6
|
1 |
/*
|
|
2 |
* reserved comment block
|
|
3 |
* DO NOT REMOVE OR ALTER!
|
|
4 |
*/
|
|
5 |
/*
|
|
6 |
* Copyright 1999-2002,2004 The Apache Software Foundation.
|
|
7 |
*
|
|
8 |
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
9 |
* you may not use this file except in compliance with the License.
|
|
10 |
* You may obtain a copy of the License at
|
|
11 |
*
|
|
12 |
* http://www.apache.org/licenses/LICENSE-2.0
|
|
13 |
*
|
|
14 |
* Unless required by applicable law or agreed to in writing, software
|
|
15 |
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
16 |
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
17 |
* See the License for the specific language governing permissions and
|
|
18 |
* limitations under the License.
|
|
19 |
*/
|
|
20 |
|
|
21 |
|
|
22 |
// Aug 21, 2000:
|
|
23 |
// Added ability to omit DOCTYPE declaration.
|
|
24 |
// Reported by Lars Martin <lars@smb-tec.com>
|
|
25 |
// Aug 25, 2000:
|
|
26 |
// Added ability to omit comments.
|
|
27 |
// Contributed by Anupam Bagchi <abagchi@jtcsv.com>
|
|
28 |
|
|
29 |
|
|
30 |
package com.sun.org.apache.xml.internal.serialize;
|
|
31 |
|
|
32 |
|
|
33 |
import java.io.UnsupportedEncodingException;
|
|
34 |
|
|
35 |
import org.w3c.dom.Document;
|
|
36 |
import org.w3c.dom.DocumentType;
|
|
37 |
import org.w3c.dom.Node;
|
|
38 |
import org.w3c.dom.html.HTMLDocument;
|
|
39 |
|
|
40 |
|
|
41 |
/**
|
|
42 |
* Specifies an output format to control the serializer. Based on the
|
|
43 |
* XSLT specification for output format, plus additional parameters.
|
|
44 |
* Used to select the suitable serializer and determine how the
|
|
45 |
* document should be formatted on output.
|
|
46 |
* <p>
|
|
47 |
* The two interesting constructors are:
|
|
48 |
* <ul>
|
|
49 |
* <li>{@link #OutputFormat(String,String,boolean)} creates a format
|
|
50 |
* for the specified method (XML, HTML, Text, etc), encoding and indentation
|
|
51 |
* <li>{@link #OutputFormat(Document,String,boolean)} creates a format
|
|
52 |
* compatible with the document type (XML, HTML, Text, etc), encoding and
|
|
53 |
* indentation
|
|
54 |
* </ul>
|
|
55 |
*
|
|
56 |
*
|
|
57 |
* @author <a href="mailto:arkin@intalio.com">Assaf Arkin</a>
|
|
58 |
* <a href="mailto:visco@intalio.com">Keith Visco</a>
|
|
59 |
* @see Serializer
|
|
60 |
* @see Method
|
|
61 |
* @see LineSeparator
|
|
62 |
*/
|
|
63 |
public class OutputFormat
|
|
64 |
{
|
|
65 |
|
|
66 |
|
|
67 |
public static class DTD
|
|
68 |
{
|
|
69 |
|
|
70 |
/**
|
|
71 |
* Public identifier for HTML 4.01 (Strict) document type.
|
|
72 |
*/
|
|
73 |
public static final String HTMLPublicId = "-//W3C//DTD HTML 4.01//EN";
|
|
74 |
|
|
75 |
/**
|
|
76 |
* System identifier for HTML 4.01 (Strict) document type.
|
|
77 |
*/
|
|
78 |
public static final String HTMLSystemId =
|
|
79 |
"http://www.w3.org/TR/html4/strict.dtd";
|
|
80 |
|
|
81 |
/**
|
|
82 |
* Public identifier for XHTML 1.0 (Strict) document type.
|
|
83 |
*/
|
|
84 |
public static final String XHTMLPublicId =
|
|
85 |
"-//W3C//DTD XHTML 1.0 Strict//EN";
|
|
86 |
|
|
87 |
/**
|
|
88 |
* System identifier for XHTML 1.0 (Strict) document type.
|
|
89 |
*/
|
|
90 |
public static final String XHTMLSystemId =
|
|
91 |
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd";
|
|
92 |
|
|
93 |
}
|
|
94 |
|
|
95 |
|
|
96 |
public static class Defaults
|
|
97 |
{
|
|
98 |
|
|
99 |
/**
|
|
100 |
* If indentation is turned on, the default identation
|
|
101 |
* level is 4.
|
|
102 |
*
|
|
103 |
* @see #setIndenting(boolean)
|
|
104 |
*/
|
|
105 |
public static final int Indent = 4;
|
|
106 |
|
|
107 |
/**
|
|
108 |
* The default encoding for Web documents it UTF-8.
