Blame - doc/example.html - platform/external/libxml2

blob: c5413e3c9f3131fc73f1010f68f2a96781f8b6bf [file] [log] [blame]

Daniel Veillard	43d3f61	2001-11-10 11:57:23 +0000	[diff] [blame]	1	<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/1999/REC-html401-19991224/loose.dtd">
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	2	<html>
				3	<head>
				4	<meta content="text/html; charset=ISO-8859-1" http-equiv="Content-Type">
Daniel Veillard	c332dab	2002-03-29 14:08:27 +0000	[diff] [blame]	5	<link rel="SHORTCUT ICON" href="/favicon.ico">
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	6	<style type="text/css"><!--
Daniel Veillard	373a475	2002-02-21 14:46:29 +0000	[diff] [blame]	7	TD {font-family: Verdana,Arial,Helvetica}
				8	BODY {font-family: Verdana,Arial,Helvetica; margin-top: 2em; margin-left: 0em; margin-right: 0em}
				9	H1 {font-family: Verdana,Arial,Helvetica}
				10	H2 {font-family: Verdana,Arial,Helvetica}
				11	H3 {font-family: Verdana,Arial,Helvetica}
Daniel Veillard	b8cfbd1	2001-10-25 10:53:28 +0000	[diff] [blame]	12	A:link, A:visited, A:active { text-decoration: underline }
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	13	--></style>
				14	<title>A real example</title>
				15	</head>
				16	<body bgcolor="#8b7765" text="#000000" link="#000000" vlink="#000000">
				17	<table border="0" width="100%" cellpadding="5" cellspacing="0" align="center"><tr>
				18	<td width="180">
				19	<a href="http://www.gnome.org/"><img src="smallfootonly.gif" alt="Gnome Logo"></a><a href="http://www.w3.org/Status"><img src="w3c.png" alt="W3C Logo"></a><a href="http://www.redhat.com/"><img src="redhat.gif" alt="Red Hat Logo"></a>
				20	</td>
				21	<td><table border="0" width="90%" cellpadding="2" cellspacing="0" align="center" bgcolor="#000000"><tr><td><table width="100%" border="0" cellspacing="1" cellpadding="3" bgcolor="#fffacd"><tr><td align="center">
				22	<h1>The XML C library for Gnome</h1>
				23	<h2>A real example</h2>
				24	</td></tr></table></td></tr></table></td>
				25	</tr></table>
				26	<table border="0" cellpadding="4" cellspacing="0" width="100%" align="center"><tr><td bgcolor="#8b7765"><table border="0" cellspacing="0" cellpadding="2" width="100%"><tr>
Daniel Veillard	594cf0b	2001-10-25 08:09:12 +0000	[diff] [blame]	27	<td valign="top" width="200" bgcolor="#8b7765"><table border="0" cellspacing="0" cellpadding="1" width="100%" bgcolor="#000000"><tr><td>
				28	<table width="100%" border="0" cellspacing="1" cellpadding="3">
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	29	<tr><td colspan="1" bgcolor="#eecfa1" align="center"><center><b>Main Menu</b></center></td></tr>
Daniel Veillard	8acca11	2002-01-21 09:52:27 +0000	[diff] [blame]	30	<tr><td bgcolor="#fffacd"><ul>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	31	<li><a href="index.html">Home</a></li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	32	<li><a href="intro.html">Introduction</a></li>
Daniel Veillard	b8cfbd1	2001-10-25 10:53:28 +0000	[diff] [blame]	33	<li><a href="FAQ.html">FAQ</a></li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	34	<li><a href="docs.html">Documentation</a></li>
				35	<li><a href="bugs.html">Reporting bugs and getting help</a></li>
				36	<li><a href="help.html">How to help</a></li>
				37	<li><a href="downloads.html">Downloads</a></li>
				38	<li><a href="news.html">News</a></li>
Daniel Veillard	7b602b4	2002-01-08 13:26:00 +0000	[diff] [blame]	39	<li><a href="XMLinfo.html">XML</a></li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	40	<li><a href="XSLT.html">XSLT</a></li>
Daniel Veillard	6dbcaf8	2002-02-20 14:37:47 +0000	[diff] [blame]	41	<li><a href="python.html">Python and bindings</a></li>
Daniel Veillard	b8cfbd1	2001-10-25 10:53:28 +0000	[diff] [blame]	42	<li><a href="architecture.html">libxml architecture</a></li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	43	<li><a href="tree.html">The tree output</a></li>
				44	<li><a href="interface.html">The SAX interface</a></li>
