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

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

// Copyright (C) 2013-2016 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
  inline std::ostream&
  _State_base::_M_print(std::ostream& ostr) const
  {
    switch (_M_opcode)
    {
      case _S_opcode_alternative:
      case _S_opcode_repeat:
	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.
  inline std::ostream&
  _State_base::_M_dot(std::ostream& __ostr, _StateIdT __id) const
  {
    switch (_M_opcode)
    {
      case _S_opcode_alternative:
      case _S_opcode_repeat:
	__ostr << __id << " [label=\"" << __id << "\\nALT\"];\n"
	       << __id << " -> " << _M_next
	       << " [label=\"next\", tailport=\"s\"];\n"
	       << __id << " -> " << _M_alt
	       << " [label=\"alt\", 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)
    {
      if (this->_M_flags & regex_constants::__polynomial)
	__throw_regex_error(regex_constants::error_complexity,
			    "Unexpected back-reference in polynomial mode.");
      // 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,
	  "Back-reference index exceeds current sub-expression count.");
      for (auto __it : this->_M_paren_stack)
	if (__index == __it)
	  __throw_regex_error(
	    regex_constants::error_backref,
	    "Back-reference referred to an opened sub-expression.");
      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_has_alt())
	    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];
	  // _M_insert_state() never return -1
	  auto __id = _M_nfa._M_insert_state(std::move(__dup));
	  __m[__u] = __id;
	  if (__dup._M_has_alt())
	    if (__dup._M_alt != _S_invalid_state_id
		&& __m.count(__dup._M_alt) == 0)
	      __stack.push(__dup._M_alt);
	  if (__u == _M_end)
	    continue;
	  if (__dup._M_next != _S_invalid_state_id
	      && __m.count(__dup._M_next) == 0)
	    __stack.push(__dup._M_next);
	}
      for (auto __it : __m)
	{
	  auto __v = __it.second;
	  auto& __ref = _M_nfa[__v];
	  if (__ref._M_next != _S_invalid_state_id)
	    {
	      __glibcxx_assert(__m.count(__ref._M_next) > 0);
	      __ref._M_next = __m[__ref._M_next];
	    }
	  if (__ref._M_has_alt())
	    if (__ref._M_alt != _S_invalid_state_id)
	      {
		__glibcxx_assert(__m.count(__ref._M_alt) > 0);
		__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
818ab71a	3	// Copyright (C) 2013-2016 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
ecb249dd	38	inline std::ostream&
7d9d2185 JW	39	_State_base::_M_print(std::ostream& ostr) const
	40	{
	41	switch (_M_opcode)
6cb784b6	42	{
7d9d2185	43	case _S_opcode_alternative:
a670a9bb	44	case _S_opcode_repeat:
7d9d2185 JW	45	ostr << "alt next=" << _M_next << " alt=" << _M_alt;
	46	break;
	47	case _S_opcode_subexpr_begin:
	48	ostr << "subexpr begin next=" << _M_next << " index=" << _M_subexpr;
	49	break;
	50	case _S_opcode_subexpr_end:
	51	ostr << "subexpr end next=" << _M_next << " index=" << _M_subexpr;
	52	break;
	53	case _S_opcode_backref:
	54	ostr << "backref next=" << _M_next << " index=" << _M_backref_index;
	55	break;
	56	case _S_opcode_match:
	57	ostr << "match next=" << _M_next;
	58	break;
	59	case _S_opcode_accept:
	60	ostr << "accept next=" << _M_next;
	61	break;
	62	default:
	63	ostr << "unknown next=" << _M_next;
	64	break;
6cb784b6	65	}
7d9d2185 JW	66	return ostr;
7d9d2185 JW	67	}
6cb784b6 TS	68
6cb784b6 TS	69	// Prints graphviz dot commands for state.
