#ropensci review #1

ropensci · Jun 26, 2017 · 2f38c20 · 2f38c20
1 parent bf8df39
commit 2f38c20
Show file tree

Hide file tree

Showing 17 changed files with 53 additions and 180 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: bib2df
 Type: Package
 Title: Parse a BibTeX File to a data.frame
-Version: 0.2
+Version: 0.2.1
 Authors@R: c(person("Philipp", "Ottolinger", email = "philipp@ottolinger.de", role = c("aut", "cre")),
              person("Thomas", "Leeper", email = "thosjleeper@gmail.com", role = "ctb"),
              person("Maëlle", "Salmon", email = "maelle.salmon@yahoo.se", role = "ctb"))
@@ -12,7 +12,6 @@ License: GPL-3
 LazyData: TRUE
 Imports:
     dplyr,
-    plyr,
     stringr,
     humaniformat
 Suggests:

diff --git a/NAMESPACE b/NAMESPACE
@@ -1,15 +1,12 @@
 # Generated by roxygen2: do not edit by hand
 
 export(bib2df)
-export(bib2df_gather)
-export(bib2df_read)
-export(bib2df_tidy)
 export(df2bib)
 import(dplyr)
+importFrom(dplyr,bind_rows)
 importFrom(humaniformat,format_period)
 importFrom(humaniformat,format_reverse)
 importFrom(humaniformat,parse_names)
-importFrom(plyr,rbind.fill)
 importFrom(stats,complete.cases)
 importFrom(stringr,str_extract)
 importFrom(stringr,str_match)

diff --git a/NEWS.md b/NEWS.md
@@ -1,6 +1,11 @@
+# bib2df 0.2.1
+
+* 
+
+
 # bib2df 0.2
 
 * Standardized return value for `bib2df()` (#5, @leeper)
-* Added functionality to write data.frame back to BibTeX file (`df2bib()`) (#5, @leeper)
-* Adds a testthat-based tests for both bib2df() and df2bib() (#5, @leeper)
+* Added functionality to write `data.frame` back to BibTeX file (`df2bib()`) (#5, @leeper)
+* Adds a testthat-based tests for both `bib2df()` and `df2bib()` (#5, @leeper)
 * Added functionality of the `humaniformat` package to split up names (#4)
diff --git a/R/bib2df-package.R b/R/bib2df-package.R
@@ -1,13 +1,13 @@
-#' bib2df: Parse a BibTeX file to data.frame
+#' bib2df: Parse a BibTeX file to \code{data.frame}
 #'
 #' This package provides functions to parse and write BibTeX files. BibTeX files
-#' can be parsed to data.frame to make them accessible with popular tools like
-#' dplyr, tidyr, ggplot2 and many more.
+#' can be parsed to \code{data.frame} to make them accessible with popular tools like
+#' \code{dplyr}, \code{tidyr}, \code{ggplot2} and many more.
 #'
-#' BibTeX entries represented in a data.frame can be altered in a familar way and
+#' BibTeX entries represented in a \code{data.frame} can be altered in a familiar way and
 #' written back to a valid BibTeX file.
 #'
-#' To learn more about bib2df, start with the vignettes:
+#' To learn more about \code{bib2df}, start with the vignettes:
 #'  \code{browseVignettes(package = "bib2df")}
 #' @docType package
 #' @name bib2df-package

