fix(io): use unicode-width for correct CJK/emoji/zero-width display width (closes #12)

Cargo.lock

@@ -2333,6 +2333,7 @@ dependencies = [
  "tempfile",
  "thiserror 2.0.18",
  "toml",
+ "unicode-width",
  "xxhash-rust",
 ]
 

Cargo.toml

@@ -27,3 +27,4 @@ textwrap = "0.16"
 tempfile = "3"
 xxhash-rust = { version = "0.8", features = ["xxh3"] }
 bincode = "1"
+unicode-width = "0.2"

crates/core/Cargo.toml

@@ -17,6 +17,7 @@ memmap2.workspace = true
 directories.workspace = true
 xxhash-rust.workspace = true
 bincode.workspace = true
+unicode-width.workspace = true
 
 [dev-dependencies]
 insta.workspace = true

crates/core/src/io/wrap.rs

@@ -2,9 +2,12 @@
 /// Lines exceeding this are returned as-is to avoid pathological cases.
 pub const MAX_WRAP_INPUT_LEN: usize = 10 * 1024 * 1024;
 
-/// Split a line into chunks of exactly `width` characters (display columns).
+/// Split a line into chunks of exactly `width` display columns.
 /// For a log viewer, we want character-level wrapping, not word-level.
+/// Uses `unicode-width` for correct CJK/emoji/zero-width handling.
 pub fn wrap_line_chars(line: &str, width: usize) -> Vec<String> {
+    use unicode_width::UnicodeWidthChar;
+
     if width == 0 {
         return vec![String::new()];
     }
@@ -15,7 +18,15 @@ pub fn wrap_line_chars(line: &str, width: usize) -> Vec<String> {
     let mut row = String::new();
     let mut col = 0;
     for ch in line.chars() {
-        let w = if ch == '\t' { 4 } else { 1 };
+        let w = if ch == '\t' {
+            4
+        } else if ch.is_control() {
+            // Control characters (except tab): width 0, still pushed to preserve content.
+            // Visible rendering is the caller's responsibility.
+            0
+        } else {
+            ch.width().unwrap_or(0)
+        };
         if col + w > width && !row.is_empty() {
             result.push(std::mem::take(&mut row));
             col = 0;
@@ -132,4 +143,48 @@ mod tests {
     fn test_max_wrap_input_len_constant() {
         assert_eq!(MAX_WRAP_INPUT_LEN, 10 * 1024 * 1024);
     }
+
+    #[test]
+    fn test_wrap_cjk_chars() {
+        let result = wrap_line_chars("你好", 3);
+        assert_eq!(result, vec!["你", "好"]);
+    }
+
+    #[test]
+    fn test_wrap_cjk_ascii_mixed() {
+        let result = wrap_line_chars("a你好", 4);
+        assert_eq!(result, vec!["a你", "好"]);
+    }
+
+    #[test]
+    fn test_wrap_zero_width_char() {
+        let result = wrap_line_chars("a\u{200B}b", 2);
+        assert_eq!(result, vec!["a\u{200B}b"]);
+    }
+
+    #[test]
+    fn test_wrap_emoji() {
+        let result = wrap_line_chars("😀a", 3);
+        assert_eq!(result, vec!["😀a"]);
+    }
+
+    #[test]
+    fn test_wrap_emoji_exact_wrap() {
+        let result = wrap_line_chars("😀a", 2);
+        assert_eq!(result, vec!["😀", "a"]);
+    }
+
+    #[test]
+    fn test_wrap_combining_mark() {
+        // Scalar-width wrapping: combining mark (width 0) stays with next base char,
+        // not the preceding one, because the base char already triggered a flush.
+        let result = wrap_line_chars("a\u{0301}b", 1);
+        assert_eq!(result, vec!["a", "\u{0301}b"]);
+    }
+
+    #[test]
+    fn test_wrap_cjk_width_one() {
+        let result = wrap_line_chars("你好", 1);
+        assert_eq!(result, vec!["你", "好"]);
+    }
 }