import urlparse
import string
import tempfile
import zipfile
import re
import os,shutil
import OFS.Image
from types import *
from OFS.Cache import Cacheable
from OFS.Image import Image
from Globals import DTMLFile
from OFS.Folder import Folder
from OFS.SimpleItem import SimpleItem
from AccessControl import ClassSecurityInfo
from AccessControl.User import UserFolder
from Globals import InitializeClass
from Globals import DTMLFile
import Globals
from Products.PageTemplates.PageTemplateFile import PageTemplateFile
from Products.PageTemplates.PageTemplate import PageTemplate
from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate,manage_addPageTemplate
from Globals import Persistent, package_home
from Acquisition import Implicit
from Products.ZCatalog.CatalogPathAwareness import CatalogAware
from Products.ZCTextIndex.ZCTextIndex import manage_addLexicon
try:
from Products.MetaDataProvider.MetaDataClient import MetaDataClient
except:
print "no metadata services"
import urllib
import urllib2
import cgi
import smtplib
import time
from Ft.Xml.Domlette import NonvalidatingReader
from Ft.Xml.Domlette import PrettyPrint, Print
from Ft.Xml import EMPTY_NAMESPACE
import Ft.Xml.XPath
import cStringIO
import sys
try:
from psycopg import libpq
except:
try:
from pyPgSQL import libpq
except:
print "ECHO_collection: Warning - No libpq imported!"
import xml.dom.minidom
import urllib
import xml.dom.minidom
import ECHO_helpers
from ECHO_helpers import *
from ECHO_movie import *
import vlp_xmlhelpers #TODO: vlp elemente aus echo herausnehmen
import xmlrpclib
import logging
class ECHO_resource(CatalogAware,Folder,Persistent,ECHO_basis):
"""ECHO Ressource"""
security=ClassSecurityInfo()
meta_type='ECHO_resource'
default_catalog='resourceCatalog'
# viewClassificationList=viewClassificationListMaster
def PrincipiaSearchSource(self):
"""Return cataloguable key for ourselves."""
return str(self)
getSubCols = ECHO_helpers.getSubCols
def index_meta(self,RESPONSE=None):
""" gibt das im metalink gespeicher xml-file zurueck"""
url = self.metalink
txt=""
logging.debug("ml:%s"%url)
try:
page = urllib.urlopen(url);
if RESPONSE:
RESPONSE.setHeader("Content-Type","text/xml")
txt = page.read();
except:
logging.error("Cannot read metadata of: %s"%self.getId())
return txt
def reindex(self):
"""generate fields for indexing and reindex"""
#TODO: korrigieren des metalink pfades konfigurierbar machen
splitted= [x for x in urlparse.urlparse(self.metalink)]
splitted[1]="foxridge.mpiwg-berlin.mpg.de"[0:]
if splitted[0]=="http":
self.metalink=urlparse.urlunparse(splitted)
self.fullTextUrl=self.getFullTextXML(noredirect="yes")
#TODO: korrigieren relative url to absoluter url volltexten, konfigurierbar?
splitted= [x for x in urlparse.urlparse(self.fullTextUrl)]
if splitted[0]=="":
splitted[0]="http"
splitted[1]="foxridge.mpiwg-berlin.mpg.de"[0:]
self.fullTextUrl=urlparse.urlunparse(splitted)
self.imagePath=self.getImagePath()
self.reindex_object()
security.declareProtected('View','createPDF')
def createPDF(self,RESPONSE=None,local=None,dpi=150):
"""erzeuge pdf file"""
pages=1
dpi=float(dpi)
imagePath=self.getImagePath().replace("/mpiwg/online","")
image="http://nausikaa2.mpiwg-berlin.mpg.de/digitallibrary/servlet/Scaler?fn="+imagePath+"&dw=%i&dh=%i&pn=%i"
xmlInfo="http://nausikaa2.mpiwg-berlin.mpg.de/digitallibrary/dlInfo-xml.jsp?fn="+imagePath
dom=xml.dom.minidom.parse(urllib.urlopen(xmlInfo))
for parameter in dom.getElementsByTagName('parameter'):
if parameter.getAttribute('name')=="pt":
pages=int(parameter.getAttribute('value'))
break
tempdir="/tmp/archivesImageServer"
if not os.path.exists(tempdir):
os.mkdir(tempdir)
tmpPath=tempfile.mkdtemp(dir=tempdir)
tmpZip=tempfile.mktemp(dir=tempdir)
tmpFn=os.path.split(tmpZip)[1]
if RESPONSE:
RESPONSE.setHeader("Content-Type","text/html")
RESPONSE.write("<h1>I am creating the pdf</h1>")
txt="<h3>1. step: getting the images( %i pages)</h3>"%pages
RESPONSE.write(txt)
c=canvas.Canvas(tmpZip)
for i in range(1,pages+1):
if RESPONSE:
RESPONSE.write(str("<p>Get Page: %i<br>\n"%i))
faktor=dpi/72.0
fn=tmpPath+"/%i"%i
width,height=A4
#print image%(width*faktor,height*faktor,i)
url=urllib.urlopen(image%(width*faktor,height*faktor,i)).read()
fh=file(fn,"w")
fh.write(url)
fh.close()
c.drawImage(fn,0,0,width=width,height=height)
c.showPage()
c.save()
if RESPONSE:
RESPONSE.write("<p>finished<br>\n")
if RESPONSE:
len=os.stat(tmpZip)[6]
downloadUrl=self.absolute_url()+"/downloadPDF"
RESPONSE.write("""<h1><a href="downloadPDF?fn=%s">Click here for download ( %i Byte)</a></h1>\n"""%(tmpFn,len))
RESPONSE.write("""<p>The file will be stored for a while, you can download it later, the URL is:</p>
<p><a href="downloadPDF?fn=%s">%s?fn=%s</a></h1>\n"""%(tmpFn,downloadUrl,tmpFn))
RESPONSE.close()
def downloadPDF(self,fn):
"""download prepared set"""
filename="/tmp/archivesImageServer/"+fn
namePDF=self.getId()+".pdf"
self.REQUEST.RESPONSE.setHeader("Content-Disposition","""attachement; filename="%s" """%namePDF)
self.REQUEST.RESPONSE.setHeader("Content-Type","application/octet-stream")
len=os.stat(filename)[6]
self.REQUEST.RESPONSE.setHeader("Content-Length",len)
images=file(filename).read()
self.REQUEST.RESPONSE.write(images)
self.REQUEST.RESPONSE.close()
def getRDF(self,urn=None):
"""rdf"""
ap = self.getArchivePathFromMetadata()
ret=getRDFDescription(self,self.link,urn=urn,ap=ap)
return ret+self.createSubElementRDF(urn=urn)
def changeAccessRightForm(self,preselect=None):
"""change the access rights"""
pt=zptFile(self, 'zpt/ChangeECHO_resourceAccessRight.zpt')
return pt(preselect=preselect)
