/usr/share/perl5/Locale/Po4a/Text.pm is in po4a 0.41-1ubuntu1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 | #!/usr/bin/perl -w
# Po4a::Text.pm
#
# extract and translate translatable strings from a text documents
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
#
########################################################################
=encoding UTF-8
=head1 NAME
Locale::Po4a::Text - convert text documents from/to PO files
=head1 DESCRIPTION
The po4a (PO for anything) project goal is to ease translations (and more
interestingly, the maintenance of translations) using gettext tools on
areas where they were not expected like documentation.
Locale::Po4a::Text is a module to help the translation of text documents into
other [human] languages.
Paragraphs are split on empty lines (or lines containing only spaces or
tabulations).
If a paragraph contains a line starting by a space (or tabulation), this
paragraph won't be rewrapped.
=cut
package Locale::Po4a::Text;
use 5.006;
use strict;
use warnings;
require Exporter;
use vars qw(@ISA @EXPORT);
@ISA = qw(Locale::Po4a::TransTractor);
@EXPORT = qw();
use Locale::Po4a::TransTractor;
use Locale::Po4a::Common;
=head1 OPTIONS ACCEPTED BY THIS MODULE
These are this module's particular options:
=over
=item B<nobullets>
Deactivate detection of bullets.
By default, when a bullet is detected, the bullet paragraph is not considered
as a verbatim paragraph (with the no-wrap flag in the PO file), but the module
rewrap this paragraph in the generated PO file and in the translation.
=cut
my $bullets = 1;
=item B<tabs=>I<mode>
Specify how tabulations shall be handled. The I<mode> can be any of:
=over
=item B<split>
Lines with tabulations introduce breaks in the current paragraph.
=item B<verbatim>
Paragraph containing tabulations will not be re-wrapped.
=back
By default, tabulations are considered as spaces.
=cut
my $tabs = "";
=item B<breaks=>I<regex>
A regular expression matching lines which introduce breaks.
The regular expression will be anchored so that the whole line must match.
=cut
my $breaks;
=item B<debianchangelog>
Handle the header and footer of
released versions, which only contain non translatable informations.
=cut
my $debianchangelog = 0;
=item B<fortunes>
Handle the fortunes format, which separate fortunes with a line which
consists in '%' or '%%', and use '%%' as the beginning of a comment.
=cut
my $fortunes = 0;
=item B<markdown>
Handle some special markup in Markdown-formatted texts.
=cut
my $markdown = 0;
=item B<asciidoc>
Handle documents in the AsciiDoc format.
=cut
my $asciidoc = 0;
=back
=cut
sub initialize {
my $self = shift;
my %options = @_;
$self->{options}{'asciidoc'} = 1;
$self->{options}{'breaks'} = 1;
$self->{options}{'debianchangelog'} = 1;
$self->{options}{'debug'} = 1;
$self->{options}{'fortunes'} = 1;
$self->{options}{'markdown'} = 1;
$self->{options}{'nobullets'} = 1;
$self->{options}{'tabs'} = 1;
$self->{options}{'verbose'} = 1;
foreach my $opt (keys %options) {
die wrap_mod("po4a::text",
dgettext("po4a", "Unknown option: %s"), $opt)
unless exists $self->{options}{$opt};
