[thirdparty/gcc.git] / libstdc++-v3 / include / bits / regex_automaton.tcc

// class template regex -*- C++ -*-

// Copyright (C) 2013-2014 Free Software Foundation, Inc.
//
// This file is part of the GNU ISO C++ Library.  This library is free
// software; you can redistribute it and/or modify it under the
// terms of the GNU General Public License as published by the
// Free Software Foundation; either version 3, or (at your option)
// any later version.

// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
// GNU General Public License for more details.

// Under Section 7 of GPL version 3, you are granted additional
// permissions described in the GCC Runtime Library Exception, version
// 3.1, as published by the Free Software Foundation.

// You should have received a copy of the GNU General Public License and
// a copy of the GCC Runtime Library Exception along with this program;
// see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
// <http://www.gnu.org/licenses/>.

/**
 *  @file bits/regex_automaton.tcc
 *  This is an internal header file, included by other library headers.
 *  Do not attempt to use it directly. @headername{regex}
 */

namespace std _GLIBCXX_VISIBILITY(default)
{
namespace __detail
{
_GLIBCXX_BEGIN_NAMESPACE_VERSION

#ifdef _GLIBCXX_DEBUG
  std::ostream&
  _State_base::_M_print(std::ostream& ostr) const
  {
    switch (_M_opcode)
    {
      case _S_opcode_alternative:
	ostr << "alt next=" << _M_next << " alt=" << _M_alt;
	break;
      case _S_opcode_subexpr_begin:
	ostr << "subexpr begin next=" << _M_next << " index=" << _M_subexpr;
	break;
      case _S_opcode_subexpr_end:
	ostr << "subexpr end next=" << _M_next << " index=" << _M_subexpr;
	break;
      case _S_opcode_backref:
	ostr << "backref next=" << _M_next << " index=" << _M_backref_index;
	break;
      case _S_opcode_match:
	ostr << "match next=" << _M_next;
	break;
      case _S_opcode_accept:
	ostr << "accept next=" << _M_next;
	break;
      default:
	ostr << "unknown next=" << _M_next;
	break;
    }
    return ostr;
  }

  // Prints graphviz dot commands for state.
  std::ostream&
  _State_base::_M_dot(std::ostream& __ostr, _StateIdT __id) const
  {
    switch (_M_opcode)
    {
      case _S_opcode_alternative:
	__ostr << __id << " [label=\"" << __id << "\\nALT\"];\n"
	       << __id << " -> " << _M_next
	       << " [label=\"epsilon\", tailport=\"s\"];\n"
	       << __id << " -> " << _M_alt
	       << " [label=\"epsilon\", tailport=\"n\"];\n";
	break;
      case _S_opcode_backref:
	__ostr << __id << " [label=\"" << __id << "\\nBACKREF "
	       << _M_subexpr << "\"];\n"
	       << __id << " -> " << _M_next << " [label=\"<match>\"];\n";
	break;
      case _S_opcode_line_begin_assertion:
	__ostr << __id << " [label=\"" << __id << "\\nLINE_BEGIN \"];\n"
	       << __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	break;
      case _S_opcode_line_end_assertion:
	__ostr << __id << " [label=\"" << __id << "\\nLINE_END \"];\n"
	       << __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	break;
      case _S_opcode_word_boundary:
	__ostr << __id << " [label=\"" << __id << "\\nWORD_BOUNDRY "
	       << _M_neg << "\"];\n"
	       << __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	break;
      case _S_opcode_subexpr_lookahead:
	__ostr << __id << " [label=\"" << __id << "\\nLOOK_AHEAD\"];\n"
	       << __id << " -> " << _M_next
	       << " [label=\"epsilon\", tailport=\"s\"];\n"
	       << __id << " -> " << _M_alt
	       << " [label=\"<assert>\", tailport=\"n\"];\n";
	break;
      case _S_opcode_subexpr_begin:
	__ostr << __id << " [label=\"" << __id << "\\nSBEGIN "
	       << _M_subexpr << "\"];\n"
	       << __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	break;
      case _S_opcode_subexpr_end:
	__ostr << __id << " [label=\"" << __id << "\\nSEND "
	       << _M_subexpr << "\"];\n"
	       << __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	break;
      case _S_opcode_dummy:
	break;
      case _S_opcode_match:
	__ostr << __id << " [label=\"" << __id << "\\nMATCH\"];\n"
	       << __id << " -> " << _M_next << " [label=\"<match>\"];\n";
	break;
      case _S_opcode_accept:
	__ostr << __id << " [label=\"" << __id << "\\nACC\"];\n" ;
	break;
      default:
	_GLIBCXX_DEBUG_ASSERT(false);
	break;
    }
    return __ostr;
  }

