Last active
May 13, 2020 13:35
-
-
Save IonianIronist/19a750ed12e18b42d1761eb78a13fd7e to your computer and use it in GitHub Desktop.
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
""" | |
(venv) ionianironist@debian:~/PycharmProjects/untitled$ python lab.py | |
VAR_TOKEN a32 | |
VAR_TOKEN b | |
VAR_TOKEN _67 | |
VAR_TOKEN a_9 | |
VAR_TOKEN DeF | |
VAR_TOKEN ifelse | |
VAR_TOKEN then | |
""" | |
import plex | |
# define patterns | |
letter = plex.Range("AZaz") | |
digit = plex.Range("09") | |
# the scanner lexicon - constructor argument is a list of (pattern,action ) tuples | |
lexicon = plex.Lexicon([ | |
((letter | plex.Str("_")) + plex.Rep((letter | digit) | plex.Str("_")), "VAR_TOKEN"), | |
(plex.Rep1(plex.Any(" \t\n")), plex.IGNORE) | |
]) | |
with open("identifiers.txr", "r") as fp: | |
scanner = plex.Scanner(lexicon, fp) | |
while True: | |
token, matched = scanner.read() | |
if not token: | |
break # reached end-of-text (EOT) | |
print(token, matched) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment