# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(\"[^\n]*\"(?!\\))|(//[^\n]*$|/(?!\\)\*[\s\S]*?\*(?!\\)/)"
test_str = ("#include <stdio.h>\n\n"
"int main(int argc, char** argv)\n"
"{\n"
" // this comment will be removed\n"
" if (argc > 1) {\n"
" printf(\"Too many arguments.\\n\"); // this too will be removed\n"
" return 1;\n"
" }\n"
" printf(\"Please vist http://this.will.not.be.removed.com\\n\");\n"
" printf(\"/* This will stay */\\n\");\n"
" printf(\"\\\"/* This will stay too */\\\"\\n\");\n"
" printf(\"//and so will this\\\\\");\n"
" // but not this\n"
" printf(\"just \\\"ano//ther\\\" test.\");\n"
" return 0;\n"
"}\n"
"/*\n"
" this shall disappear\n"
"*/\n"
"#include <string>\n"
"int main(int argc, char** argv)\n"
"{\n"
" string foo = \"\"/*remove that!**/;\n"
" // Remove /* this\n"
" int butNotThis = 42;\n"
" // But do */ remove this\n"
" int bar = 4 /*remove this*/* 3; // but don't remove that 3. */\n"
" return 0;//just a comment\n"
"}/*end of the file has been reached.*/")
matches = re.finditer(regex, test_str, re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html