Add support for R Markdown (Rmd) files and to ignore R package metadata (i.e. non-code files)

README.md

@@ -1030,6 +1030,7 @@ RAML                       (raml)
 RapydScript                (pyj)
 Razor                      (cshtml)
 Rexx                       (rexx)
+Rmd                        (Rmd)
 RobotFramework             (robot, tsv)
 Ruby                       (rake, rb)
 Ruby HTML                  (rhtml)

Unix/t/00_C.t

@@ -565,6 +565,11 @@ my @Tests = (
                     'ref'  => '../tests/outputs/utilities.R.yaml',
                     'args' => '../tests/inputs/utilities.R',
                 },
+                {
+                    'name' => 'Rmd',
+                    'ref'  => '../tests/output/test.Rmd.yaml',
+                    'args' => '../tests/inputs/test.Rmd',
+                },
                 {
                     'name' => 'Ruby',
                     'ref'  => '../tests/outputs/messages.rb.yaml',

cloc

@@ -5382,6 +5382,28 @@ sub remove_f90_comments {                    # {{{1
     print "<- remove_f90_comments\n" if $opt_v > 2;
     return @save_lines;
 } # 1}}}
+sub reduce_to_rmd_code_blocks {              #{{{1
+    my ($ra_lines) = @_; #in
+    print "<- remove_f90_comments\n" if $opt_v > 2;
+    print "-> reduce_to_rmd_code_blocks()\n" if $opt_v > 2;
+
+    my $in_code_block = 0;
+    my @save_lines = ();
+    foreach (@{$ra_lines}) {
+        if ( m/^```\{\s*[[:alpha:]]/ ) {
+            $in_code_block = 1;
+            next;
+        }
+        if ( m/^```\s*$/ ) {
+            $in_code_block = 0;
+        }
+        next if (!$in_code_block);
+        push @save_lines, $_;
+    }
+
+    print "<- reduce_to_rmd_code_blocks()\n" if $opt_v> 2;
+    return @save_lines;
+} # 1}}}
 sub remove_matches {                         # {{{1
     my ($ra_lines, # in
         $pattern , # in   Perl regular expression (case insensitive)
@@ -6434,6 +6456,7 @@ sub set_constants {                          # {{{1
             'psm1'        => 'PowerShell'            ,
             'R'           => 'R'                     ,
             'r'           => 'R'                     ,
+            'Rmd'         => 'Rmd'                   ,
             'raml'        => 'RAML'                  ,
             'rkt'         => 'Racket'                ,
             'rktl'        => 'Racket'                ,
@@ -7223,6 +7246,11 @@ sub set_constants {                          # {{{1
                                 [ 'remove_matches'      , '^\s*#'  ],
                                 [ 'remove_inline'       , '#.*$'   ],
                             ],
+    'Rmd'                => [
+                                [ 'reduce_to_rmd_code_blocks'      ],
+                                [ 'remove_matches'      , '^\s*#'  ],
+                                [ 'remove_inline'       , '#.*$'   ],
+                            ],
     'Racket'             => [
                                 [ 'remove_matches'      , '^\s*;'  ],
                                 [ 'remove_inline'       , ';.*$'   ],
@@ -7592,6 +7620,7 @@ sub set_constants {                          # {{{1
     'PowerShell'         =>     '\\\\$'         ,
     'Python'             =>     '\\\\$'         ,
     'R'                  =>     '\\\\$'         ,
+    'Rmd'                =>     '\\\\$'         ,
     'Ruby'               =>     '\\\\$'         ,
     'sed'                =>     '\\\\$'         ,
     'Swift'              =>     '\\\\$'         ,
@@ -7686,13 +7715,15 @@ sub set_constants {                          # {{{1
    'CHANGES'     => 1,
    'COPYING'     => 1,
    'COPYING'     => 1,
+   'DESCRIPTION' => 1, # R packages metafile
    '.cvsignore'  => 1,
    'Entries'     => 1,
    'FAQ'         => 1,
    'iconfig.h'   => 1, # Skip "iconfig.h" files; they're used in Imakefiles.
    'INSTALL'     => 1,
    'MAINTAINERS' => 1,
    'MD5SUMS'     => 1,
+   'NAMESPACE'   => 1, # R packages metafile
    'NEWS'        => 1,
    'readme'      => 1,
    'Readme'      => 1,
@@ -8206,6 +8237,7 @@ sub set_constants {                          # {{{1
     'quickbuild'                   =>   2.86,
     'quiz'                         =>   5.33,
     'R'                            =>   3.00,
+    'Rmd'                          =>   3.00,
     'Racket'                       =>   1.50,
     'rally'                        =>   2.00,
     'ramis ii'                     =>   2.00,

tests/inputs/test.Rmd

@@ -0,0 +1,33 @@
+---
+title: "Untitled"
+author: "cloc test"
+date: "5/12/2018"
+output: html_document
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+
+## R Markdown
+
+This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see <http://rmarkdown.rstudio.com>.
+
+When you click the **Knit** button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
+
+```{r cars}
+summary(cars)
+# summary(cars)
+```
+
+## Including Plots
+
+You can also embed plots, for example:
+
+```{r pressure, echo=FALSE}
+plot(pressure)
+
+plot(cars)
+```
+
+Note that the `echo = FALSE` parameter was added to the code chunk to prevent printing of the R code that generated the plot.

tests/outputs/test.Rmd.yaml

@@ -0,0 +1,24 @@
+       1 text file.
+       1 unique file.                              
+       0 files ignored.
+
+---
+# github.com/AlDanial/cloc
+header : 
+  cloc_url           : github.com/AlDanial/cloc
+  cloc_version       : 1.77
+  elapsed_seconds    : 0.00812411308288574
+  n_files            : 1
+  n_lines            : 33
+  files_per_second   : 123.090359501101
+  lines_per_second   : 4061.98186353632
+Rmd :
+  nFiles: 1
+  blank: 10
+  comment: 19
+  code: 4
+SUM: 
+  blank: 10
+  comment: 19
+  code: 4
+  nFiles: 1