Python: Remove C/C++ style comments #parser

remove_c_style_comments.py

#!/usr/bin/python
import re
import sys

def removeComments(text):
    """ remove c-style comments.
        text: blob of text with comments (can include newlines)
        returns: text with comments removed
    """
    pattern = r"""
                            ##  --------- COMMENT ---------
           //.*?$           ##  Start of // .... comment
         |                  ##
           /\*              ##  Start of /* ... */ comment
           [^*]*\*+         ##  Non-* followed by 1-or-more *'s
           (                ##
             [^/*][^*]*\*+  ##
           )*               ##  0-or-more things which don't start with /
                            ##    but do end with '*'
           /                ##  End of /* ... */ comment
         |                  ##  -OR-  various things which aren't comments:
           (                ##
                            ##  ------ " ... " STRING ------
             "              ##  Start of " ... " string
             (              ##
               \\.          ##  Escaped char
             |              ##  -OR-
               [^"\\]       ##  Non "\ characters
             )*             ##
             "              ##  End of " ... " string
           |                ##  -OR-
                            ##
                            ##  ------ ' ... ' STRING ------
             '              ##  Start of ' ... ' string
             (              ##
               \\.          ##  Escaped char
             |              ##  -OR-
               [^'\\]       ##  Non '\ characters
             )*             ##
             '              ##  End of ' ... ' string
           |                ##  -OR-
                            ##
                            ##  ------ ANYTHING ELSE -------
             .              ##  Anything other char
             [^/"'\\]*      ##  Chars which doesn't start a comment, string
           )                ##    or escape
    """
    regex = re.compile(pattern, re.VERBOSE|re.MULTILINE|re.DOTALL)
    noncomments = [m.group(2) for m in regex.finditer(text) if m.group(2)]

    return "".join(noncomments)

def commentRemover(text):
    def replacer(match):
        s = match.group(0)
        if s.startswith('/'):
            return " " # note: a space and not an empty string
        else:
            return s
    pattern = re.compile(
        r'//.*?$|/\*.*?\*/|\'(?:\\.|[^\\\'])*\'|"(?:\\.|[^\\"])*"',
        re.DOTALL | re.MULTILINE
    )
    return re.sub(pattern, replacer, text)


filename = 'test.h'
with open(filename) as f:
    # uncmtFile = removeComments(f.read())
    uncmtFile = commentRemover(f.read())
    print uncmtFile

test.h

/* This is a C-style comment. */
This is not a comment.
/* This is another
 * C-style comment.
 */
"This is /* also not a comment */"
// This is also a comment
This is still // a comment
This is still /* a comment */
This is still /* a comment */ again
This is the final line

at line number 57,
return "\n" * s.count( "\n" )
will keep line position of original input file.

Hello,

First, thank you for this it was super helpful. Second, can you state what the license is? I would like to use your code but can't without license.

Thanks,

Casey