Improve encoding non-ASCII characters to LaTeX in toBiblatex (#113)

* Remove appveyor CI Signed-off-by: Mathew W. McLean <[email protected]> * Avoid msg about page numbers in ReadPDFs for 1page PDFs * Always use pdfinfo to determine number of pages in each PDF in ReadPDFs even when use.metadata is FALSE * This avoids a message from pdftotext about incorrect pages * Refactor test-readPDF.R to make it clearer when tests are skipped if poppler is not installed Signed-off-by: Mathew W. McLean <[email protected]> * Fix pkg documentation for latest roxygen2 Signed-off-by: Mathew W. McLean <[email protected]> * Fixes for non-ASCII name list fields in toBiblatex and toBibtex * Add latexify() from dplR instead of tools::encoded_text_to_latex to improve conversion of non-ASCII characters to valid latex * Fixes #102, #105, #106 Signed-off-by: Mathew W. McLean <[email protected]> * Update documentation for latexify author Signed-off-by: Mathew W. McLean <[email protected]> * Add website to DESCRIPTION Signed-off-by: Mathew W. McLean <[email protected]> * Use default value for rettype in ReadPubMed * c.f. https://www.ncbi.nlm.nih.gov/books/NBK25499/table/chapter4.T._valid_values_of__retmode_and/ * Add mock response for one GetPubMedByID test Signed-off-by: Mathew W. McLean <[email protected]> * Add more sleep for PubMed/Entrez test Signed-off-by: Mathew W. McLean <[email protected]> --------- Signed-off-by: Mathew W. McLean <[email protected]>
ropensci · Nov 19, 2024 · d616da5 · d616da5
1 parent 2619809
commit d616da5
Show file tree

Hide file tree

Showing 16 changed files with 449 additions and 144 deletions.
diff --git a/.appveyor.yml b/.appveyor.yml
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,9 +1,11 @@
 Package: RefManageR
-Version: 1.4.0
+Version: 1.4.3
 Title: Straightforward 'BibTeX' and 'BibLaTeX' Bibliography Management
-Authors@R: person(c("Mathew", "W."), "McLean", role = c("aut", "cre"),
+Authors@R: c(person(c("Mathew", "W."), "McLean", role = c("aut", "cre"),
     email = "[email protected]",
-    comment = c(ORCID = "0000-0002-7891-9645"))
+    comment = c(ORCID = "0000-0002-7891-9645")),
+    person("Andy", "Bunn", role = "ctb",
+    email = "[email protected]", comment = "function latexify used by toBiblatex"))
 Maintainer: Mathew W. McLean <[email protected]>
 Description: Provides tools for importing and working with bibliographic
     references. It greatly enhances the 'bibentry' class by providing a class
@@ -27,6 +29,8 @@ Imports:
     httr,
     lubridate (>= 1.5.0),
     stringr,
+    stringi,
+    R.utils,
     methods,
     bibtex (>= 0.4.1)
 Suggests:
@@ -38,5 +42,5 @@ Depends:
     R (>= 3.0)
 VignetteBuilder: knitr
 BugReports: https://github.com/ropensci/RefManageR/issues
-URL: https://github.com/ropensci/RefManageR/
-RoxygenNote: 7.2.1
+URL: https://github.com/ropensci/RefManageR/, https://docs.ropensci.org/RefManageR/
+RoxygenNote: 7.3.2
diff --git a/NAMESPACE b/NAMESPACE
@@ -49,6 +49,7 @@ export(as.BibEntry)
 export(fields)
 export(is.BibEntry)
 export(toBiblatex)
+importFrom(R.utils,captureOutput)
 importFrom(bibtex,do_read_bib)
 importFrom(httr,GET)
 importFrom(httr,POST)
@@ -73,6 +74,9 @@ importFrom(methods,hasArg)
 importFrom(plyr,llply)
 importFrom(plyr,progress_text)
 importFrom(stats,setNames)
+importFrom(stringi,stri_trans_nfc)
+importFrom(stringi,stri_trans_nfd)
+importFrom(stringi,stri_unescape_unicode)
 importFrom(stringr,str_length)
 importFrom(stringr,str_sub)
 importFrom(stringr,str_trim)
@@ -82,7 +86,6 @@ importFrom(tools,Rd2txt)
 importFrom(tools,Rd2txt_options)
 importFrom(tools,bibstyle)
 importFrom(tools,deparseLatex)
-importFrom(tools,encoded_text_to_latex)
 importFrom(tools,getBibstyle)
 importFrom(tools,latexToUtf8)
 importFrom(tools,loadPkgRdMacros)