$self->{options}{$opt} = $options{$opt};
}
if (defined $options{'nobullets'}) {
$bullets = 0;
}
if (defined $options{'tabs'}) {
$tabs = $options{'tabs'};
}
if (defined $options{'breaks'}) {
$breaks = $options{'breaks'};
}
if (defined $options{'debianchangelog'}) {
$debianchangelog=1;
}
if (defined $options{'fortunes'}) {
$fortunes=1;
}
if (defined $options{'markdown'}) {
$markdown=1;
}
$asciidoc=1 if (defined $options{'asciidoc'});
}
sub parse {
my $self = shift;
my ($line,$ref);
my $paragraph="";
my $wrapped_mode = 1;
my $expect_header = 1;
my $end_of_paragraph = 0;
($line,$ref)=$self->shiftline();
my $file = $ref;
$file =~ s/:[0-9]+$// if defined($line);
while (defined($line)) {
$ref =~ m/^(.*):[0-9]+$/;
if ($1 ne $file) {
$file = $1;
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$wrapped_mode = 1;
$expect_header = 1;
}
chomp($line);
$self->{ref}="$ref";
if ($debianchangelog and
$expect_header and
$line =~ /^(\w[-+0-9a-z.]*)\ \(([^\(\) \t]+)\) # src, version
\s+([-+0-9a-z.]+); # distribution
\s*urgency\s*\=\s*(.*\S)\s*$/ix) { #
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$self->pushline("$line\n");
$expect_header=0;
} elsif ($debianchangelog and
$line =~ m/^ \-\- (.*) <(.*)> ((\w+\,\s*)?\d{1,2}\s+\w+\s+\d{4}\s+\d{1,2}:\d\d:\d\d\s+[-+]\d{4}(\s+\([^\\\(\)]\))?)$/) {
# Found trailer
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$self->pushline("$line\n");
$expect_header=1;
} elsif ($fortunes and
$line =~ m/^%%?\s*$/) {
# Found end of fortune
do_paragraph($self,$paragraph,$wrapped_mode);
$self->pushline("\n") unless ( $wrapped_mode == 0
or $paragraph eq "");
$paragraph="";
$wrapped_mode = 1;
$self->pushline("$line\n");
} elsif ( (defined $self->{verbatim})
and ($self->{verbatim} == 2)) {
# Untranslated blocks
$self->pushline($line."\n");
if ($asciidoc and
($line =~ m/^(\/{4,}|~{4,})$/)) {
undef $self->{verbatim};
undef $self->{type};
$wrapped_mode = 1;
}
} elsif ( ($line =~ /^\s*$/)
or ( defined $breaks
and $line =~ m/^$breaks$/)) {
# Break paragraphs on lines containing only spaces
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$wrapped_mode = 1 unless defined($self->{verbatim});
$self->pushline($line."\n");
} elsif ($asciidoc and (not defined($self->{verbatim})) and
($line =~ m/^(\+|--)$/)) {
# List Item Continuation or List Block
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$self->pushline($line."\n");
} elsif ($asciidoc and (not defined($self->{verbatim})) and
($line =~ m/^(={4,}|-{4,}|~{4,}|\^{4,}|\+{4,})$/) and
(defined($paragraph) )and
($paragraph =~ m/^[^\n]*\n$/s) and
(length($paragraph) == (length($line)+1))) {
# Found title
$wrapped_mode = 0;
my $level = $line;
$level =~ s/^(.).*$/$1/;
$paragraph =~ s/\n$//s;
my $t = $self->translate($paragraph,
$self->{ref},
"Title $level",
"wrap" => 0);
$self->pushline($t."\n");
$paragraph="";
$wrapped_mode = 1;
$self->pushline(($level x (length($t)))."\n");
} elsif ($asciidoc and
($line =~ m/^(={1,5})( +)(.*?)( +\1)?$/)) {
my $titlelevel1 = $1;
my $titlespaces = $2;
my $title = $3;
my $titlelevel2 = $4||"";
# Found one line title
do_paragraph($self,$paragraph,$wrapped_mode);
$wrapped_mode = 0;
