Dymas/abogen
1
0
Fork 0
mirror of https://github.com/denizsafak/abogen.git synced 2026-07-18 13:40:27 +02:00
Code Issues Packages Projects Releases Wiki Activity

Reformat using black

Browse Source
This commit is contained in:
Deniz Şafak
2026-01-09 01:36:14 +03:00
parent 3c800df450
commit 5ae153f841
48 changed files with 1530 additions and 894 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_epub_content_slicing.py
+36 -32
View File
@@ -5,10 +5,11 @@ import sys
from ebooklib import epub
# Ensure import path
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
from abogen.book_parser import get_book_parser
class TestEpubContentSlicing(unittest.TestCase):
"""
Tests for the complex content slicing logic in _execute_nav_parsing_logic.
@@ -34,7 +35,7 @@ class TestEpubContentSlicing(unittest.TestCase):
book = epub.EpubBook()
book.set_identifier("slice123")
book.set_title("Slicing Test Book")
# Create a single content file with two sections
content_html = """
<html>
@@ -50,7 +51,7 @@ class TestEpubContentSlicing(unittest.TestCase):
c1 = epub.EpubHtml(title="Full Content", file_name="content.xhtml", lang="en")
c1.content = content_html
book.add_item(c1)
# Create Nav that points to anchors in the SAME file
# We use EpubHtml for Nav to control content exactly without ebooklib interference
nav_html = """
@@ -64,55 +65,56 @@ class TestEpubContentSlicing(unittest.TestCase):
nav = epub.EpubHtml(title="Nav", file_name="nav.xhtml")
nav.content = nav_html
book.add_item(nav)
book.spine = [nav, c1]
epub.write_epub(self.epub_path, book)
# OPF Patching to valid crash
import zipfile
patched = False
with zipfile.ZipFile(self.epub_path, 'r') as zin:
opf_content = zin.read('EPUB/content.opf').decode('utf-8')
with zipfile.ZipFile(self.epub_path, "r") as zin:
opf_content = zin.read("EPUB/content.opf").decode("utf-8")
if 'toc="ncx"' in opf_content:
opf_content = opf_content.replace('toc="ncx"', '')
opf_content = opf_content.replace('toc="ncx"', "")
patched = True
if patched:
TEMP_EPUB = self.epub_path + ".temp"
with zipfile.ZipFile(TEMP_EPUB, 'w') as zout:
with zipfile.ZipFile(TEMP_EPUB, "w") as zout:
for item in zin.infolist():
if item.filename == 'EPUB/content.opf':
if item.filename == "EPUB/content.opf":
zout.writestr(item, opf_content)
else:
zout.writestr(item, zin.read(item.filename))
if patched:
shutil.move(TEMP_EPUB, self.epub_path)
# Parse
parser = get_book_parser(self.epub_path)
parser.process_content()
chapters = parser.get_chapters()
# Filter Nav/Intro
chapters = [c for c in chapters if "Chapter" in c[1]]
self.assertEqual(len(chapters), 2)
self.assertEqual(chapters[0][1], "Chapter 1")
self.assertEqual(chapters[1][1], "Chapter 2")
# Check content of Chapter 1
# It should contain "Text for chapter 1" but NOT "Text for chapter 2"
# The parser logic slices from start_pos to next_pos
text1 = parser.content_texts[chapters[0][0]]
self.assertIn("Text for chapter 1", text1)
self.assertNotIn("Text for chapter 2", text1)
# Check content of Chapter 2
text2 = parser.content_texts[chapters[1][0]]
self.assertIn("Text for chapter 2", text2)
def test_list_renumbering(self):
"""
Test that ordered lists are re-numbered when slicing.
@@ -121,7 +123,7 @@ class TestEpubContentSlicing(unittest.TestCase):
book = epub.EpubBook()
book.set_identifier("list123")
book.set_title("List Test Book")
content_html = """
<html>
<body>
@@ -141,7 +143,7 @@ class TestEpubContentSlicing(unittest.TestCase):
c1 = epub.EpubHtml(title="Content", file_name="content.xhtml", lang="en")
c1.content = content_html
book.add_item(c1)
nav_html = """
<nav epub:type="toc">
<ol>
@@ -154,46 +156,48 @@ class TestEpubContentSlicing(unittest.TestCase):
nav.content = nav_html
book.add_item(nav)
book.spine = [nav, c1]
epub.write_epub(self.epub_path, book)
# Patch
import zipfile
patched = False
with zipfile.ZipFile(self.epub_path, 'r') as zin:
opf_content = zin.read('EPUB/content.opf').decode('utf-8')
with zipfile.ZipFile(self.epub_path, "r") as zin:
opf_content = zin.read("EPUB/content.opf").decode("utf-8")
if 'toc="ncx"' in opf_content:
opf_content = opf_content.replace('toc="ncx"', '')
opf_content = opf_content.replace('toc="ncx"', "")
patched = True
if patched:
TEMP_EPUB = self.epub_path + ".temp"
with zipfile.ZipFile(TEMP_EPUB, 'w') as zout:
with zipfile.ZipFile(TEMP_EPUB, "w") as zout:
for item in zin.infolist():
if item.filename == 'EPUB/content.opf':
if item.filename == "EPUB/content.opf":
zout.writestr(item, opf_content)
else:
zout.writestr(item, zin.read(item.filename))
if patched:
shutil.move(TEMP_EPUB, self.epub_path)
parser = get_book_parser(self.epub_path)
parser.process_content()
chapters = parser.get_chapters()
chapters = [c for c in chapters if "Part" in c[1]]
self.assertEqual(len(chapters), 2)
# Check Part 1 text
text1 = parser.content_texts[chapters[0][0]]
# The parser explicitly replaces li with "1) Item A" style text
self.assertIn("1) Item A", text1)
self.assertIn("2) Item B", text1)
# Check Part 2 text
text2 = parser.content_texts[chapters[1][0]]
# Should convert start="3" to "3) Item C"
self.assertIn("3) Item C", text2)
self.assertIn("4) Item D", text2)
if __name__ == "__main__":
unittest.main()