From f2629f002c05631eba703f0b24a429413e57ad8e Mon Sep 17 00:00:00 2001
From: Yevhen Odynets <6lo5jp@proton.me>
Date: Tue, 1 Sep 2026 11:28:19 +0300
Subject: [PATCH] releaseparser: move group-agnostic parser to groups/, GB
 doc-blocks, per-group JSON reports
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Generalise the parser: the MOONBLOOD group profile is gone, the parser and
its dictionaries are now group-agnostic under internal/releaseparser/groups.

Positional model:
- [0]=Artist, [1]=Title are fixed and never matched against dictionaries, so
  titles like "Split"/"Demo"/"De" are never eaten.
- [len-1]=Group is always read from the line, not from the query key.
- [len-2]=Year when it is a 4-digit 19xx|20xx token; otherwise the slot is
  resolved as a middle-zone token (e.g. FLAC is still picked up as format).
- The middle zone is resolved via case-insensitive dictionaries in the order
  format -> source -> bit-depth -> resolution -> edition -> language ->
  catalogue number; stored values keep their original case.

Catalogue numbers: any "(...)" token in the middle zone is a catalogue number
regardless of content (digits, roman numerals, dots, underscores, mixed case);
splitting never breaks tokens inside parentheses.

Dictionaries moved to internal/releaseparser/groups/resources/dicts and
embedded via go:embed; dead profile fields (Name, ExpectedTailOrder) removed;
profile comments rewritten in British English.

File-based AnalyzeGroup/TestParseMoonblood removed — titles now come from the
database (cmd/srrdb: srrdb <releaser>..., config/secret.yaml DSN).

Validation output (cmd/srrdb):
- tmp/releaseparser/<group>.json         — per-group parsed ParsedRelease records
- tmp/releaseparser/<releaser>.report.json — per-request aggregate (same as console)
- review_unknown_tokens.txt              — unknown/warning rows for manual review

Tests updated for the positional model; added
TestParseCatalogNumberWithDotAndRoman for (DYN.3140-2) and (GOWP_DCCCLXXXIX).
go build, go vet and go test all pass.
---
 .gitignore                                    |  2 +-
 cmd/srrdb/main.go                             | 54 ++++++++++++--
 .../groups/{moonblood => }/analyzer.go        | 66 +++++++++--------
 .../groups/moonblood/dicts/bitdepth.txt       |  5 --
 .../groups/moonblood/dicts/comment.txt        |  6 --
 .../groups/moonblood/dicts/edition.txt        | 70 -------------------
 .../groups/moonblood/dicts/format.txt         |  3 -
 .../groups/moonblood/dicts/language.txt       | 38 ----------
 .../groups/moonblood/dicts/resolution.txt     |  8 ---
 .../groups/moonblood/dicts/source.txt         | 36 ----------
 .../releaseparser/groups/moonblood/profile.go | 42 -----------
 .../groups/{moonblood => }/parser.go          |  4 +-
 .../groups/{moonblood => }/parser_test.go     | 36 +---------
 internal/releaseparser/groups/profile.go      | 45 ++++++++++++
 internal/releaseparser/types.go               | 28 ++++----
 15 files changed, 150 insertions(+), 293 deletions(-)
 rename internal/releaseparser/groups/{moonblood => }/analyzer.go (76%)
 delete mode 100644 internal/releaseparser/groups/moonblood/dicts/bitdepth.txt
 delete mode 100644 internal/releaseparser/groups/moonblood/dicts/comment.txt
 delete mode 100644 internal/releaseparser/groups/moonblood/dicts/edition.txt
 delete mode 100644 internal/releaseparser/groups/moonblood/dicts/format.txt
 delete mode 100644 internal/releaseparser/groups/moonblood/dicts/language.txt
 delete mode 100644 internal/releaseparser/groups/moonblood/dicts/resolution.txt
 delete mode 100644 internal/releaseparser/groups/moonblood/dicts/source.txt
 delete mode 100644 internal/releaseparser/groups/moonblood/profile.go
 rename internal/releaseparser/groups/{moonblood => }/parser.go (99%)
 rename internal/releaseparser/groups/{moonblood => }/parser_test.go (94%)
 create mode 100644 internal/releaseparser/groups/profile.go

diff --git a/.gitignore b/.gitignore
index 86761c2..cc96208 100644
--- a/.gitignore
+++ b/.gitignore
@@ -14,7 +14,7 @@ vendor/
 config/secret.yaml
 *.md
 mdb
-internal/releaseparser/resources/*
+internal/releaseparser/groups/resources/*
 review_unknown_tokens.txt
 srrdb.exe
 **/*.exe
diff --git a/cmd/srrdb/main.go b/cmd/srrdb/main.go
index 3dea15b..ab24350 100644
--- a/cmd/srrdb/main.go
+++ b/cmd/srrdb/main.go
@@ -5,13 +5,15 @@ import (
 	"fmt"
 	"log"
 	"os"
+	"path/filepath"
+	"strings"
 
