Merge #4069

4069: Revert the fix on the filters about escaping sequences r=irevoire a=Kerollmops

This PR reverts #4038 as it introduces a breaking change. However, the fix will be kept for the v1.4.0 release.

Co-authored-by: Clément Renault <renault.cle@gmail.com>

Cargo.lock

@@ -469,7 +469,7 @@ checksum = "8c3c1a368f70d6cf7302d78f8f7093da241fb8e8807c05cc9e51a125895a6d5b"
 
 [[package]]
 name = "benchmarks"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "anyhow",
  "bytes",
@@ -700,9 +700,9 @@ dependencies = [
 
 [[package]]
 name = "charabia"
-version = "0.8.2"
+version = "0.8.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "57aa1b4a8dda126c03ebf2f7e31d16cfc8781c2fe80dedd1a33459efc3e07578"
+checksum = "098219a776307414866165a03a9cc68c1578764fe3616fe979e1c280790ddd73"
 dependencies = [
  "aho-corasick",
  "cow-utils",
@@ -1199,7 +1199,7 @@ dependencies = [
 
 [[package]]
 name = "dump"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "anyhow",
  "big_s",
@@ -1413,7 +1413,7 @@ dependencies = [
 
 [[package]]
 name = "file-store"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "faux",
  "tempfile",
@@ -1435,7 +1435,7 @@ dependencies = [
 
 [[package]]
 name = "filter-parser"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "insta",
  "nom",
@@ -1454,7 +1454,7 @@ dependencies = [
 
 [[package]]
 name = "flatten-serde-json"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "criterion",
  "serde_json",
@@ -1572,7 +1572,7 @@ dependencies = [
 
 [[package]]
 name = "fuzzers"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "arbitrary",
  "clap",
@@ -1737,8 +1737,8 @@ checksum = "95505c38b4572b2d910cecb0281560f54b440a19336cbbcb27bf6ce6adc6f5a8"
 
 [[package]]
 name = "heed"
-version = "0.12.5"
-source = "git+https://github.com/meilisearch/heed?tag=v0.12.6#8c5b94225fc949c02bb7b900cc50ffaf6b584b1e"
+version = "0.12.7"
+source = "git+https://github.com/meilisearch/heed?tag=v0.12.7#061a5276b1f336f5f3302bee291e336041d88632"
 dependencies = [
  "byteorder",
  "heed-traits",
@@ -1755,12 +1755,12 @@ dependencies = [
 [[package]]
 name = "heed-traits"
 version = "0.7.0"
-source = "git+https://github.com/meilisearch/heed?tag=v0.12.6#8c5b94225fc949c02bb7b900cc50ffaf6b584b1e"
+source = "git+https://github.com/meilisearch/heed?tag=v0.12.7#061a5276b1f336f5f3302bee291e336041d88632"
 
 [[package]]
 name = "heed-types"
 version = "0.7.2"
-source = "git+https://github.com/meilisearch/heed?tag=v0.12.6#8c5b94225fc949c02bb7b900cc50ffaf6b584b1e"
+source = "git+https://github.com/meilisearch/heed?tag=v0.12.7#061a5276b1f336f5f3302bee291e336041d88632"
 dependencies = [
  "bincode",
  "heed-traits",
@@ -1894,7 +1894,7 @@ dependencies = [
 
 [[package]]
 name = "index-scheduler"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "anyhow",
  "big_s",
@@ -2081,7 +2081,7 @@ dependencies = [
 
 [[package]]
 name = "json-depth-checker"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "criterion",
  "serde_json",
@@ -2493,7 +2493,7 @@ checksum = "490cc448043f947bae3cbee9c203358d62dbee0db12107a74be5c30ccfd09771"
 
 [[package]]
 name = "meili-snap"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "insta",
  "md5",
@@ -2502,7 +2502,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "actix-cors",
  "actix-http",
@@ -2591,7 +2591,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-auth"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "base64 0.21.2",
  "enum-iterator",
@@ -2610,7 +2610,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-types"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "actix-web",
  "anyhow",
@@ -2664,7 +2664,7 @@ dependencies = [
 
 [[package]]
 name = "milli"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "big_s",
  "bimap",
@@ -2994,7 +2994,7 @@ checksum = "478c572c3d73181ff3c2539045f6eb99e5491218eae919370993b890cdbdd98e"
 
 [[package]]
 name = "permissive-json-pointer"
-version = "1.3.0"
+version = "1.3.5"
 dependencies = [
  "big_s",
  "serde_json",

Cargo.toml

@@ -18,7 +18,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.3.0"
+version = "1.3.5"
 authors = ["Quentin de Quelen <quentin@dequelen.me>", "Clément Renault <clement@meilisearch.com>"]
 description = "Meilisearch HTTP server"
 homepage = "https://meilisearch.com"

README.md

@@ -61,7 +61,7 @@ You may also want to check out [Meilisearch 101](https://www.meilisearch.com/doc
 
 ## ⚡ Supercharge your Meilisearch experience
 
-Say goodbye to server deployment and manual updates with [Meilisearch Cloud](https://www.meilisearch.com/pricing?utm_campaign=oss&utm_source=engine&utm_medium=meilisearch). No credit card required.
+Say goodbye to server deployment and manual updates with [Meilisearch Cloud](https://www.meilisearch.com/cloud?utm_campaign=oss&utm_source=github&utm_medium=meilisearch). No credit card required.
 
