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
|
%{
#include <ctype.h>
#include "SimpleParser.hpp"
struct SqlKeyword {
const char* m_name;
int m_value;
int m_state;
static const SqlKeyword* find(Ctx& ctx, const char* name, int state);
};
%}
%option c++
%option yyclass="SimpleParser"
%option stack
%option noyywrap
space [\040\t\n\r\f]
digit [0-9]
letter [A-Za-z_]
special ("$")
identifier ({letter}({letter}|{digit}|{special})*)
integer {digit}++
decimal (({digit}*\.{digit}+)|({digit}+\.{digit}*))
real ((({digit}*\.{digit}+)|({digit}+\.{digit}*)|({digit}+))([Ee][-+]?{digit}+))
%s StateEval
%s StateType
%s StatePhys
%x StateString
%x StateQuoted
%%
{space} {
}
{identifier} {
const SqlKeyword* key = SqlKeyword::find(m_ctx, (char*)yytext, YYSTATE);
if (key != 0)
return key->m_value;
for (unsigned char* a = (unsigned char*)yytext; *a != 0; a++) {
if (islower(*a))
*a = toupper(*a);
}
m_yylval.m_string = strcpy(new char[yyleng + 1], yytext);
return T_IDENTIFIER;
}
{integer} {
m_yylval.m_string = strcpy(new char[yyleng + 1], yytext);
return T_LINTEGER;
}
{decimal} {
m_yylval.m_string = strcpy(new char[yyleng + 1], yytext);
return T_LDECIMAL;
}
{real} {
m_yylval.m_string = strcpy(new char[yyleng + 1], yytext);
return T_LREAL;
}
"--".* {
}
"/*" {
int c = 0, d;
while (1) {
d = c;
if ((c = yyinput()) == EOF) {
parseError("unterminated comment");
yyterminate();
}
if (d == '*' && c == '/')
break;
}
}
<StateEval>{
"+" return T_PLUS;
"-" return T_MINUS;
"*" return T_TIMES;
"/" return T_DIVIDE;
"=" return T_EQ;
"!=" return T_NOTEQ;
"^=" return T_NOTEQ;
"<>" return T_NOTEQ;
"<" return T_LT;
"<=" return T_LTEQ;
">" return T_GT;
">=" return T_GTEQ;
"?" m_paramNumber++; return T_QUES;
}
"." return T_PERIOD;
"," return T_COMMA;
"(" return T_PARENLEFT;
")" return T_PARENRIGHT;
"*" return T_ASTERISK;
"=" return T_ASSIGN;
"'" {
pushState(StateString);
m_string.assign("");
}
<StateString>{
[^']* {
m_string.append(yytext);
}
"''" {
m_string.append("'");
}
"'" {
m_yylval.m_string = strcpy(new char[m_string.length() + 1], m_string.c_str());
popState();
return T_STRING;
}
}
\" {
pushState(StateQuoted);
m_string.assign("");
}
<StateQuoted>{
[^"]* {
m_string.append(yytext);
}
\\\" {
m_string.append("\"");
}
\" {
m_yylval.m_string = strcpy(new char[m_string.length() + 1], m_string.c_str());
popState();
return T_IDENTIFIER;
}
}
%%
// scan states
int SimpleParser_stateEval = StateEval;
int SimpleParser_stateType = StateType;
int SimpleParser_statePhys = StatePhys;
// keep sorted
static const SqlKeyword sqlKeyword[] = {
{ "AND", T_AND, -1 },
{ "ASC", T_ASC, -1 },
