sudacode/SubMiner
1
0
Fork 0
mirror of https://github.com/ksyasuda/SubMiner.git synced 2026-08-13 13:55:57 -07:00
Code Issues Packages Projects Releases Wiki Activity

fix(stats): stop counting duplicate typeset subtitle lines

Browse Source 
- Collapse animation-burst subtitle lines (karaoke OPs, animated signs) at ingest time using the same dedup rules the subtitle sidebar already applies, so repeated frames no longer flood "Top Repeated Words"
- Add retroactive cleanup for stats already affected: a "Duplicates" scanner/cleaner in the Vocabulary tab and `subminer stats cleanup --duplicate-lines` (`--dry-run`, `--lookback-days`) on the CLI
- Only subtitle lines and the vocabulary counts they feed are touched; watch time and lines-seen totals are left as recorded
This commit is contained in:
Kyle Yasuda
2026-08-10 23:18:43 -07:00
parent 7b0fbdf254
commit 684ab9eaff
31 changed files with 1586 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/cli/args.ts
+14 -1
View File
@@ -64,6 +64,9 @@ export interface CliArgs {
statsCleanup?: boolean;
statsCleanupVocab?: boolean;
statsCleanupLifetime?: boolean;
statsCleanupDuplicateLines?: boolean;
statsCleanupDryRun?: boolean;
statsCleanupLookbackDays?: number;
statsResponsePath?: string;
jellyfin: boolean;
jellyfinLogin: boolean;
@@ -167,6 +170,8 @@ export function parseArgs(argv: string[]): CliArgs {
statsCleanup: false,
statsCleanupVocab: false,
statsCleanupLifetime: false,
statsCleanupDuplicateLines: false,
statsCleanupDryRun: false,
jellyfin: false,
jellyfinLogin: false,
jellyfinLogout: false,
@@ -368,7 +373,15 @@ export function parseArgs(argv: string[]): CliArgs {
} else if (arg === '--stats-cleanup') args.statsCleanup = true;
else if (arg === '--stats-cleanup-vocab') args.statsCleanupVocab = true;
else if (arg === '--stats-cleanup-lifetime') args.statsCleanupLifetime = true;
else if (arg.startsWith('--stats-response-path=')) {
else if (arg === '--stats-cleanup-duplicate-lines') args.statsCleanupDuplicateLines = true;
else if (arg === '--stats-cleanup-dry-run') args.statsCleanupDryRun = true;
else if (arg.startsWith('--stats-cleanup-lookback-days=')) {
const value = Number(arg.split('=', 2)[1]);
if (Number.isFinite(value) && value > 0) args.statsCleanupLookbackDays = Math.floor(value);
} else if (arg === '--stats-cleanup-lookback-days') {
const value = Number(readValue(argv[i + 1]));
if (Number.isFinite(value) && value > 0) args.statsCleanupLookbackDays = Math.floor(value);
} else if (arg.startsWith('--stats-response-path=')) {
const value = arg.split('=', 2)[1];
if (value) args.statsResponsePath = value;
} else if (arg === '--stats-response-path') {