EscapeTokenizer.java
6.46 KB
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) 2002, 2014, Oracle and/or its affiliates. All rights reserved.
The MySQL Connector/J is licensed under the terms of the GPLv2
<http://www.gnu.org/licenses/old-licenses/gpl-2.0.html>, like most MySQL Connectors.
There are special exceptions to the terms and conditions of the GPLv2 as it is applied to
this software, see the FOSS License Exception
<http://www.mysql.com/about/legal/licensing/foss-exception.html>.
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
*/
package com.mysql.jdbc;
/**
* EscapeTokenizer breaks up an SQL statement into SQL and escape code parts.
*/
public class EscapeTokenizer {
private static final char CHR_ESCAPE = '\\';
private static final char CHR_SGL_QUOTE = '\'';
private static final char CHR_DBL_QUOTE = '"';
private static final char CHR_LF = '\n';
private static final char CHR_CR = '\r';
private static final char CHR_COMMENT = '-';
private static final char CHR_BEGIN_TOKEN = '{';
private static final char CHR_END_TOKEN = '}';
private static final char CHR_VARIABLE = '@';
private String source = null;
private int sourceLength = 0;
private int pos = 0;
private boolean emittingEscapeCode = false;
private boolean sawVariableUse = false;
private int bracesLevel = 0;
private boolean inQuotes = false;
private char quoteChar = 0;
/**
* Creates a new EscapeTokenizer object.
*
* @param source
* the string to tokenize
*/
public EscapeTokenizer(String source) {
this.source = source;
this.sourceLength = source.length();
this.pos = 0;
}
/**
* Does this tokenizer have more tokens available?
*
* @return if this tokenizer has more tokens available
*/
public synchronized boolean hasMoreTokens() {
return (this.pos < this.sourceLength);
}
/**
* Returns the next token
*
* @return the next token.
*/
public synchronized String nextToken() {
StringBuilder tokenBuf = new StringBuilder();
boolean backslashEscape = false;
if (this.emittingEscapeCode) {
// Previous token ended at the beginning of an escape code, so this token must start with '{'
tokenBuf.append("{");
this.emittingEscapeCode = false;
}
for (; this.pos < this.sourceLength; this.pos++) {
char c = this.source.charAt(this.pos);
// process escape char: (\)
if (c == CHR_ESCAPE) {
tokenBuf.append(c);
backslashEscape = !backslashEscape;
continue;
}
// process quotes: ('|")
if ((c == CHR_SGL_QUOTE || c == CHR_DBL_QUOTE) && !backslashEscape) {
tokenBuf.append(c);
if (this.inQuotes) {
if (c == this.quoteChar) {
// look ahead for doubled quote
if ((this.pos + 1 < this.sourceLength) && (this.source.charAt(this.pos + 1) == this.quoteChar)) {
tokenBuf.append(c);
this.pos++; // consume following char '\'' or '"'
} else {
this.inQuotes = false;
}
}
} else {
this.inQuotes = true;
this.quoteChar = c;
}
continue;
}
// process new line: (\n|\r)
if ((c == CHR_LF) || (c == CHR_CR)) {
tokenBuf.append(c);
backslashEscape = false;
continue;
}
if (!this.inQuotes && !backslashEscape) {
// process comments: (--)
if (c == CHR_COMMENT) {
tokenBuf.append(c);
// look ahead for double hyphen
if ((this.pos + 1 < this.sourceLength) && (this.source.charAt(this.pos + 1) == CHR_COMMENT)) {
// consume following chars until new line or end of string
while (++this.pos < this.sourceLength && c != CHR_LF && c != CHR_CR) {
c = this.source.charAt(this.pos);
tokenBuf.append(c);
}
this.pos--;
}
continue;
}
// process begin token: ({)
if (c == CHR_BEGIN_TOKEN) {
this.bracesLevel++;
if (this.bracesLevel == 1) {
this.emittingEscapeCode = true;
this.pos++; // consume char '{' before returning
return tokenBuf.toString();
}
tokenBuf.append(c);
continue;
}
// process end token: (})
if (c == CHR_END_TOKEN) {
tokenBuf.append(c);
this.bracesLevel--;
if (this.bracesLevel == 0) {
this.pos++; // consume char '}' before returning
return tokenBuf.toString();
}
continue;
}
// detect variable usage: (@)
if (c == CHR_VARIABLE) {
this.sawVariableUse = true;
}
}
tokenBuf.append(c);
backslashEscape = false;
}
return tokenBuf.toString();
}
/**
* Returns true if a variable reference was found. Note that this information isn't accurate until finishing to
* process all tokens from source String. It also can't be used as per token basis.
*
* @return true if a variable reference was found.
*/
boolean sawVariableUse() {
return this.sawVariableUse;
}
}