C++中处理XML文件中华网络安全联盟 www.77941.com

先说一下在MSDN哪里找文档吧，往下看的时候也好有个参考：在Index里打：Windows Media Services 9 Series SDK=>Programming Reference=>Programming Reference (C++)=>XML DOM Interfaces (C++)。什么？Windows Media？呵呵，不错，我觉得这个guide反而是最清楚的，你直接找MSXML，得到的结果，我觉得还没这个好。

在C程序里调用MSXML基本就是一堆COM接口，不过在Visual Studio里操作先要做点简单的设置：

在你的Project里Add References=>COM标签=>Microsoft XML v4.0，5.0其实也有了，但因为是和Office一起发布的，觉得有点怪，不想用，反正也未必用什么很怪异的功能，4.0可以了。

然后在加入这两行：

#include <msxml2.h>
#import <msxml4.dll>

头文件和dll库。什么？在哪里加？头文件或者c/cpp文件啊，哪里合适放哪儿。

然后就开始编程了，先定义两个必用的变量：

IXMLDOMDocumentPtr xmlFile = NULL;
IXMLDOMElement* xmlRoot = NULL;

为什么是必用的？　　汗．．．

第一步当然是初始化COM：

if(FAILED(CoInitialize(NULL))) ....

接下来初始化xmlFile对象：

if(FAILED(xmlFile.CreateInstance("Msxml2.DOMDocument.4.0"))) ...

然后就可以加载xml文件了：

_variant_t varXml(L"C:\\test.xml"); //L for unicode
VARIANT_BOOL varOut;
xmlFile->load(varXml, &varOut);

取得root element：

xmlFile->get_documentElement(&xmlRoot))

取得第一级element：

IXMLDOMNodeList* xmlChildNodes = NULL;
xmlRoot->get_childNodes(&xmlChildNodes);

遍历所有第一级element:

IXMLDOMNode* currentNode = NULL;
while(!FAILED(xmlChildNodes->nextNode(&currentNode)) && currentNode != NULL)
{
//do something
}

取得当前element的名称：

BSTR nodeName;
currentNode->get_nodeName(&nodeName);

取得当前element的一个attribute（假设这个attribute叫type）的值：

IXMLDOMNamedNodeMap* attributes = NULL;
IXMLDOMNode* attributeName = NULL;
_bstr_t bstrAttributeName = "type";
BSTR nameVal;
currentNode->get_attributes(&attributes);
attributes->getNamedItem(bstrAttributeName, &attributeName);
attributeName->get_text(&nameVal);

需要注意的是，你要记住释放所有的借口，IXMLDOM***->Release()，这可不是.NET，有人帮你GC，你得自己调用Release()来减reference count，it's COM, remember?

好了，大致就这样，顺便提一下XPath：

_bstr_t bstrXmlQuery = L"/books/book[@type=scifi and @author=fox]";
IXMLDOMNodeList* nodes = NULL;
if(FAILED(xmlRoot->selectNodes(bstrXmlQuery, &nodes)) || FAILED(nodes->get_length(&length)) || length == 0)
//no match found or something went wrong
else
//match found

上面是找这样的node:

具体的XPath语法就查手册吧，到处都有。

哦，对了，忘了说：如果你全部用ATL的类的话，借口的调用会简单一点，不过很容易转换的，比如：

IXMLDOMDocument* 对应 IXMLDOMDocumentPtr（我这里用了），其他基本也是加个Ptr，我不废话了。

最后提供一个sample，我临时攒的。工作的时候写的程序当然不能拿来贴的，呵呵。这个sample基本就是遍历整个xml，然后报告一遍文件的结构，对每个node，如果它有一个叫id的attribute，就同时打印id的值。If you want the complete VS project, shoot me an email. But I guess no one really needs it anyway, right, : )

#include "stdafx.h"
#include <windows.h>
#include <msxml2.h>
#import <msxml4.dll>

HANDLE logFile = NULL;

#define INDENT 4

#define TESTHR(hr) \
{ \
if(FAILED(hr)) goto fail; \
}

void PrintChild(IXMLDOMNodeList* nodeList, int level)
{
if(nodeList == NULL)
return;

