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

blob: df8e9ed58888b71290020e1652806177a031dd34 [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">
				5	<style type="text/css"><!--
Daniel Veillard	373a475	2002-02-21 14:46:29 +0000	[diff] [blame^]	6	TD {font-family: Verdana,Arial,Helvetica}
				7	BODY {font-family: Verdana,Arial,Helvetica; margin-top: 2em; margin-left: 0em; margin-right: 0em}
				8	H1 {font-family: Verdana,Arial,Helvetica}
				9	H2 {font-family: Verdana,Arial,Helvetica}
				10	H3 {font-family: Verdana,Arial,Helvetica}
Daniel Veillard	b8cfbd1	2001-10-25 10:53:28 +0000	[diff] [blame]	11	A:link, A:visited, A:active { text-decoration: underline }
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	12	--></style>
				13	<title>A real example</title>
				14	</head>
				15	<body bgcolor="#8b7765" text="#000000" link="#000000" vlink="#000000">
				16	<table border="0" width="100%" cellpadding="5" cellspacing="0" align="center"><tr>
				17	<td width="180">
				18	<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>
				19	</td>
				20	<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">
				21	<h1>The XML C library for Gnome</h1>
				22	<h2>A real example</h2>
				23	</td></tr></table></td></tr></table></td>
				24	</tr></table>
				25	<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]	26	<td valign="top" width="200" bgcolor="#8b7765"><table border="0" cellspacing="0" cellpadding="1" width="100%" bgcolor="#000000"><tr><td>
				27	<table width="100%" border="0" cellspacing="1" cellpadding="3">
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	28	<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]	29	<tr><td bgcolor="#fffacd"><ul>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	30	<li><a href="index.html">Home</a></li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	31	<li><a href="intro.html">Introduction</a></li>
Daniel Veillard	b8cfbd1	2001-10-25 10:53:28 +0000	[diff] [blame]	32	<li><a href="FAQ.html">FAQ</a></li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	33	<li><a href="docs.html">Documentation</a></li>
				34	<li><a href="bugs.html">Reporting bugs and getting help</a></li>
				35	<li><a href="help.html">How to help</a></li>
				36	<li><a href="downloads.html">Downloads</a></li>
				37	<li><a href="news.html">News</a></li>
Daniel Veillard	7b602b4	2002-01-08 13:26:00 +0000	[diff] [blame]	38	<li><a href="XMLinfo.html">XML</a></li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	39	<li><a href="XSLT.html">XSLT</a></li>
Daniel Veillard	6dbcaf8	2002-02-20 14:37:47 +0000	[diff] [blame]	40	<li><a href="python.html">Python and bindings</a></li>
Daniel Veillard	b8cfbd1	2001-10-25 10:53:28 +0000	[diff] [blame]	41	<li><a href="architecture.html">libxml architecture</a></li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	42	<li><a href="tree.html">The tree output</a></li>
				43	<li><a href="interface.html">The SAX interface</a></li>
Daniel Veillard	b8cfbd1	2001-10-25 10:53:28 +0000	[diff] [blame]	44	<li><a href="xmldtd.html">Validation & DTDs</a></li>
				45	<li><a href="xmlmem.html">Memory Management</a></li>
				46	<li><a href="encoding.html">Encodings support</a></li>
				47	<li><a href="xmlio.html">I/O Interfaces</a></li>
				48	<li><a href="catalog.html">Catalog support</a></li>
				49	<li><a href="library.html">The parser interfaces</a></li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	50	<li><a href="entities.html">Entities or no entities</a></li>
				51	<li><a href="namespaces.html">Namespaces</a></li>
Daniel Veillard	b8cfbd1	2001-10-25 10:53:28 +0000	[diff] [blame]	52	<li><a href="upgrade.html">Upgrading 1.x code</a></li>
Daniel Veillard	52dcab3	2001-10-30 12:51:17 +0000	[diff] [blame]	53	<li><a href="threads.html">Thread safety</a></li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	54	<li><a href="DOM.html">DOM Principles</a></li>
				55	<li><a href="example.html">A real example</a></li>
				56	<li><a href="contribs.html">Contributions</a></li>
Daniel Veillard	594cf0b	2001-10-25 08:09:12 +0000	[diff] [blame]	57	<li>
				58	<a href="xml.html">flat page</a>, <a href="site.xsl">stylesheet</a>
