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
|
// Copyright 2011 Google Inc. All Rights Reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
// Author: jdtang@google.com (Jonathan Tang)
//
// GUnit char_ref tests. These are quick smoke tests, mostly to identify
// crashing bugs so that they can be fixed without having to debug
// multi-language tests. As such, they focus on coverage rather than
// completeness. For testing the full spec, use char_ref_py_tests, which share
// their testdata with the Python html5lib library.
#include "char_ref.h"
#include <stdio.h>
#include <string.h>
#include "gtest/gtest.h"
#include "test_utils.h"
#include "utf8.h"
namespace {
class CharRefTest : public GumboTest {
protected:
bool ConsumeCharRef(const char* input) {
return ConsumeCharRef(input, ' ', false);
}
bool ConsumeCharRef(
const char* input, int additional_allowed_char, bool is_in_attribute) {
text_ = input;
utf8iterator_init(&parser_, input, strlen(input), &iter_);
bool result = consume_char_ref(
&parser_, &iter_, additional_allowed_char, is_in_attribute, &output_);
fflush(stdout);
return result;
}
Utf8Iterator iter_;
OneOrTwoCodepoints output_;
};
TEST_F(CharRefTest, Whitespace) {
EXPECT_TRUE(ConsumeCharRef(" "));
EXPECT_EQ(kGumboNoChar, output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
}
TEST_F(CharRefTest, NumericHex) {
EXPECT_TRUE(ConsumeCharRef("ካ"));
EXPECT_EQ(0x12ab, output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
}
TEST_F(CharRefTest, NumericDecimal) {
EXPECT_TRUE(ConsumeCharRef("Ӓ"));
EXPECT_EQ(1234, output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
}
TEST_F(CharRefTest, NumericInvalidDigit) {
errors_are_expected_ = true;
EXPECT_FALSE(ConsumeCharRef("&#google"));
EXPECT_EQ(kGumboNoChar, output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
EXPECT_EQ('&', utf8iterator_current(&iter_));
}
TEST_F(CharRefTest, NumericNoSemicolon) {
errors_are_expected_ = true;
EXPECT_FALSE(ConsumeCharRef("Ӓgoogle"));
EXPECT_EQ(1234, output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
EXPECT_EQ('g', utf8iterator_current(&iter_));
}
TEST_F(CharRefTest, NumericReplacement) {
errors_are_expected_ = true;
EXPECT_FALSE(ConsumeCharRef("‚"));
// Low quotation mark character.
EXPECT_EQ(0x201A, output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
}
TEST_F(CharRefTest, NumericInvalid) {
errors_are_expected_ = true;
EXPECT_FALSE(ConsumeCharRef("�"));
EXPECT_EQ(0xFFFD, output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
}
TEST_F(CharRefTest, NumericUtfInvalid) {
errors_are_expected_ = true;
EXPECT_FALSE(ConsumeCharRef(""));
EXPECT_EQ(0x7, output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
}
TEST_F(CharRefTest, NamedReplacement) {
EXPECT_TRUE(ConsumeCharRef("<"));
EXPECT_EQ('<', output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
}
TEST_F(CharRefTest, NamedReplacementNoSemicolon) {
errors_are_expected_ = true;
EXPECT_FALSE(ConsumeCharRef(">"));
EXPECT_EQ('>', output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
}
TEST_F(CharRefTest, NamedReplacementWithInvalidUtf8) {
errors_are_expected_ = true;
EXPECT_TRUE(ConsumeCharRef("&\xc3\xa5"));
EXPECT_EQ(kGumboNoChar, output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
}
TEST_F(CharRefTest, NamedReplacementInvalid) {
errors_are_expected_ = true;
EXPECT_FALSE(ConsumeCharRef("&google;"));
EXPECT_EQ(kGumboNoChar, output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
EXPECT_EQ('&', utf8iterator_current(&iter_));
}
// TEST_F(CharRefTest, NamedReplacementInvalidNoSemicolon) {
// EXPECT_FALSE(ConsumeCharRef("&google"));
// EXPECT_EQ(kGumboNoChar, output_.first);
// EXPECT_EQ(kGumboNoChar, output_.second);
// EXPECT_EQ('&', utf8iterator_current(&iter_));
//}
TEST_F(CharRefTest, AdditionalAllowedChar) {
EXPECT_TRUE(ConsumeCharRef("&\"", '"', false));
EXPECT_EQ(kGumboNoChar, output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
EXPECT_EQ('&', utf8iterator_current(&iter_));
}
TEST_F(CharRefTest, InAttribute) {
EXPECT_TRUE(ConsumeCharRef("¬ed", ' ', true));
EXPECT_EQ(kGumboNoChar, output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
EXPECT_EQ('&', utf8iterator_current(&iter_));
}
TEST_F(CharRefTest, MultiChars) {
EXPECT_TRUE(ConsumeCharRef("⋵̸"));
EXPECT_EQ(0x22F5, output_.first);
EXPECT_EQ(0x0338, output_.second);
}
TEST_F(CharRefTest, CharAfter) {
EXPECT_TRUE(ConsumeCharRef("<x"));
EXPECT_EQ('<', output_.first);
EXPECT_EQ(kGumboNoChar, output_.second);
EXPECT_EQ('x', utf8iterator_current(&iter_));
}
} // namespace
|
