mirror/gcc
2
0
Fork 0
mirror of git://gcc.gnu.org/git/gcc.git synced 2025-02-11 23:30:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

regex.tcc: Handle regex_constants::__polynomial.

Browse Source 
* include/bits/regex.tcc: Handle regex_constants::__polynomial.
	* include/bits/regex_automaton.tcc: Throw exception when parsing
	back-reference with flag __polynomial.
	* include/bits/regex_constants.h: Add extension flag
	syntax_option_type __polynomial.
	* bits/regex_executor.tcc: Still let BFS process ECMAScript.
	Alternative operation will be fixed in the coming refactoring.
	* testsuite/28_regex/algorithms/regex_search/61424.cc: Turn
	loose match_search_debug to use DFS only.

From-SVN: r222500
This commit is contained in:
Tim Shen 2015-04-28 04:16:48 +00:00 committed by Tim Shen
parent 009b7fc187
commit e4846be7dd
6 changed files with 31 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
libstdc++-v3/ChangeLog
View File

@ -1,3 +1,15 @@
2015-04-28 Tim Shen <timshen@google.com>
* include/bits/regex.tcc: Handle regex_constants::__polynomial.
* include/bits/regex_automaton.tcc: Throw exception when parsing
back-reference with flag __polynomial.
* include/bits/regex_constants.h: Add extension flag
syntax_option_type __polynomial.
* bits/regex_executor.tcc: Still let BFS process ECMAScript.
Alternative operation will be fixed in the coming refactoring.
* testsuite/28_regex/algorithms/regex_search/61424.cc: Turn
loose match_search_debug to use DFS only.
2015-04-27 Sandra Loosemore <sandra@codesourcery.com>
PR libstdc++/65909

19
libstdc++-v3/include/bits/regex.tcc
View File

@ -28,13 +28,6 @@
* Do not attempt to use it directly. @headername{regex}
*/
// A non-standard switch to let the user pick the matching algorithm.
// If _GLIBCXX_REGEX_USE_THOMPSON_NFA is defined, the thompson NFA
// algorithm will be used. This algorithm is not enabled by default,
// and cannot be used if the regex contains back-references, but has better
// (polynomial instead of exponential) worst case performance.
// See __regex_algo_impl below.
namespace std _GLIBCXX_VISIBILITY(default)
{
namespace __detail
@ -67,16 +60,10 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
for (auto& __it : __res)
__it.matched = false;
// __policy is used by testsuites so that they can use Thompson NFA
// without defining a macro. Users should define
// _GLIBCXX_REGEX_USE_THOMPSON_NFA if they need to use this approach.
bool __ret;
if (!__re._M_automaton->_M_has_backref
&& !(__re._M_flags & regex_constants::ECMAScript)
#ifndef _GLIBCXX_REGEX_USE_THOMPSON_NFA
&& __policy == _RegexExecutorPolicy::_S_alternate
#endif
)
if ((__re.flags() & regex_constants::__polynomial)
|| (__policy == _RegexExecutorPolicy::_S_alternate
&& !__re._M_automaton->_M_has_backref))
{
_Executor<_BiIter, _Alloc, _TraitsT, false>
__executor(__s, __e, __m, __re, __flags);

2
libstdc++-v3/include/bits/regex_automaton.tcc
View File

@ -148,6 +148,8 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
_StateIdT
_NFA<_TraitsT>::_M_insert_backref(size_t __index)
{
if (this->_M_flags & regex_constants::__polynomial)
__throw_regex_error(regex_constants::error_complexity);
// To figure out whether a backref is valid, a stack is used to store
// unfinished sub-expressions. For example, when parsing
// "(a(b)(c\\1(d)))" at '\\1', _M_subexpr_count is 3, indicating that 3

10
libstdc++-v3/include/bits/regex_constants.h
View File

@ -63,6 +63,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
_S_awk,
_S_grep,
_S_egrep,
_S_polynomial,
_S_syntax_last
};
@ -169,6 +170,15 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
constexpr syntax_option_type egrep =
static_cast<syntax_option_type>(1 << _S_egrep);
/**
* Extension: Ensure both space complexity of compiled regex and
* time complexity execution are not exponential.
* If specified in a regex with back-references, the exception
* regex_constants::error_complexity will be thrown.
*/
constexpr syntax_option_type __polynomial =
static_cast<syntax_option_type>(1 << _S_polynomial);
constexpr inline syntax_option_type
operator&(syntax_option_type __a, syntax_option_type __b)
{

3
libstdc++-v3/include/bits/regex_executor.tcc
View File

@ -382,8 +382,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
case _S_opcode_alternative:
if (_M_nfa._M_flags & regex_constants::ECMAScript)
{
// TODO: Let BFS support ECMAScript's alternative operation.
_GLIBCXX_DEBUG_ASSERT(__dfs_mode);
// TODO: Fix BFS support. It is wrong.
_M_dfs(__match_mode, __state._M_alt);
// Pick lhs if it matches. Only try rhs if it doesn't.
if (!_M_has_sol)

4
libstdc++-v3/testsuite/28_regex/algorithms/regex_search/61424.cc
View File

@ -45,7 +45,9 @@ int main()
regex re("tour|tournament|tourn", g);
const char str[] = "tournament";
cmatch m;
VERIFY(regex_search_debug(str, m, re));
VERIFY(regex_search(str, m, re));
// TODO: Fix ECMAScript BFS matcher.
//VERIFY(regex_search_debug(str, m, re));
VERIFY(sol[i] == m[0]);
i++;
}