Anchor inline regexps and improve sub/super-script

The regexps are meant to extract a match immediately following the cursor - the
anchor should have been there from the beginning...

Also empty sub/superscript doesn't make sense - nested sub/superscript does
make sense but yagni.
This commit is contained in:
Niklas Fasching 2018-12-20 15:32:58 +01:00
parent ab9d87fbc8
commit d1054063cf
4 changed files with 12 additions and 8 deletions

View file

@ -35,13 +35,13 @@ type RegularLink struct {
}
var validURLCharacters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-._~:/?#[]@!$&'()*+,;="
var autolinkProtocols = regexp.MustCompile(`(https?|ftp|file)`)
var autolinkProtocols = regexp.MustCompile(`^(https?|ftp|file)$`)
var imageExtensionRegexp = regexp.MustCompile(`^[.](png|gif|jpe?g|svg|tiff?)$`)
var videoExtensionRegexp = regexp.MustCompile(`^[.](webm|mp4)$`)
var subScriptSuperScriptRegexp = regexp.MustCompile(`([_^])\{(.*?)\}`)
var footnoteRegexp = regexp.MustCompile(`\[fn:([\w-]+?)(:(.*?))?\]`)
var statisticsTokenRegexp = regexp.MustCompile(`\[(\d+/\d+|\d+%)\]`)
var subScriptSuperScriptRegexp = regexp.MustCompile(`^([_^]){([^{}]+?)}`)
var footnoteRegexp = regexp.MustCompile(`^\[fn:([\w-]+?)(:(.*?))?\]`)
var statisticsTokenRegexp = regexp.MustCompile(`^\[(\d+/\d+|\d+%)\]`)
func (d *Document) parseInline(input string) (nodes []Node) {
previous, current := 0, 0
@ -179,7 +179,11 @@ func (d *Document) parseAutoLink(input string, start int) (int, int, Node) {
return 0, 0, nil
}
protocolStart, protocol := start-1, ""
for ; protocolStart > 0 && unicode.IsLetter(rune(input[protocolStart])); protocolStart-- {
for ; protocolStart > 0; protocolStart-- {
if !unicode.IsLetter(rune(input[protocolStart])) {
protocolStart++
break
}
}
if m := autolinkProtocols.FindStringSubmatch(input[protocolStart:start]); m != nil {
protocol = m[1]