summaryrefslogtreecommitdiffstats
path: root/src/lexer.ll
blob: e1b72ab5fc1893a872d616a2ed130e2b84165bae (plain)
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
/*
 * lexer.ll - part of abakus
 * Copyright (C) 2004, 2005 Michael Pyne <[email protected]>
 *
 * 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., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
 */
%option noyywrap
%{
#define YY_NO_UNPUT

#include <kdebug.h>

#include "node.h"
#include "function.h"
#include "parser_yacc.hpp"
#include "result.h"

int yyCurTokenPos;
int yyThisTokenLength;

int yyparse(void);
%}

DIGITS [0-9]+
HEX [0-9A-Fa-f]+
%%

 /* Always skip whitespace */
[ \t]* { yyCurTokenPos += yyThisTokenLength; yyThisTokenLength = yyleng; }

 /* Power operator */
"**" { 
    yyCurTokenPos += yyThisTokenLength;
    yyThisTokenLength = 2;
    return POWER;
}

"^" {
    yyCurTokenPos += yyThisTokenLength;
    yyThisTokenLength = 1;
    return POWER;
}

[sS][eE][tT] {
    yyCurTokenPos += yyThisTokenLength;
    yyThisTokenLength = 3;
    return SET;
}

[rR][eE][mM][oO][vV][eE] {
    yyCurTokenPos += yyThisTokenLength;
    yyThisTokenLength = 6;
    return REMOVE;
}

[dD][eE][rR][iI][vV] {
    yyCurTokenPos += yyThisTokenLength;
    yyThisTokenLength = 5;
    return DERIV;
}

 /* Read numbers of the form with at least the decimal point and trailing
 * digits, such as .32, -234.45, .0, etc.  Numbers are only read in the BEGIN
 * state.
 */
{DIGITS}*([\.,]{DIGITS}+)(e[-+]?{DIGITS}+)? {
    yyCurTokenPos += yyThisTokenLength;
    yyThisTokenLength = yyleng;
    return NUM;
}

 /* Read Hex */
0x({HEX}+)? {
    yyCurTokenPos += yyThisTokenLength;
    yyThisTokenLength = yyleng;
    return NUM;
}

 /* Read numbers with at least the integral part, such as +4234, -34e8, etc.
 * Numbers are only read in the BEGIN state.
 */
{DIGITS}+([\.,]{DIGITS}*)?(e[-+]?{DIGITS}+)? {
    yyCurTokenPos += yyThisTokenLength;
    yyThisTokenLength = yyleng;
    return NUM;
}

[nN][aA][nN] {
    yyCurTokenPos += yyThisTokenLength;
    yyThisTokenLength = yyleng;
    return NUM;
}

[iI][nN][fF] {
    yyCurTokenPos += yyThisTokenLength;
    yyThisTokenLength = yyleng;
    return NUM;
}

 /* This detects textual input, and if it isn't pre-declared by the parser (in
 * other words, if it isn't a function), then it is returned as an identifier.
 */
[a-zA-Z_][a-zA-Z_0-9]* {
    yyCurTokenPos += yyThisTokenLength;
    yyThisTokenLength = yyleng;

    if(FunctionManager::instance()->isFunction(yytext))
	return FN;
    else {
	return ID;
    }
}

 /* All other characters are returned as-is to the parser, who can accept or
 * reject it as needed.
 */
. {
    yyCurTokenPos += yyThisTokenLength;
    yyThisTokenLength = 1;
    return *yytext;
}

%%

class Lexer::Private
{
public:
    YY_BUFFER_STATE buffer;
    int lastToken, thisToken;
    int lastPos, thisPos;
    QString lastTokenData, thisTokenData;
};

/* Declared in function.h, implemented here in lexer.l since this is where
 * all the yy_*() functions and types are defined.
 */
Lexer::Lexer(const QString &expr) :
    m_private(new Private)
{
    const char *exprString = expr.latin1();

    yyCurTokenPos = 0;
    yyThisTokenLength = 0;

    m_private->buffer = yy_scan_string(exprString ? exprString : "");
    m_private->lastToken = -1;
    m_private->lastPos = -1;

    m_private->thisToken = yylex();
    m_private->thisTokenData = QString(yytext);

    if(yyCurTokenPos != 0)
    {
	kdError() << "yyCurTokenPos should be 0!!\n";
    }

    m_private->thisPos = yyCurTokenPos;
}

Lexer::~Lexer()
{
    yy_delete_buffer(m_private->buffer);
    delete m_private;
}

bool Lexer::hasNext() const
{
    return m_private->thisToken > 0;
}

int Lexer::nextType()
{
    m_private->lastTokenData = m_private->thisTokenData;
    m_private->lastPos = m_private->thisPos;
    m_private->lastToken = m_private->thisToken;

    m_private->thisToken = yylex();
    m_private->thisTokenData = QString(yytext);
    m_private->thisPos = yyCurTokenPos;

    return m_private->lastToken;
}

QString Lexer::tokenValue() const
{
    return m_private->lastTokenData;
}

int Lexer::tokenPos() const
{
    return m_private->lastPos;
}

/* Declared in function.h, implemented here in lexer.l since this is where
 * all the yy_*() functions and types are defined.
 */
Abakus::number_t parseString(const char *str)
{
    YY_BUFFER_STATE buffer = yy_scan_string(str);

    yyCurTokenPos = 0;
    yyThisTokenLength = 0;

    yyparse();
    yy_delete_buffer(buffer);

    if(Result::lastResult()->type() != Result::Value)
	return Abakus::number_t();

    return Result::lastResult()->result()->value();
}