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
|
/*
* 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.catalina.ssi;
/**
* Parses an expression string to return the individual tokens. This is patterned similar to the StreamTokenizer in the
* JDK but customized for SSI conditional expression parsing.
*/
public class ExpressionTokenizer {
public static final int TOKEN_STRING = 0;
public static final int TOKEN_AND = 1;
public static final int TOKEN_OR = 2;
public static final int TOKEN_NOT = 3;
public static final int TOKEN_EQ = 4;
public static final int TOKEN_NOT_EQ = 5;
public static final int TOKEN_RBRACE = 6;
public static final int TOKEN_LBRACE = 7;
public static final int TOKEN_GE = 8;
public static final int TOKEN_LE = 9;
public static final int TOKEN_GT = 10;
public static final int TOKEN_LT = 11;
public static final int TOKEN_END = 12;
private final char[] expr;
private String tokenVal = null;
private int index;
private final int length;
/**
* Creates a new parser for the specified expression.
*
* @param expr The expression
*/
public ExpressionTokenizer(String expr) {
this.expr = expr.trim().toCharArray();
this.length = this.expr.length;
}
/**
* @return <code>true</code> if there are more tokens.
*/
public boolean hasMoreTokens() {
return index < length;
}
/**
* @return the current index for error reporting purposes.
*/
public int getIndex() {
return index;
}
protected boolean isMetaChar(char c) {
return Character.isWhitespace(c) || c == '(' || c == ')' || c == '!' || c == '<' || c == '>' || c == '|' ||
c == '&' || c == '=';
}
/**
* @return the next token type and initializes any state variables accordingly.
*/
public int nextToken() {
// Skip any leading white space
while (index < length && Character.isWhitespace(expr[index])) {
index++;
}
// Clear the current token val
tokenVal = null;
if (index == length) {
return TOKEN_END; // End of string
}
int start = index;
char currentChar = expr[index];
char nextChar = (char) 0;
index++;
if (index < length) {
nextChar = expr[index];
}
// Check for a known token start
switch (currentChar) {
case '(':
return TOKEN_LBRACE;
case ')':
return TOKEN_RBRACE;
case '=':
return TOKEN_EQ;
case '!':
if (nextChar == '=') {
index++;
return TOKEN_NOT_EQ;
}
return TOKEN_NOT;
case '|':
if (nextChar == '|') {
index++;
return TOKEN_OR;
}
break;
case '&':
if (nextChar == '&') {
index++;
return TOKEN_AND;
}
break;
case '>':
if (nextChar == '=') {
index++;
return TOKEN_GE; // Greater than or equal
}
return TOKEN_GT; // Greater than
case '<':
if (nextChar == '=') {
index++;
return TOKEN_LE; // Less than or equal
}
return TOKEN_LT; // Less than
default:
// Otherwise it's a string
break;
}
int end;
if (currentChar == '"' || currentChar == '\'') {
// It's a quoted string and the end is the next unescaped quote
boolean escaped = false;
start++;
for (; index < length; index++) {
if (expr[index] == '\\' && !escaped) {
escaped = true;
continue;
}
if (expr[index] == currentChar && !escaped) {
break;
}
escaped = false;
}
end = index;
index++; // Skip the end quote
} else if (currentChar == '/') {
// It's a regular expression and the end is the next unescaped /
boolean escaped = false;
for (; index < length; index++) {
if (expr[index] == '\\' && !escaped) {
escaped = true;
continue;
}
if (expr[index] == currentChar && !escaped) {
break;
}
escaped = false;
}
end = ++index;
} else {
// End is the next whitespace character
for (; index < length; index++) {
if (isMetaChar(expr[index])) {
break;
}
}
end = index;
}
// Extract the string from the array
this.tokenVal = new String(expr, start, end - start);
return TOKEN_STRING;
}
/**
* @return the String value of the token if it was type TOKEN_STRING. Otherwise null is returned.
*/
public String getTokenValue() {
return tokenVal;
}
}
|
