kenkui 2.3.2__tar.gz → 2.3.3__tar.gz

{kenkui-2.3.2/src/kenkui.egg-info → kenkui-2.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kenkui
-Version: 2.3.2
+Version: 2.3.3
 Summary: Convert Ebooks to Audiobooks with [custom] voice samples
 Author-email: Sumner MacArthur <spn1kolat3sla@gmail.com>
 License-Expression: MIT

{kenkui-2.3.2 → kenkui-2.3.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "kenkui"
-version = "2.3.2"
+version = "2.3.3"
 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-2.3.3}/src/kenkui/readers/epub.py

@@ -7,6 +7,7 @@ Provides EbookReader interface for EPUB files using ebooklib.
 from __future__ import annotations
 
 import re
+import tempfile
 import warnings
 import zipfile
 from pathlib import Path
@@ -30,7 +31,60 @@ class EpubReader(EbookReader):
         super().__init__(filepath, verbose)
         with warnings.catch_warnings(record=True):
             warnings.simplefilter("always")
-            self.book = epub.read_epub(str(filepath))
+            try:
+                self.book = epub.read_epub(str(filepath))
+            except AttributeError as exc:
+                if "'NoneType' object has no attribute" not in str(exc):
+                    raise
+                try:
+                    self.book = self._read_epub_without_nav_parsing()
+                except Exception:
+                    raise exc
+
+    def _read_epub_without_nav_parsing(self):
+        """Load an EPUB while bypassing EbookLib's brittle NAV parser.
+
+        EbookLib parses any manifest item marked ``properties=\"nav\"`` during
+        ``read_epub``. Some real EPUBs contain malformed NAV documents (for
+        example a TOC ``<nav>`` without an ``<ol>``), which makes EbookLib raise
+        an opaque ``'NoneType' object has no attribute ...`` before kenkui can
+        fall back to its own TOC/chapter extraction.  Strip only the ``nav``
+        property from a temporary copy so EbookLib still loads manifest/spine
+        items while kenkui parses the original file itself.
+        """
+        from xml.etree import ElementTree as ET
+
+        with tempfile.NamedTemporaryFile(suffix=".epub") as temp_epub:
+            with zipfile.ZipFile(str(self.filepath), "r") as source_zip:
+                names = source_zip.namelist()
+                container_path = "META-INF/container.xml"
+                if container_path not in names:
+                    raise ValueError("EPUB is missing META-INF/container.xml")
+                container_tree = ET.fromstring(source_zip.read(container_path))
+                container_ns = {"container": "urn:oasis:names:tc:opendocument:xmlns:container"}
+                rootfile = container_tree.find(".//container:rootfile", container_ns)
+                if rootfile is None or rootfile.get("full-path") is None:
+                    raise ValueError("EPUB container is missing rootfile full-path")
+                opf_path = rootfile.get("full-path") or ""
+                opf_tree = ET.fromstring(source_zip.read(opf_path))
+                opf_ns = {"opf": "http://www.idpf.org/2007/opf"}
+                for item in opf_tree.findall(".//opf:item", opf_ns):
+                    properties = item.get("properties")
+                    if not properties:
+                        continue
+                    remaining = [prop for prop in properties.split() if prop != "nav"]
+                    if remaining:
+                        item.set("properties", " ".join(remaining))
+                    else:
+                        item.attrib.pop("properties", None)
+                sanitized_opf = ET.tostring(opf_tree, encoding="utf-8", xml_declaration=True)
+
+                with zipfile.ZipFile(temp_epub.name, "w") as sanitized_zip:
+                    for info in source_zip.infolist():
+                        content = sanitized_opf if info.filename == opf_path else source_zip.read(info.filename)
+                        sanitized_zip.writestr(info, content)
+
+            return epub.read_epub(temp_epub.name)
 
     def get_metadata(self) -> EbookMetadata:
         """Extract metadata from EPUB."""

{kenkui-2.3.2 → kenkui-2.3.3/src/kenkui.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kenkui
-Version: 2.3.2
+Version: 2.3.3
 Summary: Convert Ebooks to Audiobooks with [custom] voice samples
 Author-email: Sumner MacArthur <spn1kolat3sla@gmail.com>
 License-Expression: MIT

{kenkui-2.3.2 → kenkui-2.3.3}/tests/test_parsing.py

@@ -1,6 +1,7 @@
 """Tests for kenkui parsing functionality."""
 
 import json
+import zipfile
 from pathlib import Path
 from types import SimpleNamespace
 
@@ -13,6 +14,38 @@ from kenkui.readers.epub import EpubReader
 TEST_EPUB = Path("src/kenkui/samples/Les Miserables - Victor Hugo.epub")
 
 
+def _write_epub_with_nav(epub_path: Path, *, nav_body: str) -> None:
+    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>""",
+        "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">bad-nav</dc:identifier>
+    <dc:title>Bad Nav</dc:title>
+    <dc:language>en</dc:language>
+  </metadata>
+  <manifest>
+    <item id="nav" href="nav.xhtml" media-type="application/xhtml+xml" properties="nav"/>
+    <item id="c1" href="chap.xhtml" media-type="application/xhtml+xml"/>
+  </manifest>
+  <spine>
+    <itemref idref="c1"/>
+  </spine>
+</package>""",
+        "OEBPS/nav.xhtml": f"""<html xmlns="http://www.w3.org/1999/xhtml"><body>{nav_body}</body></html>""",
+        "OEBPS/chap.xhtml": """<html xmlns="http://www.w3.org/1999/xhtml"><body><h1>Chapter One</h1><p>Hello world.</p></body></html>""",
+    }
+    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 +86,21 @@ class TestEpubReader:
                 assert isinstance(chapter.title, str)
                 assert isinstance(chapter.paragraphs, list)
 
+    def test_reader_handles_nav_document_without_ordered_list(self, tmp_path):
+        """EPUBs with a malformed NAV document still load chapters."""
+        epub_path = tmp_path / "bad-nav.epub"
+        _write_epub_with_nav(
+            epub_path,
+            nav_body='<nav epub:type="toc" xmlns:epub="http://www.idpf.org/2007/ops"><h1>Contents</h1></nav>',
+        )
+
+        reader = EpubReader(epub_path)
+
+        assert reader.get_metadata().title == "Bad Nav"
+        chapters = reader.get_chapters(min_text_len=1)
+        assert len(chapters) == 1
+        assert chapters[0].paragraphs == ["Chapter One", "Hello world."]
+
 
 class TestChapterDataclass:
     """Tests for the Chapter dataclass."""