From a5b93e403581ee3f864335ebd17a8d28c901dcd8 Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <Sebastian.Jeworutzki@rub.de>
Date: Fri, 9 Oct 2015 07:37:54 +0200
Subject: [PATCH 01/21] added importFrom directives - again...

---
 NAMESPACE | 6 ++++++
 R/dbcal.R | 1 +
 R/read.R  | 2 ++
 R/save.R  | 1 +
 R/tools.R | 2 ++
 5 files changed, 12 insertions(+)

diff --git a/NAMESPACE b/NAMESPACE
index cf8526cf..25f5ea62 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -13,4 +13,10 @@ export(set.lang)
 export(stata_pre13_save)
 export(stbcal)
 import(Rcpp)
+importFrom(stats,complete.cases)
+importFrom(stats,na.omit)
+importFrom(utils,download.file)
+importFrom(utils,localeToCharset)
+importFrom(utils,setTxtProgressBar)
+importFrom(utils,txtProgressBar)
 useDynLib(readstata13)
diff --git a/R/dbcal.R b/R/dbcal.R
index f507a4e8..aac4e585 100644
--- a/R/dbcal.R
+++ b/R/dbcal.R
@@ -43,6 +43,7 @@
 #' @author Sebastian Jeworutzki \email{sebastian.jeworutzki@@ruhr-uni-bochum.de}
 #' @examples
 #' sp500 <- stbcal(system.file("extdata/sp500.stbcal", package="readstata13"))
+#' @importFrom stats complete.cases
 #' @export
 stbcal <- function(stbcalfile) {
 
diff --git a/R/read.R b/R/read.R
index 2c0f40f3..5a22583e 100644
--- a/R/read.R
+++ b/R/read.R
@@ -105,6 +105,8 @@
 #' @author Jan Marvin Garbuszus \email{jan.garbuszus@@ruhr-uni-bochum.de}
 #' @author Sebastian Jeworutzki \email{sebastian.jeworutzki@@ruhr-uni-bochum.de}
 #' @useDynLib readstata13
+#' @importFrom utils download.file 
+#' @importFrom stats na.omit 
 #' @export
 read.dta13 <- function(file, convert.factors = TRUE, generate.factors=FALSE,
                        encoding = NULL, fromEncoding=NULL,
diff --git a/R/save.R b/R/save.R
index 04790057..28b011e8 100644
--- a/R/save.R
+++ b/R/save.R
@@ -61,6 +61,7 @@
 #' @author Jan Marvin Garbuszus \email{jan.garbuszus@@ruhr-uni-bochum.de}
 #' @author Sebastian Jeworutzki \email{sebastian.jeworutzki@@ruhr-uni-bochum.de}
 #' @useDynLib readstata13
+#' @importFrom utils localeToCharset
 #' @export
 save.dta13 <- function(data, file, data.label=NULL, time.stamp=TRUE,
                        convert.factors=FALSE, convert.dates=TRUE, tz="GMT",
diff --git a/R/tools.R b/R/tools.R
index 5febe16e..469dff8a 100644
--- a/R/tools.R
+++ b/R/tools.R
@@ -258,6 +258,8 @@ get.varlabel <- function(dat, var.name=NULL, lang=NA) {
 #' get.varlabel(datDE)
 #' @author Jan Marvin Garbuszus \email{jan.garbuszus@@ruhr-uni-bochum.de}
 #' @author Sebastian Jeworutzki \email{sebastian.jeworutzki@@ruhr-uni-bochum.de}
+#' @importFrom stats na.omit
+#' @importFrom utils txtProgressBar setTxtProgressBar
 #' @export
 set.lang <- function(dat, lang=NA, generate.factors=FALSE) {
   if (is.na(lang) | lang == get.lang(dat, F)$default) {

From 8d6d691307574a92e51fccc2ac34e4f6f93c6b2b Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <Sebastian.Jeworutzki@rub.de>
Date: Fri, 9 Oct 2015 08:11:16 +0200
Subject: [PATCH 02/21] Fixed some comments

---
 R/read.R          | 14 ++++++--------
 man/read.dta13.Rd | 16 +++++++---------
 2 files changed, 13 insertions(+), 17 deletions(-)

diff --git a/R/read.R b/R/read.R
index 5a22583e..c61c6797 100644
--- a/R/read.R
+++ b/R/read.R
@@ -47,7 +47,7 @@
 #' @details If the filename is a url, the file will be downloaded as a temporary
 #'  file and read afterwards.
 #'
-#' Stata files are encoded in ansinew. Depending on your system default encoding
+#' Stata files are encoded in ansinew. Depending on your system's default encoding
 #'  certain characters may appear wrong. Using a correct encoding may fix these.
 #'
 #' Variable names stored in the dta-file will be used in the resulting
@@ -67,14 +67,12 @@
 #'
 #' In R, you may use rownames to store characters (see for instance
 #'  \code{data(swiss)}). In Stata, this is not possible and rownames have to be
-#'  stored as a variable.  If this is the case for your file and you want to use
-#'  rownames, \code{add.rownames=TRUE} will convert the first variable of the
-#'  dta-file into rownames of the resulting data.frame.
+#'  stored as a variable. If you want to use rownames, set add.rownames to TRUE. 
+#'  Then the first variable of the dta-file will hold the rownames of the resulting 
+#'  data.frame.
 #'
-#' Beginning with Stata 13 (format 117), a new dta-format was introduced, which
-#'  was not handled by foreign at the time. It was implemented in this package
-#'  therefore the package got its name. Reading dta-files from earlier Stata
-#'  versions was not implemented until version 0.8.
+#' Reading dta-files of older and newer versions than 13 was introduced 
+#'  with version 0.8.
 #' @return The function returns a data.frame with attributes. The attributes
 #'  include
 #' \describe{
diff --git a/man/read.dta13.Rd b/man/read.dta13.Rd
index 0cd4f779..52d7fd90 100644
--- a/man/read.dta13.Rd
+++ b/man/read.dta13.Rd
@@ -75,7 +75,7 @@ The function returns a data.frame with attributes. The attributes
 If the filename is a url, the file will be downloaded as a temporary
  file and read afterwards.
 
-Stata files are encoded in ansinew. Depending on your system default encoding
+Stata files are encoded in ansinew. Depending on your system's default encoding
  certain characters may appear wrong. Using a correct encoding may fix these.
 
 Variable names stored in the dta-file will be used in the resulting
@@ -95,14 +95,12 @@ Stata 13 introduced a new character type called strL. strLs are able to store
 
 In R, you may use rownames to store characters (see for instance
  \code{data(swiss)}). In Stata, this is not possible and rownames have to be
- stored as a variable.  If this is the case for your file and you want to use
- rownames, \code{add.rownames=TRUE} will convert the first variable of the
- dta-file into rownames of the resulting data.frame.
-
-Beginning with Stata 13 (format 117), a new dta-format was introduced, which
- was not handled by foreign at the time. It was implemented in this package
- therefore the package got its name. Reading dta-files from earlier Stata
- versions was not implemented until version 0.8.
+ stored as a variable. If you want to use rownames, set add.rownames to TRUE.
+ Then the first variable of the dta-file will hold the rownames of the resulting
+ data.frame.
+
+Reading dta-files of older and newer versions than 13 was introduced
+ with version 0.8.
 }
 \note{
 read.dta13 uses GPL 2 licensed code by Thomas Lumley and R-core members

From 44352f4ae05c3bc6400b1e334a11b353876c5409 Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <Sebastian.Jeworutzki@rub.de>
Date: Fri, 9 Oct 2015 08:48:28 +0200
Subject: [PATCH 03/21] bump version number

