[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[6367] prepare for XSParagraph
|
From: |
Gavin D. Smith |
|
Subject: |
[6367] prepare for XSParagraph |
|
Date: |
Tue, 30 Jun 2015 11:19:13 +0000 |
Revision: 6367
http://svn.sv.gnu.org/viewvc/?view=rev&root=texinfo&revision=6367
Author: gavin
Date: 2015-06-30 11:19:12 +0000 (Tue, 30 Jun 2015)
Log Message:
-----------
prepare for XSParagraph
Modified Paths:
--------------
trunk/ChangeLog
trunk/tp/Makefile.am
trunk/tp/Texinfo/Convert/Line.pm
trunk/tp/Texinfo/Convert/Paragraph.pm
trunk/tp/Texinfo/Convert/Plaintext.pm
trunk/tp/Texinfo/Convert/UnFilled.pm
trunk/tp/t/paragraph.t
trunk/tp/texi2any.pl
Modified: trunk/ChangeLog
===================================================================
--- trunk/ChangeLog 2015-06-28 23:01:14 UTC (rev 6366)
+++ trunk/ChangeLog 2015-06-30 11:19:12 UTC (rev 6367)
@@ -1,3 +1,48 @@
+2015-06-30 Gavin Smith <address@hidden>
+
+ * tp/Texinfo/Convert/Line.pm, tp/Texinfo/Convert/Paragraph.pm,
+ tp/Texinfo/Convert/UnFilled.pm: (allow_end_sentence): New function.
+
+ * tp/Texinfo/Convert/Line.pm, tp/Texinfo/Convert/Paragraph.pm,
+ tp/Texinfo/Convert/UnFilled.pm (_add_text, add_next, _add_next):
+ Handle backspace as a marker to allow an end of sentence.
+
+ * tp/Texinfo/Convert/Plaintext.pm (_protect_sentence_ends): New
+ function.
+ (_process_text): Don't return a pair the second element of which
+ is the underlying text. Instead, call _protect_sentence_ends on
+ the text. No special handing of @code or @var. Caller in
+ _convert updated.
+
+ (new_formatter): Add commented-out line to use XSParagraph
+ instead of Texinfo::Convert::Paragraph.
+
+ (_count_added): Reinstate a commented-out use of end_line_count
+ method.
+
+ (_convert): Remove check for 'underlying_text' element, which
+ was only used for @acronym and @abbr.
+ <@acronym and @abbr>: Don't cause underlying text to be saved in
+ the formatters. Instead, call allow_end_sentence after
+ converting the argument, and return the result of the
+ conversion.
+ <close @var and close monospace>: Call allow_end_sentence method
+ on formatter.
+ <brace commands with no arguments> If command is not a single
+ character, call allow_end_sentence after converting. Call
+ allow_end_sentence if in @var or monospace.
+ <accent commands>: Don't pass underlying text to the formatters.
+ Always call allow_end_sentence in @var and monospace, and call
+ it when in @sc and the original output would have been not have
+ been an uppercase letter.
+
+ * tp/texi2any.pl (BEGIN) <in-source run> Add directories for
+ XSParagraph to @INC.
+ * tp/Makefile.am (AM_T_LOG_FLAGS): Add -I flags for XSParagraph.
+
+ * tp/t/paragraph.t (underlying text lower case)
+ (line underlying text lower case): Tests removed.
+
2015-06-26 Gavin Smith <address@hidden>
* README-hacking: Notes on how to tag source tree and update
Modified: trunk/tp/Makefile.am
===================================================================
--- trunk/tp/Makefile.am 2015-06-28 23:01:14 UTC (rev 6366)
+++ trunk/tp/Makefile.am 2015-06-30 11:19:12 UTC (rev 6367)
@@ -175,6 +175,9 @@
$(top_srcdir)/build-aux/tap-driver.sh
T_LOG_COMPILER = $(PERL)
AM_T_LOG_FLAGS = -w
+AM_T_LOG_FLAGS += -ITexinfo/Convert/XSParagraph/lib
+AM_T_LOG_FLAGS += -ITexinfo/Convert/XSParagraph/blib/arch
+
AM_TESTS_ENVIRONMENT = srcdir="$(srcdir)"; export srcdir;
top_srcdir="$(top_srcdir)"; export top_srcdir;
