kenkui 2.3.2__tar.gz → 2.3.4__tar.gz

{kenkui-2.3.2/src/kenkui.egg-info → kenkui-2.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kenkui
-Version: 2.3.2
+Version: 2.3.4
 Summary: Convert Ebooks to Audiobooks with [custom] voice samples
 Author-email: Sumner MacArthur <spn1kolat3sla@gmail.com>
 License-Expression: MIT

{kenkui-2.3.2 → kenkui-2.3.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "kenkui"
-version = "2.3.2"
+version = "2.3.4"
 description = "Convert Ebooks to Audiobooks with [custom] voice samples"
 readme = "README.md"
 authors = [{ name = "Sumner MacArthur", email = "spn1kolat3sla@gmail.com" }]

{kenkui-2.3.2 → kenkui-2.3.4}/src/kenkui/readers/epub.py

@@ -15,10 +15,21 @@ from bs4 import BeautifulSoup
 from ebooklib import epub
 
 from ..chapter_classifier import ChapterClassifier
+from ..errors import KenkuiReaderError
 from ..models import Chapter
 from ..utils import extract_epub_cover
 from . import EbookMetadata, EbookReader, Registry, TocEntry
 
+# Known DRM signatures found inside META-INF/encryption.xml. These schemes
+# encrypt the book's content documents with keys kenkui does not (and should
+# not) hold, so the book cannot be parsed. Detecting them lets us fail with an
+# actionable message instead of an opaque parser crash deep inside ebooklib.
+_DRM_SIGNATURES: tuple[tuple[str, str], ...] = (
+    ("http://ns.adobe.com/adept", "Adobe ADEPT"),
+    ("http://www.apple.com/2009/fpk", "Apple FairPlay"),
+    ("http://www.barnesandnoble.com/2010", "Barnes & Noble"),
+)
+
 
 @Registry.register
 class EpubReader(EbookReader):
@@ -28,10 +39,40 @@ class EpubReader(EbookReader):
 
     def __init__(self, filepath: Path, verbose: bool = False):
         super().__init__(filepath, verbose)
+        self._raise_if_drm_protected(Path(filepath))
         with warnings.catch_warnings(record=True):
             warnings.simplefilter("always")
             self.book = epub.read_epub(str(filepath))
 
+    @staticmethod
+    def _raise_if_drm_protected(filepath: Path) -> None:
+        """Raise ``KenkuiReaderError`` if the EPUB is DRM-encrypted.
+
+        Commercial EPUBs (Adobe ADEPT, Apple FairPlay, Barnes & Noble) encrypt
+        their content documents and record it in ``META-INF/encryption.xml``.
+        ebooklib cannot decrypt these and instead fails partway through parsing
+        with a cryptic ``'NoneType' object has no attribute ...`` error. We
+        detect the DRM signature up front and surface a clear message.
+        """
+        try:
+            with zipfile.ZipFile(str(filepath), "r") as book_zip:
+                if "META-INF/encryption.xml" not in book_zip.namelist():
+                    return
+                encryption_xml = book_zip.read("META-INF/encryption.xml").decode(
+                    "utf-8", errors="ignore"
+                )
+        except (zipfile.BadZipFile, OSError):
+            # Let ebooklib produce the definitive error for unreadable archives.
+            return
+
+        for signature, scheme in _DRM_SIGNATURES:
+            if signature in encryption_xml:
+                raise KenkuiReaderError(
+                    f"'{filepath.name}' is DRM-protected ({scheme}) and cannot be "
+                    "processed. kenkui can only read books without DRM; remove the "
+                    "DRM using software you are licensed to use, then try again."
+                )
+
     def get_metadata(self) -> EbookMetadata:
         """Extract metadata from EPUB."""
         title = self._get_title()

{kenkui-2.3.2 → kenkui-2.3.4/src/kenkui.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kenkui
-Version: 2.3.2
+Version: 2.3.4
 Summary: Convert Ebooks to Audiobooks with [custom] voice samples
 Author-email: Sumner MacArthur <spn1kolat3sla@gmail.com>
 License-Expression: MIT

