Created
March 1, 2009 10:52
-
-
Save sma/72297 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import re | |
class Scanner(object): | |
def __init__(self, *rules): | |
self.rules = rules | |
self.re = re.compile("|".join("(" + r[0] + ")" for r in rules)) | |
def scan(self, s): | |
for m in self.re.finditer(s): | |
try: | |
rule = self.rules[m.lastindex - 1] | |
except IndexError: | |
yield 'ERROR', s[m.start():] | |
break | |
value = m.group() | |
token = rule[1] if len(rule) > 1 else value | |
if len(rule) > 2: | |
value = rule[2](value) | |
if token != 'IGNORE': | |
yield token, value | |
yield 'END', '' | |
def str(s): return s[1:-1].decode("string_escape") | |
Whitespace = (r'\s+', "IGNORE") | |
Integer = (r'\d+', "integer", int) | |
Float = (r'(?:\d+\.\d*|\.\d+)(?:[eE]-?\d+)?|\d+[eE]-?\d+', "float", float) | |
Number = (r'(?:\d+(?:\.\d*)?|\.\d+)(?:[eE]-?\d+)?', "number", float) | |
String = (r'"(?:\\.|[^"])*"|\'(?:\\.|[^\'])*\'', "string", str) | |
Name = (r'\w+', "name") | |
scanner = Scanner( | |
Scanner.Number, | |
Scanner.String, | |
Scanner.Name, | |
(r'[-+*/=]=?',), | |
(r';',), | |
Scanner.Whitespace, | |
) | |
for t in scanner.scan('foo = 5 * 30; bar = "bar\\n" - 6.05e-6;'): | |
print t | |
for t in Scanner( | |
(r'[()]',), | |
(r'\d+(?![^()\s])', 'int', int), | |
(r'[^()\s]+', 'sym',), | |
(r'\s+', 'IGNORE') | |
).scan("(a 1+ (c? 3))"): | |
print t |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment