summaryrefslogtreecommitdiff
path: root/Master/texmf-dist/scripts/bibtexperllibs/BibTeX/Parser/Author.pm
blob: a0ffb455be4e8dc26249b4280eccf089427b14a1 (plain)
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
package BibTeX::Parser::Author;
{
  $BibTeX::Parser::Author::VERSION = '1.01';
}

use warnings;
use strict;

use BibTeX::Parser;


use overload
	'""' => \&to_string;



sub new {
	my $class = shift;

	if (@_) {
		my $self = [ $class->split(@_) ];
		return bless $self, $class;
	} else {
		return bless [], $class;
	}
}

sub _get_or_set_field {
	my ($self, $field, $value) = @_;
	if (defined $value) {
		$self->[$field] = $value;
	} else {
		return $self->[$field];
	}
}


sub first {
	shift->_get_or_set_field(0, @_);
}


sub von {
	shift->_get_or_set_field(1, @_);
}


sub last {
	shift->_get_or_set_field(2, @_);
}


sub jr {
	shift->_get_or_set_field(3, @_);
}


# Take a string and create an array [first, von, last, jr]
sub split {
    my ($self_or_class, $name) = @_;
    
    # remove whitespace at start and end of string
    $name =~ s/^\s*(.*)\s*$/$1/s;



    if (!length($name)) {
	return (undef, undef, undef, undef);
    }
    
    my @comma_separated = 
	BibTeX::Parser::_split_braced_string($name, 
					     '\s*,\s*');
    if (scalar(@comma_separated) == 0) {
	# Error?
	return (undef, undef, undef, undef);
    }

    my $first=undef;
    my $von=undef;
    my $last=undef;
    my $jr=undef;
    
    if (scalar(@comma_separated) == 1) {
	# First von Last form
	my @tokens = 	
	    BibTeX::Parser::_split_braced_string($name, '\s+');
	if (!scalar (@tokens)) {
	    return (undef, undef, undef, undef);
	}
	my ($start_von, $start_last) = _getStartVonLast (@tokens);
	if ($start_von >0) {
	    $first = join(' ', splice(@tokens,0,$start_von));
	}
	if (($start_last-$start_von) >0) {
	    $von = join(' ', splice(@tokens,0,$start_last-$start_von));
	}
	$last = join(' ',@tokens);
	return ($first, $von, $last, $jr);
    }
    # Now we work with von Last, [Jr,] First form
    if (scalar @comma_separated == 2) { # no jr
	my @tokens=  
	    BibTeX::Parser::_split_braced_string($comma_separated[1], '\s+');
	$first = join(' ', @tokens);
    } else { # jr is present
	my @tokens=  
	    BibTeX::Parser::_split_braced_string($comma_separated[1], '\s+');
	$jr = join(' ', @tokens);
	@tokens=  
	    BibTeX::Parser::_split_braced_string($comma_separated[2], '\s+');
	$first = join(' ', @tokens);
    }
    my @tokens = 	
	BibTeX::Parser::_split_braced_string($comma_separated[0], '\s+');
    my $start_last = _getStartLast(@tokens);
    if ($start_last > 0) {
	$von=join(' ', splice(@tokens,0,$start_last));
    }
    $last = join(' ',@tokens);
    return ($first, $von, $last, $jr);

}

# Return the index of the first von element and the first lastname 
# element.  If no von element, von=last

sub _getStartVonLast {
    my $length=scalar(@_);
    if ($length==1) {
	return (0,0);
    }
    my $start_von=-1;
    my $start_last=$length-1;
    for (my $i=0; $i<$length; $i++) {
	if  (_is_von_token($_[$i])) {
	    $start_von=$i;
	    last;
	}
    }
    if ($start_von== -1) { # no von part
	return($length-1, $length-1);
    }
    if ($start_von== $length-1) { # all parts but last are upper case?
	return($length-1, $length-1);
    }
    for (my $i=$start_von+1; $i<$length; $i++) {
	if (!_is_von_token($_[$i])) {
	    $start_last=$i;
	    last;
	}
    }
    return($start_von, $start_last);
}


# Return the index of the first lastname 
# element provided no first name elements are present

sub _getStartLast {
    my $length=scalar(@_);
    if ($length==1) {
	return 0;
    }
    my $start_last=$length-1;
    for (my $i=0; $i<$length; $i++) {
	if  (!_is_von_token($_[$i])) {
	    $start_last=$i;
	    last;
	}
    }
    return $start_last;
}


sub _split_name_parts {
    my $name = shift;

    if ( $name !~ /\{/ ) {
        return split /\s+/, $name;
    } else {
        my @parts;
        my $cur_token = '';
        while ( scalar( $name =~ /\G ( [^\s\{]* ) ( \s+ | \{ | \s* $ ) /xgc ) ) {
            $cur_token .= $1;
            if ( $2 =~ /\{/ ) {
                if ( scalar( $name =~ /\G([^\}]*)\}/gc ) ) {
                    $cur_token .= "{$1}";
                } else {
                    die "Unmatched brace in name '$name'";
                }
            } else {
                if ( $cur_token =~ /^{(.*)}$/ ) {
                    $cur_token = $1;
                }
                push @parts, $cur_token;
                $cur_token = '';
            }
        }
        return @parts;
    }

