feat: add real PDF ingestion workflow

This commit is contained in:
Codex
2026-08-02 00:29:40 +08:00
parent 0eb2a86f36
commit 4d97a30616
18 changed files with 986 additions and 93 deletions
+19
View File
@@ -0,0 +1,19 @@
from pathlib import Path
from app.services.plan_ingestion import inspect_pdf
def test_sample_pdf_detects_two_plan_regions() -> None:
workspace = Path(__file__).resolve().parents[3]
sample = workspace / "11-2-104-模型.pdf"
result = inspect_pdf(sample.read_bytes())
assert result.page_count == 1
assert result.vector_based is True
assert result.vector_element_count > 10_000
assert result.preview_width == 1600
assert len(result.regions) == 2
assert result.regions[0].name.startswith("上方")
assert result.regions[0].recommended is True
assert result.regions[1].name.startswith("下方")