C++ Style Comment Stripper

abhiwin (Abhi Win) — Mon, 19 Feb 2007 14:27:40 GMT

// This scirpt either removes the C++ style comments or places them
// just before the line in which they occur
// for ex:
//
// int i=0, sum; //This is some comment(embedded)
//
// after conversion:
// //This is some comment(embedded)
// int i=0, sum;



# comm_stripper

#

# Description :

#

#   This scirpt either removes the C++ style comments or places them

#   just before the line in which they occur

#   for ex:

#

#       int i=0, sum;    //This is some comment(embedded)

#

#   after conversion:

#       //This is some comment(embedded)

#       int i=0, sum;



import re

import os



#comm_re = re.compile(r"(\s*)(.*)(//.*)")



comm_re = re.compile(r"(\s*)(.*?)(//.*)")

ext_re  = re.compile(r"\.(cpp|h|hpp|c|icc)$")

out_ext = ".out"



TRUE  = 1

FALSE = 0



def comm_strip(file_name, keep_comment=TRUE):

    lines = file(file_name).readlines()

    out_lines = []



    out_filename = file_name + out_ext

    fout = open(out_filename, "w")



    for line in lines:

        match = comm_re.match(line.rstrip())



        if(match):

            if keep_comment:

                #print "%s%s" % (match.group(1), match.group(3))

                out_lines.append("%s%s\n" % (match.group(1), match.group(3)))

            if match.group(2):

                #print "%s%s" % (match.group(1), match.group(2).rstrip())

                out_lines.append("%s%s\n" % (match.group(1), match.group(2).rstrip()))

        else:

            #print line.rstrip()

            out_lines.append(line)



    out_lines.append("\n\n")

    fout.writelines(out_lines)

    print "File %s => %s" % (file_name, out_filename)

    print "-"*80



print os.getcwd()

file_names = os.listdir(".")

flag=TRUE



for file_name in file_names:

    match_ext = ext_re.search(file_name)



    if match_ext :

        comm_strip(file_name, flag)



print "Done!"

Regular expression to match an HTML comment

chao (Chao Lam) — Thu, 07 Dec 2006 00:45:13 GMT

// description of your code here
This snippet uses the non-greedy matcher, and the "m" option to treat strings as multi-lines, so it may not work with all regex parsers.



/\)/m



Examples in Ruby IRB:

irb(main):029:0> html = <<-EOL

irb(main):030:0"  Second Comment 

irb(main):033:0" EOL

=> " Second Comment \n"

irb(main):075:0> m = html.match(/\)/m)

=> #

irb(main):076:0> m[0]

=> ""

irb(main):077:0> m[1]

=> "  First  Comment   --\n      "

DZone Snippets: comment code

C++ Style Comment Stripper

Regular expression to match an HTML comment