---
 DESCRIPTION | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index f991bf9b..ebe61c1c 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: readstata13
 Type: Package
 Title: Import Stata Data Files
-Version: 0.7.1
+Version: 0.8.1
 Authors@R: c(
     person("Jan Marvin", "Garbuszus",
     email = "jan.garbuszus@ruhr-uni-bochum.de", role = c("aut")),

From bf6e46392ee2b5a75f4529e47a7cb75e3f92a202 Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <Sebastian.Jeworutzki@rub.de>
Date: Fri, 9 Oct 2015 09:01:05 +0200
Subject: [PATCH 04/21] fixed typo in warnings

---
 src/rcpp_pre13_savestata.cpp | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/src/rcpp_pre13_savestata.cpp b/src/rcpp_pre13_savestata.cpp
index f059f12e..7e1e4d18 100644
--- a/src/rcpp_pre13_savestata.cpp
+++ b/src/rcpp_pre13_savestata.cpp
@@ -121,7 +121,7 @@ int stata_pre13_save(const char * filePath, Rcpp::DataFrame dat)
 
     /* write a datalabel */
     if (datalabel.size() > ndlabel)
-      Rcpp::warning("Datalabel to long. Resizing. Max size is %d.",
+      Rcpp::warning("Datalabel too long. Resizing. Max size is %d.",
                     ndlabel - 1);
 
     dta.write(datalabel.c_str(), ndlabel);
@@ -131,7 +131,7 @@ int stata_pre13_save(const char * filePath, Rcpp::DataFrame dat)
     {
       if (timestamp.size() > 18)
       {
-        Rcpp::warning("Timestamp to long. Dropping.");
+        Rcpp::warning("Timestamp too long. Dropping.");
         timestamp = "";
       }
       dta.write(timestamp.c_str(),timestamp.size());
@@ -189,7 +189,7 @@ int stata_pre13_save(const char * filePath, Rcpp::DataFrame dat)
       string nvarname = as<string>(nvarnames[i]);
 
       if (nvarname.size() > nvarnameslen)
-        Rcpp::warning("Varname to long. Resizing. Max size is %d",
+        Rcpp::warning("Varname too long. Resizing. Max size is %d",
                       nvarnameslen - 1);
 
       dta.write(nvarname.c_str(),nvarnameslen);
@@ -210,7 +210,7 @@ int stata_pre13_save(const char * filePath, Rcpp::DataFrame dat)
       string nformats = as<string>(formats[i]);
 
       if (nformats.size() > nformatslen)
-        Rcpp::warning("Formats to long. Resizing. Max size is %d",
+        Rcpp::warning("Formats too long. Resizing. Max size is %d",
                       nformatslen - 1);
 
       dta.write(nformats.c_str(),nformatslen);
@@ -222,7 +222,7 @@ int stata_pre13_save(const char * filePath, Rcpp::DataFrame dat)
       string nvalLabels = as<string>(valLabels[i]);
 
       if (nvalLabels.size() > nvalLabelslen)
-        Rcpp::warning("Vallabel to long. Resizing. Max size is %d",
+        Rcpp::warning("Vallabel too long. Resizing. Max size is %d",
                       nvalLabelslen - 1);
 
       dta.write(nvalLabels.c_str(), nvalLabelslen);
@@ -237,7 +237,7 @@ int stata_pre13_save(const char * filePath, Rcpp::DataFrame dat)
         nvarLabels = as<std::string>(varLabels[i]);
 
         if (nvarLabels.size() > nvarLabelslen)
-          Rcpp::warning("Varlabel to long. Resizing. Max size is %d",
+          Rcpp::warning("Varlabel too long. Resizing. Max size is %d",
                         nvarLabelslen - 1);
       }
       dta.write(nvarLabels.c_str(),nvarLabelslen);
@@ -391,7 +391,7 @@ int stata_pre13_save(const char * filePath, Rcpp::DataFrame dat)
           // Stata 6-12 can only store 244 byte strings
           if(val_s.size()>maxstrsize)
           {
-            Rcpp::warning("Character Var.to long. Resizing. Max size is %d.",
+            Rcpp::warning("Character value too long. Resizing. Max size is %d.",
                           maxstrsize);
             // val_s.resize(244);
           }
@@ -464,7 +464,7 @@ int stata_pre13_save(const char * filePath, Rcpp::DataFrame dat)
           string labtext = as<string>(labelText[i]);
           if (labtext.size() > maxlabelsize)
           {
-            Rcpp::warning("Label to long. Resizing. Max size is %d",
+            Rcpp::warning("Label too long. Resizing. Max size is %d",
                           maxlabelsize);
             labtext.resize(maxlabelsize);
             // labtext[labtext.size()] = '\0';

From 0ab3dcd5246a98989034bf6e3a7dee87a305e644 Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <Sebastian.Jeworutzki@rub.de>
Date: Fri, 9 Oct 2015 10:09:28 +0200
Subject: [PATCH 05/21] make factor conversion for float and double values an
 option, fixes in help text for read.dta13

---
 R/read.R          | 25 ++++++++++++++++---------
 man/read.dta13.Rd | 14 +++++++++-----
 2 files changed, 25 insertions(+), 14 deletions(-)

diff --git a/R/read.R b/R/read.R
index c61c6797..3eb901d5 100644
--- a/R/read.R
+++ b/R/read.R
@@ -43,6 +43,8 @@
 #'  converted.
 #' @param add.rownames \emph{logical.} If \code{TRUE}, the first column will be
 #'  used as rownames. Variable will be dropped afterwards.
+#' @param nonint.factors \emph{logical.} If \code{TRUE}, factors labels 
+#'  will be assigned to variables of type float and double.
 #'
 #' @details If the filename is a url, the file will be downloaded as a temporary
 #'  file and read afterwards.
@@ -61,9 +63,10 @@
 #' dates.
 #'
 #' Stata 13 introduced a new character type called strL. strLs are able to store
-#'  strings of any size up to 2 billion characters.  While R is able to store
-#'  strings of this size in a character, certain data.frames may appear messed,
-#'  if long strings are inserted default is \code{FALSE}.
+#'  strings up to 2 billion characters.  While R is able to store
+#'  strings of this size in a character vector, the printed representation of such 
+#'  vectors looks rather cluttered, so by default only a reference is saved in the 
+#'  data.frame (\code{replace.strl=FALSE}). 
 #'
 #' In R, you may use rownames to store characters (see for instance
 #'  \code{data(swiss)}). In Stata, this is not possible and rownames have to be
@@ -110,7 +113,7 @@ read.dta13 <- function(file, convert.factors = TRUE, generate.factors=FALSE,
                        encoding = NULL, fromEncoding=NULL,
                        convert.underscore = FALSE, missing.type = FALSE,
                        convert.dates = TRUE, replace.strl = FALSE,
-                       add.rownames = FALSE) {
+                       add.rownames = FALSE, nonint.factors=FALSE) {
   # Check if path is a url
   if (length(grep("^(http|ftp|https)://", file))) {
     tmp <- tempfile()
@@ -319,8 +322,13 @@ read.dta13 <- function(file, convert.factors = TRUE, generate.factors=FALSE,
       vartype <- types[i]
       labtable <- label[[labname]]
       #don't convert columns of type double or float to factor
-      if (labname %in% names(label) & !(vartype == sdouble | vartype == sfloat))
-      {
+      if (labname %in% names(label)) {
+        if((vartype == sdouble | vartype == sfloat)) {
+          if(!nonint.factors) {
+            warning(paste0("\n  ",vnames[i], ":\n  Factor codes of type double or float detected - no labels assigned.\n  Set option nonint.factors to TRUE to assign labels anyway."))
+            next
+          }
+        }
         # get unique values / omit NA
         varunique <- na.omit(unique(data[, i]))
         # assign label if label set is complete
@@ -335,13 +343,12 @@ read.dta13 <- function(file, convert.factors = TRUE, generate.factors=FALSE,
           data[, i] <- factor(data[, i], levels=gen.lab,
                               labels=names(gen.lab))
         } else {
-          warning(paste(vnames[i], "Missing factor labels - no labels assigned.
-                        Set option generate.factors=T to generate labels."))
+          warning(paste0("\n  ",vnames[i], ":\n  Missing factor labels - no labels assigned.\n  Set option generate.factors=T to generate labels."))
         }
       }
     }
   }
-
+  
   if (add.rownames) {
     rownames(data) <- data[[1]]
     data[[1]] <- NULL
diff --git a/man/read.dta13.Rd b/man/read.dta13.Rd
index 52d7fd90..48c8a9fb 100644
--- a/man/read.dta13.Rd
+++ b/man/read.dta13.Rd
@@ -7,7 +7,7 @@
 read.dta13(file, convert.factors = TRUE, generate.factors = FALSE,
   encoding = NULL, fromEncoding = NULL, convert.underscore = FALSE,
   missing.type = FALSE, convert.dates = TRUE, replace.strl = FALSE,
-  add.rownames = FALSE)
+  add.rownames = FALSE, nonint.factors = FALSE)
 }
 \arguments{
 \item{file}{\emph{character.} Path to the dta file you want to import.}
@@ -42,7 +42,10 @@ a strL string in the data.frame with the actual value. The strl attribute
 will be removed from the data.frame.}
 
