From fa949a58241d2f4d4b228b8944ea572963ae0b31 Mon Sep 17 00:00:00 2001
From: Minoru Osuka <minoru.osuka@gmail.com>
Date: Tue, 3 Jun 2025 11:42:02 +0900
Subject: [PATCH 1/3] Add tests

---
 src/segmenter.rs | 46 ++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/segmenter.rs b/src/segmenter.rs
index 2a58084..3f6206d 100644
--- a/src/segmenter.rs
+++ b/src/segmenter.rs
@@ -29,6 +29,7 @@ impl Segmenter {
             (Regex::new(r"[a-zA-Zａ-ｚＡ-Ｚ]").unwrap(), "A"),
             (Regex::new(r"[0-9０-９]").unwrap(), "N"),
         ];
+
         Segmenter {
             patterns,
             learner: learner.unwrap_or_else(|| AdaBoost::new(0.01, 100, 1)),
@@ -41,14 +42,14 @@ impl Segmenter {
     /// * `ch` - A string slice representing a single character.
     ///
     /// # Returns
-    /// A static string representing the type of the character, such as "M", "H", "I", "K", "A", "N", or "O" (for others).
-    pub fn get_type(&self, ch: &str) -> &'static str {
-        for (pattern, s_type) in &self.patterns {
-            if pattern.is_match(ch) {
-                return s_type;
+    /// Returns a string slice representing the type of the character.
+    pub fn get_type(&self, ch: &str) -> &str {
+        for (regex, label) in &self.patterns {
+            if regex.is_match(ch) {
+                return label;
             }
         }
-        "O"
+        "O" // Other
     }
 
     /// Adds a sentence to the segmenter with a custom writer function.
@@ -269,3 +270,36 @@ impl Segmenter {
         .collect()
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use std::path::PathBuf;
+
+    use super::*;
+
+    #[test]
+    fn test_segmenter() {
+        let model_file = PathBuf::from(env!("CARGO_MANIFEST_DIR"))
+            .join("./resources")
+            .join("RWCP.model");
+
+        let mut learner = AdaBoost::new(0.01, 100, 1);
+        learner.load_model(model_file.as_path()).unwrap();
+
+        let mut segmenter = Segmenter::new(Some(learner));
+        let sentence = "これはテストです。";
+        segmenter.add_sentence(sentence);
+        let result = segmenter.parse(sentence);
+        assert!(!result.is_empty());
+        assert_eq!(result.len(), 5); // Adjust based on expected segmentation
+    }
+
+    #[test]
+    fn test_get_type() {
+        let segmenter = Segmenter::new(None);
+        assert_eq!(segmenter.get_type("あ"), "I"); // Hiragana
+        assert_eq!(segmenter.get_type("漢"), "H"); // Kanji
+        assert_eq!(segmenter.get_type("A"), "A"); // Latin
+        assert_eq!(segmenter.get_type("1"), "N"); // Digit
+    }
+}

From 7eed49d6e3a587f3f4a89e918579e8eb16d41bd8 Mon Sep 17 00:00:00 2001
From: Minoru Osuka <minoru.osuka@gmail.com>
Date: Tue, 3 Jun 2025 11:43:21 +0900
Subject: [PATCH 2/3] Update doc

---
 src/segmenter.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/segmenter.rs b/src/segmenter.rs
index 3f6206d..423e3e0 100644
--- a/src/segmenter.rs
+++ b/src/segmenter.rs
@@ -42,7 +42,7 @@ impl Segmenter {
     /// * `ch` - A string slice representing a single character.
     ///
     /// # Returns
-    /// Returns a string slice representing the type of the character.
+    /// A static string representing the type of the character, such as "M", "H", "I", "K", "A", "N", or "O" (for others).
     pub fn get_type(&self, ch: &str) -> &str {
         for (regex, label) in &self.patterns {
             if regex.is_match(ch) {

From fde7a04a40cca2256458181cb86be58b2a7d3e6a Mon Sep 17 00:00:00 2001
From: Minoru Osuka <minoru.osuka@gmail.com>
Date: Tue, 3 Jun 2025 11:44:29 +0900
Subject: [PATCH 3/3] Rename

---
 src/segmenter.rs | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/segmenter.rs b/src/segmenter.rs
index 423e3e0..ec613a8 100644
--- a/src/segmenter.rs
+++ b/src/segmenter.rs
@@ -44,8 +44,8 @@ impl Segmenter {
     /// # Returns
     /// A static string representing the type of the character, such as "M", "H", "I", "K", "A", "N", or "O" (for others).
     pub fn get_type(&self, ch: &str) -> &str {
-        for (regex, label) in &self.patterns {
-            if regex.is_match(ch) {
+        for (pattern, label) in &self.patterns {
+            if pattern.is_match(ch) {
                 return label;
             }
         }