$paragraph="";
my $t = $self->translate($title,
$self->{ref},
"Title $titlelevel1",
"wrap" => 0);
$self->pushline($titlelevel1.$titlespaces.$t.$titlelevel2."\n");
$wrapped_mode = 1;
} elsif ($asciidoc and
($line =~ m/^(\/{4,}|\+{4,}|-{4,}|\.{4,}|\*{4,}|_{4,}|={4,}|~{4,})$/)) {
# Found one delimited block
my $t = $line;
$t =~ s/^(.).*$/$1/;
my $type = "delimited block $t";
if (defined $self->{verbatim} and ($self->{type} ne $type)) {
$paragraph .= "$line\n";
} else {
do_paragraph($self,$paragraph,$wrapped_mode);
if ( (defined $self->{type})
and ($self->{type} eq $type)) {
undef $self->{type};
undef $self->{verbatim};
$wrapped_mode = 1;
} else {
if ($t eq "\/") {
# CommentBlock, should not be treated
$self->{verbatim} = 2;
} elsif ($t eq "+") {
# PassthroughBlock
$wrapped_mode = 0;
$self->{verbatim} = 1;
} elsif ($t eq "-") {
# ListingBlock
$wrapped_mode = 0;
$self->{verbatim} = 1;
} elsif ($t eq ".") {
# LiteralBlock
$wrapped_mode = 0;
$self->{verbatim} = 1;
} elsif ($t eq "*") {
# SidebarBlock
$wrapped_mode = 1;
} elsif ($t eq "_") {
# QuoteBlock
if ( (defined $self->{type})
and ($self->{type} eq "verse")) {
$wrapped_mode = 0;
$self->{verbatim} = 1;
} else {
$wrapped_mode = 1;
}
} elsif ($t eq "=") {
# ExampleBlock
$wrapped_mode = 1;
} elsif ($t eq "~") {
# Filter blocks, TBC: not translated
$wrapped_mode = 0;
$self->{verbatim} = 2;
}
$self->{type} = $type;
}
$paragraph="";
$self->pushline($line."\n");
}
} elsif ($asciidoc and not defined $self->{verbatim} and
($line =~ m/^\[\[([^\]]*)\]\]$/)) {
# Found BlockId
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$wrapped_mode = 1;
$self->pushline($line."\n");
undef $self->{bullet};
undef $self->{indent};
} elsif ($asciidoc and not defined $self->{verbatim} and
($paragraph eq "") and
($line =~ m/^((?:NOTE|TIP|IMPORTANT|WARNING|CAUTION):\s+)(.*)$/)) {
my $type = $1;
my $text = $2;
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph=$text."\n";
$wrapped_mode = 1;
$self->pushline($type);
undef $self->{bullet};
undef $self->{indent};
} elsif ($asciidoc and not defined $self->{verbatim} and
($line =~ m/^\[(NOTE|TIP|IMPORTANT|WARNING|CAUTION|verse|quote)\]$/)) {
my $type = $1;
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$wrapped_mode = 1;
$self->pushline($line."\n");
if ($type eq "verse") {
$wrapped_mode = 0;
}
undef $self->{bullet};
undef $self->{indent};
} elsif ($asciidoc and not defined $self->{verbatim} and
($line =~ m/^\[(verse|quote), +(.*)\]$/)) {
my $type = $1;
my $arg = $2;
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
my $t = $self->translate($arg,
$self->{ref},
"$type",
"wrap" => 0);
$self->pushline("[$type, $t]\n");
$wrapped_mode = 1;
if ($type eq "verse") {
$wrapped_mode = 0;
}
$self->{type} = $type;
undef $self->{bullet};
undef $self->{indent};
} elsif ($asciidoc and not defined $self->{verbatim} and
($line =~ m/^\[icon="(.*)"\]$/)) {
my $arg = $1;
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
my $t = $self->translate($arg,
$self->{ref},
"icon",
"wrap" => 0);
$self->pushline("[icon=\"$t\"]\n");
$wrapped_mode = 1;
undef $self->{bullet};
undef $self->{indent};
