Codespell: adding config, workflow and fixing some typos

.codespellrc

@@ -0,0 +1,4 @@
+[codespell]
+skip = .git,*.pdf,*.svg,venvs,versioneer.py,_version.py,.tox
+# mke -- is a variable name which makes sense, let's ignore for now until inline skips are supported
+ignore-words-list = mke

.github/workflows/codespell.yml

@@ -0,0 +1,19 @@
+---
+name: Codespell
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+jobs:
+  codespell:
+    name: Check for spelling errors
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v1

Makefile

@@ -1,4 +1,4 @@
-# simple makefile to simplify repetetive build env management tasks under posix
+# simple makefile to simplify repetitive build env management tasks under posix
 # Ideas borrowed from scikit-learn's and PyMVPA Makefiles  -- thanks!
 
 PYTHON ?= python

_datalad_buildsupport/formatters.py

@@ -75,7 +75,7 @@ def _mk_title(self, prog):
 
     def _mk_name(self, prog, desc):
         """
-        this method is in consitent with others ... it relies on
+        this method is in consistent with others ... it relies on
         distribution
         """
         desc = desc.splitlines()[0] if desc else 'it is in the name'

datalad_metalad/__init__.py

@@ -78,7 +78,7 @@ def get_file_id(rec):
 
     Any ID string is prefixed with 'datalad:' to identify it as a
     DataLad-recognized ID. This prefix is defined in the main JSON-LD
-    context defintion.
+    context definition.
     """
     from datalad.support.digests import Digester
 

datalad_metalad/aggregate.py

@@ -397,7 +397,7 @@ def copy_to_existing(destination_metadata_store: str,
     #  object, we have to read in the object after copying it
     #  only, to write it out again. This is wasteful. We should
     #  instead specify that the top-level object, here: the
-    #  DatasetTree, is not writen out.
+    #  DatasetTree, is not written out.
     copied_dataset_tree.read_in()
 
     root_dataset_tree.add_subtree(
@@ -498,7 +498,7 @@ def copy_tree_version_list(destination_metadata_store: str,
                 #  object, we have to read in the object after copying it
                 #  only, to write it out again. This is wasteful. We should
                 #  instead specify that the top-level object, here: the
-                #  DatasetTree, is not writen out.
+                #  DatasetTree, is not written out.
                 copied_dataset_tree.read_in()
 
                 destination_tree_version_list.set_dataset_tree(

datalad_metalad/extractors/core.py

@@ -355,7 +355,7 @@ def _get_commit_info(ds, refcommit, status):
         )
     ]
     # version, always anchored on the first commit (tags could move and
-    # make the integer commit count ambigous, and subtantially complicate
+    # make the integer commit count ambiguous, and subtantially complicate
     # version comparisons
     version = '0-{}-g{}'.format(
         len(commits),

datalad_metalad/extractors/tests/test_base.py

@@ -103,7 +103,7 @@ def test_api(path=None, *, annex):
         "Should have managed to find at least the core extractor extractor"
     if skipped_extractors:
         pytest.skip(
-            "Not fully tested/succeded since some extractors failed"
+            "Not fully tested/succeeded since some extractors failed"
             " to load:\n%s" % ("\n".join(skipped_extractors)))
 
 

datalad_metalad/filters/base.py

@@ -38,7 +38,7 @@ def filter(self,
 
         This method is called by the 'meta-filter' driver. It should iterate
         through the metadata instances that are provided by the metadata
-        coordinates, perform the filter operation ond yield the resulting
+        coordinates, perform the filter operation and yield the resulting
         metadata objects as instances of "datalad_metalad.metadatatypes.Metadata".
 
         Returned metadata is emitted as datalad invocation result, e.g. as

docs/source/user_guide/writing-extractors.rst

@@ -171,7 +171,7 @@ extractor instance::
 
 
 Please not, if dataset level extraction should be performed and you want to provide extractor
-parameter, you have to provide thw ``--force-dataset-level`` parameter to ensure
+parameter, you have to provide the ``--force-dataset-level`` parameter to ensure
 dataset-level extraction. i.e. to prevent ``meta-extract`` from interpreting the
 key of the first extractor argument as file name for a file-level extraction.
 

tox.ini

@@ -21,9 +21,10 @@ skip_install = true
 deps =
     codespell~=2.0
 commands =
-    codespell -x .codespell-ignorelines -D- -I .codespell-ignorewords --skip "_version.py,*.pem" datalad setup.py
+    codespell
 
 [testenv:flake8]
+deps = flake8
 commands = flake8 {posargs}
 
 [testenv:venv]
@@ -81,5 +82,5 @@ python_files = test_*.py *_test.py utils_pytest.py
 # W293 = Blank line contains whitespace
 #ignore = E265,W293,E266,E731
 max-line-length = 120
-include = datalad
+include = datalad_metalad
 exclude = .tox,.venv,venv-debug,build,dist,doc,git/ext/