31febb9f56
Parse releases with an explicit fixed positional model and document the whole logic in British English doc-blocks. 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 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. Position within the zone is irrelevant. Catalogue numbers: - Any "(...)" token in the middle zone is a catalogue number regardless of content (digits, roman numerals, dots, underscores, mixed case). Removed the hasDigit requirement and character whitelist that rejected real catalogues like (DYN.3140-2) and (GOWP_DCCCLXXXIX). - Splitting never breaks tokens inside parentheses. Case handling: lookups are case-insensitive; stored values keep their original case from the line. Documentation: replaced Ukrainian comments in parser.go and analyzer.go with British-English doc-blocks describing the model, tail resolution order, catalogue rule and confidence scoring. Tests: - Add TestParseCatalogNumberWithDotAndRoman for (DYN.3140-2)/(GOWP_DCCCLXXXIX). - Update case-insensitive, split-title, no-year and language expectations. - go build, go vet and go test all pass.
80 lines
1.9 KiB
Go
80 lines
1.9 KiB
Go
package main
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
"log"
|
|
"os"
|
|
|
|
"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"
|
|
)
|
|
|
|
func main() {
|
|
if len(os.Args) < 2 {
|
|
log.Fatal("usage: srrdb <releaser> [<releaser>...]")
|
|
}
|
|
releasers := os.Args[1:]
|
|
|
|
// Читаємо config/secret.yaml (без змісту в коді — тільки потрібні ключі)
|
|
viper.SetConfigFile("config/secret.yaml")
|
|
if err := viper.ReadInConfig(); err != nil {
|
|
log.Fatal("failed to read config/secret.yaml: ", err)
|
|
}
|
|
|
|
drv := viper.GetString("db.driver")
|
|
dsn := viper.GetString("db.data_source_name")
|
|
|
|
dbase, err := sqlx.Connect(drv, dsn)
|
|
if err != nil {
|
|
panic("Failed to connect to the database: " + err.Error())
|
|
}
|
|
defer dbase.Close()
|
|
|
|
out := make(map[string]moonblood.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)
|
|
if err != nil {
|
|
log.Fatal(err)
|
|
}
|
|
|
|
out[releaser] = moonblood.AnalyzeTitles(titles)
|
|
}
|
|
|
|
data, err := json.MarshalIndent(out, "", " ")
|
|
if err != nil {
|
|
log.Fatal(err)
|
|
}
|
|
|
|
// Ручна ревізія: всі невідомі токени — у файл для правки бази.
|
|
review, err := os.OpenFile("review_unknown_tokens.txt",
|
|
os.O_CREATE|os.O_WRONLY|os.O_APPEND, 0o644)
|
|
if err != nil {
|
|
log.Fatal(err)
|
|
}
|
|
defer review.Close()
|
|
for releaser, stats := range out {
|
|
for _, unk := range stats.UnknownTokens {
|
|
for _, rel := range unk.Releases {
|
|
fmt.Fprintf(review, "%s\t%s\t%s\n", releaser, unk.Token, rel)
|
|
}
|
|
}
|
|
for _, warn := range stats.WarningStats {
|
|
for _, rel := range warn.Releases {
|
|
fmt.Fprintf(review, "%s\tWARN\t%s\t%s\n", releaser, warn.Token, rel)
|
|
}
|
|
}
|
|
}
|
|
|
|
fmt.Println(string(data))
|
|
}
|