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
|
# -*- cperl -*-
use strict;
use vars qw($DEBUG);
use IO::Handle;
use Test::More tests=>27;
use utf8;
use Encode 'decode';
use Unicode::Normalize;
use Cwd;
my $common = getcwd()."/t/common.pl";
require $common;
use Text::BibTeX qw(:nameparts :joinmethods);
$DEBUG = 1;
{
# tests 1..3
# Get a name to work with (and just a quick check that the Name class
# is in working order)
my $name = Text::BibTeX::Name->new
("Charles Louis Xavier Joseph de la Vall{\\'e}e Poussin");
my @first = $name->part('first');
my @von = $name->part('von');
my @last = $name->part('last');
is_deeply \@first, [qw(Charles Louis Xavier Joseph)],
"First name is 'Charles Louis Xavier Joseph'";
is_deeply \@von, [qw(de la)],
"von part is 'de la'";
is_deeply \@last, ["Vall{\\'e}e", 'Poussin'],
"Last name is 'Vall{\\'e}e Poussin'";
}
{
# tests 4..5..
my $name1 = Text::BibTeX::Name->new('{John Henry} Ford');
my $format1 = Text::BibTeX::NameFormat->new('f', 1);
is $format1->apply($name1), 'J.', "first name is abbreviated correctly [1]";
my $name2 = Text::BibTeX::Name->new('{John} Ford');
my $format2 = Text::BibTeX::NameFormat->new('f', 1);
is $format2->apply($name2), 'J.', "first name is abbreviated correctly [2]";
}
{
# tests 6..
my $name3 = Text::BibTeX::Name->new
('{U.S. Department of Health and Human Services, National Institute of Mental Health,'.
'National Heart, Lung and Blood Institute}');
my $format3 = Text::BibTeX::NameFormat->new('l', 1);
$format3->set_text(BTN_LAST, undef, undef, undef, '.');
$format3->set_options(BTN_LAST, 1, BTJ_NOTHING, BTJ_NOTHING);
is $format3->apply($name3), 'U.', 'big institution';
}
{
# tests 7..8..
my $name4 = Text::BibTeX::Name->new("{\\'E}mile Zola");
my $format4 = Text::BibTeX::NameFormat->new('f', 1);
is $format4->apply($name4), "{\\'E}.", "accented first letter";
my $name5 = Text::BibTeX::Name->new('St John-Mollusc, Oliver');
my $format5 = Text::BibTeX::NameFormat->new('l', 1);
$format5->set_text(BTN_LAST, undef, undef, undef, '.');
$format5->set_options(BTN_LAST, 1, BTJ_MAYTIE, BTJ_NOTHING);
is $format5->apply($name5), 'S.~J.-M.', "abbreviated surname";
}
{
# tests 9..
my $name6 = Text::BibTeX::Name->new("St John-{\\'E}mile Mollusc, Oliver");
my $format6 = Text::BibTeX::NameFormat->new('l', 1);
$format6->set_text (BTN_LAST, undef, undef, undef, '.');
$format6->set_options (BTN_LAST, 1, BTJ_MAYTIE, BTJ_NOTHING);
is $format6->apply($name6), "S.~J.-{\\'E}.~M.", "Abbreviated accented surname";
