1 | <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">
|
---|
2 | <html>
|
---|
3 | <head>
|
---|
4 | <meta content="text/html; charset=ISO-8859-1" http-equiv="Content-Type">
|
---|
5 | <title>libxslt Tutorial</title>
|
---|
6 | <meta name="generator" content="DocBook XSL Stylesheets V1.41">
|
---|
7 | </head>
|
---|
8 | <body bgcolor="white" text="black" link="#0000FF" vlink="#840084" alink="#0000FF"><div class="article">
|
---|
9 | <div class="titlepage">
|
---|
10 | <div><h1 class="title">
|
---|
11 | <a name="id2702654"></a>libxslt Tutorial</h1></div>
|
---|
12 | <div><h3 class="author">John Fleck</h3></div>
|
---|
13 | <div><p class="releaseinfo">
|
---|
14 | This is version 0.4 of the libxslt Tutorial
|
---|
15 | </p></div>
|
---|
16 | <div><p class="copyright">Copyright © 2001 John Fleck</p></div>
|
---|
17 | <div><div class="legalnotice"><p>Permission is granted to copy, distribute and/or modify this
|
---|
18 | document under the terms of the <i>GNU Free Documentation
|
---|
19 | License</i>, Version 1.1 or any later version
|
---|
20 | published by the Free Software Foundation with no Invariant
|
---|
21 | Sections, no Front-Cover Texts, and no Back-Cover Texts. A copy of
|
---|
22 | the license can be found <a href="http://www.gnu.org/copyleft/fdl.html" target="_top">here</a>.</p></div></div>
|
---|
23 | <hr>
|
---|
24 | </div>
|
---|
25 | <div class="toc">
|
---|
26 | <p><b>Table of Contents</b></p>
|
---|
27 | <dl>
|
---|
28 | <dt> <a href="#introduction">Introduction</a>
|
---|
29 | </dt>
|
---|
30 | <dt> <a href="#functions">Primary Functions</a>
|
---|
31 | </dt>
|
---|
32 | <dd><dl>
|
---|
33 | <dt> <a href="#preparing">Preparing to Parse</a>
|
---|
34 | </dt>
|
---|
35 | <dt> <a href="#parsethestylesheet">Parse the Stylesheet</a>
|
---|
36 | </dt>
|
---|
37 | <dt> <a href="#parseinputfile">Parse the Input File</a>
|
---|
38 | </dt>
|
---|
39 | <dt> <a href="#applyingstylesheet">Applying the Stylesheet</a>
|
---|
40 | </dt>
|
---|
41 | <dt> <a href="#saveresult">Saving the result</a>
|
---|
42 | </dt>
|
---|
43 | <dt> <a href="#parameters">Parameters</a>
|
---|
44 | </dt>
|
---|
45 | <dt> <a href="#cleanup">Cleanup</a>
|
---|
46 | </dt>
|
---|
47 | </dl></dd>
|
---|
48 | <dt>A <a href="#thecode">The Code</a>
|
---|
49 | </dt>
|
---|
50 | </dl>
|
---|
51 | </div>
|
---|
52 | <div class="abstract">
|
---|
53 | <p>
|
---|
54 | <a name="id2705766"></a><b>Abstract</b>
|
---|
55 | </p>
|
---|
56 | <p>A tutorial on building a simple application using the
|
---|
57 | libxslt library to perform
|
---|
58 | XSLT transformations to convert an
|
---|
59 | XML file into HTML.</p>
|
---|
60 | </div>
|
---|
61 | <div class="sect1">
|
---|
62 | <a name="introduction"></a><div class="titlepage"><div><h2 class="title" style="clear: both">
|
---|
63 | <a name="introduction"></a>Introduction</h2></div></div>
|
---|
64 | <p>The Extensible Markup Language (XML) is a World
|
---|
65 | Wide Web Consortium standard for the exchange of structured data in text
|
---|
66 | form. Its popularity stems from its universality. Any computer can
|
---|
67 | read a text file. With the proper tools, any computer can read any other
|
---|
68 | computer's XML files.
