This file is indexed.

/usr/share/perl5/SWISS/TextFunc.pm is in libswiss-perl 1.67-1.

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
package SWISS::TextFunc;

use vars qw(
  $AUTOLOAD @ISA @EXPORT_OK
  @lineObjects
  @linePattern %linePattern
  $evidencePattern $evidencePatternReversed
  $textWrapPattern1 $textWrapPattern2
  $lineLength $lineLengthStar $lineLengthSQ
  );
use Exporter;
use Carp;
use strict;

BEGIN{
  @EXPORT_OK = qw(wrap);
  @ISA = ( 'Exporter' );

  @lineObjects = ('IDs', 'ACs', 'DTs', 'DEs', 'GNs', 
		  'OSs', 'OGs', 'OCs', 'OXs', 'OHs',
		  'Refs', 'CCs', 'DRs', 'PE', 'KWs', 'FTs', 'Stars', 'SQs');

  @linePattern = ('^( ?ID   .*\n)+(\*\*   .*\n)*',
		  '^( ?AC   .*\n)+(\*\*   .*\n)*',
		  '^( ?DT   .*\n){3}', 
		  '^( ?DE   .*\n)+', 
		  '^( ?GN   .*\n)+', 
		  '^( ?OS   .*\n)+', 
		  '^( ?OG   .*\n)+', 
		  '^( ?OC   .*\n)+', 
		  '^( ?OX   .*\n)+', 
		  '^( ?OH   .*\n)+', 
		  # Complex expression for Reference blocks
		  '^( ?R.   .*\n)+(( ?R.   .*\n)|( ?\*\*   .*\n))*( ?R.   .*\n)+',
		  '^( ?CC   .*\n)+',
		  # The block of DR lines may contain ** lines, except at the beginning, e.g.
		  # **   PRINTS; PR01217; PRICHEXTENSN; FALSE_POS_1.
		  '^( ?DR   .*\n)+( ?DR   .*\n| ?\*\*   \w+;.+\n)*',
		  '^( ?PE   .*\n)+', 
		  '^( ?KW   .*\n)+', 
		  '^( ?FT   .*\n)+', 
		  # Take a complex extended expression to take the
		  # LAST ** line group as the annotator's section
		  # NB: the 'Stars' comment is used to identify the hash key as 'St' in Stars.pm
		  '^(?#Stars)((\*\*\s*\n)|(\*\*   \#.*\n))+(\*\*.*\n)*(?=((SQ   .*\n)(     .*\n)+)?(\/\/\n))',
		  # The sequence contains two line types and is at the end.
		  '^(SQ   .*\n)(     .*\n)+(?=\/\/\n)'
		  );
  my ($line, $lineId);
  foreach $line (@linePattern) {
    ($lineId) = $line =~ /(\w\S)/;
    $linePattern{$lineId} = $line;
  }
 
  # The general pattern for evidence tags
  # Sets $1 to the evidence tag
  $evidencePattern = '\{(E[ACIP]\d+\,?)*\}';
  # and its reversed form for the parsing of the DE lines
  $evidencePatternReversed = '\}(\,?\d+[ACIP]E)*\{';
  
  # General pattern and last-resort pattern
  # for wrapping text fields.
  # Cut either at a whitespace that is not part of an EC or TC
  # number, e.g. "(EC 1.1.1.1)"; or at a dash that is followed
  # either by a letter/digit or an opening round or square bracket
  # (so as not to cut at "->" or "--" or "-," etc).
  # Also do not cut at a dash that is preceeded by a space,
  # because this dash might indicate a suffix.
  $textWrapPattern1 = '(?<!\([ET]C)\s+|(?<! )-(?=[A-Za-z0-9\(\[])';
  # as a last resort cut at a dash that is not part of an arrow
  # or double-dash.
  $textWrapPattern2 = '-(?![>\-])';

