fix(stats): stop counting duplicate typeset subtitle lines

- 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:
2026-08-10 23:18:43 -07:00
parent 7b0fbdf254
commit 684ab9eaff
31 changed files with 1586 additions and 30 deletions
+7
View File
@@ -162,6 +162,8 @@ export function createDefaultArgs(
statsCleanup: false,
statsCleanupVocab: false,
statsCleanupLifetime: false,
statsCleanupDuplicateLines: false,
statsCleanupDryRun: false,
doctor: false,
doctorRefreshKnownWords: false,
logsExport: false,
@@ -258,6 +260,11 @@ export function applyInvocationsToArgs(parsed: Args, invocations: CliInvocations
if (invocations.statsCleanup) parsed.statsCleanup = true;
if (invocations.statsCleanupVocab) parsed.statsCleanupVocab = true;
if (invocations.statsCleanupLifetime) parsed.statsCleanupLifetime = true;
if (invocations.statsCleanupDuplicateLines) parsed.statsCleanupDuplicateLines = true;
if (invocations.statsCleanupDryRun) parsed.statsCleanupDryRun = true;
if (invocations.statsCleanupLookbackDays !== null) {
parsed.statsCleanupLookbackDays = invocations.statsCleanupLookbackDays;
}
if (invocations.dictionaryTarget) {
parsed.dictionaryTarget = parseDictionaryTarget(invocations.dictionaryTarget);
} else if (