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)
53 LPushLexer::transaction(char ch, State newState)
57 case '{': parser.push(TToken(TToken::BEGIN)); break;
58 case '}': parser.push(TToken(TToken::END)); break;
59 case '$': parser.push(TToken(TToken::SHIFT)); break;
60 case '&': parser.push(TToken(TToken::ALIGN)); break;
62 case '\r': parser.push(TToken(TToken::EOL, ch)); break;
63 case '^': parser.push(TToken(TToken::SUPERSCRIPT)); break;
64 case '_': parser.push(TToken(TToken::SUBSCRIPT)); break;
65 case '\t': parser.push(TToken(TToken::IGNORABLE_SPACE, ch)); break;
66 case ' ': parser.push(TToken(TToken::SPACE, ch)); break;
67 case '~': parser.push(TToken(TToken::ACTIVE, ch)); break;
68 case '%': parser.push(TToken(TToken::COMMENT)); break;
69 default: parser.push(TToken(TToken::OTHER, ch)); break;
75 LPushLexer::push(char ch)
80 if (ch == '\\') state = ESCAPE;
81 else if (ch == '#') state = PARAMETER;
93 else transaction(ch, ACCEPT);
101 else if (ch == -1) error();
102 else if (isdigit(ch))
104 // in this case, the previous '\' is ignored
105 buffer.push_back(ch);
110 parser.push(TToken(TToken::CONTROL, ch));
117 parser.push(TToken(TToken::CONTROL, buffer));
123 parser.push(TToken(TToken::CONTROL, buffer));
127 else if (isalpha(ch))
128 buffer.push_back(ch);
131 parser.push(TToken(TToken::CONTROL, buffer));
135 else if (isspace(ch))
137 // we don't call transaction, because a white space is useful to exit from the macro,
138 // without "side effect". It's the TeX syntax.
139 parser.push(TToken(TToken::CONTROL, buffer));
143 else if (isdigit(ch))
145 parser.push(TToken(TToken::CONTROL, buffer));
147 buffer.push_back(ch);
152 parser.push(TToken(TToken::CONTROL, buffer));
154 transaction(ch, ACCEPT);
158 if (ch == -1) error();
161 parser.push(TToken(TToken::PARAMETER, ch));
168 parser.push(TToken(TToken::LETTER, buffer));
172 else if (isalpha(ch) || isdigit(ch))
174 buffer.push_back(ch);
176 else if (ch == '\\') state = ESCAPED_CHARACTER;
179 parser.push(TToken(TToken::LETTER, buffer));
185 parser.push(TToken(TToken::LETTER, buffer));
187 transaction(ch, ACCEPT);
190 case ESCAPED_CHARACTER:
191 if ((ch == '-') || (ch == '_'))
193 buffer.push_back(ch);
196 else if (isalpha(ch))
198 parser.push(TToken(TToken::LETTER, buffer));
200 buffer.push_back(ch);
203 else if (ch == -1) error();
204 else if (isdigit(ch))
206 parser.push(TToken(TToken::LETTER, buffer));
208 buffer.push_back(ch);
213 parser.push(TToken(TToken::LETTER, buffer));
215 parser.push(TToken(TToken::CONTROL, ch));
220 if (isdigit(ch)) buffer.push_back(ch);
221 else if (isalpha(ch))
223 parser.push(TToken(TToken::DIGIT, buffer));
225 buffer.push_back(ch);
230 parser.push(TToken(TToken::DIGIT, buffer));
236 parser.push(TToken(TToken::DIGIT, buffer));
242 parser.push(TToken(TToken::DIGIT, buffer));
248 parser.push(TToken(TToken::DIGIT, buffer));
250 transaction(ch, ACCEPT);
263 LPushLexer::drop(bool alt)
265 std::string restore = "";
271 restore = parser.drop(alt);
272 long bs_pos = restore.find('\\');
273 if ((restore.length() > 0) && (bs_pos != std::string::npos))
275 // in this case we have to control the blackslash's position
278 //logger.debug(restore);
279 buffer = std::string(restore, 1, restore.length() - 1);
280 state = (buffer.length() > 0) ? MACRO : ESCAPE;
284 assert(bs_pos == restore.length() - 1);
285 buffer = std::string(restore, 0, bs_pos);
286 state = ESCAPED_CHARACTER;
289 else if (restore.length() > 0 && isdigit(restore[0]))
294 else if (restore.length() > 0 && isalpha(restore[0]))
301 /* if (restore.length() > 0 && restore[0] == '\\')
303 logger.debug(restore);
304 buffer = std::string(restore, 1, restore.length() - 1);
305 state = (buffer.length() > 0) ? MACRO : ESCAPE;
307 else if (restore.length() > 0 && isdigit(restore[0]))
312 else if (restore.length() > 0 && isalpha(restore[0]))
318 case ESCAPED_CHARACTER:
325 if (alt) buffer.erase();
326 else buffer.erase(buffer.length() - 1, 1);
327 if (buffer.length() == 0) state = ESCAPE;
330 switch (buffer[buffer.length() - 1])
334 buffer.erase(buffer.length() - 1, 1);
335 if (alt) state = ESCAPED_CHARACTER;
338 if (alt) buffer.erase();
339 else buffer.erase(buffer.length() - 1, 1);
340 if (buffer.length() == 0) state = ACCEPT;
345 if (alt) buffer.erase();
346 else buffer.erase(buffer.length() - 1, 1);
347 if (buffer.length() == 0) state = ACCEPT;
361 LPushLexer::displayCursor()
365 case ESCAPE: parser.setCursorHint("\\"); break;
366 case ESCAPED_CHARACTER: parser.setCursorHint(buffer + "\\"); break;
367 case MACRO: parser.setCursorHint("\\" + buffer); break;
368 case PARAMETER: parser.setCursorHint("#"); break;
369 case IDENTIFIER: parser.setCursorHint(buffer); break;
370 case NUMBER: parser.setCursorHint(buffer); break;
371 default: parser.setCursorHint(""); break;
376 LPushLexer::error() const