fix: correct guessit title parsing for character dictionary sync

This commit is contained in:
2026-03-08 23:03:48 -07:00
parent 5e787183d0
commit 2127f759ca
4 changed files with 111 additions and 3 deletions

View File

@@ -0,0 +1,38 @@
---
id: TASK-140
title: Fix guessit title parsing for character dictionary sync
status: Done
assignee: []
created_date: '2026-03-09 00:00'
updated_date: '2026-03-09 00:25'
labels:
- dictionary
- anilist
- bug
- guessit
dependencies: []
references:
- /home/sudacode/projects/japanese/SubMiner/src/core/services/anilist/anilist-updater.ts
- /home/sudacode/projects/japanese/SubMiner/src/core/services/anilist/anilist-updater.test.ts
priority: high
---
## Description
<!-- SECTION:DESCRIPTION:BEGIN -->
Fix AniList character dictionary auto-sync for filenames where `guessit` misparses the full path and our title extraction keeps only the first array segment, causing AniList resolution to match the wrong anime and abort merged dictionary refresh.
<!-- SECTION:DESCRIPTION:END -->
## Acceptance Criteria
<!-- AC:BEGIN -->
- [x] #1 AniList media guessing passes basename-only targets to `guessit` so parent folder names do not corrupt series title detection.
- [x] #2 Guessit title arrays are combined into one usable title instead of truncating to the first segment.
- [x] #3 Regression coverage includes the Bunny Girl Senpai filename shape that previously resolved to the wrong AniList entry.
- [x] #4 Verification confirms the targeted AniList guessing tests pass.
<!-- AC:END -->
## Implementation Notes
<!-- SECTION:NOTES:BEGIN -->
Root repro: `guessit` parsed the Bunny Girl Senpai full path as `title: ["Rascal", "Does-not-Dream-of-Bunny-Girl-Senapi"]`, and our `firstString` helper kept only `Rascal`, which resolved to AniList 3490 (`rayca`) and produced zero character results. Fixed by sending basename-only input to `guessit` and joining multi-part guessit title arrays.
<!-- SECTION:NOTES:END -->

4
changes/task-140.md Normal file
View File

@@ -0,0 +1,4 @@
type: fixed
area: dictionary
- Fixed AniList media guessing for character dictionary auto-sync by using filename-only `guessit` input and preserving multi-part guessit titles instead of truncating them to the first segment.

View File

@@ -34,6 +34,44 @@ test('guessAnilistMediaInfo falls back to parser when guessit fails', async () =
});
});
test('guessAnilistMediaInfo uses basename for guessit input', async () => {
const mediaPath =
'/truenas/jellyfin/anime/Rascal-Does-not-Dream-of-Bunny-Girl-Senapi/Season-1/Rascal Does Not Dream of Bunny Girl Senpai (2018) - S01E01 - 001 - My Senpai Is a Bunny Girl [Bluray-1080p][10bit][x265][Opus 2.0][JA]-Subs.mkv';
const seenTargets: string[] = [];
const result = await guessAnilistMediaInfo(mediaPath, null, {
runGuessit: async (target) => {
seenTargets.push(target);
return JSON.stringify({
title: 'Rascal Does Not Dream of Bunny Girl Senpai',
episode: 1,
});
},
});
assert.deepEqual(seenTargets, [
'Rascal Does Not Dream of Bunny Girl Senpai (2018) - S01E01 - 001 - My Senpai Is a Bunny Girl [Bluray-1080p][10bit][x265][Opus 2.0][JA]-Subs.mkv',
]);
assert.deepEqual(result, {
title: 'Rascal Does Not Dream of Bunny Girl Senpai',
episode: 1,
source: 'guessit',
});
});
test('guessAnilistMediaInfo joins multi-part guessit titles', async () => {
const result = await guessAnilistMediaInfo('/tmp/demo.mkv', null, {
runGuessit: async () =>
JSON.stringify({
title: ['Rascal', 'Does-not-Dream-of-Bunny-Girl-Senpai'],
episode: 1,
}),
});
assert.deepEqual(result, {
title: 'Rascal Does not Dream of Bunny Girl Senpai',
episode: 1,
source: 'guessit',
});
});
test('updateAnilistPostWatchProgress updates progress when behind', async () => {
const originalFetch = globalThis.fetch;
let call = 0;

View File

@@ -1,4 +1,5 @@
import * as childProcess from 'child_process';
import * as path from 'path';
import { parseMediaInfo } from '../../../jimaku/utils';
@@ -90,6 +91,32 @@ function firstString(value: unknown): string | null {
return null;
}
function normalizeGuessitTitlePart(value: string): string {
return value
.replace(/[._]+/g, ' ')
.replace(/-/g, ' ')
.replace(/\s+/g, ' ')
.trim();
}
function readGuessitTitle(value: unknown): string | null {
if (typeof value === 'string') {
const normalized = normalizeGuessitTitlePart(value);
return normalized.length > 0 ? normalized : null;
}
if (Array.isArray(value)) {
const parts = value
.filter((item): item is string => typeof item === 'string')
.map((item) => normalizeGuessitTitlePart(item))
.filter((item) => item.length > 0);
if (parts.length === 0) {
return null;
}
return parts.join(' ').replace(/\s+/g, ' ').trim();
}
return null;
}
function firstPositiveInteger(value: unknown): number | null {
if (typeof value === 'number' && Number.isInteger(value) && value > 0) {
return value;
@@ -184,12 +211,13 @@ export async function guessAnilistMediaInfo(
deps: GuessAnilistMediaInfoDeps = { runGuessit },
): Promise<AnilistMediaGuess | null> {
const target = mediaPath ?? mediaTitle;
const guessitTarget = mediaPath ? path.basename(mediaPath) : mediaTitle;
if (target && target.trim().length > 0) {
if (guessitTarget && guessitTarget.trim().length > 0) {
try {
const stdout = await deps.runGuessit(target);
const stdout = await deps.runGuessit(guessitTarget);
const parsed = JSON.parse(stdout) as Record<string, unknown>;
const title = firstString(parsed.title);
const title = readGuessitTitle(parsed.title);
const episode = firstPositiveInteger(parsed.episode);
if (title) {
return { title, episode, source: 'guessit' };