File: lexer.cpp

package info (click to toggle)
qonk 0.3.1-1
  • links: PTS, VCS
  • area: main
  • in suites: lenny
  • size: 2,076 kB
  • ctags: 2,026
  • sloc: cpp: 14,978; sh: 3,464; makefile: 200
file content (254 lines) | stat: -rw-r--r-- 8,295 bytes parent folder | download | duplicates (3)
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
//  $Id: lexer.cpp 1025 2007-04-30 14:48:32Z hiker $
//
//  TuxKart - a fun racing game with go-kart
//  Copyright (C) 2004 Matthias Braun <matze@braunis.de>
//  code in this file based on lispreader from Mark Probst
//
//  This program is free software; you can redistribute it and/or
//  modify it under the terms of the GNU General Public License
//  as published by the Free Software Foundation; either version 2
//  of the License, or (at your option) any later version.
//
//  This program is distributed in the hope that it will be useful,
//  but WITHOUT ANY WARRANTY; without even the implied warranty of
//  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
//  GNU General Public License for more details.
//
//  You should have received a copy of the GNU General Public License
//  along with this program; if not, write to the Free Software
//  Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
#include <sstream>
#include <stdexcept>

#include "lexer.hpp"
#include "translation.hpp"
#if defined(WIN32) && !defined(__CYGWIN__)
#  define snprintf _snprintf
#endif
namespace lisp
{
    class EOFException
        {}
    ;

    Lexer::Lexer(std::istream& newstream)
            : m_stream(newstream), m_is_eof(false)
    {
        try
        {
            // trigger a refill of the m_buffer
            m_c = 0;
            m_buffer_end = m_c + 1;
            nextChar();
        }
        catch(EOFException& e)
        {}
    }

//-----------------------------------------------------------------------------

    Lexer::~Lexer()
    {}

//-----------------------------------------------------------------------------

    void
    Lexer::nextChar()
    {
        ++m_c;
        if(m_c >= m_buffer_end)
        {
            if(m_is_eof)
                throw EOFException();
            m_stream.read(m_buffer, LEXER_BUFFER_SIZE);
            std::streamsize n = m_stream.gcount();

            m_c = m_buffer;
            m_buffer_end = m_buffer + n;

            // the following is a hack that appends an additional ' ' at the end of
            // the file to avoid problems when parsing symbols/elements and a sudden
            // EOF. This is faster than relying on unget and IMO also nicer.
            if(n < LEXER_BUFFER_SIZE || n == 0)
            {
                *m_buffer_end = ' ';
                ++m_buffer_end;
                m_is_eof = true;
            }
        }
    }

//-----------------------------------------------------------------------------

    Lexer::TokenType
    Lexer::getNextToken()
    {
        static const char* delims = "\"();";

        try
        {
            while(isspace(*m_c))
            {
                nextChar();
                if(*m_c == '\n')
                    ++m_line_number;
            };

            m_token_length = 0;

            switch(*m_c)
            {
            case ';': // comment
                while(true)
                {
                    nextChar();
                    if(*m_c == '\n')
                    {
                        ++m_line_number;
                        break;
                    }
                }
                return getNextToken(); // and again
            case '(':
                nextChar();
                return TOKEN_OPEN_PAREN;
            case ')':
                nextChar();
                return TOKEN_CLOSE_PAREN;
            case '"': // string
                {
                    const int STARTLINE = m_line_number;
                    try
                    {
                        while(1)
                        {
                            nextChar();
                            if(*m_c == '"')
                                break;

                            if(*m_c == '\\')
                            {
                                nextChar();
                                switch(*m_c)
                                {
                                case 'n':
                                    *m_c = '\n';
                                    break;
                                case 't':
                                    *m_c = '\t';
                                    break;
                                }
                            }
                            if(m_token_length < MAX_TOKEN_LENGTH)
                                m_token_string[m_token_length++] = *m_c;
                        }
                        m_token_string[m_token_length] = 0;
                    }
                    catch(EOFException& )
                    {
                        char msg[MAX_ERROR_MESSAGE_LENGTH];
                        snprintf(msg, sizeof(msg),
                                 "Parse error in line %d: EOF while parsing string.",
                                 STARTLINE);
                        throw std::runtime_error(msg);
                    }
                    nextChar();
                    return TOKEN_STRING;
                }
            case '#': // constant
                try
                {
                    nextChar();

                    while(isalnum(*m_c) || *m_c == '_')
                    {
                        if(m_token_length < MAX_TOKEN_LENGTH)
                            m_token_string[m_token_length++] = *m_c;
                        nextChar();
                    }
                    m_token_string[m_token_length] = 0;
                }
                catch(EOFException& )
                {
                    char msg[MAX_ERROR_MESSAGE_LENGTH];
                    snprintf(msg, sizeof(msg), 
                             "Parse Error in line %d: EOF while parsing constant.",
                             m_line_number);
                    throw std::runtime_error(msg);
                }

                if(strcmp(m_token_string, "t") == 0)
                    return TOKEN_TRUE;
                if(strcmp(m_token_string, "f") == 0)
                    return TOKEN_FALSE;

                // this would be the place to add more sophisticated handling of
                // constants

                {
                    char msg[MAX_ERROR_MESSAGE_LENGTH];
                    snprintf(msg, sizeof(msg), 
                             "Parse Error in line %d: Unknown constant '%s'.",
                             m_line_number, m_token_string);
                    throw std::runtime_error(msg);
                }

            default:
                if(isdigit(*m_c) || *m_c == '-')
                {
                    bool have_nondigits = false;
                    bool have_digits = false;
                    int have_floating_point = 0;

                    do
                    {
                        if(isdigit(*m_c))
                            have_digits = true;
                        else if(*m_c == '.')
                            ++have_floating_point;
                        else if(isalnum(*m_c) || *m_c == '_')
                            have_nondigits = true;

                        if(m_token_length < MAX_TOKEN_LENGTH)
                            m_token_string[m_token_length++] = *m_c;

                        nextChar();
                    }
                    while(!isspace(*m_c) && !strchr(delims, *m_c));

                    m_token_string[m_token_length] = 0;

                    // no nextChar

                    if(have_nondigits || !have_digits || have_floating_point > 1)
                        return TOKEN_SYMBOL;
                    else if(have_floating_point == 1)
                        return TOKEN_REAL;
                    else
                        return TOKEN_INTEGER;
                }
                else
                {
                    do
                    {
                        if(m_token_length < MAX_TOKEN_LENGTH)
                            m_token_string[m_token_length++] = *m_c;
                        nextChar();
                    }
                    while(!isspace(*m_c) && !strchr(delims, *m_c));
                    m_token_string[m_token_length] = 0;

                    // no nextChar

                    return TOKEN_SYMBOL;
                }
            }
        }
        catch(EOFException& )
        {
            return TOKEN_EOF;
        }
    }

} // end of namespace lisp