/usr/share/perl5/LaTeXML/Gullet.pm is in latexml 0.7.0-1.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 | # /=====================================================================\ #
# | LaTeXML::Gullet | #
# | Analog of TeX's Gullet; deals with expansion and arg parsing | #
# |=====================================================================| #
# | Part of LaTeXML: | #
# | Public domain software, produced as part of work done by the | #
# | United States Government & not subject to copyright in the US. | #
# |---------------------------------------------------------------------| #
# | Bruce Miller <bruce.miller@nist.gov> #_# | #
# | http://dlmf.nist.gov/LaTeXML/ (o o) | #
# \=========================================================ooo==U==ooo=/ #
package LaTeXML::Gullet;
use strict;
use LaTeXML::Global;
use LaTeXML::Mouth;
use LaTeXML::Number;
use LaTeXML::Util::Pathname;
use base qw(LaTeXML::Object);
#**********************************************************************
sub new {
my($class)=@_;
bless {mouth=>undef, mouthstack=>[], pushback=>[], autoclose=>1, pending_comments=>[]
}, $class; }
#**********************************************************************
# Hmm, we should record in the output which files were included/required/etc.
# This is for the benefit of anything wanting to interpret the Math/TeX ???
# In which case, *.tex files that are included should probably be ignored
# (they're output will already be incorporated),
# But *.sty, *.cls etc, (or the *.pm equivalents) should be noted.
# However, if things are included via some other `package', presumably
# that package will be responsible for loading those extra pacakges, so
# they should be ignored too, right?
# HMM: the packageLoaded check only makes sense for style files, and
# is probably only important for latexml implementations?
sub input {
my($self,$name,$types,%options)=@_;
$name = $name->toString if ref $name;
# Try to find a Package implementing $name.
$name = $1 if $name =~ /^\{(.*)\}$/; # just in case
my $file = pathname_find($name,paths=>$STATE->lookupValue('SEARCHPATHS'),
types=>$types, installation_subdir=>'Package');
if(! $file) {
$STATE->noteStatus(missing=>$name);
Error(":missing_file:$name Cannot find file $name of type ".join(', ',@{$types||[]})
." in paths ".join(', ',@{$STATE->lookupValue('SEARCHPATHS')})); }
# elsif($file =~ /\.(ltxml|latexml)$/){ # Perl module.
elsif($file =~ /\.ltxml$/){ # Perl module.
return if $STATE->lookupValue($file.'_loaded');
$STATE->assignValue($file.'_loaded'=>1,'global');
$self->openMouth(LaTeXML::PerlMouth->new($file),0);
my $pmouth = $$self{mouth};
do $file;
Fatal(":perl:die Package $name had an error:\n $@") if $@;
$self->closeMouth if $pmouth eq $$self{mouth}; # Close immediately, unless recursive input
}
elsif($file =~ /\.(pool|sty|cls|clo|cnf)$/){ # (attempt to) interpret a style file.
return if $STATE->lookupValue($file.'_loaded');
if(! ($options{raw} || $STATE->lookupValue('INCLUDE_STYLES'))){
Warn(":unexpected:$file Ignoring style file $file");
return; }
$STATE->assignValue($file.'_loaded'=>1,'global');
$self->openMouth(LaTeXML::StyleMouth->new($file), 0); }
else { # Else read as an included file.
# If there is a file-specific declaration file (name.latexml), load it first!
my $name = $file;
$name =~ s/\.tex//;
local $LaTeXML::INHIBIT_LOAD=0;
if(my $conf = pathname_find("$name.latexml",
paths=>$STATE->lookupValue('SEARCHPATHS'))){
$self->openMouth(LaTeXML::PerlMouth->new($conf),0);
my $pmouth = $$self{mouth};
do $conf;
Fatal(":perl:die Configuration file $conf had an error:\n $@") if $@;
$self->closeMouth if $pmouth eq $$self{mouth}; # Close immediately, unless rec. input
}
# NOW load the input --- UNLESS INHIBITTED!!!
$self->openMouth(LaTeXML::FileMouth->new($file) ,0) unless $LaTeXML::INHIBIT_LOAD;
}}
#**********************************************************************
# Start reading tokens from a new Mouth.
# This pushes the mouth as the current source that $gullet->readToken (etc) will read from.
# Once this Mouth has been exhausted, readToken, etc, will return undef,
# until you call $gullet->closeMouth to clear the source.
# Exception: if $toplevel=1, readXToken will step to next source
# Note that a Tokens can act as a Mouth.
sub openMouth {
my($self,$mouth,$noautoclose)=@_;
return unless $mouth;
unshift(@{$$self{mouthstack}},[$$self{mouth},$$self{pushback},$$self{autoclose}]) if $$self{mouth};
$$self{mouth}=$mouth;
$$self{pushback}=[];
$$self{autoclose}=!$noautoclose; }
sub closeMouth {
my($self,$forced)=@_;
if(!$forced && (@{$$self{pushback}} || $$self{mouth}->hasMoreInput)){
my $next = Stringify($self->readToken);
Error(":unexpected:$next Closing mouth with input remaining: $next"); }
$$self{mouth}->finish;
if(@{$$self{mouthstack}}){
($$self{mouth},$$self{pushback},$$self{autoclose}) = @{ shift(@{$$self{mouthstack}}) }; }
else {
$$self{pushback}=[];
$$self{mouth}=Tokens();
$$self{autoclose}=1; }}
sub getMouth { $_[0]->{mouth}; }
# Obscure, but the only way I can think of to End!! (see \bye or \end{document})
# Flush all sources (close all pending mouth's)
sub flush {
my($self)=@_;
$$self{mouth}->finish;
foreach my $entry (@{$$self{mouthstack}}){
$entry->[0]->finish; }
$$self{pushback}=[];
$$self{mouth}=Tokens();
$$self{autoclose}=1;
$$self{mouthstack}=[]; }
# User feedback for where something (error?) occurred.
sub getLocator {
my($self,$long)=@_;
my $loc = (defined $$self{mouth} ? $$self{mouth}->getLocator($long) : '');
if(!$loc || $long){
$loc .= show_pushback($$self{pushback}) if $long;
foreach my $frame ( @{$$self{mouthstack}} ){
my $ml = $$frame[0]->getLocator($long);
$loc .= ' '.$ml if $ml;
last if $loc && !$long;
$loc .= show_pushback($$frame[1]) if $long; }}
$loc; }
sub getSource {
my($self)=@_;
defined $$self{mouth} && $$self{mouth}->getSource; }
sub show_pushback {
my($pb)=@_;
my @pb = @$pb;
@pb = (@pb[0..50],T_OTHER('...')) if scalar(@pb) > 55;
(@pb ? "\n To be read again ".ToString(Tokens(@pb)) : ''); }
#**********************************************************************
# Return $tokens with all tokens expanded
sub expandTokens {
my($self,$tokens)=@_;
$self->openMouth((ref $tokens eq 'LaTeXML::Token' ? Tokens($tokens) : $tokens->clone),1);
my @expanded=();
while(defined(my $t=$self->readXToken)){
push(@expanded,$t);}
$self->closeMouth;
Tokens(@expanded); }
# Not really 100% sure how this is supposed to work
# See TeX Ch 20, p216 regarding noexpand, \edef with token list registers, etc.
# Solution: Duplicate param tokens, stick NOTEXPANDED infront of expandable tokens.
sub neutralizeTokens {
my($self,@tokens)=@_;
my @result=();
foreach my $t (@tokens){
if($t->getCatcode == CC_PARAM){
push(@result,$t); }
elsif(defined(my $defn=$STATE->lookupDefinition($t))){
push(@result,Token('\noexpand',CC_NOTEXPANDED)); }
push(@result,$t); }
@result; }
#**********************************************************************
# Low-level readers: read token, read expanded token
#**********************************************************************
# Note that every char (token) comes through here (maybe even twice, through args parsing),
# So, be Fast & Clean! This method only reads from the current input stream (Mouth).
sub readToken {
my($self)=@_;
my $token = shift(@{$$self{pushback}});
return $token if defined $token;
while(defined($token = $$self{mouth}->readToken()) && ($$token[1] == CC_COMMENT)){ # NOTE: Inlined ->getCatcode
push(@{$$self{pending_comments}},$token); } # What to do with comments???
