54 lines
1.6 KiB
Python
54 lines
1.6 KiB
Python
|
import io
|
||
|
|
import os
|
||
|
|
import base64
|
||
|
|
from pathlib import Path
|
||
|
|
from zipfile import ZipFile
|
||
|
|
|
||
|
|
from app.services.docling_adapter import md_to_docx_bytes
|
||
|
|
|
||
|
|
|
||
|
|
def _make_png(tmpdir: Path) -> Path:
|
||
|
|
# Minimal 1x1 PNG
|
||
|
|
data = base64.b64decode(
|
||
|
|
b"iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR4nGNgYAAAAAMAASsJTYQAAAAASUVORK5CYII="
|
||
|
|
)
|
||
|
|
p = tmpdir / "tiny.png"
|
||
|
|
p.write_bytes(data)
|
||
|
|
return p
|
||
|
|
|
||
|
|
|
||
|
|
def test_md_to_docx_renders_blocks_and_media(tmp_path: Path):
|
||
|
|
png = _make_png(tmp_path)
|
||
|
|
html = (
|
||
|
|
f"<h1>标题</h1>"
|
||
|
|
f"<p>内容</p>"
|
||
|
|
f"<pre><code>print(\"hello\")\n</code></pre>"
|
||
|
|
f"<img src='{png.as_posix()}'>"
|
||
|
|
f"<table><thead><tr><th>A</th><th>B</th></tr></thead>"
|
||
|
|
f"<tbody><tr><td>1</td><td>2</td></tr></tbody></table>"
|
||
|
|
)
|
||
|
|
|
||
|
|
docx = md_to_docx_bytes(
|
||
|
|
html,
|
||
|
|
toc=True,
|
||
|
|
header_text="Left|Right",
|
||
|
|
footer_text="Footer",
|
||
|
|
filename_text="FileName",
|
||
|
|
product_name="Product",
|
||
|
|
document_name="DocName",
|
||
|
|
product_version="1.0",
|
||
|
|
document_version="2.0",
|
||
|
|
)
|
||
|
|
|
||
|
|
assert isinstance(docx, (bytes, bytearray)) and len(docx) > 0
|
||
|
|
zf = ZipFile(io.BytesIO(docx))
|
||
|
|
names = set(zf.namelist())
|
||
|
|
assert any(n.startswith("word/") for n in names)
|
||
|
|
# Document XML should contain core texts
|
||
|
|
doc_xml = zf.read("word/document.xml").decode("utf-8")
|
||
|
|
for tok in ["标题", "内容", "print(\"hello\")", "A", "B", "1", "2"]:
|
||
|
|
assert tok in doc_xml
|
||
|
|
# Media should be present for the image
|
||
|
|
assert any(n.startswith("word/media/") for n in names)
|
||
|
|
|