RustPython · youknowone · Jul 7, 2026 · Jul 5, 2026 · Jul 5, 2026 · Jul 5, 2026
diff --git a/Cargo.lock b/Cargo.lock
diff --git a/Cargo.toml b/Cargo.toml
@@ -179,6 +179,7 @@ rustpython-vm = { path = "crates/vm", default-features = false, version = "0.5.0
 rustpython-pylib = { path = "crates/pylib", version = "0.5.0" }
 rustpython-stdlib = { path = "crates/stdlib", default-features = false, version = "0.5.0" }
 rustpython-sre_engine = { path = "crates/sre_engine", version = "0.5.0" }
+rustpython-unicode = { path = "crates/unicode", version = "0.5.0" }
 rustpython-wtf8 = { path = "crates/wtf8", version = "0.5.0" }
 rustpython-doc = { path = "crates/doc", version = "0.5.0" }
 
@@ -192,12 +193,12 @@ der = { version = "0.8", features = ["alloc", "oid", "pem", "zeroize"] }
 phf = { version = "0.14.0", default-features = false, features = ["macros"]}
 adler32 = "1.2.0"
 approx = "0.5.1"
-ascii = "1.1"
+ascii = { version = "1.1", default-features = false }
 base64 = "0.22"
 blake2 = "0.11.0-rc.6"
 bitflags = "2.11.0"
 bitflagset = "0.0.3"
-bstr = "1"
+bstr = { version = "1", default-features = false, features = ["unicode"] }
 bzip2 = "0.6"
 chrono = { version = "0.4.44", default-features = false, features = ["clock", "std"] }
 console_error_panic_hook = "0.1"
@@ -227,7 +228,7 @@ hexf-parse = "0.2.1"
 hmac = "0.13"
 indexmap = { version = "2.14.0", features = ["std"] }
 insta = "1.47"
-itertools = "0.15.0"
+itertools = { version = "0.15.0", default-features = false, features = ["use_alloc"] }
 is-macro = "0.3.7"
 js-sys = "0.3"
 junction = "2.0.0"
@@ -248,7 +249,7 @@ malachite-bigint = "0.9.1"
 malachite-q = "0.9.1"
 malachite-base = "0.9.1"
 md-5 = "0.11"
-memchr = "2.8.1"
+memchr = { version = "2.8.1", default-features = false, features = ["alloc"] }
 memmap2 = "0.9.10"
 mt19937 = "3.3"
 num-complex = "0.4.6"
@@ -310,7 +311,7 @@ icu_locale = "2"
 icu_properties = "2"
 icu_normalizer = "2"
 uuid = "1.23.2"
-unicode_names2 = "3"
+unicode_names2 = { version = "3", default-features = false, features = ["no_std"] }
 widestring = "1.2.0"
 windows-sys = "0.61.2"
 wasm-bindgen = "0.2.106"

diff --git a/Lib/test/test_pkgutil.py b/Lib/test/test_pkgutil.py
@@ -231,7 +231,6 @@ def test_walk_packages_raises_on_string_or_bytes_input(self):
         with self.assertRaises((TypeError, ValueError)):
             list(pkgutil.walk_packages(bytes_input))
 
-    @unittest.expectedFailure  # TODO: RUSTPYTHON
     def test_name_resolution(self):
         import logging
         import logging.handlers

diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py
@@ -1734,7 +1734,6 @@ def test_bug_817234(self):
         self.assertEqual(next(iter).span(), (4, 4))
         self.assertRaises(StopIteration, next, iter)
 
-    @unittest.expectedFailure  # TODO: RUSTPYTHON
     def test_bug_6561(self):
         # '\d' should match characters in Unicode category 'Nd'
         # (Number, Decimal Digit), but not those in 'Nl' (Number,

diff --git a/crates/codegen/Cargo.toml b/crates/codegen/Cargo.toml
@@ -15,13 +15,14 @@
 [dependencies]
 rustpython-compiler-core = { workspace = true }
 rustpython-literal = {workspace = true }
+rustpython-unicode = { workspace = true }
 rustpython-wtf8 = { workspace = true }
 ruff_python_ast = { workspace = true }
 ruff_text_size = { workspace = true }

 bitflags = { workspace = true }
 indexmap = { workspace = true }
 itertools = { workspace = true }
 log = { workspace = true }
 num-complex = { workspace = true }
 num-traits = { workspace = true }
@@ -29,7 +30,6 @@
 malachite-bigint = { workspace = true }
 memchr = { workspace = true }
 rapidhash = { workspace = true }
-unicode_names2 = { workspace = true }
 
