Hashtag identifier & splitter.

hashtag.go

// Match tags in notes, etc.
// Group 1: Must start with whitespace OR start of string
// - : Must start with hash sign #
// Group 2: Match everything, until we reach a whitespace, '#' '.' ',' '!' ')'.
// Must be end of string
var matchTags = regexp.MustCompile(`[^\S]|^#([^\s#.,!)]+)$`)

// tagsSplitter returns true if the current rune is a tag ending
// Tags MUST end with whitespace, '.' ',' '!' or ')'
func tagsSplitter(c rune) bool {
	if unicode.IsSpace(c) {
		return true
	}
	switch c {
	case '.', ',', '!', ')':
		return true
	}
	return false
}

// getTags matches tags and returns them as an array of strings
//
// The hashtag itself is NOT included as part of the tag string
//
// The function should match the javascript regex: '/([^\S]|^)#([^\s#.,!)]+)(?![^\s.,!)])/g'.
// Since golang re2 engine does not have positive lookahead, the end of the tag is matched by splitting the input string.
// The 'tagsSplitter' function defines the end of a tag, and the 'matchTags' regex has a requirement that it must match the end of a string.
func getTags(s string) []string {
	res := make([]string, 0)
	fields := strings.FieldsFunc(s, tagsSplitter)
	for _, v := range fields {
		sub := matchTags.FindStringSubmatch(v)
		if len(sub) > 1 {
			res = append(res, sub[1])
		}
	}
	return res
}