fix the missing batch in the dumps in meilisearch and meilitools

crates/dump/README.md

@@ -10,8 +10,10 @@ dump
 ├── instance-uid.uuid
 ├── keys.jsonl
 ├── metadata.json
-└── tasks
-    ├── update_files
-    │   └── [task_id].jsonl
+├── tasks
+│   ├── update_files
+│   │   └── [task_id].jsonl
+│   └── queue.jsonl
+└── batches
     └── queue.jsonl
-```
+```

crates/dump/src/lib.rs

@@ -228,6 +228,7 @@ pub(crate) mod test {
 
     use big_s::S;
     use maplit::{btreemap, btreeset};
+    use meilisearch_types::batches::{Batch, BatchEnqueuedAt, BatchStats};
     use meilisearch_types::facet_values_sort::FacetValuesSort;
     use meilisearch_types::features::{Network, Remote, RuntimeTogglableFeatures};
     use meilisearch_types::index_uid_pattern::IndexUidPattern;
@@ -235,7 +236,8 @@ pub(crate) mod test {
     use meilisearch_types::milli;
     use meilisearch_types::milli::update::Setting;
     use meilisearch_types::settings::{Checked, FacetingSettings, Settings};
-    use meilisearch_types::tasks::{Details, Status};
+    use meilisearch_types::task_view::DetailsView;
+    use meilisearch_types::tasks::{Details, Kind, Status};
     use serde_json::{json, Map, Value};
     use time::macros::datetime;
     use uuid::Uuid;
@@ -305,6 +307,30 @@ pub(crate) mod test {
         settings.check()
     }
 
+    pub fn create_test_batches() -> Vec<Batch> {
+        vec![Batch {
+            uid: 0,
+            details: DetailsView {
+                received_documents: Some(12),
+                indexed_documents: Some(Some(10)),
+                ..DetailsView::default()
+            },
+            progress: None,
+            stats: BatchStats {
+                total_nb_tasks: 1,
+                status: maplit::btreemap! { Status::Succeeded => 1 },
+                types: maplit::btreemap! { Kind::DocumentAdditionOrUpdate => 1 },
+                index_uids: maplit::btreemap! { "doggo".to_string() => 1 },
+            },
+            enqueued_at: Some(BatchEnqueuedAt {
+                earliest: datetime!(2022-11-11 0:00 UTC),
+                oldest: datetime!(2022-11-11 0:00 UTC),
+            }),
+            started_at: datetime!(2022-11-20 0:00 UTC),
+            finished_at: Some(datetime!(2022-11-21 0:00 UTC)),
+        }]
+    }
+
     pub fn create_test_tasks() -> Vec<(TaskDump, Option<Vec<Document>>)> {
         vec![
             (
@@ -427,6 +453,15 @@ pub(crate) mod test {
         index.flush().unwrap();
         index.settings(&settings).unwrap();
 
+        // ========== pushing the batch queue
+        let batches = create_test_batches();
+
+        let mut batch_queue = dump.create_batches_queue().unwrap();
+        for batch in &batches {
+            batch_queue.push_batch(batch).unwrap();
+        }
+        batch_queue.flush().unwrap();
+
         // ========== pushing the task queue
         let tasks = create_test_tasks();
 

crates/dump/src/reader/mod.rs

@@ -102,6 +102,13 @@ impl DumpReader {
         }
     }
 
+    pub fn batches(&mut self) -> Result<Box<dyn Iterator<Item = Result<v6::Batch>> + '_>> {
+        match self {
+            DumpReader::Current(current) => Ok(current.batches()),
+            DumpReader::Compat(_compat) => Ok(Box::new(std::iter::empty())),
+        }
+    }
+
     pub fn keys(&mut self) -> Result<Box<dyn Iterator<Item = Result<v6::Key>> + '_>> {
         match self {
             DumpReader::Current(current) => Ok(current.keys()),
@@ -227,6 +234,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2024-05-16 15:51:34.151044 +00:00:00");
         insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -348,6 +359,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2023-07-06 7:10:27.21958 +00:00:00");
         insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -412,6 +427,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
         insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -492,6 +511,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
         insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -569,6 +592,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
         assert_eq!(dump.instance_uid().unwrap(), None);
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -662,6 +689,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
         assert_eq!(dump.instance_uid().unwrap(), None);
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -755,6 +786,10 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
         assert_eq!(dump.instance_uid().unwrap(), None);
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -831,6 +866,10 @@ pub(crate) mod test {
         assert_eq!(dump.date(), None);
         assert_eq!(dump.instance_uid().unwrap(), None);
 