 \item{add.rownames}{\emph{logical.} If \code{TRUE}, the first column will be
- used as rownames. Variable will be dropped afterwards.}
+used as rownames. Variable will be dropped afterwards.}
+
+\item{nonint.factors}{\emph{logical.} If \code{TRUE}, factors labels
+ will be assigned to variables of type float and double.}
 }
 \value{
 The function returns a data.frame with attributes. The attributes
@@ -89,9 +92,10 @@ Stata dates are converted to R's Date class the same way foreign handles
 dates.
 
 Stata 13 introduced a new character type called strL. strLs are able to store
- strings of any size up to 2 billion characters.  While R is able to store
- strings of this size in a character, certain data.frames may appear messed,
- if long strings are inserted default is \code{FALSE}.
+ strings up to 2 billion characters.  While R is able to store
+ strings of this size in a character vector, the printed representation of such
+ vectors looks rather cluttered, so by default only a reference is saved in the
+ data.frame (\code{replace.strl=FALSE}).
 
 In R, you may use rownames to store characters (see for instance
  \code{data(swiss)}). In Stata, this is not possible and rownames have to be

From 1e43c341b0531354dc109e140f0a412ea60bafd8 Mon Sep 17 00:00:00 2001
From: Marvin <jmg@edna>
Date: Fri, 9 Oct 2015 12:15:16 +0200
Subject: [PATCH 06/21] Implement a pre R-3.2 version of dir.exists(). Will be
 replaced sometime in the future.

---
 R/save.R  | 2 +-
 R/tools.R | 6 ++++++
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/R/save.R b/R/save.R
index 28b011e8..0afca23e 100644
--- a/R/save.R
+++ b/R/save.R
@@ -71,7 +71,7 @@ save.dta13 <- function(data, file, data.label=NULL, time.stamp=TRUE,
 
   if (!is.data.frame(data))
     stop("The object \"data\" must have class data.frame")
-  if (!dir.exists(dirname(file)))
+  if (!dir.exists13(dirname(file)))
     stop("Path is invalid. Possibly a non existend directory.")
 
   # Allow writing version as Stata version not Stata format
diff --git a/R/tools.R b/R/tools.R
index 469dff8a..08660460 100644
--- a/R/tools.R
+++ b/R/tools.R
@@ -33,6 +33,12 @@ save.encoding <- function(x, encoding) {
         sub="byte")
 }
 
+# Function to check if directory exists
+# @param x file path
+dir.exists13 <-function(x) {
+  path <- dirname(x)
+  return(file.exists(path))
+}
 
 # Construct File Path
 #

From efd1496fb537d150c94489b864848744d5e52971 Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <sebastian.jeworutzki@ruhr-uni-bochum.de>
Date: Sun, 11 Oct 2015 21:34:40 +0200
Subject: [PATCH 07/21] update see also section in r help

---
 R/read.R          | 4 ++--
 R/save.R          | 4 ++--
 man/read.dta13.Rd | 4 ++--
 man/save.dta13.Rd | 4 ++--
 4 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/R/read.R b/R/read.R
index 3eb901d5..094b8323 100644
--- a/R/read.R
+++ b/R/read.R
@@ -99,8 +99,8 @@
 #' }
 #' @note read.dta13 uses GPL 2 licensed code by Thomas Lumley and R-core members
 #'  from foreign::read.dta().
-#' @seealso \code{\link{read.dta}} and \code{memisc} for dta files from Stata
-#' versions < 13.
+#' @seealso \code{\link[foreign]{read.dta}} in package \code{foreign} and \code{memisc} for dta files from Stata
+#' versions < 13 and \code{\link[haven]{read_dta}} in package \code{haven} for Stata version >= 13.
 #' @references Stata Corp (2014): Description of .dta file format
 #'  \url{http://www.stata.com/help.cgi?dta}
 #' @author Jan Marvin Garbuszus \email{jan.garbuszus@@ruhr-uni-bochum.de}
diff --git a/R/save.R b/R/save.R
index 0afca23e..fd4a3f1b 100644
--- a/R/save.R
+++ b/R/save.R
@@ -54,8 +54,8 @@
 #'    type. The first element is the identifier and the second element the
 #'    string.}
 #' }
-#' @seealso \code{\link[foreign]{write.dta}} and \code{memisc} for dta files
-#' from Stata versions < 13.
+#' @seealso \code{\link[foreign]{read.dta}} in package \code{foreign} and \code{memisc} for dta files from Stata
+#' versions < 13 and \code{\link[haven]{read_dta}} in package \code{haven} for Stata version >= 13.
 #' @references Stata Corp (2014): Description of .dta file format
 #'  \url{http://www.stata.com/help.cgi?dta}
 #' @author Jan Marvin Garbuszus \email{jan.garbuszus@@ruhr-uni-bochum.de}
diff --git a/man/read.dta13.Rd b/man/read.dta13.Rd
index 48c8a9fb..dc6828e3 100644
--- a/man/read.dta13.Rd
+++ b/man/read.dta13.Rd
@@ -120,7 +120,7 @@ Stata Corp (2014): Description of .dta file format
  \url{http://www.stata.com/help.cgi?dta}
 }
 \seealso{
-\code{\link{read.dta}} and \code{memisc} for dta files from Stata
-versions < 13.
+\code{\link[foreign]{read.dta}} in package \code{foreign} and \code{memisc} for dta files from Stata
+versions < 13 and \code{\link[haven]{read_dta}} in package \code{haven} for Stata version >= 13.
 }
 
diff --git a/man/save.dta13.Rd b/man/save.dta13.Rd
index 3dc6ac80..3bab679a 100644
--- a/man/save.dta13.Rd
+++ b/man/save.dta13.Rd
@@ -72,7 +72,7 @@ Stata Corp (2014): Description of .dta file format
  \url{http://www.stata.com/help.cgi?dta}
 }
 \seealso{
-\code{\link[foreign]{write.dta}} and \code{memisc} for dta files
-from Stata versions < 13.
+\code{\link[foreign]{read.dta}} in package \code{foreign} and \code{memisc} for dta files from Stata
+versions < 13 and \code{\link[haven]{read_dta}} in package \code{haven} for Stata version >= 13.
 }
 

