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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
|
// Package xml minifies XML1.0 following the specifications at http://www.w3.org/TR/xml/.
package xml // import "github.com/tdewolff/minify/xml"
import (
"io"
"github.com/tdewolff/minify"
"github.com/tdewolff/parse"
"github.com/tdewolff/parse/xml"
)
var (
isBytes = []byte("=")
spaceBytes = []byte(" ")
voidBytes = []byte("/>")
)
////////////////////////////////////////////////////////////////
// DefaultMinifier is the default minifier.
var DefaultMinifier = &Minifier{}
// Minifier is an XML minifier.
type Minifier struct {
KeepWhitespace bool
}
// Minify minifies XML data, it reads from r and writes to w.
func Minify(m *minify.M, w io.Writer, r io.Reader, params map[string]string) error {
return DefaultMinifier.Minify(m, w, r, params)
}
// Minify minifies XML data, it reads from r and writes to w.
func (o *Minifier) Minify(m *minify.M, w io.Writer, r io.Reader, _ map[string]string) error {
omitSpace := true // on true the next text token must not start with a space
attrByteBuffer := make([]byte, 0, 64)
l := xml.NewLexer(r)
defer l.Restore()
tb := NewTokenBuffer(l)
for {
t := *tb.Shift()
if t.TokenType == xml.CDATAToken {
if text, useText := xml.EscapeCDATAVal(&attrByteBuffer, t.Text); useText {
t.TokenType = xml.TextToken
t.Data = text
}
}
switch t.TokenType {
case xml.ErrorToken:
if l.Err() == io.EOF {
return nil
}
return l.Err()
case xml.DOCTYPEToken:
if _, err := w.Write(t.Data); err != nil {
return err
}
case xml.CDATAToken:
if _, err := w.Write(t.Data); err != nil {
return err
}
if len(t.Text) > 0 && parse.IsWhitespace(t.Text[len(t.Text)-1]) {
omitSpace = true
}
case xml.TextToken:
t.Data = parse.ReplaceMultipleWhitespace(t.Data)
// whitespace removal; trim left
if omitSpace && (t.Data[0] == ' ' || t.Data[0] == '\n') {
t.Data = t.Data[1:]
}
// whitespace removal; trim right
omitSpace = false
if len(t.Data) == 0 {
omitSpace = true
} else if t.Data[len(t.Data)-1] == ' ' || t.Data[len(t.Data)-1] == '\n' {
omitSpace = true
i := 0
for {
next := tb.Peek(i)
// trim if EOF, text token with whitespace begin or block token
if next.TokenType == xml.ErrorToken {
t.Data = t.Data[:len(t.Data)-1]
omitSpace = false
break
} else if next.TokenType == xml.TextToken {
// this only happens when a comment, doctype, cdata startpi tag was in between
// remove if the text token starts with a whitespace
if len(next.Data) > 0 && parse.IsWhitespace(next.Data[0]) {
t.Data = t.Data[:len(t.Data)-1]
omitSpace = false
}
break
} else if next.TokenType == xml.CDATAToken {
if len(next.Text) > 0 && parse.IsWhitespace(next.Text[0]) {
t.Data = t.Data[:len(t.Data)-1]
omitSpace = false
}
break
} else if next.TokenType == xml.StartTagToken || next.TokenType == xml.EndTagToken {
if !o.KeepWhitespace {
t.Data = t.Data[:len(t.Data)-1]
omitSpace = false
}
break
}
i++
}
}
if _, err := w.Write(t.Data); err != nil {
return err
}
case xml.StartTagToken:
if o.KeepWhitespace {
omitSpace = false
}
if _, err := w.Write(t.Data); err != nil {
return err
}
case xml.StartTagPIToken:
if _, err := w.Write(t.Data); err != nil {
return err
}
case xml.AttributeToken:
if _, err := w.Write(spaceBytes); err != nil {
return err
}
if _, err := w.Write(t.Text); err != nil {
return err
}
if _, err := w.Write(isBytes); err != nil {
return err
}
if len(t.AttrVal) < 2 {
if _, err := w.Write(t.AttrVal); err != nil {
return err
}
} else {
// prefer single or double quotes depending on what occurs more often in value
val := xml.EscapeAttrVal(&attrByteBuffer, t.AttrVal[1:len(t.AttrVal)-1])
if _, err := w.Write(val); err != nil {
return err
}
}
case xml.StartTagCloseToken:
next := tb.Peek(0)
skipExtra := false
if next.TokenType == xml.TextToken && parse.IsAllWhitespace(next.Data) {
next = tb.Peek(1)
skipExtra = true
}
if next.TokenType == xml.EndTagToken {
// collapse empty tags to single void tag
tb.Shift()
if skipExtra {
tb.Shift()
}
if _, err := w.Write(voidBytes); err != nil {
return err
}
} else {
if _, err := w.Write(t.Text); err != nil {
return err
}
}
case xml.StartTagCloseVoidToken:
if _, err := w.Write(t.Text); err != nil {
return err
}
case xml.StartTagClosePIToken:
if _, err := w.Write(t.Text); err != nil {
return err
}
case xml.EndTagToken:
if o.KeepWhitespace {
omitSpace = false
}
if len(t.Data) > 3+len(t.Text) {
t.Data[2+len(t.Text)] = '>'
t.Data = t.Data[:3+len(t.Text)]
}
if _, err := w.Write(t.Data); err != nil {
return err
}
}
}
}
|