def changeAccessRight(self):
"""changeRights"""
argv=self.REQUEST.form
self.setAccessRightXML(argv["%s_xml"%self.getId()])
self.accessRight=argv["%s_echo"%self.getId()]
self.REQUEST.RESPONSE.redirect('manage_main')
def getAccessRightSelectorHTML(self,outlook="select",xmldominant=None,preselect=None):
"""htmlselector, xmldominant= in der regel wird der wert des xmlfiles ausgegeben ausser er existiert nicht"""
values=['','free','MPIWG']
if preselect:#set all to the preselected
ar=(preselect,preselect)
else:#else set to actual value
ar=self.getAccessRightMD()
if outlook=="select":
ret="""<select name="%s_xml">"""%self.getId()
ret1="""<select name="%s_echo">"""%self.getId()
for value in values:
if value==ar[0]:
ret+="<option selected>%s</option>"%value
else:
ret+="<option>%s</option>"%value
if value==ar[1]:
ret1+="<option selected>%s</option>"%value
else:
ret1+="<option>%s</option>"%value
if not xmldominant:
return ret+"</select>",ret1+"</select>"
else:
if ar[0] is not None:
return ret+"</select>"
else:
return "<p>No xml file (only local selection):"+ret1
else:
ret=""
ret1=""
for value in values:
if value==ar[0]:
ret+="""<input type="radio" name="%s_xml" value="%s" checked>%s"""%(self.getId(),value,value)
else:
ret+="""<input type="radio" name="%s_xml" value="%s">%s"""%(self.getId(),value,value)
if value==ar[1]:
ret1+="""<input type="radio" name="%s_echo" value="%s" checked>%s"""%(self.getId(),value,value)
else:
ret1+="""<input type="radio" name="%s_echo" value="%s">%s"""%(self.getId(),value,value)
if not xmldominant:
return ret,ret1
else:
if ar[0]:
return ret
else:
return "<p>No xml file (only local selection)</p>"+ret1
def copyAccessRightsFromMD(self):
"""kopiere rechte aus den metadaten"""
self.accessRight=self.getAccessRightMD()[0]
def getMetaLink(self):
return self.metalink
def setMetaLink(self,ml):
self.metalink=ml
return
def getAccessRightMD(self):
"""set accessright"""
url=self.metalink
try:
urllib.urlopen(url)
except:
logger("ECHO_Resource (getAccessRightMD)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
return None,getattr(self,'accessRight','')
try:
dom = NonvalidatingReader.parseUri(url)
except:
logger("ECHO_Resource (getAccessRightMD)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
return (None,"Cannot parse: "+url+"<br>"+"%s (%s)"%sys.exc_info()[0:2])
accessright=dom.xpath("//meta/access-conditions/access/@type")
if accessright:
accessright=accessright[0].value
if str(accessright)=='institution':
tmp=dom.xpath("//meta/access-conditions/access/name")
if tmp:
accessright=getTextFromNode(tmp[0])
if not accessright:
accessright=""
return accessright,getattr(self,'accessRight','')
def changeAccessRightMD(self,accessright,RESPONSE=None):
"""change the rights - not user anymore"""
#TODO: check if method still needed
params="accessright=%s"%accessright
#print ECHO_helpers.urlopen(self.absolute_url()+'/setAccessRightXML'+'?'+params).read()
tries=0
for i in range(10):
x=ECHO_helpers.urlopen('http://echo.mpiwg-berlin.mpg.de/echo_nav/storage/downloadExternalXML?index_meta_url=%s&xml_url=%s'%(self.metalink,self.absolute_url()+'/setAccessRightXML'+urllib.quote('?'+params))).read()
if x=="ok":
break;
if RESPONSE is not None:
RESPONSE.redirect('manage_main')
def setAccessRightXML(self,accessright):
"""set accessright"""
url=self.metalink
accessrights=['MPIWG','free']#allowes rights
if accessright =='':
"""do nothing"""
return ""
try:
geturl=""
for line in ECHO_helpers.urlopen(url).readlines():
geturl=geturl+line
except:
return (None,"Cannot open: "+url)
try:
dom=xml.dom.minidom.parseString(geturl)
root=dom.getElementsByTagName('resource')[0]
except:
return (None,"Cannot parse: "+url+"<br>"+geturl)
metamains=dom.getElementsByTagName('meta')
if not metamains:
nodenew=dom.createElement('meta')
root.appendChild(nodenew)
metamain=nodenew
else:
metamain=metamains[0]
metanodes=metamain.getElementsByTagName('access-conditions')
if not metanodes:
nodenew=dom.createElement('access-conditions')
metamain.appendChild(nodenew)
metanode=nodenew
else:
metanode=metanodes[0]
accesses=metanode.getElementsByTagName('access')
#delete old
if accesses:
metanode.removeChild(accesses[0]).unlink()
#create new
nodenew2=dom.createElement('access')
metanode.appendChild(nodenew2)
metanode2=nodenew2
attribute=metanode2.getAttribute('type')
if accessright=="free":
metanode2.setAttribute('type','free')
elif accessright.upper()=='MPIWG':
metanode2.setAttribute('type','institution')
nodenew4=dom.createElement('name')
metanodetext=dom.createTextNode('MPIWG')
nodenew4.appendChild(metanodetext)
nodenew2.appendChild(nodenew4)
#print dom.toxml().encode('utf-8')
string= encodeRPC(dom.toxml().encode('utf-8'))
#TODO: make server configurable
server=xmlrpclib.Server("http://foxridge.mpiwg-berlin.mpg.de/server")
path=urlparse.urlparse(self.metalink)[2]
server.writeMetaDataFile(path,string,"yes")
def setStartPageForm(self):
"""Form for changing the startpage"""
pt=zptFile(self, 'zpt/ChangeECHO_resourceStartPage.zpt')
pt.content_type="text/html"
return pt()
def createImageUrl(self,pn=1):
"""create ImageUrl"""
resourcepath=readFieldFromXML_xpath(self.metalink,'//resource/archive-path')
digiliburlprefix=readFieldFromXML(self.metalink,'texttool','digiliburlprefix')
images=readFieldFromXML(self.metalink,'texttool','image')
if (not resourcepath) or (not digiliburlprefix) or (not images):
logger("ECHO (createImageUrl)",logging.ERROR,"Cannot create ImageUrl for %s"%self.absolute_url())
return None
resourcepath=resourcepath.replace('/mpiwg/online','')
if not digiliburlprefix: digiliburlprefix="http://echo.mpiwg-berlin.mpg.de/zogilib?"
if (not images) or (not resourcepath): return None
return "%sfn=%s&pn=%i"%(digiliburlprefix,resourcepath+"/"+images,pn)
def copyTitleToInfoXML(self,RESPONSE=None):
"""copy title from the resource"""
presentationXML=readFieldFromXML(self.metalink,'texttool','presentation')
resourcepath=readFieldFromXML_xpath(self.metalink,'//resource/archive-path')
if (not presentationXML) or (not resourcepath):
if RESPONSE:
RESPONSE.write("Error: %s\n"%self.getId())
else:
return None,self.absolute_url()
try:
fh=file(os.path.join(resourcepath,presentationXML),'w')
fh.write("""<info>
<author></author>
<title>%s</title>
<date></date>
<display>yes</display>
</info>"""%self.title)
fh.close()
return 1,self.getId()
except:
if RESPONSE:
RESPONSE.write("Error: %s\n"%self.getId())
else:
return None,self.absolute_url()
def setStartPage(self,startpage=None,RESPONSE=None):
"""set start page, if no startpage defined use the generic one of the resource"""
if (not (type(startpage)==StringType)):
if ("__generic" in startpage): # checke ob generic in der liste
startpage=self.absolute_url()+"/startpage_html"
elif ("__firstPage" in startpage): # checke ob generic in der liste
startpage=self.createImageUrl()
if (not startpage):
startpage=self.absolute_url()+"/startpage_html"
elif (startpage=="__generic"):
startpage=self.absolute_url()+"/startpage_html"
elif (startpage=="__firstPage"):
startpage=self.createImageUrl()
params="startpage=%s"%startpage
#print 'http://xserve02.mpiwg-berlin.mpg.de:18880/echo_nav/storage/downloadExternalXML?index_meta_url=%s&xml_url=%s'%(self.metalink,self.absolute_url()+'/newMetaXML'+urllib.quote('?'+params))
tries=0
for i in range(10):
x=ECHO_helpers.urlopen('http://xserve02.mpiwg-berlin.mpg.de:18880/echo_nav/storage/downloadExternalXML?index_meta_url=%s&xml_url=%s'%(self.metalink,self.absolute_url()+'/newMetaXML'+urllib.quote('?'+params))).read()
if x=="ok":
break;
path=self.metalink
path=re.sub(self.REQUEST['SERVER_URL'],'',path)
path=re.sub('http://'+self.REQUEST['HTTP_HOST'],'',path)
path=re.sub('http://foxridge.mpiwg-berlin.mpg.de:8080','',path) # falls foxridge als server
path=re.sub('http://foxridge.mpiwg-berlin.mpg.de','',path) # falls foxridge als server
path=re.sub('http://foxridge.rz-berlin.mpg.de:8080','',path) # falls foxridge als server
path=re.sub('http://content.mpiwg-berlin.mpg.de','',path) # falls content als server
path=re.sub('http://foxridge.rz-berlin.mpg.de','',path) # falls foxridge als server
path=re.sub('http://vision.mpiwg-berlin.mpg.de','',path) # falls vision als server
path=re.sub('http://xserve02.mpiwg-berlin.mpg.de:18880','',path) # falls vision als server
path=re.sub('http://echo.mpiwg-berlin.mpg.de','',path) # falls echo
path=re.sub('/index.meta','',path)
ECHO_helpers.urlopen("http://nausikaa2.rz-berlin.mpg.de:86/cgi-bin/toc/admin/reg.cgi?path=%s"%path).readlines()
if RESPONSE is not None:
RESPONSE.redirect('manage_main')
def changeViewerTemplateSetForm(self):
"""change the viewer template set"""
pt=zptFile(self, 'zpt/changeResourceViewerTemplateSet')
return pt()
def setLink(self, link=None):
"""change link field"""
if link is not None:
self.link = link
def getTextToolsField(self,name,default=''):
"""Lese Textoolsfelder aus index.meta im path aus"""
try:
dom=xml.dom.minidom.parse(self.metalink)
node=dom.getElementsByTagName('texttool')[0] #getNode
subnode=node.getElementsByTagName(name)[0]
# bei text wird nur der Folder gebraucht
if name=="text":
splitted=getText(subnode.childNodes).split("/")
return splitted[len(splitted)-2]
else:
return getText(subnode.childNodes)
except:
return default
def changeViewerTemplateSet(self,project,xslt,thumbtemplate,topbar,digiLibTemplate,digiliburlprefix,RESPONSE=None):
"""changeit"""
paramList=['project','startpage','xslt','thumbtemplate','topbar','digiLibTemplate','digiliburlprefix']
#writeMetadata(self.metalink,self.metaDataHash,project,None,xslt,thumbtemplate,topbar,digiLibTemplate)
params="project=%s&xslt=%s&thumbtemplate=%s&topbar=%s&digiLibTemplate=%s&digiliburlprefix=%s"%(project,xslt,thumbtemplate,topbar,digiLibTemplate,digiliburlprefix)
try:
tries=0
for i in range(10):
x=ECHO_helpers.urlopen('http://echo.mpiwg-berlin.mpg.de/echo_nav/storage/downloadExternalXML?index_meta_url=%s&xml_url=%s'%(self.metalink,self.absolute_url()+'/newMetaXML'+urllib.quote('?'+params))).read()
