Merge pull request #109 from pharmaverse/82_set_up_styling_and_spelling_github_actions

Closes #82 add spelling action

Author: jeffreyad

.Rbuildignore

@@ -0,0 +1 @@
+^\.github$

.github/.gitignore

@@ -0,0 +1 @@
+*.html

.github/workflows/link_check.yml

@@ -0,0 +1,33 @@
+name: Links (Fail Fast)
+
+on:
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  linkChecker:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up R  # Install R from CRAN
+        uses: r-lib/actions/setup-r@v2
+        with:
+          r-version: '4.4.3' # You can specify a different R version if needed
+
+      - name: Install R packages
+        run: |
+          Rscript -e 'install.packages("fs")'
+        shell: bash
+
+      - name: Switch .qmd to .md
+        run: Rscript R/switch.R
+        shell: bash
+
+      - name: Link Checker
+        uses: lycheeverse/[email protected]
+        with:
+          fail: true
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/spellcheck.yml

@@ -0,0 +1,55 @@
+name: Spellcheck
+on:
+  pull_request:
+    branches: ['main']
+jobs:
+  Spelling:
+    runs-on: ubuntu-latest
+    container:
+      image: "rocker/tidyverse:4.3.1"
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+
+      - name: Install packages
+        run: |
+          if (!require("roxygen2")) install.packages("roxygen2")
+          if (!require("spelling")) install.packages("spelling")
+          if (!require("testthat")) install.packages("testthat")
+        shell: Rscript {0}
+
+      - name: Remove links from .qmd files (Bash)
+        run: |
+          find . -type f -name "*.qmd" -print0 | while IFS= read -r -d '' file; do
+              sed -i -E '
+                  s/\[([^\]]+)\]\((https?:\/\/[^)]+)\)/\1/g;  # Remove Markdown links, keep text
+                  s#https?://[a-zA-Z0-9./?=_-]+(\#[a-zA-Z0-9_-]*)?##g  # Remove standalone URLs, including fragments
+              ' "$file"
+              echo "Processed: $file"
+          done
+        shell: bash
+
+      - name: Check spelling
+        run: |
+          library(spelling)
+          library(readr)
+
+          qmd_files <- list.files(pattern = ".*\\.qmd$", recursive = TRUE)
+
+          words <- spelling::spell_check_files(
+            qmd_files,
+            ignore = read_lines("inst/WORDLIST")
+          )
+
+          print(words)
+
+          testthat::test_that(desc = "Check spelling", code = {
+            testthat::expect_equal(
+              object = words,
+              expected = spelling::spell_check_files(
+                path = "inst/WORDLIST",
+                ignore = read_lines("inst/WORDLIST")
+              )
+            )
+          })
+        shell: Rscript {0}

.github/workflows/style_check.yml

@@ -0,0 +1,20 @@
+name: Style
+on:
+  pull_request: {branches: ['main']}
+
+jobs:
+  Style:
+    runs-on: ubuntu-latest
+    container: {image: "rocker/tidyverse:4.2.1"}
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+      - name: Install styler
+        run: install.packages("styler")
+        shell: Rscript {0}
+      - name: styler version
+        run: packageVersion("styler")
+        shell: Rscript {0}
+      - name: Run styler
+        run: styler::style_dir(dry = "fail")
+        shell: Rscript {0}

DESCRIPTION

@@ -50,3 +50,5 @@ Suggests:
     knitr,
     rmarkdown
 Encoding: UTF-8
+Language: en-US
+

