def getXML(self):
        txt = u""
# first generate string for all the sentences from the document in order to compute document level offsets
        documentString = u""
        sentenceOffsets = {}
        sections = self.getDocumentSections()
        for s in sections:
            markups = self.getSectionMarkups(s)
            for m in markups:
                sentenceOffsets[m[0]] = len(documentString)
                documentString = documentString + m[1].getText()+" "

        txt += xmlScrub(documentString)
        # get children sections of root

        
        for s in sections:
            txt += u"""<section>\n<sectionLabel> %s </sectionLabel>\n"""%s
            markups = self.getSectionMarkups(s)
            for m in markups:
                txt += u"<sentence>\n<sentenceNumber> %s </sentenceNumber>\n<sentenceOffset> %s </sentenceOffset></sentence>\n%s"%(m[0],sentenceOffsets[m[0]],m[1].getXML())
            txt += u"""</section>\n"""

        return ConTextDocumentXMLSkel%txt
Example #2
0
    def getXML(self):
        txt = u""
        # first generate string for all the sentences from the document in order to compute document level offsets
        documentString = u""
        sentenceOffsets = {}
        sections = self.getDocumentSections()
        for s in sections:
            markups = self.getSectionMarkups(s)
            for m in markups:
                sentenceOffsets[m[0]] = len(documentString)
                documentString = documentString + m[1].getText() + " "

        txt += xmlScrub(documentString)
        # get children sections of root

        for s in sections:
            txt += u"""<section>\n<sectionLabel> %s </sectionLabel>\n""" % s
            markups = self.getSectionMarkups(s)
            for m in markups:
                txt += u"<sentence>\n<sentenceNumber> %s </sentenceNumber>\n<sentenceOffset> %s </sentenceOffset></sentence>\n%s" % (
                    m[0], sentenceOffsets[m[0]], m[1].getXML())
            txt += u"""</section>\n"""

        return ConTextDocumentXMLSkel % txt
Example #3
0
def getXML(obj):
    return tagObjectXMLSkel % (
        obj.getTagID(), xmlScrub(obj.getPhrase()), xmlScrub(obj.getLiteral()),
        xmlScrub(obj.ti.citem.getCategory()), obj.getSpan()[0],
        obj.getSpan()[1], obj.getScope()[0], obj.getScope()[1])
Example #4
0
def getXML(obj):
    return   tagObjectXMLSkel%(obj.getTagID(),xmlScrub(obj.getPhrase()),
                               xmlScrub(obj.getLiteral()),xmlScrub(obj.ti.citem.getCategory()),
                               obj.getSpan()[0],obj.getSpan()[1],
                               obj.getScope()[0],obj.getScope()[1])