added to it is discoverable too?  We dont need to,
 # the sphinext to generate the api rst knows where the source is.  If it
 # is added then the travis build will likely fail.
 

docs/src/developers_guide/contributing_ci_tests.rst

@@ -117,6 +117,14 @@ pull-requests given the `Iris`_ GitHub repository `.pre-commit-config.yaml`_.
 
 See the `pre-commit.ci dashboard`_ for details of recent past and active Iris jobs.
 
+.. note::
+
+  The `codespell`_ ``pre-commit`` hook checks the spelling of the whole codebase
+  and documentation.  This hook is configured in the ``[tool.codespell]`` section
+  of the ``pyproject.toml`` file.
+
+  Append to the ``ignore-words-list`` option any **valid words** that are
+  considered **not** a typo and should **not** be corrected by `codespell`_.
 
 .. _.pre-commit-config.yaml: https://github.com/SciTools/iris/blob/main/.pre-commit-config.yaml
 .. _pre-commit.ci dashboard: https://results.pre-commit.ci/repo/github/5312648

docs/src/developers_guide/gitwash/configure_git.rst

@@ -144,7 +144,7 @@ and it gives graph / text output something like this (but with color!)::
     | * 4aff2a8 - fixed bug 35, and added a test in test_bugfixes (2 weeks ago) [Hugo]
     |/
     * a7ff2e5 - Added notes on discussion/proposal made during Data Array Summit. (2 weeks ago) [Corran Webster]
-    * 68f6752 - Initial implimentation of AxisIndexer - uses 'index_by' which needs to be changed to a call on an Axes object - this is all very sketchy right now. (2 weeks ago) [Corr
+    * 68f6752 - Initial implementation of AxisIndexer - uses 'index_by' which needs to be changed to a call on an Axes object - this is all very sketchy right now. (2 weeks ago) [Corr
     *   376adbd - Merge pull request #46 from terhorst/main (2 weeks ago) [Jonathan Terhorst]
     |\
     | * b605216 - updated joshu example to current api (3 weeks ago) [Jonathan Terhorst]

docs/src/developers_guide/release.rst

@@ -173,7 +173,7 @@ Ensure that the artifacts are successfully uploaded and available on
 from PyPI::
 
     > conda deactivate
-    > conda env create --file ./requrements/ci/iris.yml
+    > conda env create --file ./requirements/iris.yml
     > . activate iris-dev
     > python -m pip install --no-deps scitools-iris
 

docs/src/further_topics/ugrid/operations.rst

@@ -897,7 +897,7 @@ previously initialised regridder:
 
     .. code-block:: python
 
-        # Extract a different cube defined on te same Mesh.
+        # Extract a different cube defined on the same Mesh.
         >>> mesh_cube2 = mesh_cubes.extract_cube("precipitation_flux")
         >>> print(mesh_cube2)
         precipitation_flux / (kg m-2 s-1)   (-- : 1; -- : 13824)

docs/src/userguide/plotting_examples/1d_with_legend.py

@@ -31,7 +31,7 @@
 plt.grid(True)
 
 # Provide some axis labels
-plt.ylabel("Temerature / kelvin")
+plt.ylabel("Temperature / kelvin")
 plt.xlabel("Longitude / degrees")
 
 # And a sensible title

docs/src/whatsnew/1.7.rst

@@ -21,14 +21,14 @@ Features
     transparent; for example, before the introduction of biggus, MemoryErrors
     were likely for very large datasets::
 
-        >>> result = extremely_large_cube.collapsed('time', iris.analyis.MEAN)
+        >>> result = extremely_large_cube.collapsed('time', iris.analysis.MEAN)
         MemoryError
 
     Now, for supported operations, the evaluation is lazy (i.e. it doesn't take
     place until the actual data is subsequently requested) and can handle data
     larger than available system memory::
 
-        >>> result = extremely_large_cube.collapsed('time', iris.analyis.MEAN)
+        >>> result = extremely_large_cube.collapsed('time', iris.analysis.MEAN)
         >>> print(type(result))
         <class 'iris.cube.Cube'>
 

docs/src/whatsnew/2.0.rst

@@ -36,7 +36,7 @@ Features
   * The *new* in-place arithmetic operators :data:`__iadd__`, :data:`__idiv__`,
     :data:`__imul__`, :data:`__isub__`, and :data:`__itruediv__` have been
     added to support :class:`~iris.cube.Cube` operations :data:`+=`,
-    :data:`/=`, :data:`*=`, and :data:`-=`. Note that, for **divison**
+    :data:`/=`, :data:`*=`, and :data:`-=`. Note that, for **division**
     *__future__.division* is always in effect.
 
