This file is indexed.

/usr/share/perl5/SWISS/FTs.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
package SWISS::FTs;

use vars qw($AUTOLOAD @ISA @EXPORT_OK %fields %KEYORDER);

use Exporter;
use Carp;
use strict;

use SWISS::TextFunc;
use SWISS::ListBase;


BEGIN {
  @EXPORT_OK = qw();
  
  @ISA = ( 'Exporter', 'SWISS::ListBase');
  
  %fields = (
	    );

}

#initialization code: stuff DATA into hash
{
  # Leading and trailing spaces are MANDATORY!
  local $/="\n";
  my $index=0;
  my $line;
  while (defined ($line=<DATA>)) {
    $line =~ s/\s+\z//;
    $index++;
    $KEYORDER{$_} = $index for split /\s+/, $line;
  }
  close DATA;
}

sub new {
  my $ref = shift;
  my $class = ref($ref) || $ref;
  my $self = new SWISS::ListBase;
  
  $self->rebless($class);
  return $self;
}

sub fromText {
  my $class = shift;
  my $textRef = shift;
  my $self = new SWISS::FTs;
  my $line;
  my $tmp;
  my $indentation = 0;
  my ($key, $from, $to, $description);  # attributes of one feature
  
  if ($$textRef =~ /($SWISS::TextFunc::linePattern{'FT'})/m){
    foreach $line (split /\n/m, $1) {
      my $_indent = $line =~ s/^ //;
      $line = SWISS::TextFunc->cleanLine($line);
      if ($line =~ /^(\S+)\s+(\S+)\s+(\S+)\s*(.*)$/) {
        # first line of a feature
	# if there is a previous line, write it
	if ($key) {
  
	  $description = &_cleanDescription($key, $description);
	  my $ft = [$key, $from, $to, _unpack($description)];
	  push @{$self->list()}, $ft;
	  push @{$self->{indentation}}, [$ft->[0], $ft->[1], $ft->[2], $ft->[3]] if $indentation;
	  $indentation = 0;
	}
	# assign new values
	$key = $1; $from = $2; $to = $3; $description = $4;
      }
      elsif ($line =~ /^\s+(.*)$/){
	# continuation of a feature description
	$description = SWISS::TextFunc->joinWith($description, 
						 ' ', 
						 '(?<! )[-/]', 'and ',
						 $1);
      }
      else {
	if ($main::opt_warn) {
	  carp "FT line $line parse error.";
	}
      }
      $indentation += $_indent;
    }

    # write last FT line
    
    if ($key) { 
      $description = &_cleanDescription($key, $description);
      my $ft = [$key, $from, $to, _unpack($description)];
      push @{$self->list()}, $ft;
      push @{$self->{indentation}}, [$ft->[0], $ft->[1], $ft->[2], $ft->[3]] if $indentation;
    };
  }
  else {
    $self->initialize;
  }
  
  $self->{_dirty} = 0;

  return $self;
}

sub toText {
  my $self = shift;
  my $textRef = shift;
  my $newText = '';

  if ($#{$self->list()}>-1) {
    $newText = join('', map {$self->_FTtoText($_, @{$_})} @{$self->list()});
  };
  
  $self->{_dirty} = 0;

  return SWISS::TextFunc->insertLineGroup($textRef, $newText, $SWISS::TextFunc::linePattern{'FT'});
}  

sub _unpack {
 my $text = shift;
 my ($evid, $ftid, $evidenceTags) = ('','','{}');

 return ('','','','{}') unless $text;

 if ($text =~ s/(\/FTId=\S+)$//){
   $ftid = $1;
   $ftid =~ s/\.$//;
   $text =~ s/[\n\;\.\s]+$//sg;
   
 }

 # Parse out the evidence tags
 if ($text =~ s/($SWISS::TextFunc::evidencePattern)//) {
   $evidenceTags = $1;
 }

 # Get the old-style Swiss-Prot evidence
 if ($text =~ s/ \((BY SIMILARITY|POTENTIAL|PROBABLE)\)$//i){
   $evid = $1;
 }
 elsif (grep {$_ eq uc $text} ('BY SIMILARITY', 'POTENTIAL', 'PROBABLE')) {
   $evid = $text;
   $text = "";
 }
 
