How to parse .xml.gz using PugiXML and boost::iostreams

In our previous post Minimal PugiXML file reader example we provided a short example of how to read from an uncompressed XML file using PugiXML. In practice, many large XML files are distributed as .xml.gz package.

Since you can use boost::iostreams to decompress gzipped data on the fly and pipe it directly into PugiXML, you don’t need to store the uncompressed data on your hard drive.

#include <iostream>
#include <fstream>
#include <pugixml.hpp>
#include <boost/iostreams/filtering_streambuf.hpp>
#include <boost/iostreams/copy.hpp>
#include <boost/iostreams/filter/gzip.hpp>
using namespace std;
using namespace pugi;

int main() {
    // Open "raw" gzipped data stream
    ifstream file("test.xml.gz", ios_base::in | ios_base::binary);
    // Configure decompressor filter
    boost::iostreams::filtering_streambuf<boost::iostreams::input> inbuf;
    inbuf.push(boost::iostreams::gzip_decompressor());
    inbuf.push(file);
    //Convert streambuf to istream
    istream instream(&inbuf);
    // Parse from stream
    xml_document doc;
    xml_parse_result result = doc.load(instream);
    // Print content of root element
    cout << "Load result: " << result.description() << "\n"
         << doc.child("root-element").child_value() // "Test text"
         << endl;
}

cmake_minimum_required(VERSION 3.0)
find_package(Boost 1.36.0 COMPONENTS iostreams)

include_directories(${Boost_INCLUDE_DIRS})
add_executable(pugixml-example pugixml-example.cpp)
target_link_libraries(pugixml-example pugixml ${Boost_LIBRARIES})

<?xml version="1.0" encoding="UTF-8"?>
<root-element>Test text</root-element>

Download all three files and then run

gzip test.xml
cmake .
make
./pugixml-example

You should see an output like

Load result: No error
Test text