# just a convenience for running these additional tests.
Modified: trunk/tp/Texinfo/Convert/Line.pm
===================================================================
--- trunk/tp/Texinfo/Convert/Line.pm 2015-06-28 23:01:14 UTC (rev 6366)
+++ trunk/tp/Texinfo/Convert/Line.pm 2015-06-30 11:19:12 UTC (rev 6367)
@@ -166,6 +166,9 @@
return $line->_add_next($word, undef, $space, $end_sentence, $transparent);
}
+my $end_sentence_character = quotemeta('.?!');
+my $after_punctuation_characters = quotemeta('"\')]');
+
# add a word and/or spaces and end of sentence.
sub _add_next($;$$$$$)
{
@@ -180,6 +183,10 @@
$underlying_word = $word if (!defined($underlying_word));
if (defined($word)) {
+ my $disinhibit; # full stop after capital letter ends sentence
+ if ($word =~ s/\x08$//) {
+ $disinhibit = 1;
+ }
if (!defined($line->{'word'})) {
$line->{'word'} = '';
$line->{'underlying_word'} = '';
@@ -194,7 +201,18 @@
}
}
$line->{'word'} .= $word;
- $line->{'underlying_word'} .= $underlying_word unless ($transparent);
+
+ if (!$transparent) {
+ if ($disinhibit) {
+ $line->{'underlying_word'} = 'a';
+ } elsif ($word =~
+ /([^$end_sentence_character$after_punctuation_characters])
+ [$end_sentence_character$after_punctuation_characters]*$/x) {
+ # Save the last character in $word before punctuation
+ $line->{'underlying_word'} = $1;
+ }
+ }
+
if ($line->{'DEBUG'}) {
print STDERR "WORD+.L $word -> $line->{'word'}\n";
print STDERR "WORD+.L $underlying_word -> $line->{'underlying_word'}\n";
@@ -231,6 +249,12 @@
$line->{'end_sentence'} = 0;
}
+sub allow_end_sentence($)
+{
+ my $line = shift;
+ $line->{'underlying_text'} = 'a'; # lower-case
+}
+
sub set_space_protection($$;$$$)
{
my $line = shift;
@@ -261,9 +285,6 @@
return '';
}
-my $end_sentence_character = quotemeta('.?!');
-my $after_punctuation_characters = quotemeta('"\')]');
-
# wrap a text.
sub add_text($$;$)
{
@@ -316,16 +337,32 @@
}
} elsif ($text =~ s/^(([^\s\p{InFullwidth}]|[\x{202f}\x{00a0}])+)//) {
my $added_word = $1;
- $underlying_text =~ s/^(([^\s\p{InFullwidth}]|[\x{202f}\x{00a0}])+)//;
- my $underlying_added_word = $1;
- $result .= $line->_add_next($added_word, $underlying_added_word);
- # now check if it is considered as an end of sentence
- if (defined($line->{'end_sentence'}) and
- $added_word =~ /^[$after_punctuation_characters]*$/) {
- # do nothing in the case of a continuation of
after_punctuation_characters
- } elsif ($line->{'underlying_word'} =~
/[$end_sentence_character][$after_punctuation_characters]*$/
- and $line->{'underlying_word'} !~
/[[:upper:]][$end_sentence_character$after_punctuation_characters]*$/) {
+ # Whether a sentence end is permitted in spite of a preceding
+ # upper case letter.
+ my $disinhibit = 0;
+
+ # Reverse the insertion of the control character in Plaintext.pm.