diff --git a/R/ReadPDFs.R b/R/ReadPDFs.R
@@ -89,8 +89,28 @@ ReadPDFs <- function (path, .enc = 'UTF-8', recursive = TRUE,
                                out, pages.idx))
   }else
   {
+    .findPages <- function(files)
+    {
+      n.files <- length(files)
+      page.bounding.boxes <- lapply(files, function(x)
+        system2("pdfinfo", paste(shQuote('-enc'),
+                                 shQuote(.enc), shQuote("-box"),
+                                 shQuote(normalizePath(x))),
+                stdout = TRUE, stderr = TRUE))
+      pages.idx <- lapply(page.bounding.boxes, grep, pattern = "^Pages:")
+      pages <- rep(Inf, n.files)
+      for (i in seq_along(pages.idx))
+      {
+        if (length(pages.idx[[i]]))
+          pages[i] <- as.integer(sub("^Pages:\\s+(\\d+)", "\\1",
+                                     page.bounding.boxes[[i]][pages.idx[[i]]],
+                                     perl = TRUE))
+      }
+      return(pages)
+    }
+
     doi.meta.ind <- logical(n.files)
-    pages <- rep(Inf, n.files)
+    pages <- .findPages(files)
   }
 
   ########################################

diff --git a/R/ReadPubMed.R b/R/ReadPubMed.R
@@ -114,12 +114,10 @@ GetPubMedByID <- function(id, db = "pubmed", ...){
     parms$id <- paste0(id, collapse=",")
 
   parms$retmode <- "xml"
-  parms$rettype <- "medline"
 
   base.url <- "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?"
-  ## temp <- postForm(base.url, .params = parms)
-  ## tdoc <- xmlParse(temp)
   temp <- POST(base.url, query = parms)
+  stop_for_status(temp)
   tdoc <- read_xml(temp)
 
   ## Note: directly using xpathApply on tdoc won't work if some results are

diff --git a/R/RefManageR-package.R b/R/RefManageR-package.R
@@ -1,20 +1,8 @@
-#' Import and Manage BibTeX and BibLaTeX references with RefManageR
-#'
-#' RefManageR provides tools for importing and working with
-#' bibliographic references.  It greatly enhances the bibentry class by
-#' providing a class BibEntry which stores BibTeX and BibLaTeX references,
-#' supports UTF-8 encoding, and can be easily searched by any field, by date
-#' ranges, and by various formats for name lists (author by last names,
-#' translator by full names, etc.). Entries can be updated, combined, sorted, printed
-#' in a number of styles, and exported. BibTeX and BibLaTeX .bib files can be
-#' read into R and converted to BibEntry objects.  Interfaces to NCBI's
-#' Entrez, CrossRef, and Zotero are provided for importing references and
-#' references can be created from locally stored PDFs using Poppler.  Includes
-#' functions for citing and generating a bibliography with hyperlinks for
-#' documents prepared with RMarkdown or RHTML.
+#' @keywords internal
+"_PACKAGE"
+
 #' @name RefManageR-package
 #' @aliases RefManageR refmanager
-#' @docType package
 #' @author McLean, M. W. \email{mathew.w.mclean@@gmail.com}
 #' @details
 #' \bold{Importing and Creating References}
@@ -56,7 +44,7 @@
 #' \code{\link{Cite}}.  Its interface is similar to \code{\link{options}}.
 #' @keywords package
 #' @references McLean, M. W. (2014). Straightforward Bibliography Management in R Using the RefManageR Package.
-#' \href{https://arxiv.org/abs/1403.2036}{arXiv: 1403.2036 [cs.DL]}. Submitted.
+#' \href{https://arxiv.org/abs/1403.2036}{arXiv: 1403.2036 [cs.DL]}.
 #' @references Kime, P., M. Wemheuer, and P. Lehman (2022). The biblatex Package.
 #' \url{http://mirrors.ibiblio.org/CTAN/macros/latex/contrib/biblatex/doc/biblatex.pdf}.
 #' @references Hornik, K., D. Murdoch, and A. Zeileis (2012).

diff --git a/R/WriteBib.R b/R/WriteBib.R
@@ -21,7 +21,6 @@
 #' @note To write the contents of \code{bib} \dQuote{as is}, the argument
 #' \code{biblatex} should be \code{TRUE}, otherwise
 #' conversion is done as in \code{\link{toBibtex.BibEntry}}.
-#' @importFrom tools encoded_text_to_latex
 #' @author McLean, M. W. based on \code{write.bib} by Gaujoux, R.
 #' in package \code{bibtex}.
 #' @export