}
{
# test 10...
my $name7 = Text::BibTeX::Name->new('St {John-Mollusc}, Oliver');
my $format7 = Text::BibTeX::NameFormat->new('l', 1);
$format7->set_text (BTN_LAST, undef, undef, undef, '.');
$format7->set_options (BTN_LAST, 1, BTJ_MAYTIE, BTJ_NOTHING);
is $format7->apply($name7), 'S.~J.';
}
{
# test 11... to 16
## This in raw mode
my $name8 = Text::BibTeX::Name->new('Šomeone Smith');
my $formatter = Text::BibTeX::NameFormat->new('f', 1);
is NFC(decode('UTF-8',$formatter->apply($name8))), 'Š.', "raw test 1";
my $name9 = Text::BibTeX::Name->new('Šomeone-Šomething Smith');
is NFC(decode('UTF-8',$formatter->apply($name9))), 'Š.-Š.', "raw test 2";
$formatter = Text::BibTeX::NameFormat->new('f', 1);
my $name10 = Text::BibTeX::Name->new({binmode=>'utf-8'},'{Šomeone-Šomething} Smith');
is $formatter->apply($name10), 'Š.', "utf-8 [1]";
# Initial is 2 bytes long in UTF8
my $formatterlast = Text::BibTeX::NameFormat->new('f', 1);
my $name11 = Text::BibTeX::Name->new({binmode=>'utf-8'},'Żaa Smith');
is $formatterlast->apply($name11), 'Ż.', "utf-8 [2]";
# Initial is 3 bytes long in UTF8 (Z + 2 byte combining mark)
$formatterlast = Text::BibTeX::NameFormat->new('f', 1);
my $name12 = Text::BibTeX::Name->new({binmode=>'utf-8'},'Z̃ Smith');
is $formatterlast->apply($name12), 'Z̃.', "utf-8 [3]";
# Initial is 7 bytes long in UTF8 (A + 3 * 2 byte combining marks)
$formatterlast = Text::BibTeX::NameFormat->new('f', 1);
my $name13 = Text::BibTeX::Name->new({binmode=>'utf-8'},'A̧̦̓ Smith');
is $formatterlast->apply($name13), 'A̧̦̓.', "utf-8 [3]";
}
{
# test 17... and 18
my $name14 = Text::BibTeX::Name->new('Harold {K}ent-{B}arrow');
my $format11 = Text::BibTeX::NameFormat->new('l', 1);
$format11->set_text(BTN_LAST, undef, undef, undef, '.');
$format11->set_options(BTN_LAST, 1, BTJ_MAYTIE, BTJ_NOTHING);
is $format11->apply($name14), 'K.-B.';
my $name15 = Text::BibTeX::Name->new('Mirian Neuser-Hoffman');
my $format12 = Text::BibTeX::NameFormat->new('l', 1);
$format12->set_text(BTN_LAST, undef, undef, undef, '');
$format12->set_options(BTN_LAST, 1, BTJ_MAYTIE, BTJ_NOTHING);
is $format12->apply($name15), 'N-H';
}
{
# test 19 to 26
my $name = Text::BibTeX::Name->new
("Charles Louis Xavier Joseph de la Vall{\\'e}e Poussin");
# Start with a basic "von last, jr, first" formatter
my $format = Text::BibTeX::NameFormat->new('vljf', 1);
is $format->apply($name), "de~la Vall{\\'e}e~Poussin, C.~L. X.~J.";
is $format->apply($name), $name->format($format);
# Tweak options: force ties between tokens of the first name
$format->set_options(BTN_FIRST, 1, BTJ_FORCETIE, BTJ_NOTHING);
is $format->apply($name), "de~la Vall{\\'e}e~Poussin, C.~L.~X.~J.";
# And no ties in the "von" part
$format->set_options(BTN_VON, 0, BTJ_SPACE, BTJ_SPACE);
is $format->apply($name), "de la Vall{\\'e}e~Poussin, C.~L.~X.~J.";
# No punctuation in the first name
$format->set_text(BTN_FIRST, undef, undef, undef, '');
is $format->apply($name), "de la Vall{\\'e}e~Poussin, C~L~X~J";
# And drop the first name inter-token separation entirely
$format->set_options(BTN_FIRST, 1, BTJ_NOTHING, BTJ_NOTHING);
is $format->apply($name), "de la Vall{\\'e}e~Poussin, CLXJ";
# Now we get silly: keep the first name tokens jammed together, but
# don't abbreviate them any more
$format->set_options(BTN_FIRST, 0, BTJ_NOTHING, BTJ_NOTHING);
is $format->apply($name), "de la Vall{\\'e}e~Poussin, CharlesLouisXavierJoseph";
# OK, but spaces back in to the first name
$format->set_options (BTN_FIRST, 0, BTJ_SPACE, BTJ_NOTHING);
is $format->apply($name), "de la Vall{\\'e}e~Poussin, Charles Louis Xavier Joseph";
}
{
# test 27
my $entry = new Text::BibTeX::Entry;
$entry->parse_s('@' . "article{key,\n author = {Firstlastname Secondlastname, Firstname and others},\n}");
my @authors = $entry->names("author");
my $format = new Text::BibTeX::NameFormat("vl");
is $format->apply($authors[0]), "Firstlastname~Secondlastname";
}
|
