src/commands.zig

@@ -1992,7 +1992,7 @@ fn cmd_update(ctx: *Context, msg: *wire.Message, reply: *wire.Reply) !void {
 
         if (matched.items.len == 0) {
             if (upsert) {
-                const new_doc = build_upsert_doc(reply, q, u_doc, opts) catch |err|
+                const new_doc = build_upsert_doc(reply, ctx, q, u_doc, opts) catch |err|
                     return update_refusal(reply, err, diag);
                 ctx.engine.insert(db_name, coll_name, new_doc, ctx.oid_gen) catch |err| switch (err) {
                     error.DuplicateKey, error.DuplicateKeyIndex => return duplicate_key_error(ctx, reply, db_name, coll_name, new_doc),
@@ -2134,7 +2134,7 @@ fn cmd_find_and_modify(ctx: *Context, msg: *wire.Message, reply: *wire.Reply) !v
 
     if (target == null and do_update and upsert) {
         const u_doc = doc_arg(msg.body.get("update")) orelse return bad_value(reply, "update must be a document");
-        const new_doc = build_upsert_doc(reply, q, u_doc, opts) catch |err|
+        const new_doc = build_upsert_doc(reply, ctx, q, u_doc, opts) catch |err|
             return update_refusal(reply, err, diag);
         ctx.engine.insert(db_name, coll_name, new_doc, ctx.oid_gen) catch |err| switch (err) {
             error.DuplicateKey, error.DuplicateKeyIndex => return duplicate_key_error(ctx, reply, db_name, coll_name, new_doc),
@@ -4404,8 +4404,17 @@ fn wrong_type_dynamic(
 
 /// Build the document for an upsert: equality fields from the filter, then
 /// the update operators applied. Owned by the reply arena.
+///
+/// The `_id` is settled *here* rather than in the storage engine. `insert`
+/// generates one into the bytes it writes and leaves the caller's tree without
+/// it, so `updateOne(..., {upsert: true}).upsertedId` came back null and
+/// `findOneAndUpdate` with `returnDocument: after` returned a document missing
+/// its `_id`. Both are what the client is told about a document it has never
+/// seen, and both were wrong. Found by `tests/spec/operators/`, which is the
+/// first corpus here to upsert into an empty collection and then look.
 fn build_upsert_doc(
     reply: *wire.Reply,
+    ctx: *Context,
     q: []const bson.Pair,
     u_doc: []const bson.Pair,
     opts: update.Options,
@@ -4428,6 +4437,16 @@ fn build_upsert_doc(
     var insert_opts = opts;
     insert_opts.inserting = true;
     try update.apply(owned, &.{ .arena = undefined, .pairs = u_doc }, insert_opts);
+    // After the operators, because `$setOnInsert` may supply the `_id` itself
+    // and a generated one would then be the wrong answer. At the front,
+    // because that is where MongoDB stores it and where the `_id_` index
+    // descends on it.
+    if (owned.get("_id") == null) {
+        const with_id = try arena.alloc(bson.Pair, owned.pairs.len + 1);
+        with_id[0] = .{ .key = "_id", .value = .{ .object_id = ctx.oid_gen.new(ctx.io) } };
+        @memcpy(with_id[1..], owned.pairs);
+        owned.pairs = with_id;
+    }
     return owned;
 }
 
@@ -7058,3 +7077,57 @@ test "a rebuild kills an offsets cursor and spares a streaming one" {
     try testing.expectEqual(@as(i64, 0), id);
     try testing.expectEqual(@as(u32, 60), seen);
 }
+
+test "an upsert reports the _id it generated" {
+    // The client has never seen this document, so the `_id` in the reply is
+    // the only way it can name it again. `Engine.insert` generates one into
+    // the bytes it writes and leaves the caller's tree without it, so both
+    // `upserted` here and `findAndModify`'s returned document used to come
+    // back without an `_id` at all -- `upsertedId: null` on the driver.
+    //
+    // Mutation check: delete the `_id` block in `build_upsert_doc` and both
+    // halves go red.
+    var threaded: std.Io.Threaded = .init_single_threaded;
+    defer threaded.deinit();
+    const io = threaded.io();
+    var tdb = try TestDb.init(io);
+    defer tdb.deinit();
+    var ctx = tdb.ctx(io);
+
+    const updates = [_]bson.Value{.{ .doc = &.{
+        .{ .key = "q", .value = .{ .doc = &.{.{ .key = "k", .value = .{ .int32 = 1 } }} } },
+        .{ .key = "u", .value = .{ .doc = &.{
+            .{ .key = "$set", .value = .{ .doc = &.{.{ .key = "a", .value = .{ .int32 = 1 } }} } },
+        } } },
+        .{ .key = "upsert", .value = .{ .bool = true } },
+    } }};
+    var reply = wire.Reply.init(testing.allocator);
+    defer reply.deinit();
+    var msg = try parse_fake_msg("update", .{ .string = "up" }, &.{
+        .{ .key = "updates", .value = .{ .array = &updates } },
+    });
+    defer msg.deinit();
+    try dispatch(&ctx, &msg, &reply);
+    const upserted = bson.get_pair(reply.pairs.items, "upserted").?.array;
+    try testing.expectEqual(@as(usize, 1), upserted.len);
+    try testing.expect(bson.get_pair(upserted[0].doc, "_id").? == .object_id);
+
+    // And an `_id` the update supplied itself is the one that is used, rather
+    // than being generated over.
+    const with_id = [_]bson.Value{.{ .doc = &.{
+        .{ .key = "q", .value = .{ .doc = &.{.{ .key = "k", .value = .{ .int32 = 2 } }} } },
+        .{ .key = "u", .value = .{ .doc = &.{
+            .{ .key = "$setOnInsert", .value = .{ .doc = &.{.{ .key = "_id", .value = .{ .int32 = 9 } }} } },
+        } } },
+        .{ .key = "upsert", .value = .{ .bool = true } },
+    } }};
+    var reply2 = wire.Reply.init(testing.allocator);
+    defer reply2.deinit();
+    var msg2 = try parse_fake_msg("update", .{ .string = "up" }, &.{
+        .{ .key = "updates", .value = .{ .array = &with_id } },
+    });
+    defer msg2.deinit();
+    try dispatch(&ctx, &msg2, &reply2);
+    const upserted2 = bson.get_pair(reply2.pairs.items, "upserted").?.array;
+    try testing.expectEqual(@as(i32, 9), bson.get_pair(upserted2[0].doc, "_id").?.int32);
+}