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
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
|
<html>
<body>
<h1 align='right'><a name='ADVANCED'><img src="3.gif" align="right"
hspace="10" width="100" height="100" alt="3"></a>More Mini-XML
Programming Techniques</h1>
<p>This chapter shows additional ways to use the Mini-XML
library in your programs.</p>
<h2><a name='LOAD_CALLBACKS'>Load Callbacks</a></h2>
<p><a href='#LOAD_XML'>Chapter 2</a> introduced the <a
href='#mxmlLoadFile'><tt>mxmlLoadFile()</tt></a> and <a
href='#mxmlLoadString'><tt>mxmlLoadString()</tt></a> functions.
The last argument to these functions is a callback function
which is used to determine the value type of each data node in
an XML document.</p>
<p>Mini-XML defines several standard callbacks for simple
XML data files:</p>
<ul>
<li><tt>MXML_INTEGER_CALLBACK</tt> - All data nodes
contain whitespace-separated integers.</li>
<li><tt>MXML_OPAQUE_CALLBACK</tt> - All data nodes
contain opaque strings ("CDATA").</li>
<li><tt>MXML_REAL_CALLBACK</tt> - All data nodes contain
whitespace-separated floating-point numbers.</li>
<li><tt>MXML_TEXT_CALLBACK</tt> - All data nodes contain
whitespace-separated strings.</li>
</ul>
<p>You can provide your own callback functions for more complex
XML documents. Your callback function will receive a pointer to
the current element node and must return the value type of the
immediate children for that element node: <tt>MXML_INTEGER</tt>,
<tt>MXML_OPAQUE</tt>, <tt>MXML_REAL</tt>, or <tt>MXML_TEXT</tt>.
The function is called <i>after</i> the element and its
attributes have been read, so you can look at the element name,
attributes, and attribute values to determine the proper value
type to return.</p>
<!-- NEED 2in -->
<p>The following callback function looks for an attribute named
"type" or the element name to determine the value type for its
child nodes:</p>
<pre>
mxml_type_t
type_cb(mxml_node_t *node)
{
const char *type;
/*
* You can lookup attributes and/or use the
* element name, hierarchy, etc...
*/
type = mxmlElementGetAttr(node, "type");
if (type == NULL)
type = mxmlGetElement(node);
if (!strcmp(type, "integer"))
return (MXML_INTEGER);
else if (!strcmp(type, "opaque"))
return (MXML_OPAQUE);
else if (!strcmp(type, "real"))
return (MXML_REAL);
else
return (MXML_TEXT);
}
</pre>
<p>To use this callback function, simply use the name when you
call any of the load functions:</p>
<pre>
FILE *fp;
mxml_node_t *tree;
fp = fopen("filename.xml", "r");
tree = mxmlLoadFile(NULL, fp, <b>type_cb</b>);
fclose(fp);
</pre>
<h2><a name='SAVE_CALLBACKS'>Save Callbacks</a></h2>
<p><a href='#LOAD_XML'>Chapter 2</a> also introduced the <a
href='#mxmlSaveFile'><tt>mxmlSaveFile()</tt></a>, <a
href='#mxmlSaveString'><tt>mxmlSaveString()</tt></a>, and <a
href='#mxmlSaveAllocString'><tt>mxmlSaveAllocString()</tt></a>
functions. The last argument to these functions is a callback
function which is used to automatically insert whitespace in an
XML document.</p>
<p>Your callback function will be called up to four times for
each element node with a pointer to the node and a "where" value
of <tt>MXML_WS_BEFORE_OPEN</tt>, <tt>MXML_WS_AFTER_OPEN</tt>,
<tt>MXML_WS_BEFORE_CLOSE</tt>, or <tt>MXML_WS_AFTER_CLOSE</tt>.
The callback function should return <tt>NULL</tt> if no
whitespace should be added and the string to insert (spaces,
tabs, carriage returns, and newlines) otherwise.</p>
<p>The following whitespace callback can be used to add
whitespace to XHTML output to make it more readable in a standard
text editor:</p>
<pre>
const char *
whitespace_cb(mxml_node_t *node,
int where)
{
const char *name;
/*
* We can conditionally break to a new line
* before or after any element. These are
* just common HTML elements...
*/
name = mxmlGetElement(node);
if (!strcmp(name, "html") ||
!strcmp(name, "head") ||
!strcmp(name, "body") ||
!strcmp(name, "pre") ||
!strcmp(name, "p") ||
!strcmp(name, "h1") ||
!strcmp(name, "h2") ||
!strcmp(name, "h3") ||
!strcmp(name, "h4") ||
!strcmp(name, "h5") ||
!strcmp(name, "h6"))
{
/*
* Newlines before open and after
* close...
