refactor(files): decompose S3 connector imports

src/govoplan_files/backend/storage/connector_imports.py

@@ -236,19 +236,16 @@ def _read_smb_file(profile: ConnectorProfile, *, path: str, max_bytes: int) -> C
     )
 
 
-def _read_s3_file(profile: ConnectorProfile, *, library_id: str, path: str, max_bytes: int) -> ConnectorDownloadedFile:
+def _s3_import_client(profile: ConnectorProfile) -> Any:
-    bucket = _s3_bucket(profile, library_id)
-    if not bucket:
-        raise ConnectorImportError("S3 import requires a bucket in library_id or profile metadata")
-    key = _s3_object_key(profile, path)
-    if not key:
-        raise ConnectorImportError("S3 import requires an object key")
     try:
-        client = _s3_client(profile)
+        return _s3_client(profile)
     except ConnectorBrowseUnsupported as exc:
         raise ConnectorImportUnsupported(str(exc)) from exc
     except ConnectorBrowseError as exc:
         raise ConnectorImportError(str(exc)) from exc
+
+
+def _s3_object_detail(client: Any, *, bucket: str, key: str, max_bytes: int) -> dict[str, Any]:
     try:
         detail = client.head_object(Bucket=bucket, Key=key)
     except Exception as exc:  # pragma: no cover - concrete exception types are dependency-version specific
@@ -258,7 +255,17 @@ def _read_s3_file(profile: ConnectorProfile, *, library_id: str, path: str, max_
     size = _int(detail.get("ContentLength"))
     if size is not None and size > max_bytes:
         raise ConnectorImportError(f"S3 object exceeds limit of {max_bytes} bytes")
-    version_id = _clean(detail.get("VersionId"))
+    return detail
+
+
+def _download_s3_object(
+    client: Any,
+    *,
+    bucket: str,
+    key: str,
+    version_id: str | None,
+    max_bytes: int,
+) -> tuple[Any, bytes]:
     request: dict[str, object] = {"Bucket": bucket, "Key": key}
     if version_id:
         request["VersionId"] = version_id
@@ -270,6 +277,52 @@ def _read_s3_file(profile: ConnectorProfile, *, library_id: str, path: str, max_
         raise ConnectorImportError(f"S3 object download failed: {exc}") from exc
     if len(data) > max_bytes:
         raise ConnectorImportError(f"S3 object exceeds limit of {max_bytes} bytes")
+    return response, data
+
+
+def _s3_download_metadata(
+    detail: dict[str, Any],
+    *,
+    bucket: str,
+    key: str,
+    version_id: str | None,
+    etag: str | None,
+    size: int,
+) -> dict[str, Any]:
+    metadata: dict[str, Any] = {
+        "bucket": bucket,
+        "key": key,
+        "version_id": version_id,
+        "etag": etag,
+        "size": size,
+    }
+    for source_key, target_key in (
+        ("ChecksumSHA256", "checksum_sha256"),
+        ("ChecksumCRC32", "checksum_crc32"),
+        ("StorageClass", "storage_class"),
+    ):
+        if source_key in detail:
+            metadata[target_key] = detail[source_key]
+    return metadata
+
+
+def _read_s3_file(profile: ConnectorProfile, *, library_id: str, path: str, max_bytes: int) -> ConnectorDownloadedFile:
+    bucket = _s3_bucket(profile, library_id)
+    if not bucket:
+        raise ConnectorImportError("S3 import requires a bucket in library_id or profile metadata")
+    key = _s3_object_key(profile, path)
+    if not key:
+        raise ConnectorImportError("S3 import requires an object key")
+    client = _s3_import_client(profile)
+    detail = _s3_object_detail(client, bucket=bucket, key=key, max_bytes=max_bytes)
+    version_id = _clean(detail.get("VersionId"))
+    response, data = _download_s3_object(
+        client,
+        bucket=bucket,
+        key=key,
+        version_id=version_id,
+        max_bytes=max_bytes,
+    )
     content_type = _clean(response.get("ContentType") if isinstance(response, dict) else None) or _clean(detail.get("ContentType")) or mimetypes.guess_type(key)[0]
     etag = _clean(response.get("ETag") if isinstance(response, dict) else None) or _clean(detail.get("ETag"))
     filename = filename_from_path(key)
@@ -280,16 +333,14 @@ def _read_s3_file(profile: ConnectorProfile, *, library_id: str, path: str, max_
         revision=version_id or etag or _clean(detail.get("LastModified")),
         external_id=f"{bucket}:{key}",
         external_url=f"s3://{bucket}/{key}",
-        metadata={
+        metadata=_s3_download_metadata(
-            "bucket": bucket,
+            detail,
-            "key": key,
+            bucket=bucket,
-            "version_id": version_id,
+            key=key,
-            "etag": etag,
+            version_id=version_id,
-            "size": len(data),
+            etag=etag,
-            **({"checksum_sha256": detail["ChecksumSHA256"]} if "ChecksumSHA256" in detail else {}),
+            size=len(data),
-            **({"checksum_crc32": detail["ChecksumCRC32"]} if "ChecksumCRC32" in detail else {}),
+        ),
-            **({"storage_class": detail["StorageClass"]} if "StorageClass" in detail else {}),
-        },
     )