codespell: workflow and some typos fixed (#176)

* Add github action to codespell main on push and PRs

* Add rudimentary codespell config

* Add pre-commit definition for codespell

* [DATALAD RUNCMD] Do interactive fixing of some ambigous typos

=== Do not change lines below ===
{
 "chain": [],
 "cmd": "codespell -w -i 3 -C 2 ./tests/tests_integration/test_ssh_file_transfer.py",
 "exit": 0,
 "extra_inputs": [],
 "inputs": [],
 "outputs": [],
 "pwd": "."
}
^^^ Do not change lines above ^^^

* [DATALAD RUNCMD] run codespell throughout fixing typo automagically

=== Do not change lines below ===
{
 "chain": [],
 "cmd": "codespell -w",
 "exit": 0,
 "extra_inputs": [],
 "inputs": [],
 "outputs": [],
 "pwd": "."
}
^^^ Do not change lines above ^^^

* Fix formatting of .pre-commit-config.yaml

.github/workflows/codespell.yml

@@ -0,0 +1,22 @@
+---
+name: Codespell
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+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@v2

.pre-commit-config.yaml

@@ -32,3 +32,9 @@ repos:
                 - types-appdirs
                 - types-paramiko
                 - types-simplejson
+    - repo: https://github.com/codespell-project/codespell
+      rev: v2.2.5
+      hooks:
+      - id: codespell
+        additional_dependencies:
+          - tomli

datashuttle/command_line_interface.py

@@ -1029,7 +1029,7 @@ def main() -> None:
     should match the datashuttle API function name.
 
     Next, initialise a datashuttle project using the API.
-    Supress the warning that a config file must
+    Suppress the warning that a config file must
     be made on project initialisation when
     a config is being made.
 

datashuttle/datashuttle.py

@@ -316,7 +316,7 @@ def upload(
             data type folder to upload.
         ses_names :
             a session name / list of session names, similar to
-            sub_names but requring a "ses-" prefix.
+            sub_names but requiring a "ses-" prefix.
         dry_run :
             perform a dry-run of upload. This will output as if file
             transfer was taking place, but no files will be moved. Useful

docs/source/conf.py

@@ -60,7 +60,7 @@
     "substitution",
     "tasklist",
 ]
-# Automatically add achors to markdown headings
+# Automatically add anchors to markdown headings
 myst_heading_anchors = 3
 
 # Add any paths that contain templates here, relative to this directory.

docs/source/pages/documentation.md

@@ -310,7 +310,7 @@ To discuss, contribute or give feedback on DataShuttle, please check out our dis
 
 ## Python API Guide
 
-DataShuttle can be used through the command line interface (as exampled in the *Get Started* section) or through a Python API. All commands shown in the *Get Started* guide can be used similarly in the Python API (with hypens replaced by underscores).
+DataShuttle can be used through the command line interface (as exampled in the *Get Started* section) or through a Python API. All commands shown in the *Get Started* guide can be used similarly in the Python API (with hyphens replaced by underscores).
 
 To start a project in Python, import DataShuttle and initialise the project class:
 

pyproject.toml

@@ -112,3 +112,8 @@ ignore = [
 
 [project.scripts]
 datashuttle = "datashuttle.command_line_interface:main"
+
+[tool.codespell]
+skip = '.git,*.pdf,*.svg'
+#
+# ignore-words-list = ''

tests/conftest.py

@@ -10,7 +10,7 @@
 
 FILESYSTEM_PATH and SERVER_PATH these must point
 to the same folder on the HPC, filesystem,
-as a moutned drive and server as the linux path to
+as a mounted drive and server as the linux path to
 connect through SSH
 """
 import platform

tests/test_utils.py

@@ -505,7 +505,7 @@ def get_top_level_folder_path(
 
     assert (
         folder_name in canonical_folders.get_top_level_folders()
-    ), "folder_name must be cannonical e.g. rawdata"
+    ), "folder_name must be canonical e.g. rawdata"
 
     if local_or_central == "local":
         base_path = project.cfg["local_path"]

tests/tests_integration/test_command_line_interface.py

@@ -278,7 +278,7 @@ def test_multiple_inputs(self, command):
         """
         To process lists, a syntax "<>" is used
         to specify input is list. Check the passed
-        varialbes are processed as expected.
+        variables are processed as expected.
         """
         stdout, stderr = test_utils.run_cli(
             f"{command} "

tests/tests_integration/test_ssh_file_transfer.py

@@ -167,7 +167,7 @@ def test_all_data_transfer_options(
     ):
         """
         Parse the arguments to filter the pathtable, getting
-        the files expected to be transferred pased on the arguments
+        the files expected to be transferred passed on the arguments
         Note files in sub/ses/datatype folders must be handled
         separately to those in non-sub, non-ses, non-data-type folders