--- ECHO_content/ECHO_collection.py 2004/10/06 13:02:56 1.176 +++ ECHO_content/ECHO_collection.py 2004/11/29 21:55:29 1.193 @@ -9,7 +9,13 @@ class ECHO_externalLink contains informa """ +from reportlab.pdfgen import canvas +from reportlab.lib.pagesizes import A4 + + + import string +import tempfile import re import os import OFS.Image @@ -29,8 +35,9 @@ from Products.PageTemplates.PageTemplate from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate from Globals import Persistent, package_home from Acquisition import Implicit -from ECHO_helpers import displayTypes + import urllib +import smtplib import time from Ft.Xml.Domlette import NonvalidatingReader from Ft.Xml.Domlette import PrettyPrint @@ -38,6 +45,7 @@ from Ft.Xml import EMPTY_NAMESPACE import Ft.Xml.XPath import cStringIO +import zLOG try: from psycopg import libpq @@ -53,38 +61,9 @@ import urllib import xml.dom.minidom from ECHO_graphicalOverview import javaHandler,javaScriptMain import ECHO_helpers +from ECHO_helpers import * +from ECHO_language import * -def donatus(txt2): - import xmlrpclib - - server = xmlrpclib.ServerProxy("http://archimedes.fas.harvard.edu/cgi-bin/donatus-rpc") - - txt=txt2.encode('utf-8') - bin=xmlrpclib.Binary(txt) - - - - ret=server.donatus.analyze(bin) - - - return ret['morphData'].data - - -def donatusVariant2Lemma(morphData): - """creates hash variant -> morphdata""" - ret={} - dom=xml.dom.minidom.parseString(morphData) - lemmas=dom.getElementsByTagName('lemma') - for lemma in lemmas: - variants=lemma.getElementsByTagName('variant') - for variant in variants: - atr=variant.getAttribute('form') - if ret.has_key(atr): - ret[atr].append=lemma.getAttribute('form') - else: - ret[atr]=[lemma.getAttribute('form')] - - return ret #regexp for extracting elements from xml patternTXT=r"<\s*txt.*?>(.*?)" @@ -93,391 +72,6 @@ patternPage=r"<\s*page.*?>(.*?)" regexpPage = re.compile(patternPage, re.IGNORECASE + re.DOTALL) -def ECHO_rerenderLinksMD(self,obj=None,types=['title','label']): - """Rerender all Links""" - ret="" - - if not obj: - obj = self - - entries=obj.ZopeFind(obj,obj_metatypes=['ECHO_resource'],search_sub=1) - - for entry in entries: - if entry[1].meta_type == 'ECHO_resource': - try: - entry[1].ECHO_getResourceMD(template="no") - if "title" in types: - entry[1].generate_title() - if "label" in types: - entry[1].generate_label() - ret+="OK:"+entry[0]+"-- "+entry[1].getTitle().decode('utf-8')+"-- "+entry[1].getTitle().decode('utf-8')+"
" - except: - ret+="Error:"+entry[0]+"
" - - - - - return ""+ret+"Rerenderd all links to resources in: "+self.title+"" - -def reloadMetaDataFromStorage(self,RESPONSE=None): - """copy metadata from the storage to ECHO""" - ret="" - resources=self.ZopeFind(self,obj_metatypes=['ECHO_resource'],search_sub=1) - - for resource in resources: - x=str(resource[1].copyIndex_meta2echo_resource())+"
" - ret+=x - #print x - - - if RESPONSE is not None: - #RESPONSE.redirect('./manage_main') - return ""+ret+"" - - return ret - -def getRDFDescription(self,linkURL,urn=None,nameDef=None,typeName=None): - """rdf""" - - ret="" - about="""""" - name="""%s""" - link="""%s""" - clickable="""%s""" - #link="""""" - type="""%s""" - #xlink="""""" - if not urn: - #urn="urn:"+re.sub('/',':',self.absolute_url()) - urn=self.absolute_url() - about2=about%urn - if not nameDef: - if hasattr(self,'label') and not (self.label==""): - name2=name%self.label - elif not self.title=="": - name2=name%self.title - else: - name2=name%self.getId() - - name2=re.sub('&','&',name2) - else: - name2=name%nameDef - - linkURL=re.sub('http:','',linkURL) - linkURL2=re.sub('&','&',linkURL) - link2=link%(("http:"+linkURL2),("http:"+urllib.quote(linkURL))) - clickable2=clickable%"true" - - if not typeName: - type2=type%self.meta_type - else: - type2=type%typeName - - #ret=about2+"\n"+name2+"\n"+link2+"\n"+type2+"\n"+clickable2+"\n" - ret=about2+"\n"+name2+"\n"+type2+"\n"+clickable2+"\n" - return ret - -def getCopyrightsFromForm(self,argv): - medias={} - partners={} - copyrights={} - - copyrightsFinal=[] - for arg in argv.keys(): - - if arg[0:5]=='media': - nm=int(arg[5:]) - medias[nm]=argv[arg] - elif arg[0:5]=='partn': - nm=int(arg[5:]) - partners[nm]=argv[arg] - elif arg[0:5]=='copyr': - nm=int(arg[5:]) - copyrights[nm]=argv[arg] - - - - copyrightsList=[(medias[nm],partners[nm],copyrights[nm]) for nm in medias.keys()] - for copyright in copyrightsList: - - if copyright[2]=='institution0000': - copyrightsFinal.append((copyright[0],copyright[1],self.getPartnerCopyright(copyright[1],''))) - else: - if not copyright[0]=='': - copyrightsFinal.append(copyright) - - - return copyrightsFinal - -#List of different types for the graphical linking viewer -viewClassificationListMaster=['view point','area'] - - -def checkDiffs(self,metadict): - """check differences""" - - - - - def NoneToEmpty(obj): - if obj: - return obj - else: - return "" - - - - diffs={} - - tags=self.findTagsFromMapping(self.contentType) - self.referencetypes=tags[2] - self.fields=tags[3] - - - for field in tags[1]: - try: - if (NoneToEmpty(self.getFieldValue(self.getFieldTag(tags,field)))==metadict[self.getFieldTag(tags,field)]): - diffs[self.getFieldTag(tags,field)]=1 - else: - - diffs[self.getFieldTag(tags,field)]=0 - except: - diffs[self.getFieldTag(tags,field)]=0 - - return diffs - -def content_html(self,type): - """template fuer content""" - #templates = self.ZopeFind(self.aq_parent,obj_ids=[type+"_template"]) - # - #if templates: - # return templates[0][1]() - - if hasattr(self,type+"_template"): - obj=getattr(self,type+"_template") - return obj() - else: - pt=PageTemplateFile('Products/ECHO_content/zpt/ECHO_%s_template_standard.zpt'%type).__of__(self) - pt.content_type="text/html" - return pt() - -def toList(field): - """Einzelfeld in Liste umwandeln""" - if type(field)==StringType: - return [field] - else: - return field - -def getText(nodelist): - - rc = "" - for node in nodelist: - if node.nodeType == node.TEXT_NODE: - rc = rc + node.data - return rc - -def getTextFromNode(nodename): - nodelist=nodename.childNodes - rc = "" - for node in nodelist: - if node.nodeType == node.TEXT_NODE: - rc = rc + node.data - return rc - -def sendFile(self, filename, type): - """sends an object or a local file (in the product) as response""" - paths = filename.split('/') - object = self - # look for an object called filename - for path in paths: - if hasattr(object, path): - object = getattr(object, path) - else: - object = None - break - if object: - # if the object exists then send it - return object.index_html(self.REQUEST.REQUEST, self.REQUEST.RESPONSE) - else: - # send a local file with the given content-type - fn = os.path.join(package_home(globals()), filename) - self.REQUEST.RESPONSE.setHeader("Content-Type", type) - self.REQUEST.RESPONSE.write(file(fn).read()) - return - -class BrowserCheck: - """check the browsers request to find out the browser type""" - - def __init__(self, zope): - self.ua = zope.REQUEST.get_header("HTTP_USER_AGENT") - self.isN4 = (string.find(self.ua, 'Mozilla/4.') > -1) and (string.find(self.ua, 'MSIE') < 0) - self.isIE = string.find(self.ua, 'MSIE') > -1 - self.nav = self.ua[string.find(self.ua, '('):] - ie = string.split(self.nav, "; ")[1] - if string.find(ie, "MSIE") > -1: - self.versIE = string.split(ie, " ")[1] - self.isMac = string.find(self.ua, 'Macintosh') > -1 - self.isWin = string.find(self.ua, 'Windows') > -1 - self.isIEWin = self.isIE and self.isWin - self.isIEMac = self.isIE and self.isMac - - - - -def writeMetadata(url,metadict,project=None,startpage=None,xslt=None,thumbtemplate=None,topbar=None,digiLibTemplate=None,xmlfrag=None,digiliburlprefix=None): - """Einlesen