From f8a6de1819e82165216e01e247364cd952799426 Mon Sep 17 00:00:00 2001
From: "R. Menon" <rsmenon@icloud.com>
Date: Sat, 15 Mar 2025 18:14:23 -0700
Subject: [PATCH] Recognize Greek letters in patterns

---
 mathematica/lexer.py |  7 +++++--
 setup.py             |  2 +-
 tests/test_lexer.py  | 26 +++++++++++++++++++++++++-
 3 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/mathematica/lexer.py b/mathematica/lexer.py
index a09708a..711cdd1 100644
--- a/mathematica/lexer.py
+++ b/mathematica/lexer.py
@@ -11,7 +11,8 @@
 
 
 class Regex:
-    IDENTIFIER = r'[a-zA-Z\$][a-zA-Z0-9\$]*'
+    UNICODE = mma.UNICODE_SYSTEM_UNDEFINED_SYMBOLS.union(mma.UNICODE_SYSTEM_SYMBOLS)
+    IDENTIFIER = r'[a-zA-ZΑ-Ωα-ω\${unicode}][a-zA-ZΑ-Ωα-ω0-9\${unicode}]*'.format(unicode=''.join(UNICODE))
     NAMED_CHARACTER = r'\\\[{identifier}]'.format(identifier=IDENTIFIER)
     SYMBOLS = (r'[`]?({identifier}|{named_character})(`({identifier}|{named_character}))*[`]?'
                .format(identifier=IDENTIFIER, named_character=NAMED_CHARACTER))
@@ -20,7 +21,6 @@ class Regex:
     REAL = r'({integer}|{float})`({integer}|{float})?|{float}'.format(integer=INTEGER, float=FLOAT)
     BASE_NUMBER = r'{integer}\s*\^\^\s*({real}|{integer})'.format(integer=INTEGER, real=REAL)
     SCIENTIFIC_NUMBER = r'({real}|{integer})\s*\*\^\s*{integer}'.format(real=REAL, integer=INTEGER)
-    # PATTERNS = r'{symbol}\_{{1,3}}({symbol})?|({symbol})?\_{{1,3}}{symbol}'.format(symbol=SYMBOLS)
     PATTERNS = r'{symbol}:?\_{{1,3}}({symbol})?|({symbol})?:?\_{{1,3}}{symbol}'.format(symbol=SYMBOLS)
     SLOTS = r'#{symbol}|#\"{symbol}\"|#{{1,2}}[0-9]*'.format(symbol=SYMBOLS)
     MESSAGES = r'(::)(\s*)({symbol})'.format(symbol=SYMBOLS)
@@ -131,6 +131,9 @@ def unicode(index, token, value):
             else:
                 new_token = MToken.UNKNOWN
             return index, new_token, value
+        elif token is MToken.SYMBOL and value in mma.UNICODE_SYSTEM_SYMBOLS:
+            new_token = MToken.BUILTIN
+            return index, new_token, value
         else:
             return index, token, value
 
diff --git a/setup.py b/setup.py
index ece1df8..0efe7e2 100644
--- a/setup.py
+++ b/setup.py
@@ -29,7 +29,7 @@
 
 setup(
     name='pygments-mathematica',
-    version='0.4.1',
+    version='0.4.2',
     description='Mathematica/Wolfram Language Lexer for Pygments',
     long_description=__doc__,
     author='rsmenon',
diff --git a/tests/test_lexer.py b/tests/test_lexer.py
index 34f7a9f..f33930a 100644
--- a/tests/test_lexer.py
+++ b/tests/test_lexer.py
@@ -397,4 +397,28 @@ def test_string_closing_quote_on_newline(self):
             (MToken.STRING, '"'),
             (MToken.SYMBOL, 'abc'),
         ]
-        self.verify(code, expected)
\ No newline at end of file
+        self.verify(code, expected)
+
+    def test_unicode_greek(self):
+        code = [
+            'varλ1a',
+            'Δ',
+            'f[Δx_List] := Δx',
+            'a∂_',
+        ]
+        expected = [
+            [(MToken.SYMBOL, 'varλ1a')],
+            [(MToken.SYMBOL, 'Δ')],
+            [
+                (MToken.SYMBOL, 'f'),
+                (MToken.GROUP, '['),
+                (MToken.PATTERN, 'Δx_List'),
+                (MToken.GROUP, ']'),
+                (MToken.WHITESPACE, ' '),
+                (MToken.OPERATOR, ':='),
+                (MToken.WHITESPACE, ' '),
+                (MToken.SYMBOL, 'Δx'),
+            ],
+            [(MToken.PATTERN, 'a∂_')],
+        ]
+        self.verify_all(code, expected)
\ No newline at end of file