read encrypted xlsx files

DESCRIPTION

@@ -43,3 +43,5 @@ Roxygen: list(markdown = TRUE)
 Config/testthat/edition: 3
 Config/testthat/parallel: false
 Config/testthat/start-first: aaa
+SystemRequirements: C++20, libarchive: libarchive-dev (deb),
+ libarchive-devel (rpm), libarchive (homebrew), libarchive_dev (csw)

R/RcppExports.R

@@ -1,6 +1,10 @@
 # Generated by using Rcpp::compileAttributes() -> do not edit by hand
 # Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393
 
+read_encryption <- function(PATH, OUT, PASSWORD) {
+ invisible(.Call(`_openxlsx2_read_encryption`, PATH, OUT, PASSWORD))
+}
+
 #' Check if path is to long to be an R file path
 #' @param path the file path used in file.exists()
 #' @noRd

R/wb_load.R

@@ -49,6 +49,14 @@ wb_load <- function(
  stop("File does not exist.")
  }
 
+ pwd <- list(...)$password
+
+ if (!is.null(pwd)) {
+ unencrypted_xlsx <- temp_xlsx()
+ read_encryption(PATH = path.expand(file), OUT = unencrypted_xlsx, PASSWORD = pwd)
+ file <- unencrypted_xlsx
+ }
+
  ## create temp dir
  xmlDir <- temp_dir("_openxlsx_wb_load")
 

configure

@@ -0,0 +1,78 @@
+# Anticonf (tm) script by Jeroen Ooms, Jim Hester (2017)
+# This script will query 'pkg-config' for the required cflags and ldflags.
+# If pkg-config is unavailable or does not find the library, try setting
+# INCLUDE_DIR and LIB_DIR manually via e.g:
+# R CMD INSTALL --configure-vars='INCLUDE_DIR=/.../include LIB_DIR=/.../lib'
+
+# Library settings
+PKG_CONFIG_NAME="libarchive"
+PKG_DEB_NAME="libarchive-dev"
+PKG_RPM_NAME="libarchive-devel"
+PKG_CSW_NAME="libarchive_dev"
+PKG_BREW_NAME="libarchive"
+PKG_TEST_HEADER="<archive.h>"
+PKG_LIBS=-larchive
+
+# Use pkg-config if available
+pkg-config ${PKG_CONFIG_NAME} --atleast-version=1.0 2>/dev/null
+if [ $? -eq 0 ]; then
+ PKGCONFIG_CFLAGS=`pkg-config --cflags ${PKG_CONFIG_NAME}`
+ PKGCONFIG_LIBS=`pkg-config --libs ${PKG_CONFIG_NAME}`
+fi
+
+# Note that cflags may be empty in case of success
+if [ "$INCLUDE_DIR" ] || [ "$LIB_DIR" ]; then
+ echo "Found INCLUDE_DIR and/or LIB_DIR!"
+ PKG_CFLAGS="-I$INCLUDE_DIR $PKG_CFLAGS"
+ PKG_LIBS="-L$LIB_DIR $PKG_LIBS"
+elif [ "$PKGCONFIG_CFLAGS" ] || [ "$PKGCONFIG_LIBS" ]; then
+ echo "Found pkg-config cflags and libs!"
+ PKG_CFLAGS=${PKGCONFIG_CFLAGS}
+ PKG_LIBS=${PKGCONFIG_LIBS}
+elif [ `uname` = "Darwin" ]; then
+ test ! "$CI" && brew --version 2>/dev/null
+ if [ $? -eq 0 ]; then
+ BREWDIR=`brew --prefix`
+ PKG_CFLAGS="-I$BREWDIR/opt/libarchive/include"
+ PKG_LIBS="-L$BREWDIR/opt/libarchive/lib $PKG_LIBS"
+ else
+ curl -sfL "https://autobrew.github.io/scripts/$PKG_BREW_NAME" > autobrew
+ . ./autobrew
+ fi
+fi
+
+# Find compiler
+CXX20=`${R_HOME}/bin/R CMD config CXX20`
+CXX20FLAGS=`${R_HOME}/bin/R CMD config CXX20FLAGS`
+CPPFLAGS=`${R_HOME}/bin/R CMD config CPPFLAGS`
+
+# For debugging
+echo "PKG_CFLAGS=$PKG_CFLAGS"
+echo "PKG_LIBS=$PKG_LIBS"
+
+# Test configuration
+echo "#include $PKG_TEST_HEADER" | ${CXX20} ${CPPFLAGS} ${PKG_CFLAGS} ${CXX20FLAGS} -E -xc++ - > /dev/null
+
+# Customize the error
+if [ $? -ne 0 ]; then
+ echo "--------------------------- [ANTICONF] --------------------------------"
+ echo "Configuration failed because $PKG_CONFIG_NAME was not found. Try installing:"
+ echo " * deb: $PKG_DEB_NAME (Debian, Ubuntu, etc)"
+ echo " * rpm: $PKG_RPM_NAME (Fedora, CentOS, RHEL)"
+ echo " * csw: $PKG_CSW_NAME (Solaris)"
+ echo " * brew: $PKG_BREW_NAME (Mac OSX)"
+ echo "If $PKG_CONFIG_NAME is already installed, check that 'pkg-config' is in your"
+ echo "PATH and PKG_CONFIG_PATH contains a $PKG_CONFIG_NAME.pc file. If pkg-config"
+ echo "is unavailable you can set INCLUDE_DIR and LIB_DIR manually via:"
+ echo "R CMD INSTALL --configure-vars='INCLUDE_DIR=... LIB_DIR=...'"
+ echo "-------------------------- [ERROR MESSAGE] ---------------------------"
+ cat configure.log
+ echo "--------------------------------------------------------------------"
+ exit 1
+fi
+
+# Write to Makevars
+sed -e "s|@PKG_CXXFLAGS@|$PKG_CFLAGS|" -e "s|@PKG_LIBS@|$PKG_LIBS|" src/Makevars.in > src/Makevars
+
+# Success
+exit 0