ecb249dd	70	inline std::ostream&
7d9d2185 JW	71	_State_base::_M_dot(std::ostream& __ostr, _StateIdT __id) const
	72	{
	73	switch (_M_opcode)
6cb784b6	74	{
7d9d2185	75	case _S_opcode_alternative:
a670a9bb	76	case _S_opcode_repeat:
7d9d2185 JW	77	__ostr << __id << " [label=\"" << __id << "\\nALT\"];\n"
7d9d2185 JW	78	<< __id << " -> " << _M_next
a670a9bb	79	<< " [label=\"next\", tailport=\"s\"];\n"
7d9d2185	80	<< __id << " -> " << _M_alt
a670a9bb	81	<< " [label=\"alt\", tailport=\"n\"];\n";
7d9d2185 JW	82	break;
	83	case _S_opcode_backref:
	84	__ostr << __id << " [label=\"" << __id << "\\nBACKREF "
	85	<< _M_subexpr << "\"];\n"
	86	<< __id << " -> " << _M_next << " [label=\"<match>\"];\n";
	87	break;
	88	case _S_opcode_line_begin_assertion:
	89	__ostr << __id << " [label=\"" << __id << "\\nLINE_BEGIN \"];\n"
	90	<< __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	91	break;
	92	case _S_opcode_line_end_assertion:
	93	__ostr << __id << " [label=\"" << __id << "\\nLINE_END \"];\n"
	94	<< __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	95	break;
	96	case _S_opcode_word_boundary:
	97	__ostr << __id << " [label=\"" << __id << "\\nWORD_BOUNDRY "
	98	<< _M_neg << "\"];\n"
	99	<< __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	100	break;
	101	case _S_opcode_subexpr_lookahead:
	102	__ostr << __id << " [label=\"" << __id << "\\nLOOK_AHEAD\"];\n"
	103	<< __id << " -> " << _M_next
	104	<< " [label=\"epsilon\", tailport=\"s\"];\n"
	105	<< __id << " -> " << _M_alt
	106	<< " [label=\"<assert>\", tailport=\"n\"];\n";
	107	break;
	108	case _S_opcode_subexpr_begin:
	109	__ostr << __id << " [label=\"" << __id << "\\nSBEGIN "
	110	<< _M_subexpr << "\"];\n"
	111	<< __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	112	break;
	113	case _S_opcode_subexpr_end:
	114	__ostr << __id << " [label=\"" << __id << "\\nSEND "
	115	<< _M_subexpr << "\"];\n"
	116	<< __id << " -> " << _M_next << " [label=\"epsilon\"];\n";
	117	break;
	118	case _S_opcode_dummy:
	119	break;
	120	case _S_opcode_match:
	121	__ostr << __id << " [label=\"" << __id << "\\nMATCH\"];\n"
	122	<< __id << " -> " << _M_next << " [label=\"<match>\"];\n";
	123	break;
	124	case _S_opcode_accept:
	125	__ostr << __id << " [label=\"" << __id << "\\nACC\"];\n" ;
	126	break;
	127	default:
	128	_GLIBCXX_DEBUG_ASSERT(false);
	129	break;
6cb784b6	130	}
7d9d2185 JW	131	return __ostr;
7d9d2185 JW	132	}
6cb784b6	133
68e69ce2	134	template<typename _TraitsT>
7d9d2185	135	std::ostream&
68e69ce2	136	_NFA<_TraitsT>::_M_dot(std::ostream& __ostr) const
6cb784b6 TS	137	{
6cb784b6 TS	138	__ostr << "digraph _Nfa {\n"
ddf41e9d	139	" rankdir=LR;\n";
6cb43087	140	for (size_t __i = 0; __i < this->size(); ++__i)
ddf41e9d	141	(*this)[__i]._M_dot(__ostr, __i);
6cb784b6 TS	142	__ostr << "}\n";
	143	return __ostr;
	144	}
	145	#endif
	146
68e69ce2	147	template<typename _TraitsT>
7d9d2185	148	_StateIdT
68e69ce2	149	_NFA<_TraitsT>::_M_insert_backref(size_t __index)
ce645eb0	150	{
e4846be7	151	if (this->_M_flags & regex_constants::__polynomial)
236d76c4 TS	152	__throw_regex_error(regex_constants::error_complexity,
236d76c4 TS	153	"Unexpected back-reference in polynomial mode.");
ce645eb0 TS	154	// To figure out whether a backref is valid, a stack is used to store
	155	// unfinished sub-expressions. For example, when parsing
	156	// "(a(b)(c\\1(d)))" at '\\1', _M_subexpr_count is 3, indicating that 3
	157	// sub expressions are parsed or partially parsed(in the stack), aka,
	158	// "(a..", "(b)" and "(c..").
	159	// _M_paren_stack is {1, 3}, for incomplete "(a.." and "(c..". At this
	160	// time, "\\2" is valid, but "\\1" and "\\3" are not.