 ## 🧰 SDKs & integration tools
 

dump/src/reader/snapshots/dump__reader__test__import_dump_v1-10.snap

@@ -0,0 +1,24 @@
+---
+source: dump/src/reader/mod.rs
+expression: spells.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "sortableAttributes": [],
+  "rankingRules": [
+    "typo",
+    "words",
+    "proximity",
+    "attribute",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

dump/src/reader/snapshots/dump__reader__test__import_dump_v1-4.snap

@@ -0,0 +1,38 @@
+---
+source: dump/src/reader/mod.rs
+expression: products.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [],
+  "sortableAttributes": [],
+  "rankingRules": [
+    "typo",
+    "words",
+    "proximity",
+    "attribute",
+    "exactness"
+  ],
+  "stopWords": [],
+  "synonyms": {
+    "android": [
+      "phone",
+      "smartphone"
+    ],
+    "iphone": [
+      "phone",
+      "smartphone"
+    ],
+    "phone": [
+      "android",
+      "iphone",
+      "smartphone"
+    ]
+  },
+  "distinctAttribute": null
+}

dump/src/reader/snapshots/dump__reader__test__import_dump_v1-7.snap

@@ -0,0 +1,31 @@
+---
+source: dump/src/reader/mod.rs
+expression: movies.settings().unwrap()
+---
+{
+  "displayedAttributes": [
+    "*"
+  ],
+  "searchableAttributes": [
+    "*"
+  ],
+  "filterableAttributes": [
+    "genres",
+    "id"
+  ],
+  "sortableAttributes": [
+    "genres",
+    "id"
+  ],
+  "rankingRules": [
+    "typo",
+    "words",
+    "proximity",
+    "attribute",
+    "exactness",
+    "release_date:asc"
+  ],
+  "stopWords": [],
+  "synonyms": {},
+  "distinctAttribute": null
+}

index-scheduler/src/batch.rs

@@ -67,10 +67,6 @@ pub(crate) enum Batch {
         op: IndexOperation,
         must_create_index: bool,
     },
-    IndexDocumentDeletionByFilter {
-        index_uid: String,
-        task: Task,
-    },
     IndexCreation {
         index_uid: String,
         primary_key: Option<String>,
@@ -114,6 +110,10 @@ pub(crate) enum IndexOperation {
         documents: Vec<Vec<String>>,
         tasks: Vec<Task>,
     },
+    IndexDocumentDeletionByFilter {
+        index_uid: String,
+        task: Task,
+    },
     DocumentClear {
         index_uid: String,
         tasks: Vec<Task>,
@@ -155,7 +155,6 @@ impl Batch {
             | Batch::TaskDeletion(task)
             | Batch::Dump(task)
             | Batch::IndexCreation { task, .. }
-            | Batch::IndexDocumentDeletionByFilter { task, .. }
             | Batch::IndexUpdate { task, .. } => vec![task.uid],
             Batch::SnapshotCreation(tasks) | Batch::IndexDeletion { tasks, .. } => {
                 tasks.iter().map(|task| task.uid).collect()
@@ -167,6 +166,7 @@ impl Batch {
                 | IndexOperation::DocumentClear { tasks, .. } => {
                     tasks.iter().map(|task| task.uid).collect()
                 }
+                IndexOperation::IndexDocumentDeletionByFilter { task, .. } => vec![task.uid],
                 IndexOperation::SettingsAndDocumentOperation {
                     document_import_tasks: tasks,
                     settings_tasks: other,
@@ -194,8 +194,7 @@ impl Batch {
             IndexOperation { op, .. } => Some(op.index_uid()),
             IndexCreation { index_uid, .. }
             | IndexUpdate { index_uid, .. }
-            | IndexDeletion { index_uid, .. }
-            | IndexDocumentDeletionByFilter { index_uid, .. } => Some(index_uid),
+            | IndexDeletion { index_uid, .. } => Some(index_uid),
         }
     }
 }
@@ -205,6 +204,7 @@ impl IndexOperation {
         match self {
             IndexOperation::DocumentOperation { index_uid, .. }
             | IndexOperation::DocumentDeletion { index_uid, .. }
+            | IndexOperation::IndexDocumentDeletionByFilter { index_uid, .. }
             | IndexOperation::DocumentClear { index_uid, .. }
             | IndexOperation::Settings { index_uid, .. }
             | IndexOperation::DocumentClearAndSetting { index_uid, .. }
@@ -239,9 +239,12 @@ impl IndexScheduler {
                 let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
                 match &task.kind {
                     KindWithContent::DocumentDeletionByFilter { index_uid, .. } => {
-                        Ok(Some(Batch::IndexDocumentDeletionByFilter {
-                            index_uid: index_uid.clone(),
-                            task,
+                        Ok(Some(Batch::IndexOperation {
+                            op: IndexOperation::IndexDocumentDeletionByFilter {
+                                index_uid: index_uid.clone(),
+                                task,
+                            },
+                            must_create_index: false,
                         }))
                     }
                     _ => unreachable!(),
@@ -891,51 +894,6 @@ impl IndexScheduler {
 
