Return to xmlhelper.py CVS log

Up to [Repository] / MPIWGWeb

Initial revision

    1: 
    2: from sys import argv
    3: 
    4: import string
    5: import xml.dom.minidom
    6: import Ft.Xml.XLink.Processor
    7: import Ft.Xml.XLink.XLinkElements
    8: 
    9: from Ft.Xml import XPath
   10: from Ft.Xml.XPath import Evaluate
   11: from Ft.Xml.XLink import XLINK_NAMESPACE
   12: from Ft.Xml.XLink import XLinkElements
   13: 
   14: #from Ft.Xml.Domlette import NonvalidatingReader,InputSource
   15: #from Ft.Xml import EMPTY_NAMESPACE
   16: from Ft.Lib import Uri
   17: 
   18: xml2html={'WEB_normal':('<p>','</p>'),'Normal':('<p>','</p>'),'WEB_picture':('<p>','</p>'),'WEB_figuretitle':('<i>','</i>'),'WEB_bibliography':('<p><i>','</i></p>'),'Web_kursiv':('<i>','</i>'),'WEB_kursiv':('<i>','</i>'),'WEB_hyperlink':('','')}
   19: 
   20: def addToDict(dict,name,value):
   21:     if name=="":
   22:         return 0
   23:     else:
   24:         
   25:         if not dict.has_key(name):
   26:             dict[name]=[] # als array anlegen
   27: 
   28:         dict[name].append(value)
   29:         return 1    
   30: 
   31: def proj2hash(xmlstring):
   32:     """wandelt xml-files fuer die projekte in ein hash"""
   33:     
   34:     dom=xml.dom.minidom.parseString(xmlstring)
   35:     
   36:         
   37:     list={}
   38: 
   39:     #gettitle
   40:     pars=Evaluate('par',dom.getElementsByTagName('part')[0])
   41:     for par in pars:
   42:         className=par.getAttribute('class')
   43:         content=getText(par.childNodes)
   44:         addToDict(list,className,content)
   45:              
   46:     list.update(parseTable(dom.getElementsByTagName('html:table')[0])) # Parse the Table
   47: 
   48:     #evaluate level 1
   49: 
   50:     sections=Evaluate('section',dom.getElementsByTagName('part')[0])# Parse all Sections
   51:     #print sections,dom.getElementsByTagName('part')[0]
   52:     for section in sections:
   53:         
   54:         sec=parseSection(section)
   55:         if sec[0]=="WEB_project_header": # Sonderfall project
   56:             addToDict(list,'WEB_project_header',sec[1]) # store title
   57:             addToDict(list,'WEB_project_description',sec[2]) #store description
   58:         else: # no information in heading
   59:             addToDict(list,sec[0],sec[2])
   60: 
   61:     #evaluate higher level sections
   62: 
   63:     sections=Evaluate('section/section',dom.getElementsByTagName('part')[0])
   64:     
   65:     for section in sections:
   66:         sec=parseSection(section)
   67:         
   68:         if sec[0]=="WEB_project_header": # Sonderfall project
   69:             addToDict(list,'WEB_project_header',sec[1]) # store title
   70:             addToDict(list,'WEB_project_description',sec[2]) #store description
   71:         else: # no information in heading
   72:             addToDict(list,sec[0],sec[2])
   73:     
   74:     
   75:     return list
   76: 
   77: 
   78: def parseSection(section):
   79:     heading=section.getElementsByTagName('heading')[0]
   80:     type=heading.getAttribute('class')
   81:     header=getText(heading.childNodes)
   82:     #print section.childNodes
   83:     pars=Evaluate('par',section)
   84:     content=par2html(pars)
   85:     
   86:     return (type,header,content)
   87: 
   88: def parseTable(table):
   89:     fields={}
   90:     rows=table.getElementsByTagName('html:tr')
   91:     for row in rows:
   92:         #print "ROW"
   93:         cols=row.getElementsByTagName('html:td')
   94:         
   95:         #Name des Datenfeldes einlesen
   96:         try:
   97:             field=cols[0].getElementsByTagName('par')[0].getAttribute('class')
   98:             #print "field",field
   99:         except:
  100:             print "error"
  101:             field=""
  102: 
  103:         #Wandeln der Eintrge in HTML
  104: 
  105:         pars=cols[1].getElementsByTagName('par')
  106: 
  107:         
  108:         html=par2html(pars,tags=("",";"))
  109:         
  110:         addToDict(fields,field,html)
  111:         #print fields
  112:     return fields
  113: 
  114: def par2html(pars,tags=None):
  115:     #html=""
  116: 
  117:     for par in pars:
  118:         #print "par",par
  119:         if not tags:
  120:             try:
  121:                 tag=xml2html[par.getAttribute('class')]
  122:             except:
  123:                 tag=('<p>','</p>')
  124:         else:
  125:             tag=tags
  126:         
  127:         content=getText(par.childNodes)
  128:         #print "CONTETN",content
  129:         
  130:         #print par.getAttribute('class'),node
  131:         try:
  132:             html=html+tag[0]+content+tag[1]
  133:         except:
  134:             html=tag[0]+content+tag[1]
  135: 
  136:     try:    
  137:         return html
  138:     except:
  139:         return ""
  140: 
  141: def getXlink(nodes):
  142:     """searches xlinks and gives them back as html"""
  143:     ret=""
  144:     for node in nodes:
  145:         if node.attributes:
  146:             if 'xlink:type' in node.attributes.keys(): #is a xlink?
  147:                 ret +=xlink2html(node)
  148:     return ret
  149:     
  150: def xlink2html(xlink):
  151:     ret=""
  152:     attributes=xlink.attributes
  153:     
  154:     if xlink.tagName.lower()=="image":
  155:         ret +="<img src=%s />"%xlink.getAttribute('xlink:href')
  156:     elif xlink.tagName.lower()=="link":
  157:         ret +="<a href='%s' >%s</a>"%(xlink.getAttribute('xlink:href'),getText(xlink.childNodes))
  158:     
  159:         
  160:         
  161:     
  162:     return ret
  163: 
  164: def getText(nodelist):
  165:     
  166:     rc = u''
  167:     for node in nodelist:
  168:         print "HHHH"
  169:     	if node.nodeType == node.TEXT_NODE:
  170:             #print "node",node
  171:             #print "NODE",node.data.encode('utf-8','ignore'),"V"
  172:             #print "HALII"
  173:             try:
  174:                 try:
  175:                     print "try1"
  176:                     #rc += node.data.encode('utf-8','ignore')
  177:                     rc += node.data
  178:                                         
  179:                 except:
  180:                     print "try2"
  181:                     #rc= node.data.encode('utf-8','ignore')
  182:                     rc=node.data
  183:             except:
  184:                 rc="ERROR"
  185:                 #node.data.decode('utf-8','ignore')
  186:                 print "ERROR"
  187:             node.data.encode('utf-8','ignore')
  188:             #print "RC",rc
  189:         elif node.tagName =="inline":
  190:             print "HI", node.getAttribute('class')
  191:             rc+=par2html([node])
  192:         elif node.attributes:
  193:             print "xlink?"
  194:             if 'xlink:type' in node.attributes.keys(): #is a xlink?
  195:                 rc +=xlink2html(node)
  196:     #print "RWT",rc        
  197:     return rc
  198: 
  199: 
  200: #filename=argv[1]
  201: #fileString=file(filename).read()
  202: #print proj2hash(fileString)
  203: