/usr/include/lexertl/dot.hpp is in libpuma-dev 1:2.2+git20170823-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 | // dot.hpp
// Copyright (c) 2005-2015 Ben Hanson (http://www.benhanson.net/)
// Copyright (c) 2013 Autodesk, Inc. All rights reserved.
//
// Distributed under the Boost Software License, Version 1.0. (See accompanying
// file licence_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt)
#ifndef LEXERTL_DOT_HPP
#define LEXERTL_DOT_HPP
#include <ostream>
#include "rules.hpp"
#include "state_machine.hpp"
#include "sm_to_csm.hpp"
namespace lexertl
{
//! The class template basic_dot contains utility functions used to
//! dump a description of a finite state machine formatted in the
//! DOT language (http://www.graphviz.org/doc/info/lang.html). The
//! resulting directed graph can previewed by opening the ".dot" file
//! into the GraphViz application (http://www.graphviz.org).
template<typename sm, typename char_type, typename id_type = std::size_t,
bool is_dfa = true>
class basic_dot
{
public:
typedef lexertl::basic_char_state_machine<char_type, id_type, is_dfa>
char_state_machine;
typedef lexertl::basic_rules<char_type, char_type, id_type> rules;
typedef std::basic_ostream<char_type> ostream;
typedef std::basic_string<char_type> string;
//! Dumps a description of the finite state machine expressed in
//! the DOT language to the given output stream.
static void dump(const sm &sm_, rules &rules_, ostream &stream_)
{
char_state_machine csm_;
sm_to_csm(sm_, csm_);
dump(csm_, rules_, stream_);
}
//! Dumps a description of the finite state machine expressed in
//! the DOT language to the given output stream.
static void dump(const char_state_machine &csm_, rules &rules_,
ostream &stream_)
{
header(stream_);
for (std::size_t dfa_ = 0, dfas_ = csm_.size(); dfa_ < dfas_; ++dfa_)
{
dump_ex(dfa_, csm_._sm_deque[dfa_], rules_, stream_);
}
trailer(stream_);
}
protected:
typedef typename char_state_machine::state dfa_state;
typedef typename dfa_state::string_token string_token;
typedef std::basic_stringstream<char_type> stringstream;
// Naming of nodes used in the DOT diagram. The naming is of the
// form: L<dfa_id>_S<state_id>.
static string node_name(id_type dfa_id_, id_type state_id_)
{
stringstream namestream_;
namestream_ << "L" << dfa_id_ << "_S" << state_id_;
return namestream_.str();
}
// Escape control characters twice. This is necessary when
// expressing character sets attached as to DOT nodes as
// labels.
static string double_escape_char(const id_type ch_)
{
stringstream out_;
switch (ch_)
{
case '\0':
out_ << '\\';
out_ << '\\';
out_ << '0';
break;
case '\a':
out_ << '\\';
out_ << '\\';
out_ << 'a';
break;
case '\b':
out_ << '\\';
out_ << '\\';
out_ << 'b';
break;
case '\f':
out_ << '\\';
out_ << '\\';
out_ << 'f';
break;
case '\n':
out_ << '\\';
out_ << '\\';
out_ << 'n';
break;
case '\r':
out_ << '\\';
out_ << '\\';
out_ << 'r';
break;
case '\t':
out_ << '\\';
out_ << '\\';
out_ << 't';
break;
case '\v':
out_ << '\\';
out_ << '\\';
out_ << 'v';
break;
case '\\':
out_ << '\\';
out_ << '\\';
break;
case '"':
out_ << '\\';
out_ << '\\';
out_ << '"';
break;
case '\'':
out_ << '\\';
out_ << '\\';
out_ << '\'';
break;
default:
{
if (ch_ < 32 || ch_ > 126)
{
out_ << '\\';
out_ << 'x';
out_ << std::hex <<
static_cast<std::size_t>(ch_);
}
else
{
out_ << char_type(ch_);
}
break;
}
}
return out_.str();
}
// Internal function actually performing the work of dumping the
// state machine in DOT.
static void dump_ex(id_type dfa_id_,
const typename char_state_machine::dfa &dfa_,
rules &rules_,
ostream &stream_)
{
const std::size_t states_ = dfa_._states.size();
typename dfa_state::id_type_string_token_map::const_iterator iter_;
typename dfa_state::id_type_string_token_map::const_iterator end_;
stream_ << std::endl;
for (std::size_t i_ = 0; i_ < states_; ++i_)
{
const dfa_state &state_ = dfa_._states[i_];
const string name = node_name(dfa_id_, i_);
if (i_ == 0)
{
stream_ << " " << name << " [shape = doublecircle, xlabel=\""
<< rules_.state(dfa_id_) << "\"];" << std::endl;
}
else if (state_._end_state)
{
stream_ << " " << name <<
" [shape = doublecircle, xlabel=\"id =" <<
static_cast<std::size_t>(state_._id) << "\"];" <<
std::endl;
}
else {
stream_ << " " << name << " [shape = circle];" << std::endl;
}
}
stream_ << std::endl;
for (std::size_t i_ = 0; i_ < states_; ++i_)
{
const dfa_state &state_ = dfa_._states[i_];
iter_ = state_._transitions.begin();
end_ = state_._transitions.end();
const string src_name = node_name(dfa_id_, i_);
for (; iter_ != end_; ++iter_)
{
const string dst_name = node_name(dfa_id_, iter_->first);
stream_ << " " << src_name << " -> " << dst_name <<
" [label = \"";
string_token token_ = iter_->second;
open_bracket(stream_);
if (!iter_->second.any() && iter_->second.negatable())
{
token_.negate();
negated(stream_);
}
string chars_;
typename string_token::range_vector::const_iterator
ranges_iter_ = token_._ranges.begin();
typename string_token::range_vector::const_iterator
ranges_end_ = token_._ranges.end();
for (; ranges_iter_ != ranges_end_; ++ranges_iter_)
{
if (ranges_iter_->first == '^' ||
ranges_iter_->first == ']')
{
stream_ << "\\\\";
}
chars_ = double_escape_char(ranges_iter_->first);
if (ranges_iter_->first != ranges_iter_->second)
{
if (ranges_iter_->first + 1 < ranges_iter_->second)
{
chars_ += '-';
}
if (ranges_iter_->second == '^' ||
ranges_iter_->second == ']')
{
stream_ << "\\\\";
}
chars_ += double_escape_char(ranges_iter_->second);
}
stream_ << chars_;
}
close_bracket(stream_);
stream_ << "\"];" << std::endl;
}
if (state_._end_state) {
const string dst_name = node_name(state_._next_dfa, 0);
stream_ << " " << src_name << " -> " << dst_name
<< " [style = \"dashed\"];" << std::endl;
}
}
}
static void header(ostream &stream_)
{
stream_ << "digraph DFAs {" << std::endl;
stream_ << " rankdir = LR;" << std::endl;
}
static void trailer(ostream &stream_)
{
stream_ << "}" << std::endl;
}
static void open_bracket(ostream &stream_)
{
stream_ << "[";
}
static void negated(ostream &stream_)
{
stream_ << "^";
}
static void close_bracket(ostream &stream_)
{
stream_ << "]";
}
};
typedef basic_dot<basic_state_machine<char>, char> dot;
typedef basic_dot<basic_state_machine<wchar_t>, wchar_t> wdot;
}
#endif
|