diff --git a/R/bib2df.R b/R/bib2df.R
@@ -1,6 +1,6 @@
-#' @title Parse a BibTeX file to a \code{data.frame}..
-#' @description The BibTeX file is read, parsed, tidied and written to a \code{data.frame}..
-#' @details Uses the internal \code{bib2df_read()}, \code{bib2df_gather()} and \code{bib2df_tidy()}. No magic, just a wrapper.
+#' @title Parse a BibTeX file to a \code{data.frame}
+#' @description The BibTeX file is read, parsed, tidied and written to a \code{data.frame}
+#' @details For simplicity \code{bib2df()} unifies the reading, parsing and tidying of a BibTeX file while being aware of a standardized output format, different BibTeX styles and missing values in the BibTeX file.
 #' @param file character, path to a .bib file.
 #' @param separate_names logical, should authors' and editors' names be separated into first and given name?
 #' @return A \code{data.frame}.
@@ -10,7 +10,7 @@
 #' bib2df(path)
 #' @seealso \code{\link{df2bib}}
 #' @export
-bib2df <- function(file, separate_names = c(FALSE, TRUE)) {
+bib2df <- function(file, separate_names = FALSE) {
   bib <- bib2df_read(file)
   bib <- bib2df_gather(bib)
   bib <- bib2df_tidy(bib, separate_names)

diff --git a/R/bib2df_gather.R b/R/bib2df_gather.R
@@ -1,25 +1,15 @@
-#' @title Parse a .bib file.
-#' @description \code{bib2df_gather} parses a .bib file and returns each BibTeX-item as a row in a \code{data.frame}.
-#' @details \code{bib2df_gather} extracts the BibTeX entry types, fields and the respective values. Each item is presented as a row in a data_frame whereas the entry type (column \code{CATEGORY}) is added to each row.
-#' @param bib, a character vector resulting from \code{bib2df_read()}.
-#' @return A \code{data.frame}.
-#' @author Philipp Ottolinger
 #' @importFrom stringr str_match
 #' @importFrom stringr str_extract
-#' @importFrom plyr rbind.fill
+#' @importFrom dplyr bind_rows
 #' @importFrom stats complete.cases
-#' @export bib2df_gather
-#' @examples
-#' path <- system.file("extdata", "biblio.bib", package = "bib2df")
-#' bib <- bib2df_read(path)
-#' bib <- bib2df_gather(bib)
+
 bib2df_gather <- function(bib) {
   from <- which(!is.na(str_match(bib, "@")))
   to  <- c(from[-1], length(bib))
   if (!length(from)) {
     return(empty)
   }
-  itemslist <- mapply(function(x,y) return(bib[x:y]), x = from, y = to - 1)
+  itemslist <- mapply(function(x, y) return(bib[x:y]), x = from, y = to - 1)
   keys <- lapply(itemslist,
                  function(x) {
                    str_extract(x[1], "(?<=@\\w{1,50}\\{)((.*)){1}(?=,)")
@@ -71,23 +61,23 @@ bib2df_gather <- function(bib) {
   items <- mapply(cbind, categories, values)
   items <- lapply(items,
                   function(x) {
-                    x <- cbind(toupper(x[,1]), x[,2])
+                    x <- cbind(toupper(x[, 1]), x[, 2])
                   }
   )
   items <- lapply(items,
                   function(x) {
-                    x[complete.cases(x),]
+                    x[complete.cases(x), ]
                   }
   )
-  items <- mapply(function(x,y) {
+  items <- mapply(function(x, y) {
     rbind(x, c("CATEGORY", y))
     },
     x = items, y = fields)
   items <- lapply(items, t)
   items <- lapply(items,
                   function(x) {
-                    colnames(x) <- x[1,]
-                    x <- x[-1,]
+                    colnames(x) <- x[1, ]
+                    x <- x[-1, ]
                     return(x)
                   }
   )
@@ -98,7 +88,7 @@ bib2df_gather <- function(bib) {
                     return(x)
                   }
   )
-  dat <- rbind.fill(c(list(empty), items))
+  dat <- bind_rows(c(list(empty), items))
   dat <- as_data_frame(dat)
   dat$BIBTEXKEY <- unlist(keys)
   dat

diff --git a/R/bib2df_read.R b/R/bib2df_read.R
@@ -1,15 +1,5 @@
-#' @title Read a .bib file.
-#' @description \code{bib2df_read()} reads a .bib file to a character vector.
-#' @details \code{bib2df_read()} uses \code{base::readLines()} to read from a local .bib file. UTF-8 compatibility is ensured.
-#' @param file character, path to a .bib file.
-#' @return A character vector.
-#' @author Philipp Ottolinger
 #' @importFrom stringr str_replace_all
-#' @export bib2df_read
-#' @examples
-#' path <- system.file("extdata", "biblio.bib", package = "bib2df")
-#' bib <- bib2df_read(path)
-#' bib
+
 bib2df_read <- function(file) {
   bib <- readLines(file)
   bib <- str_replace_all(bib, "[^[:graph:]]", " ")

diff --git a/R/bib2df_tidy.R b/R/bib2df_tidy.R
@@ -1,21 +1,8 @@
-#' @title Tidy a bib2df \code{data.frame}..
-#' @description \code{bib2df_tidy()} aims to tidy a \code{data.frame}. resulting from \code{bib2df_gather()}.
-#' @details If multiple Authors or Editors are supplied, the respective character string is split up into a list. The year of publication is converted to \code{as.numeric()}. The \code{CATEGORY} column moves to the very left of the tibble.
-#' @param bib, resulting from \code{bib2df_gather()}.
-#' @param separate_names logical, should authors' and editors' names be separated into first and given name?
-#' @author Philipp Ottolinger
-#' @return A \code{data.frame}.
-#' @export bib2df_tidy
 #' @import dplyr
 #' @importFrom humaniformat format_reverse
 #' @importFrom humaniformat format_period
 #' @importFrom humaniformat parse_names
-#' @examples
-#' path <- system.file("extdata", "biblio.bib", package = "bib2df")
-#' bib <- bib2df_read(path)
-#' bib <- bib2df_gather(bib)
-#' bib <- bib2df_tidy(bib)
-#' bib
+
 bib2df_tidy <- function(bib, separate_names = c(FALSE, TRUE)) {
   AUTHOR <- EDITOR <- YEAR <- CATEGORY <- NULL
   if ("AUTHOR" %in% colnames(bib)) {

diff --git a/R/df2bib.R b/R/df2bib.R
@@ -1,6 +1,6 @@
-#' @title Export a BibTeX data.frame to a .bib file.
-#' @description The BibTeX data.frame is written to a .bib file
-#' @param x data.frame, returned by \code{\link{df2bib}}.
+#' @title Export a BibTeX \code{data.frame} to a .bib file
+#' @description The BibTeX \code{data.frame} is written to a .bib file
+#' @param x \code{data.frame}, returned by \code{\link{df2bib}}.
 #' @param file character, path to a .bib file.
 #' @return \code{file} as a character string, invisibly.
 #' @author Thomas J. Leeper
@@ -16,12 +16,12 @@ df2bib <- function(x, file) {
     paste0(substr(string, 1, 1),
            tolower(substr(string, 2, nchar(string) )))
   }
-  naReplace <- function(df) {
+  na_replace <- function(df) {
     df[is.na(df)] <- ""
     return(df)
   }
   if (class(x$AUTHOR[[1]]) == "data.frame") {
-    x$AUTHOR <- lapply(x$AUTHOR, naReplace)
+    x$AUTHOR <- lapply(x$AUTHOR, na_replace)
     x$AUTHOR <- lapply(x$AUTHOR,
                        function(x) {
                          paste(x$last_name,

diff --git a/man/bib2df-package.Rd b/man/bib2df-package.Rd
diff --git a/man/bib2df.Rd b/man/bib2df.Rd
diff --git a/man/bib2df_gather.Rd b/man/bib2df_gather.Rd
diff --git a/man/bib2df_read.Rd b/man/bib2df_read.Rd
diff --git a/man/bib2df_tidy.Rd b/man/bib2df_tidy.Rd
diff --git a/man/df2bib.Rd b/man/df2bib.Rd
diff --git a/tests/testthat/tests.R b/tests/testthat/tests.R
@@ -19,4 +19,3 @@ test_that("df2bib() works", {
   expect_true(file.exists(df2bib(bib, bib2 <- tempfile())))
   expect_true(identical(bib, bib2df(bib2)))
 })
-