feat: switch search index alias atomically

backend/search/minjust_opensearch.py

@@ -15,7 +15,7 @@ import urllib.request
 from pathlib import Path
 from typing import Iterator
 
-APP_VERSION = "0.5.2"
+APP_VERSION = "0.5.3"
 LANGUAGES = {"ru", "ky"}
 DEFAULT_MAPPING = Path(__file__).with_name("minjust-fragments-index.json")
 
@@ -311,8 +311,11 @@ def load_bulk(
     limit: int | None = None,
     resume: bool = False,
     checkpoint: Path = Path("data/opensearch/minjust-fragments.checkpoint.json"),
+    alias: str | None = None,
 ) -> tuple[int, int]:
     base = url.rstrip("/")
+    if alias is not None and alias == index:
+        raise ValueError("--alias must differ from --index")
     index_url = f"{base}/{urllib.parse.quote(index, safe='')}"
     if resume:
         cluster_uuid, index_uuid = opensearch_identity(base, index, index_url)
@@ -363,11 +366,31 @@ def load_bulk(
         state["last_document_code"] = last_code
         write_json_atomic(checkpoint, state)
         print(f"checkpoint={last_code} fragments={fragments}", flush=True)
+    if alias:
+        switch_alias(base, index, alias)
     state["complete"] = True
     write_json_atomic(checkpoint, state)
     return documents, fragments
 
 
+def switch_alias(base: str, index: str, alias: str) -> None:
+    if not alias or alias == index:
+        raise ValueError("--alias must differ from --index")
+    result = request_json(
+        f"{base.rstrip('/')}/_aliases",
+        "POST",
+        json.dumps({
+            "actions": [
+                {"remove": {"index": "*", "alias": alias, "must_exist": False}},
+                {"add": {"index": index, "alias": alias}},
+            ]
+        }).encode(),
+        "application/json",
+    )
+    if result.get("acknowledged") is not True:
+        raise RuntimeError(f"OpenSearch did not acknowledge alias switch: {alias}")
+
+
 def main() -> int:
     parser = argparse.ArgumentParser(description=__doc__)
     parser.add_argument("--input", type=Path, default=Path("data/minjust-normalized"))
@@ -375,6 +398,7 @@ def main() -> int:
     parser.add_argument("--index", default="akyldash-fragments-v1")
     parser.add_argument("--limit", type=int)
     parser.add_argument("--url", help="create the index and stream bounded Bulk requests instead of writing a file")
+    parser.add_argument("--alias", help="atomically point this alias at --index after a successful load")
     parser.add_argument("--mapping", type=Path, default=DEFAULT_MAPPING)
     parser.add_argument("--batch-mb", type=int, default=25)
     parser.add_argument("--resume", action="store_true", help="load into an existing index")
@@ -389,6 +413,8 @@ def main() -> int:
         raise SystemExit("--resume requires --url")
     if arguments.checkpoint and not arguments.url:
         raise SystemExit("--checkpoint requires --url")
+    if arguments.alias and not arguments.url:
+        raise SystemExit("--alias requires --url")
     if arguments.url:
         checkpoint = arguments.checkpoint or Path("data/opensearch") / f"{arguments.index}.checkpoint.json"
         documents, fragments = load_bulk(
@@ -400,6 +426,7 @@ def main() -> int:
             arguments.limit,
             arguments.resume,
             checkpoint,
+            arguments.alias,
         )
         destination = arguments.url
     else: