From 04596f36169fb427b4ac8b2279a7ea6b61c7c134 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20Renault?= <clement@meilisearch.com>
Date: Tue, 10 Sep 2024 18:01:17 +0100
Subject: [PATCH] Move the TopLevelMap into a dedicated module

---
 .../update/new/indexer/document_operation.rs  | 37 +++----------------
 milli/src/update/new/indexer/mod.rs           |  3 +-
 milli/src/update/new/indexer/top_level_map.rs | 30 +++++++++++++++
 3 files changed, 38 insertions(+), 32 deletions(-)
 create mode 100644 milli/src/update/new/indexer/top_level_map.rs

diff --git a/milli/src/update/new/indexer/document_operation.rs b/milli/src/update/new/indexer/document_operation.rs
index 799079b0a..0521d43f9 100644
--- a/milli/src/update/new/indexer/document_operation.rs
+++ b/milli/src/update/new/indexer/document_operation.rs
@@ -1,16 +1,19 @@
 use std::borrow::Cow;
 use std::collections::{BTreeMap, HashMap};
+use std::fmt;
 use std::sync::Arc;
 
 use heed::types::Bytes;
 use heed::RoTxn;
 use memmap2::Mmap;
 use rayon::iter::{IntoParallelIterator, ParallelIterator};
+use serde_json::from_str;
 use IndexDocumentsMethod as Idm;
 
 use super::super::document_change::DocumentChange;
 use super::super::items_pool::ItemsPool;
-use super::DocumentChanges;
+use super::top_level_map::{CowStr, TopLevelMap};
+use super::{top_level_map, DocumentChanges};
 use crate::documents::PrimaryKey;
 use crate::update::new::{Deletion, Insertion, KvReaderFieldId, KvWriterFieldId, Update};
 use crate::update::{AvailableIds, IndexDocumentsMethod};
@@ -395,36 +398,8 @@ impl MergeChanges for MergeDocumentForUpdates {
     }
 }
 
-use std::borrow::Borrow;
-
-use serde::Deserialize;
-use serde_json::from_str;
-use serde_json::value::RawValue;
-
-#[derive(Deserialize)]
-pub struct TopLevelMap<'p>(#[serde(borrow)] BTreeMap<CowStr<'p>, &'p RawValue>);
-
-#[derive(Deserialize, PartialEq, Eq, PartialOrd, Ord, Hash, Clone)]
-pub struct CowStr<'p>(#[serde(borrow)] Cow<'p, str>);
-
-impl CowStr<'_> {
-    fn to_string(&self) -> String {
-        self.0.to_string()
-    }
-}
-
-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()
-    }
-}
-
+/// Returns the document ID based on the primary and
+/// search for it recursively in zero-copy-deserialized documents.
 fn get_docid<'p>(
     map: &TopLevelMap<'p>,
     primary_key: &[&str],
diff --git a/milli/src/update/new/indexer/mod.rs b/milli/src/update/new/indexer/mod.rs
index 5e3104de8..4d7e2aa47 100644
--- a/milli/src/update/new/indexer/mod.rs
+++ b/milli/src/update/new/indexer/mod.rs
@@ -26,6 +26,7 @@ use crate::{FieldsIdsMap, GlobalFieldsIdsMap, Index, Result, UserError};
 mod document_deletion;
 mod document_operation;
 mod partial_dump;
+mod top_level_map;
 mod update_by_function;
 
 pub trait DocumentChanges<'p> {
@@ -121,7 +122,7 @@ where
                             &extractor_sender,
                         )?;
                     }
-                    
+
                     {
                         let span = tracing::trace_span!(target: "indexing::documents::extract", "exact_word_docids");
                         let _entered = span.enter();
diff --git a/milli/src/update/new/indexer/top_level_map.rs b/milli/src/update/new/indexer/top_level_map.rs
new file mode 100644
index 000000000..9e1481b5e
--- /dev/null
+++ b/milli/src/update/new/indexer/top_level_map.rs
@@ -0,0 +1,30 @@
+use std::borrow::{Borrow, Cow};
+use std::collections::BTreeMap;
+use std::fmt;
+
+use serde::Deserialize;
+use serde_json::value::RawValue;
+
+#[derive(Deserialize)]
+pub struct TopLevelMap<'p>(#[serde(borrow)] pub BTreeMap<CowStr<'p>, &'p RawValue>);
+
+#[derive(Deserialize, 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()
+    }
+}