NAMESPACE

@@ -0,0 +1,2 @@
+# Generated by roxygen2: do not edit by hand
+

R/CICD.R

@@ -0,0 +1,67 @@
+# Load required packages
+library(spelling)
+library(readr)
+library(stringr)
+library(dplyr)
+
+#-------------------------- Spell-check Without Modifying Files --------------------------
+
+# Function to extract non-code content while keeping comments from code blocks
+clean_text_for_spellcheck <- function(file) {
+  text <- read_lines(file)
+
+  text_clean <- text %>%
+    # Remove Markdown links but keep link text
+    str_replace_all("\\[([^\\]]+)\\]\\([^)]*\\)", "\\1") %>%
+    # Remove standalone URLs
+    str_replace_all("https?://[^\\s)\"']+", "")
+
+  return(text_clean)
+}
+
+#-------------------------- Spell-check Without Modifying Files --------------------------
+
+# Get all .qmd files
+qmd_files <- list.files(pattern = ".*\\.qmd$", recursive = TRUE)
+file <- qmd_files[63]
+# Run spell check per file while ignoring code chunks
+
+spell_check_results <- lapply(qmd_files, function(file) {
+  cleaned_text <- clean_text_for_spellcheck(file)
+  words <- spelling::spell_check_text(cleaned_text, ignore = read_lines("inst/WORDLIST"))
+
+  if (nrow(words) > 0) {
+    words$file <- file # Add filename column
+  }
+
+  return(words)
+})
+
+# Combine results into a single dataframe
+all_typos <- bind_rows(spell_check_results)
+
+# Print results
+if (nrow(all_typos) > 0) {
+  print(all_typos %>% select(file, word, found))
+} else {
+  message("No spelling errors found!")
+}
+
+#-------------------------- Add Words to Wordlist (If Needed) --------------------------
+
+# Uncomment if you want to manually add words to the wordlist
+# write(all_typos$word, file = "inst/WORDLIST", append = TRUE)
+# sort_words <- sort(read_lines("inst/WORDLIST")) %>% unique()
+# write_lines(sort_words, "inst/WORDLIST")
+
+#-------------------------- Style-check ----------------------------------------
+
+# This is what happens in CI/CD:
+
+styler::style_dir(dry = "fail")
+
+# Fix it locally:
+styler::style_dir()
+
+# Now it should pass:
+styler::style_dir(dry = "fail")

R/switch.R

@@ -0,0 +1,51 @@
+#' fixes link-check problem
+#' Finds whether any files use the string: "(.mailto:" for linking email adresses
+#' then just replaces with: "(mailto:" as is markdown standard
+#'
+#' @param file_list vector of filenames
+#'
+#' @return messages only. side effect is: changes files.
+modify_files <- function(file_list) {
+  # Create an empty vector to store the file names that contain the string
+  matching_files <- c()
+
+  # Iterate over each file in the directory
+  for (file in file_list) {
+    # Read the contents of the file
+    file_contents <- readLines(file)
+
+    # Check if the file contains the string "(.mailto:"
+    if (any(grepl("\\(\\.mailto:", file_contents))) {
+      # Add the file name to the vector
+      matching_files <- c(matching_files, file)
+    }
+  }
+
+  # Iterate over the matching files
+  for (file in matching_files) {
+    # Read the contents of the file
+    file_contents <- readLines(file)
+
+    # Remove the "." from each line that contains the string
+    modified_contents <- gsub("\\(\\.mailto:", "(mailto:", file_contents)
+
+    # Write the modified contents back to the file
+    writeLines(modified_contents, file)
+
+    # Print a message indicating the modification has been made
+    message("Modified file:", file, "\n")
+  }
+
+  # Print the list of matching files
+  message("Matching files:", matching_files, "\n")
+}
+
+# get all qmd files
+all_qmd <- list.files(full.names = FALSE, all.files = FALSE, pattern = ".qmd$", recursive = TRUE)
+
+# modify if needed the link to email problem for link checker
+modify_files(all_qmd)
+# get filenames ending with .md
+all_md <- gsub(".qmd$", ".md", all_qmd)
+# rename all files
+file.rename(all_qmd, all_md)

README.md

@@ -1,3 +1,9 @@
+---
+editor: 
+  markdown: 
+    wrap: 72
+---
+
 # Pharmaverse Examples
 
 The true beauty of pharmaverse (and open source in general) is when
@@ -80,3 +86,7 @@ the packages being used.
 We recommend you notify the maintainers of all the packages used in your
 example, as then they are more likely to help inform us if ever anything
 changes in their packages that breaks any of our examples.
+
+To check spelling and style in a post, open the `CICD.R` file in the R/
+folder. Run the script line by line to first check the spelling in your
+post and then to make sure your code is compatible with our code-style.