Import project files

docling/app/tests/run_convert_folder_debug.py

@@ -0,0 +1,75 @@
+import io
+import os
+from pathlib import Path
+from fastapi.testclient import TestClient
+import sys
+from pathlib import Path as _Path
+base = _Path(__file__).resolve().parents[2]
+sys.path.insert(0, str(base))
+sys.path.insert(0, str(base / "docling"))
+import app.server as server
+
+
+class FakeMinio:
+    def __init__(self):
+        self.objs = {}
+
+    def put_object(self, bucket_name: str, object_name: str, data: io.BytesIO, length: int, content_type: str):
+        self.objs[(bucket_name, object_name)] = data.read(length)
+
+    def get_presigned_url(self, method: str, bucket: str, obj: str, expires: int):
+        return f"http://minio.test/presigned/{bucket}/{obj}"
+
+    def presigned_get_object(self, bucket: str, obj: str, expires: int):
+        return f"http://minio.test/presigned/{bucket}/{obj}"
+
+
+def setup():
+    server.RUNTIME_CONFIG["minio"].update({
+        "endpoint": "127.0.0.1:9000",
+        "public": "http://127.0.0.1:9000",
+        "access": "ak",
+        "secret": "sk",
+        "bucket": "test",
+        "secure": "false",
+        "prefix": "assets",
+        "store_final": "true",
+        "public_read": "true",
+    })
+    fake = FakeMinio()
+    def _cur():
+        return fake, "test", "http://127.0.0.1:9000", "assets"
+    server._minio_current = _cur  # type: ignore
+
+
+def main():
+    setup()
+    app = server.app
+    c = TestClient(app)
+    tmp = Path("/tmp/run_convert_folder_debug")
+    if tmp.exists():
+        for p in tmp.rglob("*"):
+            try:
+                p.unlink()
+            except Exception:
+                pass
+        try:
+            tmp.rmdir()
+        except Exception:
+            pass
+    tmp.mkdir(parents=True, exist_ok=True)
+
+    root = tmp / "数+产品手册-MD源文件"
+    sub = root / "DMDRS_DRS_Language_User_Manual"
+    img = sub / "images"
+    img.mkdir(parents=True, exist_ok=True)
+    (img / "p.png").write_bytes(b"PNG")
+    (sub / "a.md").write_text("# Title\n\n![](images/p.png)", "utf-8")
+
+    r = c.post("/md/convert-folder", data={"folder_path": str(root), "prefix": "assets"})
+    print("convert-folder:", r.status_code)
+    print(r.json())
+
+
+if __name__ == "__main__":
+    main()