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
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
|
/*
* $Id$
* ============================================================================
* The Apache Software License, Version 1.1
* ============================================================================
*
* Copyright (C) 1999-2003 The Apache Software Foundation. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without modifica-
* tion, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* 3. The end-user documentation included with the redistribution, if any, must
* include the following acknowledgment: "This product includes software
* developed by the Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowledgment may appear in the software itself, if
* and wherever such third-party acknowledgments normally appear.
*
* 4. The names "FOP" and "Apache Software Foundation" must not be used to
* endorse or promote products derived from this software without prior
* written permission. For written permission, please contact
* apache@apache.org.
*
* 5. Products derived from this software may not be called "Apache", nor may
* "Apache" appear in their name, without prior written permission of the
* Apache Software Foundation.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED WARRANTIES,
* INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
* FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
* APACHE SOFTWARE FOUNDATION OR ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT,
* INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLU-
* DING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS
* OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
* ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* ============================================================================
*
* This software consists of voluntary contributions made by many individuals
* on behalf of the Apache Software Foundation and was originally created by
* James Tauber <jtauber@jtauber.com>. For more information on the Apache
* Software Foundation, please see <http://www.apache.org/>.
*/
package org.apache.fop.util;
import org.apache.fop.fonts.Font;
/**
* This class provides utilities to distinguish various kinds of Unicode
* whitespace and to get character widths in a given FontState.
*/
public class CharUtilities {
/**
* Character code used to signal a character boundary in
* inline content, such as an inline with borders and padding
* or a nested block object.
*/
public static final char CODE_EOT = 0;
/**
* Character class: Unicode white space
*/
public static final int UCWHITESPACE = 0;
/**
* Character class: Line feed
*/
public static final int LINEFEED = 1;
/**
* Character class: Boundary between text runs
*/
public static final int EOT = 2;
/**
* Character class: non-whitespace
*/
public static final int NONWHITESPACE = 3;
/**
* Character class: XML whitespace
*/
public static final int XMLWHITESPACE = 4;
/**
* Utility class: Constructor prevents instantiating when subclassed.
*/
protected CharUtilities() {
throw new UnsupportedOperationException();
}
/**
* Return the appropriate CharClass constant for the type
* of the passed character.
* @param c character to inspect
* @return the determined character class
*/
public static int classOf(char c) {
if (c == CODE_EOT) { return EOT; }
if (c == '\n') { return LINEFEED; }
if (c == ' ' || c == '\r' || c == '\t') { return XMLWHITESPACE; }
if (isAnySpace(c)) { return UCWHITESPACE; }
return NONWHITESPACE;
}
/**
* Helper method for getting the width of a unicode char
* from the current fontstate.
* This also performs some guessing on widths on various
* versions of space that might not exists in the font.
* @param c character to inspect
* @param fs FontState to use
* @return the width of the character
*/
public static int getCharWidth(char c, Font fs) {
int width;
if ((c == '\n') || (c == '\r') || (c == '\t') || (c == '\u00A0')) {
width = getCharWidth(' ', fs);
} else {
width = fs.getWidth(fs.mapChar(c));
if (width <= 0) {
// Estimate the width of spaces not represented in
// the font
int em = fs.getWidth(fs.mapChar('m'));
int en = fs.getWidth(fs.mapChar('n'));
if (em <= 0) {
em = 500 * fs.getFontSize();
}
if (en <= 0) {
en = em - 10;
}
if (c == ' ') {
width = em;
}
if (c == '\u2000') {
width = en;
}
if (c == '\u2001') {
width = em;
}
if (c == '\u2002') {
width = em / 2;
}
if (c == '\u2003') {
width = fs.getFontSize();
}
if (c == '\u2004') {
width = em / 3;
}
if (c == '\u2005') {
width = em / 4;
}
if (c == '\u2006') {
width = em / 6;
}
if (c == '\u2007') {
width = getCharWidth(' ', fs);
}
if (c == '\u2008') {
width = getCharWidth('.', fs);
}
if (c == '\u2009') {
width = em / 5;
}
if (c == '\u200A') {
width = 5;
}
if (c == '\u200B') {
width = 100;
}
if (c == '\u202F') {
width = getCharWidth(' ', fs) / 2;
}
if (c == '\u3000') {
width = getCharWidth(' ', fs) * 2;
}
}
}
return width;
}
/**
* Calculates the word width.
*/
public static int getWordWidth(String word, Font fs) {
if (word == null)
return 0;
int wordLength = word.length();
int width = 0;
char[] characters = new char[wordLength];
word.getChars(0, wordLength, characters, 0);
for (int i = 0; i < wordLength; i++) {
width += getCharWidth(characters[i], fs);
}
return width;
}
/**
* Helper method to determine if the character is a
* space with normal behaviour. Normal behaviour means that
* it's not non-breaking.
* @param c character to inspect
* @return True if the character is a normal space
*/
public static boolean isSpace(char c) {
return (c == ' '
|| (c >= '\u2000' && c <= '\u200B'));
// c == '\u2000' // en quad
// c == '\u2001' // em quad
// c == '\u2002' // en space
// c == '\u2003' // em space
// c == '\u2004' // three-per-em space
// c == '\u2005' // four--per-em space
// c == '\u2006' // six-per-em space
// c == '\u2007' // figure space
// c == '\u2008' // punctuation space
// c == '\u2009' // thin space
// c == '\u200A' // hair space
// c == '\u200B' // zero width space
}
/**
* Method to determine if the character is a nonbreaking
* space.
* @param c character to check
* @return True if the character is a nbsp
*/
public static boolean isNBSP(char c) {
return
(c == '\u00A0' // no-break space
|| c == '\u202F' // narrow no-break space
|| c == '\u3000' // ideographic space
|| c == '\uFEFF'); // zero width no-break space
}
/**
* Determines if the character represents any kind of space.
* @param c character to check
* @return True if the character represents any kind of space
*/
public static boolean isAnySpace(char c) {
boolean ret = (isSpace(c) || isNBSP(c));
return ret;
}
}
|
