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
|
/*
* Copyright (c) 2014, 2015, Oracle and/or its affiliates. All rights reserved.
*
* 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; version 2 of the
* License.
*
* 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 St, Fifth Floor, Boston, MA
* 02110-1301 USA
*/
#include <sstream>
#include <algorithm>
#include <string>
#include <set>
#include <antlr3.h>
#include "MySQLLexer.h" // The generated lexer.
#include "MySQLSimpleParser.h" // The generated parser.
#include "base/log.h"
#include "mysql-syntax-check.h"
DEFAULT_LOG_DOMAIN("MySQL parsing")
//--------------------------------------------------------------------------------------------------
class MySQLSyntaxChecker::Private
{
public:
const char *_text;
size_t _text_length;
int _input_encoding;
RecognitionContext _context;
pANTLR3_INPUT_STREAM _input;
pMySQLLexer _lexer;
pANTLR3_COMMON_TOKEN_STREAM _tokens;
pMySQLSimpleParser _parser;
};
//--------------------------------------------------------------------------------------------------
MySQLSyntaxChecker::MySQLSyntaxChecker(long server_version, const std::string &sql_mode,
const std::set<std::string> &charsets)
: MySQLRecognitionBase(charsets)
{
d = new Private();
d->_context.version = server_version;
d->_context.payload = this;
set_sql_mode(sql_mode);
d->_input = NULL;
d->_lexer = NULL;
d->_tokens = NULL;
d->_parser = NULL;
}
//--------------------------------------------------------------------------------------------------
MySQLSyntaxChecker::~MySQLSyntaxChecker()
{
if (d->_parser != NULL)
d->_parser->free(d->_parser);
if (d->_tokens != NULL)
d->_tokens ->free(d->_tokens);
if (d->_lexer != NULL)
d->_lexer->free(d->_lexer);
if (d->_input != NULL)
d->_input->close(d->_input);
delete d;
}
//--------------------------------------------------------------------------------------------------
/**
* Starts parsing with new input but keeps everything else in place.
*
* @param text The text to parse.
* @param length The length of the text.
* @param is_utf8 True if text is utf-8 encoded. If false we assume ASCII encoding.
* @param parse_unit used to restrict parsing to a particular query type.
* Note: only a few types are supported, everything else is just parsed as a query.
*/
void MySQLSyntaxChecker::parse(const char *text, size_t length, bool is_utf8, MySQLQueryType parse_unit)
{
// If the text is not using utf-8 (which it should) then we interpret as 8bit encoding
// (everything requiring only one byte per char as Latin1, ASCII and similar).
// TODO: handle the (bad) case that the input encoding changes between parse runs.
d->_input_encoding = is_utf8 ? ANTLR3_ENC_UTF8 : ANTLR3_ENC_8BIT;
d->_text = text;
d->_text_length = length;
reset();
if (d->_input == NULL)
{
// Input and depending structures are only created once. If there's no input stream yet we need the full setup.
d->_input = antlr3StringStreamNew((pANTLR3_UINT8)d->_text, d->_input_encoding, (ANTLR3_UINT32)d->_text_length, (pANTLR3_UINT8)"");
d->_input->setUcaseLA(d->_input, ANTLR3_TRUE); // Make input case-insensitive. String literals must all be upper case in the grammar!
d->_lexer = MySQLLexerNew(d->_input);
d->_lexer->pLexer->rec->state->userp = &d->_context;
d->_tokens = antlr3CommonTokenStreamSourceNew(ANTLR3_SIZE_HINT, TOKENSOURCE(d->_lexer));
d->_parser = MySQLSimpleParserNew(d->_tokens);
d->_parser->pParser->rec->state->userp = &d->_context;
}
else
{
d->_input->reuse(d->_input, (pANTLR3_UINT8)d->_text, (ANTLR3_UINT32)d->_text_length, (pANTLR3_UINT8)"");
d->_tokens->reset(d->_tokens);
d->_lexer->reset(d->_lexer);
d->_parser->reset(d->_parser);
}
switch (parse_unit)
{
case QtCreateTrigger:
d->_parser->create_trigger(d->_parser);
break;
case QtCreateView:
d->_parser->create_view(d->_parser);
break;
case QtCreateRoutine:
d->_parser->create_routine(d->_parser);
break;
case QtCreateEvent:
d->_parser->create_trigger(d->_parser);
default:
d->_parser->query(d->_parser);
}
}
//--------------------------------------------------------------------------------------------------
void MySQLSyntaxChecker::set_sql_mode(const std::string &new_mode)
{
MySQLRecognitionBase::set_sql_mode(new_mode);
d->_context.sqlMode = sql_mode();
}
//--------------------------------------------------------------------------------------------------
void MySQLSyntaxChecker::set_server_version(long new_version)
{
d->_context.version = new_version;
}
//--------------------------------------------------------------------------------------------------
long MySQLSyntaxChecker::server_version()
{
return d->_context.version;
}
//--------------------------------------------------------------------------------------------------
std::string MySQLSyntaxChecker::text()
{
return std::string(d->_text, d->_text_length);
}
//--------------------------------------------------------------------------------------------------
const char* MySQLSyntaxChecker::lineStart()
{
return d->_text;
}
//--------------------------------------------------------------------------------------------------
|