+        // batches didn't exists at the time
+        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
+
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();

crates/dump/src/reader/v6/mod.rs

@@ -18,6 +18,7 @@ pub type Checked = meilisearch_types::settings::Checked;
 pub type Unchecked = meilisearch_types::settings::Unchecked;
 
 pub type Task = crate::TaskDump;
+pub type Batch = meilisearch_types::batches::Batch;
 pub type Key = meilisearch_types::keys::Key;
 pub type RuntimeTogglableFeatures = meilisearch_types::features::RuntimeTogglableFeatures;
 pub type Network = meilisearch_types::features::Network;
@@ -49,6 +50,7 @@ pub struct V6Reader {
     instance_uid: Option<Uuid>,
     metadata: Metadata,
     tasks: BufReader<File>,
+    batches: Option<BufReader<File>>,
     keys: BufReader<File>,
     features: Option<RuntimeTogglableFeatures>,
     network: Option<Network>,
@@ -79,6 +81,12 @@ impl V6Reader {
         } else {
             None
         };
+        let batches = match File::open(dump.path().join("batches").join("queue.jsonl")) {
+            Ok(file) => Some(BufReader::new(file)),
+            // The batch file was only introduced during the v1.13, anything prior to that won't have batches
+            Err(err) if err.kind() == ErrorKind::NotFound => None,
+            Err(e) => return Err(e.into()),
+        };
 
         let network_file = match fs::read(dump.path().join("network.json")) {
             Ok(network_file) => Some(network_file),
@@ -101,6 +109,7 @@ impl V6Reader {
             metadata: serde_json::from_reader(&*meta_file)?,
             instance_uid,
             tasks: BufReader::new(File::open(dump.path().join("tasks").join("queue.jsonl"))?),
+            batches,
             keys: BufReader::new(File::open(dump.path().join("keys.jsonl"))?),
             features,
             network,
@@ -144,7 +153,7 @@ impl V6Reader {
         &mut self,
     ) -> Box<dyn Iterator<Item = Result<(Task, Option<Box<super::UpdateFile>>)>> + '_> {
         Box::new((&mut self.tasks).lines().map(|line| -> Result<_> {
-            let task: Task = serde_json::from_str(&line?).unwrap();
+            let task: Task = serde_json::from_str(&line?)?;
 
             let update_file_path = self
                 .dump
@@ -156,8 +165,7 @@ impl V6Reader {
             if update_file_path.exists() {
                 Ok((
                     task,
-                    Some(Box::new(UpdateFile::new(&update_file_path).unwrap())
-                        as Box<super::UpdateFile>),
+                    Some(Box::new(UpdateFile::new(&update_file_path)?) as Box<super::UpdateFile>),
                 ))
             } else {
                 Ok((task, None))
@@ -165,6 +173,16 @@ impl V6Reader {
         }))
     }
 
+    pub fn batches(&mut self) -> Box<dyn Iterator<Item = Result<Batch>> + '_> {
+        match self.batches.as_mut() {
+            Some(batches) => Box::new((batches).lines().map(|line| -> Result<_> {
+                let batch = serde_json::from_str(&line?)?;
+                Ok(batch)
+            })),
+            None => Box::new(std::iter::empty()) as Box<dyn Iterator<Item = Result<Batch>> + '_>,
+        }
+    }
+
     pub fn keys(&mut self) -> Box<dyn Iterator<Item = Result<Key>> + '_> {
         Box::new(
             (&mut self.keys).lines().map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }),

crates/dump/src/writer.rs

@@ -4,6 +4,7 @@ use std::path::PathBuf;
 
 use flate2::write::GzEncoder;
 use flate2::Compression;
+use meilisearch_types::batches::Batch;
 use meilisearch_types::features::{Network, RuntimeTogglableFeatures};
 use meilisearch_types::keys::Key;
 use meilisearch_types::settings::{Checked, Settings};
@@ -54,6 +55,10 @@ impl DumpWriter {
         TaskWriter::new(self.dir.path().join("tasks"))
     }
 
