test(app): add content extraction edge case tests

Tests empty input, interleaved tags, malformed tags, unicode content, duplicate deduplication, place/TV extraction, tag stripping, magazine sections. 11 test cases. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-04 22:23:49 +00:00
parent c6e384a288
commit 5c82a09e65
1 changed files with 125 additions and 0 deletions
@@ -0,0 +1,125 @@
+import { describe, it, expect } from 'vitest'
+import {
+  extractAllFilms,
+  extractAllSongs,
+  extractAllBooks,
+  extractAllTVSeries,
+  extractAllPlaces,
+  extractAllImages,
+  extractMagazineSections,
+  stripContentTags,
+} from '../contentExtraction'
+
+// ─── Edge cases ──────────────────────────────────────────────────
+
+describe('contentExtraction edge cases', () => {
+  it('handles empty string', () => {
+    expect(extractAllFilms('')).toEqual([])
+    expect(extractAllSongs('', '')).toEqual([])
+    expect(extractAllBooks('', '')).toEqual([])
+    expect(extractAllTVSeries('', '')).toEqual([])
+    expect(extractAllPlaces('', '')).toEqual([])
+    expect(extractAllImages('', '')).toEqual([])
+    expect(extractMagazineSections('')).toEqual([])
+  })
+
+  it('handles text with no tags', () => {
+    const text = 'Just a regular response about movies and music.'
+    expect(extractAllFilms(text)).toEqual([])
+    expect(extractAllSongs(text, '')).toEqual([])
+  })
+
+  it('handles interleaved tags of different types', () => {
+    const text = `
+Here are some recommendations:
+[[film_ext:Inception|2010|Christopher Nolan]]
+Then a great song:
+[[song_ext:Bohemian Rhapsody|Queen|1975]]
+And a book:
+[[book_ext:Dune|Frank Herbert|1965]]
+`
+    const films = extractAllFilms(text)
+    const songs = extractAllSongs(text, '')
+    const books = extractAllBooks(text, '')
+    expect(films).toHaveLength(1)
+    expect(films[0].title).toBe('Inception')
+    expect(songs).toHaveLength(1)
+    expect(songs[0].title).toBe('Bohemian Rhapsody')
+    expect(books).toHaveLength(1)
+    expect(books[0].title).toBe('Dune')
+  })
+
+  it('handles malformed tags (missing fields)', () => {
+    // film_ext requires title|year|director — missing any means no match
+    expect(extractAllFilms('[[film_ext:Inception]]')).toHaveLength(0)
+    expect(extractAllFilms('[[film_ext:Inception|2010]]')).toHaveLength(0)
+
+    // All 3 fields present — matches
+    const films = extractAllFilms('[[film_ext:Inception|2010|Christopher Nolan]]')
+    expect(films).toHaveLength(1)
+    expect(films[0].title).toBe('Inception')
+  })
+
+  it('handles unicode content in tags', () => {
+    const text = '[[film_ext:千と千尋の神隠し|2001|宮崎駿]]'
+    const films = extractAllFilms(text)
+    expect(films).toHaveLength(1)
+    expect(films[0].title).toBe('千と千尋の神隠し')
+  })
+
+  it('handles tags with extra whitespace in pipe-separated values', () => {
+    // Regex captures include leading/trailing spaces in groups
+    // but the tag format requires no spaces around brackets
+    const text = '[[film_ext:Inception|2010|Christopher Nolan]]'
+    const films = extractAllFilms(text)
+    expect(films).toHaveLength(1)
+    expect(films[0].title).toBe('Inception')
+    expect(films[0].director).toBe('Christopher Nolan')
+  })
+
+  it('handles duplicate tags (same title)', () => {
+    const text = `
+[[film_ext:Inception|2010|Christopher Nolan]]
+[[film_ext:Inception|2010|Christopher Nolan]]
+`
+    const films = extractAllFilms(text)
+    // Should deduplicate
+    expect(films).toHaveLength(1)
+  })
+
+  it('handles place_ext with all fields', () => {
+    const text = '[[place_ext:Sushi Nakazawa|40.7258|-74.0030|Japanese|$$$$|New York]]'
+    const places = extractAllPlaces(text, '')
+    expect(places).toHaveLength(1)
+    expect(places[0].name).toBe('Sushi Nakazawa')
+  })
+
+  it('handles tv_ext tags', () => {
+    const text = '[[tv_ext:Breaking Bad|2008|Vince Gilligan]]'
+    const series = extractAllTVSeries(text, '')
+    expect(series).toHaveLength(1)
+    expect(series[0].title).toBe('Breaking Bad')
+  })
+
+  it('stripContentTags removes all tag types', () => {
+    const text = 'Watch [[film_ext:Inception|2010|Nolan]] and listen to [[song_ext:Song|Artist|2020]]'
+    const stripped = stripContentTags(text)
+    expect(stripped).not.toContain('[[')
+    expect(stripped).not.toContain(']]')
+    expect(stripped).toContain('Watch')
+    expect(stripped).toContain('and listen to')
+  })
+
+  it('handles magazine sections with bold markers', () => {
+    const text = `
+- **Bitcoin rallies**: Price surges 5% as ETF inflows hit record.
+- **Lightning Network growth**: Capacity doubles in Q1 2026.
+- **Mining difficulty**: New all-time high reached.
+`
+    const sections = extractMagazineSections(text)
+    expect(sections.length).toBeGreaterThanOrEqual(1)
+    // First section is a summary grouping the items
+    const titles = sections.map(s => s.title)
+    expect(titles.length).toBeGreaterThan(0)
+  })
+})