+ if ($added_word =~ s/\x08(?=[$end_sentence_character]
+ [$after_punctuation_characters]*$)//x) {
+ $disinhibit = 0;
+ }
+ $result .= _add_next($line, $added_word);
+
+ my $last_letter = $line->{'underlying_word'};
+
+ # Check if it is considered as an end of sentence. There are two things
+ # to check: one, that we have a ., ! or ?; and second, that it is not
+ # preceded by an upper-case letter (ignoring some punctuation)
+ if (defined($line->{'end_sentence'})
+ and $added_word =~ /^[$after_punctuation_characters]*$/) {
+ # do nothing in the case of a continuation of
+ # after_punctuation_characters
+ } elsif (($disinhibit
+ or !$last_letter
+ or $last_letter !~ /[[:upper:]]/)
+ and $added_word =~ /[$end_sentence_character]
+ [$after_punctuation_characters]*$/x) {
if ($line->{'frenchspacing'}) {
$line->{'end_sentence'} = -1;
} else {
Modified: trunk/tp/Texinfo/Convert/Paragraph.pm
===================================================================
--- trunk/tp/Texinfo/Convert/Paragraph.pm 2015-06-28 23:01:14 UTC (rev
6366)
+++ trunk/tp/Texinfo/Convert/Paragraph.pm 2015-06-30 11:19:12 UTC (rev
6367)
@@ -168,6 +168,9 @@
return $result;
}
+my $end_sentence_character = quotemeta('.?!');
+my $after_punctuation_characters = quotemeta('"\')]');
+
sub add_next($;$$$$)
{
my $paragraph = shift;
@@ -176,25 +179,27 @@
my $end_sentence = shift;
my $transparent = shift;
$paragraph->{'end_line_count'} = 0;
- return _add_next($paragraph, $word, undef, $space, $end_sentence,
+ return _add_next($paragraph, $word, $space, $end_sentence,
$transparent);
}
# add a word and/or spaces and end of sentence.
sub _add_next($;$$$$$$)
{
- my $paragraph = $_[0];
- my $word = $_[1];
- my $space = $_[3];
- my $end_sentence = $_[4];
- my $transparent = $_[5];
+ my $paragraph = shift;
+ my $word = shift;
+ my $space = shift;
+ my $end_sentence = shift;
+ my $transparent = shift;
+ my $newlines_impossible = shift;
my $result = '';
if (defined($word)) {
- my $underlying_word = $_[2];
- my $newlines_impossible = $_[6];
- $underlying_word = $word if (!defined($underlying_word));
-
+ my $disinhibit = 0;
+ # Reverse the insertion of the control character in Plaintext.pm.
+ if ($word =~ s/\x08$//) {
+ $disinhibit = 1;
+ }
if (!defined($paragraph->{'word'})) {
$paragraph->{'word'} = '';
$paragraph->{'underlying_word'} = '';
@@ -212,7 +217,18 @@
}
$paragraph->{'word'} .= $word;
- $paragraph->{'underlying_word'} .= $underlying_word unless($transparent);
+
+ if (!$transparent) {
+ if ($disinhibit) {
+ $paragraph->{'underlying_word'} = 'a';
+ } elsif ($word =~
+ /([^$end_sentence_character$after_punctuation_characters])
+ [$end_sentence_character$after_punctuation_characters]*$/x) {
+ # Save the last character in $word before punctuation
+ $paragraph->{'underlying_word'} = $1;
+ }
+ }
+
if (!$newlines_impossible and $word =~ /\n/) {
$result .= $paragraph->{'space'};
$paragraph->{'space'} = '';
@@ -229,13 +245,7 @@
if (defined($paragraph->{'word'})) {
$para_word = $paragraph->{'word'};
}
- my $para_underlying_word = 'UNDEF';;
- if (defined($paragraph->{'underlying_word'})) {
- $para_underlying_word = $paragraph->{'word'};
- }
-
print STDERR "WORD+ $word -> $para_word\n";
- print STDERR "UNDERLYING_WORD+ $underlying_word ->
$para_underlying_word\n";
