chesirecatt
94 lines
3.9 KiB
Python
94 lines
3.9 KiB
Python
#!/usr/bin/env python3
|
|
"""Самопроверка упаковщика без сети: python3 test_pack_epub.py"""
|
|
import re
|
|
import tempfile
|
|
import zipfile
|
|
from pathlib import Path
|
|
|
|
import pack_epub
|
|
|
|
BOOK = """<?xml version="1.0" encoding="utf-8"?>
|
|
<html xmlns="http://www.w3.org/1999/xhtml"><head><title>T</title>
|
|
<style>p { margin: 0; }</style></head><body>
|
|
<p>Предисловие до первой главы.</p>
|
|
<h1>Глава 1. Начало</h1>
|
|
<p>Текст первой главы.</p>
|
|
<pre>def f():
|
|
return 1</pre>
|
|
<p class="figure"><img src="images/fig.png"/></p>
|
|
<h1>Глава 2. Продолжение</h1>
|
|
<p>Текст второй главы.</p>
|
|
</body></html>"""
|
|
|
|
|
|
def test_pack(tmp: Path):
|
|
src = tmp / "book.html"
|
|
src.write_text(BOOK, encoding="utf-8")
|
|
(tmp / "images").mkdir()
|
|
(tmp / "images" / "fig.png").write_bytes(b"\x89PNG\r\n\x1a\n")
|
|
(tmp / "images" / "cover.jpg").write_bytes(b"\xff\xd8\xff")
|
|
out = tmp / "book.epub"
|
|
chapters, imgs = pack_epub.build(src, out, {
|
|
"title": "Книга & книга", "author": "Автор", "lang": "ru",
|
|
"cover": "cover.jpg", "id": "urn:uuid:test"})
|
|
|
|
# преамбула до первой главы не теряется, поэтому глав три, а не две
|
|
assert (chapters, imgs) == (3, 1), (chapters, imgs)
|
|
|
|
z = zipfile.ZipFile(out)
|
|
names = z.namelist()
|
|
# без этого часть читалок не опознаёт файл как EPUB
|
|
assert names[0] == "mimetype"
|
|
assert z.getinfo("mimetype").compress_type == zipfile.ZIP_STORED
|
|
assert "OEBPS/images/fig.png" in names and "OEBPS/images/cover.jpg" in names
|
|
|
|
opf = z.read("OEBPS/content.opf").decode("utf-8")
|
|
assert "<dc:title>Книга & книга</dc:title>" in opf, "разметку надо экранировать"
|
|
assert opf.count("<itemref") == 3
|
|
assert 'properties="cover-image"' in opf
|
|
|
|
ncx = z.read("OEBPS/toc.ncx").decode("utf-8")
|
|
assert re.findall(r"<text>([^<]*)</text>", ncx)[1:] == [
|
|
"Начало", "Глава 1. Начало", "Глава 2. Продолжение"]
|
|
|
|
ch1 = z.read("OEBPS/ch001.xhtml").decode("utf-8")
|
|
assert "<pre>def f():\n return 1</pre>" in ch1, "переносы в листинге значимы"
|
|
assert 'href="style.css"' in ch1
|
|
assert "Текст второй главы" not in ch1, "главы не должны склеиваться"
|
|
|
|
|
|
def test_cover_used_in_text_is_not_duplicated(tmp: Path):
|
|
"""Обложка, встречающаяся и в тексте, не должна попадать в архив дважды."""
|
|
src = tmp / "book.html"
|
|
src.write_text("<h1>Глава</h1>\n"
|
|
'<p class="figure"><img src="images/cover.jpg"/></p>\n'
|
|
"<p>Текст главы.</p>", encoding="utf-8")
|
|
(tmp / "images").mkdir()
|
|
(tmp / "images" / "cover.jpg").write_bytes(b"\xff\xd8\xff")
|
|
out = tmp / "book.epub"
|
|
pack_epub.build(src, out, {"title": "t", "author": "a", "lang": "ru",
|
|
"cover": "cover.jpg", "id": "i"})
|
|
names = zipfile.ZipFile(out).namelist()
|
|
assert names.count("OEBPS/images/cover.jpg") == 1, names
|
|
opf = zipfile.ZipFile(out).read("OEBPS/content.opf").decode()
|
|
assert opf.count('href="images/cover.jpg"') == 1, opf
|
|
|
|
|
|
def test_no_content(tmp: Path):
|
|
src = tmp / "empty.html"
|
|
src.write_text("<html><body>\n</body></html>", encoding="utf-8")
|
|
try:
|
|
pack_epub.build(src, tmp / "x.epub", {"title": "t", "author": "", "lang": "ru",
|
|
"cover": "", "id": "i"})
|
|
except SystemExit:
|
|
return
|
|
raise AssertionError("пустой источник должен останавливать упаковку")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
for case in (test_pack, test_cover_used_in_text_is_not_duplicated,
|
|
test_no_content):
|
|
with tempfile.TemporaryDirectory() as d:
|
|
case(Path(d))
|
|
print("OK")
|