if x=="ok":
break;
except:
logger("ECHO_ressource (changeViewerTemplateSet)", logging.ERROR,"%s (%s)"%sys.exc_info()[0:2])
logger("ECHO_ressource (changeViewerTemplateSet)", logging.ERROR,'http://echo.mpiwg-berlin.mpg.de/echo_nav/storage/downloadExternalXML?index_meta_url=%s&xml_url=%s'%(self.metalink,self.absolute_url()+'/newMetaXML'+urllib.quote('?'+params)))
#print self.absolute_url()+'/newMetaXML'+urllib.quote'?'+params)
# hack Pfad auf die Dokumente
path=self.metalink
path=re.sub('/index.meta','',path)
#TODO: direct access to the file system necessary, fix that also xmlrpc to the server where the index file is stored is possible
parsedUrl=urlparse.urlparse(path)
path=parsedUrl[2]
try:
return ECHO_helpers.urlopen("http://nausikaa2.rz-berlin.mpg.de:86/cgi-bin/toc/admin/reg.cgi?path=%s"%path).readlines()
except:
logger("ECHO_Resource (changeViewerTemplateSet)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
logger("ECHO_Resource (changeViewerTemplateSet)", logging.INFO,"http://nausikaa2.rz-berlin.mpg.de:86/cgi-bin/toc/admin/reg.cgi?path=%s"%path)
if RESPONSE is not None:
RESPONSE.redirect('manage_main')
security.declarePublic('content_html')
def content_html(self):
"""template fuer content"""
return ECHO_basis.content_html(self,'resource')
# def getViewClassification(self):
# if hasattr(self,'viewClassification'):
# return self.viewClassification
# else:
# return ""
def getFullTextXML(self,noredirect=None):
"""getFullTextXML; gives the FullText as an XML Document, and <error></error> if somthing goes wrong."""
try:
#logger("ECHO Fulltext",logging.INFO,"open %s"%self.metalink)
fh=ECHO_helpers.urlopen(self.metalink)
#logger("ECHO Fulltext",logging.INFO,"opened %s"%self.metalink)
dom=xml.dom.minidom.parse(fh)
texttools=dom.getElementsByTagName('texttool')
text=texttools[0].getElementsByTagName('text-url-path') #pfad auf text im neuen system
logging.debug(text);
if (text is not None) and len(text)>0:
texturl=getText(text[0].childNodes)
textBasisUrl=None
if hasattr(self,"getFullTextBasisUrl"):
textBasisUrl=self.getFullTextBasisUrl()
else: #default
textBasisUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/getDoc?doc=%s"
#Beispiel http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/getDoc?doc=/archimedes/la/achil_propo_087_la_1545.xml
logging.debug(textBasisUrl);
texturl=textBasisUrl%texturl
else:
text=texttools[0].getElementsByTagName('text')
texturl=getText(text[0].childNodes)
#TODO: hack has to be romoved, if index.meta for annalen are changed!! (DW)
if (texturl is not None) and (texturl.startswith("/mpiwg/online/permanent/einstein/annalen")):
texturl=texturl.replace("/mpiwg/online/permanent/einstein/annalen/","/diverse/de/")
splitted=texturl.split("/fulltext")
texturl=splitted[0]+".xml"
if hasattr(self,"getFullTextBasisUrl"):
textBasisUrl=self.getFullTextBasisUrl()
else: #default
textBasisUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/getDoc?doc=%s"
#Beispiel http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/getDoc?doc=/archimedes/la/achil_propo_087_la_1545.xml
logging.debug(textBasisUrl);
texturl=textBasisUrl%texturl
#logger("ECHO Fulltext",logging.INFO,"found %s"%texturl)
fh.close()
#logger("ECHO Fulltext",logging.INFO,"closed fh")
#keine url
if not (texturl.split(":")[0] in ['http','ftp','file']):
if not noredirect:
return file(texturl).read()
else:
return texturl
if not noredirect:
self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml')
logger("ECHO Fulltext",logging.INFO,"redirect to:%s"%texturl)
self.REQUEST.RESPONSE.redirect(texturl)
else:
return texturl
except:
logging.debug(sys.exc_info()[0])
logging.debug(sys.exc_info()[1])
logging.debug(sys.exc_info()[2])
if not noredirect:
self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml')
self.REQUEST.RESPONSE.write("<error>no fulltext available</error>")
else:
return "<error>no fulltext available</error>"
def getImagePath(self):
"""gibt pfad zum image aus"""
return self.getImageView(noredirect="yes",onlyPath="yes")
def getArchivePathFromMetadata(self):
try:
archivePath=readFieldFromXML_xpath(self.metalink,"//resource/archive-path")
return archivePath
except:
return ""
def getImageView(self,noredirect=None,onlyPath=None):
"""getImages; give Imageviewr and <error></error> if somthing goes wrong."""
