c5cf555de6
Treat each linear spine document as a single reading unit instead of splitting one spine item into multiple chapters based on section heuristics. Improve XHTML text extraction so inline spacing is preserved, list and container text is included in reading order, and non-readable tags are ignored before speech output. Resolve TOC hrefs against the nav or NCX document location so chapter titles match nested content paths correctly, and skip non-linear spine items. Add a regression test that builds a minimal EPUB fixture and verifies spine order, title resolution, preserved inline spacing, extraction of non-paragraph content, and exclusion of linear=no content. Verified with: python test_epub_parser.py; python check_naming.py src/epub_parser.py; python check_naming.py test_epub_parser.py
171 lines
5.2 KiB
Python
171 lines
5.2 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Regression tests for EPUB parsing behavior.
|
|
"""
|
|
|
|
from pathlib import Path
|
|
from tempfile import TemporaryDirectory
|
|
import zipfile
|
|
|
|
from src.epub_parser import EpubParser
|
|
|
|
|
|
def write_text_file(filePath, content):
|
|
"""Write a UTF-8 text file"""
|
|
filePath.parent.mkdir(parents=True, exist_ok=True)
|
|
filePath.write_text(content, encoding='utf-8')
|
|
|
|
|
|
def build_test_epub(epubPath):
|
|
"""Build a minimal EPUB fixture for parser regression testing"""
|
|
with TemporaryDirectory() as tempDir:
|
|
tempPath = Path(tempDir)
|
|
|
|
write_text_file(
|
|
tempPath / 'mimetype',
|
|
'application/epub+zip'
|
|
)
|
|
write_text_file(
|
|
tempPath / 'META-INF' / 'container.xml',
|
|
'''<?xml version="1.0" encoding="UTF-8"?>
|
|
<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>
|
|
'''
|
|
)
|
|
write_text_file(
|
|
tempPath / 'OEBPS' / 'content.opf',
|
|
'''<?xml version="1.0" encoding="utf-8"?>
|
|
<package version="3.0" xmlns="http://www.idpf.org/2007/opf" unique-identifier="BookId">
|
|
<metadata xmlns:dc="http://purl.org/dc/elements/1.1/">
|
|
<dc:title>Parser Regression Book</dc:title>
|
|
<dc:creator>BookStorm Test</dc:creator>
|
|
</metadata>
|
|
<manifest>
|
|
<item id="navdoc" href="nav/toc.xhtml" media-type="application/xhtml+xml" properties="nav"/>
|
|
<item id="chap1" href="text/chapter1.xhtml" media-type="application/xhtml+xml"/>
|
|
<item id="chap2" href="text/chapter2.xhtml" media-type="application/xhtml+xml"/>
|
|
<item id="notes" href="text/notes.xhtml" media-type="application/xhtml+xml"/>
|
|
</manifest>
|
|
<spine>
|
|
<itemref idref="chap1"/>
|
|
<itemref idref="notes" linear="no"/>
|
|
<itemref idref="chap2"/>
|
|
</spine>
|
|
</package>
|
|
'''
|
|
)
|
|
write_text_file(
|
|
tempPath / 'OEBPS' / 'nav' / 'toc.xhtml',
|
|
'''<?xml version="1.0" encoding="utf-8"?>
|
|
<html xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops">
|
|
<body>
|
|
<nav epub:type="toc">
|
|
<ol>
|
|
<li><a href="../text/chapter1.xhtml">Chapter One</a></li>
|
|
<li><a href="../text/chapter2.xhtml">Chapter Two</a></li>
|
|
</ol>
|
|
</nav>
|
|
</body>
|
|
</html>
|
|
'''
|
|
)
|
|
write_text_file(
|
|
tempPath / 'OEBPS' / 'text' / 'chapter1.xhtml',
|
|
'''<?xml version="1.0" encoding="utf-8"?>
|
|
<html xmlns="http://www.w3.org/1999/xhtml">
|
|
<body>
|
|
<section>
|
|
<h1>Visible Heading</h1>
|
|
<p>This is <em>very</em> bad.</p>
|
|
<ul>
|
|
<li>First item</li>
|
|
<li>Second item</li>
|
|
</ul>
|
|
</section>
|
|
</body>
|
|
</html>
|
|
'''
|
|
)
|
|
write_text_file(
|
|
tempPath / 'OEBPS' / 'text' / 'chapter2.xhtml',
|
|
'''<?xml version="1.0" encoding="utf-8"?>
|
|
<html xmlns="http://www.w3.org/1999/xhtml">
|
|
<body>
|
|
<div>Lead in <span>text</span>.</div>
|
|
<div class="section"><p>More text.</p></div>
|
|
<p>Tail text.</p>
|
|
</body>
|
|
</html>
|
|
'''
|
|
)
|
|
write_text_file(
|
|
tempPath / 'OEBPS' / 'text' / 'notes.xhtml',
|
|
'''<?xml version="1.0" encoding="utf-8"?>
|
|
<html xmlns="http://www.w3.org/1999/xhtml">
|
|
<body>
|
|
<p>This non-linear note should not appear.</p>
|
|
</body>
|
|
</html>
|
|
'''
|
|
)
|
|
|
|
with zipfile.ZipFile(epubPath, 'w') as zipRef:
|
|
mimetypePath = tempPath / 'mimetype'
|
|
zipRef.write(mimetypePath, 'mimetype', compress_type=zipfile.ZIP_STORED)
|
|
|
|
for filePath in sorted(tempPath.rglob('*')):
|
|
if filePath.is_file() and filePath != mimetypePath:
|
|
archivePath = filePath.relative_to(tempPath).as_posix()
|
|
zipRef.write(filePath, archivePath, compress_type=zipfile.ZIP_DEFLATED)
|
|
|
|
|
|
def test_epub_parser():
|
|
"""Verify EPUB parsing follows linear spine order and preserves readable text"""
|
|
with TemporaryDirectory() as tempDir:
|
|
epubPath = Path(tempDir) / 'fixture.epub'
|
|
build_test_epub(epubPath)
|
|
|
|
parser = EpubParser()
|
|
try:
|
|
book = parser.parse(epubPath)
|
|
finally:
|
|
parser.cleanup()
|
|
|
|
print("Testing spine-based chapter extraction...")
|
|
assert book.title == 'Parser Regression Book'
|
|
assert book.author == 'BookStorm Test'
|
|
assert book.get_total_chapters() == 2
|
|
assert [chapter.title for chapter in book.chapters] == ['Chapter One', 'Chapter Two']
|
|
print("Chapter extraction tests passed")
|
|
|
|
print("\nTesting readable text extraction...")
|
|
firstChapter = book.get_chapter(0)
|
|
secondChapter = book.get_chapter(1)
|
|
|
|
assert firstChapter is not None
|
|
assert secondChapter is not None
|
|
|
|
assert firstChapter.paragraphs == [
|
|
'Visible Heading',
|
|
'This is very bad.',
|
|
'First item',
|
|
'Second item'
|
|
]
|
|
assert secondChapter.paragraphs == [
|
|
'Lead in text.',
|
|
'More text.',
|
|
'Tail text.'
|
|
]
|
|
assert all('non-linear note' not in paragraph.lower() for chapter in book.chapters for paragraph in chapter.paragraphs)
|
|
print("Readable text tests passed")
|
|
|
|
print("\nAll EPUB parser tests passed!")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
test_epub_parser()
|