|
---|
69 | </p>
|
---|
70 | <p>One of the most important of those tools is XSLT:
|
---|
71 | Extensible Stylesheet Language Transformations. XSLT
|
---|
72 | is a declarative language that allows you to
|
---|
73 | translate your XML into arbitrary text output
|
---|
74 | using a stylesheet. libxslt provides the
|
---|
75 | functions to perform the transformation.
|
---|
76 | </p>
|
---|
77 | <p>libxslt is a free C language library
|
---|
78 | written by Daniel Veillard for the GNOME project
|
---|
79 | allowing you to write programs that perform XSLT
|
---|
80 | transformations.
|
---|
81 |
|
---|
82 | <div class="note" style="margin-left: 0.5in; margin-right: 0.5in;">
|
---|
83 | <h3 class="title">
|
---|
84 | <a name="id2754803"></a>Note</h3>
|
---|
85 | <p>
|
---|
86 | While libxslt was written
|
---|
87 | under the auspices of the GNOME project, it does not
|
---|
88 | depend on any GNOME libraries. None are used in the
|
---|
89 | example in this tutorial.
|
---|
90 | </p>
|
---|
91 | </div>
|
---|
92 |
|
---|
93 | </p>
|
---|
94 | <p>This tutorial illustrates a simple program that reads an
|
---|
95 | XML file, applies a stylesheet and saves the resulting
|
---|
96 | output. This is not a program you would want to create
|
---|
97 | yourself. xsltproc, which is included with the
|
---|
98 | libxslt package, does the same thing and is
|
---|
99 | more robust and full-featured. The program written for this tutorial is a
|
---|
100 | stripped-down version of xsltproc designed to
|
---|
101 | illustrate the functionality of libxslt.
|
---|
102 | </p>
|
---|
103 | <p>The full code for xsltproc is in
|
---|
104 | <tt>xsltproc.c</tt> in the libxslt
|
---|
105 | distribution. It also is available <a href="http://cvs.gnome.org/lxr/source/libxslt/libxslt/xsltproc.c" target="_top">on the
|
---|
106 | web</a>.
|
---|
107 | </p>
|
---|
108 | <p>References:
|
---|
109 | <div class="itemizedlist"><ul>
|
---|
110 | <li><p>
|
---|
111 | <a name="id2708005"></a><a href="http://www.w3.org/XML/" target="_top">W3C XML page</a>
|
---|
112 | </p></li>
|
---|
113 | <li><p>
|
---|
114 | <a name="id2708026"></a><a href="http://www.w3.org/Style/XSL/" target="_top">W3C
|
---|
115 | XSL page.</a>
|
---|
116 | </p></li>
|
---|
117 | <li><p>
|
---|
118 | <a name="id2708047"></a><a href="http://xmlsoft.org/XSLT/" target="_top">libxslt</a>
|
---|
119 | </p></li>
|
---|
120 | </ul></div>
|
---|
121 |
|
---|
122 | </p>
|
---|
123 | </div>
|
---|
124 | <div class="sect1">
|
---|
125 | <a name="functions"></a><div class="titlepage"><div><h2 class="title" style="clear: both">
|
---|
126 | <a name="functions"></a>Primary Functions</h2></div></div>
|
---|
127 | <div class="toc">
|
---|
128 | <p><b>Table of Contents</b></p>
|
---|
129 | <dl>
|
---|
130 | <dt> <a href="#preparing">Preparing to Parse</a>
|
---|
131 | </dt>
|
---|
132 | <dt> <a href="#parsethestylesheet">Parse the Stylesheet</a>
|
---|
133 | </dt>
|
---|
134 | <dt> <a href="#parseinputfile">Parse the Input File</a>
|
---|
135 | </dt>
|
---|
136 | <dt> <a href="#applyingstylesheet">Applying the Stylesheet</a>
|
---|
137 | </dt>
|
---|
138 | <dt> <a href="#saveresult">Saving the result</a>
|
---|
139 | </dt>
|
---|
140 | <dt> <a href="#parameters">Parameters</a>
|
---|
141 | </dt>
|
---|
142 | <dt> <a href="#cleanup">Cleanup</a>
|
---|
143 | </dt>
|
---|
144 | </dl>
|
---|
145 | </div>
|
---|
146 | <p>To transform an XML file, you must perform three
|
---|
147 | functions:
|
---|
148 | <div class="orderedlist"><ol type="1">
|
---|
149 | <li><p>
|
---|
150 | <a name="id2708093"></a>parse the input file</p></li>
|
---|
151 | <li><p>
|
---|
152 | <a name="id2708101"></a>parse the stylesheet</p></li>
|
---|
153 | <li><p>
|
---|
154 | <a name="id2708110"></a>apply the stylesheet</p></li>
|
---|
155 | </ol></div>
|
---|
156 | </p>
|
---|
157 | <div class="sect2">
|
---|
158 | <a name="preparing"></a><div class="titlepage"><div><h3 class="title">
|
---|
159 | <a name="preparing"></a>Preparing to Parse</h3></div></div>
|
---|
160 | <p>Before you can begin parsing input files or stylesheets, there are
|
---|
161 | several steps you need to take to set up entity handling. These steps are
|
---|
162 | not unique to libxslt. Any
|
---|
163 | libxml2 program that parses
|
---|
164 | XML files would need to take similar steps.
|
---|
165 | </p>
|
---|
166 | <p>First, you need set up some libxml
|
---|
167 | housekeeping. Pass the integer value <i><tt>1</tt></i> to the
|
---|
168 | <tt>xmlSubstituteEntitiesDefault</tt> function, which tells
|
---|
169 | the libxml2 parser to substitute entities as
|
---|
170 | it parses your file. (Passing <i><tt>0</tt></i> causes
|
---|
171 | libxml2 to not perform entity substitution.)
|
---|
172 | </p>
|
---|
173 | <p>Second, set <tt>xmlLoadExtDtdDefaultValue</tt> equal to
|
---|
174 | <i><tt>1</tt></i>. This tells libxml
|
---|
175 | to load external entity subsets. If you do not do this and your
|
---|
176 | input file includes entities through external subsets, you will get
|
---|
177 | errors.</p>
|
---|
178 | </div>
|
---|
179 | <div class="sect2">
|
---|
180 | <a name="parsethestylesheet"></a><div class="titlepage"><div><h3 class="title">
|
---|
181 | <a name="parsethestylesheet"></a>Parse the Stylesheet</h3></div></div>
|
---|
182 | <p>Parsing the stylesheet takes a single function call, which takes a
|
---|
183 | variable of type xmlChar:
|
---|
184 | <pre class="programlisting">
|
---|
185 | <tt>cur</tt> = xsltParseStylesheetFile((const xmlChar *)argv[i]);
|
---|
186 | </pre>
|
---|
187 | In this case, I cast the stylesheet file name, passed in as a
|
---|
188 | command line argument, to <i>xmlChar</i>. The return value
|
---|
189 | is of type <i>xsltStylesheetPtr</i>, a struct in memory
|
---|
190 | that contains the stylesheet tree and other information about the
|
---|
191 | stylesheet. It can be manipulated directly, but for this example you
|
---|
192 | will not need to.
|
---|
193 | </p>
|
---|
194 | </div>
|
---|
195 | <div class="sect2">
|
---|
196 | <a name="parseinputfile"></a><div class="titlepage"><div><h3 class="title">
|
---|
197 | <a name="parseinputfile"></a>Parse the Input File</h3></div></div>
|
---|
198 | <p>Parsing the input file takes a single function call:
|
---|
199 | <pre class="programlisting">
|
---|
200 | doc = xmlParseFile(argv[i]);
|
---|
201 | </pre>
|
---|
202 | It returns an <i>xmlDocPtr</i>, a struct in memory that
|
---|
203 | contains the document tree. It can be manipulated directly, but for this
|
---|
204 | example you will not need to.
|
---|
205 | </p>
|
---|
206 | </div>
|
---|
207 | <div class="sect2">
|
---|
208 | <a name="applyingstylesheet"></a><div class="titlepage"><div><h3 class="title">
|
---|
209 | <a name="applyingstylesheet"></a>Applying the Stylesheet</h3></div></div>
|
---|
210 | <p>Now that you have trees representing the document and the stylesheet
|
---|
211 | in memory, apply the stylesheet to the document. The
|
---|
212 | function that does this is <tt>xsltApplyStylesheet</tt>:
|
---|
213 | <pre class="programlisting">
|
---|
214 | res = xsltApplyStylesheet(cur, doc, params);
|
---|
215 | </pre>
|
---|
216 | The function takes an xsltStylesheetPtr and an
|
---|
217 | xmlDocPtr, the values returned by the previous two functions. The third
|
---|
218 | variable, <tt>params</tt> can be used to pass
|
---|
219 | XSLT parameters to the stylesheet. It is a
|
---|
220 | NULL-terminated array of name/value pairs of const char's.
|
---|
221 | </p>
|
---|
222 | </div>
|
---|
223 | <div class="sect2">
|
---|
224 | <a name="saveresult"></a><div class="titlepage"><div><h3 class="title">
|
---|
225 | <a name="saveresult"></a>Saving the result</h3></div></div>
|
---|
226 | <p>libxslt includes a family of functions to use in
|
---|
227 | saving the resulting output. For this example,
|
---|
228 | <tt>xsltSaveResultToFile</tt> is used, and the results are
|
---|
229 | saved to stdout:
|
---|
230 |
|
---|
231 | <pre class="programlisting">
|
---|
232 | xsltSaveResultToFile(stdout, res, cur);
|
---|
233 | </pre>
|
---|
234 |
|
---|
235 | <div class="note" style="margin-left: 0.5in; margin-right: 0.5in;">
|
---|
236 | <h3 class="title">
|
---|
237 | <a name="id2708587"></a>Note</h3>
|
---|
238 | <p>libxml also contains output
|
---|
239 | functions, such as <tt>xmlSaveFile</tt>, which can be
|
---|
240 | used here. However, output-related information contained in the
|
---|
241 | stylesheet, such as a declaration of the encoding to be used, will
|
---|
242 | be lost if one of the libxslt save
|
---|
243 | functions is not used.</p>
|
---|
244 | </div>
|
---|
245 | </p>
|
---|
246 | </div>
|
---|
247 | <div class="sect2">
|
---|
248 | <a name="parameters"></a><div class="titlepage"><div><h3 class="title">
|
---|
249 | <a name="parameters"></a>Parameters</h3></div></div>
|
---|
250 | <p>
|
---|
251 | In XSLT, parameters may be used as a way to pass
|
---|
252 | additional information to a
|
---|
253 | stylesheet. libxslt accepts
|
---|
254 | XSLT parameters as one of the values passed to
|
---|
255 | <tt>xsltApplyStylesheet</tt>.
|
---|
256 | </p>
|
---|
257 | <p>
|
---|
258 | In the tutorial example and in xsltproc,
|
---|
259 | on which the tutorial example is based, parameters to be passed take the
|
---|
260 | form of key-value pairs. The program collects them from command line
|
---|
261 | arguments, inserting them in the array <tt>params</tt>, then
|
---|
262 | passes them to the function. The final element in the array is set to
|
---|
263 | <i><tt>NULL</tt></i>.
|
---|
264 |
|
---|
265 | <div class="note" style="margin-left: 0.5in; margin-right: 0.5in;">
|
---|
266 | <h3 class="title">
|
---|
267 | <a name="id2708668"></a>Note</h3>
|
---|
268 | <p>
|
---|
269 | If a parameter being passed is a string rather than an
|
---|
270 | XSLT node, it must be escaped. For the tutorial
|
---|
271 | program, that would be done as follows:
|
---|
272 | <b>tutorial]$ ./libxslt_tutorial --param rootid "'asect1'"
|
---|
273 | stylesheet.xsl filename.xml</b>
|
---|
274 | </p>
|
---|
275 | </div>
|
---|
276 | </p>
|
---|
277 | </div>
|
---|
278 | <div class="sect2">
|
---|
279 | <a name="cleanup"></a><div class="titlepage"><div><h3 class="title">
|
---|
280 | <a name="cleanup"></a>Cleanup</h3></div></div>
|
---|
281 | <p>After you are finished, libxslt and
|
---|
282 | libxml provide functions for deallocating
|
---|
283 | memory.
|
---|
284 | </p>
|
---|
285 | <p>
|
---|
286 |
|
---|
287 | <pre class="programlisting">
|
---|
288 | xsltFreeStylesheet(cur);<a name="cleanupstylesheet"></a><img src="../images/callouts/1.png" alt="1" border="0">
|
---|
289 | xmlFreeDoc(res);<a name="cleanupresults"></a><img src="../images/callouts/2.png" alt="2" border="0">
|
---|
290 | xmlFreeDoc(doc);<a name="cleanupdoc"></a><img src="../images/callouts/3.png" alt="3" border="0">
|
---|
291 | xsltCleanupGlobals();<a name="cleanupglobals"></a><img src="../images/callouts/4.png" alt="4" border="0">
|
---|
292 | xmlCleanupParser();<a name="cleanupparser"></a><img src="../images/callouts/5.png" alt="5" border="0">
|
---|
293 |
|
---|
294 | </pre>
|
---|
295 |
|
---|
296 | <div class="calloutlist">
|
---|
297 | <a name="id2708994"></a><table border="0" summary="Callout list">
|
---|
298 | <tr>
|
---|
299 | <td width="5%" valign="top" align="left">
|
---|
300 | <a name="id2709000"></a><a href="#cleanupstylesheet"><img src="../images/callouts/1.png" alt="1" border="0"></a> </td>
|
---|
301 | <td valign="top" align="left"><p>Free the memory used by your stylesheet.</p></td>
|
---|
302 | </tr>
|
---|
303 | <tr>
|
---|
304 | <td width="5%" valign="top" align="left">
|
---|
305 | <a name="id2709117"></a><a href="#cleanupresults"><img src="../images/callouts/2.png" alt="2" border="0"></a> </td>
|
---|
306 | <td valign="top" align="left"><p>Free the memory used by the results document.</p></td>
|
---|
307 | </tr>
|
---|
308 | <tr>
|
---|
309 | <td width="5%" valign="top" align="left">
|
---|
310 | <a name="id2709136"></a><a href="#cleanupdoc"><img src="../images/callouts/3.png" alt="3" border="0"></a> </td>
|
---|
311 | <td valign="top" align="left"><p>Free the memory used by your original document.</p></td>
|
---|
312 | </tr>
|
---|
313 | <tr>
|
---|
314 | <td width="5%" valign="top" align="left">
|
---|
315 | <a name="id2709155"></a><a href="#cleanupglobals"><img src="../images/callouts/4.png" alt="4" border="0"></a> </td>
|
---|
316 | <td valign="top" align="left"><p>Free memory used by libxslt global
|
---|
317 | variables</p></td>
|
---|
318 | </tr>
|
---|
319 | <tr>
|
---|
320 | <td width="5%" valign="top" align="left">
|
---|
321 | <a name="id2709176"></a><a href="#cleanupparser"><img src="../images/callouts/5.png" alt="5" border="0"></a> </td>
|
---|
322 | <td valign="top" align="left"><p>Free memory used by the XML parser</p></td>
|
---|
323 | </tr>
|
---|
324 | </table>
|
---|
325 | </div>
|
---|
326 | </p>
|
---|
327 | </div>
|
---|
328 | </div>
|
---|
329 | <div class="appendix">
|
---|
330 | <h2 class="title" style="clear: both">
|
---|
331 | <a name="thecode"></a>A. The Code</h2>
|
---|
332 | <p>
|
---|
333 | <tt>libxslt_tutorial.c</tt>
|
---|
334 | <pre class="programlisting">
|
---|
335 | /*
|
---|
336 | * libxslt_tutorial.c: demo program for the XSL Transformation 1.0 engine
|
---|
337 | *
|
---|
338 | * based on xsltproc.c, by [email protected]
|
---|
339 | * by John Fleck
|
---|
340 | *
|
---|
341 | * This program is free software; you can redistribute it and/or modify
|
---|
342 | * it under the terms of the GNU General Public License as published by
|
---|
343 | * the Free Software Foundation; either version 2 of the License, or
|
---|
344 | * (at your option) any later version.
|
---|
345 | *
|
---|
346 | * This program is distributed in the hope that it will be useful,
|
---|
347 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
348 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
349 | * GNU General Public License for more details.