 * Changes to the :class:`iris.coords.Coord`:

docs/src/whatsnew/3.0.rst

@@ -142,7 +142,7 @@ v3.0.4 (22 July 2021)
       Firstly, ancillary-variables or cell-measures with long names can now widen the cube "dimensions map" to fit,
       whereas previously printing these cases caused an Exception.
       Secondly, cube units are now always printed, whereas previously they were missed out any time that the
-      "dimensions map" was widened to accomodate long coordinate names.
+      "dimensions map" was widened to accommodate long coordinate names.
       (:pull:`4233`)(:pull:`4238`)
 
    💼 **Internal**

docs/src/whatsnew/3.2.rst

@@ -167,7 +167,7 @@ v3.2.1 (11 Mar 2022)
    as well as some long-standing bugs with vertical coordinates and number
    formats. (:pull:`4411`)
 
-#. `@rcomer`_ fixed :meth:`~iris.cube.Cube.subset` to alway return ``None`` if
+#. `@rcomer`_ fixed :meth:`~iris.cube.Cube.subset` to always return ``None`` if
    no value match is found.  (:pull:`4417`)
 
 #. `@wjbenfold`_ changed :meth:`iris.util.points_step` to stop it from warning

docs/src/whatsnew/3.5.rst

@@ -45,7 +45,7 @@ This document explains the changes made to Iris for this release
    :ref:`documentation page<community_plugins>` for further information.
    (:pull:`5144`)
 
-#. `@rcomer`_ enabled lazy evaluation of :obj:`~iris.analysis.RMS` calcuations
+#. `@rcomer`_ enabled lazy evaluation of :obj:`~iris.analysis.RMS` calculations
    with weights. (:pull:`5017`)
 
 #. `@schlunma`_ allowed the usage of cubes, coordinates, cell measures, or

docs/src/whatsnew/latest.rst

@@ -20,6 +20,7 @@ This document explains the changes made to Iris for this release
    And finally, get in touch with us on :issue:`GitHub<new/choose>` if you have
    any issues or feature requests for improving Iris. Enjoy!
 
+
 📢 Announcements
 ================
 
@@ -68,10 +69,12 @@ This document explains the changes made to Iris for this release
 #. `@tkknight`_ migrated to `sphinx-design`_ over the legacy `sphinx-panels`_.
    (:pull:`5127`)
 
+
 💼 Internal
 ===========
 
-#. N/A
+#. `@bjlittle`_ added the `codespell`_ `pre-commit`_ ``git-hook`` to automate
+   spell checking within the code-base. (:pull:`5186`)
 
 
 .. comment
@@ -85,4 +88,4 @@ This document explains the changes made to Iris for this release
     Whatsnew resources in alphabetical order:
 
 .. _sphinx-panels: https://github.com/executablebooks/sphinx-panels
-.. _sphinx-design: https://github.com/executablebooks/sphinx-design
+.. _sphinx-design: https://github.com/executablebooks/sphinx-design

lib/iris/_concatenate.py

@@ -22,7 +22,7 @@
 #
 #   * Cope with auxiliary coordinate factories.
 #
-#   * Allow concatentation over a user specified dimension.
+#   * Allow concatenation over a user specified dimension.
 #
 
 

lib/iris/_merge.py

@@ -298,7 +298,7 @@ class _CoordSignature(
 ):
     """
     Criterion for identifying a specific type of :class:`iris.cube.Cube`
-    based on its scalar and vector coorinate data and metadata, and
+    based on its scalar and vector coordinate data and metadata, and
     auxiliary coordinate factories.
 
     Args:
@@ -516,7 +516,7 @@ class _Relation(namedtuple("Relation", ["separable", "inseparable"])):
     * separable:
         A set of independent candidate dimension names.
 
-    * inseperable:
+    * inseparable:
         A set of dependent candidate dimension names.
 
     """
@@ -1419,7 +1419,7 @@ def _define_space(self, space, positions, indexes, function_matrix):
 
         """
 
-        # Heuristic reordering of coordinate defintion indexes into
+        # Heuristic reordering of coordinate definition indexes into
         # preferred dimension order.
         def axis_and_name(name):
             axis_dict = {"T": 1, "Z": 2, "Y": 3, "X": 4}
@@ -1467,7 +1467,7 @@ def axis_and_name(name):
                     }
                 else:
                     # TODO: Consider appropriate sort order (ascending,
-                    # decending) i.e. use CF positive attribute.
+                    # descending) i.e. use CF positive attribute.
                     cells = sorted(indexes[name])
                     points = np.array(
                         [cell.point for cell in cells],

lib/iris/analysis/_area_weighted.py

@@ -433,7 +433,7 @@ def _spherical_area(y_bounds, x_bounds, radius=1.0):
     Args:
 