  template<typename _TraitsT>
    std::ostream&
    _NFA<_TraitsT>::_M_dot(std::ostream& __ostr) const
    {
      __ostr << "digraph _Nfa {\n"
	        "  rankdir=LR;\n";
      for (size_t __i = 0; __i < this->size(); ++__i)
        (*this)[__i]._M_dot(__ostr, __i);
      __ostr << "}\n";
      return __ostr;
    }
#endif

  template<typename _TraitsT>
    _StateIdT
    _NFA<_TraitsT>::_M_insert_backref(size_t __index)
    {
      // 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
      // sub expressions are parsed or partially parsed(in the stack), aka,
      // "(a..", "(b)" and "(c..").
      // _M_paren_stack is {1, 3}, for incomplete "(a.." and "(c..". At this
      // time, "\\2" is valid, but "\\1" and "\\3" are not.
      if (__index >= _M_subexpr_count)
	__throw_regex_error(regex_constants::error_backref);
      for (auto __it : this->_M_paren_stack)
	if (__index == __it)
	  __throw_regex_error(regex_constants::error_backref);
      this->_M_has_backref = true;
      _StateT __tmp(_S_opcode_backref);
      __tmp._M_backref_index = __index;
      return _M_insert_state(std::move(__tmp));
    }

  template<typename _TraitsT>
    void
    _NFA<_TraitsT>::_M_eliminate_dummy()
    {
      for (auto& __it : *this)
	{
	  while (__it._M_next >= 0 && (*this)[__it._M_next]._M_opcode
		 == _S_opcode_dummy)
	    __it._M_next = (*this)[__it._M_next]._M_next;
	  if (__it._M_opcode == _S_opcode_alternative
	      || __it._M_opcode == _S_opcode_subexpr_lookahead)
	    while (__it._M_alt >= 0 && (*this)[__it._M_alt]._M_opcode
		   == _S_opcode_dummy)
	      __it._M_alt = (*this)[__it._M_alt]._M_next;
	}
    }

  // Just apply DFS on the sequence and re-link their links.
  template<typename _TraitsT>
    _StateSeq<_TraitsT>
    _StateSeq<_TraitsT>::_M_clone()
    {
      std::map<_StateIdT, _StateIdT> __m;
      std::stack<_StateIdT> __stack;
      __stack.push(_M_start);
      while (!__stack.empty())
	{
	  auto __u = __stack.top();
	  __stack.pop();
	  auto __dup = _M_nfa[__u];
	  auto __id = _M_nfa._M_insert_state(__dup);
	  __m[__u] = __id;
	  if (__u == _M_end)
	    continue;
	  if (__m.count(__dup._M_next) == 0)
	    __stack.push(__dup._M_next);
	  if (__dup._M_opcode == _S_opcode_alternative
	      || __dup._M_opcode == _S_opcode_subexpr_lookahead)
	    if (__m.count(__dup._M_alt) == 0)
	      __stack.push(__dup._M_alt);
	}
      for (auto __it : __m)
	{
	  auto& __ref = _M_nfa[__it.second];
	  if (__ref._M_next != -1)
	    {
	      _GLIBCXX_DEBUG_ASSERT(__m.count(__ref._M_next));
	      __ref._M_next = __m[__ref._M_next];
	    }
	  if (__ref._M_opcode == _S_opcode_alternative
	      || __ref._M_opcode == _S_opcode_subexpr_lookahead)
	    if (__ref._M_alt != -1)
	      {
		_GLIBCXX_DEBUG_ASSERT(__m.count(__ref._M_alt));
		__ref._M_alt = __m[__ref._M_alt];
	      }
	}
      return _StateSeq(_M_nfa, __m[_M_start], __m[_M_end]);
    }