IXMLDOMNode* currentNode = NULL;
IXMLDOMNodeList* childNodes = NULL;
IXMLDOMNamedNodeMap* attributes = NULL;
IXMLDOMNode* attributeID = NULL;

while(!FAILED(nodeList->nextNode(&currentNode)) && currentNode != NULL)
{
BSTR nodeName;
TESTHR(currentNode->get_nodeName(&nodeName));
DWORD dwBytesWritten;
for(int i=0; i<level*INDENT; i++)
WriteFile(logFile, L" ", (DWORD)(sizeof(WCHAR)), &dwBytesWritten, NULL);

//WCHAR msg[MAX_SIZE];
//wsprintf(msg, L"%s ", nodeName);
WriteFile(logFile, nodeName, (DWORD)(wcslen(nodeName)*sizeof(WCHAR)), &dwBytesWritten, NULL);

TESTHR(currentNode->get_attributes(&attributes));
if(attributes!=NULL)
{
_bstr_t bstrAttributeName = "id";
BSTR idVal;
TESTHR(attributes->getNamedItem(bstrAttributeName, &attributeID));
if(attributeID != NULL)
{
TESTHR(attributeID->get_text(&idVal));
WriteFile(logFile, L" ", (DWORD)(sizeof(WCHAR)), &dwBytesWritten, NULL);
WriteFile(logFile, idVal, (DWORD)(wcslen(idVal)*sizeof(WCHAR)), &dwBytesWritten, NULL);
WriteFile(logFile, L"\r\n", (DWORD)(2*sizeof(WCHAR)), &dwBytesWritten, NULL);
attributeID->Release(); attributeID = NULL;
}
else
{
WriteFile(logFile, L"\r\n", (DWORD)(2*sizeof(WCHAR)), &dwBytesWritten, NULL);
}
attributes->Release(); attributes = NULL;

}
else
{
WriteFile(logFile, L"\r\n", (DWORD)(2*sizeof(WCHAR)), &dwBytesWritten, NULL);
}

TESTHR(currentNode->get_childNodes(&childNodes));
PrintChild(childNodes, level+1);
currentNode=NULL;
}

fail:
if(childNodes!=NULL)
childNodes->Release();
if(attributeID!=NULL)
attributeID->Release();
if(attributes!=NULL)
attributes->Release();
if(currentNode != NULL)
currentNode->Release();
}

int _tmain(int argc, _TCHAR* argv[])
{

IXMLDOMDocumentPtr xmlFile = NULL;
IXMLDOMElement* xmlRoot = NULL;
_variant_t varXml(L"C:\\demo1.xml");

logFile = CreateFile(L"log.txt", GENERIC_WRITE, 0, NULL, CREATE_ALWAYS, FILE_ATTRIBUTE_NORMAL, NULL);
if(logFile == INVALID_HANDLE_VALUE)
goto fail;

TESTHR(CoInitialize(NULL));

TESTHR(xmlFile.CreateInstance("Msxml2.DOMDocument.4.0"));

VARIANT_BOOL varOut;
TESTHR(xmlFile->load(varXml, &varOut));

TESTHR(xmlFile->get_documentElement(&xmlRoot));

BSTR rootName;
DWORD dwBytesWritten;
TESTHR(xmlRoot->get_nodeName(&rootName));
WriteFile(logFile, rootName, (DWORD)(wcslen(rootName)*sizeof(WCHAR)), &dwBytesWritten, NULL);
WriteFile(logFile, L"\r\n", (DWORD)(2*sizeof(WCHAR)), &dwBytesWritten, NULL);

IXMLDOMNodeList* xmlChildNodes = NULL;
TESTHR(xmlRoot->get_childNodes(&xmlChildNodes));

PrintChild(xmlChildNodes, 2);

fail:
if(logFile != INVALID_HANDLE_VALUE)
CloseHandle(logFile);
if(xmlChildNodes!=NULL)
xmlChildNodes->Release();
if(xmlRoot!=NULL)
xmlRoot->Release();
return 0;
}

字体：小大