}
# The $paragraph->{'counter'} != 0 is here to avoid having an
# additional line output when the text is longer than the max.
@@ -280,6 +290,13 @@
$paragraph->{'end_sentence'} = 0;
}
+sub allow_end_sentence($)
+{
+ my $paragraph = shift;
+ printf STDERR "ALLOW END SENTENCE\n" if $paragraph->{'DEBUG'};
+ $paragraph->{'underlying_word'} = 'a'; # lower-case
+}
+
sub set_space_protection($$;$$$)
{
my $paragraph = shift;
@@ -310,9 +327,6 @@
return '';
}
-my $end_sentence_character = quotemeta('.?!');
-my $after_punctuation_characters = quotemeta('"\')]');
-
# wrap a text.
sub add_text($$;$)
{
@@ -347,13 +361,11 @@
}
# \x{202f}\x{00a0} are non breaking spaces
if (defined $spaces) {
- $underlying_text =~ s/^([^\S\x{202f}\x{00a0}]+)//
- if defined($underlying_text);
print STDERR "SPACES($paragraph->{'counter'})
`"._print_escaped_spaces($spaces)."'\n" if $debug_flag;
#my $added_word = $paragraph->{'word'};
if ($protect_spaces_flag) {
$paragraph->{'word'} .= $spaces;
- $paragraph->{'underlying_word'} .= $spaces;
+ $paragraph->{'underlying_word'} = substr($spaces, -1);
$paragraph->{'word_counter'} += length($spaces);
#$paragraph->{'space'} .= $spaces;
if ($paragraph->{'word'} =~ s/\n/ /g
@@ -362,15 +374,9 @@
and $paragraph->{'end_sentence'} > 0) {
$paragraph->{'word'} =~ /(\s*)$/;
if (length($1) < 2) {
- #$paragraph->{'word'} =~ s/(\s*)$/ /;
- #$paragraph->{'underlying_word'} =~ s/(\s*)$/ /;
- #my $removed = $1;
- #$paragraph->{'word_counter'} += length(' ') - length($removed);
my $added = ' ' x (2 - length($1));
$paragraph->{'word'} .= $added;
- $paragraph->{'word'} =~ /(\s*)$/;
- my $end_spaces = $1;
- $paragraph->{'underlying_word'} =~ s/(\s*)$/$end_spaces/;
+ $paragraph->{'underlying_word'} = ' ';
$paragraph->{'word_counter'} += length($added);
}
}
@@ -422,23 +428,32 @@
$result .= _end_line($paragraph);
}
} elsif (defined $added_word) {
- my $underlying_added_word;
- if (defined($underlying_text)) {
- $underlying_text =~ s/^(([^\s\p{InFullwidth}]|[\x{202f}\x{00a0}])+)//;
- $underlying_added_word = $1;
- } else {
- $underlying_added_word = $added_word;
+ # Whether a sentence end is permitted in spite of a preceding
+ # upper case letter.
+ my $disinhibit = 0;
+
+ # Reverse the insertion of the control character in Plaintext.pm.
+ if ($added_word =~ s/\x08(?=[$end_sentence_character]
+ [$after_punctuation_characters]*$)//x) {
+ $disinhibit = 1;
}
- $result .= _add_next($paragraph, $added_word, $underlying_added_word,
- undef, undef, undef, !$newline_possible_flag);
+ $result .= _add_next($paragraph, $added_word, undef, undef,
+ undef, !$newline_possible_flag);
- # now check if it is considered as an end of sentence
+ my $last_letter = $paragraph->{'underlying_word'};
+
+ # Check if it is considered as an end of sentence. There are two things
+ # to check: one, that we have a ., ! or ?; and second, that it is not
+ # preceded by an upper-case letter (ignoring some punctuation)
if (defined($paragraph->{'end_sentence'})
- and $underlying_added_word =~ /^[$after_punctuation_characters]*$/o)
{
+ and $added_word =~ /^[$after_punctuation_characters]*$/o) {
# do nothing in the case of a continuation of
after_punctuation_characters
- } elsif ($paragraph->{'underlying_word'} =~
/[$end_sentence_character][$after_punctuation_characters]*$/o
- and $paragraph->{'underlying_word'} !~
/[[:upper:]][$end_sentence_character$after_punctuation_characters]*$/o) {
+ } elsif (($disinhibit
+ or !$last_letter
+ or $last_letter !~ /[[:upper:]]/)
+ and $added_word =~ /[$end_sentence_character]
+ [$after_punctuation_characters]*$/x) {
if ($paragraph->{'frenchspacing'}) {
$paragraph->{'end_sentence'} = -1;
} else {
Modified: trunk/tp/Texinfo/Convert/Plaintext.pm
===================================================================
--- trunk/tp/Texinfo/Convert/Plaintext.pm 2015-06-28 23:01:14 UTC (rev
6366)
+++ trunk/tp/Texinfo/Convert/Plaintext.pm 2015-06-30 11:19:12 UTC (rev
6367)
@@ -31,6 +31,10 @@
use Texinfo::Convert::Line;
use Texinfo::Convert::UnFilled;
+use XSParagraph;
+XSParagraph::hello ();
+# TODO: Run initialization code for XSParagraph implicitly.
+
use Carp qw(cluck);
require Exporter;
@@ -54,7 +58,7 @@
@EXPORT = qw(
);
-$VERSION = '5.1.90';
+$VERSION = '6.0';
# misc commands that are of use for formatting.
my %formatting_misc_commands =
%Texinfo::Convert::Text::formatting_misc_commands;
@@ -551,6 +555,34 @@
return undef;
}
+my $end_sentence = quotemeta('.?!');
+my $after_punctuation = quotemeta('"\')]');
+
+sub _protect_sentence_ends ($) {
+ my $text = shift;
+ # Avoid suppressing end of sentence, by inserting a control character
+ # in front of the full stop. The choice of BS for this is arbitrary.
+ $text =~ s/(?<=[^[:upper:]])
+ (?=[$end_sentence][$after_punctuation]*(?:\s|$))
+ /\x08/gx;
+
+ # Also insert a control character at end of string, to protect a full stop
+ # that may follow later.
+
+ #$text =~ s/(?<=[^[:upper:]][$after_punctuation]*)$/\x08/;
+ # Perl doesn't support "variable length lookbehind"
+
+ $text = reverse $text;
+ $text =~ s/^(?=[$after_punctuation]*
+ (?:[^[:upper:]\s]|[\x{202f}\x{00a0}]))
+ /\x08/x;
+ $text = reverse $text;
+
+ return $text;
+}
+
+# Convert ``, '', `, ', ---, -- in $COMMAND->{'text'} to their output,
+# possibly coverting to upper case as well.
sub _process_text($$$)
{
my $self = shift;
@@ -558,30 +590,22 @@
my $context = shift;
my $text = $command->{'text'};
+ if ($context->{'upper_case'}
+ or $self->{'formatters'}[-1]->{'var'}) {
+ $text = _protect_sentence_ends($text);
- my $lower_case_text;
- if ($context->{'upper_case'}) {
- $lower_case_text = $text;
+ if ($self->{'debug'}) {
+ my $debug_text = $text;
+ $debug_text =~ s/\x08/!!/g;
+ print STDERR "markers:<$debug_text>\n";
+ }
+
$text = uc($text);
}
- # Even if in upper case, in code style or @var always end a sentence.
- if (#$context->{'code'}
- $context->{'font_type_stack'}->[-1]->{'monospace'}
- or $context->{'var'}) {
- $lower_case_text = lc($text);
- }
+
if ($self->{'to_utf8'}) {
- if (defined($lower_case_text)) {
- $lower_case_text
- = Texinfo::Convert::Unicode::unicode_text($lower_case_text,
- #$context->{'code'});
- $context->{'font_type_stack'}->[-1]->{'monospace'});
- }
- return (Texinfo::Convert::Unicode::unicode_text($text,
- $context->{'font_type_stack'}->[-1]->{'monospace'}),
- #$context->{'code'}),
- $lower_case_text);
- #} elsif (!$context->{'code'}) {
+ return Texinfo::Convert::Unicode::unicode_text($text,
+ $context->{'font_type_stack'}->[-1]->{'monospace'});
} elsif (!$context->{'font_type_stack'}->[-1]->{'monospace'}) {
$text =~ s/---/\x{1F}/g;
$text =~ s/--/-/g;
@@ -589,16 +613,8 @@
$text =~ s/``/"/g;
$text =~ s/\'\'/"/g;
$text =~ s/`/'/g;
- if (defined($lower_case_text)) {
- $lower_case_text =~ s/---/\x{1F}/g;
- $lower_case_text =~ s/--/-/g;
- $lower_case_text =~ s/\x{1F}/--/g;
- $lower_case_text =~ s/``/"/g;
- $lower_case_text =~ s/\'\'/"/g;
- $lower_case_text =~ s/`/'/g;
- }
}
- return ($text, $lower_case_text);
+ return $text;
}
sub new_formatter($$;$)
@@ -641,6 +657,7 @@
$container = Texinfo::Convert::Line->new($container_conf);
} elsif ($type eq 'paragraph') {
$container = Texinfo::Convert::Paragraph->new($container_conf);
+ #$container = XSParagraph->new($container_conf);
} elsif ($type eq 'unfilled') {
$container = Texinfo::Convert::UnFilled->new($container_conf);
} else {
@@ -786,8 +803,7 @@
my $container = shift;
my $text = shift;
- #$self->_add_lines_count($container->end_line_count());
- $self->{'count_context'}->[-1]->{'lines'} += $container->{'end_line_count'};
+ $self->_add_lines_count($container->end_line_count());
#$self->_add_text_count($text);
#$self->{'count_context'}->[-1]->{'bytes'} +=
@@ -1640,12 +1656,10 @@
or $root->{'type'} eq 'last_raw_newline')) {
$result = _count_added($self, $formatter->{'container'},
$formatter->{'container'}->add_next($root->{'text'}));
- } elsif ($root->{'type'} and ($root->{'type'} eq 'underlying_text')) {
- $formatter->{'container'}->add_underlying_text($root->{'text'});
} else {
- my ($text, $lower_case_text) = _process_text($self, $root, $formatter);
+ my $text = _process_text($self, $root, $formatter);
$result = _count_added($self, $formatter->{'container'},
- $formatter->{'container'}->add_text($text,
$lower_case_text));
+ $formatter->{'container'}->add_text($text));
}
return $result;
# the following is only possible if paragraphindent is set to asis
@@ -1754,19 +1768,22 @@
my $text;
$text = Texinfo::Convert::Text::brace_no_arg_command($root,
- {%{$self->{'convert_text_options'}},
- 'sc' => $formatter->{'upper_case'}});
- my $lower_case_text;
- # always double spacing, so set underlying text lower case.
- if ($formatter->{'var'}
- or $formatter->{'font_type_stack'}->[-1]->{'monospace'}) {
- $lower_case_text = Texinfo::Convert::Text::brace_no_arg_command($root,
- {%{$self->{'convert_text_options'}},
- 'lc' => 1});
- } elsif ($formatter->{'upper_case'}) {
- $lower_case_text = Texinfo::Convert::Text::brace_no_arg_command($root,
- $self->{'convert_text_options'});
+ $self->{'convert_text_options'});
+
+ # @AA{} should suppress an end sentence, @aa{} shouldn't. This
+ # is the case whether we are in @sc or not.
+ if ($formatter->{'upper_case'}
+ and $letter_no_arg_commands{$root->{'cmdname'}}) {
+ $text = _protect_sentence_ends($text);
+ $text = uc($text);
+
+ if ($self->{'DEBUG'}) {
+ my $debug_text = $text;
+ $debug_text =~ s/\x08/!!/g;
+ print STDERR "accent markers:$debug_text\n";
+ }
}
+
if ($punctuation_no_arg_commands{$command}) {
$result .= _count_added($self, $formatter->{'container'},
$formatter->{'container'}->add_next($text, undef, 1));
@@ -1776,25 +1793,28 @@
$formatter->{'container'}->set_space_protection(1,undef))
if ($formatter->{'w'} == 1);
$result .= _count_added($self, $formatter->{'container'},
- $formatter->{'container'}->add_text($text,
- $lower_case_text));
+ $formatter->{'container'}->add_text($text));
$formatter->{'w'}--;
$result .= _count_added($self, $formatter->{'container'},
$formatter->{'container'}->set_space_protection(0,undef))
if ($formatter->{'w'} == 0);
} else {
- # This is to have @TeX{}, for example, be considered as tex
- # as underlying text in order not to prevent end sentences.