  $lineLength = 75;
  $lineLengthStar = 80;
  $lineLengthSQ = 60;
}

sub listFromText {
    my $class = shift;
    my $text = shift;
    my $sep = shift;
    my $end = shift || $sep;

    chomp $text;          # remove \n from end of text
    $text =~ s/^$sep//;   # remove separator at the beginning of the text
    $text =~ s/$end$//;   # remove separator at the end of the text

    return split /$sep/, $text;
}

sub textFromList {
    my $class = shift;
    my $list = shift;
    my $sep = shift;
    my $end = shift;
    my $width = shift;
    my $text;

    # produce one funck off long string
    $text = (join $sep, @{$list}) . $end;    
    # work out how many characters can be per line
    $width -= length $sep;                   

    while($text =~ m/(.{1,$width}(($sep)|($)))/g) {
	push @_, $1;
    }

    return @_;
}

sub wrapText {
    my $class = shift;
    my $text = shift;
    my $width = shift;

    $text = '' unless $text;
    while($text =~ m/(.{1,$width})(\s+|$)/g) {
	push @_, $1;
    }

    return @_;
}

sub wrapOn {
  my ($class, $prefix1, $prefix2, $columns, $text, @separators) = @_;
  my ($newText, $prefix, $width, $trailingBlanks);
  my ($lineText, $sepText, $match, $postMatch);

  $newText = '';
  # @separators might be empty
  # as a last resort, wrap anywhere
  push @separators, $textWrapPattern1, $textWrapPattern2, '';

  # use multiple separators for some FT lines
  my ($separator1, $border, $separator2, $longWordChar);
  if (ref $separators[0] eq "ARRAY") {
    ($separator1, $border, $separator2, $longWordChar) = @{$separators[0]};
    $separators[0] = $separator1;
  }


  $prefix=$prefix1;
 TEXT:while ($text) {

    # use multiple separators for some FT lines
    $width = $columns - length ($prefix);
    if (defined($separator1) and $separators[0] eq $separator1) {      
      if (($newText =~ /$border/)
	  ||
	  (substr($text, 0, $width) =~ /$border/)
	 ) {
	$separators[0] = $separator2;
      }
    };

    for (my $i=0; $i<@separators; $i++) {
      $width = $columns - length ($prefix); #initialize each time
      if (length($text) <= $width) {
        # No wrapping needed
        $newText = $newText . $prefix . $text . "\n";
        $text = '';
        next TEXT;
      }
      else {
        # Needs wrapping
        while (($lineText, $sepText) = 
            $text =~ /\A(.{1,$width})($separators[$i]|\Z)/) {
          $match = $&;
          $postMatch = $';
          my $spaces = $match =~ s/(\s+)\Z// ? $1 : "";
          if (length($match) > $width) {
            # The separator extends
            # beyond the maximal line length. Retry with shorter $width. 
            $width--;
          }
          else {

            if (defined $longWordChar) {
              
              # if a long word is found, cut it anywhere and append as much of it
              # as possible to the uppermost line...
              
              if ($postMatch =~ /^$longWordChar {$width}/x) {
              
                my $cutPos = $width - length($match) - length($spaces);

                #  ... however, try to cut the long word at any separators of
                # lower priority than the current one, except the empty
                # last-resort separator
                for (my $j=$i+1; $j<@separators-1; $j++) {
                  # TODO: this is currently only optimal for fixed separators
                  # of length 1 ($sepLength = 1)
                  my $sepLength = 1;
                  my $w1 = $cutPos - $sepLength;
                  if ($postMatch =~ /^(\S{0,$w1}$separators[$j])/) {
                    $cutPos = length($1);
                    last;
                  }
                }

                # ok, now do the splicing
                if ($cutPos>0) {
                  my $substr = substr($postMatch, 0, $cutPos);
                  substr($postMatch, 0, $cutPos) = "";
                  $match .= $spaces . $substr;
                }
              }
            }

            $newText = $newText . $prefix . $match . "\n";
            $text = $postMatch;
            $prefix=$prefix2; 
            next TEXT;
          }
        }
      }
    };