     * y_bounds:
-        An (n, 2) shaped NumPy array of latitide bounds in radians.
+        An (n, 2) shaped NumPy array of latitude bounds in radians.
     * x_bounds:
         An (m, 2) shaped NumPy array of longitude bounds in radians.
     * radius:
@@ -586,7 +586,7 @@ def _regrid_area_weighted_array(
     y_dim = src_data.ndim - 2
 
     # Create empty "pre-averaging" data array that will enable the
-    # src_data data coresponding to a given target grid point,
+    # src_data data corresponding to a given target grid point,
     # to be stacked per point.
     # Note that dtype is not preserved and that the array mask
     # allows for regions that do not overlap.

lib/iris/analysis/_interpolation.py

@@ -213,7 +213,7 @@ def __init__(self, src_cube, coords, method, extrapolation_mode):
         # Trigger any deferred loading of the source cube's data and snapshot
         # its state to ensure that the interpolator is impervious to external
         # changes to the original source cube. The data is loaded to prevent
-        # the snaphot having lazy data, avoiding the potential for the
+        # the snapshot having lazy data, avoiding the potential for the
         # same data to be loaded again and again.
         if src_cube.has_lazy_data():
             src_cube.data

lib/iris/analysis/_regrid.py

@@ -239,7 +239,7 @@ def _regrid_indices(cells, depth, points):
     x_indices = _regrid_indices(tx_cells, tx_depth, sx_points)
     y_indices = _regrid_indices(ty_cells, ty_depth, sy_points)
 
-    # Now construct a sparse M x N matix, where M is the flattened target
+    # Now construct a sparse M x N matrix, where M is the flattened target
     # space, and N is the flattened source space. The sparse matrix will then
     # be populated with those source cube points that contribute to a specific
     # target cube cell.
@@ -1021,7 +1021,7 @@ def _create_cube(
         The dimensions of the X and Y coordinate within the source Cube.
     tgt_coords : tuple of :class:`iris.coords.Coord`\\ 's
         Either two 1D :class:`iris.coords.DimCoord`\\ 's, two 1D
-        :class:`iris.experimental.ugrid.DimCoord`\\ 's or two ND
+        :class:`iris.experimental.ugrid.DimCoord`\\ 's or two n-D
         :class:`iris.coords.AuxCoord`\\ 's representing the new grid's
         X and Y coordinates.
     num_tgt_dims : int

lib/iris/analysis/cartography.py

@@ -1013,7 +1013,7 @@ def _transform_distance_vectors_tolerance_mask(
     """
     Return a mask that can be applied to data array to mask elements
     where the magnitude of vectors are not preserved due to numerical
-    errors introduced by the tranformation between coordinate systems.
+    errors introduced by the transformation between coordinate systems.
 
     Args:
     * src_crs (`cartopy.crs.Projection`):

lib/iris/analysis/trajectory.py

@@ -347,7 +347,7 @@ def interpolate(cube, sample_points, method=None):
         for columns_coord in columns.dim_coords + columns.aux_coords:
             src_dims = cube.coord_dims(columns_coord)
             if not squish_my_dims.isdisjoint(src_dims):
-                # Mapping the cube indicies onto the coord
+                # Mapping the cube indices onto the coord
                 initial_coord_inds = [initial_inds[ind] for ind in src_dims]
                 # Making the final ones the same way as for the cube
                 # 0 will always appear in the initial ones because we know this
@@ -660,7 +660,7 @@ def _nearest_neighbour_indices_ndcoords(cube, sample_points, cache=None):
             for c, (coord, coord_dims) in enumerate(
                 sample_space_coords_and_dims
             ):
-                # Index of this datum along this coordinate (could be nD).
+                # Index of this datum along this coordinate (could be n-D).
                 if coord_dims:
                     keys = tuple(ndi[ind] for ind in coord_dims)
                 else:

lib/iris/common/metadata.py

@@ -52,7 +52,7 @@
 
 def hexdigest(item):
     """
-    Calculate a hexidecimal string hash representation of the provided item.
+    Calculate a hexadecimal string hash representation of the provided item.
 
     Calculates a 64-bit non-cryptographic hash of the provided item, using
     the extremely fast ``xxhash`` hashing algorithm, and returns the hexdigest
@@ -67,7 +67,7 @@ def hexdigest(item):
         The item that requires to have its hexdigest calculated.
 
     Returns:
-        The string hexidecimal representation of the item's 64-bit hash.
+        The string hexadecimal representation of the item's 64-bit hash.
 
     """
     # Special case: deal with numpy arrays.