|
|
109 |
*
|
|
110 |
* @see #getEncoding()
|
|
111 |
*/
|
|
112 |
public static final String Encoding = "UTF-8";
|
|
113 |
|
|
114 |
/**
|
|
115 |
* The default line width at which to break long lines
|
|
116 |
* when identing. This is set to 72.
|
|
117 |
*/
|
|
118 |
public static final int LineWidth = 72;
|
|
119 |
|
|
120 |
}
|
|
121 |
|
|
122 |
|
|
123 |
/**
|
|
124 |
* Holds the output method specified for this document,
|
|
125 |
* or null if no method was specified.
|
|
126 |
*/
|
|
127 |
private String _method;
|
|
128 |
|
|
129 |
|
|
130 |
/**
|
|
131 |
* Specifies the version of the output method.
|
|
132 |
*/
|
|
133 |
private String _version;
|
|
134 |
|
|
135 |
|
|
136 |
/**
|
|
137 |
* The indentation level, or zero if no indentation
|
|
138 |
* was requested.
|
|
139 |
*/
|
|
140 |
private int _indent = 0;
|
|
141 |
|
|
142 |
|
|
143 |
/**
|
|
144 |
* The encoding to use, if an input stream is used.
|
|
145 |
* The default is always UTF-8.
|
|
146 |
*/
|
|
147 |
private String _encoding = Defaults.Encoding;
|
|
148 |
|
|
149 |
/**
|
|
150 |
* The EncodingInfo instance for _encoding.
|
|
151 |
*/
|
|
152 |
private EncodingInfo _encodingInfo = null;
|
|
153 |
|
|
154 |
// whether java names for encodings are permitted
|
|
155 |
private boolean _allowJavaNames = false;
|
|
156 |
|
|
157 |
/**
|
|
158 |
* The specified media type or null.
|
|
159 |
*/
|
|
160 |
private String _mediaType;
|
|
161 |
|
|
162 |
|
|
163 |
/**
|
|
164 |
* The specified document type system identifier, or null.
|
|
165 |
*/
|
|
166 |
private String _doctypeSystem;
|
|
167 |
|
|
168 |
|
|
169 |
/**
|
|
170 |
* The specified document type public identifier, or null.
|
|
171 |
*/
|
|
172 |
private String _doctypePublic;
|
|
173 |
|
|
174 |
|
|
175 |
/**
|
|
176 |
* Ture if the XML declaration should be ommited;
|
|
177 |
*/
|
|
178 |
private boolean _omitXmlDeclaration = false;
|
|
179 |
|
|
180 |
|
|
181 |
/**
|
|
182 |
* Ture if the DOCTYPE declaration should be ommited;
|
|
183 |
*/
|
|
184 |
private boolean _omitDoctype = false;
|
|
185 |
|
|
186 |
|
|
187 |
/**
|
|
188 |
* Ture if comments should be ommited;
|
|
189 |
*/
|
|
190 |
private boolean _omitComments = false;
|
|
191 |
|
|
192 |
|
|
193 |
/**
|
|
194 |
* Ture if the comments should be ommited;
|
|
195 |
*/
|
|
196 |
private boolean _stripComments = false;
|
|
197 |
|
|
198 |
|
|
199 |
/**
|
|
200 |
* True if the document type should be marked as standalone.
|
|
201 |
*/
|
|
202 |
private boolean _standalone = false;
|
|
203 |
|
|
204 |
|
|
205 |
/**
|
|
206 |
* List of element tag names whose text node children must
|
|
207 |
* be output as CDATA.
|
|
208 |
*/
|
|
209 |
private String[] _cdataElements;
|
|
210 |
|
|
211 |
|
|
212 |
/**
|
|
213 |
* List of element tag names whose text node children must
|
|
214 |
* be output unescaped.
|
|
215 |
*/
|
|
216 |
private String[] _nonEscapingElements;
|
|
217 |
|
|
218 |
|
|
219 |
/**
|
|
220 |
* The selected line separator.
|
|
221 |
*/
|
|
222 |
private String _lineSeparator = LineSeparator.Web;
|
|
223 |
|
|
224 |
|
|
225 |
/**
|
|
226 |
* The line width at which to wrap long lines when indenting.
|
|
227 |
*/
|
|
228 |
private int _lineWidth = Defaults.LineWidth;
|
|
229 |
|
|
230 |
|
|
231 |
/**
|
|
232 |
* True if spaces should be preserved in elements that do not
|
|
233 |
* specify otherwise, or specify the default behavior.
|
|
234 |
*/
|
|
235 |
private boolean _preserve = false;
|
|
236 |
/** If true, an empty string valued attribute is output as "". If false and
|
|
237 |
* and we are using the HTMLSerializer, then only the attribute name is
|
|
238 |
* serialized. Defaults to false for backwards compatibility.
|
|
239 |
*/
|
|
240 |
private boolean _preserveEmptyAttributes = false;
|
|
241 |
|
|
242 |
/**
|
|
243 |
* Constructs a new output format with the default values.