 [dev-dependencies]
 ruff_python_parser = { workspace = true }

diff --git a/crates/codegen/src/string_parser.rs b/crates/codegen/src/string_parser.rs
@@ -114,7 +114,7 @@ impl StringParser {
         let name_and_ending = self.skip_bytes(close_idx + 1);
         let name = &name_and_ending[..name_and_ending.len() - 1];
 
-        unicode_names2::character(name).ok_or_else(|| unreachable!())
+        rustpython_unicode::lookup_character(name).ok_or_else(|| unreachable!())
     }
 
     /// Parse an escaped character, returning the new character.

diff --git a/crates/common/Cargo.toml b/crates/common/Cargo.toml
@@ -16,6 +16,7 @@ wasm_js = ["getrandom/wasm_js"]
 
 [dependencies]
 rustpython-literal = { workspace = true }
+rustpython-unicode = { workspace = true }
 rustpython-wtf8 = { workspace = true }
 
 ascii = { workspace = true }
@@ -28,7 +29,6 @@ malachite-q = { workspace = true }
 malachite-base = { workspace = true }
 num-traits = { workspace = true }
 parking_lot = { workspace = true, optional = true }
-unicode_names2 = { workspace = true }
 radium = { workspace = true }
 
 lock_api = { workspace = true }

diff --git a/crates/common/src/encodings.rs b/crates/common/src/encodings.rs
@@ -414,7 +414,7 @@ pub mod errors {
             let mut out = String::with_capacity(num_chars * 4);
             for c in err_str.code_points() {
                 let c_u32 = c.to_u32();
-                if let Some(c_name) = c.to_char().and_then(unicode_names2::name) {
+                if let Some(c_name) = c.to_char().and_then(rustpython_unicode::character_name) {
                     write!(out, "\\N{{{c_name}}}").unwrap();
                 } else if c_u32 >= 0x10000 {
                     write!(out, "\\U{c_u32:08x}").unwrap();

diff --git a/crates/literal/Cargo.toml b/crates/literal/Cargo.toml
@@ -9,13 +9,13 @@ license = { workspace = true }
 rust-version = { workspace = true }
 
 [dependencies]
+rustpython-unicode = { workspace = true }
 rustpython-wtf8 = { workspace = true }
 
 hexf-parse = { workspace = true }
 is-macro.workspace = true
 lexical-parse-float = { workspace = true, features = ["format"] }
 num-traits = { workspace = true }
-icu_properties = { workspace = true }
 
 [dev-dependencies]
 rand = { workspace = true }
diff --git a/crates/literal/src/char.rs b/crates/literal/src/char.rs
diff --git a/crates/literal/src/escape.rs b/crates/literal/src/escape.rs
@@ -204,7 +204,7 @@ impl UnicodeEscape<'_> {
             '\\' | '\t' | '\r' | '\n' => 2,
             ch if ch < ' ' || ch as u32 == 0x7f => 4, // \xHH
             ch if ch.is_ascii() => 1,
-            ch if crate::char::is_printable(ch) => {
+            ch if rustpython_unicode::classify::is_repr_printable(ch) => {
                 // max = std::cmp::max(ch, max);
                 ch.len_utf8()
             }
@@ -238,7 +238,7 @@ impl UnicodeEscape<'_> {
             ch if ch.is_ascii() => {
                 write!(formatter, "\\x{:02x}", ch as u8)
             }
-            ch if crate::char::is_printable(ch) => formatter.write_char(ch),
+            ch if rustpython_unicode::classify::is_repr_printable(ch) => formatter.write_char(ch),
             '\0'..='\u{ff}' => {
                 write!(formatter, "\\x{:02x}", ch as u32)
             }

diff --git a/crates/literal/src/lib.rs b/crates/literal/src/lib.rs
@@ -2,7 +2,6 @@
 
 extern crate alloc;
 
-pub mod char;
 pub mod complex;
 pub mod escape;
 pub mod float;

diff --git a/crates/sre_engine/Cargo.toml b/crates/sre_engine/Cargo.toml
@@ -15,11 +15,11 @@ name = "benches"
 harness = false
 
 [dependencies]
+rustpython-unicode = { workspace = true }
 rustpython-wtf8 = { workspace = true }
 num_enum = { workspace = true }
 bitflags = { workspace = true }
 optional = { workspace = true }
-icu_properties = { workspace = true }
 
 [dev-dependencies]
 criterion = { workspace = true }