git
/
gcc
mirror of git://gcc.gnu.org/git/gcc.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Split _M_dfs() into smaller functions. 

* regex_executor.h(_M_handle_repeat, _M_handle_subexpr_begin)
	(_M_handle_subexpr_end, _M_handle_line_begin_assertion)
	(_M_handle_line_end_assertion, _M_handle_word_boundary)
	(_M_handle_subexpr_lookahead, _M_handle_match)
	(_M_handle_backref, _M_handle_accept, _M_handle_alternative):
	Add separate function declarations.
	* regex_executor.tcc: Split _M_dfs() into multiple handler functions.

From-SVN: r239673
This commit is contained in:
Tim Shen 2016-08-22 19:50:15 +00:00 committed by Tim Shen
parent bef18c6382
commit d79d625275
3 changed files with 313 additions and 187 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
libstdc++-v3/ChangeLog
View File

@ -1,3 +1,14 @@
2016-08-22 Tim Shen <timshen@google.com>
Split _M_dfs() into smaller functions.
* regex_executor.h(_M_handle_repeat, _M_handle_subexpr_begin)
(_M_handle_subexpr_end, _M_handle_line_begin_assertion)
(_M_handle_line_end_assertion, _M_handle_word_boundary)
(_M_handle_subexpr_lookahead, _M_handle_match)
(_M_handle_backref, _M_handle_accept, _M_handle_alternative):
Add separate function declarations.
* regex_executor.tcc: Split _M_dfs() into multiple handler functions.
2016-08-22 Gleb Natapov <gleb@scylladb.com>
PR libstdc++/68297

33
libstdc++-v3/include/bits/regex_executor.h
View File

@ -108,6 +108,39 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
void
_M_rep_once_more(_Match_mode __match_mode, _StateIdT);
void
_M_handle_repeat(_Match_mode, _StateIdT);
void
_M_handle_subexpr_begin(_Match_mode, _StateIdT);
void
_M_handle_subexpr_end(_Match_mode, _StateIdT);
void
_M_handle_line_begin_assertion(_Match_mode, _StateIdT);
void
_M_handle_line_end_assertion(_Match_mode, _StateIdT);
void
_M_handle_word_boundary(_Match_mode, _StateIdT);
void
_M_handle_subexpr_lookahead(_Match_mode, _StateIdT);
void
_M_handle_match(_Match_mode, _StateIdT);
void
_M_handle_backref(_Match_mode, _StateIdT);
void
_M_handle_accept(_Match_mode, _StateIdT);
void
_M_handle_alternative(_Match_mode, _StateIdT);
void
_M_dfs(_Match_mode __match_mode, _StateIdT __start);

