Get all the categories from Quarto blog posts (between 'categories: ' and second instance of '---')

get-categories.R

posts <- 
  list.files("posts", pattern = ".qmd", recursive = TRUE, full.names = TRUE)

get_categories <- function(post_path, ignore_rx = "resources") {
  
  post_lines <- readLines(post_path, warn = FALSE)
  
  cats_start <- which(post_lines == "categories:") + 1
  cats_end <- which(post_lines == "---")[2] - 1
  
  cats <- NULL
  
  if (length(cats_start) == 1 & length(cats_end) == 1) {
    cats <- gsub("  - ", "", post_lines[cats_start:cats_end])
    cats <- cats[!grepl(ignore_rx, cats)]
  }
  
  return(cats)
  
}

cats_list <- lapply(posts, \(post) get_categories(post)) |> 
  setNames(dirname(post_names))

all_cats <- unlist(cats_list)

table(all_cats) |> sort(decreasing = TRUE)