OpenOffice.info

Code: Alles auswählen

Sub DeleteIgnorableWhitespace(oElement as object)

REM When importing xml files into a DOM tree line feeds and indentations
REM   are treated as text nodes.
REM I haven't found an import setting to care for ignorable white space.
REM Is this a bug?
REM
REM This procedure deletes all text nodes out of a DOM tree that consist
REM   of characters ascii 9 through 13 and 32.
REM It works recursively and needs a couple of seconds with big files.

  dim oChildren as object
  dim oChild as object
  dim i as integer
  dim r as integer
  
  if oElement.hasChildNodes() then
    oChildren = oElement.getChildNodes()
    for i = 0 to oChildren.getLength() - 1
      oChild = oChildren.item(i - r)
      if oChild.getNodeType() = com.sun.star.xml.dom.NodeType.TEXT_NODE then
        if IsWhite(oChild.getNodeValue()) then
          oElement.removeChild(oChild)
          r = r + 1
        end if
      else
        DeleteIgnorableWhitespace(oChild)
      end if
    next
  end if
End Sub

Function IsWhite(sString as string) as boolean
REM Tests if there are only whitespace characters in a string:
REM   ASCII 9 - 13, and 32.
  dim i as integer
  if sString <> "" then
    for i = 1 to len(sString)
      select case asc(mid(sString, i, 1))
      case 9 to 13, 32
      case else
        IsWhite = false
        exit function
      end select
    next
  end if
  IsWhite = true
End Function

Code: Alles auswählen

<?xml version="1.0" encoding="UTF-8"?>
<slots>
  <slot status="active" type="internal" ID="10001">
    <beta userID="X000001" systemID="Y000001" />
    <document ID="1234" title="Ipp Zipp Zapp" />
    <validTo>03.08.2009</validTo>
    <lecturer name="Becker, Bobbele" ID="1704" title="Dr." email="bobbeleb@dtb.de" />
    <orgUnit ID="01.01" label="Besenkammer" />
    <derivate ID="21905" modified="15.06.2009" />
  </slot>
</slots>

Code: Alles auswählen

Sub GetXMLData()
  dim oSimpleFileAccess as object
  dim oInputStream as object
  dim oDocBuilder as object
  dim oDocTree as object
  dim sUrl as string
  
  sUrl = "Z:\Eigene Dateien\testxml.xml"
  oSimpleFileAccess = createUnoService("com.sun.star.ucb.SimpleFileAccess")
  oInputStream = oSimpleFileAccess.openFileRead(ConvertToURL(sUrl))
  oDocBuilder = createUnoService("com.sun.star.xml.dom.DocumentBuilder")
  
  oDocTree = oDocBuilder.parse(oInputStream)
  
  oInputStream.closeInput()
  ParseXMLData(oDocTree)
End Sub

Sub ParseXMLData(oTree)
  dim oSlotList, oVtList, oDocList, oLectList as object

  oDocList = oTree.getElementsByTagName("document")
  print "Document-Nodes:", oDocList.getLength()
  oSlotList = oTree.getElementsByTagName("slot")
  print "Slot-Nodes:", oSlotList.getLength()
  oVtList = oTree.getElementsByTagName("validTo")
  print "ValidTo-Nodes:", oVtList.getLength()
  oLectList = oTree.getElementsByTagName("lecturer")
  print "Lecturer-Nodes:", oLectList.getLength()
End Sub