Simple LCM type parser in Python

lcmparse.py

#!/usr/bin/env python

import re
import sys

#==============================================================================
def parse(f):
  package = []

  # Get text
  text = f.read()

  # Remove comments
  text = re.sub('//[^\n]*\n', '\n', text)
  text = re.sub('/[*]([^*]*[*][^*/])*[^*]*[*]+/', '', text)

  # Examine statements
  for statement in re.split('[{};]', text):
    tokens = statement.split()

    if not len(tokens):
      continue

    if tokens[0] == 'package':
      package = tokens[1].split('.')
    elif tokens[0] in {'struct', 'enum'}:
      print '%s %r' % (tokens[0], '.'.join(package + tokens[1:2]))

#==============================================================================
def main(args):
  if len(args) < 2 or args[1] == '-':
    parse(sys.stdin)
  else:
    parse(open(args[1]))

#==============================================================================
if __name__ == '__main__':
  main(sys.argv)

This simple parser will parse an LCM type definition file and print the list of fully qualified types that are defined by the file. It is meant to serve as an example of how one might implement such a parser.

This logic is equivalent to the parsing code that ships with LCM to allow CMake users to generate LCM bindings.