write LEX file

Project-02/triplalex.py

@@ -1,43 +1,79 @@
 # ------------------------------------------------------------
-# triplalex.py
-#
-# tokenizer for the TRIPLA parser
+# Tokenizer for the TRIPLA parser
 # ------------------------------------------------------------
+
 import ply.lex as lex
 
-
 reserved = {
-    'while' : 'WHILE',
-    'do' : 'DO',
+    'let': 'LET',
+    'in': 'IN',
+    'if': 'IF',
+    'then': 'THEN',
+    'else': 'ELSE',
+    'while': 'WHILE',
+    'do': 'DO',
+    'true': 'TRUE',
+    'false': 'FALSE'
 }
 
 # List of token names. This is always required
 tokens = [
+    'ID',
     'CONST',
-    'LBRACE', 'RBRACE'
-]+list(reserved.values())
+    'AOP',
+    'RELOP',
+    'LOP',
+    'ASSIGN',
+    'LPAREN', 'RPAREN',
+    'LBRACE', 'RBRACE',
+    'COMMA',
+    'SEMICOLON',
+] + list(reserved.values())
 
-# Regular expression rules for simple tokens
-t_LBRACE  = r'\{'
-t_RBRACE  = r'\}'
-t_WHILE = r'while'
-t_DO = r'do'
+# Simple tokens
+t_LPAREN   = r'\('
+t_RPAREN   = r'\)'
+t_LBRACE   = r'\{'
+t_RBRACE   = r'\}'
+t_COMMA    = r','
+t_SEMICOLON = r';'
+t_ASSIGN = r'='
 
-# A regular expression rule with some action code
+# Arithmetic operators
+t_AOP = r'\+|\-|\*|/'
+
+# Comparison operators
+t_RELOP = r'<=|>=|==|!=|<|>'
+
+# Logical operators
+t_LOP = r'\|\||&&|==|!='
+
+# IDs
+def t_ID(t):
+    r'[A-Za-z_][A-Za-z0-9_]*'
+    t.type = reserved.get(t.value, 'ID')
+    return t
+
+# Constants
 def t_CONST(t):
-    r'\d+'
+    r'0|[1-9][0-9]*'
     t.value = int(t.value)
     return t
 
-# Define a rule so we can track line numbers
+# Linebreaks
 def t_newline(t):
     r'\n+'
     t.lexer.lineno += len(t.value)
 
-# A string containing ignored characters (spaces and tabs)
+# Ignore whitespace
 t_ignore  = ' \t'
 
-# Error handling rule
+# Comments
+def t_comment(t):
+    r'//.*'
+    pass
+
+# Error handling
 def t_error(t):
     print("Illegal character '%s'" % t.value[0])
     t.lexer.skip(1)