feat: Make typo factor configurable

Fixes https://github.com/valeriansaliou/sonic/issues/394.

core/src/config.rs

@@ -120,6 +120,11 @@ pub struct SearchConfig {
     pub list_limit_default: u16,
 
     pub list_limit_maximum: u16,
+
+    /// Word lengths from which one more typo is allowed when correcting words
+    /// (e.g. `[4, 7, 10]` allows 1 typo from 4 letters, 2 typos from 7 letters
+    /// and 3 typos from 10 letters). Empty means no typo correction.
+    pub typo_factor_word_lengths: Vec<usize>,
 }
 
 #[derive(Debug, Deserialize)]
@@ -386,6 +391,7 @@ pub(crate) mod tests {
         suggest_limit_maximum = 20
         list_limit_default = 100
         list_limit_maximum = 500
+        typo_factor_word_lengths = [4, 7, 10]
 
         [store.kv]
         path = "./data/store/kv/"

core/src/executor/search.rs

@@ -209,7 +209,10 @@ impl super::Executor {
                     continue 'terms;
                 }
 
-                let max_typo_factor = typo_factor(original_word_len);
+                let max_typo_factor = typo_factor(
+                    original_word_len,
+                    &self.app_conf.search.typo_factor_word_lengths,
+                );
                 let mut typo_factor = 1u32;
 
                 // TODO: Rework the Levenshtein query feature to avoid repeating

core/src/executor/suggest.rs

@@ -8,6 +8,7 @@
 use super::types::QuerySearchLimit;
 use crate::lexer::preprocessor::PreprocessorOutput;
 use crate::store::StoreItemPart;
+use crate::store::fst::typo_factor;
 
 impl super::Executor {
     pub fn suggest(
@@ -27,10 +28,12 @@ impl super::Executor {
             if let (Some(token), None) = (tokens.next(), tokens.next()) {
                 let len = token.as_original().len();
                 let term = token.into_normalized();
+                let max_typo_factor =
+                    typo_factor(len, &self.app_conf.search.typo_factor_word_lengths);
 
                 tracing::debug!("running suggest on word: {term:?}");
 
-                return match fst_store.suggest_words(term, len, limit as usize, None) {
+                return match fst_store.suggest_words(term, len, limit as usize, max_typo_factor) {
                     Some(words) => Ok(Some(words.map(|(k, _)| k))),
                     None => Ok(None),
                 };

core/src/store/fst/mod.rs

@@ -245,7 +245,7 @@ impl FstStore {
         // on user input.
         original_word_len: usize,
         limit: usize,
-        max_typo_factor: Option<u32>,
+        max_typo_factor: u32,
     ) -> Option<impl ExactSizeIterator<Item = (String, u16)> + DoubleEndedIterator + use<>> {
         use indexmap::IndexMap;
 
@@ -276,8 +276,6 @@ impl FstStore {
 
         // Try to fuzzy-suggest other words? (e.g. correct typos)
         if self.action_config.fuzzy_matching_enabled && found_words.len() < limit {
-            // Allow more typos in word as the word gets longer, up to a maximum limit
-            let max_typo_factor = max_typo_factor.unwrap_or(typo_factor(original_word_len));
             let mut typo_factor = 1u32;
 
             // TODO: Rework the Levenshtein query feature to avoid repeating
@@ -403,13 +401,14 @@ impl FstStore {
 }
 
 /// Allow more typos in word as the word gets longer, up to a maximum limit.
-pub(crate) fn typo_factor(word_len: usize) -> u32 {
-    match word_len {
-        1..=3 => 0,
-        4..=6 => 1,
-        7..=9 => 2,
-        _ => 3,
-    }
+///
+/// `typo_factor_word_lengths` lists the word lengths from which one more typo
+/// is allowed (see `search.typo_factor_word_lengths`).
+pub(crate) fn typo_factor(word_len: usize, typo_factor_word_lengths: &[usize]) -> u32 {
+    typo_factor_word_lengths
+        .iter()
+        .filter(|&&min_word_len| word_len >= min_word_len)
+        .count() as u32
 }
 
 // MARK: - Helpers