Daniel Veillard	b8cfbd1	2001-10-25 10:53:28 +0000	[diff] [blame]	45	<li><a href="xmldtd.html">Validation & DTDs</a></li>
				46	<li><a href="xmlmem.html">Memory Management</a></li>
				47	<li><a href="encoding.html">Encodings support</a></li>
				48	<li><a href="xmlio.html">I/O Interfaces</a></li>
				49	<li><a href="catalog.html">Catalog support</a></li>
				50	<li><a href="library.html">The parser interfaces</a></li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	51	<li><a href="entities.html">Entities or no entities</a></li>
				52	<li><a href="namespaces.html">Namespaces</a></li>
Daniel Veillard	b8cfbd1	2001-10-25 10:53:28 +0000	[diff] [blame]	53	<li><a href="upgrade.html">Upgrading 1.x code</a></li>
Daniel Veillard	52dcab3	2001-10-30 12:51:17 +0000	[diff] [blame]	54	<li><a href="threads.html">Thread safety</a></li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	55	<li><a href="DOM.html">DOM Principles</a></li>
				56	<li><a href="example.html">A real example</a></li>
				57	<li><a href="contribs.html">Contributions</a></li>
Daniel Veillard	594cf0b	2001-10-25 08:09:12 +0000	[diff] [blame]	58	<li>
				59	<a href="xml.html">flat page</a>, <a href="site.xsl">stylesheet</a>
				60	</li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	61	</ul></td></tr>
Daniel Veillard	594cf0b	2001-10-25 08:09:12 +0000	[diff] [blame]	62	</table>
				63	<table width="100%" border="0" cellspacing="1" cellpadding="3">
Daniel Veillard	3bf65be	2002-01-23 12:36:34 +0000	[diff] [blame]	64	<tr><td colspan="1" bgcolor="#eecfa1" align="center"><center><b>API Indexes</b></center></td></tr>
				65	<tr><td bgcolor="#fffacd"><ul>
Daniel Veillard	f859256	2002-01-23 17:58:17 +0000	[diff] [blame]	66	<li><a href="APIchunk0.html">Alphabetic</a></li>
Daniel Veillard	3bf65be	2002-01-23 12:36:34 +0000	[diff] [blame]	67	<li><a href="APIconstructors.html">Constructors</a></li>
				68	<li><a href="APIfunctions.html">Functions/Types</a></li>
				69	<li><a href="APIfiles.html">Modules</a></li>
				70	<li><a href="APIsymbols.html">Symbols</a></li>
				71	</ul></td></tr>
				72	</table>
				73	<table width="100%" border="0" cellspacing="1" cellpadding="3">
Daniel Veillard	594cf0b	2001-10-25 08:09:12 +0000	[diff] [blame]	74	<tr><td colspan="1" bgcolor="#eecfa1" align="center"><center><b>Related links</b></center></td></tr>
Daniel Veillard	8acca11	2002-01-21 09:52:27 +0000	[diff] [blame]	75	<tr><td bgcolor="#fffacd"><ul>
Daniel Veillard	594cf0b	2001-10-25 08:09:12 +0000	[diff] [blame]	76	<li><a href="http://mail.gnome.org/archives/xml/">Mail archive</a></li>
				77	<li><a href="http://xmlsoft.org/XSLT/">XSLT libxslt</a></li>
Daniel Veillard	4a85920	2002-01-08 11:49:22 +0000	[diff] [blame]	78	<li><a href="http://phd.cs.unibo.it/gdome2/">DOM gdome2</a></li>
Daniel Veillard	2d347fa	2002-03-17 10:34:11 +0000	[diff] [blame]	79	<li><a href="http://www.aleksey.com/xmlsec/">XML-DSig xmlsec</a></li>
Daniel Veillard	594cf0b	2001-10-25 08:09:12 +0000	[diff] [blame]	80	<li><a href="ftp://xmlsoft.org/">FTP</a></li>
				81	<li><a href="http://www.fh-frankfurt.de/~igor/projects/libxml/">Windows binaries</a></li>
Daniel Veillard	db9dfd9	2001-11-26 17:25:02 +0000	[diff] [blame]	82	<li><a href="http://garypennington.net/libxml2/">Solaris binaries</a></li>
Daniel Veillard	e6d8e20	2002-05-02 06:11:10 +0000	[diff] [blame]	83	<li><a href="http://sourceforge.net/projects/libxml2-pas/">Pascal bindings</a></li>
Daniel Veillard	2d347fa	2002-03-17 10:34:11 +0000	[diff] [blame]	84	<li><a href="http://bugzilla.gnome.org/buglist.cgi?product=libxml&product=libxml2">Bug Tracker</a></li>
Daniel Veillard	594cf0b	2001-10-25 08:09:12 +0000	[diff] [blame]	85	</ul></td></tr>
				86	</table>
				87	</td></tr></table></td>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	88	<td valign="top" bgcolor="#8b7765"><table border="0" cellspacing="0" cellpadding="1" width="100%"><tr><td><table border="0" cellspacing="0" cellpadding="1" width="100%" bgcolor="#000000"><tr><td><table border="0" cellpadding="3" cellspacing="1" width="100%"><tr><td bgcolor="#fffacd">
