# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?s) *(<sample [^>]*>.*?<\/ ?sample>)"
test_str = ("<!DOCTYPE qhelp PUBLIC\n"
" \"-//Semmle//qhelp//EN\"\n"
" \"qhelp.dtd\">\n"
"<qhelp>\n\n\n"
"<overview>\n"
"<p>The C++ <code>throw</code> expression can take several forms. One form throws a new exception, whereas the\n"
"other re-throws the current exception. In the latter case, if there is no current exception, then the program\n"
"will be terminated. Presence of a re-throw outside of an exception handling context is often caused by the\n"
"programmer not knowing what kind of exception to throw.</p>\n\n"
"</overview>\n"
"<recommendation>\n"
"<p>The <code>throw</code> expression should be changed to throw a particular type of exception.</p>\n\n"
"</recommendation>\n"
"<example>\n"
"<sample language=\"cpp\">\n"
"void bad() {\n"
" /* ... */\n"
" if(error_condition)\n"
" throw;\n"
"}\n\n"
"void good() {\n"
" /* ... */\n"
" if(error_condition)\n"
" throw std::exception(\"Something went wrong.\");\n"
"}\n"
"</sample>\n\n"
"</example>\n"
"<references>\n\n"
" <li>Open Standards: <a href=\"http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2012/n3337.pdf\">Standard for Programming Language C++, draft n3337</a> [except.throw], clause 9, page 380.</li>\n\n\n"
"</references>\n"
"</qhelp>")
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