                 Ok(tasks)
             }
-            Batch::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
-                let (index_uid, filter) =
-                    if let KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr } =
-                        &task.kind
-                    {
-                        (index_uid, filter_expr)
-                    } else {
-                        unreachable!()
-                    };
-                let index = {
-                    let rtxn = self.env.read_txn()?;
-                    self.index_mapper.index(&rtxn, index_uid)?
-                };
-                let deleted_documents = delete_document_by_filter(filter, index);
-                let original_filter = if let Some(Details::DocumentDeletionByFilter {
-                    original_filter,
-                    deleted_documents: _,
-                }) = task.details
-                {
-                    original_filter
-                } else {
-                    // In the case of a `documentDeleteByFilter` the details MUST be set
-                    unreachable!();
-                };
-
-                match deleted_documents {
-                    Ok(deleted_documents) => {
-                        task.status = Status::Succeeded;
-                        task.details = Some(Details::DocumentDeletionByFilter {
-                            original_filter,
-                            deleted_documents: Some(deleted_documents),
-                        });
-                    }
-                    Err(e) => {
-                        task.status = Status::Failed;
-                        task.details = Some(Details::DocumentDeletionByFilter {
-                            original_filter,
-                            deleted_documents: Some(0),
-                        });
-                        task.error = Some(e.into());
-                    }
-                }
-
-                Ok(vec![task])
-            }
             Batch::IndexCreation { index_uid, primary_key, task } => {
                 let wtxn = self.env.write_txn()?;
                 if self.index_mapper.exists(&wtxn, &index_uid)? {
@@ -1292,6 +1250,47 @@ impl IndexScheduler {
 
                 Ok(tasks)
             }
+            IndexOperation::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
+                let filter =
+                    if let KindWithContent::DocumentDeletionByFilter { filter_expr, .. } =
+                        &task.kind
+                    {
+                        filter_expr
+                    } else {
+                        unreachable!()
+                    };
+                let deleted_documents = delete_document_by_filter(index_wtxn, filter, index);
+                let original_filter = if let Some(Details::DocumentDeletionByFilter {
+                    original_filter,
+                    deleted_documents: _,
+                }) = task.details
+                {
+                    original_filter
+                } else {
+                    // In the case of a `documentDeleteByFilter` the details MUST be set
+                    unreachable!();
+                };
+
+                match deleted_documents {
+                    Ok(deleted_documents) => {
+                        task.status = Status::Succeeded;
+                        task.details = Some(Details::DocumentDeletionByFilter {
+                            original_filter,
+                            deleted_documents: Some(deleted_documents),
+                        });
+                    }
+                    Err(e) => {
+                        task.status = Status::Failed;
+                        task.details = Some(Details::DocumentDeletionByFilter {
+                            original_filter,
+                            deleted_documents: Some(0),
+                        });
+                        task.error = Some(e.into());
+                    }
+                }
+
+                Ok(vec![task])
+            }
             IndexOperation::Settings { index_uid: _, settings, mut tasks } => {
                 let indexer_config = self.index_mapper.indexer_config();
                 let mut builder = milli::update::Settings::new(index_wtxn, index, indexer_config);
@@ -1491,23 +1490,22 @@ impl IndexScheduler {
     }
 }
 
-fn delete_document_by_filter(filter: &serde_json::Value, index: Index) -> Result<u64> {
+fn delete_document_by_filter<'a>(
+    wtxn: &mut RwTxn<'a, '_>,
+    filter: &serde_json::Value,
+    index: &'a Index,
+) -> Result<u64> {
     let filter = Filter::from_json(filter)?;
     Ok(if let Some(filter) = filter {
-        let mut wtxn = index.write_txn()?;
-
-        let candidates = filter.evaluate(&wtxn, &index).map_err(|err| match err {
+        let candidates = filter.evaluate(wtxn, index).map_err(|err| match err {
             milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
                 Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter)
             }
             e => e.into(),
         })?;
-        let mut delete_operation = DeleteDocuments::new(&mut wtxn, &index)?;
+        let mut delete_operation = DeleteDocuments::new(wtxn, index)?;
         delete_operation.delete_documents(&candidates);
-        let deleted_documents =
-            delete_operation.execute().map(|result| result.deleted_documents)?;
-        wtxn.commit()?;
-        deleted_documents
+        delete_operation.execute().map(|result| result.deleted_documents)?
     } else {
         0
     })

index-scheduler/src/lib.rs

@@ -790,10 +790,19 @@ impl IndexScheduler {
 
         let mut res = BTreeMap::new();
 
