add nultie gpouring

This commit is contained in:
Yevhen Odynets
2026-09-01 00:08:03 +03:00
parent 1b2521d4ac
commit 3f3598c446
9 changed files with 126 additions and 56 deletions
@@ -10,46 +10,57 @@ import (
)
type GroupStats struct {
Total int
YearDistribution map[int]int
SourceDistribution map[string]int
BitDepthDistribution map[string]int
Total int
YearDistribution map[int]int
SourceDistribution map[string]int
BitDepthDistribution map[string]int
ResolutionDistribution map[string]int
LanguageDistribution map[string]int
EditionDistribution map[string]int
UnknownTokens []releaseparser.UnknownTokenStats
AvgConfidence float64
LanguageDistribution map[string]int
EditionDistribution map[string]int
UnknownTokens []releaseparser.UnknownTokenStats
AvgConfidence float64
}
// AnalyzeGroup аналізує релізи з файлового ресурсу (для локальної перевірки довідників).
func AnalyzeGroup() (GroupStats, error) {
stats := GroupStats{
YearDistribution: make(map[int]int),
SourceDistribution: make(map[string]int),
BitDepthDistribution: make(map[string]int),
ResolutionDistribution: make(map[string]int),
LanguageDistribution: make(map[string]int),
EditionDistribution: make(map[string]int),
UnknownTokens: []releaseparser.UnknownTokenStats{},
}
file, err := os.Open("internal/releaseparser/resources/moonblood.txt")
file, err := os.Open("../../resources/moonblood.txt")
if err != nil {
return stats, err
return GroupStats{}, err
}
defer file.Close()
var titles []string
scanner := bufio.NewScanner(file)
totalConfidence := 0.0
unknownMap := make(map[string]*releaseparser.UnknownTokenStats)
for scanner.Scan() {
line := strings.TrimSpace(scanner.Text())
if line == "" {
continue
if line != "" {
titles = append(titles, line)
}
}
if err := scanner.Err(); err != nil {
return GroupStats{}, err
}
result := Parse(line)
return AnalyzeTitles(titles), nil
}
// AnalyzeTitles аналізує набір назв релізів (наприклад, з бази по ключу-групі).
func AnalyzeTitles(titles []string) GroupStats {
stats := GroupStats{
YearDistribution: make(map[int]int),
SourceDistribution: make(map[string]int),
BitDepthDistribution: make(map[string]int),
ResolutionDistribution: make(map[string]int),
LanguageDistribution: make(map[string]int),
EditionDistribution: make(map[string]int),
UnknownTokens: []releaseparser.UnknownTokenStats{},
}
totalConfidence := 0.0
unknownMap := make(map[string]*releaseparser.UnknownTokenStats)
for _, title := range titles {
result := Parse(title)
stats.Total++
if result.Year != 0 {
@@ -80,7 +91,7 @@ func AnalyzeGroup() (GroupStats, error) {
}
}
unknownMap[unknown].Count++
unknownMap[unknown].Releases = append(unknownMap[unknown].Releases, line)
unknownMap[unknown].Releases = append(unknownMap[unknown].Releases, title)
}
totalConfidence += result.Confidence
@@ -99,5 +110,5 @@ func AnalyzeGroup() (GroupStats, error) {
stats.AvgConfidence = totalConfidence / float64(stats.Total)
}
return stats, nil
return stats
}
@@ -17,4 +17,4 @@ LIMITED_EDITION_BOXSET
REMASTERED_EP
10TH_ANNIVERSARY_EDITION
OST
REISSUE_DEMO
REISSUE_DEMO
@@ -16,3 +16,4 @@ DK
AT
IS
UA
JP
@@ -1,6 +1,7 @@
# {resolution} — частота дискретизації
44KHZ
44.1KHZ
48KHZ
88.2KHZ
88KHZ
96KHZ
176KHZ
192KHZ
@@ -24,11 +24,8 @@ func Parse(raw string) releaseparser.ParsedRelease {
return result
}
// Останній токен — група
// Останній токен — група. Вона ж — ключ до профілю групи (довідників).
result.Group = tokens[len(tokens)-1]
if result.Group != "MOONBLOOD" {
result.Warnings = append(result.Warnings, "unexpected group")
}
// Передостанній — рік
last := len(tokens) - 2
@@ -139,7 +136,7 @@ func hasKnownTailToken(tokens []string) bool {
func score(result *releaseparser.ParsedRelease) {
score := 0.0
if result.Group == "MOONBLOOD" {
if result.Group != "" {
score += 0.25
}
if result.Year != 0 {
@@ -176,3 +176,26 @@ func TestParseCoreTokensNeverReported(t *testing.T) {
t.Errorf("Artist/Title = %q/%q", r.Artist, r.Title)
}
}
func TestParseAnyGroupNoWarning(t *testing.T) {
cases := []string{
"Jetsex-Down_Down_Down-24BIT-WEB-FLAC-2025-FLACCiD",
"Sabaton-The_Last_Stand-24BIT-96KHZ-WEB-FLAC-2016-FLACCiD",
"Wind_Walkers-What_If_I_Break-16BIT-WEB-FLAC-2023-FLACCiD",
}
for _, line := range cases {
r := Parse(line)
if r.Group != "FLACCiD" {
t.Errorf("%s: Group = %q, want FLACCiD", line, r.Group)
}
if len(r.Warnings) != 0 {
t.Errorf("%s: Warnings = %v, want empty", line, r.Warnings)
}
if len(r.UnknownTokens) != 0 {
t.Errorf("%s: UnknownTokens = %v, want empty", line, r.UnknownTokens)
}
if r.Year == 0 || r.Format != "FLAC" || r.Source != "WEB" || r.BitDepth == "" {
t.Errorf("%s: tail fields wrong: %+v", line, r)
}
}
}