 $text =~ s/[\n\;\.\s]+$//sg;
 
 return ($text, $evid, $ftid, $evidenceTags);
}

# remove wrongly inserted ' ' in description 
# of CONFLICT, VARIANT, VAR_SEQ and VARSPLIC

sub _cleanDescription {
  my ($key, $description) = @_;
  # parts of the description of CONFLICT, VARIANT, VAR_SEQ and VARSPLIC
  my ($sequence, $ref); 
  
  # Remove trailing dots and spaces
  $description =~ s/[\s\.]+$//;
  
  if (($key eq 'CONFLICT')
      ||
      ($key eq 'VARIANT')
      ||
      ($key eq 'VAR_SEQ')
      ||
      ($key eq 'VARSPLIC')) {
    # The * is allowed as part of the description for cases like
    # AC Q50855: AVWKA -> R*SVP
    
    if ($description !~ /^Missing/) {
    
      if (($sequence, $ref) = $description =~ /([A-Z \-\>\*]+)(.*)/) {
        $sequence =~ s/(?<! OR) (?!OR )//gm;
        $sequence =~ s/\-\>/ \-\> /;
        $sequence .= ' ';
        $description = $sequence . $ref;
      }
    }
  }

  if ($key eq 'MUTAGEN') {
    if ($description !~ /^Missing/) {
      if (($sequence, $ref) = $description =~ /([A-Z \-\>\*,]+)(.*)/) {
        $sequence =~ tr/ //d;
        $description = $sequence . $ref;
      }
    }
  }

  return $description;
}


sub _FTtoText {
  my ($self, $ft, $key, $from, $to, $description, $evidence, $ftid,
      $evidenceTags) = @_;
  my ($prefix, $text);

  $text = '';
  $prefix = sprintf("FT   %-8s  %5s  %5s       ", 
		    $key, $from, $to);
  if ($evidence) {
    if (length $description){
      $description = "$description ($evidence)";
    } else {
      $description = $evidence;
    }
  }

  # add the evidence tags
  if ($evidenceTags &&
      ($evidenceTags ne '{}')) {
    $description .= $evidenceTags;
  }

  if (length $description ) {
    $text = $description;
    # Add a dot at the end if the description does not consist only of 
    # evidence tags.
    unless ($description =~ /\A$SWISS::TextFunc::evidencePattern\Z/) {
      $text .= '.';
    }
  } else {
    # Text must not be empty, otherwise the wrapping will return ''
    $text .= ' ';
  }

  # Complex rules for the formatting of FT VARIANT, FT CONFLICT, FT VARSPLIC
  # according to softuse.txt, SFT006
  if ($prefix =~  /CONFLICT|VARIANT|VAR_SEQ|VARSPLIC/) {
    $text = SWISS::TextFunc->wrapOn($prefix, 
        "FT                                ", 
        $SWISS::TextFunc::lineLength, $text,
        ['(?!\>)\s*', '\(', "/|$SWISS::TextFunc::textWrapPattern1", '[^\s\-/]'], 
        "/|$SWISS::TextFunc::textWrapPattern2"
        );
  } else {
    $text = SWISS::TextFunc->wrapOn($prefix, 
        "FT                                ", 
        $SWISS::TextFunc::lineLength, $text, $SWISS::TextFunc::textWrapPattern1,
        "/|$SWISS::TextFunc::textWrapPattern2"
        );
  };
  
  # add a /FTId line if necessary
  if (length $ftid){
    $text .= "FT                                $ftid.\n";
  }
 
  # reinsert indentation
  if ($self->{indentation}) {
    for my $indented (@{$self->{indentation}}) {
      next unless $ft->[0] eq $indented->[0]
        and $ft->[1] eq $indented->[1]
        and $ft->[2] eq $indented->[2]
        and $ft->[3] eq $indented->[3];
      $text =~ s/^/ /mg;
      last;
    }
  }
  return $text;
}