|
|
244 |
*/
|
|
245 |
public OutputFormat()
|
|
246 |
{
|
|
247 |
}
|
|
248 |
|
|
249 |
|
|
250 |
/**
|
|
251 |
* Constructs a new output format with the default values for
|
|
252 |
* the specified method and encoding. If <tt>indent</tt>
|
|
253 |
* is true, the document will be pretty printed with the default
|
|
254 |
* indentation level and default line wrapping.
|
|
255 |
*
|
|
256 |
* @param method The specified output method
|
|
257 |
* @param encoding The specified encoding
|
|
258 |
* @param indenting True for pretty printing
|
|
259 |
* @see #setEncoding
|
|
260 |
* @see #setIndenting
|
|
261 |
* @see #setMethod
|
|
262 |
*/
|
|
263 |
public OutputFormat( String method, String encoding, boolean indenting )
|
|
264 |
{
|
|
265 |
setMethod( method );
|
|
266 |
setEncoding( encoding );
|
|
267 |
setIndenting( indenting );
|
|
268 |
}
|
|
269 |
|
|
270 |
|
|
271 |
/**
|
|
272 |
* Constructs a new output format with the proper method,
|
|
273 |
* document type identifiers and media type for the specified
|
|
274 |
* document.
|
|
275 |
*
|
|
276 |
* @param doc The document to output
|
|
277 |
* @see #whichMethod
|
|
278 |
*/
|
|
279 |
public OutputFormat( Document doc )
|
|
280 |
{
|
|
281 |
setMethod( whichMethod( doc ) );
|
|
282 |
setDoctype( whichDoctypePublic( doc ), whichDoctypeSystem( doc ) );
|
|
283 |
setMediaType( whichMediaType( getMethod() ) );
|
|
284 |
}
|
|
285 |
|
|
286 |
|
|
287 |
/**
|
|
288 |
* Constructs a new output format with the proper method,
|
|
289 |
* document type identifiers and media type for the specified
|
|
290 |
* document, and with the specified encoding. If <tt>indent</tt>
|
|
291 |
* is true, the document will be pretty printed with the default
|
|
292 |
* indentation level and default line wrapping.
|
|
293 |
*
|
|
294 |
* @param doc The document to output
|
|
295 |
* @param encoding The specified encoding
|
|
296 |
* @param indenting True for pretty printing
|
|
297 |
* @see #setEncoding
|
|
298 |
* @see #setIndenting
|
|
299 |
* @see #whichMethod
|
|
300 |
*/
|
|
301 |
public OutputFormat( Document doc, String encoding, boolean indenting )
|
|
302 |
{
|
|
303 |
this( doc );
|
|
304 |
setEncoding( encoding );
|
|
305 |
setIndenting( indenting );
|
|
306 |
}
|
|
307 |
|
|
308 |
|
|
309 |
/**
|
|
310 |
* Returns the method specified for this output format.
|
|
311 |
* Typically the method will be <tt>xml</tt>, <tt>html</tt>
|
|
312 |
* or <tt>text</tt>, but it might be other values.
|
|
313 |
* If no method was specified, null will be returned
|
|
314 |
* and the most suitable method will be determined for
|
|
315 |
* the document by calling {@link #whichMethod}.
|
|
316 |
*
|
|
317 |
* @return The specified output method, or null
|
|
318 |
*/
|
|
319 |
public String getMethod()
|
|
320 |
{
|
|
321 |
return _method;
|
|
322 |
}
|
|
323 |
|
|
324 |
|
|
325 |
/**
|
|
326 |
* Sets the method for this output format.
|
|
327 |
*
|
|
328 |
* @see #getMethod
|
|
329 |
* @param method The output method, or null
|
|
330 |
*/
|
|
331 |
public void setMethod( String method )
|
|
332 |
{
|
|
333 |
_method = method;
|
|
334 |
}
|
|
335 |
|
|
336 |
|
|
337 |
/**
|
|
338 |
* Returns the version for this output method.
|
|
339 |
* If no version was specified, will return null
|
|
340 |
* and the default version number will be used.
|
|
341 |
* If the serializerr does not support that particular
|
|
342 |
* version, it should default to a supported version.
|
|
343 |
*
|
|
344 |
* @return The specified method version, or null
|
|
345 |
*/
|
|
346 |
public String getVersion()
|
|
347 |
{
|
|
348 |
return _version;
|
|
349 |
}
|
|
350 |
|
|
351 |
|
|
352 |
/**
|
|
353 |
* Sets the version for this output method.
|
|
354 |
* For XML the value would be "1.0", for HTML
|
|
355 |
* it would be "4.0".
|
|
356 |
*
|
|
357 |
* @see #getVersion
|
|
358 |
* @param version The output method version, or null
|
|
359 |
*/
|
|
360 |
public void setVersion( String version )
|
|
361 |
{
|
|
362 |
_version = version;
|
|
363 |
}
|
|
364 |
|
|
365 |
|
|
366 |
/**
|
|
367 |
* Returns the indentation specified. If no indentation
|
|
368 |
* was specified, zero is returned and the document
|
|
369 |
* should not be indented.
|
|
370 |
*
|
|
371 |
* @return The indentation or zero
|
|
372 |
* @see #setIndenting
|
|
373 |
*/
|
|
374 |
public int getIndent()
|
|
375 |
{
|
|
376 |
return _indent;
|
|
377 |
}
|
|
378 |
|
|
379 |
|
|
380 |
/**
|
|
381 |
* Returns true if indentation was specified.
|
|
382 |
*/
|
|
383 |
public boolean getIndenting()
|
|
384 |
{
|
|
385 |
return ( _indent > 0 );
|
|
386 |
}
|
|
387 |
|
|
388 |
|
|
389 |
/**
|
|
390 |
* Sets the indentation. The document will not be
|
|
391 |
* indented if the indentation is set to zero.
|
|
392 |
* Calling {@link #setIndenting} will reset this
|
|
393 |
* value to zero (off) or the default (on).
|
|
394 |
*
|
|
395 |
* @param indent The indentation, or zero
|
|
396 |
*/
|
|
397 |
public void setIndent( int indent )
|
|
398 |
{
|
|
399 |
if ( indent < 0 )
|
|
400 |
_indent = 0;
|
|
401 |
else
|
|
402 |
_indent = indent;
|
|
403 |
}
|
|
404 |
|
|
405 |
|
|
406 |
/**
|
|
407 |
* Sets the indentation on and off. When set on, the default
|
|
408 |
* indentation level and default line wrapping is used
|
|
409 |
* (see {@link Defaults#Indent} and {@link Defaults#LineWidth}).
|
|
410 |
* To specify a different indentation level or line wrapping,
|
|
411 |
* use {@link #setIndent} and {@link #setLineWidth}.
|
|
412 |
*
|
|
413 |
* @param on True if indentation should be on
|
|
414 |
*/
|
|
415 |
public void setIndenting( boolean on )
|
|
416 |
{
|
|
417 |
if ( on ) {
|
|
418 |
_indent = Defaults.Indent;
|
|
419 |
_lineWidth = Defaults.LineWidth;
|
|
420 |
} else {
|
|
421 |
_indent = 0;
|
|
422 |
_lineWidth = 0;
|
|
423 |
}
|
|
424 |
}
|
|
425 |
|
|
426 |
|
|
427 |
/**
|
|
428 |
* Returns the specified encoding. If no encoding was
|
|
429 |
* specified, the default is always "UTF-8".
|
|
430 |
*
|
|
431 |
* @return The encoding
|
|
432 |
*/
|
|
433 |
public String getEncoding()
|
|
434 |
{
|
|
435 |
return _encoding;
|
|
436 |
}
|
|
437 |
|
|
438 |
|
|
439 |
/**
|
|
440 |
* Sets the encoding for this output method. If no
|
|
441 |
* encoding was specified, the default is always "UTF-8".
|
|
442 |
* Make sure the encoding is compatible with the one
|
|
443 |
* used by the {@link java.io.Writer}.
|
|
444 |
*
|
|
445 |
* @see #getEncoding
|
|
446 |
* @param encoding The encoding, or null
|
|
447 |
*/
|
|
448 |
public void setEncoding( String encoding )
|
|
449 |
{
|
|
450 |
_encoding = encoding;
|
|
451 |
_encodingInfo = null;
|
|
452 |
}
|
|
453 |
|
|
454 |
/**
|
|
455 |
* Sets the encoding for this output method with an <code>EncodingInfo</code>
|
|
456 |
* instance.
|
|
457 |
*/
|
|
458 |
public void setEncoding(EncodingInfo encInfo) {
|
|
459 |
_encoding = encInfo.getIANAName();
|
|
460 |
_encodingInfo = encInfo;
|
|
461 |
}
|
|
462 |
|
|
463 |
/**
|
|
464 |
* Returns an <code>EncodingInfo<code> instance for the encoding.
|
|
465 |
*
|
|
466 |
* @see #setEncoding
|
|
467 |
*/
|
|
468 |
public EncodingInfo getEncodingInfo() throws UnsupportedEncodingException {
|
|
469 |
if (_encodingInfo == null)
|
|
470 |
_encodingInfo = Encodings.getEncodingInfo(_encoding, _allowJavaNames);
|
|
471 |
return _encodingInfo;
|
|
472 |
}
|
|
473 |
|
|
474 |
/**
|
|
475 |
* Sets whether java encoding names are permitted
|
|
476 |
*/
|
|
477 |
public void setAllowJavaNames (boolean allow) {
|
|
478 |
_allowJavaNames = allow;
|
|
479 |
}
|
|
480 |
|
|
481 |
/**
|
|
482 |
* Returns whether java encoding names are permitted
|
|
483 |
*/
|
|
484 |
public boolean setAllowJavaNames () {
|
|
485 |
return _allowJavaNames;
|
|
486 |
}
|
|
487 |
|
|
488 |
/**
|
|
489 |
* Returns the specified media type, or null.
