Merge branch 'devBranch1' of https://github.com/badasahog/data.table into devBranch1

Author: badasahog

man/datatable-optimize.Rd

@@ -31,8 +31,7 @@ it does so in "C-locale". This has some subtle implications; see Examples.
 out what level of optimisation is required. The default value \code{Inf}
 activates \emph{all} available optimisations.
 
-At optimisation level \code{>= 1}, i.e., \code{getOption("datatable.optimize")}
->= 1, these are the optimisations:
+For \code{getOption("datatable.optimize") >= 1}, these are the optimisations:
 
 \itemize{
     \item The base function \code{order} is internally replaced with
@@ -52,7 +51,7 @@ At optimisation level \code{>= 1}, i.e., \code{getOption("datatable.optimize")}
     is an S3 generic and gets slow with many groups.
 }
 
-At optimisation level \code{>= 2}, i.e., \code{getOption("datatable.optimize")} >= 2, additional optimisations are implemented on top of the optimisations already shown above.
+For \code{getOption("datatable.optimize") >= 2}, additional optimisations are implemented on top of the optimisations already shown above.
 
 \itemize{
 
@@ -81,7 +80,7 @@ At optimisation level \code{>= 2}, i.e., \code{getOption("datatable.optimize")}
     discussed above.
 }
 
-At optimisation level \code{>= 3}, i.e., \code{getOption("datatable.optimize")} >= 3, additional optimisations for subsets in i are implemented on top of the optimisations already shown above. Subsetting operations are - if possible - translated into joins to make use of blazing fast binary search using indices and keys. The following queries are optimized:
+For \code{getOption("datatable.optimize") >= 3}, additional optimisations for subsets in i are implemented on top of the optimisations already shown above. Subsetting operations are - if possible - translated into joins to make use of blazing fast binary search using indices and keys. The following queries are optimized:
 
 \itemize{
 

man/foverlaps.Rd

@@ -29,15 +29,15 @@ foverlaps(x, y, by.x = key(x) \%||\% key(y),
 \item{by.x, by.y}{A vector of column names (or numbers) to compute the overlap
 joins. The last two columns in both \code{by.x} and \code{by.y} should each
 correspond to the \code{start} and \code{end} interval columns in \code{x} and
-\code{y} respectively. And the \code{start} column should always be <= \code{end}
-column. If \code{x} is keyed,  \code{by.x} is equal to \code{key(x)}, else
+\code{y} respectively. We should always have \code{start <= end}.
+If \code{x} is keyed,  \code{by.x} is equal to \code{key(x)}, else
 \code{key(y)}. \code{by.y} defaults to \code{key(y)}. }
-\item{maxgap}{It should be a non-negative integer value, >= 0. Default is 0 (no
+\item{maxgap}{Non-negative integer, i.e., \code{maxgap >= 0}. Default is 0 (no
 gap). For intervals \code{[a,b]} and \code{[c,d]}, where \code{a<=b} and
 \code{c<=d}, when \code{c > b} or \code{d < a}, the two intervals don't overlap.
 If the gap between these two intervals is \code{<= maxgap}, these two intervals
 are considered as overlapping. Note: This is not yet implemented.}
-\item{minoverlap}{ It should be a positive integer value, > 0. Default is 1. For
+\item{minoverlap}{Positive integer, i.e., \code{minoverlap > 0}. Default is 1. For
 intervals \code{[a,b]} and \code{[c,d]}, where \code{a<=b} and \code{c<=d}, when
 \code{c<=b} and \code{d>=a}, the two intervals overlap. If the length of overlap
 between these two intervals is \code{>= minoverlap}, then these two intervals are

man/openmp-utils.Rd

@@ -15,7 +15,7 @@
   \item{threads}{ NULL (default) rereads environment variables. 0 means to use all logical CPUs available. Otherwise a number >= 1 }
   \item{restore_after_fork}{ Should data.table be multi-threaded after a fork has completed? NULL leaves the current setting unchanged which by default is TRUE. See details below. }
   \item{percent}{ If provided it should be a number between 2 and 100; the percentage of logical CPUs to use. By default on startup, 50\%. }
-  \item{throttle}{ 1024 (default) means that, roughly speaking, a single thread will be used when nrow(DT)<=1024, 2 threads when nrow(DT)<=2048, etc. The throttle is to speed up small data tasks (especially when repeated many times) by not incurring the overhead of managing multiple threads. Hence the number of threads is throttled (restricted) for small tasks. }
+  \item{throttle}{ 1024 (default) means that, roughly speaking, a single thread will be used when \code{nrow(DT)<=1024}, 2 threads when \code{nrow(DT)<=2048}, etc. The throttle is to speed up small data tasks (especially when repeated many times) by not incurring the overhead of managing multiple threads. Hence the number of threads is throttled (restricted) for small tasks. }
   \item{verbose}{ Display the value of relevant OpenMP settings plus the \code{restore_after_fork} internal option. }
 }
 \value{

man/setorder.Rd

@@ -48,7 +48,7 @@ when \code{b} is of type \code{character} as well. }
 \code{order} must be either \code{1} or equal to that of \code{cols}. If
 \code{length(order) == 1}, it is recycled to \code{length(cols)}. }
 \item{na.last}{ \code{logical}. If \code{TRUE}, missing values in the data are placed last; if \code{FALSE}, they are placed first; if \code{NA} they are removed.
-\code{na.last=NA} is valid only for \code{x[order(., na.last)]} and related \code{sort_by(x, .)} (\eqn{\R \ge 4.4.0}) and its
+\code{na.last=NA} is valid only for \code{x[order(., na.last)]} and related \code{sort_by(x, .)} (\R \ifelse{html}{\out{≥}}{\eqn{\ge}} 4.4.0) and its
 default is \code{TRUE}. \code{setorder} and \code{setorderv} only accept
 \code{TRUE}/\code{FALSE} with default \code{FALSE}. }
 }
@@ -73,7 +73,7 @@ sets the \code{sorted} attribute.
 
 \code{na.last} argument, by default, is \code{FALSE} for \code{setorder} and
 \code{setorderv} to be consistent with \code{data.table}'s \code{setkey} and
-is \code{TRUE} for \code{x[order(.)]} and \code{sort_by(x, .)} (\eqn{\R \ge 4.4.0}) to be consistent with \code{base::order}.
+is \code{TRUE} for \code{x[order(.)]} and \code{sort_by(x, .)} (\R \ifelse{html}{\out{≥}}{\eqn{\ge}} 4.4.0) to be consistent with \code{base::order}.
 Only \code{x[order(.)]} (and related \code{sort_by(x, .)}) can have \code{na.last = NA} as it is a subset operation
 as opposed to \code{setorder} or \code{setorderv} which reorders the data.table
 by reference.

src/fread.c

@@ -683,7 +683,7 @@ cat("1.0E300L\n};\n", file=f, append=TRUE)
  */
 static void parse_double_regular_core(const char **pch, double *target)
 {
-  static const sflimit FLOAT_MAX_DIGITS = 18;
+  static const int_fast32_t FLOAT_MAX_DIGITS = 18;
   const char *ch = *pch;
 
   if (*ch=='0' && args.keepLeadingZeros && IS_DIGIT(ch[1])) return;
@@ -2762,7 +2762,7 @@ int freadMain(freadMainArgs _args) {
           DTWARN(_("Stopped early on line %"PRIu64". Expected %d fields but found %d. Consider fill=%d or even more based on your knowledge of the input file. Use fill=Inf for reading the whole file for detecting the number of fields. First discarded non-empty line: <<%s>>"),
           (uint64_t)DTi+row1line, ncol, tt, tt, strlim(skippedFooter,500));
         } else {
-          DTWARN(_("Stopped early on line %"PRIu64". Expected %d fields but found %d. Consider fill=TRUE and comment.char=. First discarded non-empty line: <<%s>>"),
+          DTWARN(_("Stopped early on line %"PRIu64". Expected %d fields but found %d. Consider fill=TRUE. First discarded non-empty line: <<%s>>"),
           (uint64_t)DTi+row1line, ncol, tt, strlim(skippedFooter,500));
         }
       }