version 1.1, 2004/02/04 10:03:33
|
version 1.4, 2004/09/01 09:35:12
|
Line 15 from Ft.Xml.XLink import XLinkElements
|
Line 15 from Ft.Xml.XLink import XLinkElements
|
#from Ft.Xml import EMPTY_NAMESPACE |
#from Ft.Xml import EMPTY_NAMESPACE |
from Ft.Lib import Uri |
from Ft.Lib import Uri |
|
|
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':('','')} |
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':('',''),'Hyperlink':('','')} |
|
|
def addToDict(dict,name,value): |
def addToDict(dict,name,value): |
if name=="": |
if name=="": |
Line 53 def proj2hash(xmlstring):
|
Line 53 def proj2hash(xmlstring):
|
|
|
sec=parseSection(section) |
sec=parseSection(section) |
if sec[0]=="WEB_project_header": # Sonderfall project |
if sec[0]=="WEB_project_header": # Sonderfall project |
|
|
addToDict(list,'WEB_project_header',sec[1]) # store title |
addToDict(list,'WEB_project_header',sec[1]) # store title |
addToDict(list,'WEB_project_description',sec[2]) #store description |
addToDict(list,'WEB_project_description',sec[2]) #store description |
else: # no information in heading |
else: # no information in heading |
|
|
addToDict(list,sec[0],sec[2]) |
addToDict(list,sec[0],sec[2]) |
|
|
#evaluate higher level sections |
#evaluate higher level sections |
Line 76 def proj2hash(xmlstring):
|
Line 78 def proj2hash(xmlstring):
|
|
|
|
|
def parseSection(section): |
def parseSection(section): |
heading=section.getElementsByTagName('heading')[0] |
type="" |
|
header="" |
|
for heading in section.childNodes: |
|
if getattr(heading,'tagName','')=="heading": |
|
|
type=heading.getAttribute('class') |
type=heading.getAttribute('class') |
header=getText(heading.childNodes) |
header=getText(heading.childNodes) |
|
|
|
if type=="": # falls heading fehlt, pruefe ob erster par richtig |
|
par=section.getElementsByTagName('par')[0] |
|
type=par.getAttribute('class') |
|
header=getText(par.childNodes) |
|
|
#print section.childNodes |
#print section.childNodes |
pars=Evaluate('par',section) |
pars=Evaluate('par',section) |
content=par2html(pars) |
content=par2html(pars) |
Line 165 def getText(nodelist):
|
Line 177 def getText(nodelist):
|
|
|
rc = u'' |
rc = u'' |
for node in nodelist: |
for node in nodelist: |
print "HHHH" |
|
if node.nodeType == node.TEXT_NODE: |
if node.nodeType == node.TEXT_NODE: |
#print "node",node |
#print "node",node |
#print "NODE",node.data.encode('utf-8','ignore'),"V" |
#print "NODE",node.data.encode('utf-8','ignore'),"V" |
#print "HALII" |
#print "HALII" |
try: |
try: |
try: |
try: |
print "try1" |
|
#rc += node.data.encode('utf-8','ignore') |
#rc += node.data.encode('utf-8','ignore') |
rc += node.data |
rc += node.data |
|
|
except: |
except: |
print "try2" |
|
#rc= node.data.encode('utf-8','ignore') |
#rc= node.data.encode('utf-8','ignore') |
rc=node.data |
rc=node.data |
except: |
except: |
Line 187 def getText(nodelist):
|
Line 196 def getText(nodelist):
|
node.data.encode('utf-8','ignore') |
node.data.encode('utf-8','ignore') |
#print "RC",rc |
#print "RC",rc |
elif node.tagName =="inline": |
elif node.tagName =="inline": |
print "HI", node.getAttribute('class') |
|
rc+=par2html([node]) |
rc+=par2html([node]) |
elif node.attributes: |
elif node.attributes: |
print "xlink?" |
|
if 'xlink:type' in node.attributes.keys(): #is a xlink? |
if 'xlink:type' in node.attributes.keys(): #is a xlink? |
rc +=xlink2html(node) |
rc +=xlink2html(node) |
#print "RWT",rc |
#print "RWT",rc |