Created
November 22, 2017 09:27
-
-
Save aki237/2ebcb726d5b67b7039d3f4a599b5b9b8 to your computer and use it in GitHub Desktop.
Tokeninzing lisp in python
This file contains 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
#!/usr/bin/python3 | |
class Tokenizer: | |
OPEN_BRACKET = '(' | |
CLOSE_BRACKET = ')' | |
"""Tokenizer class is used to tokenize a lisp statement into separate symbols""" | |
def __init__(self, expression): | |
"""Class constructor used to initialize some member values""" | |
self.exp = expression.strip() | |
self.offset = 0 | |
if self.exp[self.offset] is not self.OPEN_BRACKET: | |
raise Exception("Unexpected character '" + self.exp[self.offset] + "' found at 0th index. Expected '" + self.OPEN_BRACKET + "'") | |
def match_pair(self, starter, ender): | |
"""Returns the index of the matching pair for a given 2 characters""" | |
moff = self.offset | |
if self.exp[self.offset] is not starter: | |
return -1 | |
count = 1 | |
self.offset += 1 | |
while self.offset < len(self.exp): | |
if self.exp[self.offset] is starter: | |
count += 1 | |
if self.exp[self.offset] is ender: | |
count -= 1 | |
if count is 0: | |
xx = self.offset | |
self.offset = moff | |
return xx | |
self.offset += 1 | |
self.offset = moff | |
return -1 | |
def get_tokens(self): | |
"""Returns a list containing the tokens for the lisp statement.""" | |
tokens = [] | |
index = self.match_pair(self.OPEN_BRACKET, self.CLOSE_BRACKET) | |
if index is -1: | |
raise Exception("Bracket match not found") | |
temp = "" | |
while (self.offset + 1) < len(self.exp): | |
self.offset += 1 | |
curoff = self.offset | |
ch = self.exp[curoff] | |
if ch is self.OPEN_BRACKET: | |
mindex = self.match_pair(self.OPEN_BRACKET, self.CLOSE_BRACKET) | |
tokens.append(self.exp[curoff:mindex+1]) | |
self.offset = mindex | |
continue | |
if ch is ' ': | |
if temp.strip() is not "": | |
tokens.append(temp) | |
temp = "" | |
continue | |
if ch.strip() is '': | |
if temp.strip() is not "": | |
tokens.append(temp) | |
temp = "" | |
continue | |
temp += ch | |
return tokens | |
print(Tokenizer(input().strip()).get_tokens()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment