From efea1e5837571e7af4822b12b2a25af2530f0178 Mon Sep 17 00:00:00 2001
From: ManyTheFish <many@meilisearch.com>
Date: Wed, 29 Mar 2023 10:57:02 +0200
Subject: [PATCH] Fix facet normalization

---
 milli/src/lib.rs                                             | 5 +++++
 milli/src/search/facet/filter.rs                             | 2 +-
 .../extract/extract_fid_docid_facet_values.rs                | 5 +----
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/milli/src/lib.rs b/milli/src/lib.rs
index 865195df5..e49e49d9c 100644
--- a/milli/src/lib.rs
+++ b/milli/src/lib.rs
@@ -22,6 +22,7 @@ use std::collections::{BTreeMap, HashMap};
 use std::convert::{TryFrom, TryInto};
 use std::hash::BuildHasherDefault;
 
+use charabia::normalizer::{CharNormalizer, CompatibilityDecompositionNormalizer};
 pub use filter_parser::{Condition, FilterCondition, Span, Token};
 use fxhash::{FxHasher32, FxHasher64};
 pub use grenad::CompressionType;
@@ -252,6 +253,10 @@ pub fn is_faceted_by(field: &str, facet: &str) -> bool {
         && field[facet.len()..].chars().next().map(|c| c == '.').unwrap_or(true)
 }
 
+pub fn normalize_facet(original: &str) -> String {
+    CompatibilityDecompositionNormalizer.normalize_str(original.trim()).to_lowercase()
+}
+
 #[cfg(test)]
 mod tests {
     use serde_json::json;
diff --git a/milli/src/search/facet/filter.rs b/milli/src/search/facet/filter.rs
index f67219494..c24abe6a5 100644
--- a/milli/src/search/facet/filter.rs
+++ b/milli/src/search/facet/filter.rs
@@ -230,7 +230,7 @@ impl<'a> Filter<'a> {
                         &FacetGroupKey {
                             field_id,
                             level: 0,
-                            left_bound: &val.value().to_lowercase(),
+                            left_bound: &crate::normalize_facet(val.value()),
                         },
                     )?
                     .map(|v| v.bitmap)
diff --git a/milli/src/update/index_documents/extract/extract_fid_docid_facet_values.rs b/milli/src/update/index_documents/extract/extract_fid_docid_facet_values.rs
index 71ac330e2..f0bd78792 100644
--- a/milli/src/update/index_documents/extract/extract_fid_docid_facet_values.rs
+++ b/milli/src/update/index_documents/extract/extract_fid_docid_facet_values.rs
@@ -4,7 +4,6 @@ use std::fs::File;
 use std::io;
 use std::mem::size_of;
 
-use charabia::normalizer::{CharNormalizer, CompatibilityDecompositionNormalizer};
 use heed::zerocopy::AsBytes;
 use heed::BytesEncode;
 use roaring::RoaringBitmap;
@@ -136,9 +135,7 @@ fn extract_facet_values(value: &Value) -> (Vec<f64>, Vec<(String, String)>) {
                 }
             }
             Value::String(original) => {
-                let normalized = CompatibilityDecompositionNormalizer
-                    .normalize_str(original.trim())
-                    .to_lowercase();
+                let normalized = crate::normalize_facet(original);
                 output_strings.push((normalized, original.clone()));
             }
             Value::Array(values) => {