bd33e8885e
Being able to very easily get the original [1] Org mode content seems like something that will come up quite often and is very little code. [1] it's not really the original content, but rather the pretty printed version of that - as the semantics don't change it shouldn't matter.
46 lines
1.3 KiB
Go
46 lines
1.3 KiB
Go
package org
|
|
|
|
import (
|
|
"regexp"
|
|
"strings"
|
|
)
|
|
|
|
type Paragraph struct{ Children []Node }
|
|
type HorizontalRule struct{}
|
|
|
|
var horizontalRuleRegexp = regexp.MustCompile(`^(\s*)-{5,}\s*$`)
|
|
var plainTextRegexp = regexp.MustCompile(`^(\s*)(.*)`)
|
|
|
|
func lexText(line string) (token, bool) {
|
|
if m := plainTextRegexp.FindStringSubmatch(line); m != nil {
|
|
return token{"text", len(m[1]), m[2], m}, true
|
|
}
|
|
return nilToken, false
|
|
}
|
|
|
|
func lexHorizontalRule(line string) (token, bool) {
|
|
if m := horizontalRuleRegexp.FindStringSubmatch(line); m != nil {
|
|
return token{"horizontalRule", len(m[1]), "", m}, true
|
|
}
|
|
return nilToken, false
|
|
}
|
|
|
|
func (d *Document) parseParagraph(i int, parentStop stopFn) (int, Node) {
|
|
lines, start := []string{d.tokens[i].content}, i
|
|
i++
|
|
stop := func(d *Document, i int) bool {
|
|
return parentStop(d, i) || d.tokens[i].kind != "text" || d.tokens[i].content == ""
|
|
}
|
|
for ; !stop(d, i); i++ {
|
|
lines = append(lines, d.tokens[i].content)
|
|
}
|
|
consumed := i - start
|
|
return consumed, Paragraph{d.parseInline(strings.Join(lines, "\n"))}
|
|
}
|
|
|
|
func (d *Document) parseHorizontalRule(i int, parentStop stopFn) (int, Node) {
|
|
return 1, HorizontalRule{}
|
|
}
|
|
|
|
func (n Paragraph) String() string { return orgWriter.nodesAsString(n) }
|
|
func (n HorizontalRule) String() string { return orgWriter.nodesAsString(n) }
|