texinfo/tp Texinfo/Convert/Paragraph.pm Texinfo...

[Patrice Dumas]

CVSROOT:        /sources/texinfo
Module name:    texinfo
Changes by:     Patrice Dumas <pertusus>        10/11/08 00:04:37

Modified files:
        tp/Texinfo/Convert: Paragraph.pm Text.pm Unicode.pm 
        tp/t           : accents.t paragraph.t 
        tp/t/results/invalid_nestings: accents.pl 

Log message:
        Handle inhibiting end sentence.
        Convert a stack of accents.

CVSWeb URLs:
http://cvs.savannah.gnu.org/viewcvs/texinfo/tp/Texinfo/Convert/Paragraph.pm?cvsroot=texinfo&r1=1.2&r2=1.3
http://cvs.savannah.gnu.org/viewcvs/texinfo/tp/Texinfo/Convert/Text.pm?cvsroot=texinfo&r1=1.15&r2=1.16
http://cvs.savannah.gnu.org/viewcvs/texinfo/tp/Texinfo/Convert/Unicode.pm?cvsroot=texinfo&r1=1.4&r2=1.5
http://cvs.savannah.gnu.org/viewcvs/texinfo/tp/t/accents.t?cvsroot=texinfo&r1=1.2&r2=1.3
http://cvs.savannah.gnu.org/viewcvs/texinfo/tp/t/paragraph.t?cvsroot=texinfo&r1=1.2&r2=1.3
http://cvs.savannah.gnu.org/viewcvs/texinfo/tp/t/results/invalid_nestings/accents.pl?cvsroot=texinfo&r1=1.11&r2=1.12

Patches:
Index: Texinfo/Convert/Paragraph.pm
===================================================================
RCS file: /sources/texinfo/texinfo/tp/Texinfo/Convert/Paragraph.pm,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -b -r1.2 -r1.3
--- Texinfo/Convert/Paragraph.pm        7 Nov 2010 14:10:14 -0000       1.2
+++ Texinfo/Convert/Paragraph.pm        8 Nov 2010 00:04:37 -0000       1.3
@@ -118,7 +118,7 @@
   return $result;
 }
 
-# add a word and/or spaces.
+# add a word and/or spaces and end of sentence.
 sub add_next($;$$$)
 {
   my $paragraph = shift;
@@ -147,12 +147,18 @@
       $result .= $paragraph->end_line();
     }
   }
-  if ($end_sentence) {
-    $paragraph->{'end_sentence'} = 1;
+  if (defined($end_sentence)) {
+    $paragraph->{'end_sentence'} = $end_sentence;
   }
   return $result;
 }
 
+sub inhibit_end_sentence($)
+{
+  my $paragraph = shift;
+  $paragraph->{'end_sentence'} = 0;
+}
+
 my $end_sentence_character = quotemeta('.?!');
 my $after_punctuation_characters = quotemeta('"\')]');
 
@@ -202,14 +208,13 @@
       my $added_word = $1;
       $result .= $paragraph->add_next($added_word);
       # now check if it is considered as an end of sentence
-      if (!$paragraph->{'end_sentence'}) {
-        if ($paragraph->{'word'} =~ 
/[$end_sentence_character][$after_punctuation_characters]*$/
+      if (defined($paragraph->{'end_sentence'}) and 
+          $added_word =~ /^[$after_punctuation_characters]*$/) {
+        # do nothing in the case of a continuation of 
after_punctuation_characters
+      } elsif ($paragraph->{'word'} =~ 
/[$end_sentence_character][$after_punctuation_characters]*$/
          and $paragraph->{'word'} !~ 
/[[:upper:]][$end_sentence_character][$after_punctuation_characters]*$/) {
           $paragraph->{'end_sentence'} = 1;
         }
-      } elsif ($added_word !~ /^[$after_punctuation_characters]*$/) {
-        delete $paragraph->{'end_sentence'};
-      }
     }
   }
   return $result;

Index: Texinfo/Convert/Text.pm
===================================================================
RCS file: /sources/texinfo/texinfo/tp/Texinfo/Convert/Text.pm,v
retrieving revision 1.15
retrieving revision 1.16
diff -u -b -r1.15 -r1.16
--- Texinfo/Convert/Text.pm     6 Nov 2010 12:34:59 -0000       1.15
+++ Texinfo/Convert/Text.pm     8 Nov 2010 00:04:37 -0000       1.16
@@ -630,7 +630,7 @@
   return ($eight_bit, $codepoint);
 }
 
-sub eight_bit_accent($$$)
+sub eight_bit_accents($$$)
 {
   my $current = shift;
   my $encoding = shift;
@@ -748,6 +748,32 @@
   return $text . $accent;
 }
 
+# format a stack of accents as ascii
+sub ascii_accents ($)
+{
+  my $current = shift;
+  my ($result, $innermost_accent, $stack) = _find_innermost_accent($current);
+
+  foreach my $accent_command (reverse(@$stack)) {
+    $result = ascii_accent ($result, {'cmdname' => $accent_command});
+  }
+  return $result;
+}
+
+# format a stack of accents as unicode
+sub unicode_accents ($$)
+{
+  my $current = shift;
+  my $format_accents = shift;
+  my ($result, $innermost_accent, $stack) = _find_innermost_accent($current);
+
+  foreach my $accent_command (reverse(@$stack)) {
+    $result = Texinfo::Convert::Unicode::unicode_accent($result, 
+       {'cmdname' => $accent_command}, \&ascii_accent);
+  }
+  return $result;
+}
+
 sub _normalise_space($)
 {
   return undef unless (defined ($_[0]));
@@ -803,14 +829,16 @@
     } elsif ($accent_commands{$root->{'cmdname'}}) {
       return '' if (!$root->{'args'});
       if ($options->{'enable_encoding'} and $options->{'enable_encoding'} eq 
'utf-8') {
-        return 
Texinfo::Convert::Unicode::unicode_accent(convert($root->{'args'}->[0], 
$options), 
-                                            $root->{'cmdname'}, 
\&ascii_accent);
+        #return 
Texinfo::Convert::Unicode::unicode_accent(convert($root->{'args'}->[0], 
$options), 
+        #                                    $root, \&ascii_accent);
+        return unicode_accents($root, \&ascii_accent);
       } elsif ($options->{'enable_encoding'} 
          and 
$Texinfo::Commands::eight_bit_encoding_aliases{$options->{'enable_encoding'}}) {
-        return eight_bit_accent($root, $options->{'enable_encoding'}, 
+        return eight_bit_accents($root, $options->{'enable_encoding'}, 
               \&ascii_accent);
       } else {
-        return ascii_accent(convert($root->{'args'}->[0], $options), $root);
+        #return ascii_accent(convert($root->{'args'}->[0], $options), $root);
+        return ascii_accents($root);
       }
     } elsif ($root->{'cmdname'} eq 'image') {
       return convert($root->{'args'}->[0], $options);

Index: Texinfo/Convert/Unicode.pm
===================================================================
RCS file: /sources/texinfo/texinfo/tp/Texinfo/Convert/Unicode.pm,v
retrieving revision 1.4
retrieving revision 1.5
diff -u -b -r1.4 -r1.5
--- Texinfo/Convert/Unicode.pm  6 Nov 2010 12:34:59 -0000       1.4
+++ Texinfo/Convert/Unicode.pm  8 Nov 2010 00:04:37 -0000       1.5
@@ -557,4 +557,19 @@
   return &$fallback_convert_accent($text, $command);
 }
 
+sub unicode_text($$)
+{
+  my $self = shift;
+  my $command = shift;
+  my $text = $command->{'text'};
+
+  if (!$self->{'code'} and !$self->{'context'}->[-1] eq 'preformatted') {
+    $text =~ s/---/\x{2014}/g;
+    $text =~ s/--/\x{2013}/g;
+    $text =~ s/``/\x{201C}/g;
+    $text =~ s/''/\x{201D}/g;
+  }
+  return Unicode::Normalize::NFC($text);
+}
+
 1;

Index: t/accents.t
===================================================================
RCS file: /sources/texinfo/texinfo/tp/t/accents.t,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -b -r1.2 -r1.3
--- t/accents.t 6 Nov 2010 12:34:59 -0000       1.2
+++ t/accents.t 8 Nov 2010 00:04:37 -0000       1.3
@@ -45,7 +45,7 @@
   my $parser = Texinfo::Parser::parser({'context' => 'preformatted'});
   my $tree = $parser->parse_texi_text($texi);
   my $result = 
-       Texinfo::Convert::Text::eight_bit_accent($tree->{'contents'}->[0], 
+       Texinfo::Convert::Text::eight_bit_accents($tree->{'contents'}->[0], 
     'iso-8859-1', \&Texinfo::Convert::Text::ascii_accent);
   if (defined($reference)) {
     #ok (Encode::decode('iso-8859-1', $reference) eq $result, $name);

Index: t/paragraph.t
===================================================================
RCS file: /sources/texinfo/texinfo/tp/t/paragraph.t,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -b -r1.2 -r1.3
--- t/paragraph.t       7 Nov 2010 14:10:14 -0000       1.2
+++ t/paragraph.t       8 Nov 2010 00:04:37 -0000       1.3
@@ -9,7 +9,7 @@
 
 #use Test;
 use Test::More;
-BEGIN { plan tests => 33 };
+BEGIN { plan tests => 38 };
 use lib '../texi2html/lib/Unicode-EastAsianWidth/lib/';
 #push @INC, '../texi2html/lib/Unicode-EastAsianWidth/lib/';
 use Texinfo::Convert::Paragraph;
@@ -70,25 +70,25 @@
 $result .= $para->add_next('_');
 $result .= $para->wrap_next(' after');
 $result .= $para->end();
-is ("aa.)_  after\n", $result, 'add char after end sentence');
+is ($result, "aa.)_  after\n", 'add char after end sentence');
 
 $para = Texinfo::Convert::Paragraph->new();
 $result = '';
 $result .= $para->end_line();
 $result .= $para->wrap_next(' after');
 $result .= $para->end();
-is ("\nafter\n", $result, 'space after end_line');
+is ($result, "\nafter\n", 'space after end_line');
 #print STDERR "$result";
 
 $para = Texinfo::Convert::Paragraph->new();
 $result = '';
 $result .= $para->wrap_next('aa.)');
 $result .= $para->add_pending_word();
-is ('aa.)', $result, 'call add_pending_word');
+is ($result, 'aa.)', 'call add_pending_word');
 $result = $para->end_line();
-is ("\n", $result, 'call end_line after add_pending_word');
+is ($result, "\n", 'call end_line after add_pending_word');
 $result = $para->end();
-is ('', $result, 'call end after end_line');
+is ($result, '', 'call end after end_line');
 
 $para = Texinfo::Convert::Paragraph->new();
 $result = '';
@@ -96,7 +96,7 @@
 $result .= $para->add_pending_word();
 $result .= $para->wrap_next(' after');
 $result .= $para->end();
-is ("aa.)  after\n", $result, 'space after sentence and add_pending_word');
+is ($result, "aa.)  after\n", 'space after sentence and add_pending_word');
 
 $para = Texinfo::Convert::Paragraph->new();
 $result = '';
@@ -104,7 +104,7 @@
 $result .= $para->add_next('.', undef, 1);
 $result .= $para->wrap_next(' after');
 $result .= $para->end();
-is ("aA.  after\n", $result, 'force end sentence after upper case');
+is ($result, "aA.  after\n", 'force end sentence after upper case');
 
 $para = Texinfo::Convert::Paragraph->new();
 $result = '';
@@ -112,7 +112,51 @@
 $result .= $para->wrap_next('.');
 $result .= $para->wrap_next(' after');
 $result .= $para->end();
-is ("aA. after\n", $result, 'end sentence after upper case');
+is ($result, "aA. after\n", 'end sentence after upper case');
 
+$para = Texinfo::Convert::Paragraph->new();
+$result = '';
+$result .= $para->wrap_next('aa.)');
+$result .= $para->wrap_next('))');
+$result .= $para->wrap_next(' after');
+$result .= $para->end();
+is ($result, "aa.)))  after\n", 'continue with after_punctuation_characters');
+
+$para = Texinfo::Convert::Paragraph->new();
+$result = '';
+$result .= $para->wrap_next('aa.)');
+$para->inhibit_end_sentence();
+$result .= $para->wrap_next(' after');
+$result .= $para->end();
+is ($result, "aa.) after\n", 'inhibit end sentence');
+
+$para = Texinfo::Convert::Paragraph->new();
+$result = '';
+$result .= $para->wrap_next('aa.)');
+$para->inhibit_end_sentence();
+$result .= $para->add_next('_');
+$result .= $para->wrap_next(' after');
+$result .= $para->end();
+is ($result, "aa.)_ after\n", 'inhibit end sentence then add next');
+
+$para = Texinfo::Convert::Paragraph->new();
+$result = '';
+$result .= $para->wrap_next('aa.)');
+$para->inhibit_end_sentence();
+$result .= $para->wrap_next('aa.)');
+$result .= $para->wrap_next(' after');
+$result .= $para->end();
+is ($result, "aa.)aa.)  after\n", 'cancel inhibit end sentence');
+
+$para = Texinfo::Convert::Paragraph->new();
+$result = '';
+$result .= $para->wrap_next('aa.)');
+$para->inhibit_end_sentence();
+$result .= $para->wrap_next('))');
+$result .= $para->wrap_next(' after');
+$result .= $para->end();
+is ($result, "aa.))) after\n", 'inhibit end sentence and ))');
+
+$para = Texinfo::Convert::Paragraph->new();
 
 1;

Index: t/results/invalid_nestings/accents.pl
===================================================================
RCS file: /sources/texinfo/texinfo/tp/t/results/invalid_nestings/accents.pl,v
retrieving revision 1.11
retrieving revision 1.12
diff -u -b -r1.11 -r1.12
--- t/results/invalid_nestings/accents.pl       1 Nov 2010 11:40:45 -0000       
1.11
+++ t/results/invalid_nestings/accents.pl       8 Nov 2010 00:04:37 -0000       
1.12
@@ -210,7 +210,7 @@
 TeX~. @~.
 
 Invalid
-a~.  ^.
+~.  ^.
 ';
 
 $result_errors{'accents'} = [