fread support na.strings="0" and na.strings="1"

NEWS.md

@@ -155,6 +155,7 @@
     # [1] 5 1 2 3 4
     ```
 
+28. `fread()` now also supports "0" and "1" in `na.strings`, [#2927](https://github.com/Rdatatable/data.table/issues/2927). Previously this was not permitted since "0" and "1" can be recognized as boolean values. Note that it is still not permitted to use "0" and "1" in `na.strings` in combination with `logical01 = TRUE`. Thanks to @msgoussi for the request, and Benjamin Schwendinger for the PR.
 ## BUG FIXES
 
 1. `by=.EACHI` when `i` is keyed but `on=` different columns than `i`'s key could create an invalidly keyed result, [#4603](https://github.com/Rdatatable/data.table/issues/4603) [#4911](https://github.com/Rdatatable/data.table/issues/4911). Thanks to @myoung3 and @adamaltmejd for reporting, and @ColeMiller1 for the PR. An invalid key is where a `data.table` is marked as sorted by the key columns but the data is not sorted by those columns, leading to incorrect results from subsequent queries.

inst/tests/tests.Rraw

@@ -7848,10 +7848,14 @@ read_table = function(str, ...) {
 test(1552.1, fread(str, na.strings="#N/A"), read_table(str, na.strings="#N/A"))
 test(1552.2, fread(str, na.strings=c("#N/A", "-999")), read_table(str, na.strings=c("#N/A", "-999")))
 test(1552.3, fread(str, na.strings=c("#N/A", "-999", "+1")), read_table(str, na.strings=c("#N/A", "-999", "+1")))
-test(1552.4, fread(str, na.strings=c("#N/A", "-999", "+1", "1")),
-             error="NAstring <<1>> is recognized as type boolean.*not permitted")
+test(1552.4, fread(str, na.strings=c("#N/A", "-999", "+1", "1")), read_table(str, na.strings=c("#N/A", "-999", "+1", "1"))) # enabled by FR #2927
 test(1552.5, fread(str, na.strings=c("#N/A", "-999", "FALSE")), error="NAstring <<FALSE>>.*boolean.*not permitted")
 test(1552.6, fread("A\n1.0\n2\n-", na.strings=c("-")), data.table(A=c(1.0, 2.0, NA)))
+test(1552.7, fread(str, na.strings=c("#N/A", "-999", "+1", "1"), logical01=TRUE),
+  error="NAstring <<1>> and logical01=TRUE.*not permitted")
+str = "a,b,c\n0,1,2\n1,0,2"
+test(1552.8, fread(str, na.strings = "0"), data.table(a=c(NA,1L), b=c(1L,NA), c=c(2L,2L)))
+test(1552.9, fread(str, na.strings = c("0","1")), data.table(a=c(NA,NA), b=c(NA,NA), c=c(2L,2L)))
 
 # FR #1177: 'quote' option of 'print.data.table'
 DT1 <- data.table(s1=paste(" ",LETTERS[1:5],sep=""),s2=LETTERS[1:5])

src/fread.c

@@ -1287,9 +1287,10 @@ int freadMain(freadMainArgs _args) {
       STOP(_("freadMain: NAstring <<%s>> has whitespace at the beginning or end"), ch);
     if (strcmp(ch,"T")==0    || strcmp(ch,"F")==0 ||
         strcmp(ch,"TRUE")==0 || strcmp(ch,"FALSE")==0 ||
-        strcmp(ch,"True")==0 || strcmp(ch,"False")==0 ||
-        strcmp(ch,"1")==0    || strcmp(ch,"0")==0)
+        strcmp(ch,"True")==0 || strcmp(ch,"False")==0)
       STOP(_("freadMain: NAstring <<%s>> is recognized as type boolean, this is not permitted."), ch);
+    if ((strcmp(ch,"1")==0 || strcmp(ch,"0")==0) && args.logical01)
+      STOP(_("freadMain: NAstring <<%s>> and logical01=%s, this is not permitted."), ch, args.logical01 ? "TRUE" : "FALSE");
     char *end;
     errno = 0;
     (void)strtod(ch, &end);  // careful not to let "" get to here (see continue above) as strtod considers "" numeric