Prepare for intermediate release

DESCRIPTION

@@ -1,9 +1,9 @@
 Package: pdftools
 Type: Package
 Title: Text Extraction, Rendering and Converting of PDF Documents
-Version: 1.5.9000
-Author: Jeroen Ooms
-Maintainer: Jeroen Ooms <[email protected]>
+Version: 1.6
+Authors@R: person("Jeroen", "Ooms", role = c("aut", "cre"), email = "[email protected]",
+      comment = c(ORCID = "0000-0002-4035-0289"))
 Description: Utilities based on 'libpoppler' for extracting text, fonts, attachments and 
     metadata from a PDF file. Also supports high quality rendering of PDF documents info
     PNG, JPEG, TIFF format, or into raw bitmap vectors for further processing in R.

NAMESPACE

@@ -2,7 +2,6 @@
 
 export(pdf_attachments)
 export(pdf_convert)
-export(pdf_data)
 export(pdf_fonts)
 export(pdf_info)
 export(pdf_render_page)

NEWS

@@ -1,4 +1,5 @@
 1.6
+  - pdf_render_page() and pdf_convert() gain argument to control 'antialias'
   - Small tweaks in pdf_text() for dealing with malformed pdf files
 
 1.5

R/RcppExports.R

@@ -13,10 +13,6 @@ poppler_pdf_info <- function(x, opw, upw) {
     .Call('_pdftools_poppler_pdf_info', PACKAGE = 'pdftools', x, opw, upw)
 }
 
-poppler_pdf_data <- function(x, opw, upw) {
-    .Call('_pdftools_poppler_pdf_data', PACKAGE = 'pdftools', x, opw, upw)
-}
-
 poppler_pdf_text <- function(x, opw, upw) {
     .Call('_pdftools_poppler_pdf_text', PACKAGE = 'pdftools', x, opw, upw)
 }

R/tools.R

@@ -5,7 +5,7 @@
 #'
 #' Poppler is pretty verbose when encountering minor errors in PDF files,
 #' in especially \code{\link{pdf_text}}. These messages are usually safe
-#' to ignore, use \code{\link{suppressMessages}} to hide them alltogether.
+#' to ignore, use \code{\link{suppressMessages}} to hide them altogether.
 #'
 #' @export
 #' @param pdf file path or raw vector with pdf data
@@ -32,12 +32,6 @@ pdf_text <- function(pdf, opw = "", upw = "") {
   poppler_pdf_text(loadfile(pdf), opw, upw)
 }
 
-#' @rdname pdftools
-#' @export
-pdf_data <- function(pdf, opw = "", upw = "") {
-  poppler_pdf_data(loadfile(pdf), opw, upw)
-}
-
 #' @rdname pdftools
 #' @export
 pdf_fonts<- function(pdf, opw = "", upw = "") {

src/RcppExports.cpp

@@ -38,19 +38,6 @@ BEGIN_RCPP
     return rcpp_result_gen;
 END_RCPP
 }
-// poppler_pdf_data
-List poppler_pdf_data(RawVector x, std::string opw, std::string upw);
-RcppExport SEXP _pdftools_poppler_pdf_data(SEXP xSEXP, SEXP opwSEXP, SEXP upwSEXP) {
-BEGIN_RCPP
-    Rcpp::RObject rcpp_result_gen;
-    Rcpp::RNGScope rcpp_rngScope_gen;
-    Rcpp::traits::input_parameter< RawVector >::type x(xSEXP);
-    Rcpp::traits::input_parameter< std::string >::type opw(opwSEXP);
-    Rcpp::traits::input_parameter< std::string >::type upw(upwSEXP);
-    rcpp_result_gen = Rcpp::wrap(poppler_pdf_data(x, opw, upw));
-    return rcpp_result_gen;
-END_RCPP
-}
 // poppler_pdf_text
 CharacterVector poppler_pdf_text(RawVector x, std::string opw, std::string upw);
 RcppExport SEXP _pdftools_poppler_pdf_text(SEXP xSEXP, SEXP opwSEXP, SEXP upwSEXP) {
@@ -154,7 +141,6 @@ static const R_CallMethodDef CallEntries[] = {
     {"_pdftools_set_poppler_data", (DL_FUNC) &_pdftools_set_poppler_data, 1},
     {"_pdftools_get_poppler_config", (DL_FUNC) &_pdftools_get_poppler_config, 0},
     {"_pdftools_poppler_pdf_info", (DL_FUNC) &_pdftools_poppler_pdf_info, 3},
-    {"_pdftools_poppler_pdf_data", (DL_FUNC) &_pdftools_poppler_pdf_data, 3},
     {"_pdftools_poppler_pdf_text", (DL_FUNC) &_pdftools_poppler_pdf_text, 3},
     {"_pdftools_poppler_pdf_fonts", (DL_FUNC) &_pdftools_poppler_pdf_fonts, 3},
     {"_pdftools_poppler_pdf_files", (DL_FUNC) &_pdftools_poppler_pdf_files, 3},

src/bindings.cpp

@@ -12,10 +12,6 @@
 #include <Rcpp.h>
 #include <cstring>
 
-#if defined(POPPLER_VERSION_MINOR) && (POPPLER_VERSION_MINOR >= 63 || POPPLER_VERSION_MAJOR > 0)
-#define POPPLER_HAS_PAGE_TEXT_LIST
-#endif
-
 using namespace Rcpp;
 using namespace poppler;
 
@@ -164,45 +160,6 @@ List poppler_pdf_info (RawVector x, std::string opw, std::string upw) {
   );
 }
 
-// [[Rcpp::export]]
-List poppler_pdf_data (RawVector x, std::string opw, std::string upw) {
-#ifdef POPPLER_HAS_PAGE_TEXT_LIST
-  document *doc = read_raw_pdf(x, opw, upw);
-  Rcpp::List out(doc->pages());
-  for(int i = 0; i < doc->pages(); i++){
-    page *p(doc->create_page(i));
-    if(!p) continue; //missing page
-    std::vector<text_box> boxes = p->text_list();
-    CharacterVector text(boxes.size());
-    IntegerVector width(boxes.size());
-    IntegerVector height(boxes.size());
-    IntegerVector x(boxes.size());
-    IntegerVector y(boxes.size());
-    Rcpp::LogicalVector space(boxes.size());
-    for(size_t j = 0; j < boxes.size(); j++){
-      text[j] = ustring_to_utf8(boxes.at(j).text());
-      width[j] = boxes.at(j).bbox().width();
-      height[j] = boxes.at(j).bbox().height();
-      x[j] = boxes.at(j).bbox().x();
-      y[j] = boxes.at(j).bbox().y();
-      space[j] = boxes.at(j).has_space_after();
-    }
-    out[i] = DataFrame::create(
-      _["text"] = text,
-      _["width"] = width,
-      _["height"] = height,
-      _["x"] = x,
-      _["y"] = y,
-      _["space"] = space,
-      _["stringsAsFactors"] = false
-    );
-  }
-  return out;
-#else //POPPLER_HAS_PAGE_TEXT_LIST
-  throw std::runtime_error(std::string("This feature requires poppler >= 0.63. You have ") + POPPLER_VERSION);
-#endif
-}
-
 // [[Rcpp::export]]
 CharacterVector poppler_pdf_text (RawVector x, std::string opw, std::string upw) {
   document *doc = read_raw_pdf(x, opw, upw);