der Metadaten und und erstellen des geaenderten XML file""" - - def updateTextToolNode(tag,value): - #print dom,tag,value - metanode=dom.getElementsByTagName('texttool')[0] - try: - nodeOld=metanode.getElementsByTagName(tag) - except: - nodeOld=None - - if nodeOld: - metanode.removeChild(nodeOld[0]).unlink() - - node=dom.createElement(tag) - nodetext=dom.createTextNode(value) - node.appendChild(nodetext) - metanode.appendChild(node) - - if xmlfrag: - geturl=""" - - - - - - """ - dom=xml.dom.minidom.parseString(geturl) - else: - 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) - except: - return (None,"Cannot parse: "+url+"
"+geturl) - - - - metanodes=dom.getElementsByTagName('bib') - - if not metanodes: - metanodes=dom.getElementsByTagName('archimedes') - - metanode=metanodes[0] - - for metaData in metadict.keys(): - - try: - nodeOld=metanode.getElementsByTagName(metaData) - except: - nodeOld=None - - if nodeOld: - metanode.removeChild(nodeOld[0]).unlink() - else: - # try also old writing rule - instead of _: - try: - nodeOld=metanode.getElementsByTagName(re.sub('_','-',metaData)) - except: - nodeOld=None - - if nodeOld: - metanode.removeChild(nodeOld[0]).unlink() - - metanodeneu=dom.createElement(metaData) - metanodetext=dom.createTextNode(metadict[metaData]) - #try: - #metanodetext=dom.createTextNode(unicode(metadict[metaData],"utf-8")) - #except: - #metanodetext=dom.createTextNode(metadict[metaData].encode('utf-8')) - metanodeneu.appendChild(metanodetext) - metanode.appendChild(metanodeneu) - - - - - - if project: - updateTextToolNode('project',project) - - if startpage: - updateTextToolNode('startpage',startpage) - - if topbar: - updateTextToolNode('toptemplate',topbar) - - if thumbtemplate: - updateTextToolNode('thumbtemplate',thumbtemplate) - - if xslt: - updateTextToolNode('xslt',xslt) - - - if digiliburlprefix: - updateTextToolNode('digiliburlprefix',digiliburlprefix) - - try: - return dom.toxml().encode('utf-8') - except: - return dom.toxml('utf-8') - - - -def readMetadata(url): - """Methode zum Auslesen der Metadateninformation zu einer Resource - Vorerst noch Typ bib""" - - metadict={} - 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) - except: - return (None,"Cannot parse: "+url+"
"+geturl) - - metanode=dom.getElementsByTagName('bib') - metadict['bib_type']='Book' - if len(metanode)==0: - metanode=dom.getElementsByTagName('archimedes') - metadict['bib_type']='Archimedes' - - - if not len(metanode)==0: - metacontent=metanode[0].childNodes - - try: - metadict['bib_type']=getText(dom.getElementsByTagName('bib')[0].attributes['type'].childNodes) - except: - """nothing""" - - for node in metacontent: - try: - #print urllib.unquote(getText(node.childNodes)),getText(node.childNodes) - metadict[re.sub('-','_',node.tagName.lower())]=urllib.unquote(getText(node.childNodes)) - except: - """nothing""" - - - return metadict,"" - def setECHO_collectionInformation(self,title,label,description,contentType,responsible,credits,weight,coordstrs,viewClassification=""): @@ -510,7 +104,7 @@ def setECHO_collectionInformation(self,t self.coords=coords[0:] -class ECHO_copyright(Folder): +class ECHO_copyright(Folder,ECHO_basis): """Copyright informationen""" meta_type="ECHO_copyright" @@ -566,7 +160,7 @@ def manage_addECHO_copyright(self, id,ti if RESPONSE is not None: RESPONSE.redirect('manage_main') -class ECHO_layoutTemplate(ZopePageTemplate): +class ECHO_layoutTemplate(ZopePageTemplate,ECHO_basis): """Create a layout Template for different purposes""" meta_type="ECHO_layoutTemplate" @@ -589,7 +183,7 @@ class ECHO_layoutTemplate(ZopePageTempla def manage_addECHO_layoutTemplateForm(self): """Form for adding""" - pt=PageTemplateFile('Products/ECHO_content/zpt/AddECHO_layoutTemplate.zpt').__of__(self) + pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt/AddECHO_layoutTemplate.zpt')).__of__(self) return pt() from urllib import quote @@ -634,127 +228,11 @@ def manage_addECHO_layoutTemplate(self, REQUEST.RESPONSE.redirect(u+'/manage_main') return '' -class ECHO_fullText(ZopePageTemplate): +class ECHO_fullText(ZopePageTemplate,ECHO_basis,ECHO_language): """echo fulltext in xml""" meta_type="ECHO_fullText" - def donatusVariant2Lemma(self,nr='1'): - """analyze by donatus""" - return donatusVariant2Lemma(donatus(self.lemmatize(nr))) - - def tagLex(self,nr="1"): - """generate Links""" - global retLex - global toggle - - toggle=0 - retLex="" - - lemmatized=self.lemmatize(nr)[0:] - #print "ho",repr(lemmatized) - variants=donatusVariant2Lemma(donatus(lemmatized)) - - def createTag(name,attrs): - global toggle - - if name=="w": - toggle=1 - return "" - else: - tag="<" - tag+=name - for attr in attrs.keys(): - tag+=""" %s="%s" """%(attr,attrs[attr]) - tag+=">" - return tag - - def createData(data): - global toggle - astring="""%s """ - if toggle: # tag war ein w - toggle=0 - if variants.has_key(data): - return astring%(variants[data][0],data) - else: - return astring%(data,data) - - - - # 3 handler functions - def start_element(name, attrs): - global retLex - - retLex+=createTag(name,attrs) - def end_element(name): - global retLex - if not name=="w": - retLex+=""%(name.encode('utf-8')) - - - def char_data(data): - global retLex - if data: - try: - retLex+=createData(data) - except: - """no""" - - p = xml.parsers.expat.ParserCreate() - - p.StartElementHandler = start_element - p.EndElementHandler = end_element - p.CharacterDataHandler = char_data - - p.Parse(lemmatized.encode('utf-8'),1) - #print repr(lemmatized.encode('utf-8')) - - return retLex - - - def lemmatize(self,nr='1',lang="de"): - """lemmatize""" - global ret - ret="" - - def createTag(name,attrs): - tag="<" - tag+=name - for attr in attrs.keys(): - tag+=""" %s="%s" """%(attr,attrs[attr]) - tag+=">" - return tag - - def insertW(str): - splitted=str.split() - wordlist=["%s"%split for split in splitted] - return string.join(wordlist,'\n') - - # 3 handler functions - def start_element(name, attrs): - global ret - ret+=createTag(name,attrs) - def end_element(name): - global ret - ret+=""%(name.encode('utf-8')) - - def char_data(data): - global ret - ret+=insertW(data) - - p = xml.parsers.expat.ParserCreate() - - p.StartElementHandler = start_element - p.EndElementHandler = end_element - p.CharacterDataHandler = char_data - - p.Parse(self.getPage(nr), 1) - txt=""" -
%s
- """ - ret=txt%(lang,ret) - - return ret def getPage(self,nr='1'): """get page n""" @@ -800,7 +278,8 @@ def manage_addECHO_fullText(self, id, ti REQUEST.RESPONSE.redirect(u+'/manage_main') return '' -class ECHO_resource(Folder,Persistent): + +class ECHO_resource(Folder,Persistent,ECHO_basis): """ECHO Ressource""" security=ClassSecurityInfo() meta_type='ECHO_resource' @@ -811,65 +290,97 @@ class ECHO_resource(Folder,Persistent): security.declareProtected('View','index_html') - def showRDF(self): - """showrdf""" - self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml') - ret="""\n\n""" - ret+=self.getRDF(urn="echo:colllectionroot")+"\n" + + + 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) + - ret+="""""" - return ret + tmpZip=tempfile.mktemp(dir=tempdir) - def getRDF(self,urn=None): - """rdf""" - ret=getRDFDescription(self,self.link,urn=urn) - return ret+self.createSubElementRDF(urn=urn) + tmpFn=os.path.split(tmpZip)[1] - def createSubElementRDF(self,urn=None): - """rdf list""" - if not urn: - urn=self.absolute_url() - ret="" + + - rettemp="""\n"""%urn - flag=0 - - li="""\n""" - if not ('' in self.getFullTextXML(noredirect='Yes')): - nurn=self.absolute_url()+'/getFullTextXML' - rettemp+=li%nurn - flag=1 - if not ('' in self.getImageView(noredirect='Yes')): - nurn=self.absolute_url()+'/getImageView' - rettemp+=li%nurn - flag=1 + if RESPONSE: + RESPONSE.setHeader("Content-Type","text/html") + RESPONSE.write("

