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
|
--TEST--
Test mb_decode_numericentity() function : Convert HTML entities to text
--EXTENSIONS--
mbstring
--FILE--
<?php
function varDumpToString($var)
{
ob_start();
var_dump($var);
return trim(ob_get_clean());
}
function test($desc, $str, $expected, $convmap, $encoding) {
$result = mb_decode_numericentity($str, $convmap, $encoding);
echo $desc, ": ", varDumpToString($str), " => ", varDumpToString($result);
if ($result === $expected)
echo " (Good)\n";
else
echo " (BAD; expected ", varDumpToString($expected), ")\n";
}
function testNonAscii($desc, $str, $expected, $convmap, $encoding) {
$result = mb_decode_numericentity($str, $convmap, $encoding);
echo $desc, ": ", bin2hex($str), " => ", bin2hex($result);
if ($result === $expected)
echo " (Good)\n";
else
echo " (BAD; expected ", bin2hex($expected), ")\n";
}
$str1 = '¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ';
$str2 = 'ƒΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩαβγδεζηθικλμνξοπρςστυφχψωϑϒϖ•…′″‾⁄℘ℑℜ™ℵ←↑→↓↔↵⇐⇑⇒⇓⇔∀∂∃∅∇∈∉∋∏∑−∗√∝∞∠∧∨∩∪∫∴∼≅≈≠≡≤≥⊂⊃⊄⊆⊇⊕⊗⊥⋅⌈⌉⌊⌋〈〉◊♠♣♥♦';
$str3 = 'aŒbœcŠdše€fg';
// Typical convmap, typical numeric entity-encoded string
$convmap = array(0x0, 0x2FFFF, 0, 0xFFFF);
echo "1: " . mb_decode_numericentity($str1, $convmap, "UTF-8") . "\n";
echo "2: " . mb_decode_numericentity($str2, $convmap, "UTF-8") . "\n";
echo "3: " . mb_decode_numericentity($str3, $convmap, "UTF-8") . "\n";
// Numeric entities which are truncated at end of string
echo "4: " . mb_decode_numericentity('�', $convmap), "\n"; // Entity is too big
echo "5: " . mb_decode_numericentity('�', $convmap), "\n"; // Entity is too big
echo "6: " . mb_decode_numericentity('�', $convmap), "\n"; // Too many digits
echo "7: " . mb_decode_numericentity('�', $convmap), "\n"; // Too many digits
echo "8: " . mb_decode_numericentity('�', $convmap), "\n"; // Too many digits
echo "9: " . mb_decode_numericentity('�', $convmap), "\n"; // Too many digits
echo "10: " . bin2hex(mb_decode_numericentity('�', $convmap)), "\n"; // OK
echo "11: " . bin2hex(mb_decode_numericentity('�', $convmap)), "\n"; // OK
// Try with hex, not just decimal entities
echo "11b: " . bin2hex(mb_decode_numericentity('�', $convmap)), "\n"; // OK
echo "11c: " . bin2hex(mb_decode_numericentity('�', $convmap)), "\n"; // OK
echo "11d: " . bin2hex(mb_decode_numericentity('𐀀', $convmap)), "\n"; // OK
echo "11e: " . mb_decode_numericentity('�', $convmap), "\n"; // Too many digits
// Large decimal entity, converting from non-ASCII input encoding
echo "12: " . bin2hex(mb_decode_numericentity(mb_convert_encoding('�', 'UCS-4', 'ASCII'), [0, 0x7FFFFFFF, 0, 0x7FFFFFFF], 'UCS-4')), "\n";
$convmap = [];
echo "13: " . mb_decode_numericentity('föo', $convmap, "UTF-8") . "\n";
echo "15: " . bin2hex(mb_decode_numericentity('�', [0, 1, 0, 0xFFFF], 'UTF-8')) . "\n";
echo "16: " . bin2hex(mb_decode_numericentity('�', [0, 1, 0, 0xFFFF], 'UTF-8')) . "\n";
// Weird convmap
$convmap = [
0, 0, 0, 0, // Only one codepoint, empty mask
100, 50, 0, 0xFFFF // 'End' codepoint is before 'start' codepoint
];
echo "17: " . mb_decode_numericentity('föo', $convmap, "UTF-8") . "\n";
// Convmap with positive offset
$convmap = [0, 10, 1000, 0xFFFF];
echo "18: " . bin2hex(mb_decode_numericentity("ϩϪϫ", $convmap, "UTF-8")) . "\n";
echo "19: " . bin2hex(mb_decode_numericentity("ϩϪϫ", $convmap, "UTF-8")) . "\n";
echo "20: " . mb_decode_numericentity("{a;", [0, 0xFFFF, 0, 0xFFFF]) . "\n";
test("10 digits for decimal entity", "A", "A", [0, 0xFFFF, 0, 0xFFFF], 'ASCII');
test("More than 10 digits for decimal entity", "¥", "¥", [0, 0xFFFF, 0, 0xFFFF], 'ASCII');
test("8 digits for hex entity", "A", "A", [0, 0xFFFF, 0, 0xFFFF], 'ASCII');
test("More than 8 digits for hex entity", "Ł", "Ł", [0, 0xFFFF, 0, 0xFFFF], 'ASCII');
test("Single &", "&", "&", [0, 0xFFFF, 0, 0xFFFF], "ASCII");
// An entity can come right after a preceding ampersand