From 49332b6433195a0be126b76ffdd8787dfa54573f Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <Sebastian.Jeworutzki@rub.de>
Date: Thu, 15 Oct 2015 22:02:42 +0000
Subject: [PATCH 08/21] changed fseeks to test. respect initial reading of tags
 in testing of end tags

---
 inst/include/readstata.h   | 17 +++++++++
 inst/include/swap_endian.h |  2 +-
 src/read_dta.cpp           | 75 ++++++++++++++++++++++++++------------
 3 files changed, 69 insertions(+), 25 deletions(-)

diff --git a/inst/include/readstata.h b/inst/include/readstata.h
index ad93f9b5..599e2cb2 100644
--- a/inst/include/readstata.h
+++ b/inst/include/readstata.h
@@ -21,7 +21,23 @@
 #include <Rcpp.h>
 #include <fstream>
 #include <string>
+
+#define GCC_VERSION (__GNUC__ * 10000 \
++ __GNUC_MINOR__ * 100                \
++ __GNUC_PATCHLEVEL__)
+
+/* Test for GCC < 4.9.0 */
+#if GCC_VERSION < 40900 & !__clang__
+    typedef signed char int8_t;
+    typedef unsigned char uint8_t;
+    typedef signed short int16_t;
+    typedef unsigned short uint16_t;
+    typedef signed int int32_t;
+    typedef unsigned int uint32_t;
+#else
 #include <stdint.h>
+#endif
+
 
 #include "read_dta.h"
 #include "read_pre13_dta.h"
@@ -76,6 +92,7 @@ inline void test(std::string testme, FILE * file)
   readstring(test,file, test.size());
   if (testme.compare(test)!=0)
   {
+    Rcpp::warning("\n testme:%s \n test: %s\n", testme.c_str(), test.c_str());
     Rcpp::stop("When attempting to read %s: Something went wrong!", testme.c_str());
   }
 }
diff --git a/inst/include/swap_endian.h b/inst/include/swap_endian.h
index d7189ce0..343465b3 100644
--- a/inst/include/swap_endian.h
+++ b/inst/include/swap_endian.h
@@ -1,7 +1,7 @@
 #ifndef SWAP_ENDIAN
 #define SWAP_ENDIAN
 
-#include <stdint.h>
+/*#include <stdint.h>*/
 #include <typeinfo>
 
 #define GCC_VERSION (__GNUC__ * 10000 \
diff --git a/src/read_dta.cpp b/src/read_dta.cpp
index c6791814..b230946b 100644
--- a/src/read_dta.cpp
+++ b/src/read_dta.cpp
@@ -21,7 +21,8 @@ using namespace Rcpp;
 using namespace std;
 
 List read_dta(FILE * file, const bool missing) {
-  fseek(file, 18, SEEK_CUR);// stata_dta><header>
+  //fseek(file, 18, SEEK_CUR);// stata_dta><header>
+  test("stata_dta><header>", file);
   test("<release>", file);
 
   /*
@@ -73,7 +74,8 @@ List read_dta(FILE * file, const bool missing) {
     break;
   }
 
-  fseek(file, 10, SEEK_CUR); // </release>
+  //fseek(file, 10, SEEK_CUR); // </release>
+  test("</release>", file);
   test("<byteorder>", file);
 
   /*
@@ -83,7 +85,8 @@ List read_dta(FILE * file, const bool missing) {
   std::string byteorder(3, '\0');
   readstring(byteorder,file, byteorder.size());
 
-  fseek(file, 12, SEEK_CUR); // </byteorder>
+  //fseek(file, 12, SEEK_CUR); // </byteorder>
+  test("</byteorder>", file);
   test("<K>", file);
 
   bool swapit = 0;
@@ -96,7 +99,8 @@ List read_dta(FILE * file, const bool missing) {
   uint16_t k = 0;
   k = readbin(k, file, swapit);
 
-  fseek(file, 4, SEEK_CUR); //</K>
+  //fseek(file, 4, SEEK_CUR); //</K>
+  test("</K>", file);
   test("<N>", file);
 
   /*
@@ -112,7 +116,8 @@ List read_dta(FILE * file, const bool missing) {
     n = readbin(n, file, swapit);
   }
 
-  fseek(file, 4, SEEK_CUR); //</N>
+  //fseek(file, 4, SEEK_CUR); //</N>
+  test("</N>", file);
   test("<label>", file);
 
   /*
@@ -141,7 +146,8 @@ List read_dta(FILE * file, const bool missing) {
   CharacterVector datalabelCV(1);
   datalabelCV(0) = datalabel;
 
-  fseek(file, 8, SEEK_CUR); //</label>
+  //fseek(file, 8, SEEK_CUR); //</label>
+  test("</label>", file);
   test("<timestamp>", file);
 
   /*
@@ -164,7 +170,8 @@ List read_dta(FILE * file, const bool missing) {
   }
 
   CharacterVector timestampCV = timestamp;
-  fseek(file, 21, SEEK_CUR); //</timestamp></header>
+  //fseek(file, 21, SEEK_CUR); //</timestamp></header>
+  test("</timestamp></header>", file);
   test("<map>", file);
 
   /*
@@ -194,7 +201,8 @@ List read_dta(FILE * file, const bool missing) {
     map[i] = nmap;
   }
 
-  fseek(file, 6, SEEK_CUR); //</map>
+  //fseek(file, 6, SEEK_CUR); //</map>
+  test("</map>", file);
   test("<variable_types>", file);
 
   /*
@@ -216,7 +224,8 @@ List read_dta(FILE * file, const bool missing) {
     vartype[i] = nvartype;
   }
 
-  fseek(file, 17, SEEK_CUR); //</variable_types>
+  //fseek(file, 17, SEEK_CUR); //</variable_types>
+  test("</variable_types>", file);
   test("<varnames>", file);
 
   /*
@@ -232,7 +241,8 @@ List read_dta(FILE * file, const bool missing) {
     varnames[i] = nvarnames;
   }
 
-  fseek(file, 11, SEEK_CUR); //</varnames>
+  //fseek(file, 11, SEEK_CUR); //</varnames>
+  test("</varnames>", file);
   test("<sortlist>", file);
 
   /*
@@ -252,7 +262,8 @@ List read_dta(FILE * file, const bool missing) {
     sortlist[i] = nsortlist;
   }
 
-  fseek(file, 11, SEEK_CUR); //</sortlist>
+  //fseek(file, 11, SEEK_CUR); //</sortlist>
+  test("</sortlist>", file);
   test("<formats>", file);
 
   /*
@@ -269,7 +280,8 @@ List read_dta(FILE * file, const bool missing) {
     formats[i] = nformats;
   }
 
-  fseek(file, 10, SEEK_CUR); //</formats>
+  //fseek(file, 10, SEEK_CUR); //</formats>
+  test("</formats>", file);
   test("<value_label_names>",file);
 
   /*
@@ -287,7 +299,8 @@ List read_dta(FILE * file, const bool missing) {
     valLabels[i] = nvalLabels;
   }
 
-  fseek(file, 20, SEEK_CUR); //</value_label_names>
+  //fseek(file, 20, SEEK_CUR); //</value_label_names>
+  test("</value_label_names>", file);
   test("<variable_labels>", file);
 
   /*
@@ -303,7 +316,8 @@ List read_dta(FILE * file, const bool missing) {
     varLabels[i] = nvarLabels;
   }
 