_GLIBCXX_END_NAMESPACE_VERSION
} // namespace __detail
} // namespace
Commit	Line	Data
6cb784b6 TS	1	// class template regex -- C++ --
6cb784b6 TS	2
aa118a03	3	// Copyright (C) 2013-2014 Free Software Foundation, Inc.
6cb784b6 TS	4	//
	5	// This file is part of the GNU ISO C++ Library. This library is free
	6	// software; you can redistribute it and/or modify it under the
	7	// terms of the GNU General Public License as published by the
	8	// Free Software Foundation; either version 3, or (at your option)
	9	// any later version.
	10
	11	// This library is distributed in the hope that it will be useful,
	12	// but WITHOUT ANY WARRANTY; without even the implied warranty of
	13	// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
	14	// GNU General Public License for more details.
	15
	16	// Under Section 7 of GPL version 3, you are granted additional
	17	// permissions described in the GCC Runtime Library Exception, version
	18	// 3.1, as published by the Free Software Foundation.
	19
	20	// You should have received a copy of the GNU General Public License and
	21	// a copy of the GCC Runtime Library Exception along with this program;
	22	// see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
	23	// <http://www.gnu.org/licenses/>.
	24
	25	/**
	26	* @file bits/regex_automaton.tcc
	27	* This is an internal header file, included by other library headers.
	28	* Do not attempt to use it directly. @headername{regex}
	29	*/
	30
	31	namespace std _GLIBCXX_VISIBILITY(default)
	32	{
	33	namespace __detail
	34	{
	35	_GLIBCXX_BEGIN_NAMESPACE_VERSION
	36
	37	#ifdef _GLIBCXX_DEBUG
7d9d2185 JW	38	std::ostream&
	39	_State_base::_M_print(std::ostream& ostr) const
	40	{
	41	switch (_M_opcode)
6cb784b6	42	{
7d9d2185 JW	43	case _S_opcode_alternative:
	44	ostr << "alt next=" << _M_next << " alt=" << _M_alt;
	45	break;
	46	case _S_opcode_subexpr_begin:
	47	ostr << "subexpr begin next=" << _M_next << " index=" << _M_subexpr;
	48	break;
	49	case _S_opcode_subexpr_end:
	50	ostr << "subexpr end next=" << _M_next << " index=" << _M_subexpr;
	51	break;
	52	case _S_opcode_backref:
	53	ostr << "backref next=" << _M_next << " index=" << _M_backref_index;
	54	break;
	55	case _S_opcode_match:
	56	ostr << "match next=" << _M_next;
	57	break;
	58	case _S_opcode_accept:
	59	ostr << "accept next=" << _M_next;
	60	break;
	61	default:
	62	ostr << "unknown next=" << _M_next;
	63	break;
6cb784b6	64	}
7d9d2185 JW	65	return ostr;
7d9d2185 JW	66	}
6cb784b6 TS	67
6cb784b6 TS	68	// Prints graphviz dot commands for state.
7d9d2185 JW	69	std::ostream&
	70	_State_base::_M_dot(std::ostream& __ostr, _StateIdT __id) const
	71	{
	72	switch (_M_opcode)
6cb784b6	73	{
7d9d2185 JW	74	case _S_opcode_alternative:
	75	__ostr << __id << " [label=\"" << __id << "\\nALT\"];\n"
	76	<< __id << " -> " << _M_next
	77	<< " [label=\"epsilon\", tailport=\"s\"];\n"