return $token; }
# Unread tokens are assumed to be not-yet expanded.
sub unread {
my($self,@tokens)=@_;
unshift(@{$$self{pushback}}, map($_->unlist,grep($_,@tokens))); }
# Read the next non-expandable token (expanding tokens until there's a non-expandable one).
# Note that most tokens pass through here, so be Fast & Clean! readToken is folded in.
# `Toplevel' processing, (if $toplevel is true), used at the toplevel processing by Stomach,
# will step to the next input stream (Mouth)
# if one is available, and will also pass comments.
sub readXToken {
my($self,$toplevel)=@_;
return shift(@{$$self{pending_comments}}) if $toplevel && @{$$self{pending_comments}};
my($token,$cc,$defn);
while(1){
if(!defined($token = (@{$$self{pushback}} ? shift(@{$$self{pushback}}) : $$self{mouth}->readToken() ))){
return undef unless $$self{autoclose} && $toplevel && @{$$self{mouthstack}};
$self->closeMouth; } # Next input stream.
elsif(($cc = $$token[1]) == CC_NOTEXPANDED){ # NOTE: Inlined ->getCatcode
# Should only occur IMMEDIATELY after expanding \noexpand (by readXToken),
# so this token should never leak out through an EXTERNAL call to readToken.
return $self->readToken; } # Just return the next token.
elsif($cc == CC_COMMENT){
return $token if $toplevel;
push(@{$$self{pending_comments}},$token); } # What to do with comments???
elsif(defined($defn=$STATE->lookupDefinition($token)) && $defn->isExpandable){
$self->unread($defn->invoke($self)); } # Expand and push back the result (if any) and continue
else {
return $token; } # just return it
}}
#**********************************************************************
# Mid-level readers: checking and matching tokens, strings etc.
#**********************************************************************
# The following higher-level parsing methods are built upon readToken & unread.
sub readNonSpace {
my($self)=@_;
my $tok;
do { $tok=$self->readToken();
} while(defined $tok && $tok->getCatcode == CC_SPACE);
$tok; }
sub skipSpaces {
my($self)=@_;
my $tok = $self->readNonSpace;;
$self->unread($tok) if defined $tok; }
sub skip1Space {
my($self)=@_;
my $tok=$self->readToken();
$self->unread($tok) if $tok && ($tok->getCatcode != CC_SPACE); }
# <filler> = <optional spaces> | <filler>\relax<optional spaces>
sub skipFiller {
my($self)=@_;
while(1){
my $tok = $self->readNonSpace;;
return unless defined $tok;
# Should \foo work too (where \let\foo\relax) ??
if($tok->getString ne '\relax'){ $self->unread($tok); return; }
}}
# Read a sequence of tokens balanced in {}
# assuming the { has already been read.
# Returns a Tokens list of the balanced sequence, omitting the closing }
sub readBalanced {
my($self)=@_;
my @tokens=();
my ($tok,$level)=(undef,1);
while($level && defined ($tok=$self->readToken())){
my $cc = $tok->getCatcode;
$level++ if $cc == CC_BEGIN;
$level-- if $cc == CC_END;
push(@tokens,$tok) if $level; }
Tokens(@tokens); }
sub ifNext {
my($self,$token)=@_;
if(my $tok=$self->readToken()){
$self->unread($tok);
$tok->equals($token); }
else { 0; }}
# Match the input against one of the Token or Tokens in @choices; return the matching one or undef.
sub readMatch {
my($self,@choices)=@_;
foreach my $choice (@choices){
my @tomatch=$choice->unlist;
my @matched=();
my $tok;
while(@tomatch && defined($tok=$self->readToken)
&& push(@matched,$tok) && ($tok->equals($tomatch[0]))){
shift(@tomatch);
if($tok->getCatcode == CC_SPACE){ # If this was space, SKIP any following!!!
while(defined($tok=$self->readToken) && ($tok->getCatcode == CC_SPACE)){
push(@matched,$tok); }
$self->unread($tok) if $tok; }
}
return $choice unless @tomatch; # All matched!!!
$self->unread(@matched); # Put 'em back and try next!
}
return undef; }
# Match the input against a set of keywords; Similar to readMatch, but the keywords are strings,
# and Case and catcodes are ignored; additionally, leading spaces are skipped.
sub readKeyword {
my($self,@keywords)=@_;
$self->skipSpaces;
foreach my $keyword (@keywords){
$keyword = $keyword->toString if ref $keyword;
my @tomatch=split('',uc($keyword));
my @matched=();
my $tok;
while(@tomatch && defined ($tok=$self->readToken) && push(@matched,$tok)
&& (uc($tok->getString) eq $tomatch[0])){
shift(@tomatch); }
return $keyword unless @tomatch; # All matched!!!
$self->unread(@matched); # Put 'em back and try next!
}
return undef; }
# Return a (balanced) sequence tokens until a match against one of the Tokens in @delims.
# In list context, also returns the found delimiter.
sub readUntil {
my($self,@delims)=@_;
my ($found,@toks)=();
while(!defined ($found=$self->readMatch(@delims))){
my $tok=$self->readToken(); # Copy next token to args
return undef unless defined $tok;
push(@toks,$tok);
if($tok->getCatcode == CC_BEGIN){ # And if it's a BEGIN, copy till balanced END
push(@toks,$self->readBalanced->unlist,T_END); }}
(wantarray ? (Tokens(@toks),$found) : Tokens(@toks)); }
#**********************************************************************
# Higher-level readers: Read various types of things from the input:
# tokens, non-expandable tokens, args, Numbers, ...
#**********************************************************************
sub readArg {
my($self)=@_;
my $tok = $self->readNonSpace;
if(!defined $tok){
undef; }
elsif($tok->getCatcode == CC_BEGIN){
$self->readBalanced; }
else {
Tokens($tok); }}
# Note that this returns an empty array if [] is present,
# otherwise $default or undef.
sub readOptional {
my($self,$default)=@_;
my $tok = $self->readNonSpace;
if(!defined $tok){ undef; }
elsif(($tok->equals(T_OTHER('[')))){
$self->readUntil(T_OTHER(']')); }
else {
$self->unread($tok);
$default; }}
#**********************************************************************
# Numbers, Dimensions, Glue
# See TeXBook, Ch.24, pp.269-271.
#**********************************************************************
sub readValue {
my($self,$type)=@_;
if ($type eq 'Number'){ $self->readNumber; }
elsif($type eq 'Dimension' ){ $self->readDimension; }
elsif($type eq 'Glue' ){ $self->readGlue; }
elsif($type eq 'MuGlue'){ $self->readMuGlue; }
elsif($type eq 'Tokens'){ $self->readTokensValue; }
elsif($type eq 'any' ){ $self->readArg; }
}
sub readRegisterValue {
my($self,$type)=@_;
my $token = $self->readXToken;
return unless defined $token;
my $defn = $STATE->lookupDefinition($token);
if((defined $defn) && ($defn->isRegister eq $type)){
$defn->valueOf($defn->readArguments($self)); }
else {
$self->unread($token); return; }}
# Apparent behaviour of a token value (ie \toks#=<arg>)
sub readTokensValue {
my($self)=@_;
my $token = $self->readNonSpace;
if(!defined $token){
undef; }
elsif($token->getCatcode == CC_BEGIN){
$self->readBalanced; }
elsif(my $defn = $STATE->lookupDefinition($token)){
if($defn->isRegister eq 'Tokens'){
$defn->valueOf($defn->readArguments($self)); }
elsif($defn->isExpandable){
Tokens($defn->invoke($self)); }
else {
$token; }} # ?
