Fix str.isidentifier() and add tests snippets

Cargo.lock

@@ -849,6 +849,7 @@ dependencies = [
  "statrs 0.10.0 (registry+https://github.com/rust-lang/crates.io-index)",
  "unicode-casing 0.1.0 (git+https://github.com/OddCoincidence/unicode-casing?rev=90d6d1f02b9cc04ffb55a5f1c3fa1455a84231fb)",
  "unicode-segmentation 1.2.1 (registry+https://github.com/rust-lang/crates.io-index)",
+ "unicode-xid 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
 ]
 
 [[package]]

tests/snippets/strings.py

@@ -164,6 +164,13 @@ assert not ''.isdecimal()
 assert '123'.isdecimal()
 assert not '\u00B2'.isdecimal()
 
+assert not ''.isidentifier()
+assert 'python'.isidentifier()
+assert '_'.isidentifier()
+assert '유니코드'.isidentifier()
+assert not '😂'.isidentifier()
+assert not '123'.isidentifier()
+
 # String Formatting
 assert "{} {}".format(1,2) == "1 2"
 assert "{0} {1}".format(2,3) == "2 3"

vm/Cargo.toml

@@ -24,6 +24,7 @@ rustc_version_runtime = "0.1.*"
 statrs = "0.10.0"
 caseless = "0.2.1"
 unicode-segmentation = "1.2.1"
+unicode-xid = "0.1.0"
 lazy_static = "^1.0.1"
 lexical = "2.0.0"
 itertools = "^0.8.0"

vm/src/obj/objstr.rs

@@ -1,3 +1,5 @@
+extern crate unicode_xid;
+
 use std::fmt;
 use std::hash::{Hash, Hasher};
 use std::ops::Range;
@@ -7,6 +9,7 @@ use std::string::ToString;
 use num_traits::ToPrimitive;
 use unicode_casing::CharExt;
 use unicode_segmentation::UnicodeSegmentation;
+use unicode_xid::UnicodeXID;
 
 use crate::format::{FormatParseError, FormatPart, FormatString};
 use crate::function::{OptionalArg, PyFuncArgs};
@@ -832,20 +835,14 @@ impl PyString {
 
     #[pymethod]
     fn isidentifier(&self, _vm: &VirtualMachine) -> bool {
-        let value = &self.value;
+        let mut chars = self.value.chars();
+        let is_identifier_start = match chars.next() {
+            Some('_') => true,
+            Some(c) => UnicodeXID::is_xid_start(c),
+            None => false,
+        };
         // a string is not an identifier if it has whitespace or starts with a number
-        if !value.chars().any(|c| c.is_ascii_whitespace())
-            && !value.chars().nth(0).unwrap().is_digit(10)
-        {
-            for c in value.chars() {
-                if c != "_".chars().nth(0).unwrap() && !c.is_digit(10) && !c.is_alphabetic() {
-                    return false;
-                }
-            }
-            true
-        } else {
-            false
-        }
+        is_identifier_start && chars.all(|c| UnicodeXID::is_xid_continue(c))
     }
 }