mirror of
https://github.com/happycola233/tchMaterial-parser.git
synced 2026-10-18 14:34:22 +08:00
肥宅水水呀
244170e17b
按实际文件大小在当前任务内调整 PDF 流读取上限，保留其他安全限制并隔离并发任务。 将 pypdf 最低版本提高到 6.18，补充大图片、异常流长度、配置恢复、线程隔离和下载完成的回归测试。 close #100
37 lines
1.3 KiB
Python
37 lines
1.3 KiB
Python
import tempfile
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
from pypdf import PdfWriter
|
|
from pypdf.generic import DecodedStreamObject, DictionaryObject, NameObject, NumberObject
|
|
|
|
|
|
@pytest.fixture
|
|
def image_pdf():
|
|
# 缩小版的未压缩 CMYK 图片；测试中降低读取上限，避免生成百兆测试文件。
|
|
writer = PdfWriter()
|
|
page = writer.add_blank_page(width=32, height=32)
|
|
image = DecodedStreamObject()
|
|
image.set_data(b"\x10\x20\x30\x40" * 1024)
|
|
image.update({
|
|
NameObject("/Type"): NameObject("/XObject"),
|
|
NameObject("/Subtype"): NameObject("/Image"),
|
|
NameObject("/Width"): NumberObject(32),
|
|
NameObject("/Height"): NumberObject(32),
|
|
NameObject("/ColorSpace"): NameObject("/DeviceCMYK"),
|
|
NameObject("/BitsPerComponent"): NumberObject(8),
|
|
})
|
|
page[NameObject("/Resources")] = DictionaryObject({
|
|
NameObject("/XObject"): DictionaryObject({NameObject("/Im0"): writer._add_object(image)}),
|
|
})
|
|
content = DecodedStreamObject()
|
|
content.set_data(b"q 32 0 0 32 0 0 cm /Im0 Do Q\n")
|
|
page[NameObject("/Contents")] = writer._add_object(content)
|
|
|
|
root = Path(__file__).resolve().parents[1] / ".tmp"
|
|
root.mkdir(exist_ok=True)
|
|
with tempfile.TemporaryDirectory(dir=root) as directory:
|
|
path = Path(directory) / "image.pdf"
|
|
writer.write(path)
|
|
yield path
|