test("Successive &", "&A,", "&A,", [0, 0xFFFF, 0, 0xFFFF], 'ASCII');
// An entity can come right after a preceding &#
test("Successive &#", "&#2", "", [0, 0xFFFF, 0, 0xFFFF], 'ASCII');
test("Successive &#x", "&#x2", "", [0, 0xFFFF, 0, 0xFFFF], 'ASCII');
test("&#x only", "&#x;", "&#x;", [0, 0xFFFF, 0, 0xFFFF], 'ASCII');
// The starting & of an entity can terminate a preceding entity
test("Successive A", "AA", "AA", [0, 0xFFFF, 0, 0xFFFF], 'ASCII');
test("Successive hex entities", "22", "22", [0, 0xFFFF, 0, 0xFFFF], 'ASCII');
// An entity can come right after an entity which is invalid because of being too long
test("Starting entity immediately after decimal entity which is too long", "�A", "�A", [0, 0xFFFF, 0, 0xFFFF], 'ASCII');
test("Starting entity immediately after hex entity which is too long", "�A", "�", [0, 0xFFFF, 0, 0xFFFF], 'ASCII');
test("Starting entity immediately after invalid decimal entity", "�A", "�A", [0x1, 0xFFFF, 0, 0xFFFF], 'ASCII');
test("Starting entity immediately after invalid hex entity", "�A", "
", [0x1, 0xFFFF, 0, 0xFFFF], 'ASCII');
// Try with '&', '&#', or '&#' at the end of a buffer of wchars, with more input
// still left to process in the next buffer
// (mb_decode_numericentity splits its input into 'chunks' and processes it one
// chunk at a time)
$convmap = [0, 0xFFFF, 0, 0xFFFF];
for ($i = 0; $i < 256; $i++) {
$padding = str_repeat("a", $i);
// First try invalid decimal/hex entities
if (mb_decode_numericentity($padding . "&#ZZZ", $convmap, 'UTF-8') !== $padding . "&#ZZZ")
die("&#ZZZ is broken when it spans two buffers!");
if (mb_decode_numericentity($padding . "&#xZZZ", $convmap, 'UTF-8') !== $padding . "&#xZZZ")
die("&#xZZZ is broken when it spans two buffers!");
// Now try valid decimal/hex entities
if (mb_decode_numericentity($padding . "A", $convmap, 'UTF-8') !== $padding . "A")
die("A is broken when it spans two buffers!");
if (mb_decode_numericentity($padding . "A", $convmap, 'UTF-8') !== $padding . "A")
die("A is broken when it spans two buffers!");
}
// Try huge entities, big enough to fill an entire buffer
for ($i = 12; $i < 256; $i++) {
$str = "&#" . str_repeat("0", $i) . "65";
if (mb_decode_numericentity($str, $convmap, 'UTF-8') !== $str)
die("Decimal entity with huge number of digits broken");
$str = "&#x" . str_repeat("0", $i) . "41";
if (mb_decode_numericentity($str, $convmap, 'UTF-8') !== $str)
die("Hexadecimal entity with huge number of digits broken");
}
?>
--EXPECT--
1: ¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ
2: ƒΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩαβγδεζηθικλμνξοπρςστυφχψωϑϒϖ•…′″‾⁄℘ℑℜ™ℵ←↑→↓↔↵⇐⇑⇒⇓⇔∀∂∃∅∇∈∉∋∏∑−∗√∝∞∠∧∨∩∪∫∴∼≅≈≠≡≤≥⊂⊃⊄⊆⊇⊕⊗⊥⋅⌈⌉⌊⌋〈〉◊♠♣♥♦
3: aŒbœcŠdše€fg
4: �
5: �
6: �
7: �
8: �
9: �
10: 00
11: 00
11b: 00
11c: 00
11d: f0908080
11e: �
12: 00bc614e
13: föo
15: 00
16: 00
17: föo
18: 010203
19: 010203
20: {a;
10 digits for decimal entity: string(13) "A" => string(1) "A" (Good)
More than 10 digits for decimal entity: string(14) "¥" => string(14) "¥" (Good)
8 digits for hex entity: string(12) "A" => string(1) "A" (Good)
More than 8 digits for hex entity: string(13) "Ł" => string(13) "Ł" (Good)
Single &: string(1) "&" => string(1) "&" (Good)
Successive &: string(6) "&A," => string(3) "&A," (Good)
Successive &#: string(8) "&#2" => string(3) "" (Good)
Successive &#x: string(9) "&#x2" => string(4) "" (Good)
&#x only: string(4) "&#x;" => string(4) "&#x;" (Good)
Successive A: string(9) "AA" => string(2) "AA" (Good)
Successive hex entities: string(11) "22" => string(2) "22" (Good)
Starting entity immediately after decimal entity which is too long: string(18) "�A" => string(14) "�A" (Good)
Starting entity immediately after hex entity which is too long: string(17) "�A" => string(13) "�" (Good)
Starting entity immediately after invalid decimal entity: string(8) "�A" => string(4) "�A" (Good)
Starting entity immediately after invalid hex entity: string(9) "�A" => string(5) "
" (Good)
|
