1 files changed, 67 insertions, 0 deletions
diff --git a/tests/test_extractors.py b/tests/test_extractors.py
index 7b307c0..d604351 100644
--- a/tests/test_extractors.py
+++ b/tests/test_extractors.py
@@ -43,6 +43,7 @@ def _build_test_epub(path: Path, chapters=(("One", "First chapter text."),
     book.set_identifier("test-id")
     book.set_title("Test Book")
     book.set_language("en")
+    book.add_author("Test Author")
 
     items = []
     for index, (title, text) in enumerate(chapters, 1):
@@ -138,5 +139,71 @@ class ExtractSectionsTests(unittest.TestCase):
         self.assertIn("Just one chapter.", sections[0].text)
 
 
+class ExtractBookTests(unittest.TestCase):
+    def test_txt_falls_back_to_stem_and_blank_author(self):
+        from converter.extractors import extract_book
+
+        with tempfile.TemporaryDirectory() as tmp:
+            path = Path(tmp) / "mybook.txt"
+            path.write_text("Hello world.", encoding="utf-8")
+            book = extract_book(path)
+
+        self.assertEqual(book.title, "mybook")
+        self.assertEqual(book.author, "")
+        self.assertEqual(len(book.sections), 1)
+
+    def test_epub_metadata_harvested(self):
+        from converter.extractors import extract_book
+
+        with tempfile.TemporaryDirectory() as tmp:
+            path = Path(tmp) / "book.epub"
+            _build_test_epub(path)
+            book = extract_book(path)
+
+        self.assertEqual(book.title, "Test Book")
+        self.assertEqual(book.author, "Test Author")
+        self.assertEqual([s.title for s in book.sections], ["One", "Two"])
+
+    def test_pdf_metadata_harvested(self):
+        from converter.extractors import extract_book
+
+        try:
+            from pypdf import PdfWriter
+        except ImportError:
+            self.skipTest("pypdf not installed")
+
+        with tempfile.TemporaryDirectory() as tmp:
+            path = Path(tmp) / "book.pdf"
+            writer = PdfWriter()
+            writer.add_metadata({"/Title": "PDF Title", "/Author": "PDF Author"})
+            writer.add_blank_page(width=612, height=792)
+            with open(path, "wb") as handle:
+                writer.write(handle)
+            book = extract_book(path)
+
+        self.assertEqual(book.title, "PDF Title")
+        self.assertEqual(book.author, "PDF Author")
+        self.assertEqual(len(book.sections), 1)
+
+    def test_pdf_without_metadata_falls_back(self):
+        from converter.extractors import extract_book
+
+        try:
+            from pypdf import PdfWriter
+        except ImportError:
+            self.skipTest("pypdf not installed")
+
+        with tempfile.TemporaryDirectory() as tmp:
+            path = Path(tmp) / "plain.pdf"
+            writer = PdfWriter()
+            writer.add_blank_page(width=612, height=792)
+            with open(path, "wb") as handle:
+                writer.write(handle)
+            book = extract_book(path)
+
+        self.assertEqual(book.title, "plain")
+        self.assertEqual(book.author, "")
+
+
 if __name__ == "__main__":
     unittest.main()