try:
archivePath=readFieldFromXML_xpath(self.metalink,"//resource/archive-path")
archivepath=re.sub('/mpiwg/online/','',archivepath)
imageurl="http://echo.mpiwg-berlin.mpg.de/zogilib?fn="+archivepath+"/"+imagetemp
fh.close()
if not noredirect:
self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml')
self.REQUEST.RESPONSE.redirect(imageurl)
else:
if not onlyPath:
return imageurl
else:
return archivepath+"/"+imagetemp
except:
if not noredirect:
self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml')
self.REQUEST.RESPONSE.write("<error>no fulltext available</error>")
else:
return "<error>no images available</error>"
def getCopyrightsHTML(self):
"""gib (link auf copyright link, mediatyp, institution, copyrightType, label von copyrightType) aus"""
if hasattr(self,'copyrightModel'):
obj=self.copyrightModel
else:
return "ERROR"
ret=[]
for copyright in obj.getCopyrights(): #copyright - media / partner / copyrightID
try:
if hasattr(self.copyrightTypes,copyright[2]):
copyrightTypeObj=getattr(self.copyrightTypes,copyright[2])
link="copyrightTypes/"+copyright[2]+'/copyright.html'
else:
copyrightTypeObj=getattr(obj,copyright[2])
link="copyrightModel/"+copyright[2]+'/copyright.html'
label=copyrightTypeObj.label
url=getattr(copyrightTypeObj, 'url', '')
if url!='':
ret.append((url,copyright[0],copyright[1],copyright[2],label))
else:
if hasattr(copyrightTypeObj, 'copyright.html'):
ret.append(("""%s?partner=%s"""%(link,copyright[1]),copyright[0],copyright[1],copyright[2],label))
else:
ret.append(('empty',copyright[0],copyright[1],copyright[2],label))
except:
"""nothing"""
return ret
def getInstitutionsHTML(self):
"""gibt Liste der foerdernden Institutionen aus"""
if hasattr(self,'support'):
obj=self.support
ret=obj.getSupporter()
return ret
else:
return ''
def getOwnerOriginalsHTML(self):
"""gibt Liste der foerdernden Institutionen aus"""
if hasattr(self,'ownerOriginal'):
obj=self.ownerOriginal
ret=obj.getOwner()
return ret
else:
return ''
def getDigiCopyByHTML(self):
"""gibt Liste der foerdernden Institutionen aus"""
if hasattr(self,'digiCopyBy'):
obj=self.digiCopyBy
ret=obj.getDigiCopyBy()
return ret
else:
return ''
def getCredits(self):
"""Ausgabe der credits"""
if self.credits:
return self.credits
else:
return []
def getStorageManagerResourceURL(self):
"""get the link to storage"""
urlbase=self.getStorageManagerURL();
#now get the path from the metadatalink
path = self.correctPath(self.getMetaDataLink())
if path is None:
return ""
else:
path=path.replace("index.meta","")
return urlbase+path
def correctPath(self,path):
#take only the path of the url which starts with /permanent or /experimental
rs= re.search("/permanent/(.*)", path);
if rs is not None:
txt="permanent/"+rs.group(1)
else:
rs= re.search("/experimental/(.*)", path);
if rs is not None:
txt="experimental"+rs.group(1)
else:
return None
return txt
def __init__(self,id,link,metalink,resourceID,title,label,description,contentType,renderingType,copyrightType,responsible,credits,weight,coords):
self.id = id
"""Festlegen der ID"""
self.label = label
self.link= link
self.metalink=metalink
self.title=title
self.weight=weight
self.credits=toList(credits)
self.description=description
self.contentType=contentType
self.copyrightType=copyrightType
self.renderingType=renderingType
self.responsible=responsible
self.resourceID=resourceID
if coords:
coordsnew=[ string.split(x,",") for x in coords]
else:
coordsnew=[]
self.coords=coordsnew
# self.viewClassification=""
def getContentType(self):
try:
return normalizeCt(self.contentType)
except:
return ""
def getCopyrightType(self):
try:
return self.copyrightType
except:
return ""
def getRenderingType(self):
try:
return self.renderingType
except:
return ""
def ECHO_resource_config(self):
"""Main configuration"""
if not hasattr(self,'weight'):
self.weight=""
pt=zptFile(self, 'zpt/ChangeECHO_resource.zpt')
return pt()
def ECHO_resource_config_main(self):
"""Main configuration"""
if not hasattr(self,'weight'):
self.weight=""
pt=zptFile(self, 'zpt/ChangeECHO_resource_main.zpt')
return pt()
def ECHO_resource_config_coords(self):
"""Coords configuration """
pt=zptFile(self, 'zpt/ChangeECHO_resource_coords.zpt')
return pt()
def ECHO_resource_config_credits(self):
"""Main configuration"""
pt=zptFile(self, 'zpt/ChangeECHO_resource_credits.zpt')
return pt()
def ECHO_resource_config_metadata(self):
"""Main configuration"""
if (hasattr(self,'metadata')) and not (hasattr(self,'metaDataHash')):
self.metaDataHash={}
self.contentType=self.bib_type
for data in self.metadata:
data_neu=re.sub('-','_',data)
self.metaDataHash[data_neu]=getattr(self,data)[0:]
pt=zptFile(self, 'zpt/ChangeECHO_resource_metadata.zpt')
return pt()
def changeViewer(self,newViewer):
"""set newViewer to the url of the new viewer
only if metalink is set, otherwise it gives false
"""
texterUrl="http://nausikaa2.mpiwg-berlin.mpg.de/digitallibrary/servlet/Texter?fn=/"
vl,msg=self.checkValidityOfMetaLink()
if not vl: #ungueltiger link, versuche neuen
newStr=re.match(".*/mpiwg/online/(.*)",self.metalink) # suche pfad hinter /mpiwg/online
oldLink=self.metalink
if newStr:
self.metalink=texterUrl+newStr.group(1)
vl,msg=self.checkValidityOfMetaLink()
else:
logging.error("change Viewer XX(mew Metadatafile) %s"%self.metalink)
vl=False
if not vl: # geht immer noch nicht, dann setzte wieder zurueck
self.metalink=oldLink
logging.info("change Viewer (mew Metadatafile) %s"%self.metalink)
if vl:
self.newViewer=newViewer
return vl,msg
else:
return vl,msg
def checkValidityOfMetaLink(self):
"""checks if the metalink is valid xml"""
ml=self.metalink
try:
txt=urllib.urlopen(ml)
except:
return False,"Cannot open: %s)"%ml
txt.close()
try:
dom = NonvalidatingReader.parseUri(ml)
except:
return False, "Connot parse: %s)"%ml
if len(dom.xpath("//texttool"))==0:
return False, "No texttools: %s)"%ml
return True,""
def changeECHO_resource_main(self,metalink,link,title,label,description,contentType,renderingType,weight,resourceID,newViewer='',RESPONSE=None):
"""Aenderung der Properties"""
self.resourceID=resourceID
self.title=title
self.label=label
self.description=description
self.contentType=contentType
self.renderingType=renderingType
self.weight=weight
self.link=link
self.metalink=metalink
self.newViewer=newViewer
if RESPONSE is not None:
RESPONSE.redirect('manage_main')
def changeECHO_resource_coords(self,RESPONSE=None):
"""Aenderung der Properties - coords"""
#return self.REQUEST
for area in self.getMapAreas():
id = area.getId()
if self.REQUEST.has_key('del.'+id):
# delete this area
self._delObject(id)
# return to same menu
if RESPONSE is not None:
RESPONSE.redirect('ECHO_resource_config_coords')
return
# modify this area
coordstring = self.REQUEST.get('coords.'+id, '')
coords = string.split(coordstring, ',')
angle = self.REQUEST.get('angle.'+id, '0')
type = self.REQUEST.get('type.'+id, 'area')
if len(coords) == 4:
area.setCoordString(coordstring)
area.setAngle(angle)
area.setType(type)
# return to main menu
if RESPONSE is not None:
RESPONSE.redirect('manage_main')
def changeECHO_resource_credits(self,credits,responsible,copyrightType,RESPONSE=None):
"""Aenderung der Properties"""
self.credits=credits
self.responsible=responsible
self.copyrightType=copyrightType
if RESPONSE is not None:
RESPONSE.redirect('manage_main')
def changeECHO_resource_metadata_local(self,RESPONSE=None):
"""change metadata"""
tags=self.findTagsFromMapping(normalizeCt(self.contentType))
for field in tags[1]:
self.metaDataHash[self.getFieldTag(tags,field)]=self.REQUEST.form[self.getFieldTag(tags,field)][0:]
if RESPONSE is not None:
RESPONSE.redirect('manage_main')
def changeECHO_resource_metadata(self,RESPONSE=None):
"""change metadata"""
tags=self.findTagsFromMapping(normalizeCt(self.contentType))
self.OSAS_meta={}
for field in tags[1]:
try:
self.metaDataHash[self.getFieldTag(tags,field)]=self.REQUEST.form[self.getFieldTag(tags,field)]
self.OSAS_meta[self.getFieldTag(tags,field)]=self.REQUEST.form['OSAS_%s'%self.getFieldTag(tags,field)]
except:
logger("ECHO_collection (changeECHO_resource_metadata)",logging.ERROR,"%s (%s)"%sys.exc_info()[0:2])
logging.debug("changeECHO_resource_metadata:"+repr(self.newMetaXML()))
mc = MetaDataClient("http://content.mpiwg-berlin.mpg.de/metaDataServer")
x=mc.writeMetaDataFile(self.getMetaDataLink(),self.newMetaXML(),compressed=None)
logging.debug("changeECHO_resource_metadata (xlrpc return):"+repr(x))
if RESPONSE is not None:
RESPONSE.redirect('manage_main')
def getMDValueSimpleSearchField(self):
"""returns value for simple search"""
try:
return " ".join([self.getMDValue('title',generic="yes"),
self.getMDValue('author',generic="yes"),
self.getMDValue('year',generic="yes"),self.getTitle()])
except:
#logger(" ECHO_collection(getMDSimpleSearchField)",logging.INFO," ".join([self.getMDValue('title',generic="yes"),
# self.getMDValue('author',generic="yes"),
# self.getMDValue('year',generic="yes"),'']))
return ""
def getMDValue(self,fieldNameTest,empty=None,generic=None):
"""get md values"""
#TODO: cache mappinghash
fieldName=None
if generic:
if self.contentType:
ct=self.contentType.replace(" ","_").lower()
ct=self.contentType.replace("-","_").lower()
else:
logger("ECHO_collection (getMDValue)", logging.INFO, "no_content type for %s"%self.getId())
ct=""
#caching
if not hasattr(self,'_v_mapHash'): #noch keine cachevariable
self._v_mapHash={}
tmp=self._v_mapHash.get(ct,None)
if tmp: #teste ob type schon existiert
fieldName=tmp.get(fieldNameTest,None)
else:
self._v_mapHash[ct]={}
#noch nicht gecached
if not fieldName and hasattr(self.getStandardMD(),ct):
fieldName=getattr(self.getStandardMD(),ct).generateMappingHash()[fieldNameTest][0]
self._v_mapHash[ct][fieldNameTest]=fieldName
if not fieldName:
fieldName=fieldNameTest
if not empty:
#FIXME: warum gibt es manchmal kein metadatahas
try:
ret =self.metaDataHash.get(fieldName,'!!NOT USED HERE in Type: %s'%normalizeCt(self.contentType))
except:
logger("ECHO (line 1069)",logging.ERROR,"no md hash for %s"%self.getId())
return ""
else:
ret= self.metaDataHash.get(fieldNameTest,empty)
return unicodify(ret)
getFieldValue=getMDValue #depricated
def newMetaXML(self,project=None,startpage=None,xslt=None,thumbtemplate=None,topbar=None,digiLibTemplate=None,digiliburlprefix=None):
"""new index.meta"""
self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml')
if not hasattr(self,'metaDataHash'):
self.copyIndex_meta2echo_resource()
try:
return writeMetadata(self.metalink,self.OSAS_meta,project,startpage,xslt,thumbtemplate,topbar,digiLibTemplate,digiliburlprefix=digiliburlprefix)
except:
#print self.metalink,self.metaDataHash,project,startpage,xslt,thumbtemplate,topbar,digiLibTemplate,digiliburlprefix
return writeMetadata(self.metalink,self.metaDataHash,project,startpage,xslt,thumbtemplate,topbar,digiLibTemplate,digiliburlprefix=digiliburlprefix)
def showMetaDataXML(self,project=None,startpage=None,xslt=None,thumbtemplate=None,topbar=None,digiLibTemplate=None):
"""return bibliographical metadata as stored in the object"""
try:
return writeMetadata(self.metalink,self.metaDataHash,project,startpage,xslt,thumbtemplate,topbar,digiLibTemplate,xmlfrag="yes")
except:
return "<error> no metadata stored</error>"
def getXQueryMetaData(self,xquery):
'''
execute an xquery on the metadata and returns a list of tuples,