*/
if (where == MXML_WS_BEFORE_OPEN ||
where == MXML_WS_AFTER_CLOSE)
return ("\n");
}
else if (!strcmp(name, "dl") ||
!strcmp(name, "ol") ||
!strcmp(name, "ul"))
{
/*
* Put a newline before and after list
* elements...
*/
return ("\n");
}
else if (!strcmp(name, "dd") ||
!strcmp(name, "dt") ||
!strcmp(name, "li"))
{
/*
* Put a tab before <li>'s, * <dd>'s,
* and <dt>'s, and a newline after them...
*/
if (where == MXML_WS_BEFORE_OPEN)
return ("\t");
else if (where == MXML_WS_AFTER_CLOSE)
return ("\n");
}
/*
* Return NULL for no added whitespace...
*/
return (NULL);
}
</pre>
<p>To use this callback function, simply use the name when you
call any of the save functions:</p>
<pre>
FILE *fp;
mxml_node_t *tree;
fp = fopen("filename.xml", "w");
mxmlSaveFile(tree, fp, <b>whitespace_cb</b>);
fclose(fp);
</pre>
<!-- NEED 10 -->
<h2>Custom Data Types</h2>
<p>Mini-XML supports custom data types via global load and save
callbacks. Only a single set of callbacks can be active at any
time, however your callbacks can store additional information in
order to support multiple custom data types as needed. The
<tt>MXML_CUSTOM</tt> node type identifies custom data nodes.</p>
<p>The load callback receives a pointer to the current data node
and a string of opaque character data from the XML source with
character entities converted to the corresponding UTF-8
characters. For example, if we wanted to support a custom
date/time type whose value is encoded as "yyyy-mm-ddThh:mm:ssZ"
(ISO format), the load callback would look like the
following:</p>
<pre>
typedef struct
{
unsigned year, /* Year */
month, /* Month */
day, /* Day */
hour, /* Hour */
minute, /* Minute */
second; /* Second */
time_t unix; /* UNIX time */
} iso_date_time_t;
int
load_custom(mxml_node_t *node,
const char *data)
{
iso_date_time_t *dt;
struct tm tmdata;
/*
* Allocate data structure...
*/
dt = calloc(1, sizeof(iso_date_time_t));
/*
* Try reading 6 unsigned integers from the
* data string...
*/
if (sscanf(data, "%u-%u-%uT%u:%u:%uZ",
&(dt->year), &(dt->month),
&(dt->day), &(dt->hour),
&(dt->minute),
&(dt->second)) != 6)
{
/*
* Unable to read numbers, free the data
* structure and return an error...
*/
free(dt);
return (-1);
}
/*
* Range check values...
*/
if (dt->month < 1 || dt->month > 12 ||
dt->day < 1 || dt->day > 31 ||
dt->hour < 0 || dt->hour > 23 ||
dt->minute < 0 || dt->minute > 59 ||
dt->second < 0 || dt->second > 59)
{
/*
* Date information is out of range...
*/
free(dt);
return (-1);
}
/*
* Convert ISO time to UNIX time in
* seconds...
*/
tmdata.tm_year = dt->year - 1900;
tmdata.tm_mon = dt->month - 1;
tmdata.tm_day = dt->day;
tmdata.tm_hour = dt->hour;
tmdata.tm_min = dt->minute;
tmdata.tm_sec = dt->second;
dt->unix = gmtime(&tmdata);
/*
* Assign custom node data and destroy
* function pointers...
*/
mxmlSetCustom(node, data, destroy);
/*
* Return with no errors...
*/
return (0);
}
</pre>
<p>The function itself can return 0 on success or -1 if it is
unable to decode the custom data or the data contains an error.
