1/*
2 * Copyright (c) 2004, 2015, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation.  Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26package javax.xml.bind.annotation.adapters;
27
28
29
30/**
31 * Built-in {@link XmlAdapter} to handle {@code xs:token} and its derived types.
32 *
33 * <p>
34 * This adapter removes leading and trailing whitespaces, then truncate any
35 * sequence of tab, CR, LF, and SP by a single whitespace character ' '.
36 *
37 * @author Kohsuke Kawaguchi
38 * @since 1.6, JAXB 2.0
39 */
40public class CollapsedStringAdapter extends XmlAdapter<String,String> {
41    /**
42     * Removes leading and trailing whitespaces of the string
43     * given as the parameter, then truncate any
44     * sequence of tab, CR, LF, and SP by a single whitespace character ' '.
45     */
46    public String unmarshal(String text) {
47        if(text==null)  return null;        // be defensive
48
49        int len = text.length();
50
51        // most of the texts are already in the collapsed form.
52        // so look for the first whitespace in the hope that we will
53        // never see it.
54        int s=0;
55        while(s<len) {
56            if(isWhiteSpace(text.charAt(s)))
57                break;
58            s++;
59        }
60        if(s==len)
61            // the input happens to be already collapsed.
62            return text;
63
64        // we now know that the input contains spaces.
65        // let's sit down and do the collapsing normally.
66
67        StringBuilder result = new StringBuilder(len /*allocate enough size to avoid re-allocation*/ );
68
69        if(s!=0) {
70            for( int i=0; i<s; i++ )
71                result.append(text.charAt(i));
72            result.append(' ');
73        }
74
75        boolean inStripMode = true;
76        for (int i = s+1; i < len; i++) {
77            char ch = text.charAt(i);
78            boolean b = isWhiteSpace(ch);
79            if (inStripMode && b)
80                continue; // skip this character
81
82            inStripMode = b;
83            if (inStripMode)
84                result.append(' ');
85            else
86                result.append(ch);
87        }
88
89        // remove trailing whitespaces
90        len = result.length();
91        if (len > 0 && result.charAt(len - 1) == ' ')
92            result.setLength(len - 1);
93        // whitespaces are already collapsed,
94        // so all we have to do is to remove the last one character
95        // if it's a whitespace.
96
97        return result.toString();
98    }
99
100    /**
101     * No-op.
102     *
103     * Just return the same string given as the parameter.
104     */
105    public String marshal(String s) {
106        return s;
107    }
108
109
110    /** returns true if the specified char is a white space character. */
111    protected static boolean isWhiteSpace(char ch) {
112        // most of the characters are non-control characters.
113        // so check that first to quickly return false for most of the cases.
114        if( ch>0x20 )   return false;
115
116        // other than we have to do four comparisons.
117        return ch == 0x9 || ch == 0xA || ch == 0xD || ch == 0x20;
118    }
119}
120