	78	<< __id << " -> " << _M_alt
	79	<< " [label=\"epsilon\", tailport=\"n\"];\n";
	80	break;
	81	case _S_opcode_backref:
	82	__ostr << __id << " [label=\"" << __id << "\\nBACKREF "
	83	<< _M_subexpr << "\"];\n"
	84	<< __id << " -> " << _M_next << " [label=\"<match>\"];\n";
	85	break;
	86	case _S_opcode_line_begin_assertion:
	87	__ostr << __id << " [label=\"" << __id << "\\nLINE_BEGIN \"];\n"
	88	<< __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	89	break;
	90	case _S_opcode_line_end_assertion:
	91	__ostr << __id << " [label=\"" << __id << "\\nLINE_END \"];\n"
	92	<< __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	93	break;
	94	case _S_opcode_word_boundary:
	95	__ostr << __id << " [label=\"" << __id << "\\nWORD_BOUNDRY "
	96	<< _M_neg << "\"];\n"
	97	<< __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	98	break;
	99	case _S_opcode_subexpr_lookahead:
	100	__ostr << __id << " [label=\"" << __id << "\\nLOOK_AHEAD\"];\n"
	101	<< __id << " -> " << _M_next
	102	<< " [label=\"epsilon\", tailport=\"s\"];\n"
	103	<< __id << " -> " << _M_alt
	104	<< " [label=\"<assert>\", tailport=\"n\"];\n";
	105	break;
	106	case _S_opcode_subexpr_begin:
	107	__ostr << __id << " [label=\"" << __id << "\\nSBEGIN "
	108	<< _M_subexpr << "\"];\n"
	109	<< __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	110	break;
	111	case _S_opcode_subexpr_end:
	112	__ostr << __id << " [label=\"" << __id << "\\nSEND "
	113	<< _M_subexpr << "\"];\n"
	114	<< __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	115	break;
	116	case _S_opcode_dummy:
	117	break;
	118	case _S_opcode_match:
	119	__ostr << __id << " [label=\"" << __id << "\\nMATCH\"];\n"
	120	<< __id << " -> " << _M_next << " [label=\"<match>\"];\n";
	121	break;
	122	case _S_opcode_accept:
	123	__ostr << __id << " [label=\"" << __id << "\\nACC\"];\n" ;
	124	break;
	125	default:
	126	_GLIBCXX_DEBUG_ASSERT(false);
	127	break;
6cb784b6	128	}
7d9d2185 JW	129	return __ostr;
7d9d2185 JW	130	}
6cb784b6	131
68e69ce2	132	template<typename _TraitsT>
7d9d2185	133	std::ostream&
68e69ce2	134	_NFA<_TraitsT>::_M_dot(std::ostream& __ostr) const
6cb784b6 TS	135	{
6cb784b6 TS	136	__ostr << "digraph _Nfa {\n"
7d9d2185	137	" rankdir=LR;\n";
6cb43087	138	for (size_t __i = 0; __i < this->size(); ++__i)
7d9d2185	139	(*this)[__i]._M_dot(__ostr, __i);
6cb784b6 TS	140	__ostr << "}\n";
	141	return __ostr;
	142	}
	143	#endif
	144
68e69ce2	145	template<typename _TraitsT>
7d9d2185	146	_StateIdT
68e69ce2	147	_NFA<_TraitsT>::_M_insert_backref(size_t __index)
ce645eb0 TS	148	{
	149	// To figure out whether a backref is valid, a stack is used to store
	150	// unfinished sub-expressions. For example, when parsing
	151	// "(a(b)(c\\1(d)))" at '\\1', _M_subexpr_count is 3, indicating that 3
	152	// sub expressions are parsed or partially parsed(in the stack), aka,
