XML (version 1.2-0)

xmlEventParse: XML Event/Callback element-wise Parser

Description

Reads and processes the contents of an XML file or string by invoking user-level functions associated with different components of the XML tree. These include beginning and end of XML elements, comments, CDATA (escaped character data), entities, processing instructions, etc. This allows the caller to create the appropriate data structure from the XML document contents rather than the default tree (see xmlTreeParse). Functions for specific tags/elements can be used in addition to the standard callback names.

Usage

xmlEventParse(file, handlers=xmlEventHandler(), ignoreBlanks = FALSE, addContext=TRUE,
               useTagName=TRUE, asText = FALSE, trim=TRUE, useExpat=FALSE, isURL = FALSE,
                state = NULL, replaceEntities = TRUE, validate = FALSE,
                 saxVersion = 1)

Value

• The return value is the `handlers' argument. It is assumed that this is a closure and that the callback functions have manipulated variables local to it and that the caller knows how to extract this.

Details

This is now implemented using the libxml parser. Originally, this was implemented via the Expat XML parser by Jim Clark (http://www.jclark.com).

References

http://www.w3.org/XML, http://www.jclark.com/xml

See Also

xmlTreeParse

Examples

fileName <- system.file("exampleData", "mtcars.xml", package="XML")

   # Print the name of each XML tag encountered at the beginning of each
   # tag.
   # Uses the libxml SAX parser.
 xmlEventParse(fileName,
                list(startElement=function(name, attrs){
                                    cat(name,"")
                                  }),
                useTagName=FALSE, addContext = FALSE)


# Parse the text rather than a file or URL by reading the URL's contents
  # and making it a single string. Then call xmlEventParse
xmlURL <- "http://www.omegahat.org/Scripts/Data/mtcars.xml"
xmlText <- paste(scan(xmlURL, what="",sep="\n"),"\n",collapse="\n")
xmlEventParse(xmlText, asText=TRUE)

    # Using a state object to share mutable data across callbacks
f <- system.file("exampleData", "gnumeric.xml", package = "XML")
zz <- xmlEventParse(f,
                    handlers = list(startElement=function(name, atts, .state) {
                                                     .state = .state + 1
                                                     print(.state)
                                                     .state
                                                 }), state = 0)
print(zz)




    # Illustrate the startDocument and endDocument handlers.
xmlEventParse(fileName,
               handlers = list(startDocument = function() {
                                                 cat("Starting document
")
                                               },
                               endDocument = function() {
                                                 cat("ending document
")
                                             }),
               saxVersion = 2)




if(libxmlVersion()$major >= 2) {


 startElement = function(x, ...) cat(x, "")


 xmlEventParse(file(f), handlers = list(startElement = startElement))


 # Parse with a function providing the input as needed.
 xmlConnection = 
  function(con) {

   if(is.character(con))
     con = file(con, "r")
  
   if(isOpen(con, "r"))
     open(con, "r")

   function(len) {

     if(len < 0) {
        close(con)
        return(character(0))
     }

      x = character(0)
      tmp = ""
    while(length(tmp) > 0 && nchar(tmp) == 0) {
      tmp = readLines(con, 1)
      if(length(tmp) == 0)
        break
      if(nchar(tmp) == 0)
        x = append(x, "")
      else
        x = tmp
    }
    if(length(tmp) == 0)
      return(tmp)
  
    x = paste(x, collapse="")

    x
  }
 }

 ff = xmlConnection(f)
 xmlEventParse(ff, handlers = list(startElement = startElement))

  # Parse from a connection. Each time the parser needs more input, it
  # calls readLines(<con>, 1)
 xmlEventParse(file(f),  handlers = list(startElement = startElement))


  # using SAX 2
 h = list(startElement = function(name, attrs, namespace, allNamespaces){ 
                                 cat("Starting", name,"")
                                 if(length(attrs))
                                     print(attrs)
                                 print(namespace)
                                 print(allNamespaces)
                         },
          endElement = function(name, uri) {
                          cat("Finishing", name, "")
            }) 
 xmlEventParse(system.file("exampleData", "namespaces.xml", package="XML"), handlers = h, saxVersion = 2)

}