Use base pipe (#76)

* Use base pipe. Closes #75. I also updated the GHA to check all the way back to 4.1 (for now) to make sure we don't use it in a way that wasn't initially supported. * Namespace all dplyr function calls.
ropensci · Sep 5, 2024 · a39d2e5 · a39d2e5
1 parent 9d71290
commit a39d2e5
Show file tree

Hide file tree

Showing 15 changed files with 57 additions and 63 deletions.
diff --git a/.github/workflows/R-CMD-check.yaml b/.github/workflows/R-CMD-check.yaml
@@ -25,6 +25,8 @@ jobs:
           - {os: windows-latest, r: 'release'}
           - {os: ubuntu-latest,  r: 'devel', http-user-agent: 'release'}
           - {os: ubuntu-latest,  r: 'oldrel-1'}
+          - {os: ubuntu-latest,  r: 'oldrel-2'}
+          - {os: ubuntu-latest,  r: 'oldrel-3'}
 
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}

diff --git a/DESCRIPTION b/DESCRIPTION
@@ -22,7 +22,6 @@ Imports:
     cli,
     dplyr,
     glue,
-    magrittr,
     purrr,
     readr,
     rlang,

diff --git a/NAMESPACE b/NAMESPACE
@@ -5,8 +5,4 @@ export(gutenberg_get_all_mirrors)
 export(gutenberg_get_mirror)
 export(gutenberg_strip)
 export(gutenberg_works)
-importFrom(dplyr,count)
-importFrom(dplyr,distinct)
-importFrom(dplyr,filter)
-importFrom(magrittr,"%>%")
 importFrom(rlang,"%||%")
diff --git a/NEWS.md b/NEWS.md
@@ -1,8 +1,9 @@
 # gutenbergr (development version)
 
-* `gutenberg_download()` tries the `.txt` version of files when the `.zip` is unavailable (@jrdnbradford, #55).
+* `gutenberg_download()` tries the `.txt` version of files when the `.zip` is unavailable (@jrdnbradford, #55, #70).
 * New function `gutenberg_get_all_mirrors()` retrieves all mirror data (@jrdnbradford, #58).
-* The package infrastructure has been updated to make the package more robust and maintainable.
+* The package infrastructure has been updated to make the package more robust and maintainable (#60, #64, #69).
+* We now use the base R pipe (`|>`) in code and examples, not the magrittr pipe (`%>%`) (@jonthegeek, #75).
 
 # gutenbergr 0.2.4
 

diff --git a/R/data.R b/R/data.R
@@ -37,19 +37,19 @@
 #'
 #' gutenberg_metadata
 #'
-#' gutenberg_metadata %>%
+#' gutenberg_metadata |>
 #'   count(author, sort = TRUE)
 #'
 #' # look for Shakespeare, excluding collections (containing "Works") and
 #' # translations
-#' shakespeare_metadata <- gutenberg_metadata %>%
+#' shakespeare_metadata <- gutenberg_metadata |>
 #'   filter(
 #'     author == "Shakespeare, William",
 #'     language == "en",
 #'     !str_detect(title, "Works"),
 #'     has_text,
 #'     !str_detect(rights, "Copyright")
-#'   ) %>%
+#'   ) |>
 #'   distinct(title)
 #'
 #' \donttest{
@@ -101,17 +101,17 @@
 #' library(dplyr)
 #' library(stringr)
 #'
-#' gutenberg_subjects %>%
-#'   filter(subject_type == "lcsh") %>%
+#' gutenberg_subjects |>
+#'   filter(subject_type == "lcsh") |>
 #'   count(subject, sort = TRUE)
 #'
-#' sherlock_holmes_subjects <- gutenberg_subjects %>%
+#' sherlock_holmes_subjects <- gutenberg_subjects |>
 #'   filter(str_detect(subject, "Holmes, Sherlock"))
 #'
 #' sherlock_holmes_subjects
 #'
-#' sherlock_holmes_metadata <- gutenberg_works() %>%
-#'   filter(author == "Doyle, Arthur Conan") %>%
+#' sherlock_holmes_metadata <- gutenberg_works() |>
+#'   filter(author == "Doyle, Arthur Conan") |>
 #'   semi_join(sherlock_holmes_subjects, by = "gutenberg_id")
 #'
 #' sherlock_holmes_metadata