each tuple represent the content of the node as text and the whole node as xml-fragment
@param xquery: xquery auf den metadaten
'''
try:
md=writeMetadata(self.metalink,self.metaDataHash,xmlfrag="yes")
except:
return None
dom = NonvalidatingReader.parseString(md,"http://www.mpiwg-berlin.mpg.de/")
results=Ft.Xml.XPath.Evaluate(xquery, contextNode=dom)
ret=[]
for result in results:
buf = cStringIO.StringIO()
PrettyPrint(result, stream=buf)
str = buf.getvalue()[0:]
buf.close()
ret.append((getTextFromNode(result),str))
return ret
def getMetaDataXML(self,project=None,startpage=None,xslt=None,thumbtemplate=None,topbar=None,digiLibTemplate=None):
"""prints out metadata as stored in the echo environment, format is the index.meta format"""
self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml')
return writeMetadata(self.metalink,self.metaDataHash)
def getMetaDataLink(self):
"""get link to the meta data"""
return self.metalink
def changeECHO_resource(self,metalink,link,title,label,description,contentType,responsible,weight,coords=None,credits=None,RESPONSE=None):
"""Aenderung der Properties"""
setECHO_collectionInformation(self,title,label,description,contentType,responsible,credits,weight)
self.link=link
self.metalink=metalink
if RESPONSE is not None:
RESPONSE.redirect('manage_main')
manage_options = (
{'label':'Main Config','action':'ECHO_resource_config_main'},
{'label':'Change Local Metadata','action':'ECHO_resource_config_metadata'},
{'label':'Sync Metadata with Repository','action':'ECHO_getResourceMD'},
{'label':'Graphic Coords','action':'ECHO_graphicEntry'},
{'label':'Change TemplateSets and Image Viewer','action':'changeViewerTemplateSetForm'},
{'label':'set/change startpage','action':'setStartPageForm'},
{'label':'Copy MD for indexing and search','action':'copySearchFields'},
{'label':'Change AccessRights','action':'changeAccessRightForm'},
) + Folder.manage_options
def isDefinedInThisSet(self,fields,field):
"""checks if field is defined in fields"""
if (fields[0].has_key(field)) and not (fields[0][field]==""):
return 1
else:
return 0
def getFieldLabel(self,fields,field):
"""get labels"""
try:
ret =fields[0][field]
if ret == "":
return field
else:
return ret
except:
return field
def getFieldTag(self,fields,field):
"""get labels"""
try:
ret =fields[0][field]
if ret == "":
return field
else:
return ret
except:
return field
def getMetaDataHash(self):
"""md hash"""
return getattr(self,'metaDataHash',{})
def setFieldValue(self,field,value):
"""get value"""
#TODO: remove setFieldValue
if not hasattr(self,'metaDataHash'):
setattr(self,'metaDataHash',{})
self.metaDataHash[field]=value[0:]
def copySearchFields(self):
"""copys metadatafields to the object"""
# Zunaechst die gnerischen felder
fields=['author','title','year']
for field in fields:
setattr(self,'MD_'+field,self.getMDValue(field,generic="yes"))
# jetzt die spezifischen
for field in self.getMetaDataHash().keys():
if (not field is None) and (not (field in fields)):
logging.debug("ECHO_resource (copySearchFields) mapping: "+field)
logging.debug("ECHO_resource (copySearchFields) mapping value : "+self.getMDValue(field))
setattr(self,'MD_'+field,self.getMDValue(field))
def findLabelsFromMapping(self,referenceType):
"""gib hash mit label -> generic zurueck"""
#return {},[]
temp=self.ZopeFind(self.getStandardMD())
if referenceType=="":
referenceType="book"
bibdata={}
retdata={}
fields=[]
fieldlist=self.getStandardMD().fieldList
tags=self.findTagsFromMapping(normalizeCt(self.contentType))
logging.debug("ECHO_resource(findLabelsFromMapping)"+repr(tags))
self.referencetypes=tags[2]
for referenceTypeF in self.referencetypes:
logging.debug("--- compare"+normalizeCt(referenceTypeF[1].title)+normalizeCt(referenceType.lower()))
if normalizeCt(referenceTypeF[1].title) == normalizeCt(referenceType.lower()):
try:
bibdata[referenceTypeF[1].title]=referenceTypeF[1].getUsedFields()
referenceType=referenceTypeF[1].title
logging.debug("------fields:"+repr(bibdata[referenceTypeF[1].title]))
except:
bibdata[referenceType]=referenceTypeF[1].getUsedFields()
bibdata['data']=referenceTypeF[1]
fields=bibdata[referenceType]
for field in fieldlist:
retdata[field]=referenceTypeF[1].getValue(field)[1]
return retdata,fieldlist,temp,fields
def findTagsFromMapping(self,referenceType):
"""gib hash mit label -> generic zurueck"""
if referenceType=="":
referenceType="book"
temp = self.ZopeFind(self.getStandardMD())[0:]
#self.referencetypes=temp[0:]
bibdata={}
retdata={}
fieldlist=self.getStandardMD().fieldList
fields=[]
for referenceTypeF in temp:
#print referenceType
if normalizeCt(referenceTypeF[1].title) == normalizeCt(referenceType.lower()):
try:
bibdata[referenceTypeF[1].title]=referenceTypeF[1].getUsedFields()
referenceType=referenceTypeF[1].title
except:
logging.debug("Error in ECHOresource(findTagsFromMapping): %s %s"%(sys.exc_info()[0],sys.exc_info()[1]))
logging.debug(referenceTypeF)
#TODO:CCCC
bibdata[referenceType]=referenceTypeF[1].getUsedFields()
bibdata['data']=referenceTypeF[1]
fields=bibdata[referenceType]
for field in fieldlist:
retdata[field]=referenceTypeF[1].getValue(field)[0]
return retdata,fieldlist,temp,fields
security.declarePublic('copyIndex_meta2echo_resource') # has to be change, presentlyset because of OSAS koordination
def copyIndex_meta2echo_resource(self,RESPONSE=None):
"""copy MD von Index_meta to the echo_resource"""
(metadict, error)=readMetadata(self.metalink)
logging.debug(metadict)
self.metaDataHash={}
if not error=="": #Fehler beim Auslesen des Metafiles
return "ERROR:",error,self.absolute_url()
self.contentType=normalizeCt(metadict['bib_type'])[0:]
