Migrate git hooks from Husky to Prek and refresh gitattributes (#68)

* Initial plan

* chore: migrate husky to prek

Co-authored-by: maehr <14755525+maehr@users.noreply.github.com>

* docs: clarify prek usage details

Co-authored-by: maehr <14755525+maehr@users.noreply.github.com>

* chore: refresh gitattributes and link checks

Co-authored-by: maehr <14755525+maehr@users.noreply.github.com>

* docs: remove husky migration note

Co-authored-by: maehr <14755525+maehr@users.noreply.github.com>

* chore: update .gitattributes to enhance file type handling and normalization

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: maehr <14755525+maehr@users.noreply.github.com>

Author: Copilot

.gitattributes

@@ -1,5 +1,50 @@
+# Basic .gitattributes for a python repo.
+
+# Source files
+# ============
+*.pxd    text diff=python
+*.py     text diff=python
+*.py3    text diff=python
+*.pyw    text diff=python
+*.pyx    text diff=python
+*.pyz    text diff=python
+*.pyi    text diff=python
+
+# Binary files
+# ============
+*.db     binary
+*.p      binary
+*.pkl    binary
+*.pickle binary
+*.pyc    binary export-ignore
+*.pyo    binary export-ignore
+*.pyd    binary
+
+# Jupyter notebook
+*.ipynb  text eol=lf
+
+# Note: .db, .p, and .pkl files are associated
+# with the python modules ``pickle``, ``dbm.*``,
+# ``shelve``, ``marshal``, ``anydbm``, & ``bsddb``
+# (among others).
+
+# Basic .gitattributes for a R repo.
+
+# Source files
+# ============
+*.Rdata binary
+*.RData binary
+*.rda   binary
+*.rdb   binary
+*.rds   binary
+*.Rd    text
+*.Rdx   binary
+*.Rmd	  text
+*.R  	  text
+*.Rproj text
+*.[Rr]md   linguist-detectable
+
 # Common settings that generally should always be used with your language specific settings
-# generated by https://www.richie-bendall.ml/gitattributes-generator/
 
 # Auto detect text files and perform LF normalization
 *          text=auto
@@ -26,7 +71,7 @@
 *.adoc     text
 *.textile  text
 *.mustache text
-*.csv      text
+*.csv      text eol=crlf
 *.tab      text
 *.tsv      text
 *.txt      text
@@ -51,6 +96,7 @@
 # Scripts
 *.bash     text eol=lf
 *.fish     text eol=lf
+*.ksh      text eol=lf
 *.sh       text eol=lf
 *.zsh      text eol=lf
 # These are explicitly windows files and should use crlf
@@ -67,10 +113,24 @@
 
 # Archives
 *.7z       binary
+*.bz       binary
+*.bz2      binary
+*.bzip2    binary
 *.gz       binary
+*.lz       binary
+*.lzma     binary
+*.rar      binary
 *.tar      binary
+*.taz      binary
+*.tbz      binary
+*.tbz2     binary
 *.tgz      binary
+*.tlz      binary
+*.txz      binary
+*.xz       binary
+*.Z        binary
 *.zip      binary
+*.zst      binary
 
 # Text files where line endings should be preserved
 *.patch    -text
@@ -86,52 +146,6 @@
 # Apply override to all files in the directory
 *.md linguist-detectable
 
-# Basic .gitattributes for a python repo.
-
-# Source files
-# ============
-*.pxd    text diff=python
-*.py     text diff=python
-*.py3    text diff=python
-*.pyw    text diff=python
-*.pyx    text diff=python
-*.pyz    text diff=python
-*.pyi    text diff=python
-
-# Binary files
-# ============
-*.db     binary
-*.p      binary
-*.pkl    binary
-*.pickle binary
-*.pyc    binary export-ignore
-*.pyo    binary export-ignore
-*.pyd    binary
-
-# Jupyter notebook
-*.ipynb  text eol=lf
-
-# Note: .db, .p, and .pkl files are associated
-# with the python modules ``pickle``, ``dbm.*``,
-# ``shelve``, ``marshal``, ``anydbm``, & ``bsddb``
-# (among others).
-
-# Basic .gitattributes for a R repo.
-
-# Source files
-# ============
-*.Rdata binary
-*.RData binary
-*.rda   binary
-*.rdb   binary
-*.rds   binary
-*.Rd    text
-*.Rdx   binary
-*.Rmd	  text
-*.R  	  text
-*.Rproj text
-*.[Rr]md   linguist-detectable
-
 ## GITATTRIBUTES FOR WEB PROJECTS
 #
 # These settings are for any web project.
@@ -160,6 +174,8 @@
 *.inc             text
 *.ini             text
 *.js              text
+*.mjs             text
+*.cjs             text
 *.json            text
 *.jsx             text
 *.less            text
@@ -238,7 +254,7 @@ TODO              text
 *.conf            text
 *.config          text
 .editorconfig     text
-.env              text
+*.env             text
 .gitattributes    text
 .gitconfig        text
 .htaccess         text
@@ -254,6 +270,8 @@ yarn.lock         text -diff
 browserslist      text
 Makefile          text
 makefile          text
+# Fixes syntax highlighting on GitHub to allow comments
+tsconfig.json     linguist-language=JSON-with-Comments
 
