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
|
# ----------------------------------------------------------------
# this test script is written in utf8 but does not "use utf8" for 5.005-compatibility
# ----------------------------------------------------------------
use strict;
use Test::More;
# ----------------------------------------------------------------
{
local $@;
eval { require 5.008001; };
plan skip_all => 'Perl 5.8.1 is required.' if $@;
}
# ----------------------------------------------------------------
{
plan tests => 155;
use_ok('XML::TreePP');
&test_main();
}
# ----------------------------------------------------------------
sub test_main {
my $src = {};
$src->{Plain} = <<"EOT";
<root>
<a>AA</a>
<z>zz</z>
<c>©©</c>
<e>ëë</e>
<n>んん</n>
<k>漢漢</k>
</root>
EOT
$src->{XMLref} = <<"EOT";
<root>
<a>AA</a>
<z>zz</z>
<c>©©</c>
<e>ëë</e>
<n>んん</n>
<k>漢漢</k>
</root>
EOT
$src->{Mixed} = <<"EOT";
<root>
<a>AA</a>
<z>zz</z>
<c>©©</c>
<e>ëë</e>
<n>んん</n>
<k>漢漢</k>
</root>
EOT
foreach my $key ( keys %$src ) {
phase2( "$key octets", $src->{$key} );
my $copy = $src->{$key};
utf8::decode( $copy );
next unless utf8::is_utf8($copy);
phase2( "$key string", $copy );
}
}
# ----------------------------------------------------------------
sub phase2 {
my $subject = shift;
my $srcxml = shift;
my $srcutf8 = utf8::is_utf8($srcxml);
my $srcref = ( $srcxml =~ /&#\w+;/ );
foreach my $utf8_flag ( 0, 1 ) {
my $subj2 = $subject .( $utf8_flag ? ' utf8_flag' : '' );
foreach my $xml_deref ( 0, 1 ) {
my $subj3 = $subj2 .( $xml_deref ? ' xml_deref' : '' );
my $opt = {
utf8_flag => $utf8_flag,
xml_deref => $xml_deref,
};
my $tpp = XML::TreePP->new( %$opt );
my $tree = $tpp->parse( $srcxml );
if ( $xml_deref ) {
if ( $srcutf8 || $utf8_flag ) {
check_string( $subj3, $tree );
} else {
check_octets( $subj3, $tree );
}
} else {
if ( $srcref ) {
check_has_ref( $subj3, $tree );
} else {
check_no_ref( $subj3, $tree );
}
}
}
}
}
# ----------------------------------------------------------------
sub check_has_ref {
my $subject = shift;
my $tree = shift;
my $root = $tree->{root};
my $HAS_REF = qr/&#\w+;/;
# \x00-\x7F is always dereferenced.
# like( $root->{a}, $HAS_REF, "[$subject] has_ref: a" );
# like( $root->{z}, $HAS_REF, "[$subject] has_ref: z" );
like( $root->{c}, $HAS_REF, "[$subject] has_ref: c" );
like( $root->{e}, $HAS_REF, "[$subject] has_ref: e" );
like( $root->{n}, $HAS_REF, "[$subject] has_ref: n" );
like( $root->{k}, $HAS_REF, "[$subject] has_ref: k" );
}
# ----------------------------------------------------------------
sub check_no_ref {
my $subject = shift;
my $tree = shift;
my $root = $tree->{root};
my $HAS_REF = qr/&#\w+;/;
unlike( $root->{a}, $HAS_REF, "[$subject] no_ref: a" );
unlike( $root->{z}, $HAS_REF, "[$subject] no_ref: z" );
unlike( $root->{c}, $HAS_REF, "[$subject] no_ref: c" );
unlike( $root->{e}, $HAS_REF, "[$subject] no_ref: e" );
unlike( $root->{n}, $HAS_REF, "[$subject] no_ref: n" );
unlike( $root->{k}, $HAS_REF, "[$subject] no_ref: k" );
}
# ----------------------------------------------------------------
sub check_string {
my $subject = shift;
my $tree = shift;
my $root = $tree->{root};
# \x00-\x7F never have utf8 flag
# ok( utf8::is_utf8($root->{a}), "[$subject] is_utf8: a" );
# ok( utf8::is_utf8($root->{z}), "[$subject] is_utf8: z" );
ok( utf8::is_utf8($root->{c}), "[$subject] is_utf8: c" );
ok( utf8::is_utf8($root->{e}), "[$subject] is_utf8: e" );
ok( utf8::is_utf8($root->{n}), "[$subject] is_utf8: n" );
ok( utf8::is_utf8($root->{k}), "[$subject] is_utf8: k" );
is( $root->{a}, chr(0x0041) x 2, "[$subject] ok: a" );
is( $root->{z}, chr(0x007A) x 2, "[$subject] ok: z" );
is( $root->{c}, chr(0x00A9) x 2, "[$subject] ok: c" );
is( $root->{e}, chr(0x00EB) x 2, "[$subject] ok: e" );
is( $root->{n}, chr(0x3093) x 2, "[$subject] ok: n" );
is( $root->{k}, chr(0x6F22) x 2, "[$subject] ok: k" );
}
# ----------------------------------------------------------------
sub check_octets {
my $subject = shift;
my $tree = shift;
my $root = $tree->{root};
ok( ! utf8::is_utf8($root->{a}), "[$subject] is_octets: a" );
ok( ! utf8::is_utf8($root->{z}), "[$subject] is_octets: z" );
ok( ! utf8::is_utf8($root->{c}), "[$subject] is_octets: c" );
ok( ! utf8::is_utf8($root->{e}), "[$subject] is_octets: e" );
ok( ! utf8::is_utf8($root->{n}), "[$subject] is_octets: n" );
ok( ! utf8::is_utf8($root->{k}), "[$subject] is_octets: k" );
is( $root->{a}, 'AA', "[$subject] ok: a" );
is( $root->{z}, 'zz', "[$subject] ok: z" );
is( $root->{c}, '©©', "[$subject] ok: c" );
is( $root->{e}, 'ëë', "[$subject] ok: e" );
is( $root->{n}, 'んん', "[$subject] ok: n" );
is( $root->{k}, '漢漢', "[$subject] ok: k" );
}
# ----------------------------------------------------------------
;1;
# ----------------------------------------------------------------
|
