More direct fix for #563, since mkCharLen internally call mkCharLenCE.

Rdatatable · Aug 25, 2015 · e592419 · e592419
1 parent 8bb3b4c
commit e592419
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 14 deletions.
diff --git a/R/fread.R b/R/fread.R
@@ -2,9 +2,7 @@
 fread <- function(input="",sep="auto",sep2="auto",nrows=-1L,header="auto",na.strings="NA",stringsAsFactors=FALSE,verbose=getOption("datatable.verbose"),autostart=1L,skip=0L,select=NULL,drop=NULL,colClasses=NULL,integer64=getOption("datatable.integer64"),dec=if (sep!=".") "." else ",", check.names=FALSE, encoding="unknown", showProgress=getOption("datatable.showProgress"),data.table=getOption("datatable.fread.datatable")) {
     if (!is.character(dec) || length(dec)!=1L || nchar(dec)!=1) stop("dec must be a single character e.g. '.' or ','")
     # handle encoding, #563
-    if (missing(encoding)) {
-        encoding = NULL
-    } else if (!encoding %in% c("unknown", "UTF-8", "Latin-1")) {
+    if (!encoding %in% c("unknown", "UTF-8", "Latin-1")) {
         stop("Argument 'encoding' must be 'unknown', 'UTF-8' or 'Latin-1'.")
     }
     if (getOption("datatable.fread.dec.experiment") && Sys.localeconv()["decimal_point"] != dec) {

diff --git a/src/fread.c b/src/fread.c
@@ -429,13 +429,9 @@ SEXP readfile(SEXP input, SEXP separg, SEXP nrowsarg, SEXP headerarg, SEXP nastr
     // https://github.com/wch/r-source/blob/ca5348f0b5e3f3c2b24851d7aff02de5217465eb/src/main/util.c#L1115
     // Check for mkCharLenCE function to locate as to where where this is implemented.
     cetype_t ienc;
-    Rboolean is_no_encoding = TRUE;
-    if (!isNull(encoding)) {
-        is_no_encoding = FALSE;
-        if (!strcmp(CHAR(STRING_ELT(encoding, 0)), "Latin-1")) ienc = CE_LATIN1;
-        else if (!strcmp(CHAR(STRING_ELT(encoding, 0)), "UTF-8")) ienc = CE_UTF8;
-        else ienc = CE_NATIVE;
-    }
+    if (!strcmp(CHAR(STRING_ELT(encoding, 0)), "Latin-1")) ienc = CE_LATIN1;
+    else if (!strcmp(CHAR(STRING_ELT(encoding, 0)), "UTF-8")) ienc = CE_UTF8;
+    else ienc = CE_NATIVE;
 
     // Extra tracing for apparent 32bit Windows problem: https://github.com/Rdatatable/data.table/issues/1111
     if (!isInteger(showProgressArg)) error("showProgress is not type integer but type '%s'. Please report.", type2char(TYPEOF(showProgressArg)));
@@ -1095,10 +1091,7 @@ SEXP readfile(SEXP input, SEXP separg, SEXP nrowsarg, SEXP headerarg, SEXP nastr
                     SET_VECTOR_ELT(ans, resj, thiscol = coerceVectorSoFar(thiscol, type[j]++, SXP_STR, i, j));
                 case SXP_STR: case SXP_NULL: case_SXP_STR:
                     Field(1);
-                    if (type[j]==SXP_STR) {
-                        SET_STRING_ELT(thiscol, i, (is_no_encoding) ?   
-                              mkCharLen(fieldStart, fieldLen) : mkCharLenCE(fieldStart, fieldLen, ienc));
-                    }
+                    if (type[j]==SXP_STR) SET_STRING_ELT(thiscol, i, mkCharLenCE(fieldStart, fieldLen, ienc));
                 }
                 if (ch<eof && *ch==sep && j<ncol-1) {ch++; continue;}  // done, next field
                 if (j<ncol-1) {