    # Wrapping failed    
    if ($main::opt_warn) {
      carp "TextFunc::wrapOn: Cannot wrap $text";
    };
    $newText = $text . "\n";
    $text = '';
  }
  $newText =~ s/ +$//mg;
  return $newText;
}

sub cleanLine {
    my $class = shift;
    my $text = shift;

    # Drop trailing spaces
    $text =~ s/\s+$//;
    chomp($text);
    if(length($text) != 2) {
	$text = substr $text, 5;
    } else {
	$text = undef;
    }

    return $text;
}

sub joinWith {
  my $self = shift;
  my($text, $with, $noAddAfter, $addBefore, @list) = @_;
  
  unless ($text) {
    $text = shift @list;
  };
  
  for my $line (@list) {
    unless ($text =~ /$noAddAfter$/ && $line !~ /^$addBefore/) {
      $text .= $with
    };
    $text .= $line;
  }
  return $text;
}

sub insertLineGroup {
  my $class =  shift;
  my $textRef = shift;
  my $text = shift;  
  my $pattern = shift;
  my $found = -1;
  my $i;
  
  # The easy case: Replace a text block with a new one.
  if ($$textRef =~ /$pattern/m) {
    $$textRef = $` . $text . $';
    return 1;
  }

  # Nothing to replace found. Seek insertion place.
  for ($i = $#linePattern; $i>=0; $i--) {
    if ($pattern eq $linePattern[$i]) {
      $found = $i;
      last;
    }
  }
  if ($found == -1) {
    $main::opt_warn && carp "Could not insert $text into $$textRef";
    return 0;
  }
  for ($i = $found; $i>=0; $i--) {
    if ($$textRef =~ /$linePattern[$i]/m) {
      $$textRef = $` . $& . $text . $';
      return 1;
    }
  }
  
  if (defined $main::opt_warn) {
  
    $main::opt_warn >2 && carp "Prepended $text to $$textRef";
  }
  
  $$textRef = $text . $$textRef;
  return 0;
}

sub uniqueList {
  my $class = shift;

  my @oldList = @_;
  my @newList;
  my $element;

  foreach $element(@oldList) {
    unless (grep{$_ eq $element} @newList) {
      push @newList, $element;
    }
  };

  return @newList;
}


sub currentSpDate {  
  my ($dummy, $mday, $month, $year);
  
  my %month2number =  
    ('1'=>'JAN', '2'=>'FEB', '3'=>'MAR', '4'=>'APR', 
     '5'=>'MAY', '6'=>'JUN', '7'=>'JUL', '8'=>'AUG', 
     '9'=>'SEP', '10'=>'OCT', '11'=>'NOV', '12'=>'DEC');
  
  ($dummy, $dummy, $dummy, $mday, $month, $year, $dummy, $dummy, $dummy) 
    = localtime (time);
  if ($mday < 10) {
    $mday = '0' . $mday;
  }
  $month = $month2number{$month+1};
  $year += 1900;

  return "$mday-$month-$year";
}



#
# Functions used to cleanup entries in annotators' jobs
# Author : Alexandre Gattiker <gattiker@isb-sib.ch>
#

#removes wild ** comments throughout an entry, except after a DR line
#they can be reinserted again, based on the line that follows them.
#returns an pointer to a hash of "following lines" => "wild comment"
sub removeInternalComments {
	my $textRef=shift;
	my $newText;
	my %lines;
	my $afterACID;
	my $inEnd;
	my $inRef;
	my $inDR;
	my @comments;
	#remove everything before the ID line
	if ($$textRef =~ s/(.*?)^ID/ID/sm) {
		$lines{_start} = $1;
	}
	for (split /\n/, $$textRef) {
		$_ .= "\n";
		if ($inEnd || /SOURCE SECTION|INTERNAL SECTION|ANNOTATOR'S SECTION/) {
			#comments right before source section should go just inside
			$inEnd++;
			my (@textComments, @otherComments);
			for my $comment (@comments) {
				if ($comment =~ /\w/) {
					push @textComments, $comment;
				} 
				else {
					push @otherComments, $comment;
				}
			}
			$newText .= join '', @otherComments, $_, @textComments;
			undef @comments;
			next;
		}
		if (/^AC|^ID/) {
			$afterACID=1;
			if (@comments) {
				$lines{$_}=[@comments];
				splice @comments;
			}
			$newText .= $_;
			next;
		}
		#annotators' comment lines begin either with ** or ++
		elsif (/^ ?\*\*|^ ?\+\+/ && !$afterACID
			and (!$inRef or !/NO TITLE|=None/)
			and !($inDR and /^\*\*   \S+; \S+; \S+; /)
			) {
			push @comments, $_;
		}
		else {
			$afterACID=0;
			if (@comments and /(\S.*)/) {
				$lines{$1}=[@comments];
				splice @comments;
			}
			$newText .= $_;
			next;
		}
	}
	continue {
		$inRef = /^R/;
		$inDR = /^DR/ || ($inDR && /^\*/);
	};
	$$textRef=$newText;
	return \%lines;
}

#does the opposite...
#returns an array with the internal comments that could not be restored at their proper position.
#the caller should do something like $entry->Stars->ZZ->add them.
sub restoreInternalComments {
	my($textRef, $lines)=@_;

	#comments going before ID line
	my $before = delete $lines->{_start};

	#other comments : add before the relevant line
	my @newText;
	for my $line (split /(?<=\n)/, $$textRef) {
		if ($line =~ /(\S.*)/ and my ($comments) = delete $$lines{$1}) {
			push @newText, _wrapInternalComments(@$comments);
		}
		push @newText, $line;
	}

	#remaining comments : try to add before the relevant block
	my @newText2;
	for my $line (@newText) {
		if ($line =~ /^\s*(\w\w)/) {
			my $lineTag = $1;
			for my $prevline (keys %$lines) {
				if ($prevline =~ /^\s*($lineTag)/) {
					my $comments = delete $$lines{$prevline};
					push @newText2, _wrapInternalComments(@$comments);
				}
			}
		}
		push @newText2, $line;
	}

	$$textRef=$before . join "", @newText2;

	#return comments that could not be inserted
	return map{s/^\s*\*\*\s*//; s/\n$//; $_} map {@$_} values %$lines;
}

#wrap internal comments at 75 characters
sub _wrapInternalComments {
	foreach (@_) {
		my ($prefix) = s/^(\W+)// ? $1 : "";
		s/\s+$//;
		$_ = wrapOn (undef, $prefix, $prefix, $SWISS::TextFunc::lineLength, $_, '\s+')
	}
	@_;
}

sub toMixedCase {
	my ($text, @regexps) = @_;
	my $ok_regexp;
	for my $regexp (@regexps) {
		#This regexp is made complex by the need to convert e.g. "B0690/B0691" to "b0690/b0691"
		$text =~ s!(?:^|\G)($regexp)($|\/)!
			my @char = split //, $1;
			my $postfix = substr $text, $-[-1], $+[-1] - $-[-1]; #this fetches the content of the '($|\/)' part of the regexp as the last matched subgroup (i.e. the possible slash), see man perlre for "@-" for an explanation
			if ($1 =~ /^($regexp)$/) { #if it matches the regexp case-sensitively, no need to convert
					$1 . $postfix; #return value
			}
			else {
				my $num_letter=0;
				my @letter_pos;
				for (my $i=0; $i<@char; $i++) {
					$letter_pos[$i] = (uc ($char[$i]) ne lc $char[$i]) ? 1 : 0;
					$num_letter += $letter_pos[$i];
				}
				my $string_ok;
				for (my $binary=0; $binary<2**$num_letter; $binary++) { #combinatorially change casing of each letter
					my $string;
					my $j=0;
					for (my $i=0; $i<@char; $i++) {
						if ($letter_pos[$i]) {
							my $mask = 1<<$j;
							my $bin_value = ($binary & $mask) >> $j;
							$string .= $bin_value ? uc($char[$i]) : lc($char[$i]);
							$j++;
						}
						else {
							$string .= $char[$i];
						}
					}
					$string_ok = $string, last if $string =~ /^(?:$regexp)$/; #case-sensitive match
				}
				if (defined $string_ok) {
					$string_ok . $postfix; #return value
				}
				else {
					#this should never happen
					warn "INTERNAL ERROR: Could not find correct casing for ".join("",@char)." ($regexp)";
					join("",@char) . $postfix; #return value
				}
			}
		!egi or next;
		$ok_regexp = $regexp;
		last;
	}
	return wantarray ? ($text, $ok_regexp) : $text;
}


