From ab6d22ea237e0ccd6a39ab7311f4405d6d47feb0 Mon Sep 17 00:00:00 2001 From: Yaroslav Halchenko Date: Sun, 16 Jul 2023 18:20:05 -0400 Subject: [PATCH 1/5] Add github action to codespell gh-pages on push and PRs --- .github/workflows/codespell.yml | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 .github/workflows/codespell.yml diff --git a/.github/workflows/codespell.yml b/.github/workflows/codespell.yml new file mode 100644 index 0000000..418c822 --- /dev/null +++ b/.github/workflows/codespell.yml @@ -0,0 +1,22 @@ +--- +name: Codespell + +on: + push: + branches: [gh-pages] + pull_request: + branches: [gh-pages] + +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 From 4f76d72523d39f7dacdda16728374f8b4ce3058a Mon Sep 17 00:00:00 2001 From: Yaroslav Halchenko Date: Sun, 16 Jul 2023 18:20:05 -0400 Subject: [PATCH 2/5] Add rudimentary codespell config --- .codespellrc | 4 ++++ 1 file changed, 4 insertions(+) create mode 100644 .codespellrc diff --git a/.codespellrc b/.codespellrc new file mode 100644 index 0000000..da3c057 --- /dev/null +++ b/.codespellrc @@ -0,0 +1,4 @@ +[codespell] +skip = .git,*.pdf,*.svg +# +# ignore-words-list = From f58ddda987f852117b1882ab32531ed0fb14fee1 Mon Sep 17 00:00:00 2001 From: Yaroslav Halchenko Date: Sun, 16 Jul 2023 18:21:16 -0400 Subject: [PATCH 3/5] ignore some files --- .codespellrc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.codespellrc b/.codespellrc index da3c057..701191a 100644 --- a/.codespellrc +++ b/.codespellrc @@ -1,4 +1,4 @@ [codespell] -skip = .git,*.pdf,*.svg +skip = .git,*.pdf,*.svg,*.min.js,*.map,*.scss,*.css # # ignore-words-list = From 631d0abfe0f26314c52409c9dc098d0905ba81bd Mon Sep 17 00:00:00 2001 From: Yaroslav Halchenko Date: Sun, 16 Jul 2023 18:22:27 -0400 Subject: [PATCH 4/5] Ignore Nature Communication abbreviation + config setting with rogue --- .codespellrc | 1 + 1 file changed, 1 insertion(+) diff --git a/.codespellrc b/.codespellrc index 701191a..82eb835 100644 --- a/.codespellrc +++ b/.codespellrc @@ -1,4 +1,5 @@ [codespell] skip = .git,*.pdf,*.svg,*.min.js,*.map,*.scss,*.css +ignore-regex = (Nat\.? Commun.?|highlighter: rouge) # # ignore-words-list = From 06300ed25cab18ca9565160cc8a60c5ed39d5087 Mon Sep 17 00:00:00 2001 From: Yaroslav Halchenko Date: Sun, 16 Jul 2023 18:23:48 -0400 Subject: [PATCH 5/5] [DATALAD RUNCMD] run codespell throughout === Do not change lines below === { "chain": [], "cmd": "codespell -w", "exit": 0, "extra_inputs": [], "inputs": [], "outputs": [], "pwd": "." } ^^^ Do not change lines above ^^^ --- _episodes/03-remote-collaboration.md | 8 ++++---- _episodes/04-dataset-management.md | 4 ++-- _episodes/91-branching.md | 4 ++-- _episodes/92-filesystem-operations.md | 2 +- _extras/for_instructors.md | 4 ++-- bin/dependencies.R | 2 +- bin/repo_check.py | 2 +- setup.md | 2 +- 8 files changed, 14 insertions(+), 14 deletions(-) diff --git a/_episodes/03-remote-collaboration.md b/_episodes/03-remote-collaboration.md index bae3fd5..776157b 100644 --- a/_episodes/03-remote-collaboration.md +++ b/_episodes/03-remote-collaboration.md @@ -63,7 +63,7 @@ locations. Although each scenario will be slightly different, the setup steps that we will cover with GIN will look similar on other git-based hosting solutions. -## Prelude: file availability, getting and droping content +## Prelude: file availability, getting and dropping content Before we proceed to data publishing let's first take a look at the dataset we created during the first module. We used two ways of adding @@ -122,7 +122,7 @@ datalad drop inputs/images/chinstrap_01.jpg drop(error): /home/alice/Documents/rdm-workshop/example-dataset/inputs/images/chinstrap_01.jpg (file) [unsafe; Could only verify the existence of 0 out of 1 necessary copy; (Use --reckless availability to override this check, or adjust numcopies.)] -# If you were to run this with DataLad version < 0.16.0, the safety check would be overriden with --nocheck instead of --reckless