#sorting based on annotation rule ANN027,
#and additional instructions from Amos.
#FTs should be sorted based on :
#-the priority index, or
#-the starting position (lesser goes first), or
#-the ending position (longer goes first), or
#-the FT comment as a last resort.
sub sort {
	my $self = shift;

	my $self_list = $self->list;

	my @indices = sort {
		my $item1 = ${$self_list}[$a];
		my $item2 = ${$self_list}[$b];
		my $sv =
			#sort by virtual key
			($KEYORDER{$item1->[0]} || 0) <=> ($KEYORDER{$item2->[0]} || 0) ||
			#or by start position
			_numericPosition($item1->[1], $item1->[2]) <=> _numericPosition($item2->[1], $item2->[2]) ||
			#or by end position (reversed)
			_numericPosition($item2->[2], $item2->[1]) <=> _numericPosition($item1->[2], $item1->[1]);
			#for FT VARSPLIC and VAR_SEQ:
			#as a penultimate resort, alphabetically on what follows the parenthesis
			#in the FTcomment
			if (!$sv and $item1->[0] =~ /^VARSPLIC|VAR_SEQ$/
					and my ($t1) = $item1->[3] =~ /\((.*)/
					and my ($t2) = $item2->[3] =~ /\((.*)/
					) {
				$sv = lc($t1) cmp lc($t2) || $t1 cmp $t2;
			}
			#for FT CONFLICT+VARIANT:
			#as a penultimate resort, alphabetically on FTcomment
			#(except "Missing" that should go at the end)
			unless ($sv) {
				if (grep {$_ eq $item1->[0]} ("CONFLICT", "VARIANT", "MUTAGEN")) {
					if ($item1->[3] =~ /^Missing/i) {
						unless ($item2->[3] =~ /^Missing/i) {
							$sv = 1;
						}
					}
					else {
						if ($item2->[3] =~ /^Missing/i) {
							$sv = -1;
						}
					}
				}
			}
			#as a last resort, alphabetically on FTcomment (e.g. variants)
			$sv || lc($item1->[3]) cmp lc($item2->[3]) || $item1->[3] cmp $item2->[3]
		} 0..$#$self_list;
	my @newlist;
	for (@indices) {
		push @newlist, ${$self_list}[$_];
	}
	$self->list(\@newlist);
}

# For a given feature position, return the numeric position.
# This converts "fuzzy" positions for sorting purpose, according to the rule:
# 11 => 11
# >14 => 14.1
# <1 => 0.9
# ?31 => 31
# if a position is only "?", the other position should be passed as a second
# argument, to be used as a backup. For example, if a feature is
# FT   CHAIN         ?    103       Potential.
# the position 103 should be considered the best-guess start position for sorting.
sub _numericPosition {
	for my $string (@_) {
		return $1+0.1 if $string =~ />(\d+)/;
		return $1-0.1 if $string =~ /<(\d+)/;
		return $1 if $string =~ /(\d+)/;
	}
	return 0;
}

1;

=head1 Name

SWISS::FTs

=head1 Description

B<SWISS::FTs> represents the FT (feature) lines within an SWISS-PROT + TrEMBL
entry as specified in the user manual
http://www.expasy.org/sprot/userman.html .

=head1 Inherits from

SWISS::ListBase.pm

=head1 Attributes

=over

=item C<list>

An array of arrays. Each element is an array containing: a feature key, from 
position, to position, description, qualifier, FTId and an evidence tag. Example:
['CHAIN', 25, 126, 'Alpha chain', 'By similarity', '/FTId=PRO_0000023008', '{EC1}']

=back

=head1 Methods

=head2 Standard methods

=over

=item new

=item fromText

=item toText

=item sort

=back

=cut

__DATA__
INIT_MET SIGNAL PROPEP TRANSIT CHAIN PEPTIDE
TOPO_DOM TRANSMEM
DOMAIN REPEAT
CA_BIND ZN_FING DNA_BIND NP_BIND
REGION
COILED
MOTIF
COMPBIAS
ACT_SITE
METAL
BINDING
SITE
NON_STD
MOD_RES
LIPID
CARBOHYD
DISULFID 
CROSSLNK
VAR_SEQ
VARIANT
MUTAGEN
UNSURE
CONFLICT
NON_CONS
NON_TER
HELIX TURN STRAND