Merge pull request #16 from KWB-R/clean

Clean

.github/workflows/R-CMD-check.yaml

@@ -22,24 +22,25 @@ jobs:
       fail-fast: false
       matrix:
         config:
-          - {os: macOS-latest, r: 'release'}      
-          - {os: ubuntu-20.04, r: 'release', rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}      
-          - {os: windows-latest, r: 'devel'}          
+          - {os: macOS-latest, r: 'release'}
+          - {os: ubuntu-20.04, r: 'release', rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
+          - {os: windows-latest, r: 'devel'}
           - {os: windows-latest, r: 'oldrel'}
           - {os: windows-latest, r: 'release'}
 
     env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
       RSPM: ${{ matrix.config.rspm }}
 
     steps:
       - uses: actions/checkout@v2
 
-      - uses: r-lib/actions/setup-r@master
+      - uses: r-lib/actions/setup-r@v2
         with:
           r-version: ${{ matrix.config.r }}
 
-      - uses: r-lib/actions/setup-pandoc@master
+      - uses: r-lib/actions/setup-pandoc@v2
 
       - name: Query dependencies
         run: |

.github/workflows/pkgdown.yaml

@@ -15,9 +15,9 @@ jobs:
     steps:
       - uses: actions/checkout@v2
 
-      - uses: r-lib/actions/setup-r@master
+      - uses: r-lib/actions/setup-r@v2
 
-      - uses: r-lib/actions/setup-pandoc@master
+      - uses: r-lib/actions/setup-pandoc@v2
 
       - name: Query dependencies
         run: |

.github/workflows/pr-commands.yaml

@@ -11,10 +11,10 @@ jobs:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
     steps:
       - uses: actions/checkout@v2
-      - uses: r-lib/actions/pr-fetch@master
+      - uses: r-lib/actions/pr-fetch@v2
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: r-lib/actions/setup-r@master
+      - uses: r-lib/actions/setup-r@v2
       - name: Install dependencies
         run: Rscript -e 'install.packages(c("remotes", "roxygen2"))' -e 'remotes::install_deps(dependencies = TRUE)'
       - name: Document
@@ -23,7 +23,7 @@ jobs:
         run: |
           git add man/\* NAMESPACE
           git commit -m 'Document'
-      - uses: r-lib/actions/pr-push@master
+      - uses: r-lib/actions/pr-push@v2
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
   style:
@@ -34,10 +34,10 @@ jobs:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
     steps:
       - uses: actions/checkout@v2
-      - uses: r-lib/actions/pr-fetch@master
+      - uses: r-lib/actions/pr-fetch@v2
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: r-lib/actions/setup-r@master
+      - uses: r-lib/actions/setup-r@v2
       - name: Install dependencies
         run: Rscript -e 'install.packages("styler")'
       - name: Style
@@ -46,6 +46,6 @@ jobs:
         run: |
           git add \*.R
           git commit -m 'Style'
-      - uses: r-lib/actions/pr-push@master
+      - uses: r-lib/actions/pr-push@v2
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/test-coverage.yaml

@@ -18,9 +18,9 @@ jobs:
     steps:
       - uses: actions/checkout@v2
 
-      - uses: r-lib/actions/setup-r@master
+      - uses: r-lib/actions/setup-r@v2
 
-      - uses: r-lib/actions/setup-pandoc@master
+      - uses: r-lib/actions/setup-pandoc@v2
 
       - name: Query dependencies
         run: |

DESCRIPTION

@@ -29,25 +29,25 @@ Imports:
     ggplot2,
     kwb.file,
     kwb.read,
-    kwb.utils,
+    kwb.utils (>= 0.13.0),
     magrittr,
     openxlsx,
     rlang,
     stringr,
     tibble,
     tidyr,
     wordcloud2,
-    xml2, 
-    plotly
+    xml2
 Suggests: 
     covr,
     knitr,
+    plotly,
     rmarkdown
 Remotes:
     github::kwb-r/kwb.file,
     github::kwb-r/kwb.read,
     github::kwb-r/kwb.utils
 Encoding: UTF-8
 LazyData: true
-RoxygenNote: 7.1.1
+RoxygenNote: 7.2.3
 VignetteBuilder: knitr

R/check_for_differences.R

@@ -38,8 +38,8 @@
 #' head(diffs_df)
 #'
 #' }
-check_for_differences <- function(
-                                  df_x, df_y, dbg = TRUE) {
+check_for_differences <- function(df_x, df_y, dbg = TRUE)
+{
   name_df_x <- deparse(substitute(df_x))
   name_df_y <- deparse(substitute(df_y))
 