fields=self.findTagsFromMapping(normalizeCt(self.contentType))
#fields=self.findLabelsFromMapping(normalizeCt(self.contentType))
for field in fields[1]:
if self.isDefinedInThisSet(fields,field):
#print urllib.unquote(metadict.get(self.getFieldTag(fields,field),''))
self.setFieldValue(self.getFieldTag(fields,field),metadict.get(self.getFieldTag(fields,field),''))
if RESPONSE:
return RESPONSE.redirect('manage_main')
return "OK:",self.absolute_url(),normalizeCt(self.contentType)
def ECHO_getResourceMD(self,template="yes",back=None,overwrite="no"):
"""Einlesen der Metadaten und Anlegen dieser Metadaten als Informationen zur Resource"""
(metadict, error)=readMetadata(self.metalink)
logging.debug("METADICT:")
logging.debug(metadict)
if back:
self.REQUEST.SESSION['back']=back
if not error=="": #Fehler beim Auslesen des Metafiles
return "ERROR:",error
if (not self.contentType) or (overwrite=="yes"):
self.contentType=normalizeCt(normalizeCt(metadict['bib_type']).lower())
if not (normalizeCt(metadict['bib_type']).lower()==normalizeCt(self.contentType).lower()):
self.REQUEST.SESSION['contentStorage']=normalizeCt(metadict['bib_type'])
self.REQUEST.SESSION['contentZope']=normalizeCt(self.contentType)
return zptFile(self, 'zpt/ECHO_getResourceMDErrorContentType.zpt')()
#self.REQUEST.SESSION['metadict']=metadict
self.REQUEST.SESSION['diffs']=checkDiffs(self,metadict)
if template=="yes":
#pt=PageTemplateFile(os.path.join(package_home(globals()), 'zpt/ECHO_resourceMD.zpt'),metadict=metadict).__of__(self)
pt=zptFile(self, 'zpt/ECHO_resourceMD.zpt')
return pt(metadict=metadict)
def ECHO_getMD(self,item):
"""Ausgabe der MD"""
return getattr(self,item)
def checkRDF(self,path):
"""check if pdf in the path"""
try:
for fileName in os.listdir(path):
if os.path.splitext(fileName)[1]==".pdf":
return os.path.join(path,fileName)
return None
except:
return None
security.declareProtected('View','index_html')
def index_html(self):
"""standard page"""
pdf=self.checkRDF(self.link)
if pdf:
fh=file(pdf,'r').read()
self.REQUEST.RESPONSE.setHeader('Content-Type','application/pdf')
self.REQUEST.RESPONSE.write(fh)
self.REQUEST.RESPONSE.close()
return
if getattr(self,'newViewer',''): #benutze den neuen viewer
url=self.newViewer+'url='+self.metalink+"&mode=texttool"
return self.REQUEST.RESPONSE.redirect(url)
return self.REQUEST.RESPONSE.redirect(self.link)
def startpage_html(self):
"""prints out a startpage for a resource for use e.g. in the BVE"""
# suche ob startpage.html in dem Ordner vorhanden ist, dann wir diese angezeigt
sp=self.ZopeFind(self,obj_ids=['startpage.html'])
if sp:
return sp[1]()
#pruefen ob irgendwo ein template
if hasattr(self,'startpage_index_template'):
return self.startpage_index_template()
#generisches template ausgeben
pt=zptFile(self, 'zpt/ECHO_startpage_index_template_standard.zpt')
pt.content_type="text/html"
return pt()
def toc_html(self):
sp=self.ZopeFind(self,obj_ids=['toc.html'])
if sp:
return sp[0][1]()
security.declarePublic('generate_label') # has to be change, presentlyset because of OSAS koordination
def generate_label(self):
"""Erzeugt_standard_Label aus Template"""
templateName="label_template_"+normalizeCt(self.contentType).lower();
if hasattr(self, templateName):
pt=getattr(self,templateName)
self.title=pt()[0:]
return pt()
else:
pt=getattr(self.metadata,templateName)
mdHash={}
#mdHash={"author":self.getMDValue('author'),"title":self.getMDValue('title'),"year":self.MD_year}
#logging.debug(mdHash)
logging.debug("new format for template")
fields=['author','title','year']
for field in fields:
mdHash[field]=self.getMDValue(field);
# jetzt die spezifischen
for field in self.getMetaDataHash().keys():
if (not field is None) and (not (field in fields)):
logging.debug(field)
mdHash[field]=self.getMDValue(field);
self.title=pt(md=mdHash)[0:]
return pt(md=mdHash)[0:]
security.declarePublic('generate_title') # has to be change, presently set because of OSAS koordination
def generate_title(self,RESPONSE=None):
"""Erzeugt_standard_Label aus Template"""
templateName="label_template_"+normalizeCt(self.contentType).lower();
if hasattr(self, templateName):
pt=getattr(self,templateName)
self.title=pt()[0:]
return pt()
else:
pt=getattr(self.metadata,templateName)
mdHash={}
#mdHash={"author":self.getMDValue('author'),"title":self.getMDValue('title'),"year":self.MD_year}
#logging.debug(mdHash)
logging.debug("new format for template")
fields=['author','title','year']
for field in fields:
mdHash[field]=self.getMDValue(field);
# jetzt die spezifischen
for field in self.getMetaDataHash().keys():
if (not field is None) and (not (field in fields)):
logging.debug(field)
mdHash[field]=self.getMDValue(field);
self.title=pt(md=mdHash)[0:]
return pt(md=mdHash)[0:]
Globals.InitializeClass(ECHO_resource)
def manage_addECHO_resourceForm(self):
"""Form for adding a ressource"""
pt=zptFile(self, 'zpt/AddECHO_resourceForm.zpt')
return pt()
def manage_addECHO_resource(self,id,title,label,description="",responsible="",link="",metalink="",weight="",copyrightType=None,resourceID=None,contentType=None,renderingType=None,credits=None,coords=None,RESPONSE=None):
"""addresource"""
newObj=ECHO_resource(id,link,metalink,resourceID,title,label,description,contentType,renderingType,copyrightType,responsible,credits,weight,coords)
self._setObject(id,newObj)
if RESPONSE is not None:
RESPONSE.redirect('manage_main')
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/cvs/cvsweb/icons/back.gif){kind=icon}
Return to ECHO_resource.py CVS log ![[TXT]](/cvs/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvs/cvsweb/icons/dir.gif){kind=icon}
Up to [Repository] / ECHO_content