				59	</li>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	60	</ul></td></tr>
Daniel Veillard	594cf0b	2001-10-25 08:09:12 +0000	[diff] [blame]	61	</table>
				62	<table width="100%" border="0" cellspacing="1" cellpadding="3">
Daniel Veillard	3bf65be	2002-01-23 12:36:34 +0000	[diff] [blame]	63	<tr><td colspan="1" bgcolor="#eecfa1" align="center"><center><b>API Indexes</b></center></td></tr>
				64	<tr><td bgcolor="#fffacd"><ul>
Daniel Veillard	f859256	2002-01-23 17:58:17 +0000	[diff] [blame]	65	<li><a href="APIchunk0.html">Alphabetic</a></li>
Daniel Veillard	3bf65be	2002-01-23 12:36:34 +0000	[diff] [blame]	66	<li><a href="APIconstructors.html">Constructors</a></li>
				67	<li><a href="APIfunctions.html">Functions/Types</a></li>
				68	<li><a href="APIfiles.html">Modules</a></li>
				69	<li><a href="APIsymbols.html">Symbols</a></li>
				70	</ul></td></tr>
				71	</table>
				72	<table width="100%" border="0" cellspacing="1" cellpadding="3">
Daniel Veillard	594cf0b	2001-10-25 08:09:12 +0000	[diff] [blame]	73	<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]	74	<tr><td bgcolor="#fffacd"><ul>
Daniel Veillard	594cf0b	2001-10-25 08:09:12 +0000	[diff] [blame]	75	<li><a href="http://mail.gnome.org/archives/xml/">Mail archive</a></li>
				76	<li><a href="http://xmlsoft.org/XSLT/">XSLT libxslt</a></li>
Daniel Veillard	4a85920	2002-01-08 11:49:22 +0000	[diff] [blame]	77	<li><a href="http://phd.cs.unibo.it/gdome2/">DOM gdome2</a></li>
Daniel Veillard	594cf0b	2001-10-25 08:09:12 +0000	[diff] [blame]	78	<li><a href="ftp://xmlsoft.org/">FTP</a></li>
				79	<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]	80	<li><a href="http://garypennington.net/libxml2/">Solaris binaries</a></li>
Daniel Veillard	c6271d2	2001-10-27 07:50:58 +0000	[diff] [blame]	81	<li><a href="http://bugzilla.gnome.org/buglist.cgi?product=libxml">Bug Tracker</a></li>
Daniel Veillard	594cf0b	2001-10-25 08:09:12 +0000	[diff] [blame]	82	</ul></td></tr>
				83	</table>
				84	</td></tr></table></td>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	85	<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">
				86	<p>Here is a real size example, where the actual content of the application
				87	data is not kept in the DOM tree but uses internal structures. It is based on
				88	a proposal to keep a database of jobs related to Gnome, with an XML based
				89	storage structure. Here is an <a href="gjobs.xml">XML encoded jobs
				90	base</a>:</p>
				91	<pre><?xml version="1.0"?>
				92	<gjob:Helping xmlns:gjob="http://www.gnome.org/some-location">
				93	<gjob:Jobs>
				94
				95	<gjob:Job>
				96	<gjob:Project ID="3"/>
				97	<gjob:Application>GBackup</gjob:Application>
				98	<gjob:Category>Development</gjob:Category>
				99
				100	<gjob:Update>
				101	<gjob:Status>Open</gjob:Status>
				102	<gjob:Modified>Mon, 07 Jun 1999 20:27:45 -0400 MET DST</gjob:Modified>
				103	<gjob:Salary>USD 0.00</gjob:Salary>
				104	</gjob:Update>
				105
				106	<gjob:Developers>
				107	<gjob:Developer>
				108	</gjob:Developer>
				109	</gjob:Developers>
				110
				111	<gjob:Contact>
				112	<gjob:Person>Nathan Clemons</gjob:Person>
				113	<gjob:Email>nathan@windsofstorm.net</gjob:Email>
				114	<gjob:Company>
				115	</gjob:Company>
				116	<gjob:Organisation>
				117	</gjob:Organisation>
				118	<gjob:Webpage>
				119	</gjob:Webpage>
				120	<gjob:Snailmail>
				121	</gjob:Snailmail>
				122	<gjob:Phone>
				123	</gjob:Phone>
				124	</gjob:Contact>
				125
				126	<gjob:Requirements>
				127	The program should be released as free software, under the GPL.
				128	</gjob:Requirements>
				129
				130	<gjob:Skills>
				131	</gjob:Skills>
				132
				133	<gjob:Details>
				134	A GNOME based system that will allow a superuser to configure
				135	compressed and uncompressed files and/or file systems to be backed
				136	up with a supported media in the system. This should be able to
				137	perform via find commands generating a list of files that are passed
				138	to tar, dd, cpio, cp, gzip, etc., to be directed to the tape machine
				139	or via operations performed on the filesystem itself. Email
				140	notification and GUI status display very important.