} elsif ($asciidoc and not defined $self->{verbatim} and
($line =~ m/^\[icons=None, +caption="(.*)"\]$/)) {
my $arg = $1;
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
my $t = $self->translate($arg,
$self->{ref},
"caption",
"wrap" => 0);
$self->pushline("[icons=None, caption=\"$t\"]\n");
$wrapped_mode = 1;
undef $self->{bullet};
undef $self->{indent};
} elsif ($asciidoc and not defined $self->{verbatim} and
($line =~ m/^(\s*)([*_+`'#[:alnum:]].*)((?:::|;;|\?\?|:-)(?: *\\)?)$/)) {
my $indent = $1;
my $label = $2;
my $labelend = $3;
# Found labeled list
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$wrapped_mode = 1;
$self->{bullet} = "";
$self->{indent} = $indent;
my $t = $self->translate($label,
$self->{ref},
"Labeled list",
"wrap" => 0);
$self->pushline("$indent$t$labelend\n");
} elsif ($asciidoc and not defined $self->{verbatim} and
($line =~ m/^(\s*)(\S.*)((?:::|;;)\s+)(.*)$/)) {
my $indent = $1;
my $label = $2;
my $labelend = $3;
my $labeltext = $4;
# Found Horizontal Labeled Lists
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph=$labeltext."\n";
$wrapped_mode = 1;
$self->{bullet} = "";
$self->{indent} = $indent;
my $t = $self->translate($label,
$self->{ref},
"Labeled list",
"wrap" => 0);
$self->pushline("$indent$t$labelend");
} elsif ($asciidoc and not defined $self->{verbatim} and
($line =~ m/^\:(\S.*?)(:\s*)(.*)$/)) {
my $attrname = $1;
my $attrsep = $2;
my $attrvalue = $3;
# Found a Attribute entry
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$wrapped_mode = 1;
undef $self->{bullet};
undef $self->{indent};
my $t = $self->translate($attrvalue,
$self->{ref},
"Attribute :$attrname:",
"wrap" => 0);
$self->pushline(":$attrname$attrsep$t\n");
} elsif ($asciidoc and not defined $self->{verbatim} and
($line !~ m/^\.\./) and ($line =~ m/^\.(\S.*)$/)) {
my $title = $1;
# Found block title
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$wrapped_mode = 1;
undef $self->{bullet};
undef $self->{indent};
my $t = $self->translate($title,
$self->{ref},
"Block title",
"wrap" => 0);
$self->pushline(".$t\n");
} elsif ($asciidoc and not defined $self->{verbatim} and
($line =~ m/^(\s*)((?:[-*o+]|(?:[0-9]+[.\)])|(?:[a-z][.\)])|\([0-9]+\)|\.|\.\.)\s+)(.*)$/)) {
my $indent = $1||"";
my $bullet = $2;
my $text = $3;
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph = $text."\n";
$self->{indent} = $indent;
$self->{bullet} = $bullet;
} elsif ($asciidoc and not defined $self->{verbatim} and
($line =~ m/^((?:<?[0-9]+)?> +)(.*)$/)) {
my $bullet = $1;
my $text = $2;
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph = $text."\n";
$self->{indent} = "";
$self->{bullet} = $bullet;
} elsif ($asciidoc and not defined $self->{verbatim} and
(defined $self->{bullet} and $line =~ m/^(\s+)(.*)$/)) {
my $indent = $1;
my $text = $2;
if (not defined $self->{indent}) {
$paragraph .= $text."\n";
$self->{indent} = $indent;
} elsif (length($paragraph) and (length($self->{bullet}) + length($self->{indent}) == length($indent))) {
$paragraph .= $text."\n";
} else {
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph = $text."\n";
$self->{indent} = $indent;
$self->{bullet} = "";