|
|
490 |
* To determine the media type based on the
|
|
491 |
* document type, use {@link #whichMediaType}.
|
|
492 |
*
|
|
493 |
* @return The specified media type, or null
|
|
494 |
*/
|
|
495 |
public String getMediaType()
|
|
496 |
{
|
|
497 |
return _mediaType;
|
|
498 |
}
|
|
499 |
|
|
500 |
|
|
501 |
/**
|
|
502 |
* Sets the media type.
|
|
503 |
*
|
|
504 |
* @see #getMediaType
|
|
505 |
* @param mediaType The specified media type
|
|
506 |
*/
|
|
507 |
public void setMediaType( String mediaType )
|
|
508 |
{
|
|
509 |
_mediaType = mediaType;
|
|
510 |
}
|
|
511 |
|
|
512 |
|
|
513 |
/**
|
|
514 |
* Sets the document type public and system identifiers.
|
|
515 |
* Required only if the DOM Document or SAX events do not
|
|
516 |
* specify the document type, and one must be present in
|
|
517 |
* the serialized document. Any document type specified
|
|
518 |
* by the DOM Document or SAX events will override these
|
|
519 |
* values.
|
|
520 |
*
|
|
521 |
* @param publicId The public identifier, or null
|
|
522 |
* @param systemId The system identifier, or null
|
|
523 |
*/
|
|
524 |
public void setDoctype( String publicId, String systemId )
|
|
525 |
{
|
|
526 |
_doctypePublic = publicId;
|
|
527 |
_doctypeSystem = systemId;
|
|
528 |
}
|
|
529 |
|
|
530 |
|
|
531 |
/**
|
|
532 |
* Returns the specified document type public identifier,
|
|
533 |
* or null.
|
|
534 |
*/
|
|
535 |
public String getDoctypePublic()
|
|
536 |
{
|
|
537 |
return _doctypePublic;
|
|
538 |
}
|
|
539 |
|
|
540 |
|
|
541 |
/**
|
|
542 |
* Returns the specified document type system identifier,
|
|
543 |
* or null.
|
|
544 |
*/
|
|
545 |
public String getDoctypeSystem()
|
|
546 |
{
|
|
547 |
return _doctypeSystem;
|
|
548 |
}
|
|
549 |
|
|
550 |
|
|
551 |
/**
|
|
552 |
* Returns true if comments should be ommited.
|
|
553 |
* The default is false.
|
|
554 |
*/
|
|
555 |
public boolean getOmitComments()
|
|
556 |
{
|
|
557 |
return _omitComments;
|
|
558 |
}
|
|
559 |
|
|
560 |
|
|
561 |
/**
|
|
562 |
* Sets comment omitting on and off.
|
|
563 |
*
|
|
564 |
* @param omit True if comments should be ommited
|
|
565 |
*/
|
|
566 |
public void setOmitComments( boolean omit )
|
|
567 |
{
|
|
568 |
_omitComments = omit;
|
|
569 |
}
|
|
570 |
|
|
571 |
|
|
572 |
/**
|
|
573 |
* Returns true if the DOCTYPE declaration should
|
|
574 |
* be ommited. The default is false.
|
|
575 |
*/
|
|
576 |
public boolean getOmitDocumentType()
|
|
577 |
{
|
|
578 |
return _omitDoctype;
|
|
579 |
}
|
|
580 |
|
|
581 |
|
|
582 |
/**
|
|
583 |
* Sets DOCTYPE declaration omitting on and off.
|
|
584 |
*
|
|
585 |
* @param omit True if DOCTYPE declaration should be ommited
|
|
586 |
*/
|
|
587 |
public void setOmitDocumentType( boolean omit )
|
|
588 |
{
|
|
589 |
_omitDoctype = omit;
|
|
590 |
}
|
|
591 |
|
|
592 |
|
|
593 |
/**
|
|
594 |
* Returns true if the XML document declaration should
|
|
595 |
* be ommited. The default is false.
|
|
596 |
*/
|
|
597 |
public boolean getOmitXMLDeclaration()
|
|
598 |
{
|
|
599 |
return _omitXmlDeclaration;
|
|
600 |
}
|
|
601 |
|
|
602 |
|
|
603 |
/**
|
|
604 |
* Sets XML declaration omitting on and off.
|
|
605 |
*
|
|
606 |
* @param omit True if XML declaration should be ommited
|
|
607 |
*/
|
|
608 |
public void setOmitXMLDeclaration( boolean omit )
|
|
609 |
{
|
|
610 |
_omitXmlDeclaration = omit;
|
|
611 |
}
|
|
612 |
|
|
613 |
|
|
614 |
/**
|
|
615 |
* Returns true if the document type is standalone.
|
|
616 |
* The default is false.
|
|
617 |
*/
|
|
618 |
public boolean getStandalone()
|
|
619 |
{
|
|
620 |
return _standalone;
|
|
621 |
}
|
|
622 |
|
|
623 |
|
|
624 |
/**
|
|
625 |
* Sets document DTD standalone. The public and system
|
|
626 |
* identifiers must be null for the document to be
|
|
627 |
* serialized as standalone.
