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
|
package parser
import (
"bytes"
"regexp"
"github.com/yuin/goldmark/ast"
"github.com/yuin/goldmark/text"
"github.com/yuin/goldmark/util"
)
type rawHTMLParser struct {
}
var defaultRawHTMLParser = &rawHTMLParser{}
// NewRawHTMLParser return a new InlineParser that can parse
// inline htmls.
func NewRawHTMLParser() InlineParser {
return defaultRawHTMLParser
}
func (s *rawHTMLParser) Trigger() []byte {
return []byte{'<'}
}
func (s *rawHTMLParser) Parse(parent ast.Node, block text.Reader, pc Context) ast.Node {
line, _ := block.PeekLine()
if len(line) > 1 && util.IsAlphaNumeric(line[1]) {
return s.parseMultiLineRegexp(openTagRegexp, block, pc)
}
if len(line) > 2 && line[1] == '/' && util.IsAlphaNumeric(line[2]) {
return s.parseMultiLineRegexp(closeTagRegexp, block, pc)
}
if bytes.HasPrefix(line, openComment) {
return s.parseComment(block, pc)
}
if bytes.HasPrefix(line, openProcessingInstruction) {
return s.parseUntil(block, closeProcessingInstruction, pc)
}
if len(line) > 2 && line[1] == '!' && line[2] >= 'A' && line[2] <= 'Z' {
return s.parseUntil(block, closeDecl, pc)
}
if bytes.HasPrefix(line, openCDATA) {
return s.parseUntil(block, closeCDATA, pc)
}
return nil
}
var tagnamePattern = `([A-Za-z][A-Za-z0-9-]*)`
var spaceOrOneNewline = `(?:[ \t]|(?:\r\n|\n){0,1})`
var attributePattern = `(?:[\r\n \t]+[a-zA-Z_:][a-zA-Z0-9:._-]*(?:[\r\n \t]*=[\r\n \t]*(?:[^\"'=<>` + "`" + `\x00-\x20]+|'[^']*'|"[^"]*"))?)` //nolint:golint,lll
var openTagRegexp = regexp.MustCompile("^<" + tagnamePattern + attributePattern + `*` + spaceOrOneNewline + `*/?>`)
var closeTagRegexp = regexp.MustCompile("^</" + tagnamePattern + spaceOrOneNewline + `*>`)
var openProcessingInstruction = []byte("<?")
var closeProcessingInstruction = []byte("?>")
var openCDATA = []byte("<![CDATA[")
var closeCDATA = []byte("]]>")
var closeDecl = []byte(">")
var emptyComment1 = []byte("<!-->")
var emptyComment2 = []byte("<!--->")
var openComment = []byte("<!--")
var closeComment = []byte("-->")
func (s *rawHTMLParser) parseComment(block text.Reader, pc Context) ast.Node {
savedLine, savedSegment := block.Position()
node := ast.NewRawHTML()
line, segment := block.PeekLine()
if bytes.HasPrefix(line, emptyComment1) {
node.Segments.Append(segment.WithStop(segment.Start + len(emptyComment1)))
block.Advance(len(emptyComment1))
return node
}
if bytes.HasPrefix(line, emptyComment2) {
node.Segments.Append(segment.WithStop(segment.Start + len(emptyComment2)))
block.Advance(len(emptyComment2))
return node
}
offset := len(openComment)
line = line[offset:]
for {
index := bytes.Index(line, closeComment)
if index > -1 {
node.Segments.Append(segment.WithStop(segment.Start + offset + index + len(closeComment)))
block.Advance(offset + index + len(closeComment))
return node
}
offset = 0
node.Segments.Append(segment)
block.AdvanceLine()
line, segment = block.PeekLine()
if line == nil {
break
}
}
block.SetPosition(savedLine, savedSegment)
return nil
}
func (s *rawHTMLParser) parseUntil(block text.Reader, closer []byte, pc Context) ast.Node {
savedLine, savedSegment := block.Position()
node := ast.NewRawHTML()
for {
line, segment := block.PeekLine()
if line == nil {
break
}
index := bytes.Index(line, closer)
if index > -1 {
node.Segments.Append(segment.WithStop(segment.Start + index + len(closer)))
block.Advance(index + len(closer))
return node
}
node.Segments.Append(segment)
block.AdvanceLine()
}
block.SetPosition(savedLine, savedSegment)
return nil
}
func (s *rawHTMLParser) parseMultiLineRegexp(reg *regexp.Regexp, block text.Reader, pc Context) ast.Node {
sline, ssegment := block.Position()
if block.Match(reg) {
node := ast.NewRawHTML()
eline, esegment := block.Position()
block.SetPosition(sline, ssegment)
for {
line, segment := block.PeekLine()
if line == nil {
break
}
l, _ := block.Position()
start := segment.Start
if l == sline {
start = ssegment.Start
}
end := segment.Stop
if l == eline {
end = esegment.Start
}
node.Segments.Append(text.NewSegment(start, end))
if l == eline {
block.Advance(end - start)
break
}
block.AdvanceLine()
}
return node
}
return nil
}
|