158
libstdc++-v3/include/bits/regex_executor.tcc
View File

@ -195,25 +195,17 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
}
};
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_dfs(_Match_mode __match_mode, _StateIdT __i)
{
if (_M_states._M_visited(__i))
return;
const auto& __state = _M_nfa[__i];
// Every change on _M_cur_results and _M_current will be rolled back after
// finishing the recursion step.
switch (__state._M_opcode())
{
// _M_alt branch is "match once more", while _M_next is "get me out
// of this quantifier". Executing _M_next first or _M_alt first don't
// mean the same thing, and we need to choose the correct order under
// given greedy mode.
case _S_opcode_repeat:
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_handle_repeat(_Match_mode __match_mode, _StateIdT __i)
{
const auto& __state = _M_nfa[__i];
// Greedy.
if (!__state._M_neg)
{
@ -248,18 +240,28 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
}
}
}
break;
case _S_opcode_subexpr_begin:
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_handle_subexpr_begin(_Match_mode __match_mode, _StateIdT __i)
{
const auto& __state = _M_nfa[__i];
auto& __res = _M_cur_results[__state._M_subexpr];
auto __back = __res.first;
__res.first = _M_current;
_M_dfs(__match_mode, __state._M_next);
__res.first = __back;
}
break;
case _S_opcode_subexpr_end:
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_handle_subexpr_end(_Match_mode __match_mode, _StateIdT __i)
{
const auto& __state = _M_nfa[__i];
auto& __res = _M_cur_results[__state._M_subexpr];
auto __back = __res;
__res.second = _M_current;
@ -267,28 +269,58 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
_M_dfs(__match_mode, __state._M_next);
__res = __back;
}
break;
case _S_opcode_line_begin_assertion:
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
inline void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_handle_line_begin_assertion(_Match_mode __match_mode, _StateIdT __i)
{
const auto& __state = _M_nfa[__i];
if (_M_at_begin())
_M_dfs(__match_mode, __state._M_next);
break;
case _S_opcode_line_end_assertion:
}
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
inline void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_handle_line_end_assertion(_Match_mode __match_mode, _StateIdT __i)
{
const auto& __state = _M_nfa[__i];
if (_M_at_end())
_M_dfs(__match_mode, __state._M_next);
break;
case _S_opcode_word_boundary:
}
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
inline void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_handle_word_boundary(_Match_mode __match_mode, _StateIdT __i)
{
const auto& __state = _M_nfa[__i];
if (_M_word_boundary() == !__state._M_neg)
_M_dfs(__match_mode, __state._M_next);
break;
}
// Here __state._M_alt offers a single start node for a sub-NFA.
// We recursively invoke our algorithm to match the sub-NFA.
case _S_opcode_subexpr_lookahead:
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_handle_subexpr_lookahead(_Match_mode __match_mode, _StateIdT __i)
{
const auto& __state = _M_nfa[__i];
if (_M_lookahead(__state._M_alt) == !__state._M_neg)
_M_dfs(__match_mode, __state._M_next);
break;
case _S_opcode_match:
}
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_handle_match(_Match_mode __match_mode, _StateIdT __i)
{
const auto& __state = _M_nfa[__i];
if (_M_current == _M_end)
break;
return;
if (__dfs_mode)
{
if (__state._M_matches(*_M_current))
@ -301,17 +333,23 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
else
if (__state._M_matches(*_M_current))
_M_states._M_queue(__state._M_next, _M_cur_results);
break;
}
// First fetch the matched result from _M_cur_results as __submatch;
// then compare it with
// (_M_current, _M_current + (__submatch.second - __submatch.first)).
// If matched, keep going; else just return and try another state.
case _S_opcode_backref:
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_handle_backref(_Match_mode __match_mode, _StateIdT __i)
{
__glibcxx_assert(__dfs_mode);
const auto& __state = _M_nfa[__i];
auto& __submatch = _M_cur_results[__state._M_backref_index];
if (!__submatch.matched)
break;
return;
auto __last = _M_current;
for (auto __tmp = __submatch.first;
__last != _M_end && __tmp != __submatch.second;
@ -332,8 +370,12 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
_M_dfs(__match_mode, __state._M_next);
}
}
break;
case _S_opcode_accept:
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_handle_accept(_Match_mode __match_mode, _StateIdT __i)
{
if (__dfs_mode)
{
__glibcxx_assert(!_M_has_sol);
@ -373,7 +415,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
{
if (_M_current == _M_begin
&& (_M_flags & regex_constants::match_not_null))
break;
return;
if (__match_mode == _Match_mode::_Prefix || _M_current == _M_end)
if (!_M_has_sol)
{
@ -381,8 +423,15 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
_M_results = _M_cur_results;
}
}
break;
case _S_opcode_alternative:
}
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_handle_alternative(_Match_mode __match_mode, _StateIdT __i)
{
const auto& __state = _M_nfa[__i];
if (_M_nfa._M_flags & regex_constants::ECMAScript)
{
// TODO: Fix BFS support. It is wrong.
@ -401,7 +450,40 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
_M_dfs(__match_mode, __state._M_next);
_M_has_sol |= __has_sol;
}
break;
}
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_dfs(_Match_mode __match_mode, _StateIdT __i)
{
if (_M_states._M_visited(__i))
return;
switch (_M_nfa[__i]._M_opcode())
{
case _S_opcode_repeat:
_M_handle_repeat(__match_mode, __i); break;
case _S_opcode_subexpr_begin:
_M_handle_subexpr_begin(__match_mode, __i); break;
case _S_opcode_subexpr_end:
_M_handle_subexpr_end(__match_mode, __i); break;
case _S_opcode_line_begin_assertion:
_M_handle_line_begin_assertion(__match_mode, __i); break;
case _S_opcode_line_end_assertion:
_M_handle_line_end_assertion(__match_mode, __i); break;
case _S_opcode_word_boundary:
_M_handle_word_boundary(__match_mode, __i); break;
case _S_opcode_subexpr_lookahead:
_M_handle_subexpr_lookahead(__match_mode, __i); break;
case _S_opcode_match:
_M_handle_match(__match_mode, __i); break;
case _S_opcode_backref:
_M_handle_backref(__match_mode, __i); break;
case _S_opcode_accept:
_M_handle_accept(__match_mode, __i); break;
case _S_opcode_alternative:
_M_handle_alternative(__match_mode, __i); break;
default:
__glibcxx_assert(false);
}