Updated documentation & README

R/tidy.r

@@ -45,7 +45,8 @@
 #' @param verbose output document errors? (default: \code{FALSE})
 #' @note If document parsing errors are severe enough, \code{tidy_html()} will not be able
 #'   to clean the document and will display the errors (this output can be captured with
-#'   \code{sink()} or \code{capture.output()}) along with a warning and return \code{NA}.
+#'   \code{sink()} or \code{capture.output()}) along with a warning and return a "best effort"
+#'   cleaned version of the document.
 #' @return Tidied HTML/XHTML content. The object type will be the same as that of the input type
 #'         except when it is a \code{connection}, then a character vector will be returned.
 #' @references \url{http://api.html-tidy.org/tidy/quickref_5.1.25.html} &

README.md

@@ -214,7 +214,7 @@ sum(map_int(book, nchar))
 ## [1] 207501
 system.time(tidy_book <- tidy_html(book))
 ##    user  system elapsed 
-##   0.021   0.001   0.023
+##   0.022   0.002   0.024
 ```
 
 (It's usually between 20 & 25 milliseconds to process those 202 kilobytes of HTML.) Not too shabby.

man/tidy_html.Rd

@@ -86,7 +86,8 @@ It may also be advantageous to remove all comments with \code{TidyHideComments}.
 \note{
 If document parsing errors are severe enough, \code{tidy_html()} will not be able
   to clean the document and will display the errors (this output can be captured with
-  \code{sink()} or \code{capture.output()}) along with a warning and return \code{NULL}.
+  \code{sink()} or \code{capture.output()}) along with a warning and return a "best effort"
+  cleaned version of the document.
 }
 \examples{
 opts <- list(

src/htmltidy.cpp

@@ -176,6 +176,9 @@ Rcpp::CharacterVector tidy_html_int(std::string source, Rcpp::List options,
     if (ok == no) Rcpp::stop("Error setting TidyHTML options");
   }
 
+  ok = tidyOptSetBool(tdoc, TidyForceOutput, yes);
+  if (ok == no) Rcpp::stop("Error setting TidyHTML options");
+
   rc = tidySetErrorBuffer(tdoc, &errbuf);
   max_rc = (rc > max_rc) ? rc : max_rc;
 
@@ -210,10 +213,14 @@ Rcpp::CharacterVector tidy_html_int(std::string source, Rcpp::List options,
     show_errors = true;
   }
 
-  if (show_errors & (errbuf.allocated > 0)) {
+  if (max_rc > 1) show_errors = true;
-    Rcpp::Rcout << std::string(reinterpret_cast<const char*>(errbuf.bp)) << std::endl;
+
+  if (show_errors) {
+    if (errbuf.allocated > 0) {
+      Rcpp::Rcout << std::string(reinterpret_cast<const char*>(errbuf.bp)) << std::endl;
+    }
     if (max_rc > 1) {
-      Rcpp::warning("\nSevere errors were generated during document evaluation.\nReturing original document");
+      Rcpp::warning("\nSevere errors were generated during document evaluation.\n");
     }
   }
 
@@ -222,6 +229,6 @@ Rcpp::CharacterVector tidy_html_int(std::string source, Rcpp::List options,
 
   tidyRelease(tdoc);
 
-  return((max_rc > 1) ? NA_STRING : Rcpp::wrap(ret));
+  return(Rcpp::wrap(ret));
 
 }