[no subject]

[Patrice Dumas]

branch: master
commit 01fb008e9a6383f1ba8c753004072b0d44be1ec4
Author: Patrice Dumas <pertusus@free.fr>
AuthorDate: Sat Dec 30 09:52:01 2023 +0100

    * tp/Texinfo/Convert/Converter.pm (convert_accents): reorganize code
    for more clarity.
    
    * tp/Texinfo/Convert/HTML.pm (_accent_entities_html_accent): do not
    consider an end of line in an accent command argument to allow to use
    the entity.
    
    * tp/Texinfo/Convert/Unicode.pm (%unicode_accented_letters): fix a
    codepoint.
---
 ChangeLog                                          | 12 ++++++++++++
 tp/Texinfo/Convert/Converter.pm                    | 22 +++++++++++-----------
 tp/Texinfo/Convert/HTML.pm                         |  4 +++-
 tp/Texinfo/Convert/Unicode.pm                      |  6 +++---
 .../results/coverage/lettered_accent_and_spaces.pl |  4 ++--
 tp/t/results/coverage/unknown_accents.pl           |  4 ++--
 6 files changed, 33 insertions(+), 19 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index ed72e4675b..aea265909d 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,15 @@
+2023-12-30  Patrice Dumas  <pertusus@free.fr>
+
+       * tp/Texinfo/Convert/Converter.pm (convert_accents): reorganize code
+       for more clarity.
+
+       * tp/Texinfo/Convert/HTML.pm (_accent_entities_html_accent): do not
+       consider an end of line in an accent command argument to allow to use
+       the entity.
+
+       * tp/Texinfo/Convert/Unicode.pm (%unicode_accented_letters): fix a
+       codepoint.
+
 2023-12-29  Patrice Dumas  <pertusus@free.fr>
 
        Add gnulib module for XS
diff --git a/tp/Texinfo/Convert/Converter.pm b/tp/Texinfo/Convert/Converter.pm
index 1693d22a32..534aa0bbbd 100644
--- a/tp/Texinfo/Convert/Converter.pm
+++ b/tp/Texinfo/Convert/Converter.pm
@@ -1521,24 +1521,24 @@ sub convert_accents($$$;$$)
 
   my ($contents_element, $stack)
       = Texinfo::Convert::Utils::find_innermost_accent_contents($accent);
-  my $result = $self->convert_tree($contents_element);
+  my $arg_text = $self->convert_tree($contents_element);
 
-  my $encoded;
   if ($output_encoded_characters) {
-    $encoded = Texinfo::Convert::Unicode::encoded_accents($self, $result, 
$stack,
+    my $encoded = Texinfo::Convert::Unicode::encoded_accents($self,
+                                       $arg_text, $stack,
                                        $self->get_conf('OUTPUT_ENCODING_NAME'),
                                        $format_accents,
                                        $in_upper_case);
-  }
-  if (!defined($encoded)) {
-    foreach my $accent_command (reverse(@$stack)) {
-      $result = &$format_accents ($self, $result, $accent_command,
-                                  $in_upper_case);
+    if (defined($encoded)) {
+      return $encoded;
     }
-    return $result;
-  } else {
-    return $encoded;
   }
+  my $result = $arg_text;
+  foreach my $accent_command (reverse(@$stack)) {
+    $result = &$format_accents ($self, $result, $accent_command,
+                                $in_upper_case);
+  }
+  return $result;
 }
 
 # index sub-entries specified with @subentry, separated by commas, or by
diff --git a/tp/Texinfo/Convert/HTML.pm b/tp/Texinfo/Convert/HTML.pm
index e4c89a03b6..e7cd3ad2f1 100644
--- a/tp/Texinfo/Convert/HTML.pm
+++ b/tp/Texinfo/Convert/HTML.pm
@@ -3835,7 +3835,9 @@ sub _accent_entities_html_accent($$$;$$$)
     return "&${text}$accent_command_entity;"
       if ($accent_command_entity
           and defined($accent_command_text_with_entities)
-          and ($text =~ /^[$accent_command_text_with_entities]$/));
+          # \z ensures that a \n at the end prevents matching, we do not
+          # want an end of line in the middle of the entity
+          and ($text =~ /^[$accent_command_text_with_entities]\z/));
     my $formatted_accent
       = Texinfo::Convert::Converter::xml_numeric_entity_accent($accent, $text);
     if (defined($formatted_accent)) {
diff --git a/tp/Texinfo/Convert/Unicode.pm b/tp/Texinfo/Convert/Unicode.pm
index 4ada262e59..4ccf70440b 100644
--- a/tp/Texinfo/Convert/Unicode.pm
+++ b/tp/Texinfo/Convert/Unicode.pm
@@ -304,7 +304,7 @@ our %unicode_accented_letters = (
         'Y' => '00DD',
         'y' => '00FD',
         'Z' => '0179',
-        'z' => '018A',
+        'z' => '017A',
     },
     '~' => { # tilde
         'A' => '00C3',
@@ -431,8 +431,8 @@ our %unicode_accented_letters = (
         'o' => '01EB',
     },
     'dotless' => {
-        'i' => '0131',
-        'j' => '0237',
+        'i' => '0131', # 305
+        'j' => '0237', # 567
     }
 );
 
diff --git a/tp/t/results/coverage/lettered_accent_and_spaces.pl 
b/tp/t/results/coverage/lettered_accent_and_spaces.pl
index 59b8fdad05..fc26a94c10 100644
--- a/tp/t/results/coverage/lettered_accent_and_spaces.pl
+++ b/tp/t/results/coverage/lettered_accent_and_spaces.pl
@@ -422,8 +422,8 @@ 
$result_converted{'html_text'}->{'lettered_accent_and_spaces'} = '<p>&aring;
 </p>
 <p>&acirc;
 </p>
-<p>&a
-circ;
+<p>a
+&#770;
 </p>
 ';
 
diff --git a/tp/t/results/coverage/unknown_accents.pl 
b/tp/t/results/coverage/unknown_accents.pl
index 4fa8ef0fa3..4f1ab6ae1e 100644
--- a/tp/t/results/coverage/unknown_accents.pl
+++ b/tp/t/results/coverage/unknown_accents.pl
@@ -608,7 +608,7 @@ $result_converted{'plaintext'}->{'unknown_accents'} = 'Ẍ ẍ 
Q̈ Ÿ
 
 $result_converted{'html_text'}->{'unknown_accents'} = '<p>&#7820; &#7821; 
Q&#776; &#376;
 </p>
-<p>&#394; q&#769; &#341;
+<p>&#378; q&#769; &#341;
 &#377; Q&#769; &#340;
 </p>
 <p>&#7720; &#7721;
@@ -656,7 +656,7 @@ $result_converted{'latex_text'}->{'unknown_accents'} = 
'\\"{X} \\"{x} \\"{Q} \\"
 
 $result_converted{'docbook'}->{'unknown_accents'} = '<para>&#7820; &#7821; 
Q&#776; &#376;
 </para>
-<para>&#394; q&#769; &#341;
+<para>&#378; q&#769; &#341;
 &#377; Q&#769; &#340;
 </para>
 <para>&#7720; &#7721;