--- documentViewer/documentViewer.py 2006/06/13 15:10:35 1.11 +++ documentViewer/documentViewer.py 2007/05/04 13:17:02 1.26 @@ -1,6 +1,8 @@ + + from OFS.Folder import Folder from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate -from Products.PageTemplates.PageTemplateFile import PageTemplateFile +from Products.PageTemplates.PageTemplateFile import PageTemplateFile from AccessControl import ClassSecurityInfo from AccessControl import getSecurityManager from Globals import package_home @@ -15,8 +17,15 @@ import os.path import sys import cgi import urllib -import zLOG +import logging + +import urlparse +def logger(txt,method,txt2): + """logging""" + logging.info(txt+ txt2) + + def getInt(number, default=0): """returns always an int (0 in case of problems)""" try: @@ -25,6 +34,7 @@ def getInt(number, default=0): return default def getTextFromNode(nodename): + """get the cdata content of a node""" if nodename is None: return "" nodelist=nodename.childNodes @@ -55,7 +65,8 @@ def urlopen(url,timeout=2): ## class documentViewer(Folder): """document viewer""" - + #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" + meta_type="Document viewer" security=ClassSecurityInfo() @@ -69,16 +80,19 @@ class documentViewer(Folder): image_main = PageTemplateFile('zpt/image_main', globals()) head_main = PageTemplateFile('zpt/head_main', globals()) docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) + info_xml = PageTemplateFile('zpt/info_xml', globals()) security.declareProtected('View management screens','changeDocumentViewerForm') changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) - def __init__(self,id,imageViewerUrl,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): + def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): """init document viewer""" self.id=id self.title=title self.imageViewerUrl=imageViewerUrl + self.textViewerUrl=textViewerUrl + if not digilibBaseUrl: self.digilibBaseUrl = self.findDigilibUrl() else: @@ -92,14 +106,16 @@ class documentViewer(Folder): security.declareProtected('View','index_html') - def index_html(self,mode,url,start=None,pn=1): + def index_html(self,mode,url,viewMode="auto",start=None,pn=1): ''' view it - @param mode: defines which type of document is behind url + @param mode: defines how to access the document behind url @param url: url which contains display information + @param viewMode: if images display images, if text display text, default is images (text,images or auto) + ''' - zLOG.LOG("documentViewer (index)", zLOG.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) + logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) if not hasattr(self, 'template'): # create template folder if it doesn't exist @@ -111,7 +127,14 @@ class documentViewer(Folder): docinfo = self.getDocinfo(mode=mode,url=url) pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) pt = getattr(self.template, 'viewer_main') - return pt(docinfo=docinfo,pageinfo=pageinfo) + + if viewMode=="auto": # automodus gewaehlt + if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert + viewMode="text" + else: + viewMode="images" + + return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) def getLink(self,param=None,val=None): @@ -129,26 +152,35 @@ class documentViewer(Folder): url=self.REQUEST['URL1']+"?"+ps return url + + def getInfo_xml(self,url,mode): + """returns info about the document as XML""" + + if not self.digilibBaseUrl: + self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" + + docinfo = self.getDocinfo(mode=mode,url=url) + pt = getattr(self.template, 'info_xml') + return pt(docinfo=docinfo) + def getStyle(self, idx, selected, style=""): """returns a string with the given style and append 'sel' if path == selected.""" - #zLOG.LOG("documentViewer (getstyle)", zLOG.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) + #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) if idx == selected: return style + 'sel' else: return style - + def isAccessible(self, docinfo): """returns if access to the resource is granted""" access = docinfo.get('accessType', None) - if access is None: - # no information - no access - #TODO: check - return True - elif access == 'free': + logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) + if access is not None and access == 'free': + logger("documentViewer (accessOK)", logging.INFO, "access is free") return True - elif access in self.authgroups: + elif access is None or access in self.authgroups: # only local access -- only logged in users user = getSecurityManager().getUser() if user is not None: @@ -157,30 +189,33 @@ class documentViewer(Folder): else: return False - zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "unknown access type %s"%access) + logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) return False def getDirinfoFromDigilib(self,path,docinfo=None): """gibt param von dlInfo aus""" + num_retries = 3 if docinfo is None: docinfo = {} - imageUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path + infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path - zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(imageUrl)) + logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) - for cnt in (1,2,3): + for cnt in range(num_retries): try: - dom = NonvalidatingReader.parseUri(imageUrl) + # dom = NonvalidatingReader.parseUri(imageUrl) + txt=urllib.urlopen(infoUrl).read() + dom = Parse(txt) break except: - zLOG.LOG("documentViewer (getdirinfofromdigilib)", zLOG.ERROR, "error reading %s (try %d)"%(imageUrl,cnt)) + logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) else: - raise IOError("Unable to get dir-info from %s"%(imageUrl)) + raise IOError("Unable to get dir-info from %s"%(infoUrl)) sizes=dom.xpath("//dir/size") - zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:size"%sizes) + logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) if sizes: docinfo['numPages'] = int(getTextFromNode(sizes[0])) @@ -192,35 +227,67 @@ class documentViewer(Folder): def getIndexMeta(self, url): """returns dom of index.meta document at url""" + num_retries = 3 dom = None + metaUrl = None if url.startswith("http://"): # real URL - try: - dom = NonvalidatingReader.parseUri(url) - except: - zLOG.LOG("documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2]) - raise IOError("Unable to read index.meta from %s"%(url)) + metaUrl = url else: # online path server=self.digilibBaseUrl+"/servlet/Texter?fn=" - metaUrl=server+url + metaUrl=server+url.replace("/mpiwg/online","") if not metaUrl.endswith("index.meta"): metaUrl += "/index.meta" + print metaUrl + for cnt in range(num_retries): try: - # patch dirk encoding fehler treten dann nicht mehr auf + # patch dirk encoding fehler treten dann nicht mehr auf # dom = NonvalidatingReader.parseUri(metaUrl) - txt=urllib.urlopen(metaUrl).read() - dom = Parse(txt) + txt=urllib.urlopen(metaUrl).read() + dom = Parse(txt) + break except: - zLOG.LOG("documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2]) - raise IOError("Unable to read index meta from %s"%(metaUrl)) + logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) + + if dom is None: + raise IOError("Unable to read index meta from %s"%(url)) + + return dom + + def getPresentationInfoXML(self, url): + """returns dom of info.xml document at url""" + num_retries = 3 + dom = None + metaUrl = None + if url.startswith("http://"): + # real URL + metaUrl = url + else: + # online path + server=self.digilibBaseUrl+"/servlet/Texter?fn=" + metaUrl=server+url.replace("/mpiwg/online","") + + + for cnt in range(num_retries): + try: + # patch dirk encoding fehler treten dann nicht mehr auf + # dom = NonvalidatingReader.parseUri(metaUrl) + txt=urllib.urlopen(metaUrl).read() + dom = Parse(txt) + break + except: + logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) + + if dom is None: + raise IOError("Unable to read infoXMLfrom %s"%(url)) return dom def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None): """gets authorization info from the index.meta file at path or given by dom""" - zLOG.LOG("documentViewer (getauthinfofromindexmeta)", zLOG.INFO,"path: %s"%(path)) + logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) access = None @@ -229,7 +296,7 @@ class documentViewer(Folder): if dom is None: dom = self.getIndexMeta(getParentDir(path)) - + acctype = dom.xpath("//access-conditions/access/@type") if acctype and (len(acctype)>0): access=acctype[0].value @@ -242,7 +309,7 @@ class documentViewer(Folder): def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None): """gets bibliographical info from the index.meta file at path or given by dom""" - zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path)) + logger("documentViewer (getbibinfofromindexmeta)", logging.INFO,"path: %s"%(path)) if docinfo is None: docinfo = {} @@ -264,22 +331,34 @@ class documentViewer(Folder): docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) - + + logging.info("bla") + try: + docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) + except: + docinfo['lang']='' return docinfo def getDocinfoFromTextTool(self,url,dom=None,docinfo=None): """parse texttool tag in index meta""" - zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.INFO,"url: %s"%(url)) + logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url)) if docinfo is None: docinfo = {} + if docinfo.get('lang',None) is None: + docinfo['lang']='' # default keine Sprache gesetzt if dom is None: dom = self.getIndexMeta(url) + archivePath = None + archiveName = None + archiveNames=dom.xpath("//resource/name") if archiveNames and (len(archiveNames)>0): archiveName=getTextFromNode(archiveNames[0]) + else: + logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/name missing in: %s"%(url)) archivePaths=dom.xpath("//resource/archive-path") if archivePaths and (len(archivePaths)>0): @@ -287,18 +366,30 @@ class documentViewer(Folder): # clean up archive path if archivePath[0] != '/': archivePath = '/' + archivePath - if not archivePath.endswith(archiveName): + if archiveName and (not archivePath.endswith(archiveName)): archivePath += "/" + archiveName else: - archivePath=None + # try to get archive-path from url + logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/archive-path missing in: %s"%(url)) + if (not url.startswith('http')): + archivePath = url.replace('index.meta', '') + + if archivePath is None: + # we balk without archive-path + raise IOError("Missing archive-path (for text-tool) in %s"%(url)) imageDirs=dom.xpath("//texttool/image") if imageDirs and (len(imageDirs)>0): imageDir=getTextFromNode(imageDirs[0]) else: - # we balk with no image tag - raise IOError("No text-tool