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.

org/inline.go

@@ -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]

org/testdata/inline.html

@@ -61,7 +61,7 @@ empty emphasis markers like ++ // __ and so on are ignored
 </li>
 <li>
 <p>
-subscript<sub>sub</sub> and superscript<sup>super</sup>
+use _{} for subscript<sub>sub</sub> and ^{} for superscript<sup>super</sup>
 </p>
 </li>
 <li>

org/testdata/inline.org

@@ -17,7 +17,7 @@
   is
   not emphasized/
 - empty emphasis markers like ++ // __ and so on are ignored
-- subscript_{sub} and superscript^{super}
+- use _{} for subscript_{sub} and ^{} for superscript^{super}
 - links
   1. regular link [[https://example.com]] link without description
   2. regular link [[https://example.com][example.com]] link with description

org/testdata/inline.pretty_org

@@ -17,7 +17,7 @@
   is
   not emphasized/
 - empty emphasis markers like ++ // __ and so on are ignored
-- subscript_{sub} and superscript^{super}
+- use _{} for subscript_{sub} and ^{} for superscript^{super}
 - links
   1. regular link [[https://example.com]] link without description
   2. regular link [[https://example.com][example.com]] link with description