@@ -49,9 +49,9 @@ check_for_differences <- function(
   tidy_name <- function(name) paste0(name, "_tidy")
 
   get_text <- function(name_df, name_value) sprintf(
-      "Tidying data.frame '%s' and rename 'value' to '%s'. Saving to %s",
-      name_df, name_value, tidy_name(name_df)
-    )
+    "Tidying data.frame '%s' and rename 'value' to '%s'. Saving to %s",
+    name_df, name_value, tidy_name(name_df)
+  )
 
   df_x_tidy <- kwb.utils::catAndRun(
     messageText = get_text(name_df_x, name_value_x), dbg = dbg,
@@ -84,10 +84,12 @@ check_for_differences <- function(
 
   diffs_idx <- kwb.utils::catAndRun(
     messageText = messageText, dbg = dbg,
-    expr = which(!sapply(seq_len(nrow(df_xy_tidy)), function(row) identical(
+    expr = which(
+      !sapply(seq_len(nrow(df_xy_tidy)), function(row) identical(
         df_xy_tidy[[name_value_x]][row],
         df_xy_tidy[[name_value_y]][row]
-      )))
+      ))
+    )
   )
 
   kwb.utils::catIf(dbg, sprintf(

R/check_problematic_entries.R

@@ -13,21 +13,21 @@
 #' head(problematic_entries)
 #' }
 check_problematic_entries <- function(
-                                      endnote_list, give_hints = TRUE, dbg = TRUE) {
+  endnote_list,
+  give_hints = TRUE,
+  dbg = TRUE
+)
+{
+  name <- deparse(substitute(endnote_list))
+
   entries_org <- kwb.utils::catAndRun(
-    sprintf(
-      "Creating data frame from '%s'",
-      deparse(substitute(endnote_list))
-    ),
+    sprintf("Creating data frame from '%s'", name),
     dbg = dbg,
     expr = create_references_df(endnote_list)
   )
 
   entries_cleaned <- kwb.utils::catAndRun(
-    sprintf(
-      "Creating 'cleaned' data frame from '%s' for comparison",
-      deparse(substitute(endnote_list))
-    ),
+    sprintf("Creating 'cleaned' data frame from '%s' for comparison", name),
     dbg = dbg,
     expr = clean_references_df(endnote_list, give_hints, dbg)
   )
@@ -36,9 +36,7 @@ check_problematic_entries <- function(
     identical(entries_org[[col_name]], entries_cleaned[[col_name]])
   })
 
-  cols_with_problems <- names(which(has_problems))
-
-  check_list <- lapply(cols_with_problems, function(column) {
+  check_list <- lapply(names(which(has_problems)), function(column) {
     indices <- which(!sapply(seq_len(nrow(entries_org)), function(i) {
       identical(entries_org[[column]][i], entries_cleaned[[column]][i])
     }))

R/clean_references_df.R

@@ -6,7 +6,8 @@
 #' @export
 #' @importFrom stringr str_remove_all regex str_trim
 #' @importFrom kwb.utils catAndRun
-clean_dois <- function(dois, dbg = TRUE) {
+clean_dois <- function(dois, dbg = TRUE)
+{
   remove <- stringr::str_remove_all
 