+        let processing_tasks = { self.processing_tasks.read().unwrap().processing.len() };
+
         res.insert(
             "statuses".to_string(),
             enum_iterator::all::<Status>()
-                .map(|s| Ok((s.to_string(), self.get_status(&rtxn, s)?.len())))
+                .map(|s| {
+                    let tasks = self.get_status(&rtxn, s)?.len();
+                    match s {
+                        Status::Enqueued => Ok((s.to_string(), tasks - processing_tasks)),
+                        Status::Processing => Ok((s.to_string(), processing_tasks)),
+                        s => Ok((s.to_string(), tasks)),
+                    }
+                })
                 .collect::<Result<BTreeMap<String, u64>>>()?,
         );
         res.insert(
@@ -4129,4 +4138,154 @@ mod tests {
         snapshot!(json_string!(tasks, { "[].enqueuedAt" => "[date]", "[].startedAt" => "[date]", "[].finishedAt" => "[date]", ".**.original_filter" => "[filter]", ".**.query" => "[query]" }), name: "everything_has_been_processed");
         drop(rtxn);
     }
+
+    #[test]
+    fn basic_get_stats() {
+        let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
+
+        let kind = index_creation_task("catto", "mouse");
+        let _task = index_scheduler.register(kind).unwrap();
+        let kind = index_creation_task("doggo", "sheep");
+        let _task = index_scheduler.register(kind).unwrap();
+        let kind = index_creation_task("whalo", "fish");
+        let _task = index_scheduler.register(kind).unwrap();
+
+        snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
+        {
+          "indexes": {
+            "catto": 1,
+            "doggo": 1,
+            "whalo": 1
+          },
+          "statuses": {
+            "canceled": 0,
+            "enqueued": 3,
+            "failed": 0,
+            "processing": 0,
+            "succeeded": 0
+          },
+          "types": {
+            "documentAdditionOrUpdate": 0,
+            "documentDeletion": 0,
+            "dumpCreation": 0,
+            "indexCreation": 3,
+            "indexDeletion": 0,
+            "indexSwap": 0,
+            "indexUpdate": 0,
+            "settingsUpdate": 0,
+            "snapshotCreation": 0,
+            "taskCancelation": 0,
+            "taskDeletion": 0
+          }
+        }
+        "###);
+
+        handle.advance_till([Start, BatchCreated]);
+        snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
+        {
+          "indexes": {
+            "catto": 1,
+            "doggo": 1,
+            "whalo": 1
+          },
+          "statuses": {
+            "canceled": 0,
+            "enqueued": 2,
+            "failed": 0,
+            "processing": 1,
+            "succeeded": 0
+          },
+          "types": {
+            "documentAdditionOrUpdate": 0,
+            "documentDeletion": 0,
+            "dumpCreation": 0,
+            "indexCreation": 3,
+            "indexDeletion": 0,
+            "indexSwap": 0,
+            "indexUpdate": 0,
+            "settingsUpdate": 0,
+            "snapshotCreation": 0,
+            "taskCancelation": 0,
+            "taskDeletion": 0
+          }
+        }
+        "###);
+
+        handle.advance_till([
+            InsideProcessBatch,
+            InsideProcessBatch,
+            ProcessBatchSucceeded,
+            AfterProcessing,
+            Start,
+            BatchCreated,
+        ]);
+        snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
+        {
+          "indexes": {
+            "catto": 1,
+            "doggo": 1,
+            "whalo": 1
+          },
+          "statuses": {
+            "canceled": 0,
+            "enqueued": 1,
+            "failed": 0,
+            "processing": 1,
+            "succeeded": 1
+          },
+          "types": {
+            "documentAdditionOrUpdate": 0,
+            "documentDeletion": 0,
+            "dumpCreation": 0,
+            "indexCreation": 3,
+            "indexDeletion": 0,
+            "indexSwap": 0,
+            "indexUpdate": 0,
+            "settingsUpdate": 0,
+            "snapshotCreation": 0,
+            "taskCancelation": 0,
+            "taskDeletion": 0
+          }
+        }
+        "###);
+
+        // now we make one more batch, the started_at field of the new tasks will be past `second_start_time`
+        handle.advance_till([
+            InsideProcessBatch,
+            InsideProcessBatch,
+            ProcessBatchSucceeded,
+            AfterProcessing,
+            Start,
+            BatchCreated,
+        ]);
+        snapshot!(json_string!(index_scheduler.get_stats().unwrap()), @r###"
+        {
+          "indexes": {
+            "catto": 1,
+            "doggo": 1,
+            "whalo": 1
+          },
+          "statuses": {
+            "canceled": 0,
+            "enqueued": 0,
+            "failed": 0,
+            "processing": 1,
+            "succeeded": 2
+          },
+          "types": {
+            "documentAdditionOrUpdate": 0,
+            "documentDeletion": 0,
+            "dumpCreation": 0,
+            "indexCreation": 3,
+            "indexDeletion": 0,
+            "indexSwap": 0,
+            "indexUpdate": 0,
+            "settingsUpdate": 0,
+            "snapshotCreation": 0,
+            "taskCancelation": 0,
+            "taskDeletion": 0
+          }
+        }
+        "###);
+    }
 }

meili-snap/src/lib.rs

@@ -167,7 +167,9 @@ macro_rules! snapshot {
         let (settings, snap_name, _) = $crate::default_snapshot_settings_for_test(test_name, Some(&snap_name));
         settings.bind(|| {
             let snap = format!("{}", $value);
-            meili_snap::insta::assert_snapshot!(format!("{}", snap_name), snap);
+            insta::allow_duplicates! {
+                meili_snap::insta::assert_snapshot!(format!("{}", snap_name), snap);
+            }
         });
     };
     ($value:expr, @$inline:literal) => {
@@ -176,7 +178,9 @@ macro_rules! snapshot {
         let (settings, _, _) = $crate::default_snapshot_settings_for_test("", Some("_dummy_argument"));
         settings.bind(|| {
             let snap = format!("{}", $value);
-            meili_snap::insta::assert_snapshot!(snap, @$inline);
+            insta::allow_duplicates! {
+                meili_snap::insta::assert_snapshot!(snap, @$inline);
+            }
         });
     };
     ($value:expr) => {
@@ -194,7 +198,9 @@ macro_rules! snapshot {
         let (settings, snap_name, _) = $crate::default_snapshot_settings_for_test(test_name, None);
         settings.bind(|| {
             let snap = format!("{}", $value);
-            meili_snap::insta::assert_snapshot!(format!("{}", snap_name), snap);
+            insta::allow_duplicates! {
+                meili_snap::insta::assert_snapshot!(format!("{}", snap_name), snap);
+            }
         });
     };
 }

meilisearch/Cargo.toml

@@ -141,5 +141,5 @@ thai = ["meilisearch-types/thai"]
 greek = ["meilisearch-types/greek"]
 