{kenkui-2.3.2 → kenkui-2.3.4}/tests/test_parsing.py

@@ -1,18 +1,62 @@
 """Tests for kenkui parsing functionality."""
 
 import json
+import zipfile
 from pathlib import Path
 from types import SimpleNamespace
 
 import pytest
 
 from kenkui.chapter_filter import FilterOperation
+from kenkui.errors import KenkuiReaderError
 from kenkui.models import Chapter, ProcessingConfig
 from kenkui.readers.epub import EpubReader
 
 TEST_EPUB = Path("src/kenkui/samples/Les Miserables - Victor Hugo.epub")
 
 
+def _write_adept_drm_epub(epub_path: Path) -> None:
+    """Write a minimal EPUB whose content is encrypted with Adobe ADEPT DRM."""
+    encryption_xml = """<?xml version="1.0"?>
+<encryption xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
+  <EncryptedData xmlns="http://www.w3.org/2001/04/xmlenc#">
+    <EncryptionMethod Algorithm="http://www.w3.org/2001/04/xmlenc#aes128-cbc"/>
+    <KeyInfo xmlns="http://www.w3.org/2000/09/xmldsig#">
+      <resource xmlns="http://ns.adobe.com/adept">urn:uuid:2b63d91e-1c6f-4e2d-ae4b-f73c8ad67fd7</resource>
+    </KeyInfo>
+    <CipherData>
+      <CipherReference URI="OEBPS/chap.xhtml"/>
+    </CipherData>
+  </EncryptedData>
+</encryption>"""
+    files = {
+        "META-INF/container.xml": """<?xml version="1.0"?>
+<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
+  <rootfiles>
+    <rootfile full-path="OEBPS/content.opf" media-type="application/oebps-package+xml"/>
+  </rootfiles>
+</container>""",
+        "META-INF/encryption.xml": encryption_xml,
+        "OEBPS/content.opf": """<?xml version="1.0"?>
+<package xmlns="http://www.idpf.org/2007/opf" version="3.0" unique-identifier="id">
+  <metadata xmlns:dc="http://purl.org/dc/elements/1.1/">
+    <dc:identifier id="id">drm-book</dc:identifier>
+    <dc:title>DRM Book</dc:title>
+  </metadata>
+  <manifest>
+    <item id="c1" href="chap.xhtml" media-type="application/xhtml+xml"/>
+  </manifest>
+  <spine><itemref idref="c1"/></spine>
+</package>""",
+        # Ciphertext stand-in — deliberately not valid XHTML, as in a real DRM'd book.
+        "OEBPS/chap.xhtml": b"\x9c\x1e\xd3encrypted-bytes\x00\xff",
+    }
+    with zipfile.ZipFile(epub_path, "w") as epub_zip:
+        epub_zip.writestr("mimetype", "application/epub+zip", compress_type=zipfile.ZIP_STORED)
+        for name, content in files.items():
+            epub_zip.writestr(name, content)
+
+
 class TestEpubReader:
     """Tests for the EpubReader class."""
 
@@ -53,6 +97,18 @@ class TestEpubReader:
                 assert isinstance(chapter.title, str)
                 assert isinstance(chapter.paragraphs, list)
 
+    def test_adept_drm_epub_raises_actionable_error(self, tmp_path):
+        """A DRM-protected EPUB fails with a clear message, not a cryptic crash."""
+        epub_path = tmp_path / "drm.epub"
+        _write_adept_drm_epub(epub_path)
+
+        with pytest.raises(KenkuiReaderError) as excinfo:
+            EpubReader(epub_path)
+
+        message = str(excinfo.value)
+        assert "DRM" in message
+        assert "Adobe" in message
+
 
 class TestChapterDataclass:
     """Tests for the Chapter dataclass."""