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
|
package converter
import (
"unicode/utf8"
"github.com/JohannesKaufmann/html-to-markdown/v2/marker"
)
const (
actionKeep = iota
actionEscape = iota
)
// IMPORTANT: Only internally we assume it is only byte
var placeholderByte byte = marker.BytesMarkerEscaping[0]
func (conv *Converter) escapeContent(chars []byte) []byte {
if conv.escapeMode == EscapeModeDisabled {
return chars
}
newChars := make([]byte, 0, len(chars))
for index := 0; index < len(chars); index++ {
if chars[index] == '\u0000' {
// For security reasons, the Unicode character U+0000 must be replaced with the REPLACEMENT CHARACTER (U+FFFD).
newChars = append(newChars, []byte(string('\ufffd'))...)
continue
}
r, _ := utf8.DecodeRune(chars[index:])
isMarkdownChar := conv.checkIsEscapedChar(r)
if isMarkdownChar {
newChars = append(newChars, placeholderByte, chars[index])
} else {
newChars = append(newChars, chars[index])
}
}
return newChars
}
func (conv *Converter) unEscapeContent(chars []byte) []byte {
if conv.escapeMode == EscapeModeDisabled {
return chars
}
checkElements := func(index int) int {
for _, handler := range conv.getUnEscapeHandlers() {
if skip := handler.Value(chars, index); skip != -1 {
return skip
}
}
return -1
}
changes := make([]uint8, len(chars))
for index := 0; index < len(chars); index++ {
if chars[index] != placeholderByte {
continue
}
if index+1 >= len(chars) {
break
}
skip := checkElements(index + 1)
if skip == -1 {
continue
}
changes[index] = actionEscape
index += skip - 1
}
newChars := make([]byte, 0, len(chars))
for index, char := range chars {
if char != placeholderByte {
newChars = append(newChars, char)
continue
}
// What to do with this placeholder? Should we escape or not?
if changes[index] == actionEscape {
newChars = append(newChars, '\\')
}
}
return newChars
}
|