}
} elsif ($markdown and
(not defined($self->{verbatim})) and
($line =~ m/^(={4,}|-{4,})$/) and
(defined($paragraph) )and
($paragraph =~ m/^[^\n]*\n$/s) and
(length($paragraph) == (length($line)+1))) {
# XXX: There can be any number of underlining according
# to the documentation. This detection, which avoid
# translating the formatting, is only supported if
# the underlining has the same size as the header text.
# Found title
$wrapped_mode = 0;
my $level = $line;
$level =~ s/^(.).*$/$1/;
my $t = $self->translate($paragraph,
$self->{ref},
"Title $level",
"wrap" => 0);
$self->pushline($t);
$paragraph="";
$wrapped_mode = 1;
$self->pushline(($level x (length($t)-1))."\n");
} elsif ($markdown and
($line =~ m/^(#{1,6})( +)(.*?)( +\1)?$/)) {
my $titlelevel1 = $1;
my $titlespaces = $2;
my $title = $3;
my $titlelevel2 = $4||"";
# Found one line title
do_paragraph($self,$paragraph,$wrapped_mode);
$wrapped_mode = 0;
$paragraph="";
my $t = $self->translate($title,
$self->{ref},
"Title $titlelevel1",
"wrap" => 0);
$self->pushline($titlelevel1.$titlespaces.$t.$titlelevel2."\n");
$wrapped_mode = 1;
} elsif ($markdown and
($paragraph eq "") and
($line =~ /^((\*\s*){3,}|(-\s*){3,}|(_\s*){3,})$/)) {
# Horizontal rule
$wrapped_mode = 1;
$self->pushline($line."\n");
} elsif ($line =~ /^-- $/) {
# Break paragraphs on email signature hint
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$wrapped_mode = 1;
$self->pushline($line."\n");
} elsif ( $line =~ /^=+$/
or $line =~ /^_+$/
or $line =~ /^-+$/) {
$wrapped_mode = 0;
$paragraph .= $line."\n";
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$wrapped_mode = 1;
} elsif ($markdown and
( $line =~ /^\s*\[\[\!\S+\s*$/ # macro begin
or $line =~ /^\s*"""\s*\]\]\s*$/)) { # """ textblock inside macro end
# Avoid translating Markdown lines containing only markup
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$wrapped_mode = 1;
$self->pushline("$line\n");
} elsif ($markdown and
( $line =~ /^#/ # headline
or $line =~ /^\s*\[\[\!\S[^\]]*\]\]\s*$/)) { # sole macro
# Preserve some Markdown markup as a single line
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="$line\n";
$wrapped_mode = 0;
$end_of_paragraph = 1;
} elsif ($markdown and
( $line =~ /^"""/)) { # """ textblock inside macro end
# Markdown markup needing separation _before_ this line
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="$line\n";
$wrapped_mode = 1;
} elsif ($tabs eq "split" and $line =~ m/\t/ and $paragraph !~ m/\t/s) {
$wrapped_mode = 0;
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph = "$line\n";
$wrapped_mode = 0;
} elsif ($tabs eq "split" and $line !~ m/\t/ and $paragraph =~ m/\t/s) {
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph = "$line\n";
$wrapped_mode = 1;
} else {
if ($line =~ /^\s/) {
# A line starting by a space indicates a non-wrap
# paragraph
$wrapped_mode = 0;
}
if ($markdown and
( $line =~ /\S $/ # explicit newline
or $line =~ /"""$/)) { # """ textblock inside macro begin
# Markdown markup needing separation _after_ this line
$end_of_paragraph = 1;
} else {
undef $self->{bullet};
undef $self->{indent};
}
if ($fortunes) {
$line =~ s/%%(.*)$//;
}
# TODO: comments
$paragraph .= $line."\n";
}