Custom data nodes contain a <tt>void</tt> pointer to the
allocated custom data for the node and a pointer to a destructor
function which will free the custom data when the node is
deleted.</p>
<!-- NEED 15 -->
<p>The save callback receives the node pointer and returns an
allocated string containing the custom data value. The following
save callback could be used for our ISO date/time type:</p>
<pre>
char *
save_custom(mxml_node_t *node)
{
char data[255];
iso_date_time_t *dt;
dt = (iso_date_time_t *)mxmlGetCustom(node);
snprintf(data, sizeof(data),
"%04u-%02u-%02uT%02u:%02u:%02uZ",
dt->year, dt->month, dt->day,
dt->hour, dt->minute, dt->second);
return (strdup(data));
}
</pre>
<p>You register the callback functions using the <a
href='#mxmlSetCustomHandlers'><tt>mxmlSetCustomHandlers()</tt></a>
function:</p>
<pre>
mxmlSetCustomHandlers(<b>load_custom</b>,
<b>save_custom</b>);
</pre>
<!-- NEED 20 -->
<h2>Changing Node Values</h2>
<p>All of the examples so far have concentrated on creating and
loading new XML data nodes. Many applications, however, need to
manipulate or change the nodes during their operation, so
Mini-XML provides functions to change node values safely and
without leaking memory.</p>
<p>Existing nodes can be changed using the <a
href='#mxmlSetElement'><tt>mxmlSetElement()</tt></a>, <a
href='#mxmlSetInteger'><tt>mxmlSetInteger()</tt></a>, <a
href='#mxmlSetOpaque'><tt>mxmlSetOpaque()</tt></a>, <a
href='#mxmlSetReal'><tt>mxmlSetReal()</tt></a>, <a
href='#mxmlSetText'><tt>mxmlSetText()</tt></a>, and <a
href='#mxmlSetTextf'><tt>mxmlSetTextf()</tt></a> functions. For
example, use the following function call to change a text node
to contain the text "new" with leading whitespace:</p>
<pre>
mxml_node_t *node;
mxmlSetText(node, 1, "new");
</pre>
<h2>Formatted Text</h2>
<p>The <a href='#mxmlNewTextf'><tt>mxmlNewTextf()</tt></a> and <a
href='#mxmlSetTextf'><tt>mxmlSetTextf()</tt></a> functions create
and change text nodes, respectively, using <tt>printf</tt>-style
format strings and arguments. For example, use the following
function call to create a new text node containing a constructed
filename:</p>
<pre>
mxml_node_t</a> *node;
node = mxmlNewTextf(node, 1, "%s/%s",
path, filename);
</pre>
<h2>Indexing</h2>
<p>Mini-XML provides functions for managing indices of nodes.
The current implementation provides the same functionality as
<a href='#mxmlFindElement'><tt>mxmlFindElement()</tt></a>.
The advantage of using an index is that searching and
enumeration of elements is significantly faster. The only
disadvantage is that each index is a static snapshot of the XML
document, so indices are not well suited to XML data that is
updated more often than it is searched. The overhead of creating
an index is approximately equal to walking the XML document
tree. Nodes in the index are sorted by element name and
attribute value.</p>
<p>Indices are stored in <a href='#mxml_index_t'><tt>mxml_index_t</tt></a>
structures. The <a href='#mxmlIndexNew'><tt>mxmlIndexNew()</tt></a> function
creates a new index:</p>
<pre>
mxml_node_t *tree;
mxml_index_t *ind;
ind = mxmlIndexNew(tree, "element",
"attribute");
</pre>
<p>The first argument is the XML node tree to index. Normally this
will be a pointer to the <tt>?xml</tt> element.</p>
<p>The second argument contains the element to index; passing
<tt>NULL</tt> indexes all element nodes alphabetically.</p>
<p>The third argument contains the attribute to index; passing
<tt>NULL</tt> causes only the element name to be indexed.</p>
<p>Once the index is created, the <a
href='#mxmlIndexEnum'><tt>mxmlIndexEnum()</tt></a>, <a
href='#mxmlIndexFind'><tt>mxmlIndexFind()</tt></a>, and <a
href='#mxmlIndexReset'><tt>mxmlIndexReset()</tt></a> functions
are used to access the nodes in the index. The <a
href='#mxmlIndexReset'><tt>mxmlIndexReset()</tt></a> function
resets the "current" node pointer in the index, allowing you to
do new searches and enumerations on the same index. Typically
you will call this function prior to your calls to <a
href='#mxmlIndexEnum'><tt>mxmlIndexEnum()</tt></a> and <a
href='#mxmlIndexFind'><tt>mxmlIndexFind()</tt></a>.</p>
<p>The <a href='#mxmlIndexEnum'><tt>mxmlIndexEnum()</tt></a>
function enumerates each of the nodes in the index and can be
used in a loop as follows:</p>
<pre>
mxml_node_t *node;
mxmlIndexReset(ind);
while ((node = mxmlIndexEnum(ind)) != NULL)
{
// do something with node
}
</pre>
<p>The <a href='#mxmlIndexFind'><tt>mxmlIndexFind()</tt></a>
function locates the next occurrence of the named element and
attribute value in the index. It can be used to find all
matching elements in an index, as follows:</p>
<pre>
mxml_node_t *node;
mxmlIndexReset(ind);
while ((node = mxmlIndexFind(ind, "element",
"attr-value"))
!= NULL)
{
// do something with node
}
</pre>
<p>The second and third arguments represent the element name and
attribute value, respectively. A <tt>NULL</tt> pointer is used
to return all elements or attributes in the index. Passing
<tt>NULL</tt> for both the element name and attribute value
is equivalent to calling <tt>mxmlIndexEnum</tt>.</p>
<p>When you are done using the index, delete it using the
<a href='#mxmlIndexDelete()'><tt>mxmlIndexDelete()</tt></a>
function:</p>
<pre>
mxmlIndexDelete(ind);
</pre>
<h2>SAX (Stream) Loading of Documents</h2>
<p>Mini-XML supports an implementation of the Simple API for XML
(SAX) which allows you to load and process an XML document as a
stream of nodes. Aside from allowing you to process XML documents of
any size, the Mini-XML implementation also allows you to retain
portions of the document in memory for later processing.</p>
<p>The <a href='#mxmlSAXLoad'><tt>mxmlSAXLoadFd</tt></a>, <a
href='#mxmlSAXLoadFile'><tt>mxmlSAXLoadFile</tt></a>, and <a
href='#mxmlSAXLoadString'><tt>mxmlSAXLoadString</tt></a> functions
provide the SAX loading APIs. Each function works like the
corresponding <tt>mxmlLoad</tt> function but uses a callback to
process each node as it is read.</p>
<p>The callback function receives the node, an event code, and
a user data pointer you supply:</p>
<pre>
void
sax_cb(mxml_node_t *node,
mxml_sax_event_t event,
void *data)
{
... do something ...