 [package.metadata.mini-dashboard]
-assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.10/build.zip"
-sha1 = "974cd7729138f629fee323c16b4e4f2cfdff266f"
+assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.11/build.zip"
+sha1 = "83cd44ed1e5f97ecb581dc9f958a63f4ccc982d9"

meilisearch/src/main.rs

@@ -187,7 +187,7 @@ Anonymous telemetry:\t\"Enabled\""
     }
 
     eprintln!();
-    eprintln!("Check out Meilisearch Cloud!\thttps://cloud.meilisearch.com/login?utm_campaign=oss&utm_source=engine&utm_medium=cli");
+    eprintln!("Check out Meilisearch Cloud!\thttps://www.meilisearch.com/cloud?utm_campaign=oss&utm_source=engine&utm_medium=cli");
     eprintln!("Documentation:\t\t\thttps://www.meilisearch.com/docs");
     eprintln!("Source code:\t\t\thttps://github.com/meilisearch/meilisearch");
     eprintln!("Discord:\t\t\thttps://discord.meilisearch.com");

meilisearch/src/search.rs

@@ -666,6 +666,7 @@ fn compute_semantic_score(query: &[f32], vectors: Value) -> milli::Result<Option
         .map_err(InternalError::SerdeJson)?;
     Ok(vectors
         .into_iter()
+        .flatten()
         .map(|v| OrderedFloat(dot_product_similarity(query, &v)))
         .max()
         .map(OrderedFloat::into_inner))

meilisearch/tests/documents/delete_documents.rs

@@ -154,6 +154,19 @@ async fn delete_document_by_filter() {
         )
         .await;
     index.wait_task(1).await;
+
+    let (stats, _) = index.stats().await;
+    snapshot!(json_string!(stats), @r###"
+    {
+      "numberOfDocuments": 4,
+      "isIndexing": false,
+      "fieldDistribution": {
+        "color": 3,
+        "id": 4
+      }
+    }
+    "###);
+
     let (response, code) =
         index.delete_document_by_filter(json!({ "filter": "color = blue"})).await;
     snapshot!(code, @"202 Accepted");
@@ -188,6 +201,18 @@ async fn delete_document_by_filter() {
     }
     "###);
 
+    let (stats, _) = index.stats().await;
+    snapshot!(json_string!(stats), @r###"
+    {
+      "numberOfDocuments": 2,
+      "isIndexing": false,
+      "fieldDistribution": {
+        "color": 1,
+        "id": 2
+      }
+    }
+    "###);
+
     let (documents, code) = index.get_all_documents(GetAllDocumentsOptions::default()).await;
     snapshot!(code, @"200 OK");
     snapshot!(json_string!(documents), @r###"
@@ -241,6 +266,18 @@ async fn delete_document_by_filter() {
     }
     "###);
 
+    let (stats, _) = index.stats().await;
+    snapshot!(json_string!(stats), @r###"
+    {
+      "numberOfDocuments": 1,
+      "isIndexing": false,
+      "fieldDistribution": {
+        "color": 1,
+        "id": 1
+      }
+    }
+    "###);
+
     let (documents, code) = index.get_all_documents(GetAllDocumentsOptions::default()).await;
     snapshot!(code, @"200 OK");
     snapshot!(json_string!(documents), @r###"

meilisearch/tests/search/geo.rs

@@ -1,3 +1,4 @@
+use meili_snap::{json_string, snapshot};
 use once_cell::sync::Lazy;
 use serde_json::{json, Value};
 
@@ -60,3 +61,59 @@ async fn geo_sort_with_geo_strings() {
         )
         .await;
 }
+
+#[actix_rt::test]
+async fn geo_bounding_box_with_string_and_number() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let documents = DOCUMENTS.clone();
+    index.update_settings_filterable_attributes(json!(["_geo"])).await;
+    index.update_settings_sortable_attributes(json!(["_geo"])).await;
+    index.add_documents(documents, None).await;
+    index.wait_task(2).await;
+
+    index
+        .search(
+            json!({
+                "filter": "_geoBoundingBox([89, 179], [-89, -179])",
+            }),
+            |response, code| {
+                assert_eq!(code, 200, "{}", response);
+                snapshot!(json_string!(response, { ".processingTimeMs" => "[time]" }), @r###"
+                {
+                  "hits": [
+                    {
+                      "id": 1,
+                      "name": "Taco Truck",
+                      "address": "444 Salsa Street, Burritoville",
+                      "type": "Mexican",
+                      "rating": 9,
+                      "_geo": {
+                        "lat": 34.0522,
+                        "lng": -118.2437
+                      }
+                    },
+                    {
+                      "id": 2,
+                      "name": "La Bella Italia",
+                      "address": "456 Elm Street, Townsville",
+                      "type": "Italian",
+                      "rating": 9,
+                      "_geo": {
+                        "lat": "45.4777599",
+                        "lng": "9.1967508"
+                      }
+                    }
+                  ],
+                  "query": "",
+                  "processingTimeMs": "[time]",
+                  "limit": 20,
+                  "offset": 0,
+                  "estimatedTotalHits": 2
+                }
+                "###);
+            },
+        )
+        .await;
+}

meilisearch/tests/search/mod.rs

@@ -820,8 +820,8 @@ async fn experimental_feature_score_details() {
                       },
                       "attribute": {
                         "order": 3,
-                        "attribute_ranking_order_score": 1.0,
-                        "query_word_distance_score": 0.8095238095238095,
+                        "attributeRankingOrderScore": 1.0,
+                        "queryWordDistanceScore": 0.8095238095238095,
                         "score": 0.9365079365079364
                       },
                       "exactness": {