availablity) +# If you were to run this with DataLad version < 0.16.0, the safety check would be overridden with --nocheck instead of --reckless availability) ``` {: .output} @@ -716,7 +716,7 @@ With a cloned dataset, you can do the following: - Change a (text) file. For example, in the `inputs/images/chinstrap_02.yaml` file we entered `penguin_count: - 2`, but if you look closely at the related fotograph, there are + 2`, but if you look closely at the related photograph, there are actually three penguins (one is partially behind a rock). Edit the file and save the changes with an informative commit message, such as "Include penguins occluded by rocks in the count" or something @@ -738,7 +738,7 @@ With a cloned dataset, you can do the following: location on the website. #### Contributing back -When ready, you can contribute back wih `datalad push`. If the other +When ready, you can contribute back with `datalad push`. If the other person has granted you access to their repository (as should be the case during the workshop), you can do it right away. Note that in this case you are pushing to `origin` - this is a default name given to a diff --git a/_episodes/04-dataset-management.md b/_episodes/04-dataset-management.md index 66011af..26b3d44 100644 --- a/_episodes/04-dataset-management.md +++ b/_episodes/04-dataset-management.md @@ -363,7 +363,7 @@ This is important: a *superdataset* does not record individual changes within th In other words, it points to the subdataset location and a point in its life (indicated by a specific commit). Let's acknowledge that we want our superdataset to point to the updated version of the subdataset (ie. that which has all three tabular files) by saving this change in the superdataset's history. -In other words, while the subdataset progressed by three comits, in the parent dataset we can record it as a single change (from empty to populated subdataset): +In other words, while the subdataset progressed by three commits, in the parent dataset we can record it as a single change (from empty to populated subdataset): ~~~ datalad save -d . -m "Progress the subdataset version" @@ -566,6 +566,6 @@ save(ok): . (dataset) ~~~ {: .output} -The end! We have produced a nested datset: +The end! We have produced a nested dataset: - the superdataset (penguin-report) directly contains our code, figures, and report (tracking their history), and includes inputs as a subdatset. - the subdataset (inputs) tracks the history of the raw data files. diff --git a/_episodes/91-branching.md b/_episodes/91-branching.md index 88d9972..cbb4735 100644 --- a/_episodes/91-branching.md +++ b/_episodes/91-branching.md @@ -263,7 +263,7 @@ $ git merge preproc #### And... what now? -Branching opens up the possibility to keep parallel developments neat and orderly next to eachother, hidden away in branches. A `checkout` of your favourite branch lets you travel to its timeline and view all of the changes it contains, and a `merge` combines one or more timelines into another one. +Branching opens up the possibility to keep parallel developments neat and orderly next to each other, hidden away in branches. A `checkout` of your favourite branch lets you travel to its timeline and view all of the changes it contains, and a `merge` combines one or more timelines into another one. > ## Exercise > @@ -383,7 +383,7 @@ $ datalad save -m "Fix: Change absolute to relative paths In order to propose the fix to the central dataset as an addition, the collaborator pushes their branch to the central sibling. When the central sibling is on GitHub or a similar hosting service, the hosting service assists with merging `fix-paths` to `main` with a **pull request** - a browser-based description and overview of the changes a branch carries. -Collaborators can conviently take a look and decide whether they accept the pull request and thereby merge the `fix-paths` into `upstream`'s `main`. +Collaborators can conveniently take a look and decide whether they accept the pull request and thereby merge the `fix-paths` into `upstream`'s `main`. You can see how opening and merging PRs look like in GitHub's interface in the expandable box below. > ## Creating a PR on GitHub diff --git a/_episodes/92-filesystem-operations.md b/_episodes/92-filesystem-operations.md index c9ebb0e..3ea2b64 100644 --- a/_episodes/92-filesystem-operations.md +++ b/_episodes/92-filesystem-operations.md @@ -231,7 +231,7 @@ datalad remove -d local-dataset uninstall(error): . (dataset) [to-be-dropped dataset has revisions that are not available at any known sibling. Use `datalad push --to ...` to push these before dropping the local dataset, or ignore via `--reckless availability`. Unique revisions: ['main']] ~~~ -``remove`` advises to either ``push`` the "unique revisions" to a different place (i.e., creating a sibling to host your pristine, version-controlled changes), or, similarily to how it was done for ``drop``, to disable the availability check with ``--reckless availability``. +``remove`` advises to either ``push`` the "unique revisions" to a different place (i.e., creating a sibling to host your pristine, version-controlled changes), or, similarly to how it was done for ``drop``, to disable the availability check with ``--reckless availability``. ~~~ datalad remove -d local-dataset --reckless availability diff --git a/_extras/for_instructors.md b/_extras/for_instructors.md index 668bbfc..e584b54 100644 --- a/_extras/for_instructors.md +++ b/_extras/for_instructors.md @@ -154,7 +154,7 @@ This can be done with [Let's Encrypt](https://letsencrypt.org/) by following ins ~~~ sudo tljh-config set https.enabled true ~~~ -2. Set your email addres for Let's Encrypt: +2. Set your email address for Let's Encrypt: ~~~ sudo tljh-config set https.letsencrypt.email ~~~ @@ -326,7 +326,7 @@ Different authentication options are possible (e.g. admin can also authenticate 2022/12/01 12:40:30Z: OsProductName: Ubuntu 2022/12/01 12:40:30Z: OsVersion: 22.04 ~~~ -- If the JupyterHub bootsrap script succeeded, within the last 30 lines you will find: +- If the JupyterHub bootstrap script succeeded, within the last 30 lines you will find: ~~~ [ 210.143720] cloud-init[1233]: Waiting for JupyterHub to come up (1/20 tries) [ 210.147437] cloud-init[1233]: Done! diff --git a/bin/dependencies.R b/bin/dependencies.R index 4eeeb21..df7ad63 100644 --- a/bin/dependencies.R +++ b/bin/dependencies.R @@ -79,7 +79,7 @@ create_description <- function(required_pkgs) { # We have to write the description twice to get the hidden dependencies # because renv only considers explicit dependencies. # - # This is needed because some of the hidden dependencis will require system + # This is needed because some of the hidden dependencies will require system # libraries to be configured. suppressMessages(repo <- BiocManager::repositories()) deps <- remotes::dev_package_deps(dependencies = TRUE, repos = repo) diff --git a/bin/repo_check.py b/bin/repo_check.py index 6988ca5..45254ea 100644 --- a/bin/repo_check.py +++ b/bin/repo_check.py @@ -146,7 +146,7 @@ def check_labels(reporter, repo_url): for name in sorted(overlap): reporter.check(EXPECTED[name].lower() == actual[name].lower(), None, - 'Color mis-match for label {0} in {1}: expected {2}, found {3}', + 'Color mismatch for label {0} in {1}: expected {2}, found {3}', name, repo_url, EXPECTED[name], actual[name]) diff --git a/setup.md b/setup.md index 441fbe1..56de32f 100644 --- a/setup.md +++ b/setup.md @@ -29,7 +29,7 @@ about collaboration you won't be able to publish all example data). ## Participate with own computer: install software -If you want to follow the exaples on your own machine, you will need +If you want to follow the examples on your own machine, you will need to install DataLad and some additional software which we will use during the walkthrough. Note that Linux or MacOS are strongly recommended for this workshop; although DataLad works on all main