info in %s"%(url)) - + # we balk with no image tag / not necessary anymore because textmode is now standard + #raise IOError("No text-tool info in %s"%(url)) + imageDir="" + docinfo['numPages']=1 # im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht + + docinfo['imagePath'] = "" # keine Bilder + docinfo['imageURL'] = "" + if imageDir and archivePath: #print "image: ", imageDir, " archivepath: ", archivePath imageDir=os.path.join(archivePath,imageDir) @@ -315,16 +406,36 @@ class documentViewer(Folder): textUrls=dom.xpath("//texttool/text") if textUrls and (len(textUrls)>0): textUrl=getTextFromNode(textUrls[0]) + if urlparse.urlparse(textUrl)[0]=="": #keine url + textUrl=os.path.join(archivePath,textUrl) + docinfo['textURL'] = textUrl - - docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) - docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) - return docinfo + presentationUrls=dom.xpath("//texttool/presentation") + docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get info von bib tag + + if presentationUrls and (len(presentationUrls)>0): # ueberschreibe diese durch presentation informationen + # presentation url ergiebt sich ersetzen von index.meta in der url der fŸr die Metadaten + # durch den relativen Pfad auf die presentation infos + presentationUrl=url.replace('index.meta',getTextFromNode(presentationUrls[0])) + docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom) + docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info + return docinfo + + + def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): + """gets the bibliographical information from the preseantion entry in texttools + """ + dom=self.getPresentationInfoXML(url) + docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) + docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) + docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) + return docinfo + def getDocinfoFromImagePath(self,path,docinfo=None): """path ist the path to the images it assumes that the index.meta file is one level higher.""" - zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path)) + logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) if docinfo is None: docinfo = {} path=path.replace("/mpiwg/online","") @@ -340,13 +451,13 @@ class documentViewer(Folder): def getDocinfo(self, mode, url): """returns docinfo depending on mode""" - zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"mode: %s, url: %s"%(mode,url)) + logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) # look for cached docinfo in session if self.REQUEST.SESSION.has_key('docinfo'): docinfo = self.REQUEST.SESSION['docinfo'] # check if its still current if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: - zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo in session: %s"%docinfo) + logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) return docinfo # new docinfo docinfo = {'mode': mode, 'url': url} @@ -355,10 +466,10 @@ class documentViewer(Folder): elif mode=="imagepath": docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) else: - zLOG.LOG("documentViewer (getdocinfo)", zLOG.ERROR,"unknown mode!") + logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") raise ValueError("Unknown mode %s"%(mode)) - zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo: %s"%docinfo) + logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) self.REQUEST.SESSION['docinfo'] = docinfo return docinfo @@ -443,16 +554,25 @@ class documentViewer(Folder): def findDigilibUrl(self): """try to get the digilib URL from zogilib""" url = self.imageViewerUrl[:-1] + "/getScalerUrl" + #print urlparse.urlparse(url)[0] + #print urlparse.urljoin(self.absolute_url(),url) + logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0]) + logging.info("finddigiliburl: %s"%urlparse.urljoin(self.absolute_url(),url)) + try: + if urlparse.urlparse(url)[0]=='': #relative path + url=urlparse.urljoin(self.absolute_url()+"/",url) + scaler = urlopen(url).read() return scaler.replace("/servlet/Scaler?", "") except: return None - def changeDocumentViewer(self,imageViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): + def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): """init document viewer""" self.title=title self.imageViewerUrl=imageViewerUrl + self.textViewerUrl=textViewerUrl self.digilibBaseUrl = digilibBaseUrl self.thumbrows = thumbrows self.thumbcols = thumbcols @@ -470,9 +590,9 @@ def manage_AddDocumentViewerForm(self): pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) return pt() -def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None): +def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None): """add the viewer""" - newObj=documentViewer(id,imageViewerUrl,title) + newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl) self._setObject(id,newObj) if RESPONSE is not None: @@ -498,7 +618,9 @@ def manage_addDocumentViewerTemplate(sel self._setObject(id, DocumentViewerTemplate(id)) ob = getattr(self, id) - ob.pt_edit(open(os.path.join(package_home(globals()),'zpt/viewer_main.zpt')).read(),None) + txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() + logging.info("txt %s:"%txt) + ob.pt_edit(txt,"text/html") if title: ob.pt_setTitle(title) try: @@ -511,4 +633,4 @@ def manage_addDocumentViewerTemplate(sel return '' - \ No newline at end of file +