✨

lexer.py

@@ -0,0 +1,86 @@
+from rply import LexerGenerator
+
+keyword_tokens = [("KEYWORD_"+i, i) for i in [
+    "ALUID",
+    "DEFINI",
+    "DESIGNA",
+    "DONICUM",
+    "DUM",
+    "EST",
+    "FACE",
+    "FALSITAS",
+    "INVOCA",
+    "MINUS",
+    "NULLUS",
+    "PER",
+    "PLUS",
+    "REDI",
+    "SI",
+    "TUNC",
+    "USQUE",
+    "UT",
+    "VERITAS",
+    "VOCA"
+]]
+
+builtin_tokens = [("BUILTIN", i) for i in [
+    "AUDI_NUMERUS",
+    "AUDI",
+    "DICE",
+    "ERUMPE",
+    "FORTIS_NUMERUS",
+    "FORTIS_ELECTIONIS",
+    "LONGITUDO"
+]]
+
+data_tokens = [
+    ("DATA_STRING", r"\".*?\""),
+    ("DATA_NUMERAL", r"[IVXLCDM]+")
+]
+
+module_tokens = [("MODULE", i) for i in [
+    "FORS",
+    "FRACTIO",
+    "MAGNUM",
+    "SUBNULLA"
+]]
+
+symbol_tokens = [
+    ("SYMBOL_LPARENS", r"\("),
+    ("SYMBOL_RPARENS", r"\)"),
+    ("SYMBOL_LBRACKET", r"\["),
+    ("SYMBOL_RBRACKET", r"\]"),
+    ("SYMBOL_LCURL", r"\{"),
+    ("SYMBOL_RCURL", r"\}"),
+    ("SYMBOL_PLUS", r"\+"),
+    ("SYMBOL_MINUS", r"\-"),
+    ("SYMBOL_TIMES", r"\*"),
+    ("SYMBOL_DIVIDE", r"\/")
+]
+
+whitespace_tokens = [
+    ("NEWLINE", r"\n+")
+]
+
+all_tokens = (
+    keyword_tokens +
+    builtin_tokens +
+    module_tokens +
+    symbol_tokens +
+    data_tokens +
+    whitespace_tokens +
+    [("ID", r"([a-z]|_)+")]
+)
+
+class Lexer():
+    def __init__(self):
+        self.lexer = LexerGenerator()
+
+    def _add_tokens(self):
+        for token in all_tokens:
+            self.lexer.add(*token)
+        self.lexer.ignore(r" +")
+
+    def get_lexer(self):
+        self._add_tokens()
+        return self.lexer.build()