	161	if (__index >= _M_subexpr_count)
236d76c4 TS	162	__throw_regex_error(
	163	regex_constants::error_backref,
	164	"Back-reference index exceeds current sub-expression count.");
7d9d2185	165	for (auto __it : this->_M_paren_stack)
e280b6ff	166	if (__index == __it)
236d76c4 TS	167	__throw_regex_error(
	168	regex_constants::error_backref,
	169	"Back-reference referred to an opened sub-expression.");
7d9d2185	170	this->_M_has_backref = true;
7b86458e TS	171	_StateT __tmp(_S_opcode_backref);
7b86458e TS	172	__tmp._M_backref_index = __index;
7d9d2185	173	return _M_insert_state(std::move(__tmp));
ce645eb0 TS	174	}
ce645eb0 TS	175
68e69ce2	176	template<typename _TraitsT>
7d9d2185	177	void
68e69ce2	178	_NFA<_TraitsT>::_M_eliminate_dummy()
6cb784b6	179	{
7c812a2a TS	180	for (auto& __it : *this)
7c812a2a TS	181	{
81b7ff07	182	while (__it._M_next >= 0 && (*this)[__it._M_next]._M_opcode()
7b86458e	183	== _S_opcode_dummy)
7c812a2a	184	__it._M_next = (*this)[__it._M_next]._M_next;
81b7ff07 TS	185	if (__it._M_has_alt())
81b7ff07 TS	186	while (__it._M_alt >= 0 && (*this)[__it._M_alt]._M_opcode()
7c812a2a TS	187	== _S_opcode_dummy)
	188	__it._M_alt = (*this)[__it._M_alt]._M_next;
	189	}
6cb784b6 TS	190	}
6cb784b6 TS	191
7c812a2a	192	// Just apply DFS on the sequence and re-link their links.
68e69ce2 JW	193	template<typename _TraitsT>
	194	_StateSeq<_TraitsT>
	195	_StateSeq<_TraitsT>::_M_clone()
6cb784b6	196	{
5bcb66df	197	std::map<_StateIdT, _StateIdT> __m;
7c812a2a TS	198	std::stack<_StateIdT> __stack;
	199	__stack.push(_M_start);
	200	while (!__stack.empty())
	201	{
	202	auto __u = __stack.top();
	203	__stack.pop();
	204	auto __dup = _M_nfa[__u];
ddf41e9d	205	// _M_insert_state() never return -1
81b7ff07	206	auto __id = _M_nfa._M_insert_state(std::move(__dup));
7c812a2a	207	__m[__u] = __id;
81b7ff07	208	if (__dup._M_has_alt())
5bcb66df TS	209	if (__dup._M_alt != _S_invalid_state_id
5bcb66df TS	210	&& __m.count(__dup._M_alt) == 0)
7c812a2a	211	__stack.push(__dup._M_alt);
836c42f6 TS	212	if (__u == _M_end)
836c42f6 TS	213	continue;
5bcb66df TS	214	if (__dup._M_next != _S_invalid_state_id
5bcb66df TS	215	&& __m.count(__dup._M_next) == 0)
836c42f6	216	__stack.push(__dup._M_next);
7c812a2a	217	}
5bcb66df	218	for (auto __it : __m)
7c812a2a	219	{
5bcb66df	220	auto __v = __it.second;
ddf41e9d TS	221	auto& __ref = _M_nfa[__v];
ddf41e9d TS	222	if (__ref._M_next != _S_invalid_state_id)
7c812a2a	223	{
2f1e8e7c	224	__glibcxx_assert(__m.count(__ref._M_next) > 0);
7c812a2a TS	225	__ref._M_next = __m[__ref._M_next];
7c812a2a TS	226	}
81b7ff07	227	if (__ref._M_has_alt())
ddf41e9d	228	if (__ref._M_alt != _S_invalid_state_id)
7c812a2a	229	{
2f1e8e7c	230	__glibcxx_assert(__m.count(__ref._M_alt) > 0);
7c812a2a TS	231	__ref._M_alt = __m[__ref._M_alt];
	232	}
	233	}
	234	return _StateSeq(_M_nfa, __m[_M_start], __m[_M_end]);
6cb784b6 TS	235	}
6cb784b6 TS	236
6cb784b6 TS	237	_GLIBCXX_END_NAMESPACE_VERSION
	238	} // namespace __detail
	239	} // namespace