Merge #5192

5192: Fix empty document addition r=irevoire a=irevoire

# Pull Request

## Related issue
Fixes #5190

## What does this PR do?
- Improve a test just to make sure this issue never arises again
- Fix the issue

For the reviewer: Calling `add_documents` with an empty `mmap` seems to work, but does it impact the perf in a significant way? / 

Co-authored-by: Tamo <tamo@meilisearch.com>

Cargo.lock

@@ -496,7 +496,7 @@ source = "git+https://github.com/meilisearch/bbqueue#cbb87cc707b5af415ef203bdaf2
 
 [[package]]
 name = "benchmarks"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "anyhow",
  "bumpalo",
@@ -689,7 +689,7 @@ dependencies = [
 
 [[package]]
 name = "build-info"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "anyhow",
  "time",
@@ -1664,7 +1664,7 @@ dependencies = [
 
 [[package]]
 name = "dump"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "anyhow",
  "big_s",
@@ -1876,7 +1876,7 @@ checksum = "486f806e73c5707928240ddc295403b1b93c96a02038563881c4a2fd84b81ac4"
 
 [[package]]
 name = "file-store"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "tempfile",
  "thiserror",
@@ -1898,7 +1898,7 @@ dependencies = [
 
 [[package]]
 name = "filter-parser"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "insta",
  "nom",
@@ -1918,7 +1918,7 @@ dependencies = [
 
 [[package]]
 name = "flatten-serde-json"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "criterion",
  "serde_json",
@@ -2057,7 +2057,7 @@ dependencies = [
 
 [[package]]
 name = "fuzzers"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "arbitrary",
  "bumpalo",
@@ -2624,7 +2624,7 @@ checksum = "206ca75c9c03ba3d4ace2460e57b189f39f43de612c2f85836e65c929701bb2d"
 
 [[package]]
 name = "index-scheduler"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "anyhow",
  "arroy 0.5.0 (registry+https://github.com/rust-lang/crates.io-index)",
@@ -2822,7 +2822,7 @@ dependencies = [
 
 [[package]]
 name = "json-depth-checker"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "criterion",
  "serde_json",
@@ -3441,7 +3441,7 @@ checksum = "490cc448043f947bae3cbee9c203358d62dbee0db12107a74be5c30ccfd09771"
 
 [[package]]
 name = "meili-snap"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "insta",
  "md5",
@@ -3450,7 +3450,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "actix-cors",
  "actix-http",
@@ -3540,7 +3540,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-auth"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "base64 0.22.1",
  "enum-iterator",
@@ -3559,7 +3559,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-types"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "actix-web",
  "anyhow",
@@ -3592,7 +3592,7 @@ dependencies = [
 
 [[package]]
 name = "meilitool"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "anyhow",
  "arroy 0.5.0 (git+https://github.com/meilisearch/arroy/?tag=DO-NOT-DELETE-upgrade-v04-to-v05)",
@@ -3627,7 +3627,7 @@ dependencies = [
 
 [[package]]
 name = "milli"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "allocator-api2",
  "arroy 0.5.0 (registry+https://github.com/rust-lang/crates.io-index)",
@@ -4083,7 +4083,7 @@ checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
 
 [[package]]
 name = "permissive-json-pointer"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "big_s",
  "serde_json",
@@ -6486,7 +6486,7 @@ dependencies = [
 
 [[package]]
 name = "xtask"
-version = "1.12.0"
+version = "1.12.1"
 dependencies = [
  "anyhow",
  "build-info",

Cargo.toml

@@ -22,7 +22,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.12.0"
+version = "1.12.1"
 authors = [
     "Quentin de Quelen <quentin@dequelen.me>",
     "Clément Renault <clement@meilisearch.com>",

crates/index-scheduler/src/batch.rs

@@ -1312,9 +1312,7 @@ impl IndexScheduler {
                     if let DocumentOperation::Add(content_uuid) = operation {
                         let content_file = self.file_store.get_update(*content_uuid)?;
                         let mmap = unsafe { memmap2::Mmap::map(&content_file)? };
-                        if !mmap.is_empty() {
+                        content_files.push(mmap);
-                            content_files.push(mmap);
-                        }
                     }
                 }
 

crates/index-scheduler/src/utils.rs

@@ -291,7 +291,10 @@ impl IndexScheduler {
 
         debug_assert!(old_task != *task);
         debug_assert_eq!(old_task.uid, task.uid);
-        debug_assert!(old_task.batch_uid.is_none() && task.batch_uid.is_some());
+        debug_assert!(
+            old_task.batch_uid.is_none() && task.batch_uid.is_some(),
+            "\n==> old: {old_task:?}\n==> new: {task:?}"
+        );
 
         if old_task.status != task.status {
             self.update_status(wtxn, old_task.status, |bitmap| {

crates/meilisearch/tests/documents/add_documents.rs

@@ -1220,9 +1220,89 @@ async fn replace_document() {
 #[actix_rt::test]
 async fn add_no_documents() {
     let server = Server::new().await;
-    let index = server.index("test");
+    let index = server.index("kefir");
-    let (_response, code) = index.add_documents(json!([]), None).await;
+    let (task, code) = index.add_documents(json!([]), None).await;
     snapshot!(code, @"202 Accepted");
+    let task = server.wait_task(task.uid()).await;
+    let task = task.succeeded();
+    snapshot!(task, @r#"
+    {
+      "uid": "[uid]",
+      "batchUid": "[batch_uid]",
+      "indexUid": "kefir",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 0,
+        "indexedDocuments": 0
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "#);
+
+    let (task, _code) = index.add_documents(json!([]), Some("kefkef")).await;
+    let task = server.wait_task(task.uid()).await;
+    let task = task.succeeded();
+    snapshot!(task, @r#"
+    {
+      "uid": "[uid]",
+      "batchUid": "[batch_uid]",
+      "indexUid": "kefir",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 0,
+        "indexedDocuments": 0
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "#);
+
+    let (task, _code) = index.add_documents(json!([{ "kefkef": 1 }]), None).await;
+    let task = server.wait_task(task.uid()).await;
+    let task = task.succeeded();
+    snapshot!(task, @r#"
+    {
+      "uid": "[uid]",
+      "batchUid": "[batch_uid]",
+      "indexUid": "kefir",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "#);
+    let (documents, _status) = index.get_all_documents(GetAllDocumentsOptions::default()).await;
+    snapshot!(documents, @r#"
+    {
+      "results": [
+        {
+          "kefkef": 1
+        }
+      ],
+      "offset": 0,
+      "limit": 20,
+      "total": 1
+    }
+    "#);
 }
 
 #[actix_rt::test]

crates/milli/src/update/new/indexer/document_operation.rs

@@ -252,6 +252,24 @@ fn extract_addition_payload_changes<'r, 'pl: 'r>(
         previous_offset = iter.byte_offset();
     }
 
+    if payload.is_empty() {
+        let result = retrieve_or_guess_primary_key(
+            rtxn,
+            index,
+            new_fields_ids_map,
+            primary_key_from_op,
+            None,
+        );
+        match result {
+            Ok(Ok((pk, _))) => {
+                primary_key.get_or_insert(pk);
+            }
+            Ok(Err(UserError::NoPrimaryKeyCandidateFound)) => (),
+            Ok(Err(user_error)) => return Err(Error::UserError(user_error)),
+            Err(error) => return Err(error),
+        };
+    }
+
     Ok(new_docids_version_offsets)
 }