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
|
/**
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.spark.sql.catalyst.parser;
import java.nio.charset.StandardCharsets;
/**
* A couple of utility methods that help with parsing ASTs.
*
* The 'unescapeSQLString' method in this class was take from the SemanticAnalyzer in Hive:
* ql/src/java/org/apache/hadoop/hive/ql/parse/BaseSemanticAnalyzer.java
*/
public final class ParseUtils {
private ParseUtils() {
super();
}
private static final int[] multiplier = new int[] {1000, 100, 10, 1};
@SuppressWarnings("nls")
public static String unescapeSQLString(String b) {
Character enclosure = null;
// Some of the strings can be passed in as unicode. For example, the
// delimiter can be passed in as \002 - So, we first check if the
// string is a unicode number, else go back to the old behavior
StringBuilder sb = new StringBuilder(b.length());
for (int i = 0; i < b.length(); i++) {
char currentChar = b.charAt(i);
if (enclosure == null) {
if (currentChar == '\'' || b.charAt(i) == '\"') {
enclosure = currentChar;
}
// ignore all other chars outside the enclosure
continue;
}
if (enclosure.equals(currentChar)) {
enclosure = null;
continue;
}
if (currentChar == '\\' && (i + 6 < b.length()) && b.charAt(i + 1) == 'u') {
int code = 0;
int base = i + 2;
for (int j = 0; j < 4; j++) {
int digit = Character.digit(b.charAt(j + base), 16);
code += digit * multiplier[j];
}
sb.append((char)code);
i += 5;
continue;
}
if (currentChar == '\\' && (i + 4 < b.length())) {
char i1 = b.charAt(i + 1);
char i2 = b.charAt(i + 2);
char i3 = b.charAt(i + 3);
if ((i1 >= '0' && i1 <= '1') && (i2 >= '0' && i2 <= '7')
&& (i3 >= '0' && i3 <= '7')) {
byte bVal = (byte) ((i3 - '0') + ((i2 - '0') * 8) + ((i1 - '0') * 8 * 8));
byte[] bValArr = new byte[1];
bValArr[0] = bVal;
String tmp = new String(bValArr, StandardCharsets.UTF_8);
sb.append(tmp);
i += 3;
continue;
}
}
if (currentChar == '\\' && (i + 2 < b.length())) {
char n = b.charAt(i + 1);
switch (n) {
case '0':
sb.append("\0");
break;
case '\'':
sb.append("'");
break;
case '"':
sb.append("\"");
break;
case 'b':
sb.append("\b");
break;
case 'n':
sb.append("\n");
break;
case 'r':
sb.append("\r");
break;
case 't':
sb.append("\t");
break;
case 'Z':
sb.append("\u001A");
break;
case '\\':
sb.append("\\");
break;
// The following 2 lines are exactly what MySQL does TODO: why do we do this?
case '%':
sb.append("\\%");
break;
case '_':
sb.append("\\_");
break;
default:
sb.append(n);
}
i++;
} else {
sb.append(currentChar);
}
}
return sb.toString();
}
}
|