				141	</gjob:Details>
				142
				143	</gjob:Job>
				144
				145	</gjob:Jobs>
				146	</gjob:Helping></pre>
				147	<p>While loading the XML file into an internal DOM tree is a matter of
				148	calling only a couple of functions, browsing the tree to gather the ata and
				149	generate the internal structures is harder, and more error prone.</p>
				150	<p>The suggested principle is to be tolerant with respect to the input
				151	structure. For example, the ordering of the attributes is not significant,
				152	the XML specification is clear about it. It's also usually a good idea not to
				153	depend on the order of the children of a given node, unless it really makes
				154	things harder. Here is some code to parse the information for a person:</p>
				155	<pre>/*
				156	* A person record
				157	*/
				158	typedef struct person {
				159	char *name;
				160	char *email;
				161	char *company;
				162	char *organisation;
				163	char *smail;
				164	char *webPage;
				165	char *phone;
				166	} person, *personPtr;
				167
				168	/*
				169	* And the code needed to parse it
				170	*/
				171	personPtr parsePerson(xmlDocPtr doc, xmlNsPtr ns, xmlNodePtr cur) {
				172	personPtr ret = NULL;
				173
				174	DEBUG("parsePerson\n");
				175	/*
				176	* allocate the struct
				177	*/
				178	ret = (personPtr) malloc(sizeof(person));
				179	if (ret == NULL) {
				180	fprintf(stderr,"out of memory\n");
				181	return(NULL);
				182	}
				183	memset(ret, 0, sizeof(person));
				184
				185	/* We don't care what the top level element name is */
				186	cur = cur->xmlChildrenNode;
				187	while (cur != NULL) {
				188	if ((!strcmp(cur->name, "Person")) && (cur->ns == ns))
				189	ret->name = xmlNodeListGetString(doc, cur->xmlChildrenNode, 1);
				190	if ((!strcmp(cur->name, "Email")) && (cur->ns == ns))
				191	ret->email = xmlNodeListGetString(doc, cur->xmlChildrenNode, 1);
				192	cur = cur->next;
				193	}
				194
				195	return(ret);
				196	}</pre>
				197	<p>Here are a couple of things to notice:</p>
				198	<ul>
				199	<li>Usually a recursive parsing style is the more convenient one: XML data
				200	is by nature subject to repetitive constructs and usually exibits highly
				201	stuctured patterns.</li>
				202	<li>The two arguments of type <em>xmlDocPtr</em> and <em>xmlNsPtr</em>,
				203	i.e. the pointer to the global XML document and the namespace reserved to
				204	the application. Document wide information are needed for example to
				205	decode entities and it's a good coding practice to define a namespace for
				206	your application set of data and test that the element and attributes
				207	you're analyzing actually pertains to your application space. This is
				208	done by a simple equality test (cur->ns == ns).</li>
				209	<li>To retrieve text and attributes value, you can use the function
				210	<em>xmlNodeListGetString</em> to gather all the text and entity reference
				211	nodes generated by the DOM output and produce an single text string.</li>
				212	</ul>
				213	<p>Here is another piece of code used to parse another level of the
				214	structure:</p>
				215	<pre>#include <libxml/tree.h>
				216	/*
				217	* a Description for a Job
				218	*/
				219	typedef struct job {
				220	char *projectID;
				221	char *application;
				222	char *category;
				223	personPtr contact;
				224	int nbDevelopers;
				225	personPtr developers[100]; /* using dynamic alloc is left as an exercise */
				226	} job, *jobPtr;
				227
				228	/*
				229	* And the code needed to parse it
				230	*/
				231	jobPtr parseJob(xmlDocPtr doc, xmlNsPtr ns, xmlNodePtr cur) {
				232	jobPtr ret = NULL;
				233
				234	DEBUG("parseJob\n");
				235	/*
				236	* allocate the struct
				237	*/
				238	ret = (jobPtr) malloc(sizeof(job));
				239	if (ret == NULL) {
				240	fprintf(stderr,"out of memory\n");
				241	return(NULL);
				242	}
				243	memset(ret, 0, sizeof(job));
				244
				245	/* We don't care what the top level element name is */
				246	cur = cur->xmlChildrenNode;
				247	while (cur != NULL) {
				248
				249	if ((!strcmp(cur->name, "Project")) && (cur->ns == ns)) {
				250	ret->projectID = xmlGetProp(cur, "ID");
				251	if (ret->projectID == NULL) {
				252	fprintf(stderr, "Project has no ID\n");
				253	}
				254	}
				255	if ((!strcmp(cur->name, "Application")) && (cur->ns == ns))
				256	ret->application = xmlNodeListGetString(doc, cur->xmlChildrenNode, 1);
				257	if ((!strcmp(cur->name, "Category")) && (cur->ns == ns))
				258	ret->category = xmlNodeListGetString(doc, cur->xmlChildrenNode, 1);
				259	if ((!strcmp(cur->name, "Contact")) && (cur->ns == ns))
				260	ret->contact = parsePerson(doc, ns, cur);
				261	cur = cur->next;
				262	}
				263
				264	return(ret);
				265	}</pre>
				266	<p>Once you are used to it, writing this kind of code is quite simple, but
				267	boring. Ultimately, it could be possble to write stubbers taking either C
				268	data structure definitions, a set of XML examples or an XML DTD and produce
				269	the code needed to import and export the content between C data and XML
				270	storage. This is left as an exercise to the reader :-)</p>
				271	<p>Feel free to use <a href="example/gjobread.c">the code for the full C
				272	parsing example</a> as a template, it is also available with Makefile in the
				273	Gnome CVS base under gnome-xml/example</p>
Daniel Veillard	3f4c40f	2002-02-13 09:19:28 +0000	[diff] [blame]	274	<p><a href="bugs.html">Daniel Veillard</a></p>
Daniel Veillard	c948420	2001-10-24 12:35:52 +0000	[diff] [blame]	275	</td></tr></table></td></tr></table></td></tr></table></td>
				276	</tr></table></td></tr></table>
				277	</body>
				278	</html>