				89	<p>Here is a real size example, where the actual content of the application
				90	data is not kept in the DOM tree but uses internal structures. It is based on
				91	a proposal to keep a database of jobs related to Gnome, with an XML based
				92	storage structure. Here is an <a href="gjobs.xml">XML encoded jobs
				93	base</a>:</p>
				94	<pre><?xml version="1.0"?>
				95	<gjob:Helping xmlns:gjob="http://www.gnome.org/some-location">
				96	<gjob:Jobs>
				97
				98	<gjob:Job>
				99	<gjob:Project ID="3"/>
				100	<gjob:Application>GBackup</gjob:Application>
				101	<gjob:Category>Development</gjob:Category>
				102
				103	<gjob:Update>
				104	<gjob:Status>Open</gjob:Status>
				105	<gjob:Modified>Mon, 07 Jun 1999 20:27:45 -0400 MET DST</gjob:Modified>
				106	<gjob:Salary>USD 0.00</gjob:Salary>
				107	</gjob:Update>
				108
				109	<gjob:Developers>
				110	<gjob:Developer>
				111	</gjob:Developer>
				112	</gjob:Developers>
				113
				114	<gjob:Contact>
				115	<gjob:Person>Nathan Clemons</gjob:Person>
				116	<gjob:Email>nathan@windsofstorm.net</gjob:Email>
				117	<gjob:Company>
				118	</gjob:Company>
				119	<gjob:Organisation>
				120	</gjob:Organisation>
				121	<gjob:Webpage>
				122	</gjob:Webpage>
				123	<gjob:Snailmail>
				124	</gjob:Snailmail>
				125	<gjob:Phone>
				126	</gjob:Phone>
				127	</gjob:Contact>
				128
				129	<gjob:Requirements>
				130	The program should be released as free software, under the GPL.
				131	</gjob:Requirements>
				132
				133	<gjob:Skills>
				134	</gjob:Skills>
				135
				136	<gjob:Details>
				137	A GNOME based system that will allow a superuser to configure
				138	compressed and uncompressed files and/or file systems to be backed
				139	up with a supported media in the system. This should be able to
				140	perform via find commands generating a list of files that are passed
				141	to tar, dd, cpio, cp, gzip, etc., to be directed to the tape machine
				142	or via operations performed on the filesystem itself. Email
				143	notification and GUI status display very important.
				144	</gjob:Details>
				145
				146	</gjob:Job>
				147
				148	</gjob:Jobs>
				149	</gjob:Helping></pre>
				150	<p>While loading the XML file into an internal DOM tree is a matter of
Daniel Veillard	a8a89fe	2002-04-12 21:03:34 +0000	[diff] [blame]	151	calling only a couple of functions, browsing the tree to gather the ata and
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	152	generate the internal structures is harder, and more error prone.</p>
				153	<p>The suggested principle is to be tolerant with respect to the input
				154	structure. For example, the ordering of the attributes is not significant,
				155	the XML specification is clear about it. It's also usually a good idea not to
				156	depend on the order of the children of a given node, unless it really makes
				157	things harder. Here is some code to parse the information for a person:</p>
				158	<pre>/*
				159	* A person record
				160	*/
				161	typedef struct person {
				162	char *name;
				163	char *email;
				164	char *company;
				165	char *organisation;
				166	char *smail;
				167	char *webPage;
				168	char *phone;
				169	} person, *personPtr;
				170
				171	/*
				172	* And the code needed to parse it
				173	*/
				174	personPtr parsePerson(xmlDocPtr doc, xmlNsPtr ns, xmlNodePtr cur) {
				175	personPtr ret = NULL;
				176
				177	DEBUG("parsePerson\n");
				178	/*
				179	* allocate the struct
				180	*/
				181	ret = (personPtr) malloc(sizeof(person));
				182	if (ret == NULL) {
				183	fprintf(stderr,"out of memory\n");
				184	return(NULL);
				185	}
				186	memset(ret, 0, sizeof(person));
				187
				188	/* We don't care what the top level element name is */
				189	cur = cur->xmlChildrenNode;
				190	while (cur != NULL) {
				191	if ((!strcmp(cur->name, "Person")) && (cur->ns == ns))