 	"github.com/jmoiron/sqlx"
 	"github.com/spf13/viper"
 
 	_ "github.com/go-sql-driver/mysql"
 
-	"git.kplus.net.ua/yevhen/resource-scraper/internal/releaseparser/groups/moonblood"
+	"git.kplus.net.ua/yevhen/resource-scraper/internal/releaseparser/groups"
 )
 
 func main() {
@@ -35,19 +37,33 @@ func main() {
 	}
 	defer dbase.Close()
 
-	out := make(map[string]moonblood.GroupStats, len(releasers))
+	const outDir = "tmp/releaseparser"
+	if err := os.MkdirAll(outDir, 0o755); err != nil {
+		log.Fatal(err)
+	}
+
+	out := make(map[string]groups.GroupStats, len(releasers))
 
 	for _, releaser := range releasers {
 		var titles []string
 
 		err = dbase.Select(&titles,
 			`SELECT title FROM theamok_mdb.external_sources
-			  WHERE type = 'prescene' AND releaser = ?`, releaser)
+			  WHERE type = 'prescene' AND releaser = ? limit 1000`, releaser)
 		if err != nil {
 			log.Fatal(err)
 		}
 
-		out[releaser] = moonblood.AnalyzeTitles(titles)
+		out[releaser] = groups.AnalyzeTitles(titles)
+
+		// Per-group parsed records keyed by the actual group read from each
+		// line: every release with all resolved fields for manual validation.
+		for group, parsed := range groups.ParseByGroup(titles) {
+			writeJSON(filepath.Join(outDir, safeName(group)+".json"), parsed)
+		}
+
+		// Per-request report identical to what is printed to the console.
+		writeJSON(filepath.Join(outDir, safeName(releaser)+".report.json"), out[releaser])
 	}
 
 	data, err := json.MarshalIndent(out, "", "  ")
@@ -77,3 +93,33 @@ func main() {
 
 	fmt.Println(string(data))
 }
+
+// writeJSON writes value as an indented JSON document to the given path.
+func writeJSON(path string, value any) {
+	data, err := json.MarshalIndent(value, "", "  ")
+	if err != nil {
+		log.Fatalf("marshal %s: %v", path, err)
+	}
+	if err := os.WriteFile(path, data, 0o644); err != nil {
+		log.Fatalf("write %s: %v", path, err)
+	}
+}
+
+// safeName strips characters that are unsafe in file names.
+func safeName(s string) string {
+	repl := func(r rune) rune {
+		switch {
+		case r >= 'a' && r <= 'z':
+			return r
+		case r >= 'A' && r <= 'Z':
+			return r
+		case r >= '0' && r <= '9':
+			return r
+		case r == '-' || r == '_' || r == '.':
+			return r
+		default:
+			return '_'
+		}
+	}
+	return strings.Map(repl, s)
+}
diff --git a/internal/releaseparser/groups/moonblood/analyzer.go b/internal/releaseparser/groups/analyzer.go
similarity index 76%
rename from internal/releaseparser/groups/moonblood/analyzer.go
rename to internal/releaseparser/groups/analyzer.go
index 15a420c..585e0a7 100644
--- a/internal/releaseparser/groups/moonblood/analyzer.go
+++ b/internal/releaseparser/groups/analyzer.go
@@ -1,8 +1,6 @@
-package moonblood
+package groups
 
 import (
-	"bufio"
-	"os"
 	"sort"
 	"strings"
 
@@ -12,6 +10,7 @@ import (
 // GroupStats summarises how a set of release lines parsed: field
 // distributions, unknown tokens and warnings aggregated by occurrence, and
 // the average parsing confidence. The slices are sorted by descending count.
+
 type GroupStats struct {
 	Total                  int
 	YearDistribution       map[int]int
@@ -26,34 +25,11 @@ type GroupStats struct {
 	AvgConfidence          float64
 }
 