-  fseek(file, 18, SEEK_CUR); //</variable_labels>
+  //fseek(file, 18, SEEK_CUR); //</variable_labels>
+  test("</variable_labels>", file);
   test("<characteristics>", file);
 
   /*
@@ -324,11 +338,13 @@ List read_dta(FILE * file, const bool missing) {
 
   List ch = List();
   CharacterVector chs(3);
-
-  while (chtag.compare(tago)==0)
+  
+  if(chtag.compare(tago)==0)
   {
-    uint32_t nocharacter = 0;
-    nocharacter = readbin(nocharacter, file, swapit);
+    while (chtag.compare(tago)==0)
+    {
+      uint32_t nocharacter = 0;
+      nocharacter = readbin(nocharacter, file, swapit);
 
     std::string chvarname(chlen, '\0');
     std::string chcharact(chlen, '\0');
@@ -354,7 +370,9 @@ List read_dta(FILE * file, const bool missing) {
     readstring(tago, file, tago.size());
   }
 
-  fseek(file, 14, SEEK_CUR); //[</ch]aracteristics>
+  //fseek(file, 14, SEEK_CUR); //[</ch]aracteristics>
+  }
+  test("aracteristics>", file);
   test("<data>", file);
 
   /*
@@ -515,7 +533,8 @@ List read_dta(FILE * file, const bool missing) {
   df.attr("names") = varnames;
   df.attr("class") = "data.frame";
 
-  fseek(file, 7, SEEK_CUR); //</data>
+  //fseek(file, 7, SEEK_CUR); //</data>
+  test("</data>", file);
   test("<strls>", file);
 
   /*
@@ -533,7 +552,8 @@ List read_dta(FILE * file, const bool missing) {
   readstring(tags, file, tags.size());
 
   List strlstable = List(); //put strLs into this list
-
+if(gso.compare(tags)==0)
+{
   while(gso.compare(tags)==0)
   {
     CharacterVector strls(2);
@@ -588,7 +608,11 @@ List read_dta(FILE * file, const bool missing) {
   }
 
   // after strls
-  fseek(file, 5, SEEK_CUR); //[</s]trls>
+  //fseek(file, 5, SEEK_CUR); //[</s]trls>
+  //test("</strls>", file);
+} 
+  test("trls>", file);
+
   test("<value_labels>", file);
 
   /*
@@ -607,7 +631,7 @@ List read_dta(FILE * file, const bool missing) {
   readstring(tag, file, tag.size());
 
   List labelList = List(); //put labels into this list
-
+if(lbltag.compare(tag)==0) {
   while(lbltag.compare(tag)==0)
   {
     int32_t nlen = 0, labn = 0, txtlen = 0, noff = 0, val = 0;
@@ -695,7 +719,10 @@ List read_dta(FILE * file, const bool missing) {
    * close the file
    */
 
-  fseek(file, 10, SEEK_CUR); // [</val]ue_labels>
+  //fseek(file, 10, SEEK_CUR); // [</val]ue_labels>#
+  //test("</value_labels>", file);
+} 
+  test("ue_labels>", file);
   test("</stata_dta>", file);
 
 

From b721e04951fd15b47faad96434350040eb0eb1c3 Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <Sebastian.Jeworutzki@rub.de>
Date: Fri, 16 Oct 2015 00:13:51 +0200
Subject: [PATCH 09/21] Update DESCRIPTION

---
 DESCRIPTION | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index ebe61c1c..c303f42b 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: readstata13
 Type: Package
 Title: Import Stata Data Files
-Version: 0.8.1
+Version: 0.8.2
 Authors@R: c(
     person("Jan Marvin", "Garbuszus",
     email = "jan.garbuszus@ruhr-uni-bochum.de", role = c("aut")),

From 96f768526c442cefc0ca0c2b1a7d34caf388ed96 Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <sebastian.jeworutzki@ruhr-uni-bochum.de>
Date: Fri, 16 Oct 2015 09:49:02 +0200
Subject: [PATCH 10/21] removed not needed ifs

---
 src/read_dta.cpp | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/src/read_dta.cpp b/src/read_dta.cpp
index b230946b..6d5ccd3f 100644
--- a/src/read_dta.cpp
+++ b/src/read_dta.cpp
@@ -339,8 +339,6 @@ List read_dta(FILE * file, const bool missing) {
   List ch = List();
   CharacterVector chs(3);
   
-  if(chtag.compare(tago)==0)
-  {
     while (chtag.compare(tago)==0)
     {
       uint32_t nocharacter = 0;
@@ -371,7 +369,7 @@ List read_dta(FILE * file, const bool missing) {
   }
 
   //fseek(file, 14, SEEK_CUR); //[</ch]aracteristics>
-  }
+  
   test("aracteristics>", file);
   test("<data>", file);
 
@@ -552,8 +550,7 @@ List read_dta(FILE * file, const bool missing) {
   readstring(tags, file, tags.size());
 
   List strlstable = List(); //put strLs into this list
-if(gso.compare(tags)==0)
-{
+
   while(gso.compare(tags)==0)
   {
     CharacterVector strls(2);
@@ -610,7 +607,7 @@ if(gso.compare(tags)==0)
   // after strls
   //fseek(file, 5, SEEK_CUR); //[</s]trls>
   //test("</strls>", file);
-} 
+ 
   test("trls>", file);
 
   test("<value_labels>", file);
@@ -631,7 +628,7 @@ if(gso.compare(tags)==0)
   readstring(tag, file, tag.size());
 
   List labelList = List(); //put labels into this list
-if(lbltag.compare(tag)==0) {
+  
   while(lbltag.compare(tag)==0)
   {
     int32_t nlen = 0, labn = 0, txtlen = 0, noff = 0, val = 0;
@@ -721,7 +718,7 @@ if(lbltag.compare(tag)==0) {
 
   //fseek(file, 10, SEEK_CUR); // [</val]ue_labels>#
   //test("</value_labels>", file);
-} 
+ 
   test("ue_labels>", file);
   test("</stata_dta>", file);
 

From 03e3b8a73c7918c90af29031e8dfddd604356e6c Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <Sebastian.Jeworutzki@rub.de>
Date: Mon, 19 Oct 2015 09:32:21 +0200
Subject: [PATCH 11/21] bump version / add download badge

---
 README.md | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index cabc66a1..73d592bb 100644
--- a/README.md
+++ b/README.md
@@ -35,12 +35,12 @@ users need to install
 
 ```R
 # install.packages("devtools")
-devtools::install_github("sjewo/readstata13", ref="0.8")
+devtools::install_github("sjewo/readstata13", ref="0.8.1")
 ```
 
 Older Versions of devtools require a username option:
 ```R
-install_github("readstata13", username="sjewo", ref="0.8")
+install_github("readstata13", username="sjewo", ref="0.8.1")
 ```
 
 To install the current development version from github:
@@ -53,7 +53,7 @@ devtools::install_github("sjewo/readstata13", ref="testing")
 ## Current Status
 
 [![Build Status](https://travis-ci.org/sjewo/readstata13.svg?branch=master)](https://travis-ci.org/sjewo/readstata13)
-
+[![CRAN Downloads](http://cranlogs.r-pkg.org/badges/readstata13)](https://cran.r-project.org/web/packages/readstata13/index.html)
 ### Working features
 
 * reading data files from disk or url and create a data.frame

From af7b3e9f449e3e8d7f6927041914359d8c5943e1 Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <sebastian.jeworutzki@ruhr-uni-bochum.de>
Date: Mon, 19 Oct 2015 10:58:21 +0200
Subject: [PATCH 12/21] change version to 0.8.1

---
 DESCRIPTION | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index c303f42b..ebe61c1c 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: readstata13
 Type: Package
 Title: Import Stata Data Files
-Version: 0.8.2
+Version: 0.8.1
 Authors@R: c(
     person("Jan Marvin", "Garbuszus",
     email = "jan.garbuszus@ruhr-uni-bochum.de", role = c("aut")),

From 1b8eff69f8eedcba580f1f9b63ab50473bcf636e Mon Sep 17 00:00:00 2001
From: Marvin <jmg@edna>
Date: Wed, 4 Nov 2015 13:35:20 +0100
Subject: [PATCH 13/21] Comment cleanup.