|
|
628 |
*
|
|
629 |
* @param standalone True if document DTD is standalone
|
|
630 |
*/
|
|
631 |
public void setStandalone( boolean standalone )
|
|
632 |
{
|
|
633 |
_standalone = standalone;
|
|
634 |
}
|
|
635 |
|
|
636 |
|
|
637 |
/**
|
|
638 |
* Returns a list of all the elements whose text node children
|
|
639 |
* should be output as CDATA, or null if no such elements were
|
|
640 |
* specified.
|
|
641 |
*/
|
|
642 |
public String[] getCDataElements()
|
|
643 |
{
|
|
644 |
return _cdataElements;
|
|
645 |
}
|
|
646 |
|
|
647 |
|
|
648 |
/**
|
|
649 |
* Returns true if the text node children of the given elements
|
|
650 |
* should be output as CDATA.
|
|
651 |
*
|
|
652 |
* @param tagName The element's tag name
|
|
653 |
* @return True if should serialize as CDATA
|
|
654 |
*/
|
|
655 |
public boolean isCDataElement( String tagName )
|
|
656 |
{
|
|
657 |
int i;
|
|
658 |
|
|
659 |
if ( _cdataElements == null )
|
|
660 |
return false;
|
|
661 |
for ( i = 0 ; i < _cdataElements.length ; ++i )
|
|
662 |
if ( _cdataElements[ i ].equals( tagName ) )
|
|
663 |
return true;
|
|
664 |
return false;
|
|
665 |
}
|
|
666 |
|
|
667 |
|
|
668 |
/**
|
|
669 |
* Sets the list of elements for which text node children
|
|
670 |
* should be output as CDATA.
|
|
671 |
*
|
|
672 |
* @param cdataElements List of CDATA element tag names
|
|
673 |
*/
|
|
674 |
public void setCDataElements( String[] cdataElements )
|
|
675 |
{
|
|
676 |
_cdataElements = cdataElements;
|
|
677 |
}
|
|
678 |
|
|
679 |
|
|
680 |
/**
|
|
681 |
* Returns a list of all the elements whose text node children
|
|
682 |
* should be output unescaped (no character references), or null
|
|
683 |
* if no such elements were specified.
|
|
684 |
*/
|
|
685 |
public String[] getNonEscapingElements()
|
|
686 |
{
|
|
687 |
return _nonEscapingElements;
|
|
688 |
}
|
|
689 |
|
|
690 |
|
|
691 |
/**
|
|
692 |
* Returns true if the text node children of the given elements
|
|
693 |
* should be output unescaped.
|
|
694 |
*
|
|
695 |
* @param tagName The element's tag name
|
|
696 |
* @return True if should serialize unescaped
|
|
697 |
*/
|
|
698 |
public boolean isNonEscapingElement( String tagName )
|
|
699 |
{
|
|
700 |
int i;
|
|
701 |
|
|
702 |
if ( _nonEscapingElements == null ) {
|
|
703 |
return false;
|
|
704 |
}
|
|
705 |
for ( i = 0 ; i < _nonEscapingElements.length ; ++i )
|
|
706 |
if ( _nonEscapingElements[ i ].equals( tagName ) )
|
|
707 |
return true;
|
|
708 |
return false;
|
|
709 |
}
|
|
710 |
|
|
711 |
|
|
712 |
/**
|
|
713 |
* Sets the list of elements for which text node children
|
|
714 |
* should be output unescaped (no character references).
|
|
715 |
*
|
|
716 |
* @param nonEscapingElements List of unescaped element tag names
|
|
717 |
*/
|
|
718 |
public void setNonEscapingElements( String[] nonEscapingElements )
|
|
719 |
{
|
|
720 |
_nonEscapingElements = nonEscapingElements;
|
|
721 |
}
|
|
722 |
|
|
723 |
|
|
724 |
|
|
725 |
/**
|
|
726 |
* Returns a specific line separator to use. The default is the
|
|
727 |
* Web line separator (<tt>\n</tt>). A string is returned to
|
|
728 |
* support double codes (CR + LF).
|
|
729 |
*
|
|
730 |
* @return The specified line separator
|
|
731 |
*/
|
|
732 |
public String getLineSeparator()
|
|
733 |
{
|
|
734 |
return _lineSeparator;
|
|
735 |
}
|
|
736 |
|
|
737 |
|
|
738 |
/**
|
|
739 |
* Sets the line separator. The default is the Web line separator
|
|
740 |
* (<tt>\n</tt>). The machine's line separator can be obtained
|
|
741 |
* from the system property <tt>line.separator</tt>, but is only
|
|
742 |
* useful if the document is edited on machines of the same type.
|
|
743 |
* For general documents, use the Web line separator.