else {
$token; }}
#======================================================================
# some helpers...
# <optional signs> = <optional spaces> | <optional signs><plus or minus><optional spaces>
# return +1 or -1
sub readOptionalSigns {
my($self)=@_;
my ($sign,$t)=("+1",'');
while(defined($t=$self->readXToken)
&& (($t->getString eq '+') || ($t->getString eq '-') || ($t->equals(T_SPACE)))){
$sign = -$sign if ($t->getString eq '-'); }
$self->unread($t) if $t;
$sign; }
sub readDigits {
my($self,$range,$skip)=@_;
my $string='';
my($t,$d);
while(($t=$self->readXToken()) && (($d=$t->getString) =~ /^[$range]$/)){
$string .= $d; }
$self->unread($t) if $t && !($skip && $t->getCatcode == CC_SPACE);
$string; }
# <factor> = <normal integer> | <decimal constant>
# <decimal constant> = . | , | <digit><decimal constant> | <decimal constant><digit>
# Return a number (perl number)
sub readFactor {
my($self)=@_;
my $string = $self->readDigits('0-9');
my $token = $self->readXToken;
if($token && $token->getString =~ /^[\.\,]$/){
$string .= '.'.$self->readDigits('0-9');
$token = $self->readXToken; }
if(length($string)>0){
$self->unread($token) if $token && $token->getCatcode!=CC_SPACE;
$string; }
else {
$self->unread($token);
my $n = $self->readNormalInteger;
(defined $n ? $n->valueOf : undef); }}
#======================================================================
# Integer, Number
#======================================================================
# <number> = <optional signs><unsigned number>
# <unsigned number> = <normal integer> | <coerced integer>
# <coerced integer> = <internal dimen> | <internal glue>
sub readNumber {
my($self)=@_;
my $s = $self->readOptionalSigns;
if (defined (my $n = $self->readNormalInteger )){ ($s < 0 ? $n->negate : $n); }
elsif(defined ( $n = $self->readInternalDimension)){ Number($s * $n->valueOf); }
elsif(defined ( $n = $self->readInternalGlue )){ Number($s * $n->valueOf); }
else{ my $t = $self->readToken;
$self->unread($t);
Warn(":expected:<number> Missing number, treated as zero at ".ToString($t)); Number(0); }}
# <normal integer> = <internal integer> | <integer constant>
# | '<octal constant><one optional space> | "<hexadecimal constant><one optional space>
# | `<character token><one optional space>
# Return a Number or undef
sub readNormalInteger {
my($self)=@_;
my $t=$self->readXToken;
if(!defined $t){}
elsif(($t->getCatcode == CC_OTHER) && ($t->getString =~ /^[0-9]$/)){ # Read decimal literal
Number(int($t->getString . $self->readDigits('0-9',1))); }
elsif( $t->equals(T_OTHER("\'"))){ # Read Octal literal
Number(oct($self->readDigits('0-7',1))); }
elsif( $t->equals(T_OTHER("\""))){ # Read Hex literal
Number(hex($self->readDigits('0-9A-F',1))); }
elsif( $t->equals(T_OTHER("\`"))){ # Read Charcode
my $s = $self->readToken->getString;
$s =~ s/^\\//;
Number(ord($s)); } # Only a character token!!! NOT expanded!!!!
else {
$self->unread($t);