1;

__END__

=head1 NAME

SWISS::TextFunc

=head1 DESCRIPTION

This module is designed to be a repository of functions that are
repeatedly used during parsing and formatting of SWISS-PROT/TREMBL lines.
If more than two line types need to do aproximately the same thing
then it is probably in here.

All functions expect to be called as package->function(param list)

=over

=item listFromText

Takes a piece of text, a seperator regex and a seperator that may appear at the end.
Returns an array of items that were seperated in the text by that seperator.  Takes care of
null items (looses them for you).

=item textFromList

Takes an array of items, a separator, a terminating string, and a line width.
Returns an array of strings, each ending with the separator or the terminator with
a width less than or equal to the width specified.

Seems to do the wrong thing for references - not sure why.  
Don't use it for that.

=item wrapText

Takes a string and a length.  Returns an array of strings which are shorter or equal
in length to length, spliting the string on white space.

=item wrapOn ($firstLinePrefix, $linePrefix, $colums, $text[, @separators])

Wraps $text into lines with at most $colums colums. Prepends the
prefixes to the lines. @separators is a list of expressions on which
to wrap. The expression itself is part of the upper line. 

If no @separators are provided, the $text is wrapped at whitespace
except in EC/TC numbers or at dashes that separate words.

First tries to wrap on the first item of @separators, then the next
etc.  If no wrap on any element of @separators or whitespaces is
possible, wraps into lines of exactly length $colums. 

A special case is that the first item of @separators may be a reference
to an array. This is used internally for wrapping FT VARIANT-like lines.

Example:

 wrapOn('DE ', 'DE ', 40, 
        '14-3-3 PROTEIN BETA/ALPHA (PROTEIN KINASE C INHIBITOR PROTEIN-1)', 
        '\s+') 
 returns ['14-3-3 PROTEIN BETA/ALPHA (PROTEIN ', 
          'KINASE C INHIBITOR PROTEIN-1)']
 wrapOn('DE ', 'DE ', 40, 
        '14-3-3 PROTEIN BETA/ALPHA (PROTEIN KINASE C INHIBITOR PROTEIN-1)', 
        ' (?=\()', '\s+')
 returns ['14-3-3 PROTEIN BETA/ALPHA ', 
          '(PROTEIN KINASE C INHIBITOR PROTEIN-1)']

=item cleanLine

Remove the leading line Identifier and three blanks and trailing spaces from an SP line. 

=item joinWith ($text, $with, $noAddAfter, @list)

Concatenates $text and @list into one string. Adds $with between the 
original elements, unless the postfix of the current string is $noAddAfter. 
This is used to avoid inserting blanks after hyphens during concatenation. 
So unpleasant strings like 'CALMODULIN- DEPENDENT' are avoided. Unfortunately 
a correct reassembly of strings like 'CARBON-DIOXIDE' is not done.

=item insertLineGroup ($textRef, $text, $pattern)

Inserts text block $text into the text referred to by $textRef. $text will replace the text block in $textRef matched by $pattern.

=item uniqueList (@list)

Returns a list in which all duplicates from @list have been removed. 

=item currentSpDate

returns the current date in SWISS-PROT format

=item toMixedCase($text, @regexps)

Convert a text to mixed case, according to one or more regular expressions.
In scalar context, returns the new text; in array context, also returns
the regexp with which the change was performed, or undef on failure.
See corresponding item in SWISS::GN for more details.

=back