				192	ret->name = xmlNodeListGetString(doc, cur->xmlChildrenNode, 1);
				193	if ((!strcmp(cur->name, "Email")) && (cur->ns == ns))
				194	ret->email = xmlNodeListGetString(doc, cur->xmlChildrenNode, 1);
				195	cur = cur->next;
				196	}
				197
				198	return(ret);
				199	}</pre>
				200	<p>Here are a couple of things to notice:</p>
				201	<ul>
				202	<li>Usually a recursive parsing style is the more convenient one: XML data
				203	is by nature subject to repetitive constructs and usually exibits highly
				204	stuctured patterns.</li>
				205	<li>The two arguments of type <em>xmlDocPtr</em> and <em>xmlNsPtr</em>,
				206	i.e. the pointer to the global XML document and the namespace reserved to
				207	the application. Document wide information are needed for example to
				208	decode entities and it's a good coding practice to define a namespace for
				209	your application set of data and test that the element and attributes
				210	you're analyzing actually pertains to your application space. This is
				211	done by a simple equality test (cur->ns == ns).</li>
				212	<li>To retrieve text and attributes value, you can use the function
				213	<em>xmlNodeListGetString</em> to gather all the text and entity reference
				214	nodes generated by the DOM output and produce an single text string.</li>
				215	</ul>
				216	<p>Here is another piece of code used to parse another level of the
				217	structure:</p>
				218	<pre>#include <libxml/tree.h>
				219	/*
				220	* a Description for a Job
				221	*/
				222	typedef struct job {
				223	char *projectID;
				224	char *application;
				225	char *category;
				226	personPtr contact;
				227	int nbDevelopers;
				228	personPtr developers[100]; /* using dynamic alloc is left as an exercise */
				229	} job, *jobPtr;
				230
				231	/*
				232	* And the code needed to parse it
				233	*/
				234	jobPtr parseJob(xmlDocPtr doc, xmlNsPtr ns, xmlNodePtr cur) {
				235	jobPtr ret = NULL;
				236
				237	DEBUG("parseJob\n");
				238	/*
				239	* allocate the struct
				240	*/
				241	ret = (jobPtr) malloc(sizeof(job));
				242	if (ret == NULL) {
				243	fprintf(stderr,"out of memory\n");
				244	return(NULL);
				245	}
				246	memset(ret, 0, sizeof(job));
				247
				248	/* We don't care what the top level element name is */
				249	cur = cur->xmlChildrenNode;
				250	while (cur != NULL) {
				251
				252	if ((!strcmp(cur->name, "Project")) && (cur->ns == ns)) {
				253	ret->projectID = xmlGetProp(cur, "ID");
				254	if (ret->projectID == NULL) {
				255	fprintf(stderr, "Project has no ID\n");
				256	}
				257	}
				258	if ((!strcmp(cur->name, "Application")) && (cur->ns == ns))
				259	ret->application = xmlNodeListGetString(doc, cur->xmlChildrenNode, 1);
				260	if ((!strcmp(cur->name, "Category")) && (cur->ns == ns))
				261	ret->category = xmlNodeListGetString(doc, cur->xmlChildrenNode, 1);
				262	if ((!strcmp(cur->name, "Contact")) && (cur->ns == ns))
				263	ret->contact = parsePerson(doc, ns, cur);
				264	cur = cur->next;
				265	}
				266
				267	return(ret);
				268	}</pre>
				269	<p>Once you are used to it, writing this kind of code is quite simple, but
				270	boring. Ultimately, it could be possble to write stubbers taking either C
				271	data structure definitions, a set of XML examples or an XML DTD and produce
				272	the code needed to import and export the content between C data and XML
				273	storage. This is left as an exercise to the reader :-)</p>
				274	<p>Feel free to use <a href="example/gjobread.c">the code for the full C
				275	parsing example</a> as a template, it is also available with Makefile in the
				276	Gnome CVS base under gnome-xml/example</p>
Daniel Veillard	3f4c40f	2002-02-13 09:19:28 +0000	[diff] [blame]	277	<p><a href="bugs.html">Daniel Veillard</a></p>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	278	</td></tr></table></td></tr></table></td></tr></table></td>
				279	</tr></table></td></tr></table>
				280	</body>
				281	</html>