From 65b1d09d55400349b00219afaa62f92ab3233acb Mon Sep 17 00:00:00 2001
From: Kerollmops <clement@meilisearch.com>
Date: Wed, 9 Jun 2021 14:57:03 +0200
Subject: [PATCH] Move the obkv merging functions into the merge_function
 module

---
 .../update/index_documents/merge_function.rs  | 20 ++++++++++++++++--
 milli/src/update/index_documents/transform.rs | 21 ++-----------------
 2 files changed, 20 insertions(+), 21 deletions(-)

diff --git a/milli/src/update/index_documents/merge_function.rs b/milli/src/update/index_documents/merge_function.rs
index 0a32603b5..8c93773ce 100644
--- a/milli/src/update/index_documents/merge_function.rs
+++ b/milli/src/update/index_documents/merge_function.rs
@@ -1,12 +1,28 @@
 use std::borrow::Cow;
 
-use anyhow::bail;
-use bstr::ByteSlice as _;
 use fst::IntoStreamer;
 use roaring::RoaringBitmap;
 
 use crate::heed_codec::CboRoaringBitmapCodec;
 
+/// Only the last value associated with an id is kept.
+pub fn keep_latest_obkv(_key: &[u8], obkvs: &[Cow<[u8]>]) -> anyhow::Result<Vec<u8>> {
+    Ok(obkvs.last().unwrap().clone().into_owned())
+}
+
+/// Merge all the obks in the order we see them.
+pub fn merge_obkvs(_key: &[u8], obkvs: &[Cow<[u8]>]) -> anyhow::Result<Vec<u8>> {
+    let mut iter = obkvs.iter();
+    let first = iter.next().map(|b| b.clone().into_owned()).unwrap();
+    Ok(iter.fold(first, |acc, current| {
+        let first = obkv::KvReader::new(&acc);
+        let second = obkv::KvReader::new(current);
+        let mut buffer = Vec::new();
+        merge_two_obkvs(first, second, &mut buffer);
+        buffer
+    }))
+}
+
 // Union of multiple FSTs
 pub fn fst_merge(_key: &[u8], values: &[Cow<[u8]>]) -> anyhow::Result<Vec<u8>> {
     let fsts = values.iter().map(fst::Set::new).collect::<Result<Vec<_>, _>>()?;
diff --git a/milli/src/update/index_documents/transform.rs b/milli/src/update/index_documents/transform.rs
index cfc2530b4..5fbd24bb1 100644
--- a/milli/src/update/index_documents/transform.rs
+++ b/milli/src/update/index_documents/transform.rs
@@ -10,8 +10,9 @@ use log::info;
 use roaring::RoaringBitmap;
 use serde_json::{Map, Value};
 
-use crate::{Index, BEU32, MergeFn, FieldsIdsMap, ExternalDocumentsIds, FieldId, FieldsDistribution};
+use crate::update::index_documents::merge_function::{merge_obkvs, keep_latest_obkv};
 use crate::update::{AvailableDocumentsIds, UpdateIndexingStep};
+use crate::{Index, BEU32, MergeFn, FieldsIdsMap, ExternalDocumentsIds, FieldId, FieldsDistribution};
 use super::merge_function::merge_two_obkvs;
 use super::{create_writer, create_sorter, IndexDocumentsMethod};
 
@@ -552,24 +553,6 @@ fn compute_primary_key_pair(
     }
 }
 
-/// Only the last value associated with an id is kept.
-fn keep_latest_obkv(_key: &[u8], obkvs: &[Cow<[u8]>]) -> anyhow::Result<Vec<u8>> {
-    obkvs.last().context("no last value").map(|last| last.clone().into_owned())
-}
-
-/// Merge all the obks in the order we see them.
-fn merge_obkvs(_key: &[u8], obkvs: &[Cow<[u8]>]) -> anyhow::Result<Vec<u8>> {
-    let mut iter = obkvs.iter();
-    let first = iter.next().map(|b| b.clone().into_owned()).context("no first value")?;
-    Ok(iter.fold(first, |acc, current| {
-        let first = obkv::KvReader::new(&acc);
-        let second = obkv::KvReader::new(current);
-        let mut buffer = Vec::new();
-        merge_two_obkvs(first, second, &mut buffer);
-        buffer
-    }))
-}
-
 fn validate_document_id(document_id: &str) -> Option<&str> {
     let document_id = document_id.trim();
     Some(document_id).filter(|id| {