diff --git a/R/gutenberg_download.R b/R/gutenberg_download.R
@@ -35,7 +35,7 @@
 #'   dplyr::count(books, title)
 #'
 #'   # download all books from Jane Austen
-#'   austen <- gutenberg_works(author == "Austen, Jane") %>%
+#'   austen <- gutenberg_works(author == "Austen, Jane") |>
 #'     gutenberg_download(meta_fields = "title")
 #'   austen
 #'   dplyr::count(austen, title)

diff --git a/R/gutenberg_works.R b/R/gutenberg_works.R
@@ -50,16 +50,16 @@
 #'
 #' # language specifications
 #'
-#' gutenberg_works(languages = "es") %>%
+#' gutenberg_works(languages = "es") |>
 #'   count(language, sort = TRUE)
 #'
-#' gutenberg_works(languages = c("en", "es")) %>%
+#' gutenberg_works(languages = c("en", "es")) |>
 #'   count(language, sort = TRUE)
 #'
-#' gutenberg_works(languages = c("en", "es"), all_languages = TRUE) %>%
+#' gutenberg_works(languages = c("en", "es"), all_languages = TRUE) |>
 #'   count(language, sort = TRUE)
 #'
-#' gutenberg_works(languages = c("en", "es"), only_languages = FALSE) %>%
+#' gutenberg_works(languages = c("en", "es"), only_languages = FALSE) |>
 #'   count(language, sort = TRUE)
 #' }
 #' @export
@@ -82,37 +82,37 @@ gutenberg_works <- function(..., languages = "en",
       )
     }
   )
-  ret <- filter(gutenberg_metadata, ...)
+  ret <- dplyr::filter(gutenberg_metadata, ...)
 
   if (!is.null(languages)) {
-    lang_filt <- gutenberg_languages %>%
-      filter(language %in% languages) %>%
-      count(gutenberg_id, total_languages)
+    lang_filt <- gutenberg_languages |>
+      dplyr::filter(language %in% languages) |>
+      dplyr::count(gutenberg_id, total_languages)
 
     if (all_languages) {
-      lang_filt <- lang_filt %>%
-        filter(n >= length(languages))
+      lang_filt <- lang_filt |>
+        dplyr::filter(n >= length(languages))
     }
     if (only_languages) {
-      lang_filt <- lang_filt %>%
-        filter(total_languages <= n)
+      lang_filt <- lang_filt |>
+        dplyr::filter(total_languages <= n)
     }
 
-    ret <- ret %>%
-      filter(gutenberg_id %in% lang_filt$gutenberg_id)
+    ret <- ret |>
+      dplyr::filter(gutenberg_id %in% lang_filt$gutenberg_id)
   }
 
   if (!is.null(rights)) {
     .rights <- rights
-    ret <- filter(ret, rights %in% .rights)
+    ret <- dplyr::filter(ret, rights %in% .rights)
   }
 
   if (only_text) {
-    ret <- filter(ret, has_text)
+    ret <- dplyr::filter(ret, has_text)
   }
 
   if (distinct) {
-    ret <- distinct(ret, title, gutenberg_author_id, .keep_all = TRUE)
+    ret <- dplyr::distinct(ret, title, gutenberg_author_id, .keep_all = TRUE)
     # in older versions of dplyr, distinct_ didn't need .keep_all
     if (any(colnames(ret) == ".keep_all")) {
       ret$.keep_all <- NULL # nocov

diff --git a/R/gutenbergr-package.R b/R/gutenbergr-package.R
@@ -2,10 +2,6 @@
 "_PACKAGE"
 
 ## usethis namespace: start
-#' @importFrom dplyr count
-#' @importFrom dplyr distinct
-#' @importFrom dplyr filter
-#' @importFrom magrittr %>%
 #' @importFrom rlang %||%
 ## usethis namespace: end
 NULL
diff --git a/README.Rmd b/README.Rmd
@@ -66,7 +66,7 @@ Suppose we wanted to download Emily Bronte's "Wuthering Heights." We could find
 library(dplyr)
 library(gutenbergr)
 
-gutenberg_works() %>%
+gutenberg_works() |>
   filter(title == "Wuthering Heights")
 
 # or just:
@@ -87,14 +87,14 @@ wuthering_heights
 books <- gutenberg_download(c(768, 1260), meta_fields = "title")
 books
 
-books %>%
+books |>
   count(title)
 ```
 
 It can also take the output of `gutenberg_works` directly. For example, we could get the text of all Aristotle's works, each annotated with both `gutenberg_id` and `title`, using:
 
 ```{r}
-aristotle_books <- gutenberg_works(author == "Aristotle") %>%
+aristotle_books <- gutenberg_works(author == "Aristotle") |>
   gutenberg_download(meta_fields = "title")
 
 aristotle_books

diff --git a/README.md b/README.md
@@ -71,7 +71,7 @@ could find the book’s ID by filtering:
 library(dplyr)
 library(gutenbergr)
 
-gutenberg_works() %>%
+gutenberg_works() |>
   filter(title == "Wuthering Heights")
 #> # A tibble: 1 × 8
 #>   gutenberg_id title             author        gutenberg_author_id language
@@ -137,7 +137,7 @@ books
 #> 10          768 ""                  Wuthering Heights
 #> # ℹ 33,333 more rows
 
-books %>%
+books |>
   count(title)
 #> # A tibble: 2 × 2
 #>   title                           n
@@ -151,7 +151,7 @@ we could get the text of all Aristotle’s works, each annotated with both
 `gutenberg_id` and `title`, using:
 
 ``` r
-aristotle_books <- gutenberg_works(author == "Aristotle") %>%
+aristotle_books <- gutenberg_works(author == "Aristotle") |>
   gutenberg_download(meta_fields = "title")
 
 aristotle_books

diff --git a/man/gutenberg_download.Rd b/man/gutenberg_download.Rd
diff --git a/man/gutenberg_metadata.Rd b/man/gutenberg_metadata.Rd
diff --git a/man/gutenberg_subjects.Rd b/man/gutenberg_subjects.Rd
diff --git a/man/gutenberg_works.Rd b/man/gutenberg_works.Rd
diff --git a/vignettes/intro.Rmd b/vignettes/intro.Rmd
@@ -46,7 +46,7 @@ gutenberg_metadata
 For example, you could find the Gutenberg ID(s) of Jane Austen's _Persuasion_ by doing:
 
 ```{r filter}
-gutenberg_metadata %>%
+gutenberg_metadata |>
   filter(title == "Persuasion")
 ```
 
@@ -107,7 +107,7 @@ books
 Notice that the `meta_fields` argument allows us to add one or more additional fields from the `gutenberg_metadata` to the downloaded text, such as title or author.
 
 ```{r count books}
-books %>%
+books |>
   count(title)
 ```
 
@@ -122,10 +122,10 @@ gutenberg_subjects
 This is useful for extracting texts from a particular topic or genre, such as detective stories, or a particular character, such as Sherlock Holmes. The `gutenberg_id` column can then be used to download these texts or to link with other metadata.
 
 ```{r filter subjects}
-gutenberg_subjects %>%
+gutenberg_subjects |>
   filter(subject == "Detective and mystery stories")
 
-gutenberg_subjects %>%
+gutenberg_subjects |>
   filter(grepl("Holmes, Sherlock", subject))
 ```
 
@@ -140,13 +140,13 @@ gutenberg_authors
 What's next after retrieving a book's text? Well, having the book as a data frame is especially useful for working with the [tidytext](https://github.com/juliasilge/tidytext) package for text analysis.
 
 ```{r tidytext}
-words <- books %>%
+words <- books |>
   unnest_tokens(word, text)
 
 words
 
-word_counts <- words %>%
-  anti_join(stop_words, by = "word") %>%
+word_counts <- words |>
+  anti_join(stop_words, by = "word") |>
   count(title, word, sort = TRUE)
 
 word_counts