}


sub _get_single_author_from_tokens {
    my (@tokens) = @_;
    if (@tokens == 0) {
        return (undef, undef, undef, undef);
    } elsif (@tokens == 1) {	# name without comma
        if ( $tokens[0] =~ /(^|\s)[[:lower:]]/) { # name has von part or has only lowercase names
            my @name_parts = _split_name_parts $tokens[0];

            my $first;
            while (@name_parts && ucfirst($name_parts[0]) eq $name_parts[0] ) {
                $first .= $first ? ' ' . shift @name_parts : shift @name_parts;
            }

            my $von;
            # von part are lowercase words
            while ( @name_parts && lc($name_parts[0]) eq $name_parts[0] ) {
                $von .= $von ? ' ' . shift @name_parts : shift @name_parts;
            }

            if (@name_parts) {
                return ($first, $von, join(" ", @name_parts), undef);
            } else {
                return (undef, undef, $tokens[0], undef);
            }
        } else {
            if ( $tokens[0] !~ /\{/ && $tokens[0] =~ /^((.*)\s+)?\b(\S+)$/) {
                return ($2, undef, $3, undef);
            } else {
                my @name_parts = _split_name_parts $tokens[0];
                return ($name_parts[0], undef, $name_parts[1], undef);
            }
        }

    } elsif (@tokens == 2) {
        my @von_last_parts = _split_name_parts $tokens[0];
        my $von;
        # von part are lowercase words
        while ( @von_last_parts && lc($von_last_parts[0]) eq $von_last_parts[0] ) {
            $von .= $von ? ' ' . shift @von_last_parts : shift @von_last_parts;
        }
        return ($tokens[1], $von, join(" ", @von_last_parts), undef);
    } else {
        my @von_last_parts = _split_name_parts $tokens[0];
        my $von;
        # von part are lowercase words
        while ( @von_last_parts && lc($von_last_parts[0]) eq $von_last_parts[0] ) {
            $von .= $von ? ' ' . shift @von_last_parts : shift @von_last_parts;
        }
        return ($tokens[2], $von, join(" ", @von_last_parts), $tokens[1]);
    }

}




sub to_string {
	my $self = shift;

	if ($self->jr) {
		return $self->von . " " . $self->last . ", " . $self->jr . ", " . $self->first;
	} else {
		return ($self->von ? $self->von . " " : '') . $self->last . ($self->first ? ", " . $self->first : '');
	}
}


# Return 1 if the first letter on brace level 0 is lowercase
sub _is_von_token {
    my $string = shift;
    while ($string =~ 
	   s/^(\\[[:alpha:]]+\{|\{|\\[[:^alpha:]]?|[[:^alpha:]])//) {
	if ($1 eq '{' ) {
	    my $numbraces=1;
	    while ($numbraces !=0 && length($string)) {
		my $symbol = substr($string, 0, 1);
		if ($symbol eq '{') {
		    $numbraces ++;
		} elsif ($symbol eq '}') {
		    $numbraces --;
		}
		$string = substr($string,1);
	    }
	}
    }

    if (length $string ) {
	my $symbol = substr($string, 0, 1);
	if (lc($symbol) eq $symbol) {
	    return 1;
	} else {
	    return 0;
	}
    } else {
	return 1;
    }

}

1; # End of BibTeX::Entry

__END__
=pod

=head1 NAME

BibTeX::Author - Contains a single author for a BibTeX document.

=head1 SYNOPSIS

This class ist a wrapper for a single BibTeX author. It is usually created
by a BibTeX::Parser.

    use BibTeX::Parser::Author;

    my $entry = BibTeX::Parser::Author->new($full_name);
    
    my $firstname = $author->first;
    my $von	  = $author->von;
    my $last      = $author->last;
    my $jr	  = $author->jr;

    # or ...
    
    my ($first, $von, $last, $jr) = BibTeX::Author->split($fullname);



=head1 FUNCTIONS

=head2 new

Create new author object. Expects full name as parameter.

=head2 first

Set or get first name(s).

=head2 von

Set or get 'von' part of name.

=head2 last

Set or get last name(s).

=head2 jr

Set or get 'jr' part of name.

=head2 split

Split name into (firstname, von part, last name, jr part). Returns array
with four strings, some of them possibly empty.

=head2 to_string

Return string representation of the name.

=head1 NOTES

BibTeX allows three representations of a person's name:

=over 4

=item 1.

First von Last

=item 2.

von Last, First

=item 3.

von Last, Jr, First

=back

The module always converts the first form to the second of third one
to allow simple string comparisons.  

The algorithm to determine the von part is the following: von part
consists of tokens where the first letter at brace level 0 is in lower case.
Anything in a "special characters" is on brace level 0.  Thus the following
tokens are considered von parts:  C<von>, C<\NOOP{von}Von>, and
the following token is not: C<{von}>

=head1 VERSION

version 1.01


=head1 AUTHOR

Gerhard Gossen <gerhard.gossen@googlemail.com> and
Boris Veytsman <boris@varphi.com>

=head1 COPYRIGHT AND LICENSE

This software is copyright (c) 2013--2016 by Gerhard Gossen and Boris Veytsman.

This is free software; you can redistribute it and/or modify it under
the same terms as the Perl 5 programming language system itself.

=cut