# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"if\s*\((?P<conditional>(?:(?:(?:\"(?:(?:\\\")|[^\"])*\")|(?:'(?:(?:\\')|[^'])*'))|[^\(\)]|\((?1)\))*+)\)\s*(?P<true_body>(?:{(?:(?:(?:\"(?:(?:\\\")|[^\"])*\")|(?:'(?:(?:\\')|[^'])*'))|[^{}]|{(?2)})*+})|(?:[^{}\n]*))\s*(?:(?:else\s+?(?!if)(?P<else_body>(?:{(?:(?:(?:(?:\"(?:(?:\\\")|[^\"])*\")|(?:'(?:(?:\\')|[^'])*'))|[^{}]|{(?3)})+)})|(?:[^{}\n])*)\s*)|(?:else\s*if\s*\((?P<else_if_condition>(?:(?:(?:\"(?:(?:\\\")|[^\"])*\")|(?:'(?:(?:\\')|[^'])*'))|[^\(\)]|\((?4)\))+)\)\s*(?P<else_if_body>(?:(?:{(?:(?:(?:\"(?:(?:\\\")|[^\"])*\")|(?:'(?:(?:\\')|[^'])*'))|[^{}]|{(?5)})+})|(?:[^{}\n]*)))\s*))*"
test_str = ("// in_out.cpp: определяет точку входа для консольного приложения.\n"
" \n"
"#include \"stdafx.h\"\n"
"#include <iostream>\n"
"using namespace std;\n"
" \n"
"int main()\n"
"{\n"
" int a, \n\n\n"
"b; // объявление переменных типа int, то есть в таких переменных хранятся только целые числа\n"
" cout << \"Vvedite \n\n"
"pervoe \n\n"
"chislo: \";\n"
" cin >> a;\n"
" cout << \"Vvedite vtoroe chislo: \";\n"
" cin >> b;\n"
" if (a > b) \n"
" cout << a << \" > \" << b << endl; // печатать данное сообщение\n"
" \n"
" if (a <\n"
"b and c ==k\n"
" or (s == f && f==d))\n"
" {\n"
" cout << a << \" < \" << b << endl;\n"
" cout << a << \" < \" << b << endl;\n"
" cout << a << \" < \" << b << endl;\n"
" cout << a << \" < \" << b << endl;\n"
" cout << a << \" < \" << b << endl;\n"
" cout << a << \" < \" << b << endl;\n"
" if (sdfsdf) {\n"
"sdfsdf\n"
" }\n\n"
" cout << a << \" < \" << b << endl;\n"
" cout << a << \" < \" << b << endl;\n\n"
" cout << a << \" < \" << b << endl;\n"
" }\n"
" if (a == b) // если а = b\n"
" cout << a << \" = \" << b << endl; // в теле условного оператора опущены фигурные скобочки\n"
" system(\"pause\");\n"
" return 0;\n"
"}\n\n\n"
" if (a <b) {\n"
" cout << a << \" < \" << b << endl;\n"
" }\n\n\n"
" if (a <b\n"
"cvxcv sdfsd sdfsd \n"
"sdfds \n\n"
") {\n"
" cout << a << \" < \" << b << endl;\n"
" } else {\n"
"dsfsdfsdf\n"
"}\n\n"
"if (var1 == \"(\"){\n"
" echo \"{в\";\n"
"}\n\n\n"
"if(boolean_expression 1)\n"
"{\n"
" // Executes when the boolean expression 1 is true\n"
"}\n"
"else if(boolean_expression 2)\n"
"{\n"
" // Executes when the boolean expression 2 is true\n"
"}\n"
"else if( boolean_expression 3)\n"
"{\n"
" // Executes when the boolean expression 3 is true\n"
"}\n"
"else \n"
"{\n"
" // executes when the none of the above condition is true.\n"
"}\n\n")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE)
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