c++ - 使用 C++/MSXML 中的变音符号根据嵌入式 XSD 资源验证 XML 文件

Question

我想使用 MSXML6 解析器验证 C++ 中的 XML 文件，并已按照 http://msdn.microsoft.com/en-us/library/ms762774%28v=vs.85%29.aspx 上的说明进行操作.但是，我正在处理的项目需要将 XSD 架构嵌入到二进制文件中。

这是应该验证的 XML 文件(为演示目的简化了所有文件):

<?xml version="1.0" encoding="UTF-8"?>
<Document xsi:schemaLocation="urn:test schema.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="urn:test">
  <Party>
    <Id>1</Id>
    <Name>Bob</Name>
    <Salary>100.00</Salary>
  </Party>
  <Party>
    <Id>2</Id>
    <Name>Alice</Name>
    <Salary>200.00</Salary>
  </Party>
  <Party>
    <Id>3</Id>
    <Name>Günther</Name>
    <Salary>300.00</Salary>
  </Party>
</Document>

这是 XSD 架构:

<?xml version="1.0" encoding="utf-8" standalone="no"?>
<xs:schema xmlns="urn:test" xmlns:xs="http://www.w3.org/2001/XMLSchema" targetNamespace="urn:test" elementFormDefault="qualified">

  <xs:simpleType name="NameType">
    <xs:restriction base="xs:string">
      <xs:pattern value="([A-Za-z0-9ÄÖÜäöü]){1,10}"/>
    </xs:restriction>
  </xs:simpleType>

  <xs:complexType name="PartyType">
    <xs:sequence>
      <xs:element name="Id" type="xs:integer"/>
      <xs:element name="Name" type="NameType"/>
      <xs:element name="Salary" type="xs:decimal"/>
    </xs:sequence>
  </xs:complexType>

  <xs:element name="Document">
    <xs:complexType>
      <xs:choice minOccurs="1" maxOccurs="9999999">
        <xs:element name="Party" type="PartyType"/>
      </xs:choice>
    </xs:complexType>
  </xs:element>

</xs:schema>

上述 XSD 模式作为 Win32 资源嵌入到可执行文件中，可以通过标识符“IDR_XSDSCHEMA1”引用(参见选项 1 的注释行):

#include <stdio.h>
#include <tchar.h>
#include <windows.h>
#import <msxml6.dll>
#include "resource.h"

// Macro that calls a COM method returning HRESULT value.
#define CHK_HR(stmt) do { hr=(stmt); if (FAILED(hr)) return bstrResult; } while(0)

//Method for acquiring own handle
HMODULE GetThisDllHandle()
{
    MEMORY_BASIC_INFORMATION info;
    size_t len = VirtualQueryEx(GetCurrentProcess(), (void*)GetThisDllHandle, &info, sizeof(info));
    return len ? (HMODULE)info.AllocationBase : NULL;
}

_bstr_t validateFile(_bstr_t bstrFile)
{
    //Schema collection
    MSXML2::IXMLDOMSchemaCollectionPtr pXS;

    //XML document
    MSXML2::IXMLDOMDocument2Ptr pXD;

    //XSD document
    MSXML2::IXMLDOMDocument2Ptr pXSD;

    //Validation object
    MSXML2::IXMLDOMParseErrorPtr pErr;

    _bstr_t bstrResult = L"";
    HRESULT hr = S_OK;

    //Load XSD schema from resource
    HMODULE handle = GetThisDllHandle();
    HRSRC rc = ::FindResource(handle, MAKEINTRESOURCE(IDR_XSDSCHEMA1), L"XSDSCHEMA");
    HGLOBAL rcData = ::LoadResource(handle, rc);
    LPVOID data = (::LockResource(rcData));
    ::FreeResource(rcData);

    //Load schema stream into document
    CHK_HR(pXSD.CreateInstance(__uuidof(MSXML2::DOMDocument60), NULL, CLSCTX_INPROC_SERVER));

    if (pXSD->loadXML((LPCSTR)data) != VARIANT_TRUE)
        return bstrResult;

    // Create a schema cache
    CHK_HR(pXS.CreateInstance(__uuidof(MSXML2::XMLSchemaCache60), NULL, CLSCTX_INPROC_SERVER));

    //--> OPTION 1: VALIDATING AGAINST EMBEDDED XSD RESOURCE; DOESN'T WORK <--
    CHK_HR(pXS->add(L"urn:test", pXSD.GetInterfacePtr()));

    //--> OPTION 2: VALIDATING AGAINST PHYSICAL XSD FILE; WORKS FINE <--
    //CHK_HR(pXS->add(L"urn:test", L"schema.xsd"));

    // Create a DOMDocument and set its properties.
    CHK_HR(pXD.CreateInstance(__uuidof(MSXML2::DOMDocument60), NULL, CLSCTX_INPROC_SERVER));

    pXD->async = VARIANT_FALSE;
    pXD->validateOnParse = VARIANT_TRUE;
    pXD->preserveWhiteSpace = VARIANT_TRUE;

    //Assign the schema cache to the Document's schema collection
    pXD->schemas = pXS.GetInterfacePtr();

    //Load XML file
    if(pXD->load(bstrFile) != VARIANT_TRUE)
    {
        pErr = pXD->parseError;

        bstrResult = _bstr_t(L"Validation failed on ") + bstrFile +
        _bstr_t(L"\n=====================") +
        _bstr_t(L"\nReason: ") + _bstr_t(pErr->Getreason()) +       
        _bstr_t(L"\nSource: ") + _bstr_t(pErr->GetsrcText()) +
        _bstr_t(L"\nLine: ") + _bstr_t(pErr->Getline());
    }

    else
    {
        bstrResult = _bstr_t(L"Validation succeeded for ") + bstrFile +
        _bstr_t(L"\n======================\n") +
        _bstr_t(pXD->xml);
    }

    return bstrResult;    
}

int _tmain(int argc, _TCHAR* argv[])
{
    HRESULT hr = CoInitialize(NULL);
    if(SUCCEEDED(hr))
    {
        try
        {
            _bstr_t bstrOutput = validateFile(L"Document.xml");
            MessageBox(NULL, bstrOutput, L"schemaCache",MB_OK);
        }

        catch(_com_error &e)
        {
              MessageBox(NULL, e.Description(), L"schemaCache",MB_OK);
        }
        CoUninitialize();
    }
    return 0;
}

不幸的是，我在尝试运行验证例程时遇到了一些奇怪的行为(OPTION 1 评论)。看起来，XSD 资源中的变音符号在加载到流中时未正确解码。这会导致困惑的验证引用，如以下结果所示:

但是，当模式文件直接从磁盘加载时(选项 2 注释)，验证例程运行得很好:

我已经尝试将加载的流从 Unicode 转换为多字节，反之亦然，但无济于事。我在这里缺少什么吗？还是 Win32 资源仅限于特定字符集？感谢您的任何建议。

Answer 1

请参阅 WhozCraig 的评论: 使用 MultiByteToWideChar() 并将 CP_UTF8 作为输入参数返回有效的 Unicode 字符串。