jsonl support

meilisearch-lib/Cargo.toml

@@ -31,7 +31,7 @@ log = "0.4.14"
 meilisearch-error = { path = "../meilisearch-error" }
 meilisearch-tokenizer = { git = "https://github.com/meilisearch/tokenizer.git", tag = "v0.2.5" }
 memmap = "0.7.0"
-milli = { path = "../../milli/milli" }
+milli = { git = "https://github.com/meilisearch/milli.git", rev = "f65153ad6454317213680e9a9a908ec78d5645a7"}
 mime = "0.3.16"
 num_cpus = "1.13.0"
 once_cell = "1.8.0"

meilisearch-lib/src/document_formats.rs

@@ -1,5 +1,5 @@
-use std::io::{self, Read, Result as IoResult, Seek, Write};
 use std::fmt;
+use std::io::{self, Read, Result as IoResult, Seek, Write};
 
 use csv::{Reader as CsvReader, StringRecordsIntoIter};
 use milli::documents::DocumentBatchBuilder;
@@ -9,7 +9,7 @@ type Result<T> = std::result::Result<T, DocumentFormatError>;
 
 #[derive(Debug)]
 pub enum PayloadType {
-    Jsonl,
+    Ndjson,
     Json,
     Csv,
 }
@@ -17,7 +17,7 @@ pub enum PayloadType {
 impl fmt::Display for PayloadType {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         match self {
-            PayloadType::Jsonl => write!(f, "ndjson"),
+            PayloadType::Ndjson => write!(f, "ndjson"),
             PayloadType::Json => write!(f, "json"),
             PayloadType::Csv => write!(f, "csv"),
         }
@@ -56,14 +56,13 @@ pub fn read_csv(input: impl Read, writer: impl Write + Seek) -> Result<()> {
     Ok(())
 }
 
-
 /// read jsonl from input and write an obkv batch to writer.
-pub fn read_jsonl(input: impl Read, writer: impl Write + Seek) -> Result<()> {
+pub fn read_ndjson(input: impl Read, writer: impl Write + Seek) -> Result<()> {
     let mut builder = DocumentBatchBuilder::new(writer)?;
     let stream = Deserializer::from_reader(input).into_iter::<Map<String, Value>>();
 
     for value in stream {
-        let value = malformed!(PayloadType::Jsonl, value)?;
+        let value = malformed!(PayloadType::Ndjson, value)?;
         builder.add_documents(&value)?;
     }
 
@@ -84,7 +83,6 @@ pub fn read_json(input: impl Read, writer: impl Write + Seek) -> Result<()> {
     Ok(())
 }
 
-
 enum AllowedType {
     String,
     Number,
@@ -141,12 +139,12 @@ impl<R: Read> Iterator for CsvDocumentIter<R> {
                 for ((field_name, field_type), value) in
                     self.headers.iter().zip(csv_document.into_iter())
                 {
-                    let parsed_value = (|| match field_type {
-                        AllowedType::Number => malformed!(PayloadType::Csv, value
-                            .parse::<f64>()
-                            .map(Value::from)),
+                    let parsed_value = match field_type {
+                        AllowedType::Number => {
+                            malformed!(PayloadType::Csv, value.parse::<f64>().map(Value::from))
+                        }
                         AllowedType::String => Ok(Value::String(value.to_string())),
-                    })();
+                    };
 
                     match parsed_value {
                         Ok(value) => drop(document.insert(field_name.to_string(), value)),
@@ -156,7 +154,10 @@ impl<R: Read> Iterator for CsvDocumentIter<R> {
 
                 Some(Ok(document))
             }
-            Err(e) => Some(Err(DocumentFormatError::MalformedPayload(Box::new(e), PayloadType::Csv))),
+            Err(e) => Some(Err(DocumentFormatError::MalformedPayload(
+                Box::new(e),
+                PayloadType::Csv,
+            ))),
         }
     }
 }

meilisearch-lib/src/index/dump.rs

@@ -9,7 +9,7 @@ use milli::documents::DocumentBatchReader;
 use serde::{Deserialize, Serialize};
 use serde_json::Value;
 
-use crate::document_formats::read_jsonl;
+use crate::document_formats::read_ndjson;
 use crate::index::update_handler::UpdateHandler;
 use crate::index::updates::apply_settings_to_builder;
 use crate::index_controller::{asc_ranking_rule, desc_ranking_rule};
@@ -142,7 +142,7 @@ impl Index {
 
         let mut tmp_doc_file = tempfile::tempfile()?;
 
-        read_jsonl(reader, &mut tmp_doc_file)?;
+        read_ndjson(reader, &mut tmp_doc_file)?;
 
         tmp_doc_file.seek(SeekFrom::Start(0))?;
 

meilisearch-lib/src/index_controller/dump_actor/loaders/v1.rs

@@ -11,7 +11,7 @@ use milli::update::Setting;
 use serde::{Deserialize, Deserializer, Serialize};
 use uuid::Uuid;
 
-use crate::document_formats::read_jsonl;
+use crate::document_formats::read_ndjson;
 use crate::index::apply_settings_to_builder;
 use crate::index::update_handler::UpdateHandler;
 use crate::index_controller::index_resolver::uuid_store::HeedUuidStore;
@@ -124,7 +124,7 @@ fn load_index(
 
     let mut tmp_doc_file = tempfile::tempfile()?;
 
-    read_jsonl(reader, &mut tmp_doc_file)?;
+    read_ndjson(reader, &mut tmp_doc_file)?;
 
     tmp_doc_file.seek(SeekFrom::Start(0))?;
 
