From e62a807b600a56a45e3a88f2adc6f8313635b76d Mon Sep 17 00:00:00 2001
From: Louis Dureuil <louis@meilisearch.com>
Date: Tue, 29 Jul 2025 13:56:47 +0200
Subject: [PATCH] Add new `milli::update::new::indexer::sharding` module

---
 crates/milli/src/update/new/indexer/mod.rs    |  1 +
 .../milli/src/update/new/indexer/sharding.rs  | 22 +++++++++++++++++++
 2 files changed, 23 insertions(+)
 create mode 100644 crates/milli/src/update/new/indexer/sharding.rs

diff --git a/crates/milli/src/update/new/indexer/mod.rs b/crates/milli/src/update/new/indexer/mod.rs
index a6ba3a919..b24081c02 100644
--- a/crates/milli/src/update/new/indexer/mod.rs
+++ b/crates/milli/src/update/new/indexer/mod.rs
@@ -36,6 +36,7 @@ mod guess_primary_key;
 mod partial_dump;
 mod post_processing;
 pub mod settings_changes;
+pub mod sharding;
 mod update_by_function;
 mod write;
 
diff --git a/crates/milli/src/update/new/indexer/sharding.rs b/crates/milli/src/update/new/indexer/sharding.rs
new file mode 100644
index 000000000..c0322f868
--- /dev/null
+++ b/crates/milli/src/update/new/indexer/sharding.rs
@@ -0,0 +1,22 @@
+// Copyright © 2025 Meilisearch Some Rights Reserved
+// This file is part of Meilisearch Enterprise Edition (EE).
+// Use of this source code is governed by the Business Source License 1.1,
+// as found in the LICENSE-EE file or at <https://mariadb.com/bsl11>
+
+use std::hash::{BuildHasher as _, BuildHasherDefault};
+
+pub struct Shards {
+    pub own: Vec<String>,
+    pub others: Vec<String>,
+}
+
+impl Shards {
+    pub fn must_process(&self, docid: &str) -> bool {
+        let hasher = BuildHasherDefault::<twox_hash::XxHash3_64>::new();
+        let to_hash = |shard: &String| hasher.hash_one((shard, docid));
+
+        let max_hash = self.others.iter().map(to_hash).max().unwrap_or_default();
+
+        self.own.iter().map(to_hash).any(|hash| hash > max_hash)
+    }
+}