|
1 /* |
|
2 * Copyright (c) 2007, 2013, 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 |
|
26 package javax.xml.bind; |
|
27 |
|
28 /** |
|
29 * Processes white space normalization. |
|
30 * |
|
31 * @since 1.0 |
|
32 */ |
|
33 abstract class WhiteSpaceProcessor { |
|
34 |
|
35 // benchmarking (see test/src/ReplaceTest.java in the CVS Attic) |
|
36 // showed that this code is slower than the current code. |
|
37 // |
|
38 // public static String replace(String text) { |
|
39 // final int len = text.length(); |
|
40 // StringBuffer result = new StringBuffer(len); |
|
41 // |
|
42 // for (int i = 0; i < len; i++) { |
|
43 // char ch = text.charAt(i); |
|
44 // if (isWhiteSpace(ch)) |
|
45 // result.append(' '); |
|
46 // else |
|
47 // result.append(ch); |
|
48 // } |
|
49 // |
|
50 // return result.toString(); |
|
51 // } |
|
52 |
|
53 public static String replace(String text) { |
|
54 return replace( (CharSequence)text ).toString(); |
|
55 } |
|
56 |
|
57 /** |
|
58 * @since 2.0 |
|
59 */ |
|
60 public static CharSequence replace(CharSequence text) { |
|
61 int i=text.length()-1; |
|
62 |
|
63 // look for the first whitespace char. |
|
64 while( i>=0 && !isWhiteSpaceExceptSpace(text.charAt(i)) ) |
|
65 i--; |
|
66 |
|
67 if( i<0 ) |
|
68 // no such whitespace. replace(text)==text. |
|
69 return text; |
|
70 |
|
71 // we now know that we need to modify the text. |
|
72 // allocate a char array to do it. |
|
73 StringBuilder buf = new StringBuilder(text); |
|
74 |
|
75 buf.setCharAt(i--,' '); |
|
76 for( ; i>=0; i-- ) |
|
77 if( isWhiteSpaceExceptSpace(buf.charAt(i))) |
|
78 buf.setCharAt(i,' '); |
|
79 |
|
80 return new String(buf); |
|
81 } |
|
82 |
|
83 /** |
|
84 * Equivalent of {@link String#trim()}. |
|
85 * @since 2.0 |
|
86 */ |
|
87 public static CharSequence trim(CharSequence text) { |
|
88 int len = text.length(); |
|
89 int start = 0; |
|
90 |
|
91 while( start<len && isWhiteSpace(text.charAt(start)) ) |
|
92 start++; |
|
93 |
|
94 int end = len-1; |
|
95 |
|
96 while( end>start && isWhiteSpace(text.charAt(end)) ) |
|
97 end--; |
|
98 |
|
99 if(start==0 && end==len-1) |
|
100 return text; // no change |
|
101 else |
|
102 return text.subSequence(start,end+1); |
|
103 } |
|
104 |
|
105 public static String collapse(String text) { |
|
106 return collapse( (CharSequence)text ).toString(); |
|
107 } |
|
108 |
|
109 /** |
|
110 * This is usually the biggest processing bottleneck. |
|
111 * |
|
112 * @since 2.0 |
|
113 */ |
|
114 public static CharSequence collapse(CharSequence text) { |
|
115 int len = text.length(); |
|
116 |
|
117 // most of the texts are already in the collapsed form. |
|
118 // so look for the first whitespace in the hope that we will |
|
119 // never see it. |
|
120 int s=0; |
|
121 while(s<len) { |
|
122 if(isWhiteSpace(text.charAt(s))) |
|
123 break; |
|
124 s++; |
|
125 } |
|
126 if(s==len) |
|
127 // the input happens to be already collapsed. |
|
128 return text; |
|
129 |
|
130 // we now know that the input contains spaces. |
|
131 // let's sit down and do the collapsing normally. |
|
132 |
|
133 StringBuilder result = new StringBuilder(len /*allocate enough size to avoid re-allocation*/ ); |
|
134 |
|
135 if(s!=0) { |
|
136 for( int i=0; i<s; i++ ) |
|
137 result.append(text.charAt(i)); |
|
138 result.append(' '); |
|
139 } |
|
140 |
|
141 boolean inStripMode = true; |
|
142 for (int i = s+1; i < len; i++) { |
|
143 char ch = text.charAt(i); |
|
144 boolean b = isWhiteSpace(ch); |
|
145 if (inStripMode && b) |
|
146 continue; // skip this character |
|
147 |
|
148 inStripMode = b; |
|
149 if (inStripMode) |
|
150 result.append(' '); |
|
151 else |
|
152 result.append(ch); |
|
153 } |
|
154 |
|
155 // remove trailing whitespaces |
|
156 len = result.length(); |
|
157 if (len > 0 && result.charAt(len - 1) == ' ') |
|
158 result.setLength(len - 1); |
|
159 // whitespaces are already collapsed, |
|
160 // so all we have to do is to remove the last one character |
|
161 // if it's a whitespace. |
|
162 |
|
163 return result; |
|
164 } |
|
165 |
|
166 /** |
|
167 * Returns true if the specified string is all whitespace. |
|
168 */ |
|
169 public static final boolean isWhiteSpace(CharSequence s) { |
|
170 for( int i=s.length()-1; i>=0; i-- ) |
|
171 if(!isWhiteSpace(s.charAt(i))) |
|
172 return false; |
|
173 return true; |
|
174 } |
|
175 |
|
176 /** returns true if the specified char is a white space character. */ |
|
177 public static final boolean isWhiteSpace(char ch) { |
|
178 // most of the characters are non-control characters. |
|
179 // so check that first to quickly return false for most of the cases. |
|
180 if( ch>0x20 ) return false; |
|
181 |
|
182 // other than we have to do four comparisons. |
|
183 return ch == 0x9 || ch == 0xA || ch == 0xD || ch == 0x20; |
|
184 } |
|
185 |
|
186 /** |
|
187 * Returns true if the specified char is a white space character |
|
188 * but not 0x20. |
|
189 */ |
|
190 protected static final boolean isWhiteSpaceExceptSpace(char ch) { |
|
191 // most of the characters are non-control characters. |
|
192 // so check that first to quickly return false for most of the cases. |
|
193 if( ch>=0x20 ) return false; |
|
194 |
|
195 // other than we have to do four comparisons. |
|
196 return ch == 0x9 || ch == 0xA || ch == 0xD; |
|
197 } |
|
198 } |