$self->readInternalInteger; }}
sub readInternalInteger{ $_[0]->readRegisterValue('Number'); }
#======================================================================
# Float, a floating point number.
# Similar to factor, but does NOT accept comma!
# This is NOT part of TeX, but is convenient.
sub readFloat {
my($self)=@_;
my $s = $self->readOptionalSigns;
my $string = $self->readDigits('0-9');
my $token = $self->readXToken;
if($token && $token->getString =~ /^[\.]$/){
$string .= '.'.$self->readDigits('0-9');
$token = $self->readXToken; }
my $n;
if(length($string)>0){
$self->unread($token) if $token && $token->getCatcode!=CC_SPACE;
$n = $string; }
else {
$self->unread($token) if $token;
$n = $self->readNormalInteger;
$n = $n->valueOf if defined $n; }
(defined $n ? Float($s*$n) : undef); }
#======================================================================
# Dimensions
#======================================================================
# <dimen> = <optional signs><unsigned dimen>
# <unsigned dimen> = <normal dimen> | <coerced dimen>
# <coerced dimen> = <internal glue>
sub readDimension {
my($self)=@_;
my $s = $self->readOptionalSigns;
if (defined (my $d = $self->readInternalDimension)){ ($s < 0 ? $d->negate : $d); }
elsif(defined ( $d = $self->readInternalGlue) ){ Dimension($s * $d->valueOf); }
elsif(defined ( $d = $self->readFactor) ){
my $unit = $self->readUnit;
if(!defined $unit){
Warn(":expected:<unit> Illegal unit of measure (pt inserted).");
$unit = 65536; }
Dimension($s * $d * $unit); }
else{ Warn(":expected:<number> Missing number, treated as zero."); Dimension(0); }}
# <unit of measure> = <optional spaces><internal unit>
# | <optional true><physical unit><one optional space>
# <internal unit> = em <one optional space> | ex <one optional space>
# | <internal integer> | <internal dimen> | <internal glue>
# <physical unit> = pt | pc | in | bp | cm | mm | dd | cc | sp
# Read a unit, returning the equivalent number of scaled points,
sub readUnit {
my($self)=@_;
if(defined(my $u=$self->readKeyword('ex','em'))){ $self->skip1Space; $STATE->convertUnit($u); }
elsif(defined($u=$self->readInternalInteger )){ $u->valueOf; } # These are coerced to number=>sp
elsif(defined($u=$self->readInternalDimension)){ $u->valueOf; }
elsif(defined($u=$self->readInternalGlue )){ $u->valueOf; }
else {
$self->readKeyword('true'); # But ignore, we're not bothering with mag...
$u = $self->readKeyword('pt','pc','in','bp','cm','mm','dd','cc','sp');
if($u){ $self->skip1Space; $STATE->convertUnit($u); }
else { undef; }}}
# Return a dimension value or undef
sub readInternalDimension { $_[0]->readRegisterValue('Dimension'); }
#======================================================================
# Mu Dimensions
#======================================================================
# <mudimen> = <optional signs><unsigned mudimem>
# <unsigned mudimen> = <normal mudimen> | <coerced mudimen>
# <normal mudimen> = <factor><mu unit>
# <mu unit> = <optional spaces><internal muglue> | mu <one optional space>
# <coerced mudimen> = <internal muglue>
sub readMuDimension {
my($self)=@_;
my $s = $self->readOptionalSigns;
if (defined (my $m = $self->readFactor )){
my $munit = $self->readMuUnit;
if(!defined $munit){
Warn(":expected:<unit> Illegal unit of measure (mu inserted).");
$munit = $STATE->convertUnit('mu'); }
MuDimension($s * $m * $munit); }
elsif(defined ( $m = $self->readInternalMuGlue)){ MuDimension($s * $m->valueOf); }
else{ Warn(":expected:<mudimen> Expecting mudimen; assuming 0 "); MuDimension(0); }}
sub readMuUnit {
my($self)=@_;
if (my $m=$self->readKeyword('mu')){ $self->skip1Space; $STATE->convertUnit($m); }
elsif($m=$self->readInternalMuGlue ){ $m->valueOf; }
else { undef; }}
#======================================================================
# Glue
#======================================================================
# <glue> = <optional signs><internal glue> | <dimen><stretch><shrink>
# <stretch> = plus <dimen> | plus <fil dimen> | <optional spaces>
# <shrink> = minus <dimen> | minus <fil dimen> | <optional spaces>
sub readGlue {
my($self)=@_;
my $s = $self->readOptionalSigns;
my $n;
if(defined ($n = $self->readInternalGlue)){
($s < 0 ? $n->negate : $n); }
else{
my $d = $self->readDimension;
if(!$d){
Warn(":expected:<number> Missing number, treated as zero."); return Glue(0); }
$d = $d->negate if $s < 0;
my($r1,$f1,$r2,$f2);
($r1,$f1) = $self->readRubber if $self->readKeyword('plus');
($r2,$f2) = $self->readRubber if $self->readKeyword('minus');
Glue($d->valueOf*$s,$r1,$f1,$r2,$f2); }}
our %FILLS = (fil=>1,fill=>2,filll=>3);
sub readRubber {
my($self,$mu)=@_;
my $s = $self->readOptionalSigns;
my $f = $self->readFactor;
if(!defined $f){
$f = ($mu ? $self->readMuDimension : $self->readDimension);
($f->valueOf * $s, 0); }
elsif(defined(my $fil = $self->readKeyword('filll','fill','fil'))){
($s*$f,$FILLS{$fil}); }
elsif($mu){
my $u = $self->readMuUnit;
if(!defined $u){
Warn(":expected:<unit> Illegal unit of measure (mu inserted).");
$u = $STATE->convertUnit('mu'); }
($s*$f*$u,0); }
else {
my $u = $self->readUnit;
if(!defined $u){
Warn(":expected:<unit> Illegal unit of measure (pt inserted).");