}
</pre>
<p>The event will be one of the following:</p>
<ul>
<li><tt>MXML_SAX_CDATA</tt> - CDATA was just read</li>
<li><tt>MXML_SAX_COMMENT</tt> - A comment was just read</li>
<li><tt>MXML_SAX_DATA</tt> - Data (custom, integer, opaque, real, or text) was just read</li>
<li><tt>MXML_SAX_DIRECTIVE</tt> - A processing directive was just read</li>
<li><tt>MXML_SAX_ELEMENT_CLOSE</tt> - A close element was just read (<tt></element></tt>)</li>
<li><tt>MXML_SAX_ELEMENT_OPEN</tt> - An open element was just read (<tt><element></tt>)</li>
</ul>
<p>Elements are <em>released</em> after the close element is
processed. All other nodes are released after they are processed.
The SAX callback can <em>retain</em> the node using the <a
href='#mxmlRetain'><tt>mxmlRetain</tt></a> function. For example,
the following SAX callback will retain all nodes, effectively
simulating a normal in-memory load:</p>
<pre>
void
sax_cb(mxml_node_t *node,
mxml_sax_event_t event,
void *data)
{
if (event != MXML_SAX_ELEMENT_CLOSE)
mxmlRetain(node);
}
</pre>
<p>More typically the SAX callback will only retain a small portion
of the document that is needed for post-processing. For example, the
following SAX callback will retain the title and headings in an
XHTML file. It also retains the (parent) elements like <tt><html></tt>, <tt><head></tt>, and <tt><body></tt>, and processing
directives like <tt><?xml ... ?></tt> and <tt><!DOCTYPE ... ></tt>:</p>
<!-- NEED 10 -->
<pre>
void
sax_cb(mxml_node_t *node,
mxml_sax_event_t event,
void *data)
{
if (event == MXML_SAX_ELEMENT_OPEN)
{
/*
* Retain headings and titles...
*/
char *name = mxmlGetElement(node);
if (!strcmp(name, "html") ||
!strcmp(name, "head") ||
!strcmp(name, "title") ||
!strcmp(name, "body") ||
!strcmp(name, "h1") ||
!strcmp(name, "h2") ||
!strcmp(name, "h3") ||
!strcmp(name, "h4") ||
!strcmp(name, "h5") ||
!strcmp(name, "h6"))
mxmlRetain(node);
}
else if (event == MXML_SAX_DIRECTIVE)
mxmlRetain(node);
else if (event == MXML_SAX_DATA)
{
if (mxmlGetRefCount(mxmlGetParent(node)) > 1)
{
/*
* If the parent was retained, then retain
* this data node as well.
*/
mxmlRetain(node);
}
}
}
</pre>
<p>The resulting skeleton document tree can then be searched just
like one loaded using the <tt>mxmlLoad</tt> functions. For example,
a filter that reads an XHTML document from stdin and then shows the
title and headings in the document would look like:</p>
<pre>
mxml_node_t *doc, *title, *body, *heading;
doc = mxmlSAXLoadFd(NULL, 0,
MXML_TEXT_CALLBACK,
<b>sax_cb</b>, NULL);
title = mxmlFindElement(doc, doc, "title",
NULL, NULL,
MXML_DESCEND);
if (title)
print_children(title);
body = mxmlFindElement(doc, doc, "body",
NULL, NULL,
MXML_DESCEND);
if (body)
{
for (heading = mxmlGetFirstChild(body);
heading;
heading = mxmlGetNextSibling(heading))
print_children(heading);
}
</pre>
</body>
</html>
|
