mirror of
https://github.com/yuin/goldmark
synced 2025-03-04 23:04:52 +00:00
126 lines
3.3 KiB
Go
126 lines
3.3 KiB
Go
package parser
|
|
|
|
import (
|
|
"bytes"
|
|
"github.com/yuin/goldmark/ast"
|
|
"github.com/yuin/goldmark/text"
|
|
"github.com/yuin/goldmark/util"
|
|
"regexp"
|
|
)
|
|
|
|
type rawHTMLParser struct {
|
|
HTMLConfig
|
|
}
|
|
|
|
// NewRawHTMLParser return a new InlineParser that can parse
|
|
// inline htmls
|
|
func NewRawHTMLParser(opts ...HTMLOption) InlineParser {
|
|
p := &rawHTMLParser{}
|
|
for _, o := range opts {
|
|
o.SetHTMLOption(&p.HTMLConfig)
|
|
}
|
|
return p
|
|
}
|
|
|
|
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, []byte("<!--")) {
|
|
return s.parseMultiLineRegexp(commentRegexp, block, pc)
|
|
}
|
|
if bytes.HasPrefix(line, []byte("<?")) {
|
|
return s.parseSingleLineRegexp(processingInstructionRegexp, block, pc)
|
|
}
|
|
if len(line) > 2 && line[1] == '!' && line[2] >= 'A' && line[2] <= 'Z' {
|
|
return s.parseSingleLineRegexp(declRegexp, block, pc)
|
|
}
|
|
if bytes.HasPrefix(line, []byte("<![CDATA[")) {
|
|
return s.parseMultiLineRegexp(cdataRegexp, block, pc)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
var tagnamePattern = `([A-Za-z][A-Za-z0-9-]*)`
|
|
var attributePattern = `(?:\s+[a-zA-Z_:][a-zA-Z0-9:._-]*(?:\s*=\s*(?:[^\"'=<>` + "`" + `\x00-\x20]+|'[^']*'|"[^"]*"))?)`
|
|
var openTagRegexp = regexp.MustCompile("^<" + tagnamePattern + attributePattern + `*\s*/?>`)
|
|
var closeTagRegexp = regexp.MustCompile("^</" + tagnamePattern + `\s*>`)
|
|
var commentRegexp = regexp.MustCompile(`^<!---->|<!--(?:-?[^>-])(?:-?[^-])*-->`)
|
|
var processingInstructionRegexp = regexp.MustCompile(`^(?:<\?).*?(?:\?>)`)
|
|
var declRegexp = regexp.MustCompile(`^<![A-Z]+\s+[^>]*>`)
|
|
var cdataRegexp = regexp.MustCompile(`<!\[CDATA\[[\s\S]*?\]\]>`)
|
|
|
|
func (s *rawHTMLParser) parseSingleLineRegexp(reg *regexp.Regexp, block text.Reader, pc Context) ast.Node {
|
|
line, segment := block.PeekLine()
|
|
match := reg.FindSubmatchIndex(line)
|
|
if match == nil {
|
|
return nil
|
|
}
|
|
node := ast.NewRawHTML()
|
|
node.Segments.Append(segment.WithStop(segment.Start + match[1]))
|
|
block.Advance(match[1])
|
|
return node
|
|
}
|
|
|
|
var dummyMatch = [][]byte{}
|
|
|
|
func (s *rawHTMLParser) parseMultiLineRegexp(reg *regexp.Regexp, block text.Reader, pc Context) ast.Node {
|
|
sline, ssegment := block.Position()
|
|
var m [][]byte
|
|
if s.FilterTags != nil {
|
|
m = block.FindSubMatch(reg)
|
|
} else {
|
|
if block.Match(reg) {
|
|
m = dummyMatch
|
|
}
|
|
}
|
|
|
|
if m != nil {
|
|
if s.FilterTags != nil {
|
|
tagName := string(m[1])
|
|
if _, ok := s.FilterTags[tagName]; ok {
|
|
return nil
|
|
}
|
|
}
|
|
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
|
|
} else {
|
|
block.AdvanceLine()
|
|
}
|
|
}
|
|
return node
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func (s *rawHTMLParser) CloseBlock(parent ast.Node, pc Context) {
|
|
// nothing to do
|
|
}
|