From 8d093a24a9b61dccd5b53000fc7d4b3535fac720 Mon Sep 17 00:00:00 2001
From: DualFroz <me@dualfroz.com>
Date: Wed, 2 Sep 2026 10:25:31 +0200
Subject: [PATCH] fix(strings): count and slice strings by Unicode code point

str_length and str_slice used UTF-8 byte offsets, so any input with
multi-byte characters produced wrong results: str_length("cafe") with
an accented final character returned 5 instead of 4, and str_slice(0,
4, ...) on the same string returned an empty string because the byte
index fell inside the encoding of the last character. This also broke
the higher-level helpers built on top of them (str_find, str_contains,
str_replace).

Count characters with chars().count() and index str_slice by character.
Out-of-range slices still return an empty string, so behavior for ASCII
input is unchanged.
---
 examples/tests/strings.nbt |  8 ++++++++
 numbat/src/ffi/strings.rs  | 13 ++++++++++---
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/examples/tests/strings.nbt b/examples/tests/strings.nbt
index 2678dee..be01dec 100644
--- a/examples/tests/strings.nbt
+++ b/examples/tests/strings.nbt
@@ -1,11 +1,19 @@
 assert_eq(str_length(""), 0)
 assert_eq(str_length("foo"), 3)
 
+# Length and slicing operate on Unicode code points, not on UTF-8 bytes
+assert_eq(str_length("café"), 4)
+assert_eq(str_length("❤"), 1)
+
 assert_eq(str_slice(0, 5, "hello world"), "hello")
 assert_eq(str_slice(6, 11, "hello world"), "world")
 assert_eq(str_slice(0, 0, "hello world"), "")
 assert_eq(str_slice(0, 100, "hello world"), "")
 
+assert_eq(str_slice(0, 4, "café"), "café")
+assert_eq(str_slice(3, 4, "café"), "é")
+assert_eq(str_slice(0, 3, "café"), "caf")
+
 assert_eq(chr(65), "A")
 assert_eq(chr(97), "a")
 assert_eq(chr(0x2764), "❤")
diff --git a/numbat/src/ffi/strings.rs b/numbat/src/ffi/strings.rs
index a810080..1ec031c 100644
--- a/numbat/src/ffi/strings.rs
+++ b/numbat/src/ffi/strings.rs
@@ -12,7 +12,7 @@ pub fn str_length(
     mut args: Args,
     _return_type: &TypeScheme,
 ) -> Result<Value, Box<RuntimeErrorKind>> {
-    let len = string_arg!(args).len();
+    let len = string_arg!(args).chars().count();
     return_scalar!(len as f64)
 }
 
@@ -41,9 +41,16 @@ pub fn str_slice(
     let end = quantity_arg!(args).unsafe_value().to_f64() as usize;
     let input = string_arg!(args);
 
-    let output = input.get(start..end).unwrap_or_default();
+    // Indices refer to code points, not bytes; out-of-range requests yield an
+    // empty string as before.
+    let characters = input.chars().collect::<Vec<char>>();
+    let output = if start <= end && end <= characters.len() {
+        characters[start..end].iter().collect::<String>()
+    } else {
+        String::new()
+    };
 
-    return_string!(borrowed = output)
+    return_string!(from = &output)
 }
 
 pub fn chr(