I am creating the pdf

") + txt="

1. step: getting the images( %i pages)

"%pages + RESPONSE.write(txt) + + c=canvas.Canvas(tmpZip) + for i in range(1,pages+1): + if RESPONSE: + RESPONSE.write(str("

Get Page: %i
\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() + - if not ('' in self.showMetaDataXML()): - nurn=self.absolute_url()+'/showMetaDataXML' - rettemp+=li%nurn - flag=1 - - rettemp+="" + c.drawImage(fn,0,0,width=width,height=height) + c.showPage() + c.save() + if RESPONSE: + RESPONSE.write("

finished
\n") - if flag==1: - ret+=rettemp - - if not ('' in self.getFullTextXML(noredirect='Yes')): - nurn=self.absolute_url()+'/getFullTextXML' - ret+=getRDFDescription(self,self.absolute_url()+'/getFullTextXML',urn=nurn,nameDef="Fulltext",typeName="ECHO_fulltext") - - if not ('' in self.getImageView(noredirect='Yes')): - nurn=self.absolute_url()+'/getImageView' - ret+=getRDFDescription(self,self.absolute_url()+'/getImageView',urn=nurn,nameDef="Image View",typeName="ECHO_imageview") - - if not ('' in self.showMetaDataXML()): - nurn=self.absolute_url()+'/showMetaDataXML' - ret+=getRDFDescription(self,self.absolute_url()+'/showMetaDataXML',urn=nurn,nameDef="Metadata",typeName="ECHO_metaData") + if RESPONSE: + len=os.stat(tmpZip)[6] + downloadUrl=self.absolute_url()+"/downloadPDF" + RESPONSE.write("""

Click here for download ( %i Byte)

\n"""%(tmpFn,len)) + RESPONSE.write("""

The file will be stored for a while, you can download it later, the URL is:

+

%s?fn=%s\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() - return ret - + + def getRDF(self,urn=None): + """rdf""" + ret=getRDFDescription(self,self.link,urn=urn) + return ret+self.createSubElementRDF(urn=urn) + + def getAccessRightSelectorHTML(self,outlook="select"): """htmlselector""" values=['free','mpiwg'] @@ -1011,19 +522,73 @@ class ECHO_resource(Folder,Persistent): pt.content_type="text/html" return pt() + + def createImageUrl(self,pn=1): + """create ImageUrl""" + + + resourcepath=readFieldFromXML(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): + zLOG.LOG("ECHO (createImageUrl)",zLOG.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(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(""" + + %s + + yes + """%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)) and ("__generic" in startpage): # checke ob generic in der liste + 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" - - if (not startpage) or (startpage=="__generic"): - 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)) + 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() @@ -1031,13 +596,14 @@ class ECHO_resource(Folder,Persistent): 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.rz-berlin.mpg.de','',path) # falls vision 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) @@ -1053,6 +619,7 @@ class ECHO_resource(Folder,Persistent): return pt() + def getTextToolsField(self,name,default=''): """Lese Textoolsfelder aus index.meta im path aus""" @@ -1113,25 +680,11 @@ class ECHO_resource(Folder,Persistent): RESPONSE.redirect('manage_main') - def getTitle(self): - """title""" - try: - return self.title.encode('utf-8','ignore') - except: - self.title=self.title.decode('iso-8859-1','ignore')[0:] #correnct conding error - return self.title.encode('utf-8','ignore') - - def getLabel(self): - """title""" - try: - return self.label.encode('utf-8','ignore') - except: - self.label=self.label.decode('iso-8859-1','ignore')[0:] #correnct conding error - return self.label.encode('utf-8','ignore') + def content_html(self): """template fuer content""" - return