+    pub fn create_batches_queue(&self) -> Result<BatchWriter> {
+        BatchWriter::new(self.dir.path().join("batches"))
+    }
+
     pub fn create_experimental_features(&self, features: RuntimeTogglableFeatures) -> Result<()> {
         Ok(std::fs::write(
             self.dir.path().join("experimental-features.json"),
@@ -130,6 +135,30 @@ impl TaskWriter {
     }
 }
 
+pub struct BatchWriter {
+    queue: BufWriter<File>,
+}
+
+impl BatchWriter {
+    pub(crate) fn new(path: PathBuf) -> Result<Self> {
+        std::fs::create_dir(&path)?;
+        let queue = File::create(path.join("queue.jsonl"))?;
+        Ok(BatchWriter { queue: BufWriter::new(queue) })
+    }
+
+    /// Pushes batches in the dump.
+    pub fn push_batch(&mut self, batch: &Batch) -> Result<()> {
+        self.queue.write_all(&serde_json::to_vec(batch)?)?;
+        self.queue.write_all(b"\n")?;
+        Ok(())
+    }
+
+    pub fn flush(mut self) -> Result<()> {
+        self.queue.flush()?;
+        Ok(())
+    }
+}
+
 pub struct UpdateFile {
     path: PathBuf,
     writer: Option<BufWriter<File>>,
@@ -209,8 +238,8 @@ pub(crate) mod test {
     use super::*;
     use crate::reader::Document;
     use crate::test::{
-        create_test_api_keys, create_test_documents, create_test_dump, create_test_instance_uid,
-        create_test_settings, create_test_tasks,
+        create_test_api_keys, create_test_batches, create_test_documents, create_test_dump,
+        create_test_instance_uid, create_test_settings, create_test_tasks,
     };
 
     fn create_directory_hierarchy(dir: &Path) -> String {
@@ -285,8 +314,10 @@ pub(crate) mod test {
         let dump_path = dump.path();
 
         // ==== checking global file hierarchy (we want to be sure there isn't too many files or too few)
-        insta::assert_snapshot!(create_directory_hierarchy(dump_path), @r###"
+        insta::assert_snapshot!(create_directory_hierarchy(dump_path), @r"
         .
+        ├---- batches/
+        │    └---- queue.jsonl
         ├---- indexes/
         │    └---- doggos/
         │    │    ├---- documents.jsonl
@@ -301,7 +332,7 @@ pub(crate) mod test {
         ├---- keys.jsonl
         ├---- metadata.json
         └---- network.json
-        "###);
+        ");
 
         // ==== checking the top level infos
         let metadata = fs::read_to_string(dump_path.join("metadata.json")).unwrap();
@@ -354,6 +385,16 @@ pub(crate) mod test {
             }
         }
 
+        // ==== checking the batch queue
+        let batches_queue = fs::read_to_string(dump_path.join("batches/queue.jsonl")).unwrap();
+        for (batch, expected) in batches_queue.lines().zip(create_test_batches()) {
+            let mut batch = serde_json::from_str::<Batch>(batch).unwrap();
+            if batch.details.settings == Some(Box::new(Settings::<Unchecked>::default())) {
+                batch.details.settings = None;
+            }
+            assert_eq!(batch, expected, "{batch:#?}{expected:#?}");
+        }
+
         // ==== checking the keys
         let keys = fs::read_to_string(dump_path.join("keys.jsonl")).unwrap();
         for (key, expected) in keys.lines().zip(create_test_api_keys()) {