	153	// "(a..", "(b)" and "(c..").
	154	// _M_paren_stack is {1, 3}, for incomplete "(a.." and "(c..". At this
	155	// time, "\\2" is valid, but "\\1" and "\\3" are not.
	156	if (__index >= _M_subexpr_count)
e280b6ff	157	__throw_regex_error(regex_constants::error_backref);
7d9d2185	158	for (auto __it : this->_M_paren_stack)
e280b6ff TS	159	if (__index == __it)
e280b6ff TS	160	__throw_regex_error(regex_constants::error_backref);
7d9d2185	161	this->_M_has_backref = true;
7b86458e TS	162	_StateT __tmp(_S_opcode_backref);
7b86458e TS	163	__tmp._M_backref_index = __index;
7d9d2185	164	return _M_insert_state(std::move(__tmp));
ce645eb0 TS	165	}
ce645eb0 TS	166
68e69ce2	167	template<typename _TraitsT>
7d9d2185	168	void
68e69ce2	169	_NFA<_TraitsT>::_M_eliminate_dummy()
6cb784b6	170	{
7c812a2a TS	171	for (auto& __it : *this)
	172	{
	173	while (__it._M_next >= 0 && (*this)[__it._M_next]._M_opcode
7b86458e	174	== _S_opcode_dummy)
7c812a2a	175	__it._M_next = (*this)[__it._M_next]._M_next;
70b50ed7 TS	176	if (__it._M_opcode == _S_opcode_alternative
70b50ed7 TS	177	\|\| __it._M_opcode == _S_opcode_subexpr_lookahead)
7c812a2a TS	178	while (__it._M_alt >= 0 && (*this)[__it._M_alt]._M_opcode
	179	== _S_opcode_dummy)
	180	__it._M_alt = (*this)[__it._M_alt]._M_next;
	181	}
6cb784b6 TS	182	}
6cb784b6 TS	183
7c812a2a	184	// Just apply DFS on the sequence and re-link their links.
68e69ce2 JW	185	template<typename _TraitsT>
	186	_StateSeq<_TraitsT>
	187	_StateSeq<_TraitsT>::_M_clone()
6cb784b6	188	{
7c812a2a TS	189	std::map<_StateIdT, _StateIdT> __m;
	190	std::stack<_StateIdT> __stack;
	191	__stack.push(_M_start);
	192	while (!__stack.empty())
	193	{
	194	auto __u = __stack.top();
	195	__stack.pop();
	196	auto __dup = _M_nfa[__u];
	197	auto __id = _M_nfa._M_insert_state(__dup);
	198	__m[__u] = __id;
	199	if (__u == _M_end)
	200	continue;
	201	if (__m.count(__dup._M_next) == 0)
	202	__stack.push(__dup._M_next);
70b50ed7 TS	203	if (__dup._M_opcode == _S_opcode_alternative
70b50ed7 TS	204	\|\| __dup._M_opcode == _S_opcode_subexpr_lookahead)
7c812a2a TS	205	if (__m.count(__dup._M_alt) == 0)
	206	__stack.push(__dup._M_alt);
	207	}
	208	for (auto __it : __m)
	209	{
	210	auto& __ref = _M_nfa[__it.second];
	211	if (__ref._M_next != -1)
	212	{
	213	_GLIBCXX_DEBUG_ASSERT(__m.count(__ref._M_next));
	214	__ref._M_next = __m[__ref._M_next];
	215	}
70b50ed7 TS	216	if (__ref._M_opcode == _S_opcode_alternative
70b50ed7 TS	217	\|\| __ref._M_opcode == _S_opcode_subexpr_lookahead)
7c812a2a TS	218	if (__ref._M_alt != -1)
	219	{
	220	_GLIBCXX_DEBUG_ASSERT(__m.count(__ref._M_alt));
	221	__ref._M_alt = __m[__ref._M_alt];
	222	}
	223	}
	224	return _StateSeq(_M_nfa, __m[_M_start], __m[_M_end]);
6cb784b6 TS	225	}
6cb784b6 TS	226
6cb784b6 TS	227	_GLIBCXX_END_NAMESPACE_VERSION
	228	} // namespace __detail
	229	} // namespace