branch master updated: * tp/Texinfo/Convert/Converter.pm (xml_format_text_with_numeric_entities), tp/Texinfo/Convert/DocBook.pm (_convert), tp/Texinfo/Convert/HTML.pm (_convert_text): add xml_format_text_with_numeric_entities() based on DocBook converter text, and use it in HTML if USE_NUMERIC_ENTITY is set.

[Patrice Dumas]

This is an automated email from the git hooks/post-receive script.

pertusus pushed a commit to branch master
in repository texinfo.

The following commit(s) were added to refs/heads/master by this push:
     new c8c62a8  * tp/Texinfo/Convert/Converter.pm 
(xml_format_text_with_numeric_entities), tp/Texinfo/Convert/DocBook.pm 
(_convert), tp/Texinfo/Convert/HTML.pm (_convert_text): add 
xml_format_text_with_numeric_entities() based on DocBook converter text, and 
use it in HTML if USE_NUMERIC_ENTITY is set.
c8c62a8 is described below

commit c8c62a8132a1a02c91a2de98d52b124bbc855b01
Author: Patrice Dumas <pertusus@free.fr>
AuthorDate: Sun Dec 19 15:32:52 2021 +0100

    * tp/Texinfo/Convert/Converter.pm
    (xml_format_text_with_numeric_entities),
    tp/Texinfo/Convert/DocBook.pm (_convert),
    tp/Texinfo/Convert/HTML.pm (_convert_text): add
    xml_format_text_with_numeric_entities() based on DocBook
    converter text, and use it in HTML if USE_NUMERIC_ENTITY
    is set.
---
 ChangeLog                       | 10 ++++++++++
 tp/Texinfo/Convert/Converter.pm | 28 ++++++++++++++++++++++++++++
 tp/Texinfo/Convert/DocBook.pm   | 17 +++--------------
 tp/Texinfo/Convert/HTML.pm      |  4 +++-
 4 files changed, 44 insertions(+), 15 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index 7b301e0..9abc551 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -28,6 +28,16 @@
 
 2021-12-19  Patrice Dumas  <pertusus@free.fr>
 
+       * tp/Texinfo/Convert/Converter.pm
+       (xml_format_text_with_numeric_entities),
+       tp/Texinfo/Convert/DocBook.pm (_convert),
+       tp/Texinfo/Convert/HTML.pm (_convert_text): add
+       xml_format_text_with_numeric_entities() based on DocBook
+       converter text, and use it in HTML if USE_NUMERIC_ENTITY
+       is set.
+
+2021-12-19  Patrice Dumas  <pertusus@free.fr>
+
        * tp/Texinfo/ParserNonXS.pm (_parse_macro_command_line)
        (_lookup_macro_parameter, _expand_macro_body, _parse_texi):
        Add _lookup_macro_parameter() to find the formal argument index
diff --git a/tp/Texinfo/Convert/Converter.pm b/tp/Texinfo/Convert/Converter.pm
index 1a31e73..92575e6 100644
--- a/tp/Texinfo/Convert/Converter.pm
+++ b/tp/Texinfo/Convert/Converter.pm
@@ -1364,6 +1364,29 @@ sub sort_element_counts($$;$$)
 
 # XML related methods and variables that may be used in different
 # XML Converters.
+
+my $xml_numeric_entity_mdash = '&#'.hex('2014').';';
+my $xml_numeric_entity_ndash = '&#'.hex('2013').';';
+my $xml_numeric_entity_ldquo = '&#'.hex('201C').';';
+my $xml_numeric_entity_rdquo = '&#'.hex('201D').';';
+my $xml_numeric_entity_lsquo = '&#'.hex('2018').';';
+my $xml_numeric_entity_rsquo = '&#'.hex('2019').';';
+
+sub xml_format_text_with_numeric_entities($$)
+{
+  my $self = shift;
+  my $text = shift;
+ 
+  $text =~ s/``/$xml_numeric_entity_ldquo/g;
+  $text =~ s/\'\'/$xml_numeric_entity_rdquo/g;
+  $text =~ s/`/$xml_numeric_entity_lsquo/g;
+  $text =~ s/\'/$xml_numeric_entity_rsquo/g;
+  $text =~ s/---/$xml_numeric_entity_mdash/g;
+  $text =~ s/--/$xml_numeric_entity_ndash/g;
+
+  return $text;
+}
+
 sub xml_protect_text($$)
 {
   my $self = shift;
@@ -1835,6 +1858,11 @@ Other C<Texinfo::Convert::Converter> methods target 
conversion to XML:
 
 =over
 
+=item $formatted_text = 
$converter->xml_format_text_with_numeric_entities($text)
+
+Replace quotation marks and hyphens used to represent dash in
+Texinfo text with numeric XML entities.
+
 =item $protected_text = $converter->xml_protect_text($text)
 
 Protect special XML characters (&, E<lt>, E<gt>, ") of I<$text>.
diff --git a/tp/Texinfo/Convert/DocBook.pm b/tp/Texinfo/Convert/DocBook.pm
index 8b9f613..a1565d0 100644
--- a/tp/Texinfo/Convert/DocBook.pm
+++ b/tp/Texinfo/Convert/DocBook.pm
@@ -43,12 +43,6 @@ $VERSION = '6.8dev';
 
 
 my $nbsp = '&#'.hex('00A0').';';
-my $mdash = '&#'.hex('2014').';';
-my $ndash = '&#'.hex('2013').';';
-my $ldquo = '&#'.hex('201C').';';
-my $rdquo = '&#'.hex('201D').';';
-my $lsquo = '&#'.hex('2018').';';
-my $rsquo = '&#'.hex('2019').';';
 
 my %defaults = (
   #'ENABLE_ENCODING'      => 0,
@@ -60,8 +54,8 @@ my %defaults = (
   'output_format'        => 'docbook',
   'SPLIT'                => 0,
   'documentlanguage'     => undef,
-  'OPEN_QUOTE_SYMBOL'    => $lsquo,
-  'CLOSE_QUOTE_SYMBOL'   => $rsquo,
+  'OPEN_QUOTE_SYMBOL'    => '&#'.hex('2018').';',
+  'CLOSE_QUOTE_SYMBOL'   => '&#'.hex('2019').';',
   'USE_NUMERIC_ENTITY'   => 1,
 );
 
@@ -523,12 +517,7 @@ sub _convert($$;$)
     $result = $self->_protect_text($result);
     if (! defined($element->{'type'}) or $element->{'type'} ne 'raw') {
       if (!$self->{'document_context'}->[-1]->{'monospace'}->[-1]) {
-        $result =~ s/``/$ldquo/g;
-        $result =~ s/\'\'/$rdquo/g;
-        $result =~ s/`/$lsquo/g;
-        $result =~ s/\'/$rsquo/g;
-        $result =~ s/---/$mdash/g;
-        $result =~ s/--/$ndash/g;
+        $result = $self->xml_format_text_with_numeric_entities($result);
       }
     }
     #warn "had text `$element->{'text'}', returning $result\n";
diff --git a/tp/Texinfo/Convert/HTML.pm b/tp/Texinfo/Convert/HTML.pm
index d5ed74d..6d2f127 100644
--- a/tp/Texinfo/Convert/HTML.pm
+++ b/tp/Texinfo/Convert/HTML.pm
@@ -4276,7 +4276,9 @@ sub _convert_text($$$)
     $text = Texinfo::Convert::Unicode::unicode_text($text,
                                         ($self->in_code() or 
$self->in_math()));
   } elsif (!$self->in_code() and !$self->in_math()) { 
-    if ($self->get_conf('USE_ISO')) {
+    if ($self->get_conf('USE_NUMERIC_ENTITY')) {
+      $text = $self->xml_format_text_with_numeric_entities($text);
+    } elsif ($self->get_conf('USE_ISO')) {
       $text =~ s/---/\&mdash\;/g;
       $text =~ s/--/\&ndash\;/g;
       $text =~ s/``/\&ldquo\;/g;