-// AnalyzeGroup parses the release lines from the local resource file. It is
-// used for a quick local check of the dictionaries without touching a
-// database.
-func AnalyzeGroup() (GroupStats, error) {
-	file, err := os.Open("../../resources/moonblood.txt")
-	if err != nil {
-		return GroupStats{}, err
-	}
-	defer file.Close()
-
-	var titles []string
-	scanner := bufio.NewScanner(file)
-	for scanner.Scan() {
-		line := strings.TrimSpace(scanner.Text())
-		if line != "" {
-			titles = append(titles, line)
-		}
-	}
-	if err := scanner.Err(); err != nil {
-		return GroupStats{}, err
-	}
-
-	return AnalyzeTitles(titles), nil
-}
 
 // AnalyzeTitles parses a set of release lines (for example fetched from the
 // database by a particular releaser key) and aggregates the results into a
 // GroupStats summary.
+
 func AnalyzeTitles(titles []string) GroupStats {
 	stats := GroupStats{
 		YearDistribution:       make(map[int]int),
@@ -67,10 +43,12 @@ func AnalyzeTitles(titles []string) GroupStats {
 		WarningStats:           []releaseparser.UnknownTokenStats{},
 	}
 
+
 	totalConfidence := 0.0
 	unknownMap := make(map[string]*releaseparser.UnknownTokenStats)
 	warningMap := make(map[string]*releaseparser.UnknownTokenStats)
 
+
 	for _, title := range titles {
 		result := Parse(title)
 		stats.Total++
@@ -131,7 +109,6 @@ func AnalyzeTitles(titles []string) GroupStats {
 	for _, tokenStats := range unknownMap {
 		stats.UnknownTokens = append(stats.UnknownTokens, *tokenStats)
 	}
-
 	sort.Slice(stats.UnknownTokens, func(i, j int) bool {
 		return stats.UnknownTokens[i].Count > stats.UnknownTokens[j].Count
 	})
@@ -149,3 +126,36 @@ func AnalyzeTitles(titles []string) GroupStats {
 