# paragraphs starting by a bullet, or numbered
# or paragraphs with a line containing many consecutive spaces
# (more than 3)
# are considered as verbatim paragraphs
$wrapped_mode = 0 if ( $paragraph =~ m/^(\*|[0-9]+[.)] )/s
or $paragraph =~ m/[ \t][ \t][ \t]/s);
$wrapped_mode = 0 if ( $tabs eq "verbatim"
and $paragraph =~ m/\t/s);
if ($markdown) {
# Some Markdown markup can (or might) not survive wrapping
$wrapped_mode = 0 if (
$paragraph =~ /^>/ms # blockquote
or $paragraph =~ /^( {8}|\t)/ms # monospaced
or $paragraph =~ /^\$(\S+[{}]\S*\s*)+/ms # Xapian macro
or $paragraph =~ /<(?![a-z]+[:@])/ms # maybe html (tags but not wiki <URI>)
or $paragraph =~ /^[^<]+>/ms # maybe html (tag with vertical space)
or $paragraph =~ /\S $/ms # explicit newline
or $paragraph =~ /\[\[\!\S[^\]]+$/ms # macro begin
);
}
if ($end_of_paragraph) {
do_paragraph($self,$paragraph,$wrapped_mode);
$paragraph="";
$wrapped_mode = 1;
$end_of_paragraph = 0;
}
($line,$ref)=$self->shiftline();
}
if (length $paragraph) {
do_paragraph($self,$paragraph,$wrapped_mode);
}
}
sub do_paragraph {
my ($self, $paragraph, $wrap) = (shift, shift, shift);
my $type = shift || $self->{type} || "Plain text";
return if ($paragraph eq "");
# DEBUG
# my $b;
# if (defined $self->{bullet}) {
# $b = $self->{bullet};
# } else {
# $b = "UNDEF";
# }
# $type .= " verbatim: '".($self->{verbatim}||"NONE")."' bullet: '$b' indent: '".($self->{indent}||"NONE")."' type: '".($self->{type}||"NONE")."'";
if ($bullets and not $wrap and not defined $self->{verbatim}) {
# Detect bullets
# | * blah blah
# |<spaces> blah
# | ^-- aligned
# <empty line>
#
# Other bullets supported:
# - blah o blah + blah
# 1. blah 1) blah (1) blah
TEST_BULLET:
if ($paragraph =~ m/^(\s*)((?:[-*o+]|([0-9]+[.\)])|\([0-9]+\))\s+)([^\n]*\n)(.*)$/s) {
my $para = $5;
my $bullet = $2;
my $indent1 = $1;
my $indent2 = "$1".(' ' x length $bullet);
my $text = $4;
while ($para !~ m/$indent2(?:[-*o+]|([0-9]+[.\)])|\([0-9]+\))\s+/
and $para =~ s/^$indent2(\S[^\n]*\n)//s) {
$text .= $1;
}
# TODO: detect if a line starts with the same bullet
if ($text !~ m/\S[ \t][ \t][ \t]+\S/s) {
my $bullet_regex = quotemeta($indent1.$bullet);
$bullet_regex =~ s/[0-9]+/\\d\+/;
if ($para eq '' or $para =~ m/^$bullet_regex\S/s) {
my $trans = $self->translate($text,
$self->{ref},
"Bullet: '$indent1$bullet'",
"wrap" => 1,
"wrapcol" => - (length $indent2));
$trans =~ s/^/$indent1$bullet/s;
$trans =~ s/\n(.)/\n$indent2$1/sg;
$self->pushline( $trans."\n" );
if ($para eq '') {
return;
} else {
# Another bullet
$paragraph = $para;
goto TEST_BULLET;
}
}
}
}
}
my $end = "";
if ($wrap) {
$paragraph =~ s/^(.*?)(\n*)$/$1/s;
$end = $2 || "";
}
my $t = $self->translate($paragraph,
$self->{ref},
$type,
"wrap" => $wrap);
if (defined $self->{bullet}) {
my $bullet = $self->{bullet};
my $indent1 = $self->{indent};
my $indent2 = $indent1.(' ' x length($bullet));
$t =~ s/^/$indent1$bullet/s;
$t =~ s/\n(.)/\n$indent2$1/sg;
}
$self->pushline( $t.$end );
}
1;
=head1 STATUS OF THIS MODULE
Tested successfully on simple text files and NEWS.Debian files.
=head1 AUTHORS
Nicolas François <nicolas.francois@centraliens.net>
=head1 COPYRIGHT AND LICENSE
Copyright 2005-2008 by Nicolas FRANÇOIS <nicolas.francois@centraliens.net>.
This program is free software; you may redistribute it and/or modify it
under the terms of GPL (see the COPYING file).
|