src/Makevars

@@ -1 +1,42 @@
-PKG_CPPFLAGS = -I. -I../inst/include/pugixml
+
+#PKG_CPPFLAGS = -I. -I../inst/include/pugixml -Ixlcpp -DXLCPP_EXPORT
+PKG_CXXFLAGS = -I. -Ixlcpp -I../inst/include/pugixml -DXLCPP_EXPORT
+
+#PKG_LIBS=-Lpugixml -Lcfbf -L/usr/lib -larchive -L/usr/lib -lfmt
+PKG_LIBS = -larchive -Lpugixml -Lxlcpp -lfmt
+
+PKGROOT = ./xlcpp
+
+OBJECTS = decrypt.o \
+ helper_functions.o \
+ load_workbook.o \
+ pugi.o \
+ strings_xml.o \
+ styles_xml.o \
+ write_file.o \
+ $(PKGROOT)/aes.o \
+ $(PKGROOT)/b64.o \
+ $(PKGROOT)/cfbf.o \
+ $(PKGROOT)/mmap.o \
+ $(PKGROOT)/sha1.o \
+ $(PKGROOT)/sha512.o \
+ $(PKGROOT)/xlcpp.o \
+ $(PKGROOT)/xlsb.o \
+ $(PKGROOT)/xml-reader.o \
+ $(PKGROOT)/xml-writer.o \
+ RcppExports.o
+
+XLCPP = $(PKGROOT)/aes.cpp \
+ $(PKGROOT)/b64.cpp \
+ $(PKGROOT)/cfbf.cpp \
+ $(PKGROOT)/mmap.cpp \
+ $(PKGROOT)/sha1.cpp \
+ $(PKGROOT)/sha512.cpp \
+ $(PKGROOT)/xml-reader.cpp \
+ $(PKGROOT)/xml-writer.cpp \
+ $(PKGROOT)/xlcpp.cpp \
+ $(PKGROOT)/xlsb.cpp
+
+PUGIXML = ../inst/include/pugixml/pugixml.cpp
+
+# CXX_STD=CXX20