{ "AUTO_INCREMENT", T_AUTO_INCREMENT, -1 },
{ "BIGINT", T_BIGINT, StateType },
{ "BINARY", T_BINARY, StateType },
{ "BLOB", T_BLOB, StateType },
{ "BY", T_BY, -1 },
{ "CHAR", T_CHAR, StateType },
{ "CONSTRAINT", T_CONSTRAINT, -1 },
{ "CREATE", T_CREATE, -1 },
{ "DATETIME", T_DATETIME, StateType },
{ "DEFAULT", T_DEFAULT, -1 },
{ "DELETE", T_DELETE, -1 },
{ "DESC", T_DESC, -1 },
{ "DISTINCT", T_DISTINCT, -1 },
{ "DOUBLE", T_DOUBLE, StateType },
{ "DROP", T_DROP, -1 },
{ "FLOAT", T_FLOAT, StateType },
{ "FOREIGN", T_FOREIGN, -1 },
{ "FROM", T_FROM, -1 },
{ "GROUP", T_GROUP, -1 },
{ "HASH", T_HASH, -1 },
{ "HAVING", T_HAVING, -1 },
{ "IN", T_IN, -1 },
{ "INDEX", T_INDEX, -1 },
{ "INSERT", T_INSERT, -1 },
{ "INT", T_INT, StateType },
{ "INTEGER", T_INTEGER, StateType },
{ "INTO", T_INTO, -1 },
{ "IS", T_IS, -1 },
{ "KEY", T_KEY, -1 },
{ "LARGE", T_LARGE, StatePhys },
{ "LIKE", T_LIKE, -1 },
{ "LIMIT", T_LIMIT, -1 },
{ "LOGGING", T_LOGGING, StatePhys },
{ "LONGBLOB", T_LONGBLOB, StateType },
{ "MEDIUM", T_MEDIUM, StatePhys },
{ "NOLOGGING", T_NOLOGGING, StatePhys },
{ "NOT", T_NOT, -1 },
{ "NULL", T_NULL, -1 },
{ "OFFSET", T_OFFSET, -1 },
{ "ON", T_ON, -1 },
{ "OR", T_OR, -1 },
{ "ORDER", T_ORDER, -1 },
{ "PRECISION", T_PRECISION, StateType },
{ "PRIMARY", T_PRIMARY, -1 },
{ "REAL", T_REAL, StateType },
{ "REFERENCES", T_REFERENCES, -1 },
{ "ROWNUM", T_ROWNUM, -1 },
{ "SELECT", T_SELECT, -1 },
{ "SET", T_SET, -1 },
{ "SINGLE", T_SINGLE, StatePhys },
{ "SMALL", T_SMALL, StatePhys },
{ "SMALLINT", T_SMALLINT, StateType },
{ "STORAGE", T_STORAGE, StatePhys },
{ "SYSDATE", T_SYSDATE, -1 },
{ "TABLE", T_TABLE, -1 },
{ "UNIQUE", T_UNIQUE, -1 },
{ "UNSIGNED", T_UNSIGNED, -1 },
{ "UPDATE", T_UPDATE, -1 },
{ "VALUES", T_VALUES, -1 },
{ "VARBINARY", T_VARBINARY, StateType },
{ "VARCHAR", T_VARCHAR, StateType },
{ "WHERE", T_WHERE, -1 },
{ "WRITE", T_WRITE, -1 }
};
static const unsigned sqlKeywordCount = sizeof(sqlKeyword) / sizeof(sqlKeyword[0]);
const SqlKeyword*
SqlKeyword::find(Ctx& ctx, const char* name, int state)
{
ctx_log4(("find keyword '%s' lex state = %d", name, state));
const unsigned maxlen = 99;
char buf[maxlen + 1];
char* a = buf;
const char* b = name;
while (*b != 0) {
if (a >= buf + maxlen) // will not be found
break;
char c = *b++;
if ('a' <= c && c <= 'z') // locale independent
c -= 'a' - 'A';
*a++ = c;
}
*a = 0;
for (unsigned i = 0; i < sqlKeywordCount; i++) {
const SqlKeyword* key = &sqlKeyword[i];
if (strcmp(key->m_name, buf) == 0) {
if (key->m_state != -1 && key->m_state != state)
return 0;
return key;
}
}
return 0;
}
/* vim: set filetype=lex: */
|