 	return stats
 }
+
+
+// AnalyzeByGroup parses a set of release lines and returns per-group
+// statistics keyed by the actual group read from each line (not from the
+// query key, which may cover several groups). It is used to validate parsing
+// quality against the original data, grouped by the real releaser name.
+func AnalyzeByGroup(titles []string) map[string]GroupStats {
+	byGroup := make(map[string][]string)
+	for _, title := range titles {
+		group := Parse(title).Group
+		byGroup[group] = append(byGroup[group], title)
+	}
+
+	out := make(map[string]GroupStats, len(byGroup))
+	for group, lines := range byGroup {
+		out[group] = AnalyzeTitles(lines)
+	}
+	return out
+}
+
+
+// ParseByGroup parses a set of release lines into a per-group list of fully
+// populated ParsedRelease records, keyed by the actual group read from each
+// line. It is used to validate parsing quality field-by-field against the
+// original data.
+func ParseByGroup(titles []string) map[string][]releaseparser.ParsedRelease {
+	byGroup := make(map[string][]releaseparser.ParsedRelease)
+	for _, title := range titles {
+		result := Parse(title)
+		byGroup[result.Group] = append(byGroup[result.Group], result)
+	}
+	return byGroup
+}
diff --git a/internal/releaseparser/groups/moonblood/dicts/bitdepth.txt b/internal/releaseparser/groups/moonblood/dicts/bitdepth.txt
deleted file mode 100644
index 0c539ac..0000000
--- a/internal/releaseparser/groups/moonblood/dicts/bitdepth.txt
+++ /dev/null
@@ -1,5 +0,0 @@
-# {bit_depth}
-16BIT
-24BIT
-32BIT
-DE16BIT
diff --git a/internal/releaseparser/groups/moonblood/dicts/comment.txt b/internal/releaseparser/groups/moonblood/dicts/comment.txt
deleted file mode 100644
index 20e3f4c..0000000
--- a/internal/releaseparser/groups/moonblood/dicts/comment.txt
+++ /dev/null
@@ -1,6 +0,0 @@
-REPACK
-REAL_REPACK
-READNFO
-PROPER
-RERIP
-199X
\ No newline at end of file
diff --git a/internal/releaseparser/groups/moonblood/dicts/edition.txt b/internal/releaseparser/groups/moonblood/dicts/edition.txt
deleted file mode 100644
index c93f391..0000000
--- a/internal/releaseparser/groups/moonblood/dicts/edition.txt
+++ /dev/null
@@ -1,70 +0,0 @@
-# {edition} — тип видання
-EP
-DEMO
-SPLIT
-REISSUE
-DELUXE_EDITION
-REMASTERED
-BOXSET
-SINGLE
-PROMO
-REISSUE_REMASTERED
-REMASTERED_25TH_ANNIVERSARY_EDITION
-REMASTERED_20TH_ANNIVERSARY_EDITION
-20TH_ANNIVERSARY_EDITION_REMASTERED
-Deluxe_Edition
-LIMITED_EDITION_BOXSET
-REMASTERED_EP
-10TH_ANNIVERSARY_EDITION
-OST
-XX_Legacy_Edition
-REISSUE_DEMO
-JP_Deluxe_Edition
-Remastered_Edition
-Anniversary_Edition
-Limited_Edition
-CDS
-CDM
-RETAIL
-JP_RETAIL
-JP_REISSUE
-DEMO_REMASTERED
-EU_RETAIL
-DE_RETAIL
-REISSUE_DELUXE_EDITION
-RETAIL_REISSUE
-SPECIAL_EDITION
-SPECIAL_COLLECTORS_EDITION_REMASTERED
-30_YEARS_SPECIAL_COLLECTORS_EDITION_REMASTERED
-LIMITED_EDITION_REMASTERED
-25th_Anniversary_Edition
-DEMO_REISSUE
-Ultimate_Edition
-Issue_255
-Issue_254
-Issue_198
-7INCH_VINYL
-REMASTERED_REISSUE
-PROMO_DEMO
-ES_RETAIL
-BOX_SET
-BONUS
-REISSUE_EP
-30th_Anniversary
-REDUX
-REMASTERED_BOXSET
-MAG
-REISSUE_BOXSET
-30TH_ANNIVERSARY_EDITION_REMASTERED
-DELUXE
-Deluxe_Edition_Reissue
-INSTRUMENTAL
-REISSUE_EXPANDED_EDITION
-BOOTLEG
-EXPANDED_EDITION
-ADVANCE
-15TH_ANNIVERSARY_DELUXE_EDITION
-TOUR_EDITION
-REMASTERED_DEMO
-REMASTERED_DELUXE_EDITION
-30TH_ANNIVERSARY_EDITION
\ No newline at end of file
diff --git a/internal/releaseparser/groups/moonblood/dicts/format.txt b/internal/releaseparser/groups/moonblood/dicts/format.txt
deleted file mode 100644
index b7c21f2..0000000