|
|
744 |
*
|
|
745 |
* @param lineSeparator The specified line separator
|
|
746 |
*/
|
|
747 |
public void setLineSeparator( String lineSeparator )
|
|
748 |
{
|
|
749 |
if ( lineSeparator == null )
|
|
750 |
_lineSeparator = LineSeparator.Web;
|
|
751 |
else
|
|
752 |
_lineSeparator = lineSeparator;
|
|
753 |
}
|
|
754 |
|
|
755 |
|
|
756 |
/**
|
|
757 |
* Returns true if the default behavior for this format is to
|
|
758 |
* preserve spaces. All elements that do not specify otherwise
|
|
759 |
* or specify the default behavior will be formatted based on
|
|
760 |
* this rule. All elements that specify space preserving will
|
|
761 |
* always preserve space.
|
|
762 |
*/
|
|
763 |
public boolean getPreserveSpace()
|
|
764 |
{
|
|
765 |
return _preserve;
|
|
766 |
}
|
|
767 |
|
|
768 |
|
|
769 |
/**
|
|
770 |
* Sets space preserving as the default behavior. The default is
|
|
771 |
* space stripping and all elements that do not specify otherwise
|
|
772 |
* or use the default value will not preserve spaces.
|
|
773 |
*
|
|
774 |
* @param preserve True if spaces should be preserved
|
|
775 |
*/
|
|
776 |
public void setPreserveSpace( boolean preserve )
|
|
777 |
{
|
|
778 |
_preserve = preserve;
|
|
779 |
}
|
|
780 |
|
|
781 |
|
|
782 |
/**
|
|
783 |
* Return the selected line width for breaking up long lines.
|
|
784 |
* When indenting, and only when indenting, long lines will be
|
|
785 |
* broken at space boundaries based on this line width.
|
|
786 |
* No line wrapping occurs if this value is zero.
|
|
787 |
*/
|
|
788 |
public int getLineWidth()
|
|
789 |
{
|
|
790 |
return _lineWidth;
|
|
791 |
}
|
|
792 |
|
|
793 |
|
|
794 |
/**
|
|
795 |
* Sets the line width. If zero then no line wrapping will
|
|
796 |
* occur. Calling {@link #setIndenting} will reset this
|
|
797 |
* value to zero (off) or the default (on).
|
|
798 |
*
|
|
799 |
* @param lineWidth The line width to use, zero for default
|
|
800 |
* @see #getLineWidth
|
|
801 |
* @see #setIndenting
|
|
802 |
*/
|
|
803 |
public void setLineWidth( int lineWidth )
|
|
804 |
{
|
|
805 |
if ( lineWidth <= 0 )
|
|
806 |
_lineWidth = 0;
|
|
807 |
else
|
|
808 |
_lineWidth = lineWidth;
|
|
809 |
}
|
|
810 |
/**
|
|
811 |
* Returns the preserveEmptyAttribute flag. If flag is false, then'
|
|
812 |
* attributes with empty string values are output as the attribute
|
|
813 |
* name only (in HTML mode).
|
|
814 |
* @return preserve the preserve flag
|
|
815 |
*/ public boolean getPreserveEmptyAttributes () { return _preserveEmptyAttributes; } /**
|
|
816 |
* Sets the preserveEmptyAttribute flag. If flag is false, then'
|
|
817 |
* attributes with empty string values are output as the attribute
|
|
818 |
* name only (in HTML mode).
|
|
819 |
* @param preserve the preserve flag
|
|
820 |
*/ public void setPreserveEmptyAttributes (boolean preserve) { _preserveEmptyAttributes = preserve; }
|
|
821 |
|
|
822 |
/**
|
|
823 |
* Returns the last printable character based on the selected
|
|
824 |
* encoding. Control characters and non-printable characters
|
|
825 |
* are always printed as character references.
|
|
826 |
*/
|
|
827 |
public char getLastPrintable()
|
|
828 |
{
|
|
829 |
if ( getEncoding() != null &&
|
|
830 |
( getEncoding().equalsIgnoreCase( "ASCII" ) ) )
|
|
831 |
return 0xFF;
|
|
832 |
else
|
|
833 |
return 0xFFFF;
|
|
834 |
}
|
|
835 |
|
|
836 |
|
|
837 |
/**
|
|
838 |
* Determine the output method for the specified document.
|
|
839 |
* If the document is an instance of {@link org.w3c.dom.html.HTMLDocument}
|
|
840 |
* then the method is said to be <tt>html</tt>. If the root
|
|
841 |
* element is 'html' and all text nodes preceding the root
|
|
842 |
* element are all whitespace, then the method is said to be
|
|
843 |
* <tt>html</tt>. Otherwise the method is <tt>xml</tt>.
|
|
844 |
*
|
|
845 |
* @param doc The document to check
|
|
846 |
* @return The suitable method
|
|
847 |
*/
|
|
848 |
public static String whichMethod( Document doc )
|
|
849 |
{
|
|
850 |
Node node;
|
|
851 |
String value;
|
|
852 |
int i;
|
|
853 |
|
|
854 |
// If document is derived from HTMLDocument then the default
|
|
855 |
// method is html.