+ $result .= _count_added($self, $formatter->{'container'},
+ $formatter->{'container'}->add_text($text));
+
+ # This is to have @TeX{}, for example, not to prevent end sentences.
if (!$letter_no_arg_commands{$command}) {
- $lower_case_text = lc($text);
+ $formatter->{'container'}->allow_end_sentence();
}
- $result .= _count_added($self, $formatter->{'container'},
- $formatter->{'container'}->add_text($text,
- $lower_case_text));
+
if ($command eq 'dots') {
$formatter->{'container'}->inhibit_end_sentence();
}
}
+ if ($formatter->{'var'}
+ or $formatter->{'font_type_stack'}->[-1]->{'monospace'}) {
+ $formatter->{'container'}->allow_end_sentence();
+ }
return $result;
# commands with braces
} elsif ($accent_commands{$root->{'cmdname'}}) {
@@ -1808,18 +1828,22 @@
}
my $accented_text
= Texinfo::Convert::Text::text_accents($root, $encoding, $sc);
- my $accented_text_lower_case;
- if ($formatter->{'var'}
- or $formatter->{'font_type_stack'}->[-1]->{'monospace'}) {
- $accented_text_lower_case
- = Texinfo::Convert::Text::text_accents($root, $encoding, -1);
- } elsif ($formatter->{'upper_case'}) {
- $accented_text_lower_case
+ $result .= _count_added($self, $formatter->{'container'},
+ $formatter->{'container'}->add_text($accented_text));
+
+ my $accented_text_original;
+ if ($formatter->{'upper_case'}) {
+ $accented_text_original
= Texinfo::Convert::Text::text_accents($root, $encoding);
}
- $result .= _count_added($self, $formatter->{'container'},
- $formatter->{'container'}->add_text($accented_text,
- $accented_text_lower_case));
+
+ if ($accented_text_original
+ and $accented_text_original !~ /[[:upper:]]/
+ or $formatter->{'var'}
+ or $formatter->{'font_type_stack'}->[-1]->{'monospace'}) {
+ $formatter->{'container'}->allow_end_sentence();
+ }
+
# in case the text added ends with punctuation.
# If the text is empty (likely because of an error) previous
# punctuation will be cancelled, we don't want that.
@@ -1907,6 +1931,7 @@
if ($code_style_commands{$command}) {
#$formatter->{'code'}--;
$formatter->{'font_type_stack'}->[-1]->{'monospace'}--;
+ $formatter->{'container'}->allow_end_sentence();
pop @{$formatter->{'font_type_stack'}}
if !$formatter->{'font_type_stack'}->[-1]->{'monospace'};
} elsif ($regular_font_style_commands{$command}) {
@@ -1929,7 +1954,11 @@
}
if ($upper_case_commands{$command}) {
$formatter->{'upper_case'}--;
- $formatter->{'var'}-- if ($command eq 'var');
+ if ($command eq 'var') {
+ $formatter->{'var'}--;
+ # Allow a following full stop to terminate a sentence.
+ $formatter->{'container'}->allow_end_sentence();
+ }
}
return $result;
} elsif ($root->{'cmdname'} eq 'image') {
@@ -2207,13 +2236,13 @@
$root->{'extra'}->{'brace_command_contents'}->[-1]});
#print STDERR "".Data::Dumper->Dump([$prepended])."\n";
unshift @{$self->{'current_contents'}->[-1]}, $prepended;
+ return '';
} else {
- # FIXME The underlying_text added is very ugly. It leads to 'a'
- # being prepended in the underlying word after the abbr or acronym,
- # the intended effect being that a following period is always
- # interpreted as ending a sentence.
