strsim crate now covered by strsim feature.

leontoeides · Nov 15, 2023 · ac094fa · ac094fa
1 parent 0dade8c
commit ac094fa
Show file tree

Hide file tree

Showing 41 changed files with 94 additions and 77 deletions.
diff --git a/src/lib.rs b/src/lib.rs
@@ -225,8 +225,10 @@
 //!
 //! // Demonstrating fuzzy matching:
 //!
+//! # #[cfg(feature = "strsim")]
 //! let resulting_keys: Vec<&usize> = search_index.search("Harry");
 //!
+//! # #[cfg(feature = "strsim")]
 //! assert_eq!(resulting_keys, vec![&0]);
 //! ```
 //!
@@ -268,9 +270,11 @@
 //!
 //! // Demonstrating fuzzy matching:
 //!
+//! # #[cfg(feature = "strsim")]
 //! let autocomplete_options: Vec<String> =
 //!     search_index.autocomplete("a very big birf");
 //!
+//! # #[cfg(feature = "strsim")]
 //! assert_eq!(
 //!     autocomplete_options,
 //!     vec!["a very big bird", "a very big birthday"]

diff --git a/src/simple/builder.rs b/src/simple/builder.rs
@@ -1,4 +1,4 @@
-use crate::simple::{AutocompleteType, SearchIndex, SearchType, StrsimMetric};
+use crate::simple::{AutocompleteType, EddieMetric, SearchIndex, SearchType, StrsimMetric};
 use kstring::KString;
 use std::collections::{BTreeMap, BTreeSet};
 use std::{clone::Clone, cmp::Ord};
@@ -18,8 +18,9 @@ pub struct SearchIndexBuilder<K> {
     search_type: SearchType,
     autocomplete_type: AutocompleteType,
     strsim_metric: Option<StrsimMetric>,
-    strsim_length: usize,
-    strsim_minimum_score: f64,
+    eddie_metric: Option<EddieMetric>,
+    fuzzy_length: usize,
+    fuzzy_minimum_score: f64,
     split_pattern: Option<Vec<char>>,
     case_sensitive: bool,
     minimum_keyword_length: usize,
@@ -42,8 +43,9 @@ impl<K: Clone + Ord> From<SearchIndex<K>> for SearchIndexBuilder<K> {
             search_type: search_index.search_type,
             autocomplete_type: search_index.autocomplete_type,
             strsim_metric: search_index.strsim_metric,
-            strsim_length: search_index.strsim_length,
-            strsim_minimum_score: search_index.strsim_minimum_score,
+            eddie_metric: search_index.eddie_metric,
+            fuzzy_length: search_index.fuzzy_length,
+            fuzzy_minimum_score: search_index.fuzzy_minimum_score,
             split_pattern: search_index.split_pattern,
             case_sensitive: search_index.case_sensitive,
             minimum_keyword_length: search_index.minimum_keyword_length,
@@ -68,8 +70,9 @@ impl<K: Clone + Ord> From<SearchIndexBuilder<K>> for SearchIndex<K> {
             search_type: search_index.search_type,
             autocomplete_type: search_index.autocomplete_type,
             strsim_metric: search_index.strsim_metric,
-            strsim_length: search_index.strsim_length,
-            strsim_minimum_score: search_index.strsim_minimum_score,
+            eddie_metric: search_index.eddie_metric,
+            fuzzy_length: search_index.fuzzy_length,
+            fuzzy_minimum_score: search_index.fuzzy_minimum_score,
             split_pattern: search_index.split_pattern,
             case_sensitive: search_index.case_sensitive,
             minimum_keyword_length: search_index.minimum_keyword_length,
@@ -163,8 +166,8 @@ impl<K: Clone + Ord> SearchIndexBuilder<K> {
     ///
     /// **Default:** `3` characters
     #[cfg(feature = "strsim")]
-    pub fn strsim_length(mut self, strsim_length: usize) -> Self {
-        self.strsim_length = strsim_length;
+    pub fn fuzzy_length(mut self, fuzzy_length: usize) -> Self {
+        self.fuzzy_length = fuzzy_length;
         self
     } // fn
 
@@ -182,8 +185,8 @@ impl<K: Clone + Ord> SearchIndexBuilder<K> {
     ///
     /// **Default:** `0.3`
     #[cfg(feature = "strsim")]
-    pub fn strsim_minimum_score(mut self, strsim_minimum_score: f64) -> Self {
-        self.strsim_minimum_score = strsim_minimum_score;
+    pub fn fuzzy_minimum_score(mut self, fuzzy_minimum_score: f64) -> Self {
+        self.fuzzy_minimum_score = fuzzy_minimum_score;
         self
     } // fn
 

diff --git a/src/simple/default.rs b/src/simple/default.rs
@@ -1,4 +1,4 @@
-use crate::simple::{AutocompleteType, SearchIndex, SearchType, StrsimMetric};
+use crate::simple::{AutocompleteType, EddieMetric, SearchIndex, SearchType, StrsimMetric};
 use std::cmp::Ord;
 
 // -----------------------------------------------------------------------------
@@ -11,7 +11,8 @@ impl<K: Ord> Default for SearchIndex<K> {
         Self::new(
             SearchType::Live,               // Search type.
             AutocompleteType::Context,      // Autocompletion type.
-            Some(StrsimMetric::Levenshtein),  // String similarity metric type.
+            Some(StrsimMetric::Levenshtein),// String similarity metric type.
+            Some(EddieMetric::Levenshtein), // String similarity metric type.
             3,                              // String similarity match length.
             0.3,                            // String similarity minimum score.
             // Default split pattern:

diff --git a/src/simple/internal/eddie/autocomplete/context_damerau_levenshtein.rs b/src/simple/internal/eddie/autocomplete/context_damerau_levenshtein.rs
@@ -69,7 +69,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = normalized_damerau_levenshtein(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/eddie/autocomplete/context_jaro.rs b/src/simple/internal/eddie/autocomplete/context_jaro.rs
@@ -69,7 +69,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = jaro(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/eddie/autocomplete/context_jaro_winkler.rs b/src/simple/internal/eddie/autocomplete/context_jaro_winkler.rs
@@ -69,7 +69,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = jaro_winkler(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/eddie/autocomplete/context_levenshtein.rs b/src/simple/internal/eddie/autocomplete/context_levenshtein.rs
@@ -69,7 +69,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = normalized_levenshtein(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/eddie/autocomplete/context_sorensen_dice.rs b/src/simple/internal/eddie/autocomplete/context_sorensen_dice.rs
@@ -69,7 +69,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = sorensen_dice(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/eddie/autocomplete/global_damerau_levenshtein.rs b/src/simple/internal/eddie/autocomplete/global_damerau_levenshtein.rs
@@ -55,7 +55,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = normalized_damerau_levenshtein(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/eddie/autocomplete/global_jaro.rs b/src/simple/internal/eddie/autocomplete/global_jaro.rs
@@ -55,7 +55,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = jaro(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/eddie/autocomplete/global_jaro_winkler.rs b/src/simple/internal/eddie/autocomplete/global_jaro_winkler.rs
@@ -55,7 +55,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = jaro_winkler(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/eddie/autocomplete/global_levenshtein.rs b/src/simple/internal/eddie/autocomplete/global_levenshtein.rs
@@ -55,7 +55,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = normalized_levenshtein(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/eddie/autocomplete/global_sorensen_dice.rs b/src/simple/internal/eddie/autocomplete/global_sorensen_dice.rs
@@ -55,7 +55,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = sorensen_dice(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/eddie/eddie_context_autocomplete.rs b/src/simple/internal/eddie/eddie_context_autocomplete.rs
@@ -44,13 +44,13 @@ impl<K: Hash + Ord> SearchIndex<K> {
         // will be fuzzy matched against every keyword in the index. This is OK
         // (or even desirable) if the search index isn't large, however, this
         // will be crippling slow on very large search indicies.
-        let index_range: &str = if self.strsim_length > 0 {
+        let index_range: &str = if self.fuzzy_length > 0 {
             // The user keyword must be longer than the match length to be
             // evaluated for fuzzy-matches:
-            if user_keyword.len() >= self.strsim_length {
+            if user_keyword.len() >= self.fuzzy_length {
                 // Use the first _n_ characters of the user's keyword to find
                 // search index keywords to compare against:
-                &user_keyword[0..self.strsim_length]
+                &user_keyword[0..self.fuzzy_length]
             } else {
                 // The user's keyword is too short. Do not perform any fuzzy
                 // matching:

diff --git a/src/simple/internal/eddie/eddie_global_autocomplete.rs b/src/simple/internal/eddie/eddie_global_autocomplete.rs
@@ -43,13 +43,13 @@ impl<K: Hash + Ord> SearchIndex<K> {
         // will be fuzzy matched against every keyword in the index. This is OK
         // (or even desirable) if the search index isn't large, however, this
         // will be crippling slow on very large search indicies.
-        let index_range: &str = if self.strsim_length > 0 {
+        let index_range: &str = if self.fuzzy_length > 0 {
             // The user keyword must be longer than the match length to be
             // evaluated for fuzzy-matches:
-            if user_keyword.len() >= self.strsim_length {
+            if user_keyword.len() >= self.fuzzy_length {
                 // Use the first _n_ characters of the user's keyword to find
                 // search index keywords to compare against:
-                &user_keyword[0..self.strsim_length]
+                &user_keyword[0..self.fuzzy_length]
             } else {
                 // The user's keyword is too short. Do not perform any fuzzy
                 // matching:

diff --git a/src/simple/internal/eddie/eddie_global_keyword.rs b/src/simple/internal/eddie/eddie_global_keyword.rs
@@ -42,13 +42,13 @@ impl<K: Hash + Ord> SearchIndex<K> {
         // will be fuzzy matched against every keyword in the index. This is OK
         // (or even desirable) if the search index isn't large, however, this
         // will be crippling slow on very large search indicies.
-        let index_range: &str = if self.strsim_length > 0 {
+        let index_range: &str = if self.fuzzy_length > 0 {
             // The user keyword must be longer than the match length to be
             // evaluated for fuzzy-matches:
-            if user_keyword.len() >= self.strsim_length {
+            if user_keyword.len() >= self.fuzzy_length {
                 // Use the first _n_ characters of the user's keyword to find
                 // search index keywords to compare against:
-                &user_keyword[0..self.strsim_length]
+                &user_keyword[0..self.fuzzy_length]
             } else {
                 // The user's keyword is too short. Do not perform any fuzzy
                 // matching:

diff --git a/src/simple/internal/eddie/keyword/global_damerau_levenshtein.rs b/src/simple/internal/eddie/keyword/global_damerau_levenshtein.rs
@@ -52,7 +52,7 @@ impl<K: Ord> SearchIndex<K> {
             ) // map
             // Search index keyword must meet minimum score to be considered as
             // a fuzzy match:
-            .filter(|(_keyword, score)| score >= &self.strsim_minimum_score)
+            .filter(|(_keyword, score)| score >= &self.fuzzy_minimum_score)
             // Find the `(keyword, score)` tuple with the highest score:
             .max_by(|(_a_keyword, a_score), (_b_keyword, b_score)|
                 a_score.partial_cmp(b_score).unwrap()

diff --git a/src/simple/internal/eddie/keyword/global_jaro.rs b/src/simple/internal/eddie/keyword/global_jaro.rs
@@ -51,7 +51,7 @@ impl<K: Ord> SearchIndex<K> {
             ) // map
             // Search index keyword must meet minimum score to be considered as
             // a fuzzy match:
-            .filter(|(_keyword, score)| score >= &self.strsim_minimum_score)
+            .filter(|(_keyword, score)| score >= &self.fuzzy_minimum_score)
             // Find the `(keyword, score)` tuple with the highest score:
             .max_by(|(_a_keyword, a_score), (_b_keyword, b_score)|
                 a_score.partial_cmp(b_score).unwrap()

diff --git a/src/simple/internal/eddie/keyword/global_jaro_winkler.rs b/src/simple/internal/eddie/keyword/global_jaro_winkler.rs
@@ -51,7 +51,7 @@ impl<K: Ord> SearchIndex<K> {
             ) // map
             // Search index keyword must meet minimum score to be considered as
             // a fuzzy match:
-            .filter(|(_keyword, score)| score >= &self.strsim_minimum_score)
+            .filter(|(_keyword, score)| score >= &self.fuzzy_minimum_score)
             // Find the `(keyword, score)` tuple with the highest score:
             .max_by(|(_a_keyword, a_score), (_b_keyword, b_score)|
                 a_score.partial_cmp(b_score).unwrap()

diff --git a/src/simple/internal/eddie/keyword/global_levenshtein.rs b/src/simple/internal/eddie/keyword/global_levenshtein.rs
@@ -51,7 +51,7 @@ impl<K: Ord> SearchIndex<K> {
             ) // map
             // Search index keyword must meet minimum score to be considered as
             // a fuzzy match:
-            .filter(|(_keyword, score)| score >= &self.strsim_minimum_score)
+            .filter(|(_keyword, score)| score >= &self.fuzzy_minimum_score)
             // Find the `(keyword, score)` tuple with the highest score:
             .max_by(|(_a_keyword, a_score), (_b_keyword, b_score)|
                 a_score.partial_cmp(b_score).unwrap()

diff --git a/src/simple/internal/eddie/keyword/global_sorensen_dice.rs b/src/simple/internal/eddie/keyword/global_sorensen_dice.rs
@@ -51,7 +51,7 @@ impl<K: Ord> SearchIndex<K> {
             ) // map
             // Search index keyword must meet minimum score to be considered as
             // a fuzzy match:
-            .filter(|(_keyword, score)| score >= &self.strsim_minimum_score)
+            .filter(|(_keyword, score)| score >= &self.fuzzy_minimum_score)
             // Find the `(keyword, score)` tuple with the highest score:
             .max_by(|(_a_keyword, a_score), (_b_keyword, b_score)|
                 a_score.partial_cmp(b_score).unwrap()

diff --git a/src/simple/internal/strsim/autocomplete/context_damerau_levenshtein.rs b/src/simple/internal/strsim/autocomplete/context_damerau_levenshtein.rs
@@ -69,7 +69,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = normalized_damerau_levenshtein(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/strsim/autocomplete/context_jaro.rs b/src/simple/internal/strsim/autocomplete/context_jaro.rs
@@ -69,7 +69,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = jaro(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/strsim/autocomplete/context_jaro_winkler.rs b/src/simple/internal/strsim/autocomplete/context_jaro_winkler.rs
@@ -69,7 +69,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = jaro_winkler(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/strsim/autocomplete/context_levenshtein.rs b/src/simple/internal/strsim/autocomplete/context_levenshtein.rs
@@ -69,7 +69,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = normalized_levenshtein(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/strsim/autocomplete/context_sorensen_dice.rs b/src/simple/internal/strsim/autocomplete/context_sorensen_dice.rs
@@ -69,7 +69,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = sorensen_dice(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/strsim/autocomplete/global_damerau_levenshtein.rs b/src/simple/internal/strsim/autocomplete/global_damerau_levenshtein.rs
@@ -55,7 +55,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = normalized_damerau_levenshtein(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/strsim/autocomplete/global_jaro.rs b/src/simple/internal/strsim/autocomplete/global_jaro.rs
@@ -55,7 +55,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = jaro(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each

diff --git a/src/simple/internal/strsim/autocomplete/global_jaro_winkler.rs b/src/simple/internal/strsim/autocomplete/global_jaro_winkler.rs
@@ -55,7 +55,7 @@ impl<K: Hash + Ord> SearchIndex<K> {
                 let score = jaro_winkler(index_keyword, user_keyword);
                 // Insert the score into the top scores (if it's normal and high
                 // enough):
-                if score.is_normal() && score >= self.strsim_minimum_score {
+                if score.is_normal() && score >= self.fuzzy_minimum_score {
                     top_scores.insert(index_keyword, index_keys, score)
                 } // if
             }); // for_each