--- a/internal/releaseparser/groups/moonblood/dicts/format.txt
+++ /dev/null
@@ -1,3 +0,0 @@
-# {format} — аудіоформат
-# один токен на рядок, регістр не має значення
-FLAC
diff --git a/internal/releaseparser/groups/moonblood/dicts/language.txt b/internal/releaseparser/groups/moonblood/dicts/language.txt
deleted file mode 100644
index 681f69e..0000000
--- a/internal/releaseparser/groups/moonblood/dicts/language.txt
+++ /dev/null
@@ -1,38 +0,0 @@
-# {language} — мовні маркери
-DE
-FR
-ES
-SK
-FI
-SE
-BR
-PL
-NL
-NO
-PT
-IT
-HU
-DK
-AT
-IS
-UA
-JP
-GR
-CN
-RU
-ID
-PH
-RO
-LT
-BY
-CZ
-SP
-IR
-FO
-RS
-DA
-HI
-CH
-LU
-CY
-EE
\ No newline at end of file
diff --git a/internal/releaseparser/groups/moonblood/dicts/resolution.txt b/internal/releaseparser/groups/moonblood/dicts/resolution.txt
deleted file mode 100644
index fda0157..0000000
--- a/internal/releaseparser/groups/moonblood/dicts/resolution.txt
+++ /dev/null
@@ -1,8 +0,0 @@
-# {resolution} — частота дискретизації
-44KHZ
-48KHZ
-48.0kHz
-88KHZ
-96KHZ
-176KHZ
-192KHZ
\ No newline at end of file
diff --git a/internal/releaseparser/groups/moonblood/dicts/source.txt b/internal/releaseparser/groups/moonblood/dicts/source.txt
deleted file mode 100644
index 3d16cd0..0000000
--- a/internal/releaseparser/groups/moonblood/dicts/source.txt
+++ /dev/null
@@ -1,36 +0,0 @@
-# {source} — джерело релізу
-# VINYL сюди входить як source (за домовленістю, не edition)
-WEB
-CD
-2CD
-CDEP
-VINYL
-TAPE
-CDR
-17CD
-3CD
-4CD
-18CD
-3CDEP
-DVD
-7CD
-2CDR
-10CD
-6CD
-2CDEP
-2VINYL
-CDREP
-LP
-2LP
-3VINYL
-3TAPE
-13CD
-13CDR
-10INCH_VINYL
-25CD
-WEBFLAC
-2TAPE
-BLURAY
-VLS
-MCD
-24BIT_WEB
\ No newline at end of file
diff --git a/internal/releaseparser/groups/moonblood/profile.go b/internal/releaseparser/groups/moonblood/profile.go
deleted file mode 100644
index 63babdc..0000000
--- a/internal/releaseparser/groups/moonblood/profile.go
+++ /dev/null
@@ -1,42 +0,0 @@
-package moonblood
-
-import (
-	"embed"
-	"strings"
-
-	"git.kplus.net.ua/yevhen/resource-scraper/internal/releaseparser"
-)
-
-// Словники токенів лежать у dicts/*.txt — один токен на рядок.
-// Їх можна редагувати без перекомпіляції логіки (embed тягне їх у бінарник на збірці).
-
-//go:embed dicts/*.txt
-var dictFS embed.FS
-
-func loadDict(name string) map[string]bool {
-	data, err := dictFS.ReadFile("dicts/" + name + ".txt")
-	if err != nil {
-		panic("moonblood: cannot load dictionary " + name + ": " + err.Error())
-	}
-	out := make(map[string]bool)
-	for _, line := range strings.Split(string(data), "\n") {
-		line = strings.ToUpper(strings.TrimSpace(line))
-		if line == "" || strings.HasPrefix(line, "#") {
-			continue
-		}
-		out[line] = true
-	}
-	return out
-}
-
-var Profile = releaseparser.GroupProfile{
-	Name:              "MOONBLOOD",
-	ExpectedTailOrder: []string{"bit_depth", "resolution", "source", "format", "year", "group"},
-	FormatTokens:      loadDict("format"),
-	SourceTokens:      loadDict("source"),
-	BitDepthTokens:    loadDict("bitdepth"),
-	ResolutionTokens:  loadDict("resolution"),
-	LanguageMarkers:   loadDict("language"),
-	EditionTokens:     loadDict("edition"),
-	CommentTokens:     loadDict("comment"),
-}
diff --git a/internal/releaseparser/groups/moonblood/parser.go b/internal/releaseparser/groups/parser.go
similarity index 99%
rename from internal/releaseparser/groups/moonblood/parser.go
rename to internal/releaseparser/groups/parser.go
index 63fdd8a..38b888b 100644
--- a/internal/releaseparser/groups/moonblood/parser.go
+++ b/internal/releaseparser/groups/parser.go
@@ -1,4 +1,4 @@
-package moonblood
+package groups
 
 import (
 	"regexp"
@@ -110,7 +110,7 @@ func split(raw string) []string {
 // list and returns the cleaned list together with the removed comments.
 func extractComments(tokens []string) ([]string, []string) {
 	out := make([]string, 0, len(tokens))
-	comments := []string{}
+	var comments []string
 	for _, tok := range tokens {
 		if Profile.CommentTokens[strings.ToUpper(tok)] {
 			comments = append(comments, tok)
diff --git a/internal/releaseparser/groups/moonblood/parser_test.go b/internal/releaseparser/groups/parser_test.go
similarity index 94%
rename from internal/releaseparser/groups/moonblood/parser_test.go
rename to internal/releaseparser/groups/parser_test.go
index bbbe1e2..7d12a76 100644
--- a/internal/releaseparser/groups/moonblood/parser_test.go
+++ b/internal/releaseparser/groups/parser_test.go
@@ -1,43 +1,9 @@
-package moonblood
+package groups
 
 import (
-	"bufio"
-	"os"
 	"testing"
 )
 
-func TestParseMoonblood(t *testing.T) {
-	file, err := os.Open("../../resources/moonblood.txt")
-	if err != nil {
-		t.Skipf("resource file not found (DB mode), skipping: %v", err)
-		t.Fatal(err)
-	}
-	defer file.Close()
-
-	scanner := bufio.NewScanner(file)
-	total, success := 0, 0
-
-	for scanner.Scan() {
-		line := scanner.Text()
-		if line == "" {
-			continue
-		}
-
-		result := Parse(line)
-		total++
-
-		if result.Group == "MOONBLOOD" && result.Year != 0 && result.Format == "FLAC" {
-			success++
-		}
-
-		if result.Confidence < 0.7 {
-			t.Logf("Low confidence: %s (%.2f)", line, result.Confidence)
-		}
-	}
-
-	t.Logf("Parsed %d releases, %d successful (%.1f%%)", total, success, float64(success)/float64(total)*100)
-}
-
 func TestParseFullTail(t *testing.T) {
 	r := Parse("Fane-Dragged_Through_the_Unending-24BIT-WEB-FLAC-2025-MOONBLOOD")
 	if r.Artist != "Fane" {
diff --git a/internal/releaseparser/groups/profile.go b/internal/releaseparser/groups/profile.go
new file mode 100644
index 0000000..1db32c1
--- /dev/null
+++ b/internal/releaseparser/groups/profile.go
@@ -0,0 +1,45 @@
+package groups
+
+import (
+	"embed"
+	"strings"
+
+	"git.kplus.net.ua/yevhen/resource-scraper/internal/releaseparser"
+)
+
+// The token dictionaries live under resources/dicts/*.txt — one token (in any
+// case) per line; blank lines and lines starting with "#" are ignored. They
+// can be edited without recompiling the parsing logic: go:embed pulls them
+// into the binary at build time.
+
+//go:embed resources/dicts/*.txt
+var dictFS embed.FS
+
+func loadDict(name string) map[string]bool {
+	data, err := dictFS.ReadFile("resources/dicts/" + name + ".txt")
+	if err != nil {
+		panic("release parser: cannot load dictionary " + name + ": " + err.Error())
+	}
+	out := make(map[string]bool)
+	for line := range strings.SplitSeq(string(data), "\n") {
+		line = strings.ToUpper(strings.TrimSpace(line))
+		if line == "" || strings.HasPrefix(line, "#") {
+			continue
+		}
+		out[line] = true
+	}
+	return out
+}
+
+// Profile holds the shared dictionaries for the release parser. The parser is
+// group-agnostic: the group name is read from each release line, never from
+// this profile, so there is a single set of dictionaries covering all groups.
+var Profile = releaseparser.GroupProfile{
+	FormatTokens:     loadDict("format"),
+	SourceTokens:     loadDict("source"),
+	BitDepthTokens:   loadDict("bitdepth"),
+	ResolutionTokens: loadDict("resolution"),
+	LanguageMarkers:  loadDict("language"),
+	EditionTokens:    loadDict("edition"),
+	CommentTokens:    loadDict("comment"),
+}
diff --git a/internal/releaseparser/types.go b/internal/releaseparser/types.go
index 21e0ecb..f15efa0 100644
--- a/internal/releaseparser/types.go
+++ b/internal/releaseparser/types.go
@@ -1,32 +1,30 @@
 package releaseparser
 
 type GroupProfile struct {
-	Name              string
-	ExpectedTailOrder []string
-	FormatTokens      map[string]bool
-	SourceTokens      map[string]bool
-	BitDepthTokens    map[string]bool
-	ResolutionTokens  map[string]bool
-	LanguageMarkers   map[string]bool
-	EditionTokens     map[string]bool
-	CommentTokens     map[string]bool
+	FormatTokens     map[string]bool
+	SourceTokens     map[string]bool
+	BitDepthTokens   map[string]bool
+	ResolutionTokens map[string]bool
+	LanguageMarkers  map[string]bool
+	EditionTokens    map[string]bool
+	CommentTokens    map[string]bool
 }
 
 type ParsedRelease struct {
 	Raw           string
 	Group         string
+	Artist        string
 	Year          int
+	Title         string
+	Source        string
+	Edition       string
+	CatalogNo     string
+	Language      string
 	BitDepth      string
 	Resolution    string
 	Comment       string
-	CatalogNo     string
-	Source        string
 	Format        string
-	Language      string
-	Edition       string
 	Core          string
-	Artist        string
-	Title         string
 	UnknownTokens []string
 	Warnings      []string
 	Confidence    float64