MSXML from C++ - pretty print / indent newly created documents

Question

I'm writing out XML files using the MSXML parser, with a wrapper I downloaded from here: http://www.codeproject.com/KB/XML/JW_CXml.aspx. Works great except that when I create a new document from code (so not load from file and modify), the result is all in one big line. I'd like elements to be indented nicely so that I can read it easily in a text editor.

Googling shows many people with the same question - asked around 2001 or so. Replies usually say 'apply an XSL transformation' or 'add your own whitespace nodes'. Especially the last one makes me go %( so I'm hoping that in 2008 there's an easier way to pretty MSXML output. So my question; is there, and how do I use it?

Answer 1

Unless the library has a format option then the only other way is to use XSLT, or an external pretty printer ( I think htmltidy can also do xml) There doen't seem to be an option in the codeproject lib but you can specify an XSLT stylesheet to MSXML.

Answer 2

Try this, I found this years ago on the web.

#include <msxml2.h>

bool FormatDOMDocument (IXMLDOMDocument *pDoc, IStream *pStream)
{

    // Create the writer

    CComPtr <IMXWriter> pMXWriter;
    if (FAILED (pMXWriter.CoCreateInstance(__uuidof (MXXMLWriter), NULL, CLSCTX_ALL)))
    {
        return false;
    }
    CComPtr <ISAXContentHandler> pISAXContentHandler;
    if (FAILED (pMXWriter.QueryInterface(&pISAXContentHandler)))
    {
        return false;
    }
    CComPtr <ISAXErrorHandler> pISAXErrorHandler;
    if (FAILED (pMXWriter.QueryInterface (&pISAXErrorHandler)))
    {
        return false;
    }
    CComPtr <ISAXDTDHandler> pISAXDTDHandler;
    if (FAILED (pMXWriter.QueryInterface (&pISAXDTDHandler)))
    {
        return false;
    }

    if (FAILED (pMXWriter ->put_omitXMLDeclaration (VARIANT_FALSE)) ||
        FAILED (pMXWriter ->put_standalone (VARIANT_TRUE)) ||
        FAILED (pMXWriter ->put_indent (VARIANT_TRUE)) ||
        FAILED (pMXWriter ->put_encoding (L"UTF-8")))
    {
        return false;
    }

    // Create the SAX reader

    CComPtr <ISAXXMLReader> pSAXReader;
    if (FAILED (pSAXReader.CoCreateInstance (__uuidof (SAXXMLReader), NULL, CLSCTX_ALL)))
    {
        return false;
    }

    if (FAILED (pSAXReader ->putContentHandler (pISAXContentHandler)) ||
        FAILED (pSAXReader ->putDTDHandler (pISAXDTDHandler)) ||
        FAILED (pSAXReader ->putErrorHandler (pISAXErrorHandler)) ||
        FAILED (pSAXReader ->putProperty (
        L"http://xml.org/sax/properties/lexical-handler", CComVariant (pMXWriter))) ||
        FAILED (pSAXReader ->putProperty (
        L"http://xml.org/sax/properties/declaration-handler", CComVariant (pMXWriter))))
    {
        return false;
    }

    // Perform the write

    return 
       SUCCEEDED (pMXWriter ->put_output (CComVariant (pStream))) &&
       SUCCEEDED (pSAXReader ->parse (CComVariant (pDoc)));
}

Answer 3

Here's a modified version of the accepted answer that will transform in-memory (changes only in the last few lines but I'm posting the whole block for the convenience of future readers):

bool CXml::FormatDOMDocument(IXMLDOMDocument *pDoc)
{
    // Create the writer
    CComPtr <IMXWriter> pMXWriter;
    if (FAILED (pMXWriter.CoCreateInstance(__uuidof (MXXMLWriter), NULL, CLSCTX_ALL))) {
        return false;
    }
    CComPtr <ISAXContentHandler> pISAXContentHandler;
    if (FAILED (pMXWriter.QueryInterface(&pISAXContentHandler))) {
        return false;
    }
    CComPtr <ISAXErrorHandler> pISAXErrorHandler;
    if (FAILED (pMXWriter.QueryInterface (&pISAXErrorHandler))) {
        return false;
    }
    CComPtr <ISAXDTDHandler> pISAXDTDHandler;
    if (FAILED (pMXWriter.QueryInterface (&pISAXDTDHandler))) {
        return false;
    }

    if (FAILED (pMXWriter->put_omitXMLDeclaration (VARIANT_FALSE)) ||
        FAILED (pMXWriter->put_standalone (VARIANT_TRUE)) ||
        FAILED (pMXWriter->put_indent (VARIANT_TRUE)) ||
        FAILED (pMXWriter->put_encoding (L"UTF-8")))
    {
        return false;
    }

    // Create the SAX reader
    CComPtr <ISAXXMLReader> pSAXReader;
    if (FAILED(pSAXReader.CoCreateInstance(__uuidof (SAXXMLReader), NULL, CLSCTX_ALL))) {
        return false;
    }

    if (FAILED(pSAXReader->putContentHandler (pISAXContentHandler)) ||
        FAILED(pSAXReader->putDTDHandler (pISAXDTDHandler)) ||
        FAILED(pSAXReader->putErrorHandler (pISAXErrorHandler)) ||
        FAILED(pSAXReader->putProperty (L"http://xml.org/sax/properties/lexical-handler", CComVariant (pMXWriter))) ||
        FAILED(pSAXReader->putProperty (L"http://xml.org/sax/properties/declaration-handler", CComVariant (pMXWriter))))
    {
        return false;
    }

    // Perform the write
 bool success1 = SUCCEEDED(pMXWriter->put_output(CComVariant(pDoc.GetInterfacePtr())));
 bool success2 = SUCCEEDED(pSAXReader->parse(CComVariant(pDoc.GetInterfacePtr())));

 return success1 && success2;
}

Answer 4

I've written a sed script a while back for basic xml indenting. You can use it as an external indenter if all else fails (save this to xmlindent.sed, and process your xml with sed -f xmlindent.sed <filename>). You might need cygwin or some other posix environment to use it though.

Here's the source:

:a
/>/!N;s/\n/ /;ta
s/  / /g;s/^ *//;s/  */ /g
/^<!--/{
:e
/-->/!N;s/\n//;te
s/-->/\n/;D;
}
/^<[?!][^>]*>/{
H;x;s/\n//;s/>.*$/>/;p;bb
}
/^<\/[^>]*>/{
H;x;s/\n//;s/>.*$/>/;s/^    //;p;bb
}
/^<[^>]*\/>/{
H;x;s/\n//;s/>.*$/>/;p;bb
}
/^<[^>]*[^\/]>/{
H;x;s/\n//;s/>.*$/>/;p;s/^/ /;bb
}
/</!ba
{
H;x;s/\n//;s/ *<.*$//;p;s/[^    ].*$//;x;s/^[^<]*//;ba
}
:b
{
s/[^    ].*$//;x;s/^<[^>]*>//;ba
}

Hrmp, tabs seem to be garbled... You can copy-waste from here instead: XML indenting with sed(1)