- unshift @{$self->{'current_contents'}->[-1]}, ($argument,
- {'type' => 'underlying_text', 'text' => 'a'});
+ $result = $self->_convert($argument);
+
+ # We want to permit an end of sentence, but not force it as @. does.
+ $formatter->{'container'}->allow_end_sentence();
+ return $result;
}
}
return '';
Modified: trunk/tp/Texinfo/Convert/UnFilled.pm
===================================================================
--- trunk/tp/Texinfo/Convert/UnFilled.pm 2015-06-28 23:01:14 UTC (rev
6366)
+++ trunk/tp/Texinfo/Convert/UnFilled.pm 2015-06-30 11:19:12 UTC (rev
6367)
@@ -88,6 +88,7 @@
{
my $line = shift;
my $text = shift;
+ $text =~ s/\x08//g;
if ($line->{'line_beginning'}) {
if ($line->{'indent_length'}) {
my $nspaces = $line->{'indent_length'} - $line->{'counter'};
@@ -176,6 +177,11 @@
my $line = shift;
}
+sub allow_end_sentence($)
+{
+ my $line = shift;
+}
+
sub set_space_protection($$;$$$)
{
return '';
Modified: trunk/tp/t/paragraph.t
===================================================================
--- trunk/tp/t/paragraph.t 2015-06-28 23:01:14 UTC (rev 6366)
+++ trunk/tp/t/paragraph.t 2015-06-30 11:19:12 UTC (rev 6367)
@@ -2,7 +2,7 @@
use Test::More;
use File::Spec;
-BEGIN { plan tests => 129;
+BEGIN { plan tests => 127;
if (defined($ENV{'top_srcdir'})) {
unshift @INC, File::Spec->catdir($ENV{'top_srcdir'}, 'tp');
my $lib_dir = File::Spec->catdir($ENV{'top_srcdir'}, 'tp',
'maintain');
@@ -490,11 +490,6 @@
$result .= $para->end();
is ($para->{'lines_counter'}, 2, 'count lines end paragraph');
-$para = Texinfo::Convert::Paragraph->new();
-$result = $para->add_text('AA. BB.', 'aa. bb.');
-$result .= $para->end();
-is ($result, "AA. BB.\n", 'underlying text lower case');
-
sub test_line($$$;$)
{
my $args = shift;
@@ -691,11 +686,6 @@
$result .= $line->end();
is ($line->{'lines_counter'}, 2, 'line count line end line');
-$line = Texinfo::Convert::Line->new();
-$result = $line->add_text('AA. BB.', 'aa. bb.');
-$result .= $line->end();
-is ($result, "AA. BB.", 'line underlying text lower case');
-
my $unfilled = Texinfo::Convert::UnFilled->new({'indent_length' => 5});
$result = '';
is ($unfilled->{'lines_counter'}, 0, 'line count unfilled first line begin');
Modified: trunk/tp/texi2any.pl
===================================================================
--- trunk/tp/texi2any.pl 2015-06-28 23:01:14 UTC (rev 6366)
+++ trunk/tp/texi2any.pl 2015-06-30 11:19:12 UTC (rev 6367)
@@ -87,6 +87,9 @@
# cause trouble if the modules are separately installed.
push @INC, $texinfolibdir;
}
+ push @INC, "${texinfolibdir}Texinfo/Convert/XSParagraph/lib";
+ push @INC, "${texinfolibdir}Texinfo/Convert/XSParagraph/blib/arch";
+ push @INC, "${texinfolibdir}Texinfo/Convert/XSParagraph";
# '@USE_EXTERNAL_LIBINTL @ and similar are substituted in the
# makefile using values from configure
| [Prev in Thread] |
Current Thread |
[Next in Thread] |
- [6367] prepare for XSParagraph,
Gavin D. Smith <=