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
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
|
// Copyright 2018 The Hugo Authors. All rights reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package urlreplacers
import (
"bytes"
"io"
"unicode"
"unicode/utf8"
"github.com/gohugoio/hugo/transform"
)
type absurllexer struct {
// the source to absurlify
content []byte
// the target for the new absurlified content
w io.Writer
// path may be set to a "." relative path
path []byte
pos int // input position
start int // item start position
quotes [][]byte
}
type prefix struct {
disabled bool
b []byte
f func(l *absurllexer)
nextPos int
}
func (p *prefix) find(bs []byte, start int) bool {
if p.disabled {
return false
}
if p.nextPos == -1 {
idx := bytes.Index(bs[start:], p.b)
if idx == -1 {
p.disabled = true
// Find the closest match
return false
}
p.nextPos = start + idx + len(p.b)
}
return true
}
func newPrefixState() []*prefix {
return []*prefix{
{b: []byte("src="), f: checkCandidateBase},
{b: []byte("href="), f: checkCandidateBase},
{b: []byte("action="), f: checkCandidateBase},
{b: []byte("srcset="), f: checkCandidateSrcset},
}
}
func (l *absurllexer) emit() {
l.w.Write(l.content[l.start:l.pos])
l.start = l.pos
}
var (
relURLPrefix = []byte("/")
relURLPrefixLen = len(relURLPrefix)
)
func (l *absurllexer) consumeQuote() []byte {
for _, q := range l.quotes {
if bytes.HasPrefix(l.content[l.pos:], q) {
l.pos += len(q)
l.emit()
return q
}
}
return nil
}
// handle URLs in src and href.
func checkCandidateBase(l *absurllexer) {
l.consumeQuote()
if !bytes.HasPrefix(l.content[l.pos:], relURLPrefix) {
return
}
// check for schemaless URLs
posAfter := l.pos + relURLPrefixLen
if posAfter >= len(l.content) {
return
}
r, _ := utf8.DecodeRune(l.content[posAfter:])
if r == '/' {
// schemaless: skip
return
}
if l.pos > l.start {
l.emit()
}
l.pos += relURLPrefixLen
l.w.Write(l.path)
l.start = l.pos
}
func (l *absurllexer) posAfterURL(q []byte) int {
if len(q) > 0 {
// look for end quote
return bytes.Index(l.content[l.pos:], q)
}
return bytes.IndexFunc(l.content[l.pos:], func(r rune) bool {
return r == '>' || unicode.IsSpace(r)
})
}
// handle URLs in srcset.
func checkCandidateSrcset(l *absurllexer) {
q := l.consumeQuote()
if q == nil {
// srcset needs to be quoted.
return
}
// special case, not frequent (me think)
if !bytes.HasPrefix(l.content[l.pos:], relURLPrefix) {
return
}
// check for schemaless URLs
posAfter := l.pos + relURLPrefixLen
if posAfter >= len(l.content) {
return
}
r, _ := utf8.DecodeRune(l.content[posAfter:])
if r == '/' {
// schemaless: skip
return
}
posEnd := l.posAfterURL(q)
// safe guard
if posEnd < 0 || posEnd > 2000 {
return
}
if l.pos > l.start {
l.emit()
}
section := l.content[l.pos : l.pos+posEnd+1]
fields := bytes.Fields(section)
for i, f := range fields {
if f[0] == '/' {
l.w.Write(l.path)
l.w.Write(f[1:])
} else {
l.w.Write(f)
}
if i < len(fields)-1 {
l.w.Write([]byte(" "))
}
}
l.pos += len(section)
l.start = l.pos
}
// main loop
func (l *absurllexer) replace() {
contentLength := len(l.content)
prefixes := newPrefixState()
for {
if l.pos >= contentLength {
break
}
var match *prefix
for _, p := range prefixes {
if !p.find(l.content, l.pos) {
continue
}
if match == nil || p.nextPos < match.nextPos {
match = p
}
}
if match == nil {
// Done!
l.pos = contentLength
break
} else {
l.pos = match.nextPos
match.nextPos = -1
match.f(l)
}
}
// Done!
if l.pos > l.start {
l.emit()
}
}
func doReplace(path string, ct transform.FromTo, quotes [][]byte) {
lexer := &absurllexer{
content: ct.From().Bytes(),
w: ct.To(),
path: []byte(path),
quotes: quotes}
lexer.replace()
}
type absURLReplacer struct {
htmlQuotes [][]byte
xmlQuotes [][]byte
}
func newAbsURLReplacer() *absURLReplacer {
return &absURLReplacer{
htmlQuotes: [][]byte{[]byte("\""), []byte("'")},
xmlQuotes: [][]byte{[]byte("""), []byte("'")}}
}
func (au *absURLReplacer)
|