Replace PyICU with Rust icu_segmenter crate (#18553)

Co-authored-by: anoa's Codex Agent <codex@amorgan.xyz>
Co-authored-by: Quentin Gliech <quenting@element.io>

rust/Cargo.toml

@@ -43,6 +43,7 @@ sha2 = "0.10.8"
 serde = { version = "1.0.144", features = ["derive"] }
 serde_json = "1.0.85"
 ulid = "1.1.2"
+icu_segmenter = "2.0.0"
 reqwest = { version = "0.12.15", default-features = false, features = [
     "http2",
     "stream",

rust/src/lib.rs

@@ -13,6 +13,7 @@ pub mod identifier;
 pub mod matrix_const;
 pub mod push;
 pub mod rendezvous;
+pub mod segmenter;
 
 lazy_static! {
     static ref LOGGING_HANDLE: ResetHandle = pyo3_log::init();
@@ -53,6 +54,7 @@ fn synapse_rust(py: Python<'_>, m: &Bound<'_, PyModule>) -> PyResult<()> {
     events::register_module(py, m)?;
     http_client::register_module(py, m)?;
     rendezvous::register_module(py, m)?;
+    segmenter::register_module(py, m)?;
 
     Ok(())
 }

rust/src/segmenter.rs

@@ -0,0 +1,33 @@
+use icu_segmenter::options::WordBreakInvariantOptions;
+use icu_segmenter::WordSegmenter;
+use pyo3::prelude::*;
+
+#[pyfunction]
+pub fn parse_words(text: &str) -> PyResult<Vec<String>> {
+    let segmenter = WordSegmenter::new_auto(WordBreakInvariantOptions::default());
+    let mut parts = Vec::new();
+    let mut last = 0usize;
+
+    // `segment_str` gives us word boundaries as a vector of indexes. Use that
+    // to build a vector of words, and return.
+    for boundary in segmenter.segment_str(text) {
+        if boundary > last {
+            parts.push(text[last..boundary].to_string());
+        }
+        last = boundary;
+    }
+    Ok(parts)
+}
+
+pub fn register_module(py: Python<'_>, m: &Bound<'_, PyModule>) -> PyResult<()> {
+    let child_module = PyModule::new(py, "segmenter")?;
+    child_module.add_function(wrap_pyfunction!(parse_words, m)?)?;
+
+    m.add_submodule(&child_module)?;
+
+    py.import("sys")?
+        .getattr("modules")?
+        .set_item("synapse.synapse_rust.segmenter", child_module)?;
+
+    Ok(())
+}