Linux 下C/C++解析XML文件（一）
Linux 下C/C++解析XML文件（一）
在工程项目中我们的项目需要根据不同的环境配置不同的程序参数，而常用的两种文件分别是ini文件和XML文件，接下来我来分析下在Linux下解析XML文件过程。
我们首先使用linux自带的libxml2来解析XML文件。
1. libxml2数据结构
在libxml2中比较重要的数据结构是xmlNodePtr，它在libxml/tree.h中定义为
/**
* xmlNode:
*
* A node in an XML tree.
*/
typedef struct _xmlNode xmlNode;
typedef xmlNode *xmlNodePtr;
struct _xmlNode {
void *_private; /* application data */
xmlElementType type; /* type number, must be second ! */
const xmlChar *name; /* the name of the node, or the entity */
struct _xmlNode *children; /* parent->childs link */
struct _xmlNode *last; /* last child link */
struct _xmlNode *parent; /* child->parent link */
struct _xmlNode *next; /* next sibling link */
struct _xmlNode *prev; /* previous sibling link */
struct _xmlDoc *doc; /* the containing document */
/* End of common part */
xmlNs *ns; /* pointer to the associated namespace */
xmlChar *content; /* the content */
struct _xmlAttr *properties;/* properties list */
xmlNs *nsDef; /* namespace definitions on this node */
void *psvi; /* for type/PSVI informations */
unsigned short line; /* line number */
unsigned short extra; /* extra data for XPath/XSLT */
}; 2. 解析代码
#include
#include
#include
#include
#include
/////////////////////////////////////////////////
//
#if 0
int main(int argc, char* argv[])
{
xmlDocPtr doc; //定义解析文档指针
xmlNodePtr curNode; //定义结点指针(你需要它为了在各个结点间移动)
xmlChar *szKey; //临时字符串变量
char *szDocName;
if (argc <= 1)
{
printf("Usage: %s docname\n", argv[0]);
return(0);
}
szDocName = argv[1];
doc = xmlReadFile(szDocName,"UTF-8",XML_PARSE_RECOVER); //解析文件
//检查解析文档是否成功，如果不成功，libxml将指一个注册的错误并停止。
//一个常见错误是不适当的编码。XML标准文档除了用UTF-8或UTF-16外还可用其它编码保存。
//如果文档是这样，libxml将自动地为你转换到UTF-8。更多关于XML编码信息包含在XML标准中.
if (NULL == doc)
{
fprintf(stderr, "xmlParseFile Error in %s %d\n",__FUNCTION__, __LINE__);
return -1;
}
curNode = xmlDocGetRootElement(doc); //确定文档根元素
if (NULL == curNode)
{
fprintf(stderr, "xmlDocGetRootElement Error in %s %d\n", __FUNCTION__, __LINE__);
xmlFreeDoc(doc);
return -1;
}
printf("Node name is %s!\n", pRoot->name);
if (xmlStrcmp(curNode->name, BAD_CAST "root"))
{
fprintf(stderr,"document of the wrong type, root node != root\n");
xmlFreeDoc(doc);
return -1;
}
curNode = curNode->xmlChildrenNode; //子节点集是链表
xmlNodePtr propNodePtr = curNode;
while(curNode != NULL)
{
//取出节点中的内容
if ((!xmlStrcmp(curNode->name, (const xmlChar *)"monitor")))
{
szKey = xmlNodeGetContent(curNode);
printf("newNode1: %s\n", szKey);
xmlFree(szKey);
}
//查找带有属性attribute的节点
if (xmlHasProp(curNode,BAD_CAST "attribute"))
{
propNodePtr = curNode;
}
curNode = curNode->next;
}
//查找属性
xmlAttrPtr attrPtr = propNodePtr->properties; //属性集是链表
while (attrPtr != NULL)
{
if (!xmlStrcmp(attrPtr->name, BAD_CAST "attribute"))
{
xmlChar* szAttr = xmlGetProp(propNodePtr,BAD_CAST "attribute");
//szAttr要调用函数xmlFree(szAttr)手动删除否则会发生内存泄露。
// cout<<"get attribute = "<
xmlFree(szAttr);
}
attrPtr = attrPtr->next;
}
xmlFreeDoc(doc);
return 0;
}
#endif
int main(int argc, const char *argv[])
{
if(2 != argc)
{
fprintf(stdout, "Please statrt this program with %s xmlfilepath!", argv[0]);
return 1;
}
xmlDocPtr pDoc = xmlReadFile(argv[1], "UTF-8", XML_PARSE_RECOVER); //获取XML文档的指针
if(NULL == pDoc)
{
fprintf(stderr, "xmlParseFile Error in %s %d\n",__FUNCTION__, __LINE__);
return -1;
}
xmlNodePtr pRoot = xmlDocGetRootElement(pDoc);//获取根节点
if(NULL == pRoot)
{
fprintf(stderr, "xmlDocGetRootElement Error in %s %d\n", __FUNCTION__, __LINE__);
xmlFreeDoc(pDoc);
return -1;
}
printf("Node name is %s!\n", pRoot->name);
xmlNodePtr pFirst = pRoot->xmlChildrenNode;//获取子节点
while(NULL != pFirst)
{
if(!xmlStrcmp(pFirst->name, (const xmlChar *)("monitor")))
{
xmlNodePtr pSecond = pFirst->xmlChildrenNode;
while(NULL != pSecond)
{
xmlChar* value= NULL;
if(!xmlStrcmp(pSecond->name, (const xmlChar *)("name")))
{
value = xmlNodeGetContent(pSecond);
printf("\n%s-->%s\n", pSecond->name, value);
xmlFree(value);
value = NULL;
}
if(!xmlStrcmp(pSecond->name, (const xmlChar *)("path")))
{
value = xmlNodeGetContent(pSecond);
printf("\n%s-->%s\n", pSecond->name, value);
xmlFree(value);
value = NULL;
}
if(!xmlStrcmp(pSecond->name, (const xmlChar *)("log")))
{
xmlNodePtr pThird = pSecond->xmlChildrenNode;
while(NULL != pThird)
{
if(!xmlStrcmp(pThird->name, (const xmlChar *)("folderpath")))
{
value = xmlNodeGetContent(pThird);
printf("\n%s-->%s\n", pThird->name, value);
xmlFree(value);
value = NULL;
}
if(!xmlStrcmp(pThird->name, (const xmlChar *)("savedays")))
{
value = xmlNodeGetContent(pThird);
printf("\n%s-->%s\n", pThird->name, value);
xmlFree(value);
value = NULL;
}
pThird = pThird->next;
}
}
pSecond = pSecond->next;
}
}
pFirst = pFirst->next;
}
xmlFreeDoc(pDoc);
return 0;
} 3. 被解析xml文件
<root>
<monitor>
<name>ftpname>
<path>/usr/bin/path>
<interval>30interval>
<restartwait>30restartwait>
<ip>127.0.0.1ip>
<port>9878port>
<request>1;monitorrequest>
<response>The ftp is working ok.response>
<log>
<folderpath>log/folderpath>
<savedays>2savedays>
log>
monitor>
root> 4. 编译
#!/bin/sh
gcc test.c -o test -lxml2 -I/usr/include/libxml25. 结果
sean@sean:~/tmp/xml2$ ./test test-1.xml
Node name is root!
name-->ftp
path-->/usr/bin/
folderpath-->log/
savedays-->2