Bump version to 1.02 now that we fully support the original Markdown …

…syntax.

Changes

@@ -1,8 +1,10 @@
 Revision history for pmarkdown and the Markdown::Perl module.
 
-1.02 - ??
+1.02 - 2024-04-06
 
- - Improvement to the support of the original markdown syntax.
+ - Improvement to the support of the original markdown syntax. This is probably
+   the best that we will do as this is now quite faithful and some of the
+   remaining differences are bugs in the original implementation.
  - Bugfixes:
    - Do not make a list loose when it is followed by blank lines.
    - Tab stops after list markers are properly computed.

README.md

@@ -7,8 +7,9 @@ extensions.
 
 This software supports the entire
 [`CommonMark` spec](https://spec.commonmark.org/0.31.2/) syntax, as well as all
-[GitHub Flavored Markdown (gfm) extensions](https://github.github.com/gfm/) and
-some more custom extensions.
+[GitHub Flavored Markdown (gfm) extensions](https://github.github.com/gfm/)
+some more custom extensions. It also has compatibility with the
+[original Markdown syntax](https://daringfireball.net/projects/markdown/syntax).
 
 It is based on the [Markdown::Perl](https://metacpan.org/pod/Markdown::Perl)
 library that can be used in standalone Perl program.

lib/App/pmarkdown.pm

@@ -5,7 +5,7 @@ use warnings;
 
 use Markdown::Perl;
 
-our $VERSION = '1.01';  # Remember to also set the Markdown::Perl version.
+our $VERSION = '1.02';  # Remember to also set the Markdown::Perl version.
 
 1;
 

lib/Markdown/Perl.pm

@@ -17,7 +17,7 @@ use Scalar::Util 'blessed';
 
 use parent 'Markdown::Perl::Options';
 
-our $VERSION = '1.01';  # Remember to also set the App::pmarkdown version.
+our $VERSION = '1.02';  # Remember to also set the App::pmarkdown version.
 
 our @EXPORT_OK = qw(convert set_options);
 our %EXPORT_TAGS = (all => \@EXPORT_OK);

lib/Markdown/Perl/BlockParser.pm

@@ -160,7 +160,7 @@ sub _finalize_paragraph {
     if ($this->{last_line_was_blank}) {
       if (@{$this->{blocks_stack}}
         && $this->{blocks_stack}[-1]{block}{type} eq 'list_item') {
-          $this->{blocks_stack}[-1]{block}{loose} = 1;
+        $this->{blocks_stack}[-1]{block}{loose} = 1;
       }
     }
   }
@@ -268,7 +268,7 @@ sub _test_lazy_continuation {
 
 sub _count_matching_blocks {
   my ($this, $lr) = @_;  # $lr is a scalar *reference* to the current line text.
-  $this->{matched_prefix_size} += 0;
+  $this->{matched_prefix_size} = 0;
   for my $i (0 .. $#{$this->{blocks_stack}}) {
     local *::_ = $lr;
     my $r = $this->{blocks_stack}[$i]{cond}();
@@ -430,8 +430,9 @@ sub _do_indented_code_block {
   if (@{$this->{paragraph}} || $l !~ m/${indented_code_re}/) {
     return;
   }
-  my $preserve_tabs = !$this->get_code_blocks_convert_tabs_to_spaces;
-  my @code_lines = scalar(remove_prefix_spaces(4, $l.$this->line_ending(), $preserve_tabs));
+  my $convert_tabs = $this->get_code_blocks_convert_tabs_to_spaces;
+  tabs_to_space($l, $this->{matched_prefix_size}) if $convert_tabs;
+  my @code_lines = scalar(remove_prefix_spaces(4, $l.$this->line_ending()));
   my $count = 1;  # The number of lines we have read
   my $valid_count = 1;  # The number of lines we know are in the code block.
   my $valid_pos = $this->get_pos();
@@ -441,11 +442,10 @@ sub _do_indented_code_block {
       if ($nl =~ m/${indented_code_re}/) {
         $valid_pos = $this->get_pos();
         $valid_count = $count;
-        push @code_lines,
-            scalar(remove_prefix_spaces(4, $nl.$this->line_ending(), $preserve_tabs));
+        tabs_to_space($nl, $this->{matched_prefix_size}) if $convert_tabs;
+        push @code_lines, scalar(remove_prefix_spaces(4, $nl.$this->line_ending()));
       } elsif ($nl eq '') {
-        push @code_lines,
-            scalar(remove_prefix_spaces(4, $nl.$this->line_ending(), $preserve_tabs));
+        push @code_lines, scalar(remove_prefix_spaces(4, $nl.$this->line_ending(), !$convert_tabs));
       } else {
         last;
       }
@@ -617,9 +617,10 @@ sub _do_list_item {
   my $mode = $this->get_lists_can_interrupt_paragraph;
   if (@{$this->{paragraph}}) {
     return if $mode eq 'never';
-    if ($mode eq 'within_list' && !(@{$this->{blocks_stack}} && $this->{blocks_stack}[-1]{block}{type} eq 'list_item')) {
+    if ($mode eq 'within_list'
+      && !(@{$this->{blocks_stack}} && $this->{blocks_stack}[-1]{block}{type} eq 'list_item')) {
       return;
-    };
+    }
     if ($mode eq 'strict' && ($text eq '' || ($type eq 'ol' && $digits != 1))) {
       return;
     }

