4 // Copyright (C) 2006 Matthias Braun <matze@braunis.de>
6 // This program is free software; you can redistribute it and/or
7 // modify it under the terms of the GNU General Public License
8 // as published by the Free Software Foundation; either version 2
9 // of the License, or (at your option) any later version.
11 // This program 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.
16 // You should have received a copy of the GNU General Public License
17 // along with this program; if not, write to the Free Software
18 // Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
35 Lexer::Lexer(std::istream& newstream)
36 : stream(newstream), eof(false), linenumber(0)
39 // trigger a refill of the buffer
43 } catch(EOFException& ) {
58 stream.read(buffer, BUFFER_SIZE);
59 size_t bytes_read = stream.gcount();
62 bufend = buffer + bytes_read;
64 // the following is a hack that appends an additional ' ' at the end of
65 // the file to avoid problems when parsing symbols/elements and a sudden
66 // EOF. This is faster than relying on unget and IMO also nicer.
67 if(bytes_read == 0 || stream.eof()) {
78 static const char* delims = "\"();";
98 return getNextToken(); // and again
101 return TOKEN_OPEN_PAREN;
104 return TOKEN_CLOSE_PAREN;
105 case '"': { // string
106 int startline = linenumber;
112 else if (*c == '\r') // XXX this breaks with pure \r EOL
116 else if(*c == '\\') {
127 if(token_length < MAX_TOKEN_LENGTH)
128 token_string[token_length++] = *c;
130 token_string[token_length] = 0;
131 } catch(EOFException& ) {
132 std::stringstream msg;
133 msg << "Parse error in line " << startline << ": "
134 << "EOF while parsing string.";
135 throw std::runtime_error(msg.str());
140 case '#': // constant
144 while(isalnum(*c) || *c == '_') {
145 if(token_length < MAX_TOKEN_LENGTH)
146 token_string[token_length++] = *c;
149 token_string[token_length] = 0;
150 } catch(EOFException& ) {
151 std::stringstream msg;
152 msg << "Parse Error in line " << linenumber << ": "
153 << "EOF while parsing constant.";
154 throw std::runtime_error(msg.str());
157 if(strcmp(token_string, "t") == 0)
159 if(strcmp(token_string, "f") == 0)
162 // we only handle #t and #f constants at the moment...
165 std::stringstream msg;
166 msg << "Parse Error in line " << linenumber << ": "
167 << "Unknown constant '" << token_string << "'.";
168 throw std::runtime_error(msg.str());
172 if(isdigit(*c) || *c == '-') {
173 bool have_nondigits = false;
174 bool have_digits = false;
175 int have_floating_point = 0;
181 ++have_floating_point;
182 else if(isalnum(*c) || *c == '_')
183 have_nondigits = true;
185 if(token_length < MAX_TOKEN_LENGTH)
186 token_string[token_length++] = *c;
189 } while(!isspace(*c) && !strchr(delims, *c));
191 token_string[token_length] = 0;
195 if(have_nondigits || !have_digits || have_floating_point > 1)
197 else if(have_floating_point == 1)
200 return TOKEN_INTEGER;
203 if(token_length < MAX_TOKEN_LENGTH)
204 token_string[token_length++] = *c;
206 } while(!isspace(*c) && !strchr(delims, *c));
207 token_string[token_length] = 0;
214 } catch(EOFException& ) {
219 } // end of namespace lisp