src/html/escape_test.go


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

// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

package html

import (
	"strings"
	"testing"
)

type unescapeTest struct {
	// A short description of the test case.
	desc string
	// The HTML text.
	html string
	// The unescaped text.
	unescaped string
}

var unescapeTests = []unescapeTest{
	// Handle no entities.
	{
		"copy",
		"A\ttext\nstring",
		"A\ttext\nstring",
	},
	// Handle simple named entities.
	{
		"simple",
		"&amp; &gt; &lt;",
		"& > <",
	},
	// Handle hitting the end of the string.
	{
		"stringEnd",
		"&amp &amp",
		"& &",
	},
	// Handle entities with two codepoints.
	{
		"multiCodepoint",
		"text &gesl; blah",
		"text \u22db\ufe00 blah",
	},
	// Handle decimal numeric entities.
	{
		"decimalEntity",
		"Delta = &#916; ",
		"Delta = Δ ",
	},
	// Handle hexadecimal numeric entities.
	{
		"hexadecimalEntity",
		"Lambda = &#x3bb; = &#X3Bb ",
		"Lambda = λ = λ ",
	},
	// Handle numeric early termination.
	{
		"numericEnds",
		"&# &#x &#128;43 &copy = &#169f = &#xa9",
		"&# &#x €43 © = ©f = ©",
	},
	// Handle numeric ISO-8859-1 entity replacements.
	{
		"numericReplacements",
		"Footnote&#x87;",
		"Footnote‡",
	},
	// Handle single ampersand.
	{
		"copySingleAmpersand",
		"&",
		"&",
	},
	// Handle ampersand followed by non-entity.
	{
		"copyAmpersandNonEntity",
		"text &test",
		"text &test",
	},
	// Handle "&#".
	{
		"copyAmpersandHash",
		"text &#",
		"text &#",
	},
}

func TestUnescape(t *testing.T) {
	for _, tt := range unescapeTests {
		unescaped := UnescapeString(tt.html)
		if unescaped != tt.unescaped {
			t.Errorf("TestUnescape %s: want %q, got %q", tt.desc, tt.unescaped, unescaped)
		}
	}
}

func TestUnescapeEscape(t *testing.T) {
	ss := []string{
		``,
		`abc def`,
		`a & b`,
		`a&amp;b`,
		`a &amp b`,
		`&quot;`,
		`"`,
		`"<&>"`,
		`&quot;&lt;&amp;&gt;&quot;`,
		`3&5==1 && 0<1, "0&lt;1", a+acute=&aacute;`,
		`The special characters are: <, >, &, ' and "`,
	}
	for _, s := range ss {
		if got := UnescapeString(EscapeString(s)); got != s {
			t.Errorf("got %q want %q", got, s)
		}
	}
}

var (
	benchEscapeData     = strings.Repeat("AAAAA < BBBBB > CCCCC & DDDDD ' EEEEE \" ", 100)
	benchEscapeNone     = strings.Repeat("AAAAA x BBBBB x CCCCC x DDDDD x EEEEE x ", 100)
	benchUnescapeSparse = strings.Repeat(strings.Repeat("AAAAA x BBBBB x CCCCC x DDDDD x EEEEE x ", 10)+"&amp;", 10)
	benchUnescapeDense  = strings.Repeat("&amp;&lt; &amp; &lt;", 100)
)

func BenchmarkEscape(b *testing.B) {
	n := 0
	for i := 0; i < b.N; i++ {
		n += len(EscapeString(benchEscapeData))
	}
}

func BenchmarkEscapeNone(b *testing.B) {
	n := 0
	for i := 0; i < b.N; i++ {
		n += len(EscapeString(benchEscapeNone))
	}
}

func BenchmarkUnescape(b *testing.B) {
	s := EscapeString(benchEscapeData)
	n := 0
	for i := 0; i < b.N; i++ {
		n += len(UnescapeString(s))
	}
}

func BenchmarkUnescapeNone(b *testing.B) {
	s := EscapeString(benchEscapeNone)
	n := 0
	for i := 0; i < b.N; i++ {
		n += len(UnescapeString(s))
	}
}

func BenchmarkUnescapeSparse(b *testing.B) {
	n := 0
	for i := 0; i < b.N; i++ {
		n += len(UnescapeString(benchUnescapeSparse))
	}
}

func BenchmarkUnescapeDense(b *testing.B) {
	n := 0
	for i := 0; i < b.N; i++ {
		n += len(UnescapeString(benchUnescapeDense))
	}
}