1 /* This file is part of EdiTeX, an editor of mathematical
2 * expressions based on TeX syntax.
4 * Copyright (C) 2002-2003 Luca Padovani <lpadovan@cs.unibo.it>,
5 * 2003 Paolo Marinelli <pmarinel@cs.unibo.it>.
7 * This library is free software; you can redistribute it and/or
8 * modify it under the terms of the GNU Lesser General Public
9 * License as published by the Free Software Foundation; either
10 * version 2.1 of the License, or (at your option) any later version.
12 * This library is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15 * Lesser General Public License for more details.
17 * You should have received a copy of the GNU Lesser General Public
18 * License along with this library; if not, write to the Free Software
19 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
21 * For more information, please visit the project's home page
22 * http://helm.cs.unibo.it/editex/
23 * or send an email to <lpadovan@cs.unibo.it>
30 #include "LPushLexer.hh"
31 #include "APushParser.hh"
33 LPushLexer::LPushLexer(ALogger& l, APushParser& p) : APushLexer(l, p)
52 LPushLexer::transaction(char ch, State newState)
56 case '{': parser.push(TToken(TToken::BEGIN)); break;
57 case '}': parser.push(TToken(TToken::END)); break;
58 case '$': parser.push(TToken(TToken::SHIFT)); break;
59 case '&': parser.push(TToken(TToken::ALIGN)); break;
61 case '\r': parser.push(TToken(TToken::EOL, ch)); break;
62 case '^': parser.push(TToken(TToken::SUPERSCRIPT)); break;
63 case '_': parser.push(TToken(TToken::SUBSCRIPT)); break;
64 case '\t': parser.push(TToken(TToken::IGNORABLE_SPACE, ch)); break;
65 case ' ': parser.push(TToken(TToken::SPACE, ch)); break;
66 case '~': parser.push(TToken(TToken::ACTIVE, ch)); break;
67 case '%': parser.push(TToken(TToken::COMMENT)); break;
68 default: parser.push(TToken(TToken::OTHER, ch)); break;
74 LPushLexer::push(char ch)
79 if (ch == '\\') state = ESCAPE;
80 else if (ch == '#') state = PARAMETER;
92 else transaction(ch, ACCEPT);
100 else if (ch == -1) error();
101 else if (isdigit(ch))
103 // in this case, the previous '\' is ignored
104 buffer.push_back(ch);
109 parser.push(TToken(TToken::CONTROL, ch));
116 parser.push(TToken(TToken::CONTROL, buffer));
122 parser.push(TToken(TToken::CONTROL, buffer));
126 else if (isalpha(ch))
127 buffer.push_back(ch);
130 parser.push(TToken(TToken::CONTROL, buffer));
134 else if (isspace(ch))
136 // we don't call transaction, because a white space is useful to exit from the macro,
137 // without "side effect". It's the TeX syntax.
138 parser.push(TToken(TToken::CONTROL, buffer));
142 else if (isdigit(ch))
144 parser.push(TToken(TToken::CONTROL, buffer));
146 buffer.push_back(ch);
151 parser.push(TToken(TToken::CONTROL, buffer));
153 transaction(ch, ACCEPT);
157 if (ch == -1) error();
160 parser.push(TToken(TToken::PARAMETER, ch));
167 parser.push(TToken(TToken::LETTER, buffer));
171 else if (isalpha(ch) || isdigit(ch))
173 buffer.push_back(ch);
175 else if (ch == '\\') state = ESCAPED_CHARACTER;
178 parser.push(TToken(TToken::LETTER, buffer));
184 parser.push(TToken(TToken::LETTER, buffer));
186 transaction(ch, ACCEPT);
189 case ESCAPED_CHARACTER:
190 if ((ch == '-') || (ch == '_'))
192 buffer.push_back(ch);
195 else if (isalpha(ch))
197 parser.push(TToken(TToken::LETTER, buffer));
199 buffer.push_back(ch);
202 else if (ch == -1) error();
203 else if (isdigit(ch))
205 parser.push(TToken(TToken::LETTER, buffer));
207 buffer.push_back(ch);
212 parser.push(TToken(TToken::LETTER, buffer));
214 parser.push(TToken(TToken::CONTROL, ch));
219 if (isdigit(ch)) buffer.push_back(ch);
220 else if (isalpha(ch))
222 parser.push(TToken(TToken::DIGIT, buffer));
224 buffer.push_back(ch);
229 parser.push(TToken(TToken::DIGIT, buffer));
235 parser.push(TToken(TToken::DIGIT, buffer));
241 parser.push(TToken(TToken::DIGIT, buffer));
247 parser.push(TToken(TToken::DIGIT, buffer));
249 transaction(ch, ACCEPT);
262 LPushLexer::drop(bool alt)
264 std::string restore = "";
270 restore = parser.drop(alt);
271 long bs_pos = restore.find('\\');
272 if ((restore.length() > 0) && (bs_pos != std::string::npos))
274 // in this case we have to control the blackslash's position
277 //logger.debug(restore);
278 buffer = std::string(restore, 1, restore.length() - 1);
279 state = (buffer.length() > 0) ? MACRO : ESCAPE;
283 assert(bs_pos == restore.length() - 1);
284 buffer = std::string(restore, 0, bs_pos);
285 state = ESCAPED_CHARACTER;
288 else if (restore.length() > 0 && isdigit(restore[0]))
293 else if (restore.length() > 0 && isalpha(restore[0]))
300 /* if (restore.length() > 0 && restore[0] == '\\')
302 logger.debug(restore);
303 buffer = std::string(restore, 1, restore.length() - 1);
304 state = (buffer.length() > 0) ? MACRO : ESCAPE;
306 else if (restore.length() > 0 && isdigit(restore[0]))
311 else if (restore.length() > 0 && isalpha(restore[0]))
317 case ESCAPED_CHARACTER:
324 if (alt) buffer.erase();
325 else buffer.erase(buffer.length() - 1, 1);
326 if (buffer.length() == 0) state = ESCAPE;
329 switch (buffer[buffer.length() - 1])
333 buffer.erase(buffer.length() - 1, 1);
334 if (alt) state = ESCAPED_CHARACTER;
337 if (alt) buffer.erase();
338 else buffer.erase(buffer.length() - 1, 1);
339 if (buffer.length() == 0) state = ACCEPT;
344 if (alt) buffer.erase();
345 else buffer.erase(buffer.length() - 1, 1);
346 if (buffer.length() == 0) state = ACCEPT;
360 LPushLexer::displayCursor()
364 case ESCAPE: parser.setCursorHint("\\"); break;
365 case ESCAPED_CHARACTER: parser.setCursorHint(buffer + "\\"); break;
366 case MACRO: parser.setCursorHint("\\" + buffer); break;
367 case PARAMETER: parser.setCursorHint("#"); break;
368 case IDENTIFIER: parser.setCursorHint(buffer); break;
369 case NUMBER: parser.setCursorHint(buffer); break;
370 default: parser.setCursorHint(""); break;
375 LPushLexer::error() const