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
|
package commonmark_test
import (
"testing"
"github.com/JohannesKaufmann/html-to-markdown/v2/converter"
"github.com/JohannesKaufmann/html-to-markdown/v2/plugin/base"
"github.com/JohannesKaufmann/html-to-markdown/v2/plugin/commonmark"
)
func TestNewCommonmarkPlugin_Italic(t *testing.T) {
const nonBreakingSpace = '\u00A0'
const zeroWidthSpace = '\u200b'
runs := []struct {
desc string
input string
expected string
}{
{
desc: "simple",
input: `<p><em>Text</em></p>`,
expected: `*Text*`,
},
{
desc: "normal text surrounded by italic",
input: `<em>Italic</em>Normal<em>Italic</em>`,
expected: `*Italic*Normal*Italic*`,
},
{
desc: "italic text surrounded by normal",
input: `Normal<em>Italic</em>Normal`,
expected: `Normal*Italic*Normal`,
},
{
desc: "with spaces inside",
input: `<p><em> Text </em></p>`,
expected: `*Text*`,
},
{
desc: "with delimiter inside",
input: `<p><em>*A*B*</em></p>`,
expected: `*\*A\*B\**`,
},
{
desc: "adjacent",
input: `<em>A</em><em>B</em> <em>C</em>`,
expected: `*AB* *C*`,
},
{
desc: "adjacent and lots of spaces",
input: `<em> A </em><em> B </em> <em> C </em>`,
expected: `*A B* *C*`,
},
{
desc: "nested",
input: `<em>A <em>B</em> C</em>`,
expected: `*A B C*`,
},
{
desc: "nested and lots of spaces",
input: `<em> A <em> B </em> C </em>`,
expected: `*A B C*`,
},
{
desc: "mixed nested 1",
input: `<em>A <strong>B</strong> C</em>`,
expected: `*A **B** C*`,
},
{
desc: "mixed nested 2",
input: `<strong>A <em>B</em> C</strong>`,
expected: `**A *B* C**`,
},
{
desc: "mixed different italic",
input: `<i>A<em>B</em>C</i>`,
expected: `*ABC*`,
},
{
desc: "next to each other in other containers",
input: `<div>
<em>A</em>
<article><em>B</em></article>
<em>C</em>
</div>`,
expected: "*A*\n\n*B*\n\n*C*",
},
// - - - - //
{
desc: "empty italic #1",
input: `before<i></i>after`,
expected: `beforeafter`,
},
{
desc: "empty italic #2",
input: `before<i> </i>after`,
expected: `before after`,
},
{
desc: "empty italic #3",
input: `before <i> </i> after`,
expected: `before after`,
},
{
desc: "italic with non-breaking-space",
input: `before<i>` + string(nonBreakingSpace) + `</i>after`,
expected: `before` + string(nonBreakingSpace) + `after`,
},
{
desc: "italic with zero-width-space",
input: `before<i>` + string(zeroWidthSpace) + `</i>after`,
expected: `before*` + string(zeroWidthSpace) + `*after`,
},
}
for _, run := range runs {
t.Run(run.desc, func(t *testing.T) {
conv := converter.NewConverter(
converter.WithPlugins(
base.NewBasePlugin(),
commonmark.NewCommonmarkPlugin(),
),
)
out, err := conv.ConvertString(run.input)
if err != nil {
t.Error(err)
}
if out != run.expected {
t.Errorf("expected %q but got %q", run.expected, out)
}
})
}
}
|
