From dcc3caef0dc4ddfd084f46bd1d6316b6ed52b62d Mon Sep 17 00:00:00 2001
From: Louis Dureuil <louis@meilisearch.com>
Date: Thu, 21 Nov 2024 16:56:46 +0100
Subject: [PATCH] Remove TopLevelMap

---
 .../meilisearch-types/src/document_formats.rs | 14 ++--
 crates/milli/src/update/new/mod.rs            |  2 -
 crates/milli/src/update/new/top_level_map.rs  | 66 -------------------
 3 files changed, 10 insertions(+), 72 deletions(-)
 delete mode 100644 crates/milli/src/update/new/top_level_map.rs

diff --git a/crates/meilisearch-types/src/document_formats.rs b/crates/meilisearch-types/src/document_formats.rs
index aec236949..096349448 100644
--- a/crates/meilisearch-types/src/document_formats.rs
+++ b/crates/meilisearch-types/src/document_formats.rs
@@ -6,7 +6,6 @@ use std::marker::PhantomData;
 use bumpalo::Bump;
 use memmap2::Mmap;
 use milli::documents::Error;
-use milli::update::new::TopLevelMap;
 use milli::Object;
 use raw_collections::RawMap;
 use serde::de::{SeqAccess, Visitor};
@@ -212,7 +211,7 @@ pub fn read_csv(input: &File, output: impl io::Write, delimiter: u8) -> Result<u
 
 /// Reads JSON from file and write it in NDJSON in a file checking it along the way.
 pub fn read_json(input: &File, output: impl io::Write) -> Result<u64> {
-    // We memory map to be able to deserialize into a TopLevelMap<'pl> that
+    // We memory map to be able to deserialize into a RawMap that
     // does not allocate when possible and only materialize the first/top level.
     let input = unsafe { Mmap::map(input).map_err(DocumentFormatError::Io)? };
     let mut doc_alloc = Bump::with_capacity(1024 * 1024 * 1024); // 1MiB
@@ -253,16 +252,23 @@ pub fn read_json(input: &File, output: impl io::Write) -> Result<u64> {
 
 /// Reads NDJSON from file and write it in NDJSON in a file checking it along the way.
 pub fn read_ndjson(input: &File, output: impl io::Write) -> Result<u64> {
-    // We memory map to be able to deserialize into a TopLevelMap<'pl> that
+    // We memory map to be able to deserialize into a RawMap that
     // does not allocate when possible and only materialize the first/top level.
     let input = unsafe { Mmap::map(input).map_err(DocumentFormatError::Io)? };
     let mut output = BufWriter::new(output);
 
+    let mut bump = Bump::with_capacity(1024 * 1024);
+
     let mut count = 0;
     for result in serde_json::Deserializer::from_slice(&input).into_iter() {
+        bump.reset();
         count += 1;
         result
-            .and_then(|map: TopLevelMap| to_writer(&mut output, &map))
+            .and_then(|raw: &RawValue| {
+                // try to deserialize as a map
+                let map = RawMap::from_raw_value(raw, &bump)?;
+                to_writer(&mut output, &map)
+            })
             .map_err(|e| DocumentFormatError::from((PayloadType::Ndjson, e)))?;
     }
 
diff --git a/crates/milli/src/update/new/mod.rs b/crates/milli/src/update/new/mod.rs
index 140f4ccf0..87995ee55 100644
--- a/crates/milli/src/update/new/mod.rs
+++ b/crates/milli/src/update/new/mod.rs
@@ -2,7 +2,6 @@ pub use document_change::{Deletion, DocumentChange, Insertion, Update};
 pub use merger::{
     merge_and_send_docids, merge_and_send_facet_docids, FacetDatabases, FacetFieldIdsDelta,
 };
-pub use top_level_map::{CowStr, TopLevelMap};
 
 use super::del_add::DelAdd;
 use crate::FieldId;
@@ -19,7 +18,6 @@ mod parallel_iterator_ext;
 mod ref_cell_ext;
 pub(crate) mod steps;
 pub(crate) mod thread_local;
-mod top_level_map;
 pub mod vector_document;
 mod word_fst_builder;
 mod words_prefix_docids;
diff --git a/crates/milli/src/update/new/top_level_map.rs b/crates/milli/src/update/new/top_level_map.rs
deleted file mode 100644
index aebb64bc9..000000000
--- a/crates/milli/src/update/new/top_level_map.rs
+++ /dev/null
@@ -1,66 +0,0 @@
-use std::borrow::{Borrow, Cow};
-use std::collections::BTreeMap;
-use std::{fmt, ops};
-
-use serde::{Deserialize, Serialize};
-use serde_json::value::RawValue;
-use serde_json::{Map, Value};
-
-#[derive(Deserialize, Serialize)]
-pub struct TopLevelMap<'p>(#[serde(borrow)] pub BTreeMap<CowStr<'p>, &'p RawValue>);
-
-impl TryFrom<&'_ TopLevelMap<'_>> for Map<String, Value> {
-    type Error = serde_json::Error;
-
-    fn try_from(tlmap: &TopLevelMap<'_>) -> Result<Self, Self::Error> {
-        let mut object = Map::new();
-        for (k, v) in &tlmap.0 {
-            let value = serde_json::from_str(v.get())?;
-            object.insert(k.to_string(), value);
-        }
-        Ok(object)
-    }
-}
-
-impl TryFrom<TopLevelMap<'_>> for Map<String, Value> {
-    type Error = serde_json::Error;
-
-    fn try_from(tlmap: TopLevelMap<'_>) -> Result<Self, Self::Error> {
-        TryFrom::try_from(&tlmap)
-    }
-}
-
-impl<'p> ops::Deref for TopLevelMap<'p> {
-    type Target = BTreeMap<CowStr<'p>, &'p RawValue>;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl ops::DerefMut for TopLevelMap<'_> {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.0
-    }
-}
-
-#[derive(Deserialize, Serialize, PartialEq, Eq, PartialOrd, Ord, Hash, Clone)]
-pub struct CowStr<'p>(#[serde(borrow)] pub Cow<'p, str>);
-
-impl fmt::Display for CowStr<'_> {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        fmt::Display::fmt(&self.0, f)
-    }
-}
-
-impl AsRef<str> for CowStr<'_> {
-    fn as_ref(&self) -> &str {
-        self.0.as_ref()
-    }
-}
-
-impl<'doc> Borrow<str> for CowStr<'doc> {
-    fn borrow(&self) -> &str {
-        self.0.borrow()
-    }
-}