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
|
package commonmark
import (
"bytes"
"regexp"
"github.com/JohannesKaufmann/dom"
"github.com/JohannesKaufmann/html-to-markdown/v2/converter"
"github.com/JohannesKaufmann/html-to-markdown/v2/internal/textutils"
"github.com/JohannesKaufmann/html-to-markdown/v2/marker"
"golang.org/x/net/html"
)
// TODO: remove regex
var multipleSpacesR = regexp.MustCompile(` +`)
func (r *commonmark) setextUnderline(level int, width int) []byte {
line := "-"
if level == 1 {
line = "="
}
return bytes.Repeat([]byte(line), width)
}
func (r *commonmark) atxPrefix(level int) []byte {
return bytes.Repeat([]byte("#"), level)
}
func getHeadingLevel(name string) int {
switch name {
case "h1":
return 1
case "h2":
return 2
case "h3":
return 3
case "h4":
return 4
case "h5":
return 5
case "h6":
return 6
default:
return 6
}
}
func runeCount(chars []rune) (count int) {
for _, char := range chars {
if char == marker.MarkerEscaping {
continue
}
count++
}
return
}
func getUnderlineWidth(content []byte, minVal int) int {
var width int
parts := bytes.Split(content, []byte("\n"))
for _, part := range parts {
// Count how wide the line should be,
// while using RuneCount to correctly count ä, ö, ...
//
// TODO: optimize function w := utf8.RuneCount(part)
w := runeCount([]rune(string(part)))
if w > width {
width = w
}
}
// Technically the minimum value is only one character,
// but one dash could easily trigger a heading.
if width < minVal {
return minVal
}
return width
}
func escapePoundSignAtEnd(s []byte) []byte {
// -1 #
// -2 placeholder
// -3 maybe \
if s[len(s)-1] != '#' {
// We don't have a # at the end,
// so there is no work to do...
return s
}
if len(s) >= 3 && s[len(s)-3] == '\\' {
// It is already escaped,
// so there is no work to do...
return s
}
// Because we have a # at the end,
// we should manually force the escaping
// by overriding the placeholder.
s[len(s)-2] = '\\'
return s
}
func (c *commonmark) renderHeading(ctx converter.Context, w converter.Writer, n *html.Node) converter.RenderStatus {
// ctx = context.WithValue(ctx, "is_inside_heading", true)
level := getHeadingLevel(dom.NodeName(n))
var buf bytes.Buffer
ctx.RenderChildNodes(ctx, &buf, n)
content := buf.Bytes()
if len(bytes.TrimSpace(content)) == 0 {
return converter.RenderSuccess
}
if c.HeadingStyle == HeadingStyleSetext && level < 3 {
// Note: We don't want to use `TrimUnnecessaryHardLineBreaks` here,
// since `EscapeMultiLine` also takes care of newlines.
content = textutils.TrimConsecutiveNewlines(content)
content = textutils.EscapeMultiLine(content)
width := getUnderlineWidth(content, 3)
underline := c.setextUnderline(level, width)
w.WriteString("\n\n")
w.Write(content)
w.WriteRune('\n')
w.Write(underline)
w.WriteString("\n\n")
} else {
content = bytes.ReplaceAll(content, []byte("\n"), []byte(" "))
content = bytes.ReplaceAll(content, []byte("\r"), []byte(" "))
// Replace multiple spaces by one space.
content = multipleSpacesR.ReplaceAll(content, []byte(" "))
content = bytes.TrimSpace(content)
// A # sign at the end would be removed otherwise
content = escapePoundSignAtEnd(content)
w.WriteString("\n\n")
w.Write(c.atxPrefix(level))
w.WriteRune(' ')
w.Write(content)
w.WriteString("\n\n")
}
return converter.RenderSuccess
}
|