content_html(self,'resource') + return ECHO_basis.content_html(self,'resource') def getViewClassification(self): if hasattr(self,'viewClassification'): @@ -1141,17 +694,29 @@ class ECHO_resource(Folder,Persistent): def getFullTextXML(self,noredirect=None): """getFullTextXML; gives the FullText as an XML Document, and if somthing goes wrong.""" + try: + #zLOG.LOG("ECHO Fulltext",zLOG.INFO,"open %s"%self.metalink) fh=ECHO_helpers.urlopen(self.metalink) + #zLOG.LOG("ECHO Fulltext",zLOG.INFO,"opened %s"%self.metalink) dom=xml.dom.minidom.parse(fh) texttools=dom.getElementsByTagName('texttool') text=texttools[0].getElementsByTagName('text') texturl=getText(text[0].childNodes) + + #zLOG.LOG("ECHO Fulltext",zLOG.INFO,"found %s"%texturl) + fh.close() + #zLOG.LOG("ECHO Fulltext",zLOG.INFO,"closed fh") + #keine url if not (texturl.split(":")[0] in ['http','ftp','file']): - texturl=re.sub("//","/",texturl) - #return texturl+"::"+texturl.split(":")[0] + if not noredirect: + return file(texturl).read() + else: + return texturl + if not noredirect: self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml') + zLOG.LOG("ECHO Fulltext",zLOG.INFO,"redirect to:%s"%texturl) self.REQUEST.RESPONSE.redirect(texturl) else: return texturl @@ -1163,8 +728,11 @@ class ECHO_resource(Folder,Persistent): else: return "no fulltext available" - - def getImageView(self,noredirect=None): + def getImagePath(self): + """gibt pfad zum image aus""" + return self.getImageView(noredirect="yes",onlyPath="yes") + + def getImageView(self,noredirect=None,onlyPath=None): """getImages; give Imageviewr and if somthing goes wrong.""" try: fh=ECHO_helpers.urlopen(self.metalink) @@ -1177,11 +745,16 @@ class ECHO_resource(Folder,Persistent): archivepath=getText(text[0].childNodes) 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: - return imageurl + if not onlyPath: + return imageurl + else: + return archivepath+"/"+imagetemp except: if not noredirect: @@ -1423,9 +996,13 @@ class ECHO_resource(Folder,Persistent): RESPONSE.redirect('manage_main') - def getMDValue(self,fieldName): - return self.metaDataHash.get(fieldName,'!!NOT USED HERE in Type: %s'%self.contentType) - + def getMDValue(self,fieldName,empty=None): + if empty: + return self.metaDataHash.get(fieldName,'!!NOT USED HERE in Type: %s'%self.contentType) + + else: + return self.metaDataHash.get(fieldName,empty) + 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') @@ -1709,10 +1286,27 @@ class ECHO_resource(Folder,Persistent): 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 + + def index_html(self): """standard page""" - + pdf=self.checkRDF(self.link) + if pdf: + fh=file(pdf,'r').read() + self.REQUEST.RESPONSE.setHeader('Content-Type','x-Application/pdf') + self.REQUEST.RESPONSE.write(fh) + self.REQUEST.RESPONSE.close() + return return self.REQUEST.RESPONSE.redirect(self.link) def startpage_html(self): @@ -1782,30 +1376,15 @@ def manage_addECHO_resource(self,id,titl RESPONSE.redirect('manage_main') -class ECHO_externalLink(Folder): +class ECHO_externalLink(Folder,ECHO_basis): """Link zu einer externen Ressource""" security=ClassSecurityInfo() meta_type='ECHO_externalLink' - def getTitle(self): - """title""" - try: - return self.title.encode('utf-8','ignore') - except: - self.title=self.title.decode('iso-8859-1','ignore')[0:] #correnct conding error - return self.title.encode('utf-8','ignore') - - def getLabel(self): - """title""" - try: - return self.label.encode('utf-8','ignore') - except: - self.label=self.label.decode('iso-8859-1','ignore')[0:] #correnct conding error - return self.label.encode('utf-8','ignore') def content_html(self): """template fuer content""" - return content_html(self,'externalLink') + return ECHO_basis.content_html(self,'externalLink') def __init__(self,id,link,title,label,description,contentType,responsible,credits,weight,coords): @@ -1889,9 +1468,9 @@ class ECHO_link(ECHO_externalLink): def content_html(self): """template fuer link""" if hasattr(self,"link_template"): - return content_html(self,'link') + return ECHO_basis.content_html(self,'link') else: - return content_html(self,'collection') + return ECHO_basis.content_html(self,'collection') def manage_addECHO_linkForm(self): """Form for external Links""" @@ -1910,7 +1489,7 @@ def manage_addECHO_link(self,id,title,la RESPONSE.redirect('manage_main') -class ECHO_collection(Folder, Persistent, Implicit, Cacheable): +class ECHO_collection(Folder, Persistent, Implicit, Cacheable,ECHO_basis): """ECHO Collection""" security=ClassSecurityInfo() @@ -1942,17 +1521,6 @@ class ECHO_collection(Folder, Persistent ret+=li%nurn return ret+"" - - def showRDF(self): - """showrdf""" - self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml') - ret="""\n\n""" - ret+=self.getRDF(urn="echo:collectionroot")+"\n" - - ret+="""""" - - return ret - def changeLabels(self): @@ -2165,8 +1733,28 @@ class ECHO_collection(Folder, Persistent if RESPONSE is not None: RESPONSE.redirect('manage_main') + def copyTitleToInfoXMLFolder(self,RESPONSE=None): + """copy title into the title field of info.xml + author and date werden leer!!! + """ - + + resources=self.ZopeFind(self,obj_metatypes=['ECHO_resource'],search_sub=1) + + + for resource in resources: + ret,txt=resource[1].copyTitleToInfoXML() + if (not ret) and RESPONSE: + RESPONSE.write("error: %s\n"%txt) + if ret and RESPONSE: + RESPONSE.write("ok: %s\n"%txt) + + #zLOG.LOG("ECHO (copyTitleToInfoXMLFolder)",zLOG.INFO,txt) + if RESPONSE is not None: + RESPONSE.write("done!\n") + RESPONSE.close() + RESPONSE.redirect('manage_main') + def copySearchFields(self,RESPONSE=None): """copys import metadatafields to the object""" resources=self.ZopeFind(self,obj_metatypes=['ECHO_resource']) @@ -2224,21 +1812,6 @@ class ECHO_collection(Folder, Persistent else: return "" - def getTitle(self): - """title""" - try: - return self.title.encode('utf-8','ignore') - except: - self.title=self.title.decode('iso-8859-1','ignore')[0:] #correnct conding error - return self.title.encode('utf-8','ignore') - - def getLabel(self): - """title""" - try: - return self.label.encode('utf-8','ignore') - except: - self.label=self.label.decode('iso-8859-1','ignore')[0:] #correnct conding error - return self.label.encode('utf-8','ignore') def createRessourcesFromXMLForm(self): """form""" @@ -2634,9 +2207,10 @@ class ECHO_collection(Folder, Persistent self.ZCacheable_set(ret) return ret - def content_html(self): + def content_html(self,**argv): """template fuer content""" - return content_html(self,'collection') + #print "NN",argv + return ECHO_basis.content_html(self,'collection') def getCredits(self): """Ausgabe der credits""" @@ -2730,15 +2304,6 @@ class ECHO_group(ECHO_collection): security.declareProtected('View','index_html') - def showRDF(self): - """showrdf""" - self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml') - ret="""\n\n""" - ret+=self.getRDF(urn="echo:collectionroot")+"\n" - - ret+="""""" - - return ret def getRDF(self,urn=None): """rdf of the collection""" @@ -2832,7 +2397,7 @@ class ECHO_group(ECHO_collection): def content_html(self): """template fuer content""" - return content_html(self,'group') + return ECHO_basis.content_html(self,'group') @@ -3023,7 +2588,35 @@ class ECHO_root(Folder,Persistent,Implic #return "http://enlil.museum.upenn.edu/cgi-bin/cdlget.plx?item=%s&project=ncdl" ###END CDLI add - + + def checkResource(self,id): + """checks if a resource is in the tree, gives back none or list of resources""" + if hasattr(self,"_v_checkResource") and self._v_checkResource.has_key(id): #existiert ein cache und id ist bereits drin? + return