---
 src/read_dta.cpp | 48 +++++++++++++++++++++---------------------------
 1 file changed, 21 insertions(+), 27 deletions(-)

diff --git a/src/read_dta.cpp b/src/read_dta.cpp
index 6d5ccd3f..dddb99a3 100644
--- a/src/read_dta.cpp
+++ b/src/read_dta.cpp
@@ -21,7 +21,7 @@ using namespace Rcpp;
 using namespace std;
 
 List read_dta(FILE * file, const bool missing) {
-  //fseek(file, 18, SEEK_CUR);// stata_dta><header>
+  // stata_dta><header>
   test("stata_dta><header>", file);
   test("<release>", file);
 
@@ -74,7 +74,7 @@ List read_dta(FILE * file, const bool missing) {
     break;
   }
 
-  //fseek(file, 10, SEEK_CUR); // </release>
+  // </release>
   test("</release>", file);
   test("<byteorder>", file);
 
@@ -85,7 +85,7 @@ List read_dta(FILE * file, const bool missing) {
   std::string byteorder(3, '\0');
   readstring(byteorder,file, byteorder.size());
 
-  //fseek(file, 12, SEEK_CUR); // </byteorder>
+  // </byteorder>
   test("</byteorder>", file);
   test("<K>", file);
 
@@ -99,7 +99,7 @@ List read_dta(FILE * file, const bool missing) {
   uint16_t k = 0;
   k = readbin(k, file, swapit);
 
-  //fseek(file, 4, SEEK_CUR); //</K>
+  //</K>
   test("</K>", file);
   test("<N>", file);
 
@@ -116,7 +116,7 @@ List read_dta(FILE * file, const bool missing) {
     n = readbin(n, file, swapit);
   }
 
-  //fseek(file, 4, SEEK_CUR); //</N>
+  //</N>
   test("</N>", file);
   test("<label>", file);
 
@@ -146,7 +146,7 @@ List read_dta(FILE * file, const bool missing) {
   CharacterVector datalabelCV(1);
   datalabelCV(0) = datalabel;
 
-  //fseek(file, 8, SEEK_CUR); //</label>
+  //</label>
   test("</label>", file);
   test("<timestamp>", file);
 
@@ -170,7 +170,7 @@ List read_dta(FILE * file, const bool missing) {
   }
 
   CharacterVector timestampCV = timestamp;
-  //fseek(file, 21, SEEK_CUR); //</timestamp></header>
+  //</timestamp></header>
   test("</timestamp></header>", file);
   test("<map>", file);
 
@@ -201,7 +201,7 @@ List read_dta(FILE * file, const bool missing) {
     map[i] = nmap;
   }
 
-  //fseek(file, 6, SEEK_CUR); //</map>
+  //</map>
   test("</map>", file);
   test("<variable_types>", file);
 
@@ -224,7 +224,7 @@ List read_dta(FILE * file, const bool missing) {
     vartype[i] = nvartype;
   }
 
-  //fseek(file, 17, SEEK_CUR); //</variable_types>
+  //</variable_types>
   test("</variable_types>", file);
   test("<varnames>", file);
 
@@ -241,7 +241,7 @@ List read_dta(FILE * file, const bool missing) {
     varnames[i] = nvarnames;
   }
 
-  //fseek(file, 11, SEEK_CUR); //</varnames>
+  //</varnames>
   test("</varnames>", file);
   test("<sortlist>", file);
 
@@ -262,7 +262,7 @@ List read_dta(FILE * file, const bool missing) {
     sortlist[i] = nsortlist;
   }
 
-  //fseek(file, 11, SEEK_CUR); //</sortlist>
+  //</sortlist>
   test("</sortlist>", file);
   test("<formats>", file);
 
@@ -280,7 +280,7 @@ List read_dta(FILE * file, const bool missing) {
     formats[i] = nformats;
   }
 
-  //fseek(file, 10, SEEK_CUR); //</formats>
+  //</formats>
   test("</formats>", file);
   test("<value_label_names>",file);
 
@@ -299,7 +299,7 @@ List read_dta(FILE * file, const bool missing) {
     valLabels[i] = nvalLabels;
   }
 
-  //fseek(file, 20, SEEK_CUR); //</value_label_names>
+  //</value_label_names>
   test("</value_label_names>", file);
   test("<variable_labels>", file);
 
@@ -316,7 +316,7 @@ List read_dta(FILE * file, const bool missing) {
     varLabels[i] = nvarLabels;
   }
 
-  //fseek(file, 18, SEEK_CUR); //</variable_labels>
+  //</variable_labels>
   test("</variable_labels>", file);
   test("<characteristics>", file);
 
@@ -338,7 +338,7 @@ List read_dta(FILE * file, const bool missing) {
 
   List ch = List();
   CharacterVector chs(3);
-  
+
     while (chtag.compare(tago)==0)
     {
       uint32_t nocharacter = 0;
@@ -361,15 +361,14 @@ List read_dta(FILE * file, const bool missing) {
     // add characteristics to the list
     ch.push_front( chs );
 
-    //fseek(file, 5, SEEK_CUR); // </ch>
+    // </ch>
     test("</ch>", file);
 
     // read next tag
     readstring(tago, file, tago.size());
   }
 
-  //fseek(file, 14, SEEK_CUR); //[</ch]aracteristics>
-  
+  //[</ch]aracteristics>
   test("aracteristics>", file);
   test("<data>", file);
 
@@ -531,7 +530,7 @@ List read_dta(FILE * file, const bool missing) {
   df.attr("names") = varnames;
   df.attr("class") = "data.frame";
 
-  //fseek(file, 7, SEEK_CUR); //</data>
+  //</data>
   test("</data>", file);
   test("<strls>", file);
 
@@ -605,11 +604,8 @@ List read_dta(FILE * file, const bool missing) {
   }
 
   // after strls
-  //fseek(file, 5, SEEK_CUR); //[</s]trls>
-  //test("</strls>", file);
- 
+  //[</s]trls>
   test("trls>", file);
-
   test("<value_labels>", file);
 
   /*
@@ -628,7 +624,7 @@ List read_dta(FILE * file, const bool missing) {
   readstring(tag, file, tag.size());
 
   List labelList = List(); //put labels into this list
-  
+
   while(lbltag.compare(tag)==0)
   {
     int32_t nlen = 0, labn = 0, txtlen = 0, noff = 0, val = 0;
@@ -716,9 +712,7 @@ List read_dta(FILE * file, const bool missing) {
    * close the file
    */
 
-  //fseek(file, 10, SEEK_CUR); // [</val]ue_labels>#
-  //test("</value_labels>", file);
- 
+  // [</val]ue_labels>
   test("ue_labels>", file);
   test("</stata_dta>", file);
 

From 64c68c883a4db397ae3106cf80372b4f0c588572 Mon Sep 17 00:00:00 2001
From: Marvin <jmg@edna>
Date: Thu, 5 Nov 2015 17:03:44 +0100
Subject: [PATCH 14/21] Replace remaining fseeks with a simple skip function.