|
|
856 |
if ( doc instanceof HTMLDocument )
|
|
857 |
return Method.HTML;
|
|
858 |
|
|
859 |
// Lookup the root element and the text nodes preceding it.
|
|
860 |
// If root element is html and all text nodes contain whitespace
|
|
861 |
// only, the method is html.
|
|
862 |
|
|
863 |
// FIXME (SM) should we care about namespaces here?
|
|
864 |
|
|
865 |
node = doc.getFirstChild();
|
|
866 |
while (node != null) {
|
|
867 |
// If the root element is html, the method is html.
|
|
868 |
if ( node.getNodeType() == Node.ELEMENT_NODE ) {
|
|
869 |
if ( node.getNodeName().equalsIgnoreCase( "html" ) ) {
|
|
870 |
return Method.HTML;
|
|
871 |
} else if ( node.getNodeName().equalsIgnoreCase( "root" ) ) {
|
|
872 |
return Method.FOP;
|
|
873 |
} else {
|
|
874 |
return Method.XML;
|
|
875 |
}
|
|
876 |
} else if ( node.getNodeType() == Node.TEXT_NODE ) {
|
|
877 |
// If a text node preceding the root element contains
|
|
878 |
// only whitespace, this might be html, otherwise it's
|
|
879 |
// definitely xml.
|
|
880 |
value = node.getNodeValue();
|
|
881 |
for ( i = 0 ; i < value.length() ; ++i )
|
|
882 |
if ( value.charAt( i ) != 0x20 && value.charAt( i ) != 0x0A &&
|
|
883 |
value.charAt( i ) != 0x09 && value.charAt( i ) != 0x0D )
|
|
884 |
return Method.XML;
|
|
885 |
}
|
|
886 |
node = node.getNextSibling();
|
|
887 |
}
|
|
888 |
// Anything else, the method is xml.
|
|
889 |
return Method.XML;
|
|
890 |
}
|
|
891 |
|
|
892 |
|
|
893 |
/**
|
|
894 |
* Returns the document type public identifier
|
|
895 |
* specified for this document, or null.
|
|
896 |
*/
|
|
897 |
public static String whichDoctypePublic( Document doc )
|
|
898 |
{
|
|
899 |
DocumentType doctype;
|
|
900 |
|
|
901 |
/* DOM Level 2 was introduced into the code base*/
|
|
902 |
doctype = doc.getDoctype();
|
|
903 |
if ( doctype != null ) {
|
|
904 |
// Note on catch: DOM Level 1 does not specify this method
|
|
905 |
// and the code will throw a NoSuchMethodError
|
|
906 |
try {
|
|
907 |
return doctype.getPublicId();
|
|
908 |
} catch ( Error except ) { }
|
|
909 |
}
|
|
910 |
|
|
911 |
if ( doc instanceof HTMLDocument )
|
|
912 |
return DTD.XHTMLPublicId;
|
|
913 |
return null;
|
|
914 |
}
|
|
915 |
|
|
916 |
|
|
917 |
/**
|
|
918 |
* Returns the document type system identifier
|
|
919 |
* specified for this document, or null.
|
|
920 |
*/
|
|
921 |
public static String whichDoctypeSystem( Document doc )
|
|
922 |
{
|
|
923 |
DocumentType doctype;
|
|
924 |
|
|
925 |
/* DOM Level 2 was introduced into the code base*/
|
|
926 |
doctype = doc.getDoctype();
|
|
927 |
if ( doctype != null ) {
|
|
928 |
// Note on catch: DOM Level 1 does not specify this method
|
|
929 |
// and the code will throw a NoSuchMethodError
|
|
930 |
try {
|
|
931 |
return doctype.getSystemId();
|
|
932 |
} catch ( Error except ) { }
|
|
933 |
}
|
|
934 |
|
|
935 |
if ( doc instanceof HTMLDocument )
|
|
936 |
return DTD.XHTMLSystemId;
|
|
937 |
return null;
|
|
938 |
}
|
|
939 |
|
|
940 |
|
|
941 |
/**
|
|
942 |
* Returns the suitable media format for a document
|
|
943 |
* output with the specified method.
|
|
944 |
*/
|
|
945 |
public static String whichMediaType( String method )
|
|
946 |
{
|
|
947 |
if ( method.equalsIgnoreCase( Method.XML ) )
|
|
948 |
return "text/xml";
|
|
949 |
if ( method.equalsIgnoreCase( Method.HTML ) )
|
|
950 |
return "text/html";
|
|
951 |
if ( method.equalsIgnoreCase( Method.XHTML ) )
|
|
952 |
return "text/html";
|
|
953 |
if ( method.equalsIgnoreCase( Method.TEXT ) )
|
|
954 |
return "text/plain";
|
|
955 |
if ( method.equalsIgnoreCase( Method.FOP ) )
|
|
956 |
return "application/pdf";
|
|
957 |
return null;
|
|
958 |
}
|
|
959 |
|
|
960 |
|
|
961 |
}
|