✨

2024-10-30 15:31:46 +01:00
parent e955ef4e28
commit 2f4e606fbf
9 changed files with 1032 additions and 3 deletions
--- a/gwendolyn/funcs/other/roll/lexer.py
+++ b/gwendolyn/funcs/other/roll/lexer.py
@ -0,0 +1,48 @@
+
+from string import ascii_letters, digits
+from rply import LexerGenerator
+
+VALID_CHARACTERS = ascii_letters[:3]+ascii_letters[4:]+"_"+digits
+
+TOKENS = [
+    ("ROLL_DIE",            r"d"),
+    ("ROLL_KEEP_HIGHEST",   r"kh"),
+    ("ROLL_KEEP_LOWEST",    r"kl"),
+    ("ROLL_MIN",            r"min"),
+    ("ROLL_MAX",            r"max"),
+    ("ROLL_EXPLODE",        r"!"),
+
+    ("SYMBOL_LE",           r"\<\="),
+    # ("SYMBOL_GE",           r"\>\="),
+    ("SYMBOL_EQUALS",       r"\="),
+    ("SYMBOL_ARROW",        r"\-\>"),
+    ("SYMBOL_BACKSLASH",    r"\\"),
+    ("SYMBOL_LPARENS",      r"\("),
+    ("SYMBOL_RPARENS",      r"\)"),
+    ("SYMBOL_PLUS",         r"\+"),
+    ("SYMBOL_MINUS",        r"\-"),
+    ("SYMBOL_TIMES",        r"\*"),
+    ("SYMBOL_DIVIDE",       r"\/"),
+
+    ("KEYWORD_LET",         r"let"),
+    ("KEYWORD_IN",          r"in"),
+    ("KEYWORD_IF",          r"if"),
+    ("KEYWORD_THEN",        r"then"),
+    ("KEYWORD_ELSE",        r"else"),
+
+    ("INT",                 r"\d+"),
+    ("ID",                  f"[{ascii_letters}][{VALID_CHARACTERS}]*")
+]
+
+class Lexer():
+    def __init__(self):
+        self.lexer = LexerGenerator()
+
+    def _add_tokens(self):
+        for token in TOKENS:
+            self.lexer.add(*token)
+        self.lexer.ignore(r"\s+")
+
+    def get_lexer(self):
+        self._add_tokens()
+        return self.lexer.build()