@@ -213,7 +213,7 @@ impl From<Settings> for index_controller::Settings<Unchecked> {
     }
 }
 
-// /// Extract Settings from `settings.json` file present at provided `dir_path`
+/// Extract Settings from `settings.json` file present at provided `dir_path`
 fn import_settings(dir_path: impl AsRef<Path>) -> anyhow::Result<Settings> {
     let path = dir_path.as_ref().join("settings.json");
     let file = File::open(path)?;

meilisearch-lib/src/index_controller/mod.rs

@@ -72,6 +72,7 @@ pub struct IndexController {
 pub enum DocumentAdditionFormat {
     Json,
     Csv,
+    Ndjson,
 }
 
 #[derive(Serialize, Debug)]

meilisearch-lib/src/index_controller/update_file_store.rs

@@ -10,7 +10,7 @@ use uuid::Uuid;
 
 const UPDATE_FILES_PATH: &str = "updates/updates_files";
 
-use crate::document_formats::read_jsonl;
+use crate::document_formats::read_ndjson;
 
 pub struct UpdateFile {
     path: PathBuf,
@@ -86,7 +86,7 @@ impl UpdateFileStore {
                 .ok_or_else(|| anyhow::anyhow!("invalid update file name"))?;
             let dst_path = dst_update_files_path.join(file_uuid);
             let dst_file = BufWriter::new(File::create(dst_path)?);
-            read_jsonl(update_file, dst_file)?;
+            read_ndjson(update_file, dst_file)?;
         }
 
         Ok(())
@@ -98,9 +98,9 @@ impl UpdateFileStore {
         Ok(Self { path })
     }
 
-    /// Created a new temporary update file.
+    /// Creates a new temporary update file.
     ///
-    /// A call to persist is needed to persist in the database.
+    /// A call to `persist` is needed to persist the file in the database.
     pub fn new_update(&self) -> Result<(Uuid, UpdateFile)> {
         let file = NamedTempFile::new()?;
         let uuid = Uuid::new_v4();
@@ -110,14 +110,14 @@ impl UpdateFileStore {
         Ok((uuid, update_file))
     }
 
-    /// Returns a the file corresponding to the requested uuid.
+    /// Returns the file corresponding to the requested uuid.
     pub fn get_update(&self, uuid: Uuid) -> Result<File> {
         let path = self.path.join(uuid.to_string());
         let file = File::open(path)?;
         Ok(file)
     }
 
-    /// Copies the content of the update file poited to by uuid to dst directory.
+    /// Copies the content of the update file pointed to by `uuid` to the `dst` directory.
     pub fn snapshot(&self, uuid: Uuid, dst: impl AsRef<Path>) -> Result<()> {
         let src = self.path.join(uuid.to_string());
         let mut dst = dst.as_ref().join(UPDATE_FILES_PATH);
@@ -127,7 +127,7 @@ impl UpdateFileStore {
         Ok(())
     }
 
-    /// Peform a dump of the given update file uuid into the provided snapshot path.
+    /// Peforms a dump of the given update file uuid into the provided dump path.
     pub fn dump(&self, uuid: Uuid, dump_path: impl AsRef<Path>) -> Result<()> {
         let uuid_string = uuid.to_string();
         let update_file_path = self.path.join(&uuid_string);
@@ -140,7 +140,8 @@ impl UpdateFileStore {
         let mut document_reader = DocumentBatchReader::from_reader(update_file)?;
 
         let mut document_buffer = Map::new();
-        // TODO: we need to find a way to do this more efficiently. (create a custom serializer to
+        // TODO: we need to find a way to do this more efficiently. (create a custom serializer
+        // for
         // jsonl for example...)
         while let Some((index, document)) = document_reader.next_document_with_index()? {
             for (field_id, content) in document.iter() {

meilisearch-lib/src/index_controller/updates/error.rs

@@ -17,8 +17,6 @@ pub enum UpdateLoopError {
     UnexistingUpdate(u64),
     #[error("Internal error: {0}")]
     Internal(Box<dyn Error + Send + Sync + 'static>),
-    //#[error("{0}")]
-    //IndexActor(#[from] IndexActorError),
     #[error(
         "update store was shut down due to a fatal error, please check your logs for more info."
     )]

meilisearch-lib/src/index_controller/updates/mod.rs

@@ -21,7 +21,7 @@ use uuid::Uuid;
 use self::error::{Result, UpdateLoopError};
 pub use self::message::UpdateMsg;
 use self::store::{UpdateStore, UpdateStoreInfo};
-use crate::document_formats::{read_csv, read_json};
+use crate::document_formats::{read_csv, read_json, read_ndjson};
 use crate::index::{Index, Settings, Unchecked};
 use crate::index_controller::update_file_store::UpdateFileStore;
 use status::UpdateStatus;
@@ -40,7 +40,7 @@ pub fn create_update_handler(
     let (sender, receiver) = mpsc::channel(100);
     let actor = UpdateLoop::new(update_store_size, receiver, path, index_resolver)?;
 
-    tokio::task::spawn_local(actor.run());
+    tokio::task::spawn(actor.run());
 
     Ok(sender)
 }
@@ -197,6 +197,7 @@ impl UpdateLoop {
                     match format {
                         DocumentAdditionFormat::Json => read_json(reader, &mut *update_file)?,
                         DocumentAdditionFormat::Csv => read_csv(reader, &mut *update_file)?,
+                        DocumentAdditionFormat::Ndjson => read_ndjson(reader, &mut *update_file)?,
                     }
 
                     update_file.persist()?;