$u = 65536; }
($s*$f*$u,0); }}
# Return a glue value or undef.
sub readInternalGlue { $_[0]->readRegisterValue('Glue'); }
#======================================================================
# Mu Glue
#======================================================================
# <muglue> = <optional signs><internal muglue> | <mudimen><mustretch><mushrink>
# <mustretch> = plus <mudimen> | plus <fil dimen> | <optional spaces>
# <mushrink> = minus <mudimen> | minus <fil dimen> | <optional spaces>
sub readMuGlue {
my($self)=@_;
my $s = $self->readOptionalSigns;
my $n;
if(defined ($n = $self->readInternalMuGlue)){
($s < 0 ? $n->negate : $n); }
else{
my $d = $self->readMuDimension;
if(!$d){
Warn(":expected:<number> Missing number, treated as zero."); return MuGlue(0); }
$d = $d->negate if $s < 0;
my($r1,$f1,$r2,$f2);
($r1,$f1) = $self->readRubber(1) if $self->readKeyword('plus');
($r2,$f2) = $self->readRubber(1) if $self->readKeyword('minus');
MuGlue($d->valueOf*$s,$r1,$f1,$r2,$f2); }}
# Return a muglue value or undef.
sub readInternalMuGlue { $_[0]->readRegisterValue('MuGlue'); }
#======================================================================
# See pp 272-275 for lists of the various registers.
# These are implemented in Primitive.pm
#**********************************************************************
1;
__END__
=pod
=head1 NAME
C<LaTeXML::Gullet> - expands expandable tokens and parses common token sequences.
=head1 DESCRIPTION
A C<LaTeXML::Gullet> reads tokens (L<LaTeXML::Token>) from a L<LaTeXML::Mouth>.
It is responsible for expanding macros and expandable control sequences,
if the current definition associated with the token in the L<LaTeXML::State>
is an L<LaTeXML::Expandable> definition. The C<LaTeXML::Gullet> also provides a
variety of methods for reading various types of input such as arguments, optional arguments,
as well as for parsing L<LaTeXML::Number>, L<LaTeXML::Dimension>, etc, according
to TeX's rules.
=head2 Managing Input
=over 4
=item C<< $gullet->input($name,$types,%options); >>
Input the file named C<$name>; Searches for matching files in the
current C<searchpath> with an extension being one of C<$types> (an array
of strings). If the found file has a perl extension (pm, ltxml, or latexml),
it will be executed (loaded). If the found file has a TeX extension
(tex, sty, cls) it will be opened and latexml will prepare to read
from it.
=item C<< $gullet->openMouth($mouth, $noautoclose); >>
Is this public? Prepares to read tokens from C<$mouth>.
If $noautoclose is true, the Mouth will not be automatically closed
when it is exhausted.
=item C<< $gullet->closeMouth; >>
Is this public? Finishes reading from the current mouth, and
reverts to the one in effect before the last openMouth.
=item C<< $gullet->flush; >>
Is this public? Clears all inputs.
=item C<< $gullet->getLocator; >>
Returns a string describing the current location in the input stream.
