xml2struct.m

function  outStruct  = xml2struct(input)
%XML2STRUCT converts xml file into a MATLAB structure
%
% outStruct = xml2struct2(input)
% 
% xml2struct2 takes either a java xml object, an xml file, or a string in
% xml format as input and returns a parsed xml tree in structure. 
% 
% Please note that the following characters are substituted
% '-' by '_dash_', ':' by '_colon_' and '.' by '_dot_'
%
% Originally written by W. Falkena, ASTI, TUDelft, 21-08-2010
% Attribute parsing speed increase by 40% by A. Wanner, 14-6-2011
% Added CDATA support by I. Smirnov, 20-3-2012
% Modified by X. Mo, University of Wisconsin, 12-5-2012
% Modified by Chao-Yuan Yeh, August 2016

errorMsg = ['%s is not in a supported format.\n\nInput has to be',...
        ' a java xml object, an xml file, or a string in xml format.'];

% check if input is a java xml object
if isa(input, 'org.apache.xerces.dom.DeferredDocumentImpl') ||...
        isa(input, 'org.apache.xerces.dom.DeferredElementImpl')
    xDoc = input;
else
    try 
        if exist(input, 'file') == 2
            xDoc = xmlread(input);
        else
            try
                xDoc = xmlFromString(input);
            catch
                error(errorMsg, inputname(1));
            end
        end
    catch ME
        if strcmp(ME.identifier, 'MATLAB:UndefinedFunction')
            error(errorMsg, inputname(1));
        else
            rethrow(ME)
        end
    end
end

% parse xDoc into a MATLAB structure
outStruct = parseChildNodes(xDoc);
    
end

% ----- Local function parseChildNodes -----
function [children, ptext, textflag] = parseChildNodes(theNode)
% Recurse over node children.
children = struct;
ptext = struct; 
textflag = 'Text';

if theNode.hasChildNodes
    childNodes = theNode.getChildNodes;
    numChildNodes = childNodes.getLength;

    for count = 1:numChildNodes

        theChild = childNodes.item(count-1);
        [text, name, attr, childs, textflag] = getNodeData(theChild);
        
        if ~strcmp(name,'#text') && ~strcmp(name,'#comment') && ...
                ~strcmp(name,'#cdata_dash_section')
            % XML allows the same elements to be defined multiple times,
            % put each in a different cell
            if (isfield(children,name))
                if (~iscell(children.(name)))
                    % put existsing element into cell format
                    children.(name) = {children.(name)};
                end
                index = length(children.(name))+1;
                % add new element
                children.(name){index} = childs;
                
                textfields = fieldnames(text);
                if ~isempty(textfields)
                    for ii = 1:length(textfields)
                        children.(name){index}.(textfields{ii}) = ...
                            text.(textfields{ii});
                    end
                end
                if(~isempty(attr)) 
                    children.(name){index}.('Attributes') = attr; 
                end
            else
                % add previously unknown (new) element to the structure
                
                children.(name) = childs;
                
                % add text data ( ptext returned by child node )
                textfields = fieldnames(text);
                if ~isempty(textfields)
                    for ii = 1:length(textfields)
                        children.(name).(textfields{ii}) = text.(textfields{ii});
                    end
                end

                if(~isempty(attr)) 
                    children.(name).('Attributes') = attr; 
                end
            end
        else
            ptextflag = 'Text';
            if (strcmp(name, '#cdata_dash_section'))
                ptextflag = 'CDATA';
            elseif (strcmp(name, '#comment'))
                ptextflag = 'Comment';
            end

            % this is the text in an element (i.e., the parentNode) 
            if (~isempty(regexprep(text.(textflag),'[\s]*','')))
                if (~isfield(ptext,ptextflag) || isempty(ptext.(ptextflag)))
                    ptext.(ptextflag) = text.(textflag);
                else
                    % This is what happens when document is like this:
                    % <element>Text <!--Comment--> More text</element>
                    %
                    % text will be appended to existing ptext
                    ptext.(ptextflag) = [ptext.(ptextflag) text.(textflag)];
                end
            end
        end

    end
end
end

% ----- Local function getNodeData -----
function [text,name,attr,childs,textflag] = getNodeData(theNode)
% Create structure of node info.

%make sure name is allowed as structure name
name = char(theNode.getNodeName);
name = strrep(name, '-', '_');
name = strrep(name, ':', '_');
name = strrep(name, '.', '_');
%name = strrep(name, '_', 'u_');

attr = parseAttributes(theNode);
if (isempty(fieldnames(attr))) 
    attr = []; 
end

%parse child nodes
[childs, text, textflag] = parseChildNodes(theNode);

% Get data from any childless nodes. This version is faster than below.
if isempty(fieldnames(childs)) && isempty(fieldnames(text))
    text.(textflag) = char(theNode.getTextContent);
end

% This alterative to the above 'if' block will also work but very slowly.
% if any(strcmp(methods(theNode),'getData'))
%   text.(textflag) = char(getData(theNode));
% end
    
end

% ----- Local function parseAttributes -----
function attributes = parseAttributes(theNode)
% Create attributes structure.
attributes = struct;
if theNode.hasAttributes
   theAttributes = theNode.getAttributes;
   numAttributes = theAttributes.getLength;

   for count = 1:numAttributes
        % Suggestion of Adrian Wanner
        str = char((theAttributes.item(count-1)).toString);
        k = strfind(str,'='); 
        attr_name = str(1:(k(1)-1));
        attr_name = strrep(attr_name, '-', '_');
        attr_name = strrep(attr_name, ':', '_');
        attr_name = strrep(attr_name, '.', '_');
        attributes.(attr_name) = str((k(1)+2):(end-1));
   end
end
end

% ----- Local function xmlFromString -----
function xmlroot = xmlFromString(iString)
import org.xml.sax.InputSource
import java.io.*

iSource = InputSource();
iSource.setCharacterStream(StringReader(iString));
xmlroot = xmlread(iSource);
end