fix(txt): parse author from txt filename and use edited metadata on fallback cover (#4095) (#4102)

When importing a `.txt` file the author field stayed empty unless the
text content itself contained an `作者：…` header, even when the filename
already encoded it. Common Chinese naming patterns like `《书名》作者：张三.txt`,
`《书名》[张三].txt`, or `《书名》张三.txt` now contribute the author when
the file body doesn't.

- Added `extractTxtFilenameMetadata` in `utils/txt.ts` and replaced the
  ad-hoc `extractBookTitle` regex used by both convertSmallFile and
  convertLargeFile. Content-extracted author still wins; the filename
  author is the next fallback before the caller-provided one.
- `BookCover` now reads `book.author || book.metadata?.author` so the
  author typed into the metadata edit dialog shows on auto-generated
  fallback covers when the original `book.author` was empty.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

apps/readest-app/src/__tests__/components/BookCover.test.tsx

@@ -38,4 +38,15 @@ describe('BookCover', () => {
     expect(img).toBeTruthy();
     expect(img?.getAttribute('loading')).toBe('lazy');
   });
+
+  it('falls back to metadata.author on the fallback cover when book.author is empty', () => {
+    const book = makeBook({
+      author: '',
+      coverImageUrl: undefined,
+      metadata: { author: 'Edited Author' } as Book['metadata'],
+    });
+    const { container } = render(<BookCover book={book} coverFit='crop' />);
+    const fallback = container.querySelector('.fallback-cover');
+    expect(fallback?.textContent).toContain('Edited Author');
+  });
 });

apps/readest-app/src/__tests__/utils/txt-converter.test.ts

@@ -1,7 +1,7 @@
 // @vitest-environment node
 import { describe, expect, it } from 'vitest';
 
-import { TxtToEpubConverter } from '@/utils/txt';
+import { TxtToEpubConverter, extractTxtFilenameMetadata } from '@/utils/txt';
 
 type TestChapter = {
   title: string;
@@ -345,3 +345,71 @@ describe('TxtToEpubConverter', () => {
     expect(cancelled).toBe(true);
   });
 });
+
+describe('extractTxtFilenameMetadata', () => {
+  it('extracts the title from CJK 《》 brackets', () => {
+    expect(extractTxtFilenameMetadata('《三体》.txt')).toEqual({ title: '三体' });
+  });
+
+  it('extracts title and labeled author with full-width colon', () => {
+    expect(extractTxtFilenameMetadata('《书名》作者:张三.txt')).toEqual({
+      title: '书名',
+      author: '张三',
+    });
+    expect(extractTxtFilenameMetadata('《书名》作者：张三.txt')).toEqual({
+      title: '书名',
+      author: '张三',
+    });
+  });
+
+  it('extracts title and labeled author with leading whitespace', () => {
+    expect(extractTxtFilenameMetadata('《书名》 作者：张三.txt')).toEqual({
+      title: '书名',
+      author: '张三',
+    });
+  });
+
+  it('extracts title and bracketed author after the title', () => {
+    expect(extractTxtFilenameMetadata('《书名》[张三].txt')).toEqual({
+      title: '书名',
+      author: '张三',
+    });
+    expect(extractTxtFilenameMetadata('《书名》(张三).txt')).toEqual({
+      title: '书名',
+      author: '张三',
+    });
+    expect(extractTxtFilenameMetadata('《书名》【张三】.txt')).toEqual({
+      title: '书名',
+      author: '张三',
+    });
+  });
+
+  it('extracts title and bare author after the title', () => {
+    expect(extractTxtFilenameMetadata('《书名》张三.txt')).toEqual({
+      title: '书名',
+      author: '张三',
+    });
+  });
+
+  it('strips leading/trailing punctuation from the author', () => {
+    expect(extractTxtFilenameMetadata('《书名》 - 张三.txt')).toEqual({
+      title: '书名',
+      author: '张三',
+    });
+  });
+
+  it('handles paths with directories', () => {
+    expect(extractTxtFilenameMetadata('/inbox/《书名》作者：张三.txt')).toEqual({
+      title: '书名',
+      author: '张三',
+    });
+  });
+
+  it('falls back to the base filename when no 《》 are present', () => {
+    expect(extractTxtFilenameMetadata('plain-name.txt')).toEqual({ title: 'plain-name' });
+  });
+
+  it('returns empty object for empty input', () => {
+    expect(extractTxtFilenameMetadata('')).toEqual({ title: '' });
+  });
+});

apps/readest-app/src/components/BookCover.tsx

@@ -138,7 +138,7 @@ const BookCover: React.FC<BookCoverProps> = memo<BookCoverProps>(
                 isPreview ? 'text-[0.4em]' : mode === 'grid' ? 'text-base' : 'text-xs',
               )}
             >
-              {formatAuthors(book.author)}
+              {formatAuthors(book.author || book.metadata?.author || '')}
             </span>
           </div>
         </div>

apps/readest-app/src/utils/txt.ts

@@ -10,6 +10,46 @@ interface Metadata {
   identifier: string;
 }
 
+// Pull a title and (optionally) an author out of a TXT filename. Recognized
+// patterns center on Chinese conventions where books are named with the title
+// in 《》 and an author tacked on, e.g. 《书名》作者：张三.txt, 《书名》[张三].txt,
+// 《书名》张三.txt. Falls back to the base filename as the title when no
+// 《》 are present.
+export const extractTxtFilenameMetadata = (
+  filename: string,
+): { title: string; author?: string } => {
+  const base = getBaseFilename(filename);
+  const cjkMatch = base.match(/《([^》]+)》(.*)/);
+  if (!cjkMatch) {
+    return { title: base };
+  }
+  const title = cjkMatch[1]!.trim();
+  const rest = (cjkMatch[2] ?? '').trim();
+  const author = parseAuthorFragment(rest);
+  return author ? { title, author } : { title };
+};
+
+const parseAuthorFragment = (text: string): string => {
+  if (!text) return '';
+  // 作者：X / 作者:X / 作者 X — labeled author wins
+  const labeled = text.match(/作者\s*[：:\s]\s*(.+)$/);
+  if (labeled) return stripWrappingPunctuation(labeled[1]!);
+  // [X] (X) 【X】 （X）［X］ — bracketed author
+  const bracketed = text.match(/[[(（【［]\s*([^\])）】］]+?)\s*[\])）】］]/);
+  if (bracketed) return stripWrappingPunctuation(bracketed[1]!);
+  // bare token — strip any leading separator like " - " / "·" / "-"
+  return stripWrappingPunctuation(text);
+};
+
+const stripWrappingPunctuation = (text: string): string => {
+  const trimmed = text.trim();
+  try {
+    return trimmed.replace(/^[\p{P}\p{S}\s]+|[\p{P}\p{S}\s]+$/gu, '');
+  } catch {
+    return trimmed;
+  }
+};
+
 interface Chapter {
   title: string;
   content: string;
@@ -73,18 +113,19 @@ export class TxtToEpubConverter {
     const decoder = new TextDecoder(runtimeEncoding);
     const txtContent = decoder.decode(fileContent).trim();
 
-    const bookTitle = this.extractBookTitle(getBaseFilename(txtFile.name));
+    const filenameMeta = extractTxtFilenameMetadata(txtFile.name);
+    const bookTitle = filenameMeta.title;
     const fileName = `${bookTitle}.epub`;
 
     const fileHeader = txtContent.slice(0, 1024);
     const authorMatch =
       fileHeader.match(/[【\[]?作者[】\]]?[:：\s]\s*(.+)\r?\n/) ||
       fileHeader.match(/[【\[]?\s*(.+)\s+著\s*[】\]]?\r?\n/);
-    let matchedAuthor = authorMatch ? authorMatch[1]!.trim() : providedAuthor || '';
+    let matchedAuthor = authorMatch ? authorMatch[1]!.trim() : '';
     try {
       matchedAuthor = matchedAuthor.replace(/^[\p{P}\p{S}]+|[\p{P}\p{S}]+$/gu, '');
     } catch {}
-    const author = matchedAuthor || providedAuthor || '';
+    const author = matchedAuthor || filenameMeta.author || providedAuthor || '';
     const language = providedLanguage || detectLanguage(fileHeader);
     // console.log(`Detected language: ${language}`);
     const identifier = await partialMD5(txtFile);
@@ -126,7 +167,8 @@ export class TxtToEpubConverter {
     const runtimeEncoding = this.resolveSupportedEncoding(detectedEncoding);
     // console.log(`Detected encoding: ${detectedEncoding}, runtime encoding: ${runtimeEncoding}`);
 
-    const bookTitle = this.extractBookTitle(getBaseFilename(txtFile.name));
+    const filenameMeta = extractTxtFilenameMetadata(txtFile.name);
+    const bookTitle = filenameMeta.title;
     const fileName = `${bookTitle}.epub`;
     const fileHeader = await this.readHeaderTextFromFile(
       txtFile,
@@ -137,7 +179,7 @@ export class TxtToEpubConverter {
 
     const { author, language } = this.extractAuthorAndLanguage(
       fileHeader,
-      providedAuthor,
+      filenameMeta.author ?? providedAuthor,
       providedLanguage,
     );
     // console.log(`Detected language: ${language}`);
@@ -931,11 +973,6 @@ export class TxtToEpubConverter {
     return 'utf-8';
   }
 
-  private extractBookTitle(filename: string): string {
-    const match = filename.match(/《([^》]+)》/);
-    return match ? match[1]! : filename.split('.')[0]!;
-  }
-
   private assertStrictUtf8Sample(sample: Uint8Array): void {
     const decoder = new TextDecoder('utf-8', { fatal: true });
     try {