milli/Cargo.toml

@@ -17,7 +17,7 @@ bincode = "1.3.3"
 bstr = "1.4.0"
 bytemuck = { version = "1.13.1", features = ["extern_crate_alloc"] }
 byteorder = "1.4.3"
-charabia = { version = "0.8.2", default-features = false }
+charabia = { version = "0.8.3", default-features = false }
 concat-arrays = "0.1.2"
 crossbeam-channel = "0.5.8"
 deserr = "0.5.0"
@@ -29,9 +29,8 @@ geoutils = "0.5.1"
 grenad = { version = "0.4.4", default-features = false, features = [
     "tempfile",
 ] }
-heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.6", default-features = false, features = [
-    "lmdb",
-    "sync-read-txn",
+heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.7", default-features = false, features = [
+    "lmdb", "read-txn-no-tls"
 ] }
 indexmap = { version = "1.9.3", features = ["serde"] }
 instant-distance = { version = "0.6.1", features = ["with-serde"] }

milli/src/index.rs

@@ -1718,11 +1718,11 @@ pub(crate) mod tests {
             .unwrap();
         index
             .add_documents(documents!([
-                { "id": 0, "_geo": { "lat": 0, "lng": 0 } },
-                { "id": 1, "_geo": { "lat": 0, "lng": -175 } },
-                { "id": 2, "_geo": { "lat": 0, "lng": 175 } },
+                { "id": 0, "_geo": { "lat": "0", "lng": "0" } },
+                { "id": 1, "_geo": { "lat": 0, "lng": "-175" } },
+                { "id": 2, "_geo": { "lat": "0", "lng": 175 } },
                 { "id": 3, "_geo": { "lat": 85, "lng": 0 } },
-                { "id": 4, "_geo": { "lat": -85, "lng": 0 } },
+                { "id": 4, "_geo": { "lat": "-85", "lng": "0" } },
             ]))
             .unwrap();
 

milli/src/lib.rs

@@ -97,7 +97,7 @@ const MAX_LMDB_KEY_LENGTH: usize = 500;
 ///
 /// This number is determined by the keys of the different facet databases
 /// and adding a margin of safety.
-pub const MAX_FACET_VALUE_LENGTH: usize = MAX_LMDB_KEY_LENGTH - 20;
+pub const MAX_FACET_VALUE_LENGTH: usize = MAX_LMDB_KEY_LENGTH - 32;
 
 /// The maximum length a word can be
 pub const MAX_WORD_LENGTH: usize = MAX_LMDB_KEY_LENGTH / 2;
@@ -293,15 +293,15 @@ pub fn normalize_facet(original: &str) -> String {
 #[derive(serde::Serialize, serde::Deserialize, Debug)]
 #[serde(transparent)]
 pub struct VectorOrArrayOfVectors {
-    #[serde(with = "either::serde_untagged")]
-    inner: either::Either<Vec<f32>, Vec<Vec<f32>>>,
+    #[serde(with = "either::serde_untagged_optional")]
+    inner: Option<either::Either<Vec<f32>, Vec<Vec<f32>>>>,
 }
 
 impl VectorOrArrayOfVectors {
-    pub fn into_array_of_vectors(self) -> Vec<Vec<f32>> {
-        match self.inner {
-            either::Either::Left(vector) => vec![vector],
-            either::Either::Right(vectors) => vectors,
+    pub fn into_array_of_vectors(self) -> Option<Vec<Vec<f32>>> {
+        match self.inner? {
+            either::Either::Left(vector) => Some(vec![vector]),
+            either::Either::Right(vectors) => Some(vectors),
         }
     }
 }

milli/src/score_details.rs

@@ -84,7 +84,7 @@ impl ScoreDetails {
                     // For now, fid is a virtual rule always followed by the "position" rule
                     let fid_details = serde_json::json!({
                         "order": order,
-                        "attribute_ranking_order_score": fid.local_score(),
+                        "attributeRankingOrderScore": fid.local_score(),
                     });
                     details_map.insert("attribute".into(), fid_details);
                     order += 1;
@@ -102,7 +102,7 @@ impl ScoreDetails {
                     };
 
                     attribute_details
-                        .insert("query_word_distance_score".into(), position.local_score().into());
+                        .insert("queryWordDistanceScore".into(), position.local_score().into());
                     let score = Rank::global_score([fid_details, *position].iter().copied());
                     attribute_details.insert("score".into(), score.into());
 

milli/src/search/new/bucket_sort.rs

@@ -91,11 +91,12 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
     /// Update the universes accordingly and inform the logger.
     macro_rules! back {
         () => {
-            assert!(
-                ranking_rule_universes[cur_ranking_rule_index].is_empty(),
-                "The ranking rule {} did not sort its bucket exhaustively",
-                ranking_rules[cur_ranking_rule_index].id()
-            );
+            // FIXME: temporarily disabled assert: see <https://github.com/meilisearch/meilisearch/pull/4013>
+            // assert!(
+            //     ranking_rule_universes[cur_ranking_rule_index].is_empty(),
+            //     "The ranking rule {} did not sort its bucket exhaustively",
+            //     ranking_rules[cur_ranking_rule_index].id()
+            // );
             logger.end_iteration_ranking_rule(
                 cur_ranking_rule_index,
                 ranking_rules[cur_ranking_rule_index].as_ref(),

milli/src/update/facet/mod.rs

@@ -94,7 +94,7 @@ use crate::heed_codec::facet::{FacetGroupKey, FacetGroupKeyCodec, FacetGroupValu
 use crate::heed_codec::ByteSliceRefCodec;
 use crate::update::index_documents::create_sorter;
 use crate::update::merge_btreeset_string;
-use crate::{BEU16StrCodec, Index, Result, BEU16};
+use crate::{BEU16StrCodec, Index, Result, BEU16, MAX_FACET_VALUE_LENGTH};
 