 # Heroku
 Procfile          text
@@ -333,9 +351,15 @@ Procfile          text
 # Executables
 *.exe             binary
 *.pyc             binary
+# Prevents massive diffs caused by vendored, minified files
+**/.yarn/releases/**   binary
+**/.yarn/plugins/**    binary
 
 # RC files (like .babelrc or .eslintrc)
 *.*rc             text
 
 # Ignore files (like .npmignore or .gitignore)
 *.*ignore         text
+
+# Prevents massive diffs from built files
+dist/**           binary

.husky/pre-commit

@@ -2,7 +2,17 @@
 # https://lychee.cli.rs/configuration/
 
 # Exclude template placeholders from link checking
-exclude = ["USERNAME", "REPO_NAME", "ZENODO_RECORD", "GITHUB_REPO_ID", "FULLNAME", "\\[INSERT CONTACT METHOD\\]"]
+exclude = [
+  "USERNAME",
+  "REPO_NAME",
+  "ZENODO_RECORD",
+  "GITHUB_REPO_ID",
+  "FULLNAME",
+  "\\[INSERT CONTACT METHOD\\]",
+  "https://www.gnu.org/licenses/",
+  "https://www.gnu.org/licenses/agpl-3.0.html",
+  "https://www.makeareadme.com/",
+]
 
 # Timeout for requests (seconds)
 timeout = 10
@@ -23,4 +33,4 @@ cache = true
 max_cache_age = "7d"
 
 # Accept status codes: 100-103 (informational), 200-299 (success), 429 (rate limit), 503 (unavailable) as non-blocking
-accept = ["100..=103", "200..=299", "429", "503"]
+accept = ["100..=103", "200..=299", "429", "503", "521", "522", "524"]

.lycheerc.toml

@@ -0,0 +1,8 @@
+repos:
+  - repo: local
+    hooks:
+      - id: prettier-check
+        name: Prettier check
+        entry: npm run check
+        language: system
+        stages: [pre-commit]

.pre-commit-config.yaml

@@ -70,7 +70,7 @@ Place new files accordingly.
 
 1. `npm install <package>`
 2. Commit `package.json` and `package-lock.json`
-3. If needed: `npm run prepare` to reinit Husky hooks
+3. If needed: `npm run prepare` to install Prek git hooks
 
 ### Python (uv)
 
@@ -150,7 +150,7 @@ Place new files accordingly.
 | `lintr::lint_dir(".")`    | Lint R code                                      |
 | `npm run commit`          | Conventional Commits wizard                      |
 | `npm run changelog`       | Generate changelog from commits                  |
-| `npm run prepare`         | Setup Husky git hooks                            |
+| `npm run prepare`         | Setup Prek git hooks                             |
 | `uv sync`                 | Sync Python dependencies                         |
 | `renv::restore()`         | Restore R environment                            |
 | `quarto render`           | **Production render** (avoid in agent sessions)  |

AGENTS.md

@@ -14,6 +14,8 @@ Please note we have a [code of conduct](CODE_OF_CONDUCT.md), please follow it in
 3. Ensure all code is properly formatted and linted:
    - Run `npm run format` to format general files with Prettier
    - Run `npm run check` to verify formatting
+   - Install Prek hooks with `npm run prepare`
+   - Run `prek run --all-files` to run all hooks locally (or `npx @j178/prek run --all-files` if Prek isn't installed globally)
    - Run `uv run ruff format` to format Python code
    - Run `uv run ruff check` to lint Python code
    - Run `uv run ty check` to type check Python code (if applicable)

CONTRIBUTING.md

@@ -52,7 +52,7 @@ Conventional data publication as static supplementary files offers limited repro
 - Python type checking with [ty](https://github.com/astral-sh/ty)
 - Python dependency management with [uv](https://github.com/astral-sh/uv)
 - R dependency management with [renv](https://rstudio.github.io/renv/)
-- Commit messages following [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/) enforced via [husky](https://github.com/typicode/husky)
+- Commit messages following [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/) enforced via [prek](https://prek.j178.dev/)
 - Versioning following [Semantic Versioning](https://semver.org/spec/v2.0.0.html)
 - Workflow based on [fork and pull](https://gist.github.com/Chaser324/ce0505fbed06b947d962) with [GitHub branch protection](https://docs.github.com/en/repositories/configuring-branches-and-merges-in-your-repository/defining-the-mergeability-of-pull-requests/managing-a-branch-protection-rule)
 - Issue tracking via [issue templates](https://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/configuring-issue-templates-for-your-repository)
@@ -109,6 +109,27 @@ We recommend using **[GitHub Codespaces](https://github.com/features/codespaces)
 
 ## Getting Started
 
+### Prek Git Hooks
+
+This template uses [Prek](https://prek.j178.dev/) for managing Git hooks with a pre-commit-compatible configuration. To install hooks locally:
+
+```bash
+npm install
+npm run prepare
+```
+
+To run all hooks on demand:
+
+```bash
+prek run --all-files
+```
+
+If Prek is not installed globally, you can run:
+
+```bash
+npx @j178/prek run --all-files
+```
+
 ### For Most Users: Reproducible Setup with GitHub Codespaces
 
 1. **[Use this template](https://github.com/new?template_name=open-research-data-template&template_owner=maehr)** for your project in a new repository on your GitHub account.