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>
31 #include "LPushLexer.hh"
32 #include "APushParser.hh"
34 LPushLexer::LPushLexer(ALogger& l, APushParser& p) : APushLexer(l, p)
55 LPushLexer::transaction(char ch, State newState)
59 case '{': parser.push(TToken(TToken::BEGIN)); break;
60 case '}': parser.push(TToken(TToken::END)); break;
61 case '$': parser.push(TToken(TToken::SHIFT)); break;
62 case '&': parser.push(TToken(TToken::ALIGN)); break;
64 case '\r': parser.push(TToken(TToken::EOL, ch)); break;
65 case '^': parser.push(TToken(TToken::SUPERSCRIPT)); break;
66 case '_': parser.push(TToken(TToken::SUBSCRIPT)); break;
67 case '\t': parser.push(TToken(TToken::IGNORABLE_SPACE, ch)); break;
68 case ' ': parser.push(TToken(TToken::SPACE, ch)); break;
69 case '~': parser.push(TToken(TToken::ACTIVE, ch)); break;
70 case '%': parser.push(TToken(TToken::COMMENT)); break;
71 default: parser.push(TToken(TToken::OTHER, ch)); break;
77 LPushLexer::push(char ch)
82 if (ch == '\\') state = ESCAPE;
83 else if (ch == '#') state = PARAMETER;
95 else transaction(ch, ACCEPT);
100 buffer.push_back(ch);
103 else if (ch == -1) error();
104 else if (isdigit(ch))
106 // in this case, the previous '\' is ignored
107 buffer.push_back(ch);
112 parser.push(TToken(TToken::CONTROL, ch));
119 parser.push(TToken(TToken::CONTROL, buffer));
125 parser.push(TToken(TToken::CONTROL, buffer));
129 else if (isalpha(ch))
130 buffer.push_back(ch);
133 parser.push(TToken(TToken::CONTROL, buffer));
137 else if (isspace(ch))
139 // we don't call transaction, because a white space is useful to exit from the macro,
140 // without "side effect". It's the TeX syntax.
141 parser.push(TToken(TToken::CONTROL, buffer));
145 else if (isdigit(ch))
147 parser.push(TToken(TToken::CONTROL, buffer));
149 buffer.push_back(ch);
154 parser.push(TToken(TToken::CONTROL, buffer));
156 transaction(ch, ACCEPT);
160 if (ch == -1) error();
163 parser.push(TToken(TToken::PARAMETER, ch));
170 parser.push(TToken(TToken::LETTER, buffer));
174 else if (isalpha(ch) || isdigit(ch))
176 buffer.push_back(ch);
178 else if (ch == '\\') state = ESCAPED_CHARACTER;
181 parser.push(TToken(TToken::LETTER, buffer));
187 parser.push(TToken(TToken::LETTER, buffer));
189 transaction(ch, ACCEPT);
192 case ESCAPED_CHARACTER:
193 if ((ch == '-') || (ch == '_') || (ch == '/'))
195 buffer.push_back(ch);
198 else if (isalpha(ch))
200 parser.push(TToken(TToken::LETTER, buffer));
202 buffer.push_back(ch);
205 else if (ch == -1) error();
206 else if (isdigit(ch))
208 parser.push(TToken(TToken::LETTER, buffer));
210 buffer.push_back(ch);
215 parser.push(TToken(TToken::LETTER, buffer));
217 parser.push(TToken(TToken::CONTROL, ch));
222 if (isdigit(ch)) buffer.push_back(ch);
223 else if (isalpha(ch))
225 parser.push(TToken(TToken::DIGIT, buffer));
227 buffer.push_back(ch);
232 parser.push(TToken(TToken::DIGIT, buffer));
238 parser.push(TToken(TToken::DIGIT, buffer));
244 parser.push(TToken(TToken::DIGIT, buffer));
250 parser.push(TToken(TToken::DIGIT, buffer));
252 transaction(ch, ACCEPT);
265 LPushLexer::drop(bool alt)
267 std::string restore = "";
273 restore = parser.drop(alt);
274 long bs_pos = restore.find('\\');
275 if ((restore.length() > 0) && (bs_pos != std::string::npos))
277 // in this case we have to control the blackslash's position
280 //logger.debug(restore);
281 buffer = std::string(restore, 1, restore.length() - 1);
282 state = (buffer.length() > 0) ? MACRO : ESCAPE;
286 assert(bs_pos == restore.length() - 1);
287 buffer = std::string(restore, 0, bs_pos);
288 state = ESCAPED_CHARACTER;
291 else if (restore.length() > 0 && isdigit(restore[0]))
296 else if (restore.length() > 0 && isalpha(restore[0]))
303 /* if (restore.length() > 0 && restore[0] == '\\')
305 logger.debug(restore);
306 buffer = std::string(restore, 1, restore.length() - 1);
307 state = (buffer.length() > 0) ? MACRO : ESCAPE;
309 else if (restore.length() > 0 && isdigit(restore[0]))
314 else if (restore.length() > 0 && isalpha(restore[0]))
320 case ESCAPED_CHARACTER:
327 if (alt) buffer.erase();
328 else buffer.erase(buffer.length() - 1, 1);
329 if (buffer.length() == 0) state = ESCAPE;
332 switch (buffer[buffer.length() - 1])
336 buffer.erase(buffer.length() - 1, 1);
337 if (alt) state = ESCAPED_CHARACTER;
340 if (alt) buffer.erase();
341 else buffer.erase(buffer.length() - 1, 1);
342 if (buffer.length() == 0) state = ACCEPT;
347 if (alt) buffer.erase();
348 else buffer.erase(buffer.length() - 1, 1);
349 if (buffer.length() == 0) state = ACCEPT;
363 LPushLexer::displayCursor()
367 case ESCAPE: parser.setCursorHint("\\"); break;
368 case ESCAPED_CHARACTER: parser.setCursorHint(buffer + "\\"); break;
369 case MACRO: parser.setCursorHint("\\" + buffer); break;
370 case PARAMETER: parser.setCursorHint("#"); break;
371 case IDENTIFIER: parser.setCursorHint(buffer); break;
372 case NUMBER: parser.setCursorHint(buffer); break;
373 default: parser.setCursorHint(""); break;
378 LPushLexer::error() const