 pub mod bulk;
 pub mod delete;
@@ -191,7 +191,16 @@ impl<'i> FacetsUpdate<'i> {
         for result in database.iter(wtxn)? {
             let (facet_group_key, ()) = result?;
             if let FacetGroupKey { field_id, level: 0, left_bound } = facet_group_key {
-                let normalized_facet = left_bound.normalize(&options);
+                let mut normalized_facet = left_bound.normalize(&options);
+                let normalized_truncated_facet: String;
+                if normalized_facet.len() > MAX_FACET_VALUE_LENGTH {
+                    normalized_truncated_facet = normalized_facet
+                        .char_indices()
+                        .take_while(|(idx, _)| *idx < MAX_FACET_VALUE_LENGTH)
+                        .map(|(_, c)| c)
+                        .collect();
+                    normalized_facet = normalized_truncated_facet.into();
+                }
                 let set = BTreeSet::from_iter(std::iter::once(left_bound));
                 let key = (field_id, normalized_facet.as_ref());
                 let key = BEU16StrCodec::bytes_encode(&key).ok_or(heed::Error::Encoding)?;

milli/src/update/index_documents/extract/extract_facet_string_docids.rs

@@ -44,7 +44,7 @@ pub fn extract_facet_string_docids<R: io::Read + io::Seek>(
         if normalised_value.len() > MAX_FACET_VALUE_LENGTH {
             normalised_truncated_value = normalised_value
                 .char_indices()
-                .take_while(|(idx, _)| idx + 4 < MAX_FACET_VALUE_LENGTH)
+                .take_while(|(idx, _)| *idx < MAX_FACET_VALUE_LENGTH)
                 .map(|(_, c)| c)
                 .collect();
             normalised_value = normalised_truncated_value.as_str();

milli/src/update/index_documents/extract/extract_fid_docid_facet_values.rs

@@ -28,11 +28,13 @@ pub struct ExtractedFacetValues {
 ///
 /// Returns the generated grenad reader containing the docid the fid and the orginal value as key
 /// and the normalized value as value extracted from the given chunk of documents.
+/// We need the fid of the geofields to correctly parse them as numbers if they were sent as strings initially.
 #[logging_timer::time]
 pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
     obkv_documents: grenad::Reader<R>,
     indexer: GrenadParameters,
     faceted_fields: &HashSet<FieldId>,
+    geo_fields_ids: Option<(FieldId, FieldId)>,
 ) -> Result<ExtractedFacetValues> {
     let max_memory = indexer.max_memory_by_thread();
 
@@ -82,7 +84,10 @@ pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
 
                 let value = from_slice(field_bytes).map_err(InternalError::SerdeJson)?;
 
-                match extract_facet_values(&value) {
+                match extract_facet_values(
+                    &value,
+                    geo_fields_ids.map_or(false, |(lat, lng)| field_id == lat || field_id == lng),
+                ) {
                     FilterableValues::Null => {
                         facet_is_null_docids.entry(field_id).or_default().insert(document);
                     }
@@ -175,12 +180,13 @@ enum FilterableValues {
     Values { numbers: Vec<f64>, strings: Vec<(String, String)> },
 }
 
-fn extract_facet_values(value: &Value) -> FilterableValues {
+fn extract_facet_values(value: &Value, geo_field: bool) -> FilterableValues {
     fn inner_extract_facet_values(
         value: &Value,
         can_recurse: bool,
         output_numbers: &mut Vec<f64>,
         output_strings: &mut Vec<(String, String)>,
+        geo_field: bool,
     ) {
         match value {
             Value::Null => (),
@@ -191,13 +197,30 @@ fn extract_facet_values(value: &Value) -> FilterableValues {
                 }
             }
             Value::String(original) => {
+                // if we're working on a geofield it MUST be something we can parse or else there was an internal error
+                // in the enrich pipeline. But since the enrich pipeline worked, we want to avoid crashing at all costs.
+                if geo_field {
+                    if let Ok(float) = original.parse() {
+                        output_numbers.push(float);
+                    } else {
+                        log::warn!(
+                            "Internal error, could not parse a geofield that has been validated. Please open an issue."
+                        )
+                    }
+                }
                 let normalized = crate::normalize_facet(original);
                 output_strings.push((normalized, original.clone()));
             }
             Value::Array(values) => {
                 if can_recurse {
                     for value in values {
-                        inner_extract_facet_values(value, false, output_numbers, output_strings);
+                        inner_extract_facet_values(
+                            value,
+                            false,
+                            output_numbers,
+                            output_strings,
+                            geo_field,
+                        );
                     }
                 }
             }
@@ -213,7 +236,7 @@ fn extract_facet_values(value: &Value) -> FilterableValues {
         otherwise => {
             let mut numbers = Vec::new();
             let mut strings = Vec::new();
-            inner_extract_facet_values(otherwise, true, &mut numbers, &mut strings);
+            inner_extract_facet_values(otherwise, true, &mut numbers, &mut strings, geo_field);
             FilterableValues::Values { numbers, strings }
         }
     }

milli/src/update/index_documents/extract/extract_vector_points.rs

@@ -33,7 +33,7 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
         // lazily get it when needed
         let document_id = || -> Value {
             let document_id = obkv.get(primary_key_id).unwrap();
-            serde_json::from_slice(document_id).unwrap()
+            from_slice(document_id).unwrap()
         };
 
         // first we retrieve the _vectors field
@@ -50,12 +50,14 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
                 }
             };
 