lib/Markdown/Perl/Options.pm

@@ -292,7 +292,7 @@ A list can interrupt a paragraph only when we are already inside another list.
 
 =item B<strict> I<(default)>
 
-A list can interrupt a paragraph but only with some non anbiguous list markers.
+A list can interrupt a paragraph but only with some non ambiguous list markers.
 
 =item B<always>
 
@@ -424,7 +424,7 @@ _make_option(code_blocks_info => 'language', _enum(qw(ignored language)));
 
 =head3 B<code_blocks_convert_tabs_to_spaces> I<(boolean, default: false)>
 
-By default, tabs are preserved inside codeblocks. With this option, all tabs (at
+By default, tabs are preserved inside code blocks. With this option, all tabs (at
 the beginning of the lines or inside) are turned into spaces, aligned with the
 tab stops (currently always a multiple of 4).
 

lib/Markdown/Perl/Util.pm

@@ -15,7 +15,7 @@ use Unicode::CaseFold 'fc';
 our $VERSION = 0.01;
 
 our @EXPORT_OK =
-    qw(split_while remove_prefix_spaces indent_size indented_one_tab horizontal_size normalize_label indented);
+    qw(split_while remove_prefix_spaces indent_size indented_one_tab horizontal_size normalize_label indented tabs_to_space);
 our %EXPORT_TAGS = (all => \@EXPORT_OK);
 
 # Partition a list into a continuous chunk for which the given code evaluates to
@@ -130,4 +130,21 @@ sub normalize_label {
   return $label;
 }
 
+# Convert tabs to space in the given string. Assuming $prefix horizontal spaces
+# before the string.
+sub tabs_to_space {  ## no critic (RequireArgUnpacking)
+  my ($str, $prefix) = @_;
+  $prefix //= 0;
+  while ($str =~ m/\G[^\t]*\t/g) {
+    $prefix += $LAST_MATCH_END[0] - $LAST_MATCH_START[0] - 1;
+    my $nb_space = 4 - $prefix % 4;
+    substr $str, $LAST_MATCH_END[0] - 1, 1, ' ' x $nb_space;
+    pos($str) = $LAST_MATCH_END[0] - 1 + $nb_space;
+    $prefix = 0;  # By definition we are now aligned with a tab stop.
+  }
+  return $str if defined wantarray;
+  $_[0] = $str;
+  return;
+}
+
 1;

script/pmarkdown

@@ -143,7 +143,8 @@ CommonMark spec.
 This mode implements the
 L<original Markdown syntax|https://daringfireball.net/projects/markdown/syntax>.
 
-Note that this mode is not 100% similar to the original F<Markdown.pl> script.
+Note that this mode is not 100% similar to the original F<Markdown.pl> script
+as that script has some buggy behavior that we are not reproducing.
 
 =back
 

t/100-util.t

@@ -69,4 +69,15 @@ is(indented(5, "\t\tfoo"), T(), 'indented8');
 is(indented(5, "     foo"), T(), 'indented9');
 is(indented(5, "    foo"), F(), 'indented10');
 
+is(tabs_to_space("ab\tcd"), 'ab  cd', 'tabs_to_space1');
+is(tabs_to_space("ab\tcd", 2), 'ab    cd', 'tabs_to_space2');
+is(tabs_to_space("ab\t\tcd"), 'ab      cd', 'tabs_to_space3');
+is(tabs_to_space("\t\tab"), '        ab', 'tabs_to_space4');
+{
+  my $s = "ab\tcd";
+  tabs_to_space($s);
+  is($s, 'ab  cd', 'tabs_to_space5');
+}
+
+
 done_testing;

t/902-markdown-test-suite.t

@@ -9,9 +9,13 @@ use Markdown::Perl;
 use MmdTest;
 use Test2::V0;
 
-# TODO: remove these todos.
 my %opt = (
-  todo => [16, 18, 22],
+  todo => [
+    # We will probably never support this test, which has quotes inside link
+    # titles that are in quotes. The "spec" does not say anything about that and
+    # it would be a nightmare to parse it.
+    16,
+  ],
   # These are bugs in the Markdown "spec", not in our implementation. All of
   # these have been tested to be buggy in the real Markdown.pl implementation.
   bugs => [