   kwb.utils::catAndRun("Clean 'DOI'", dbg = dbg, expr = {
@@ -28,8 +29,8 @@ clean_dois <- function(dois, dbg = TRUE) {
 #' @export
 #' @importFrom stringr str_remove_all str_replace_all regex str_trim
 #' @importFrom kwb.utils catAndRun
-clean_project_names <- function(
-                                project_names, give_hints = FALSE, dbg = TRUE) {
+clean_project_names <- function(project_names, give_hints = FALSE, dbg = TRUE)
+{
   kwb.utils::catAndRun("Clean 'Project Names'", dbg = dbg, expr = {
     project_names <- project_names %>%
       stringr::str_replace_all("\\s+?/", ",") %>%
@@ -68,8 +69,8 @@ if (FALSE) {
 #' @return vector with cleaned author names
 #' @export
 #' @importFrom kwb.utils catAndRun
-clean_author_names <- function(
-                               author_names, give_hints = FALSE, dbg = TRUE) {
+clean_author_names <- function(author_names, give_hints = FALSE, dbg = TRUE)
+{
   kwb.utils::catAndRun(
     "No cleaning of author_names implemented yet. Only hints are generated in
     case that user defines 'give_hints = TRUE' (default: FALSE)",
@@ -94,8 +95,8 @@ clean_author_names <- function(
 #' @return vector with cleaned accessibility information
 #' @export
 #' @importFrom stringr str_remove_all str_replace_all regex str_trim
-clean_accessibility <- function(
-                                access, give_hints = FALSE, dbg = TRUE) {
+clean_accessibility <- function(access, give_hints = FALSE, dbg = TRUE)
+{
   replace_all <- function(string, pattern, replacement) {
     stringr::str_replace_all(
       string = string,
@@ -133,7 +134,8 @@ clean_accessibility <- function(
 #' refs_clean_df <- clean_references_df(endnote_list)
 #' head(refs_clean_df)
 #' }
-clean_references_df <- function(endnote_list, give_hints = FALSE, dbg = TRUE) {
+clean_references_df <- function(endnote_list, give_hints = FALSE, dbg = TRUE)
+{
   refs_df <- create_references_df(endnote_list, collapse = TRUE)
 
   refs_df <- kwb.utils::catAndRun(

R/create_df_from_endnote_xml.R

@@ -14,24 +14,29 @@
 #' references_df <- create_df_from_endnote_xml()
 #' head(references_df)
 #'
-create_df_from_endnote_xml <- function(endnote_xml = default_xml()) {
+create_df_from_endnote_xml <- function(endnote_xml = default_xml())
+{
   references <- kwb.read::read_xml_as_path_value(endnote_xml)
 
   xml_paths <- references$path %>%
     stringr::str_remove_all(pattern = "^/xml/records/record")
 
   references_df <- kwb.utils::asNoFactorDataFrame(cbind(
     kwb.file::to_subdir_matrix(xml_paths),
-    references[, -1]
+    references[, -1L]
   ))
 
-  references_df[, 1] <- as.numeric(stringr::str_remove_all(
-    references_df[, 1], "\\[|\\]"
+  references_df[, 1L] <- as.numeric(stringr::str_remove_all(
+    references_df[, 1L], "\\[|\\]"
   ))
 
   n_col <- ncol(references_df)
 
-  colnames(references_df) <- c("record_id", paste0("key", 1:(n_col - 2)), "value")
+  colnames(references_df) <- c(
+    "record_id",
+    paste0("key", seq_len(n_col - 2L)),
+    "value"
+  )
 
   endnote_df <- dplyr::left_join(
     references_df,
@@ -41,7 +46,8 @@ create_df_from_endnote_xml <- function(endnote_xml = default_xml()) {
   add_file_info_attributes(endnote_df, endnote_xml)
 }
 
-if (FALSE) {
+if (FALSE)
+{
   abstracts <- references_df %>%
     dplyr::filter(.data$key1 == "abstract") %>%
     dplyr::group_by(

R/create_endnote_list.R

@@ -10,9 +10,9 @@
 #' str(endnote_list[1]$record)
 #' attr(endnote_list, "xml_file_info")
 #' attr(endnote_list, "xml_filename_without_extension")
-create_endnote_list <- function(endnote_xml = default_xml()) {
+create_endnote_list <- function(endnote_xml = default_xml())
+{
   endnote_list <- xml2::as_list(xml2::read_xml(endnote_xml))$xml$records
 
-
   add_file_info_attributes(endnote_list, endnote_xml)
 }

R/create_list_by_pubtype_from_df.R

@@ -12,7 +12,8 @@
 #' refs_list_by_pubtype <- create_list_by_pubtype_from_df(refs_df)
 #' str(refs_list_by_pubtype, 1)
 #' }
-create_list_by_pubtype_from_df <- function(refs_df) {
+create_list_by_pubtype_from_df <- function(refs_df)
+{
   refs_df <- refs_df %>%
     dplyr::arrange(dplyr::desc(.data$rec_number))
 

R/create_list_with_unique_entries.R

@@ -12,7 +12,8 @@
 #' unique_entries_list <- create_list_with_unique_entries(refs_df)
 #' str(unique_entries_list, 1)
 #' }
-create_list_with_unique_entries <- function(refs_df) {
+create_list_with_unique_entries <- function(refs_df)
+{
   select_columns <- function(pattern) {
     columns <- unique(stringr::str_extract(names(refs_df), pattern))
     columns[!is.na(columns)]