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
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
|
/* This file is part of the KDE project
Copyright (C) 2004 David Faure <faure@kde.org>
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Library General Public
License as published by the Free Software Foundation; either
version 2 of the License, or (at your option) any later version.
This library 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
Library General Public License for more details.
You should have received a copy of the GNU Library General Public License
along with this library; see the file COPYING.LIB. If not, write to
the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
* Boston, MA 02110-1301, USA.
*/
#include "KoXmlWriter.h"
#include <kglobal.h> // kMin
#include <kdebug.h>
#include <tqiodevice.h>
#include <float.h>
static const int s_indentBufferLength = 100;
KoXmlWriter::KoXmlWriter( TQIODevice* dev, int indentLevel )
: m_dev( dev ), m_baseIndentLevel( indentLevel )
{
init();
}
void KoXmlWriter::init()
{
m_indentBuffer = new char[ s_indentBufferLength ];
memset( m_indentBuffer, ' ', s_indentBufferLength );
*m_indentBuffer = '\n'; // write newline before indentation, in one go
m_escapeBuffer = new char[s_escapeBufferLen];
}
KoXmlWriter::~KoXmlWriter()
{
delete[] m_indentBuffer;
delete[] m_escapeBuffer;
}
void KoXmlWriter::startDocument( const char* rootElemName, const char* publicId, const char* systemId )
{
Q_ASSERT( m_tags.isEmpty() );
writeCString( "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" );
// There isn't much point in a doctype if there's no DTD to refer to
// (I'm told that files that are validated by a RelaxNG schema cannot refer to the schema)
if ( publicId ) {
writeCString( "<!DOCTYPE " );
writeCString( rootElemName );
writeCString( " PUBLIC \"" );
writeCString( publicId );
writeCString( "\" \"" );
writeCString( systemId );
writeCString( "\"" );
writeCString( ">\n" );
}
}
void KoXmlWriter::endDocument()
{
// just to do exactly like TQDom does (newline at end of file).
writeChar( '\n' );
Q_ASSERT( m_tags.isEmpty() );
}
// returns the value of indentInside of the parent
bool KoXmlWriter::prepareForChild()
{
if ( !m_tags.isEmpty() ) {
Tag& parent = m_tags.top();
if ( !parent.hasChildren ) {
closeStartElement( parent );
parent.hasChildren = true;
parent.lastChildIsText = false;
}
if ( parent.indentInside ) {
writeIndent();
}
return parent.indentInside;
}
return true;
}
void KoXmlWriter::prepareForTextNode()
{
Tag& parent = m_tags.top();
if ( !parent.hasChildren ) {
closeStartElement( parent );
parent.hasChildren = true;
parent.lastChildIsText = true;
}
}
void KoXmlWriter::startElement( const char* tagName, bool indentInside )
{
Q_ASSERT( tagName != 0 );
// Tell parent that it has children
bool parentIndent = prepareForChild();
m_tags.push( Tag( tagName, parentIndent && indentInside ) );
writeChar( '<' );
writeCString( tagName );
//kdDebug() << k_funcinfo << tagName << endl;
}
void KoXmlWriter::addCompleteElement( const char* cstr )
{
prepareForChild();
writeCString( cstr );
}
void KoXmlWriter::addCompleteElement( TQIODevice* indev )
{
prepareForChild();
bool openOk = indev->open( IO_ReadOnly );
Q_ASSERT( openOk );
if ( !openOk )
return;
static const int MAX_CHUNK_SIZE = 8*1024; // 8 KB
TQByteArray buffer(MAX_CHUNK_SIZE);
while ( !indev->atEnd() ) {
TQ_LONG len = indev->readBlock( buffer.data(), buffer.size() );
if ( len <= 0 ) // e.g. on error
break;
m_dev->writeBlock( buffer.data(), len );
}
}
void KoXmlWriter::endElement()
{
if ( m_tags.isEmpty() )
kdWarning() << "Ouch, endElement() was called more times than startElement(). "
"The generated XML will be invalid! "
"Please report this bug (by saving the document to another format...)" << endl;
Tag tag = m_tags.pop();
//kdDebug() << k_funcinfo << " tagName=" << tag.tagName << " hasChildren=" << tag.hasChildren << endl;
if ( !tag.hasChildren ) {
writeCString( "/>" );
}
else {
if ( tag.indentInside && !tag.lastChildIsText ) {
writeIndent();
}
writeCString( "</" );
Q_ASSERT( tag.tagName != 0 );
writeCString( tag.tagName );
writeChar( '>' );
}
}
void KoXmlWriter::addTextNode( const char* cstr )
{
prepareForTextNode();
char* escaped = escapeForXML( cstr, -1 );
writeCString( escaped );
if(escaped != m_escapeBuffer)
delete[] escaped;
}
void KoXmlWriter::addProcessingInstruction( const char* cstr )
{
prepareForTextNode();
writeCString( "<?" );
addTextNode( cstr );
writeCString( "?>");
}
void KoXmlWriter::addAttribute( const char* attrName, const char* value )
{
writeChar( ' ' );
writeCString( attrName );
writeCString("=\"");
char* escaped = escapeForXML( value, -1 );
writeCString( escaped );
if(escaped != m_escapeBuffer)
delete[] escaped;
writeChar( '"' );
}
void KoXmlWriter::addAttribute( const char* attrName, double value )
{
TQCString str;
str.setNum( value, 'g', DBL_DIG );
addAttribute( attrName, str.data() );
}
void KoXmlWriter::addAttributePt( const char* attrName, double value )
{
TQCString str;
str.setNum( value, 'g', DBL_DIG );
str += "pt";
addAttribute( attrName, str.data() );
}
void KoXmlWriter::writeIndent()
{
// +1 because of the leading '\n'
m_dev->writeBlock( m_indentBuffer, kMin( indentLevel() + 1,
s_indentBufferLength ) );
}
void KoXmlWriter::writeString( const TQString& str )
{
// cachegrind says .utf8() is where most of the time is spent
TQCString cstr = str.utf8();
m_dev->writeBlock( cstr.data(), cstr.size() - 1 );
}
// In case of a reallocation (ret value != m_buffer), the caller owns the return value,
// it must delete it (with [])
char* KoXmlWriter::escapeForXML( const char* source, int length = -1 ) const
{
// we're going to be pessimistic on char length; so lets make the outputLength less
// the amount one char can take: 6
char* destBoundary = m_escapeBuffer + s_escapeBufferLen - 6;
char* destination = m_escapeBuffer;
char* output = m_escapeBuffer;
const char* src = source; // src moves, source remains
for ( ;; ) {
if(destination >= destBoundary) {
// When we come to realize that our escaped string is going to
// be bigger than the escape buffer (this shouldn't happen very often...),
// we drop the idea of using it, and we allocate a bigger buffer.
// Note that this if() can only be hit once per call to the method.
if ( length == -1 )
length = tqstrlen( source ); // expensive...
uint newLength = length * 6 + 1; // worst case. 6 is due to " and '
char* buffer = new char[ newLength ];
destBoundary = buffer + newLength;
uint amountOfCharsAlreadyCopied = destination - m_escapeBuffer;
memcpy( buffer, m_escapeBuffer, amountOfCharsAlreadyCopied );
output = buffer;
destination = buffer + amountOfCharsAlreadyCopied;
}
switch( *src ) {
case 60: // <
memcpy( destination, "<", 4 );
destination += 4;
break;
case 62: // >
memcpy( destination, ">", 4 );
destination += 4;
break;
case 34: // "
memcpy( destination, """, 6 );
destination += 6;
break;
#if 0 // needed?
case 39: // '
memcpy( destination, "'", 6 );
destination += 6;
break;
#endif
case 38: // &
memcpy( destination, "&", 5 );
destination += 5;
break;
case 0:
*destination = '\0';
return output;
default:
*destination++ = *src++;
continue;
}
++src;
}
// NOTREACHED (see case 0)
return output;
}
void KoXmlWriter::addManifestEntry( const TQString& fullPath, const TQString& mediaType )
{
startElement( "manifest:file-entry" );
addAttribute( "manifest:media-type", mediaType );
addAttribute( "manifest:full-path", fullPath );
endElement();
}
void KoXmlWriter::addConfigItem( const TQString & configName, const TQString& value )
{
startElement( "config:config-item" );
addAttribute( "config:name", configName );
addAttribute( "config:type", "string" );
addTextNode( value );
endElement();
}
void KoXmlWriter::addConfigItem( const TQString & configName, bool value )
{
startElement( "config:config-item" );
addAttribute( "config:name", configName );
addAttribute( "config:type", "boolean" );
addTextNode( value ? "true" : "false" );
endElement();
}
void KoXmlWriter::addConfigItem( const TQString & configName, int value )
{
startElement( "config:config-item" );
addAttribute( "config:name", configName );
addAttribute( "config:type", "int");
addTextNode(TQString::number( value ) );
endElement();
}
void KoXmlWriter::addConfigItem( const TQString & configName, double value )
{
startElement( "config:config-item" );
addAttribute( "config:name", configName );
addAttribute( "config:type", "double" );
addTextNode( TQString::number( value ) );
endElement();
}
void KoXmlWriter::addConfigItem( const TQString & configName, long value )
{
startElement( "config:config-item" );
addAttribute( "config:name", configName );
addAttribute( "config:type", "long" );
addTextNode( TQString::number( value ) );
endElement();
}
void KoXmlWriter::addConfigItem( const TQString & configName, short value )
{
startElement( "config:config-item" );
addAttribute( "config:name", configName );
addAttribute( "config:type", "short" );
addTextNode( TQString::number( value ) );
endElement();
}
void KoXmlWriter::addTextSpan( const TQString& text )
{
TQMap<int, int> tabCache;
addTextSpan( text, tabCache );
}
void KoXmlWriter::addTextSpan( const TQString& text, const TQMap<int, int>& tabCache )
{
uint len = text.length();
int nrSpaces = 0; // number of consecutive spaces
bool leadingSpace = false;
TQString str;
str.reserve( len );
// Accumulate chars either in str or in nrSpaces (for spaces).
// Flush str when writing a subelement (for spaces or for another reason)
// Flush nrSpaces when encountering two or more consecutive spaces
for ( uint i = 0; i < len ; ++i ) {
TQChar ch = text[i];
if ( ch != ' ' ) {
if ( nrSpaces > 0 ) {
// For the first space we use ' '.
// "it is good practice to use (text:s) for the second and all following SPACE
// characters in a sequence." (per the ODF spec)
// however, per the HTML spec, "authors should not rely on user agents to render
// white space immediately after a start tag or immediately before an end tag"
// (and both we and OO.o ignore leading spaces in <text:p> or <text:h> elements...)
if (!leadingSpace)
{
str += ' ';
--nrSpaces;
}
if ( nrSpaces > 0 ) { // there are more spaces
if ( !str.isEmpty() )
addTextNode( str );
str = TQString();
startElement( "text:s" );
if ( nrSpaces > 1 ) // it's 1 by default
addAttribute( "text:c", nrSpaces );
endElement();
}
}
nrSpaces = 0;
leadingSpace = false;
}
switch ( ch.unicode() ) {
case '\t':
if ( !str.isEmpty() )
addTextNode( str );
str = TQString();
startElement( "text:tab" );
if ( tabCache.contains( i ) )
addAttribute( "text:tab-ref", tabCache[i] + 1 );
endElement();
break;
case '\n':
if ( !str.isEmpty() )
addTextNode( str );
str = TQString();
startElement( "text:line-break" );
endElement();
break;
case ' ':
if ( i == 0 )
leadingSpace = true;
++nrSpaces;
break;
default:
str += text[i];
break;
}
}
// either we still have text in str or we have spaces in nrSpaces
if ( !str.isEmpty() ) {
addTextNode( str );
}
if ( nrSpaces > 0 ) { // there are more spaces
startElement( "text:s" );
if ( nrSpaces > 1 ) // it's 1 by default
addAttribute( "text:c", nrSpaces );
endElement();
}
}
|