Canonical path adherence (#10)

Reviewed-on: https://gitea.westgate.pw/ShadowsOverWestgate/sow-tools/pulls/10
Co-authored-by: vickydotbat <vickydotbat@tutamail.com>
Co-committed-by: vickydotbat <vickydotbat@tutamail.com>

internal/topdata/wiki_slug.go

@@ -8,6 +8,59 @@ import (
 	"golang.org/x/text/unicode/norm"
 )
 
+func canonicalWikiSegment(value string) string {
+	value = html.UnescapeString(strings.TrimSpace(value))
+	var b strings.Builder
+	lastSeparator := false
+	for _, r := range norm.NFKD.String(value) {
+		transliterated := transliterateWikiSlugRune(unicode.ToLower(r))
+		switch {
+		case (r >= 'a' && r <= 'z') || (r >= 'A' && r <= 'Z') || (r >= '0' && r <= '9'):
+			b.WriteRune(r)
+			lastSeparator = false
+		case r == '_':
+			if b.Len() > 0 && !lastSeparator {
+				b.WriteRune(r)
+				lastSeparator = true
+			}
+		case unicode.Is(unicode.Mn, r):
+			continue
+		case isWikiSlugJoinerPunctuation(r):
+			continue
+		case transliterated != "":
+			b.WriteString(matchWikiTransliterationCase(r, transliterated))
+			lastSeparator = false
+		default:
+			if b.Len() > 0 && !lastSeparator {
+				b.WriteByte('_')
+				lastSeparator = true
+			}
+		}
+	}
+	return strings.Trim(b.String(), "_")
+}
+
+func matchWikiTransliterationCase(r rune, value string) string {
+	if unicode.IsUpper(r) {
+		if len(value) == 1 {
+			return strings.ToUpper(value)
+		}
+		return strings.ToUpper(value[:1]) + value[1:]
+	}
+	return value
+}
+
+func canonicalWikiPath(segments ...string) string {
+	out := []string{}
+	for _, segment := range segments {
+		canonical := canonicalWikiSegment(segment)
+		if canonical != "" {
+			out = append(out, canonical)
+		}
+	}
+	return strings.Join(out, "/")
+}
+
 func slugifyWikiText(value string, fallback string) string {
 	value = html.UnescapeString(strings.TrimSpace(value))
 	var b strings.Builder