-            for (i, vector) in vectors.into_iter().enumerate().take(u16::MAX as usize) {
-                let index = u16::try_from(i).unwrap();
-                let mut key = docid_bytes.to_vec();
-                key.extend_from_slice(&index.to_be_bytes());
-                let bytes = cast_slice(&vector);
-                writer.insert(key, bytes)?;
+            if let Some(vectors) = vectors {
+                for (i, vector) in vectors.into_iter().enumerate().take(u16::MAX as usize) {
+                    let index = u16::try_from(i).unwrap();
+                    let mut key = docid_bytes.to_vec();
+                    key.extend_from_slice(&index.to_be_bytes());
+                    let bytes = cast_slice(&vector);
+                    writer.insert(key, bytes)?;
+                }
             }
         }
         // else => the `_vectors` object was `null`, there is nothing to do

milli/src/update/index_documents/extract/mod.rs

@@ -55,7 +55,13 @@ pub(crate) fn data_from_obkv_documents(
     original_obkv_chunks
         .par_bridge()
         .map(|original_documents_chunk| {
-            send_original_documents_data(original_documents_chunk, lmdb_writer_sx.clone())
+            send_original_documents_data(
+                original_documents_chunk,
+                indexer,
+                lmdb_writer_sx.clone(),
+                vectors_field_id,
+                primary_key_id,
+            )
         })
         .collect::<Result<()>>()?;
 
@@ -72,7 +78,6 @@ pub(crate) fn data_from_obkv_documents(
                     &faceted_fields,
                     primary_key_id,
                     geo_fields_ids,
-                    vectors_field_id,
                     &stop_words,
                     max_positions_per_attributes,
                 )
@@ -257,11 +262,33 @@ fn spawn_extraction_task<FE, FS, M>(
 /// - documents
 fn send_original_documents_data(
     original_documents_chunk: Result<grenad::Reader<File>>,
+    indexer: GrenadParameters,
     lmdb_writer_sx: Sender<Result<TypedChunk>>,
+    vectors_field_id: Option<FieldId>,
+    primary_key_id: FieldId,
 ) -> Result<()> {
     let original_documents_chunk =
         original_documents_chunk.and_then(|c| unsafe { as_cloneable_grenad(&c) })?;
 
+    if let Some(vectors_field_id) = vectors_field_id {
+        let documents_chunk_cloned = original_documents_chunk.clone();
+        let lmdb_writer_sx_cloned = lmdb_writer_sx.clone();
+        rayon::spawn(move || {
+            let result = extract_vector_points(
+                documents_chunk_cloned,
+                indexer,
+                primary_key_id,
+                vectors_field_id,
+            );
+            let _ = match result {
+                Ok(vector_points) => {
+                    lmdb_writer_sx_cloned.send(Ok(TypedChunk::VectorPoints(vector_points)))
+                }
+                Err(error) => lmdb_writer_sx_cloned.send(Err(error)),
+            };
+        });
+    }
+
     // TODO: create a custom internal error
     lmdb_writer_sx.send(Ok(TypedChunk::Documents(original_documents_chunk))).unwrap();
     Ok(())
@@ -283,7 +310,6 @@ fn send_and_extract_flattened_documents_data(
     faceted_fields: &HashSet<FieldId>,
     primary_key_id: FieldId,
     geo_fields_ids: Option<(FieldId, FieldId)>,
-    vectors_field_id: Option<FieldId>,
     stop_words: &Option<fst::Set<&[u8]>>,
     max_positions_per_attributes: Option<u32>,
 ) -> Result<(
@@ -312,25 +338,6 @@ fn send_and_extract_flattened_documents_data(
         });
     }
 
-    if let Some(vectors_field_id) = vectors_field_id {
-        let documents_chunk_cloned = flattened_documents_chunk.clone();
-        let lmdb_writer_sx_cloned = lmdb_writer_sx.clone();
-        rayon::spawn(move || {
-            let result = extract_vector_points(
-                documents_chunk_cloned,
-                indexer,
-                primary_key_id,
-                vectors_field_id,
-            );
-            let _ = match result {
-                Ok(vector_points) => {
-                    lmdb_writer_sx_cloned.send(Ok(TypedChunk::VectorPoints(vector_points)))
-                }
-                Err(error) => lmdb_writer_sx_cloned.send(Err(error)),
-            };
-        });
-    }
-
     let (docid_word_positions_chunk, docid_fid_facet_values_chunks): (Result<_>, Result<_>) =
         rayon::join(
             || {
@@ -366,6 +373,7 @@ fn send_and_extract_flattened_documents_data(
                     flattened_documents_chunk.clone(),
                     indexer,
                     faceted_fields,
+                    geo_fields_ids,
                 )?;
 
                 // send docid_fid_facet_numbers_chunk to DB writer

milli/src/update/index_documents/mod.rs

@@ -2519,6 +2519,25 @@ mod tests {
         db_snap!(index, word_position_docids, 3, @"74f556b91d161d997a89468b4da1cb8f");
     }
 
+    /// Index multiple different number of vectors in documents.
+    /// Vectors must be of the same length.
+    #[test]
+    fn test_multiple_vectors() {
+        let index = TempIndex::new();
+
+        index.add_documents(documents!([{"id": 0, "_vectors": [[0, 1, 2], [3, 4, 5]] }])).unwrap();
+        index.add_documents(documents!([{"id": 1, "_vectors": [6, 7, 8] }])).unwrap();
+        index
+            .add_documents(
+                documents!([{"id": 2, "_vectors": [[9, 10, 11], [12, 13, 14], [15, 16, 17]] }]),
+            )
+            .unwrap();
+
+        let rtxn = index.read_txn().unwrap();
+        let res = index.search(&rtxn).vector([0.0, 1.0, 2.0]).execute().unwrap();
+        assert_eq!(res.documents_ids.len(), 3);
+    }
+
     #[test]
     fn reproduce_the_bug() {
         /*