|
---|
350 | *
|
---|
351 | * You should have received a copy of the GNU General Public License
|
---|
352 | * along with this program; if not, write to the Free Software
|
---|
353 | * Foundation, Inc., 59 Temple Place - Suite 330, Cambridge, MA 02139, USA.
|
---|
354 | *
|
---|
355 | */
|
---|
356 |
|
---|
357 | #include <string.h>
|
---|
358 | #include <libxml/xmlmemory.h>
|
---|
359 | #include <libxml/debugXML.h>
|
---|
360 | #include <libxml/HTMLtree.h>
|
---|
361 | #include <libxml/xmlIO.h>
|
---|
362 | #include <libxml/DOCBparser.h>
|
---|
363 | #include <libxml/xinclude.h>
|
---|
364 | #include <libxml/catalog.h>
|
---|
365 | #include <libxslt/xslt.h>
|
---|
366 | #include <libxslt/xsltInternals.h>
|
---|
367 | #include <libxslt/transform.h>
|
---|
368 | #include <libxslt/xsltutils.h>
|
---|
369 |
|
---|
370 |
|
---|
371 |
|
---|
372 | extern int xmlLoadExtDtdDefaultValue;
|
---|
373 |
|
---|
374 | static void usage(const char *name) {
|
---|
375 | printf("Usage: %s [options] stylesheet file [file ...]\n", name);
|
---|
376 | printf(" --param name value : pass a (parameter,value) pair\n");
|
---|
377 |
|
---|
378 | }
|
---|
379 |
|
---|
380 | int
|
---|
381 | main(int argc, char **argv) {
|
---|
382 | int i;
|
---|
383 | const char *params[16 + 1];
|
---|
384 | int nbparams = 0;
|
---|
385 | xsltStylesheetPtr cur = NULL;
|
---|
386 | xmlDocPtr doc, res;
|
---|
387 |
|
---|
388 | if (argc <= 1) {
|
---|
389 | usage(argv[0]);
|
---|
390 | return(1);
|
---|
391 | }
|
---|
392 |
|
---|
393 |
|
---|
394 | for (i = 1; i < argc; i++) {
|
---|
395 | if (argv[i][0] != '-')
|
---|
396 | break;
|
---|
397 | if ((!strcmp(argv[i], "-param")) ||
|
---|
398 | (!strcmp(argv[i], "--param"))) {
|
---|
399 | i++;
|
---|
400 | params[nbparams++] = argv[i++];
|
---|
401 | params[nbparams++] = argv[i];
|
---|
402 | if (nbparams >= 16) {
|
---|
403 | fprintf(stderr, "too many params\n");
|
---|
404 | return (1);
|
---|
405 | }
|
---|
406 | } else {
|
---|
407 | fprintf(stderr, "Unknown option %s\n", argv[i]);
|
---|
408 | usage(argv[0]);
|
---|
409 | return (1);
|
---|
410 | }
|
---|
411 | }
|
---|
412 |
|
---|
413 | params[nbparams] = NULL;
|
---|
414 | xmlSubstituteEntitiesDefault(1);
|
---|
415 | xmlLoadExtDtdDefaultValue = 1;
|
---|
416 | cur = xsltParseStylesheetFile((const xmlChar *)argv[i]);
|
---|
417 | i++;
|
---|
418 | doc = xmlParseFile(argv[i]);
|
---|
419 | res = xsltApplyStylesheet(cur, doc, params);
|
---|
420 | xsltSaveResultToFile(stdout, res, cur);
|
---|
421 |
|
---|
422 | xsltFreeStylesheet(cur);
|
---|
423 | xmlFreeDoc(res);
|
---|
424 | xmlFreeDoc(doc);
|
---|
425 |
|
---|
426 | xsltCleanupGlobals();
|
---|
427 | xmlCleanupParser();
|
---|
428 | return(0);
|
---|
429 |
|
---|
430 | }
|
---|
431 |
|
---|
432 | </pre>
|
---|
433 |
|
---|
434 | </p>
|
---|
435 | </div>
|
---|
436 | </div></body>
|
---|
437 | </html>
|
---|