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
|
package ui
import (
"bytes"
"errors"
"io"
"strconv"
"strings"
"golang.org/x/net/html"
)
var tagsToAvoid = make(map[string]bool)
func init() {
tagsToAvoid["blockquote"] = true
tagsToAvoid["br"] = true
tagsToAvoid["cite"] = true
tagsToAvoid["em"] = true
tagsToAvoid["font"] = true
tagsToAvoid["p"] = true
tagsToAvoid["span"] = true
tagsToAvoid["strong"] = true
tagsToAvoid["a"] = true
tagsToAvoid["i"] = true
tagsToAvoid["b"] = true
tagsToAvoid["u"] = true
tagsToAvoid["img"] = true
}
// StripSomeHTML removes the most common html presentation tags from the text
func StripSomeHTML(msg []byte) (out []byte) {
z := html.NewTokenizer(bytes.NewReader(msg))
loop:
for {
tt := z.Next()
switch tt {
case html.TextToken:
out = append(out, z.Text()...)
case html.ErrorToken:
if err := z.Err(); err != nil && err != io.EOF {
out = msg
return
}
break loop
case html.StartTagToken, html.EndTagToken, html.SelfClosingTagToken:
raw := z.Raw()
name, _ := z.TagName()
if !tagsToAvoid[string(name)] {
out = append(out, raw...)
}
case html.CommentToken:
out = append(out, z.Raw()...)
case html.DoctypeToken:
out = append(out, z.Raw()...)
}
}
return
}
// StripHTML removes all html in the text
func StripHTML(msg []byte) (out []byte) {
z := html.NewTokenizer(bytes.NewReader(msg))
loop:
for {
tt := z.Next()
switch tt {
case html.TextToken:
out = append(out, z.Text()...)
case html.ErrorToken:
if err := z.Err(); err != nil && err != io.EOF {
out = msg
return
}
break loop
}
}
return
}
func EscapeAllHTMLTags(in string) string {
in = strings.Replace(in, "<", "<", -1)
in = strings.Replace(in, ">", ">", -1)
return in
}
var (
hexTable = "0123456789abcdef"
// NewLine contains a new line
NewLine = []byte{'\n'}
)
// EscapeNonASCII replaces tabs and other non-printable characters with a
// "\x01" form of hex escaping. It works on a byte-by-byte basis.
func EscapeNonASCII(in string) string {
escapes := 0
for i := 0; i < len(in); i++ {
if in[i] < 32 || in[i] > 126 || in[i] == '\\' {
escapes++
}
}
if escapes == 0 {
return in
}
out := make([]byte, 0, len(in)+3*escapes)
for i := 0; i < len(in); i++ {
if in[i] < 32 || in[i] > 126 || in[i] == '\\' {
out = append(out, '\\', 'x', hexTable[in[i]>>4], hexTable[in[i]&15])
} else {
out = append(out, in[i])
}
}
return string(out)
}
// UnescapeNonASCII undoes the transformation of escapeNonASCII.
func UnescapeNonASCII(in string) (string, error) {
needsUnescaping := false
for i := 0; i < len(in); i++ {
if in[i] == '\\' {
needsUnescaping = true
break
}
}
if !needsUnescaping {
return in, nil
}
out := make([]byte, 0, len(in))
for i := 0; i < len(in); i++ {
if in[i] == '\\' {
if len(in) <= i+3 {
return "", errors.New("truncated escape sequence at end: " + in)
}
if in[i+1] != 'x' {
return "", errors.New("escape sequence didn't start with \\x in: " + in)
}
v, err := strconv.ParseUint(in[i+2:i+4], 16, 8)
if err != nil {
return "", errors.New("failed to parse value in '" + in + "': " + err.Error())
}
out = append(out, byte(v))
i += 3
} else {
out = append(out, in[i])
}
}
return string(out), nil
}
|