self._v_checkResource[id] + + else: + resources=self.ZopeFind(self,obj_metatypes=['ECHO_resource'],obj_ids=[id],search_sub=1) + + if not hasattr(self,"_v_checkResource"): self._v_checkResource={}#lege cache an falls nicht existent + if resources: + self._v_checkResource[id]=resources[0:] # slicing to be sure that data is stabil + else: + self._v_checkResource[id]=None + + return self._v_checkResource[id] + + def sendForm(self,fromaddr,content,server='mail.mpiwg-berlin.mpg.de'): + """sendform""" + toaddrs=["dwinter@mpiwg-berlin.mpg.de"] + + msg = ("From: %s\r\nTo: %s\r\nSubject: %s\r\n\r\n" + % (fromaddr, ", ".join(toaddrs),"testsub")) + server = smtplib.SMTP(server) + #server.set_debuglevel(1) + msg=msg+content + server.sendmail(fromaddr, toaddrs, msg) + server.quit() + def generateFromRDFForm(self): """change form""" pt=PageTemplateFile('Products/ECHO_content/zpt/generateFromRDFForm').__of__(self) @@ -3157,15 +2750,6 @@ class ECHO_root(Folder,Persistent,Implic ) - def showRDF(self): - """showrdf""" - self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml') - ret="""\n\n""" - ret+=self.getRDF(urn="echo:collectionroot")+"\n" - - ret+="""""" - return ret - def reloadMetaDataFromStorageWarning(self,RESPONSE=None): """warning""" @@ -3510,9 +3094,9 @@ class ECHO_root(Folder,Persistent,Implic if self.checkRef(ref): if pn: - link.setAttribute("href",self.aq_parent.absolute_url()+"/vlp_coll?id="+ref+"&p="+pn) + link.setAttribute("href",self.aq_parent.absolute_url()+"/references?id="+ref+"&p="+pn) else: - link.setAttribute("href",self.aq_parent.absolute_url()+"/vlp_coll?id="+ref) + link.setAttribute("href",self.aq_parent.absolute_url()+"/references?id="+ref) newxml=dom.toxml('utf-8') @@ -3595,9 +3179,10 @@ class ECHO_root(Folder,Persistent,Implic def getPartners(self): """Get list of Partners. Presently only from a subfolder partners""" - - return [ item[1] for item in self.partners.ZopeFind(self.partners,obj_metatypes=['ECHO_partner'])] - + if hasattr(self,'partners'): + return [ item[1] for item in self.partners.ZopeFind(self.partners,obj_metatypes=['ECHO_partner'])] + else: + return [] def getInstitutions(self): """Get list of Partners. Presently only from a subfolder partners""" @@ -3791,7 +3376,7 @@ def manage_addECHO_rootForm(self): pt=PageTemplateFile('Products/ECHO_content/zpt/AddECHO_root.zpt').__of__(self) return pt() -class ECHO_copyrightType(Folder): +class ECHO_copyrightType(Folder,ECHO_basis): """copyright typ""" meta_type="ECHO_copyrightType" @@ -3840,7 +3425,7 @@ def manage_addECHO_copyrightType(self,id -class ECHO_partner(Image,Persistent): +class ECHO_partner(Image,Persistent,ECHO_basis): """ECHO Partner""" meta_type="ECHO_partner" @@ -3924,7 +3509,7 @@ def manage_addECHO_partner(self, id, url REQUEST.RESPONSE.redirect('%s/manage_main' % url) return id -class ECHO_linkList(ZopePageTemplate): +class ECHO_linkList(ZopePageTemplate,ECHO_basis): """LinkList Objekt""" meta_type="ECHO_linkList" @@ -3936,7 +3521,7 @@ class ECHO_linkList(ZopePageTemplate): def content_html(self): """content_html""" - return content_html(self,'pageTemplate') + return ECHO_basis.content_html(self,'pageTemplate') def changeECHO_linkListWeightForm(self): """change""" @@ -4020,8 +3605,8 @@ def manage_addECHO_linkList(self, id, la return '' -class ECHO_support(Folder): - """gefšrdert durch""" +class ECHO_support(Folder,ECHO_basis): + """gefoerdert durch""" meta_type="ECHO_support" @@ -4074,7 +3659,7 @@ def manage_addECHO_support(self, id,inst RESPONSE.redirect('manage_main') -class ECHO_institution(Image,Persistent): +class ECHO_institution(Image,Persistent,ECHO_basis): """ECHO Institution""" meta_type="ECHO_institution" @@ -4153,3 +3738,4 @@ def manage_addECHO_institution(self, id, except: url=REQUEST['URL1'] REQUEST.RESPONSE.redirect('%s/manage_main' % url) return id +