fix(stats): stop counting duplicate typeset subtitle lines (#191)

launcher/commands/stats-command.ts

@@ -157,6 +157,15 @@ export async function runStatsCommand(
     if (args.statsCleanupLifetime) {
       forwarded.push('--stats-cleanup-lifetime');
     }
+    if (args.statsCleanupDuplicateLines) {
+      forwarded.push('--stats-cleanup-duplicate-lines');
+    }
+    if (args.statsCleanupDryRun) {
+      forwarded.push('--stats-cleanup-dry-run');
+    }
+    if (args.statsCleanupLookbackDays) {
+      forwarded.push('--stats-cleanup-lookback-days', String(args.statsCleanupLookbackDays));
+    }
     if (shouldForwardLogLevel(args.logLevel)) {
       forwarded.push('--log-level', args.logLevel);
     }

launcher/config/args-normalizer.test.ts

@@ -134,6 +134,9 @@ test('applyInvocationsToArgs maps config and jellyfin invocation state', () => {
     statsCleanup: false,
     statsCleanupVocab: false,
     statsCleanupLifetime: false,
+    statsCleanupDuplicateLines: false,
+    statsCleanupDryRun: false,
+    statsCleanupLookbackDays: null,
     statsLogLevel: null,
     syncTriggered: false,
     syncCliTokens: [],
@@ -185,6 +188,9 @@ test('applyInvocationsToArgs maps settings invocation to settings window', () =>
     statsCleanup: false,
     statsCleanupVocab: false,
     statsCleanupLifetime: false,
+    statsCleanupDuplicateLines: false,
+    statsCleanupDryRun: false,
+    statsCleanupLookbackDays: null,
     statsLogLevel: null,
     syncTriggered: false,
     syncCliTokens: [],
@@ -229,6 +235,9 @@ test('applyInvocationsToArgs fails when config invocation has no action', () =>
       statsCleanup: false,
       statsCleanupVocab: false,
       statsCleanupLifetime: false,
+      statsCleanupDuplicateLines: false,
+      statsCleanupDryRun: false,
+      statsCleanupLookbackDays: null,
       statsLogLevel: null,
       syncTriggered: false,
       syncCliTokens: [],
@@ -271,6 +280,9 @@ test('applyInvocationsToArgs maps texthooker browser-open request', () => {
     statsCleanup: false,
     statsCleanupVocab: false,
     statsCleanupLifetime: false,
+    statsCleanupDuplicateLines: false,
+    statsCleanupDryRun: false,
+    statsCleanupLookbackDays: null,
     statsLogLevel: null,
     syncTriggered: false,
     syncCliTokens: [],

launcher/config/args-normalizer.ts

@@ -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 (

launcher/config/cli-parser-builder.ts

@@ -37,6 +37,9 @@ export interface CliInvocations {
   statsCleanup: boolean;
   statsCleanupVocab: boolean;
   statsCleanupLifetime: boolean;
+  statsCleanupDuplicateLines: boolean;
+  statsCleanupDryRun: boolean;
+  statsCleanupLookbackDays: number | null;
   statsLogLevel: string | null;
   syncTriggered: boolean;
   syncCliTokens: string[];
@@ -53,6 +56,16 @@ export interface CliInvocations {
   texthookerOpenBrowser: boolean;
 }
 
+/** `--lookback-days` narrows the duplicate-line cleanup; fractions are floored. */
+function parseStatsLookbackDays(value: unknown): number | null {
+  if (typeof value !== 'string' && typeof value !== 'number') return null;
+  const days = Number(value);
+  if (!Number.isFinite(days) || days < 1) {
+    throw new Error('Stats --lookback-days must be at least one day.');
+  }
+  return Math.floor(days);
+}
+
 function applyRootOptions(program: Command): void {
   program
     .option(
@@ -169,6 +182,9 @@ export function parseCliPrograms(
   let statsCleanup = false;
   let statsCleanupVocab = false;
   let statsCleanupLifetime = false;
+  let statsCleanupDuplicateLines = false;
+  let statsCleanupDryRun = false;
+  let statsCleanupLookbackDays: number | null = null;
   let statsLogLevel: string | null = null;
   let syncTriggered = false;
   let syncCliTokens: string[] = [];
@@ -269,6 +285,9 @@ export function parseCliPrograms(
     .option('-s, --stop', 'Stop the background stats server')
     .option('-v, --vocab', 'Clean vocabulary rows in the stats database')
     .option('-l, --lifetime', 'Rebuild lifetime summary rows from retained data')
+    .option('-d, --duplicate-lines', 'Collapse repeated subtitle lines from typeset animations')
+    .option('--dry-run', 'Report what a cleanup would remove without changing anything')
+    .option('--lookback-days <days>', 'Only clean lines recorded in the last N days')
     .option('--log-level <level>', 'Log level')
     .action((action: string | undefined, options: Record<string, unknown>) => {
       statsTriggered = true;
@@ -289,13 +308,35 @@ export function parseCliPrograms(
       if (normalizedAction && (statsBackground || statsStop)) {
         throw new Error('Stats background and stop flags cannot be combined with stats actions.');
       }
-      if (normalizedAction !== 'cleanup' && (options.vocab === true || options.lifetime === true)) {
-        throw new Error('Stats --vocab and --lifetime flags require the cleanup action.');
+      if (
+        normalizedAction !== 'cleanup' &&
+        (options.vocab === true || options.lifetime === true || options.duplicateLines === true)
+      ) {
+        throw new Error(
+          'Stats --vocab, --lifetime and --duplicate-lines flags require the cleanup action.',
+        );
+      }
+      if (
+        options.duplicateLines !== true &&
+        (options.dryRun === true || options.lookbackDays !== undefined)
+      ) {
+        throw new Error('Stats --dry-run and --lookback-days require --duplicate-lines.');
       }
       if (normalizedAction === 'cleanup') {
         statsCleanup = true;
         statsCleanupLifetime = options.lifetime === true;
-        statsCleanupVocab = statsCleanupLifetime ? false : options.vocab !== false;
+        statsCleanupDuplicateLines = options.duplicateLines === true;
+        const explicitModeCount = [options.vocab, options.lifetime, options.duplicateLines].filter(
+          (value) => value === true,
+        ).length;
+        if (explicitModeCount > 1) {
+          throw new Error('Stats cleanup runs one mode at a time.');
+        }
+        // Vocabulary cleanup stays the default so `stats cleanup` keeps its old meaning.
+        statsCleanupVocab =
+          statsCleanupLifetime || statsCleanupDuplicateLines ? false : options.vocab !== false;
+        statsCleanupDryRun = options.dryRun === true;
+        statsCleanupLookbackDays = parseStatsLookbackDays(options.lookbackDays);
       } else if (normalizedAction === 'rebuild' || normalizedAction === 'backfill') {
         statsCleanup = true;
         statsCleanupLifetime = true;
@@ -483,6 +524,9 @@ export function parseCliPrograms(
       statsCleanup,
       statsCleanupVocab,
       statsCleanupLifetime,
+      statsCleanupDuplicateLines,
+      statsCleanupDryRun,
+      statsCleanupLookbackDays,
       statsLogLevel,
       syncTriggered,
       syncCliTokens,

launcher/parse-args.test.ts

@@ -232,6 +232,75 @@ test('parseArgs maps lifetime stats cleanup flag', () => {
   assert.equal(parsed.statsCleanupLifetime, true);
 });
 
+test('parseArgs maps duplicate-line stats cleanup flags', () => {
+  const parsed = parseArgs(
+    ['stats', 'cleanup', '--duplicate-lines', '--dry-run', '--lookback-days', '30'],
+    'subminer',
+    {},
+  );
+
+  assert.equal(parsed.statsCleanup, true);
+  assert.equal(parsed.statsCleanupVocab, false);
+  assert.equal(parsed.statsCleanupDuplicateLines, true);
+  assert.equal(parsed.statsCleanupDryRun, true);
+  assert.equal(parsed.statsCleanupLookbackDays, 30);
+
+  const fractional = parseArgs(
+    ['stats', 'cleanup', '--duplicate-lines', '--lookback-days', '1.5'],
+    'subminer',
+    {},
+  );
+  assert.equal(fractional.statsCleanupLookbackDays, 1);
+});
+
+test('parseArgs rejects duplicate-line flags without the duplicate-lines mode', () => {
+  const error = withProcessExitIntercept(() => {
+    parseArgs(['stats', 'cleanup', '--dry-run'], 'subminer', {});
+  });
+
+  assert.equal(error.code, 1);
+  assert.match(error.stderr, /--dry-run and --lookback-days require --duplicate-lines/);
+});
+
+test('parseArgs rejects an empty lookback value outside duplicate-line cleanup', () => {
+  const error = withProcessExitIntercept(() => {
+    parseArgs(['stats', '--lookback-days', ''], 'subminer', {});
+  });
+
+  assert.equal(error.code, 1);
+  assert.match(error.stderr, /--dry-run and --lookback-days require --duplicate-lines/);
+});
+
+test('parseArgs rejects combining explicit cleanup modes', () => {
+  for (const modes of [
+    ['--lifetime', '--duplicate-lines'],
+    ['--vocab', '--duplicate-lines'],
+    ['--vocab', '--lifetime'],
+  ]) {
+    const error = withProcessExitIntercept(() => {
+      parseArgs(['stats', 'cleanup', ...modes], 'subminer', {});
+    });
+
+    assert.equal(error.code, 1);
+    assert.match(error.stderr, /Stats cleanup runs one mode at a time/);
+  }
+});
+
+test('parseArgs rejects unusable lookback windows', () => {
+  for (const value of ['0', '0.5', '-5', 'soon']) {
+    const error = withProcessExitIntercept(() => {
+      parseArgs(
+        ['stats', 'cleanup', '--duplicate-lines', '--lookback-days', value],
+        'subminer',
+        {},
+      );
+    });
+
+    assert.equal(error.code, 1);
+    assert.match(error.stderr, /--lookback-days must be at least one day/);
+  }
+});
+
 test('parseArgs rejects cleanup-only stats flags without cleanup action', () => {
   const error = withProcessExitIntercept(() => {
     parseArgs(['stats', '--vocab'], 'subminer', {});
@@ -239,7 +308,10 @@ test('parseArgs rejects cleanup-only stats flags without cleanup action', () =>
 
   assert.equal(error.code, 1);
   assert.match(error.message, /exit:1/);
-  assert.match(error.stderr, /Stats --vocab and --lifetime flags require the cleanup action/);
+  assert.match(
+    error.stderr,
+    /Stats --vocab, --lifetime and --duplicate-lines flags require the cleanup action/,
+  );
 });
 
 test('parseArgs maps stats rebuild action to cleanup lifetime mode', () => {

launcher/types.ts

@@ -142,6 +142,9 @@ export interface Args {
   statsCleanup?: boolean;
   statsCleanupVocab?: boolean;
   statsCleanupLifetime?: boolean;
+  statsCleanupDuplicateLines?: boolean;
+  statsCleanupDryRun?: boolean;
+  statsCleanupLookbackDays?: number;
   dictionaryTarget?: string;
   doctor: boolean;
   doctorRefreshKnownWords: boolean;