---
 inst/include/readstata.h | 11 +++++++++++
 src/read_dta.cpp         |  4 ++--
 src/read_pre13_dta.cpp   |  2 +-
 3 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/inst/include/readstata.h b/inst/include/readstata.h
index 599e2cb2..4ee2995e 100644
--- a/inst/include/readstata.h
+++ b/inst/include/readstata.h
@@ -85,6 +85,17 @@ static void readstring(std::string &mystring, FILE * fp, int nchar)
     Rcpp::warning("char: a binary read error occurred");
 }
 
+static void skip(uint32_t sbit, FILE * file)
+{
+  uint8_t bit = 0;
+
+  if (fread(&bit, sbit, 1, file) != 1){
+    if (ferror(file)){
+      Rcpp::warning("num: a binary read error occurred.");
+    }
+  }
+}
+
 inline void test(std::string testme, FILE * file)
 {
   std::string test(testme.size(), '\0');
diff --git a/src/read_dta.cpp b/src/read_dta.cpp
index dddb99a3..82a9009d 100644
--- a/src/read_dta.cpp
+++ b/src/read_dta.cpp
@@ -639,7 +639,7 @@ List read_dta(FILE * file, const bool missing) {
     readstring(nlabname, file, nlabname.size());
 
     //padding
-    fseek(file, 3, SEEK_CUR);
+    skip(3, file);
 
     // value_label_table for actual label set
     labn = readbin(labn, file, swapit);
@@ -702,7 +702,7 @@ List read_dta(FILE * file, const bool missing) {
     // add this set to output list
     labelList.push_front( code, labset);
 
-    fseek(file, 6, SEEK_CUR); //</lbl>
+    skip(6, file); //</lbl>
 
     readstring(tag, file, tag.size());
   }
diff --git a/src/read_pre13_dta.cpp b/src/read_pre13_dta.cpp
index 593a40a3..274d915e 100644
--- a/src/read_pre13_dta.cpp
+++ b/src/read_pre13_dta.cpp
@@ -510,7 +510,7 @@ List read_pre13_dta(FILE * file, const bool missing)
       readstring(nlabname, file, nlabname.size());
 
       //padding
-      fseek(file, 3, SEEK_CUR);
+      skip(3, file);
 
       // value_label_table for actual label set
       labn = readbin(labn, file, swapit);

From 1b8880b7e7ee31800ebe0a33ee74c88017ffe100 Mon Sep 17 00:00:00 2001
From: Marvin <jmg@edna>
Date: Thu, 5 Nov 2015 17:18:29 +0100
Subject: [PATCH 15/21] If test() calls stop() make sure to close the file.
 Otherwise memory will be polluted. Maybe a additional call to gc() is
 required. However stopping should not happen in the first place.

---
 inst/include/readstata.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/inst/include/readstata.h b/inst/include/readstata.h
index 4ee2995e..cf482283 100644
--- a/inst/include/readstata.h
+++ b/inst/include/readstata.h
@@ -103,6 +103,7 @@ inline void test(std::string testme, FILE * file)
   readstring(test,file, test.size());
   if (testme.compare(test)!=0)
   {
+    fclose(file);
     Rcpp::warning("\n testme:%s \n test: %s\n", testme.c_str(), test.c_str());
     Rcpp::stop("When attempting to read %s: Something went wrong!", testme.c_str());
   }

From 63b9bba70fce2a1dd562603ebefaa3f1b8e97786 Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <sebastian.jeworutzki@ruhr-uni-bochum.de>
Date: Mon, 9 Nov 2015 18:45:36 +0100
Subject: [PATCH 16/21] save strl attribute as named character vector, not as
 list

---
 R/read.R         |  5 ++---
 src/read_dta.cpp | 23 +++++++++++++----------
 2 files changed, 15 insertions(+), 13 deletions(-)

diff --git a/R/read.R b/R/read.R
index 094b8323..97ec29ea 100644
--- a/R/read.R
+++ b/R/read.R
@@ -89,9 +89,8 @@
 #'   \item{var.labels:}{Variable labels}
 #'   \item{version:}{dta file format version}
 #'   \item{label.table:}{List of value labels.}
-#'   \item{strl:}{List of character vectors for the new strl string variable
-#'    type. The first element is the identifier and
-#'    the second element the string.}
+#'   \item{strl:}{Character vector with long strings for the new strl string variable
+#'    type. The name of every element is the identifier.}
 #'   \item{expansion.fields:}{list providing variable name, characteristic name
 #'    and the contents of Stata characteristic field.}
 #'   \item{missing:}{List of numeric vectors with Stata missing type for each
diff --git a/src/read_dta.cpp b/src/read_dta.cpp
index 82a9009d..7a451356 100644
--- a/src/read_dta.cpp
+++ b/src/read_dta.cpp
@@ -548,12 +548,14 @@ List read_dta(FILE * file, const bool missing) {
   std::string tags(3, '\0');
   readstring(tags, file, tags.size());
 
-  List strlstable = List(); //put strLs into this list
+  //put strLs into a named vector
+  CharacterVector strlvalues(0);
+  CharacterVector strlnames(0);
 
   while(gso.compare(tags)==0)
   {
     CharacterVector strls(2);
-    char erg[22];
+    char ref[22];
 
     // FixMe: Strl in 118
     switch (release)
@@ -565,7 +567,7 @@ List read_dta(FILE * file, const bool missing) {
       v = readbin(v, file, swapit);
       o = readbin(o, file, swapit);
 
-      sprintf(erg, "%010d%010d", v, o);
+      sprintf(ref, "%010d%010d", v, o);
       break;
     }
     case 118:
@@ -577,12 +579,11 @@ List read_dta(FILE * file, const bool missing) {
       o = readbin(o, file, swapit);
       // z = readbin(z, file, swapit);
 
-      sprintf(erg, "%010d%010ld", v, o);
-      // sprintf(erg, "%010ld", z);
+      sprintf(ref, "%010d%010ld", v, o);
+      // sprintf(ref, "%010ld", z);
       break;
     }
     }
-    strls(0) = erg;
 
     // (129 = binary) | (130 = ascii)
     uint8_t t = 0;
@@ -596,13 +597,15 @@ List read_dta(FILE * file, const bool missing) {
     std::string strl(len, '\0');
     readstring(strl, file, strl.size());
 
-    strls(1) = strl;
-
-    strlstable.push_back( strls );
+    strlvalues.push_back( strl );
+    strlnames.push_back( ref );
 
     readstring(tags, file, tags.size());
   }
 
+  // set identifier as name
+  strlvalues.attr("names") = strlnames;
+
   // after strls
   //[</s]trls>
   test("trls>", file);
@@ -731,7 +734,7 @@ List read_dta(FILE * file, const bool missing) {
   df.attr("version") = versionIV;
   df.attr("label.table") = labelList;
   df.attr("expansion.fields") = ch;
-  df.attr("strl") = strlstable;
+  df.attr("strl") = strlvalues;
   df.attr("byteorder") = wrap(byteorder);
 
   return df;

From f7f90176e4c1e5b206f80aeb83288bad66cfc0ac Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <sebastian.jeworutzki@ruhr-uni-bochum.de>
Date: Mon, 9 Nov 2015 23:13:16 +0100
Subject: [PATCH 17/21] Revert "Replace remaining fseeks with a simple skip
 function."