src/Makevars.in

@@ -0,0 +1,42 @@
+
+#PKG_CPPFLAGS = -I. -I../inst/include/pugixml -Ixlcpp -DXLCPP_EXPORT
+PKG_CXXFLAGS = @PKG_CXXFLAGS@ -I. -Ixlcpp -I../inst/include/pugixml -DXLCPP_EXPORT
+
+#PKG_LIBS=-Lpugixml -Lcfbf -L/usr/lib -larchive -L/usr/lib -lfmt
+PKG_LIBS = @PKG_LIBS@ -Lpugixml -Lxlcpp -lfmt
+
+PKGROOT = ./xlcpp
+
+OBJECTS = decrypt.o \
+ helper_functions.o \
+ load_workbook.o \
+ pugi.o \
+ strings_xml.o \
+ styles_xml.o \
+ write_file.o \
+ $(PKGROOT)/aes.o \
+ $(PKGROOT)/b64.o \
+ $(PKGROOT)/cfbf.o \
+ $(PKGROOT)/mmap.o \
+ $(PKGROOT)/sha1.o \
+ $(PKGROOT)/sha512.o \
+ $(PKGROOT)/xlcpp.o \
+ $(PKGROOT)/xlsb.o \
+ $(PKGROOT)/xml-reader.o \
+ $(PKGROOT)/xml-writer.o \
+ RcppExports.o
+
+XLCPP = $(PKGROOT)/aes.cpp \
+ $(PKGROOT)/b64.cpp \
+ $(PKGROOT)/cfbf.cpp \
+ $(PKGROOT)/mmap.cpp \
+ $(PKGROOT)/sha1.cpp \
+ $(PKGROOT)/sha512.cpp \
+ $(PKGROOT)/xml-reader.cpp \
+ $(PKGROOT)/xml-writer.cpp \
+ $(PKGROOT)/xlcpp.cpp \
+ $(PKGROOT)/xlsb.cpp
+
+PUGIXML = ../inst/include/pugixml/pugixml.cpp
+
+# CXX_STD=CXX20

src/RcppExports.cpp

@@ -11,6 +11,18 @@ Rcpp::Rostream<true>& Rcpp::Rcout = Rcpp::Rcpp_cout_get();
 Rcpp::Rostream<false>& Rcpp::Rcerr = Rcpp::Rcpp_cerr_get();
 #endif
 
+// read_encryption
+void read_encryption(std::string PATH, std::string OUT, std::string PASSWORD);
+RcppExport SEXP _openxlsx2_read_encryption(SEXP PATHSEXP, SEXP OUTSEXP, SEXP PASSWORDSEXP) {
+BEGIN_RCPP
+ Rcpp::RNGScope rcpp_rngScope_gen;
+ Rcpp::traits::input_parameter< std::string >::type PATH(PATHSEXP);
+ Rcpp::traits::input_parameter< std::string >::type OUT(OUTSEXP);
+ Rcpp::traits::input_parameter< std::string >::type PASSWORD(PASSWORDSEXP);
+ read_encryption(PATH, OUT, PASSWORD);
+ return R_NilValue;
+END_RCPP
+}
 // to_long
 bool to_long(std::string path);
 RcppExport SEXP _openxlsx2_to_long(SEXP pathSEXP) {
@@ -842,6 +854,7 @@ END_RCPP
 }
 
 static const R_CallMethodDef CallEntries[] = {
+ {"_openxlsx2_read_encryption", (DL_FUNC) &_openxlsx2_read_encryption, 3},
  {"_openxlsx2_to_long", (DL_FUNC) &_openxlsx2_to_long, 1},
  {"_openxlsx2_openxlsx2_type", (DL_FUNC) &_openxlsx2_openxlsx2_type, 1},
  {"_openxlsx2_int_to_col", (DL_FUNC) &_openxlsx2_int_to_col, 1},

src/decrypt.cpp

@@ -0,0 +1,12 @@
+#include <xlcpp/xlcpp.h>
+
+// [[Rcpp::export]]
+void read_encryption(std::string PATH, std::string OUT, std::string PASSWORD) {
+
+ const std::filesystem::path path = PATH;
+
+ xlcpp::workbook wb(path, PASSWORD, OUT);
+
+ // this creates xlcpp workbook, not the unzipped xlsx file
+ // wb.save(OUT);
+}