aboutsummaryrefslogtreecommitdiff
path: root/src/jdk/nashorn/internal/runtime/QuotedStringTokenizer.java
blob: 3aae7fd23a5dfed7101b52251edbaeaf096d651d (plain)
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
/*
 * Copyright (c) 2010, 2013, Oracle and/or its affiliates. All rights reserved.
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
 *
 * This code is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 only, as
 * published by the Free Software Foundation.  Oracle designates this
 * particular file as subject to the "Classpath" exception as provided
 * by Oracle in the LICENSE file that accompanied this code.
 *
 * This code 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
 * version 2 for more details (a copy is included in the LICENSE file that
 * accompanied this code).
 *
 * You should have received a copy of the GNU General Public License version
 * 2 along with this work; if not, write to the Free Software Foundation,
 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
 *
 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
 * or visit www.oracle.com if you need additional information or have any
 * questions.
 */

package jdk.nashorn.internal.runtime;

import java.util.LinkedList;
import java.util.Stack;
import java.util.StringTokenizer;

/**
 * A string tokenizer that supports entries with quotes and nested quotes. If
 * the separators are quoted either by ' and ", or whatever quotes the user
 * supplies they will be ignored and considered part of another token
 */
public final class QuotedStringTokenizer {
    private final LinkedList<String> tokens;

    private final char quotes[];

    /**
     * Constructor
     *
     * @param str string to tokenize
     */
    public QuotedStringTokenizer(final String str) {
        this(str, " ");
    }

    /**
     * Create a quoted string tokenizer
     *
     * @param str
     *            a string to tokenize
     * @param delim
     *            delimiters between tokens
     *
     */
    public QuotedStringTokenizer(final String str, final String delim) {
        this(str, delim, new char[] { '"', '\'' });
    }

    /**
     * Create a quoted string tokenizer
     *
     * @param str
     *            a string to tokenize
     * @param delim
     *            delimiters between tokens
     * @param quotes
     *            all the characters that should be accepted as quotes, default
     *            is ' or "
     */
    private QuotedStringTokenizer(final String str, final String delim, final char[] quotes) {
        this.quotes = quotes;

        boolean delimIsWhitespace = true;
        for (int i = 0; i < delim.length(); i++) {
            if (!Character.isWhitespace(delim.charAt(i))) {
                delimIsWhitespace = false;
                break;
            }
        }

        final StringTokenizer st = new StringTokenizer(str, delim);
        tokens = new LinkedList<>();
        while (st.hasMoreTokens()) {
            String token = st.nextToken();

            while (unmatchedQuotesIn(token)) {
                if (!st.hasMoreTokens()) {
                    throw new IndexOutOfBoundsException(token);
                }
                token += (delimIsWhitespace ? " " : delim) + st.nextToken();
            }
            tokens.add(stripQuotes(token));
        }
    }

    /**
     * @return the number of tokens in the tokenizer
     */
    public int countTokens() {
        return tokens.size();
    }

    /**
     * @return true if there are tokens left
     */
    public boolean hasMoreTokens() {
        return countTokens() > 0;
    }

    /**
     * @return the next token in the tokenizer
     */
    public String nextToken() {
        return tokens.removeFirst();
    }

    private String stripQuotes(final String value0) {
        String value = value0.trim();
        for (final char q : quotes) {
            if (value.length() >= 2 && value.startsWith("" + q) && value.endsWith("" + q)) {
                // also go over the value and remove \q sequences. they are just
                // plain q now
                value = value.substring(1, value.length() - 1);
                value = value.replace("\\" + q, "" + q);
            }
        }
        return value;
    }

    private boolean unmatchedQuotesIn(final String str) {
        final Stack<Character> quoteStack = new Stack<>();
        for (int i = 0; i < str.length(); i++) {
            final char c = str.charAt(i);
            for (final char q : this.quotes) {
                if (c == q) {
                    if (quoteStack.isEmpty()) {
                        quoteStack.push(c);
                    } else {
                        final char top = quoteStack.pop();
                        if (top != c) {
                            quoteStack.push(top);
                            quoteStack.push(c);
                        }
                    }
                }
            }
        }

        return !quoteStack.isEmpty();
    }
}