This reverts commit 64c68c883a4db397ae3106cf80372b4f0c588572.
---
 inst/include/readstata.h | 11 -----------
 src/read_dta.cpp         |  4 ++--
 src/read_pre13_dta.cpp   |  2 +-
 3 files changed, 3 insertions(+), 14 deletions(-)

diff --git a/inst/include/readstata.h b/inst/include/readstata.h
index cf482283..08256908 100644
--- a/inst/include/readstata.h
+++ b/inst/include/readstata.h
@@ -85,17 +85,6 @@ static void readstring(std::string &mystring, FILE * fp, int nchar)
     Rcpp::warning("char: a binary read error occurred");
 }
 
-static void skip(uint32_t sbit, FILE * file)
-{
-  uint8_t bit = 0;
-
-  if (fread(&bit, sbit, 1, file) != 1){
-    if (ferror(file)){
-      Rcpp::warning("num: a binary read error occurred.");
-    }
-  }
-}
-
 inline void test(std::string testme, FILE * file)
 {
   std::string test(testme.size(), '\0');
diff --git a/src/read_dta.cpp b/src/read_dta.cpp
index 7a451356..ae7a4287 100644
--- a/src/read_dta.cpp
+++ b/src/read_dta.cpp
@@ -642,7 +642,7 @@ List read_dta(FILE * file, const bool missing) {
     readstring(nlabname, file, nlabname.size());
 
     //padding
-    skip(3, file);
+    fseek(file, 3, SEEK_CUR);
 
     // value_label_table for actual label set
     labn = readbin(labn, file, swapit);
@@ -705,7 +705,7 @@ List read_dta(FILE * file, const bool missing) {
     // add this set to output list
     labelList.push_front( code, labset);
 
-    skip(6, file); //</lbl>
+    fseek(file, 6, SEEK_CUR); //</lbl>
 
     readstring(tag, file, tag.size());
   }
diff --git a/src/read_pre13_dta.cpp b/src/read_pre13_dta.cpp
index 274d915e..593a40a3 100644
--- a/src/read_pre13_dta.cpp
+++ b/src/read_pre13_dta.cpp
@@ -510,7 +510,7 @@ List read_pre13_dta(FILE * file, const bool missing)
       readstring(nlabname, file, nlabname.size());
 
       //padding
-      skip(3, file);
+      fseek(file, 3, SEEK_CUR);
 
       // value_label_table for actual label set
       labn = readbin(labn, file, swapit);

From 684be2b735a81c4dbfc78c96f108e03e1625d571 Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <sebastian.jeworutzki@ruhr-uni-bochum.de>
Date: Mon, 9 Nov 2015 23:15:24 +0100
Subject: [PATCH 18/21] More efficient strl replacement

---
 R/read.R | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

diff --git a/R/read.R b/R/read.R
index 97ec29ea..2b96de9d 100644
--- a/R/read.R
+++ b/R/read.R
@@ -260,21 +260,12 @@ read.dta13 <- function(file, convert.factors = TRUE, generate.factors=FALSE,
 
   if (replace.strl) {
     if (version >= 117L) {
-      strl <- do.call(rbind, attr(data,"strl"))
+      strl <- c("")
+      names(strl) <- "00000000000000000000"
+      strl <- c(strl, attr(data,"strl"))
       for (j in seq(ncol(data))[types == 32768] ) {
-        refs <- unique(data[, j])
-        for (ref in refs) {
-          if (length(strl[strl[,1] == ref,2]) != 0){
-            data[data[, j] == ref, j] <- strl[strl[, 1] == ref, 2]
-          }
-        }
+        data[, j] <- strl[data[,j]]
       }
-
-      # recode strL 0 to void
-      for (v in (1:ncol(data))[types == sstrl]) {
-        data[[v]] <- gsub("00000000000000000000","", data[[v]] )
-      }
-
       # if strls are in data.frame remove attribute strl
       attr(data, "strl") <- NULL
     } else {

From 853c078e370be663ddfebb3eabe8a9ea6cf5f192 Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <Sebastian.Jeworutzki@rub.de>
Date: Sat, 14 Nov 2015 14:37:21 +0100
Subject: [PATCH 19/21] prepare cran release 0.8.1

---
 DESCRIPTION | 3 ++-
 README.md   | 8 +++++++-
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index ebe61c1c..22bf26d6 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -7,7 +7,8 @@ Authors@R: c(
     email = "jan.garbuszus@ruhr-uni-bochum.de", role = c("aut")),
     person("Sebastian", "Jeworutzki",
     email="Sebastian.Jeworutzki@ruhr-uni-bochum.de", role = c("aut", "cre")),
-    person("R Core Team", role="cph")
+    person("R Core Team", role="cph"),
+    person("Magnus Thor", "Torfason", role="ctb")
     )
 Description: Function to read and write the Stata file format.
 URL: https://github.com/sjewo/readstata13
diff --git a/README.md b/README.md
index 73d592bb..c616a5f6 100644
--- a/README.md
+++ b/README.md
@@ -54,12 +54,18 @@ devtools::install_github("sjewo/readstata13", ref="testing")
 
 [![Build Status](https://travis-ci.org/sjewo/readstata13.svg?branch=master)](https://travis-ci.org/sjewo/readstata13)
 [![CRAN Downloads](http://cranlogs.r-pkg.org/badges/readstata13)](https://cran.r-project.org/web/packages/readstata13/index.html)
+
 ### Working features
 
+* [new in 0.8.1] convert non-integer variables to factors (```nonint.factors=T```) 
+* [new in 0.8.1] handle large datasets
+* [new in 0.8.1] working with strL variables is now a lot faster
+
+
 * reading data files from disk or url and create a data.frame
 * saving dta files to disk - most features of the dta file format are supported
 * assign variable names
-* read the new strL strings and save them as attribute
+* read the new strL strings and save them as attribute 
 * convert stata label to factors and save them as attribute
 * read some meta data (timestamp, dataset label, formats,...)
 * convert strings to system encoding

From e3457d5173d19891183f1537a1989f1acc230a91 Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <Sebastian.Jeworutzki@rub.de>
Date: Sat, 14 Nov 2015 14:38:59 +0100
Subject: [PATCH 20/21] update manpage for strL

---
 man/read.dta13.Rd | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/man/read.dta13.Rd b/man/read.dta13.Rd
index dc6828e3..8565448c 100644
--- a/man/read.dta13.Rd
+++ b/man/read.dta13.Rd
@@ -61,9 +61,8 @@ The function returns a data.frame with attributes. The attributes
   \item{var.labels:}{Variable labels}
   \item{version:}{dta file format version}
   \item{label.table:}{List of value labels.}
-  \item{strl:}{List of character vectors for the new strl string variable
-   type. The first element is the identifier and
-   the second element the string.}
+  \item{strl:}{Character vector with long strings for the new strl string variable
+   type. The name of every element is the identifier.}
   \item{expansion.fields:}{list providing variable name, characteristic name
    and the contents of Stata characteristic field.}
   \item{missing:}{List of numeric vectors with Stata missing type for each

From 856250df57289c30c856c105b956091bdbd7a90e Mon Sep 17 00:00:00 2001
From: Sebastian Jeworutzki <Sebastian.Jeworutzki@rub.de>
Date: Sat, 14 Nov 2015 14:42:46 +0100
Subject: [PATCH 21/21] typos in readme.md

---
 README.md | 1 -
 1 file changed, 1 deletion(-)

diff --git a/README.md b/README.md
index c616a5f6..5439cf69 100644
--- a/README.md
+++ b/README.md
@@ -61,7 +61,6 @@ devtools::install_github("sjewo/readstata13", ref="testing")
 * [new in 0.8.1] handle large datasets
 * [new in 0.8.1] working with strL variables is now a lot faster
 
-
 * reading data files from disk or url and create a data.frame
 * saving dta files to disk - most features of the dta file format are supported
 * assign variable names