feat: extract normalization into internal/normalize package

internal/musicbrainz/api.go

@@ -4,11 +4,9 @@ import (
 	"context"
 	"fmt"
 	"net/url"
-	"regexp"
-	"strings"
-	"unicode"
 
 	"naviwatcher/internal/database"
+	"naviwatcher/internal/normalize"
 )
 
 // excludedStatuses contains release-group statuses that should be filtered out.
@@ -26,14 +24,6 @@ var includedTypes = map[string]bool{
 	"Compilation": true,
 }
 
-// Precompiled regexes for NormalizeString — compiled once at package init.
-var (
-	bracketRe = regexp.MustCompile(`\[[^\]]*\]`)
-	parenRe   = regexp.MustCompile(`\([^)]*\)`)
-	yearRe    = regexp.MustCompile(`\b(1[0-9]{3}|2[0-9]{3})\b`)
-	spaceRe   = regexp.MustCompile(`\s+`)
-)
-
 // GetArtistReleaseGroups fetches all release groups for a given artist from MusicBrainz.
 // It queries the artist's release groups via the MusicBrainz Web Service API,
 // parses the XML response, and applies status and type filtering.
@@ -122,63 +112,18 @@ func IsTypeIncluded(releaseType string) bool {
 	return includedTypes[releaseType]
 }
 
-// NormalizeString normalizes a string for fuzzy matching by:
-//   - Converting to lowercase
-//   - Removing special characters (keeping only letters, digits, and spaces)
-//   - Removing years (4-digit numbers that look like years)
-//   - Removing bracketed keywords (e.g., [Deluxe], [Remastered])
-//   - Collapsing multiple spaces into one
-//   - Trimming leading/trailing whitespace
+// NormalizeString normalizes a string for fuzzy matching.
+// It delegates to the shared normalize package; see normalize.NormalizeString
+// for the full normalization contract.
 func NormalizeString(s string) string {
-	// Convert to lowercase
-	s = strings.ToLower(s)
-
-	// Remove bracketed content first (e.g., [Deluxe Edition], [Remastered 2020])
-	s = bracketRe.ReplaceAllString(s, "")
-
-	// Remove parenthesized content (e.g., (Deluxe), (Remastered))
-	s = parenRe.ReplaceAllString(s, "")
-
-	// Remove years (4-digit numbers between 1000-2999)
-	s = yearRe.ReplaceAllString(s, "")
-
-	// Replace common separators with spaces before stripping other special chars
-	s = strings.ReplaceAll(s, "-", " ")
-	s = strings.ReplaceAll(s, "_", " ")
-
-	// Keep only letters, digits, and spaces
-	var b strings.Builder
-	for _, r := range s {
-		if unicode.IsLetter(r) || unicode.IsDigit(r) || unicode.IsSpace(r) {
-			b.WriteRune(r)
-		}
-	}
-	s = b.String()
-
-	// Collapse multiple spaces
-	s = spaceRe.ReplaceAllString(s, " ")
-
-	// Trim
-	s = strings.TrimSpace(s)
-
-	return s
+	return normalize.NormalizeString(s)
 }
 
 // NormalizeArtistName normalizes an artist name for comparison.
-// It applies NormalizeString and additionally handles common prefixes.
+// It delegates to the shared normalize package; see
+// normalize.NormalizeArtistName for the full normalization contract.
 func NormalizeArtistName(name string) string {
-	name = NormalizeString(name)
-
-	// Remove common leading articles for better matching
-	prefixes := []string{"the ", "a ", "an "}
-	for _, prefix := range prefixes {
-		if strings.HasPrefix(name, prefix) {
-			name = strings.TrimPrefix(name, prefix)
-			break
-		}
-	}
-
-	return strings.TrimSpace(name)
+	return normalize.NormalizeArtistName(name)
 }
 
 // ToExternalRelease converts a ReleaseGroup to an ExternalRelease