=back
=head2 Low-level methods
=over 4
=item C<< $tokens = $gullet->expandTokens($tokens); >>
Return the L<LaTeXML::Tokens> resulting from expanding all the tokens in C<$tokens>.
This is actually only used in a few circumstances where the arguments to
an expandable need explicit expansion; usually expansion happens at the right time.
=item C<< @tokens = $gullet->neutralizeTokens(@tokens); >>
Another unusual method: Used for things like \edef and token registers, to
inhibit further expansion of control sequences and proper spawning of register tokens.
=item C<< $token = $gullet->readToken; >>
Return the next token from the input source, or undef if there is no more input.
=item C<< $token = $gullet->readXToken($toplevel); >>
Return the next unexpandable token from the input source, or undef if there is no more input.
If the next token is expandable, it is expanded, and its expansion is reinserted into the input.
=item C<< $gullet->unread(@tokens); >>
Push the C<@tokens> back into the input stream to be re-read.
=back
=head2 Mid-level methods
=over 4
=item C<< $token = $gullet->readNonSpace; >>
Read and return the next non-space token from the input after discarding any spaces.
=item C<< $gullet->skipSpaces; >>
Skip the next spaces from the input.
=item C<< $gullet->skip1Space; >>
Skip the next token from the input if it is a space.
=item C<< $tokens = $gullet->readBalanced; >>
Read a sequence of tokens from the input until the balancing '}' (assuming the '{' has
already been read). Returns a L<LaTeXML::Tokens>.
=item C<< $boole = $gullet->ifNext($token); >>
Returns true if the next token in the input matches C<$token>;
the possibly matching token remains in the input.
=item C<< $tokens = $gullet->readMatch(@choices); >>
Read and return whichever of C<@choices> (each are L<LaTeXML::Tokens>)
matches the input, or undef if none do.
=item C<< $keyword = $gullet->readKeyword(@keywords); >>
Read and return whichever of C<@keywords> (each a string) matches the input, or undef
if none do. This is similar to readMatch, but case and catcodes are ignored.
Also, leading spaces are skipped.
=item C<< $tokens = $gullet->readUntil(@delims); >>
Read and return a (balanced) sequence of L<LaTeXML::Tokens> until matching one of the tokens
in C<@delims>. In a list context, it also returns which of the delimiters ended the sequence.
=back
=head2 High-level methods
=over 4
=item C<< $tokens = $gullet->readArg; >>
Read and return a TeX argument; the next Token or Tokens (if surrounded by braces).
=item C<< $tokens = $gullet->readOptional($default); >>
Read and return a LaTeX optional argument; returns C<$default> if there is no '[',
otherwise the contents of the [].
=item C<< $thing = $gullet->readValue($type); >>
Reads an argument of a given type: one of 'Number', 'Dimension', 'Glue', 'MuGlue' or 'any'.
=item C<< $value = $gullet->readRegisterValue($type); >>
Read a control sequence token (and possibly it's arguments) that names a register,
and return the value. Returns undef if the next token isn't such a register.
=item C<< $number = $gullet->readNumber; >>
Read a L<LaTeXML::Number> according to TeX's rules of the various things that
can be used as a numerical value.
=item C<< $dimension = $gullet->readDimension; >>
Read a L<LaTeXML::Dimension> according to TeX's rules of the various things that
can be used as a dimension value.
=item C<< $mudimension = $gullet->readMuDimension; >>
Read a L<LaTeXML::MuDimension> according to TeX's rules of the various things that
can be used as a mudimension value.
=item C<< $glue = $gullet->readGlue; >>
Read a L<LaTeXML::Glue> according to TeX's rules of the various things that
can be used as a glue value.
=item C<< $muglue = $gullet->readMuGlue; >>
Read a L<LaTeXML::MuGlue> according to TeX's rules of the various things that
can be used as a muglue value.
=back
=head1 AUTHOR
Bruce Miller <bruce.miller@nist.gov>
=head1 COPYRIGHT
Public domain software, produced as part of work done by the
United States Government & not subject to copyright in the US.
=cut
|