--- documentViewer/documentViewer.py 2006/09/11 14:43:09 1.19 +++ documentViewer/documentViewer.py 2008/11/04 22:03:56 1.37 @@ -2,7 +2,7 @@ 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 @@ -17,15 +17,22 @@ import os.path import sys import cgi import urllib -import zLOG -import urlparse +import logging +import math +import urlparse +from types import * +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: return int(number) except: - return default + return int(default) def getTextFromNode(nodename): """get the cdata content of a node""" @@ -59,7 +66,7 @@ def urlopen(url,timeout=2): ## class documentViewer(Folder): """document viewer""" - textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" + #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" meta_type="Document viewer" @@ -74,7 +81,9 @@ 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()) + thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) security.declareProtected('View management screens','changeDocumentViewerForm') changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) @@ -98,17 +107,48 @@ class documentViewer(Folder): self.manage_addFolder('template') + security.declareProtected('View','thumbs_rss') + def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): + ''' + view it + @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) + + ''' + logging.info("HHHHHHHHHHHHHH:load the rss") + 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 + self.manage_addFolder('template') + + if not self.digilibBaseUrl: + self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" + + docinfo = self.getDocinfo(mode=mode,url=url) + pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) + pt = getattr(self.template, 'thumbs_main_rss') + + 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) + security.declareProtected('View','index_html') - def index_html(self,mode,url,viewMode="images",start=None,pn=1): + def index_html(self,mode,url,viewMode="auto",start=None,pn=1,mk=None): ''' 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 + @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 @@ -120,9 +160,26 @@ 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,viewMode=viewMode) - + + 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,mk=self.generateMarks(mk)) + def generateMarks(self,mk): + ret="" + if mk is None: + return "" + + if type(mk) is not ListType: + mk=[mk] + for m in mk: + ret+="mk=%s"%m + return ret + def getLink(self,param=None,val=None): """link to documentviewer with parameter param set to val""" params=self.REQUEST.form.copy() @@ -138,22 +195,47 @@ class documentViewer(Folder): url=self.REQUEST['URL1']+"?"+ps return url + def getLinkAmp(self,param=None,val=None): + """link to documentviewer with parameter param set to val""" + params=self.REQUEST.form.copy() + if param is not None: + if val is None: + if params.has_key(param): + del params[param] + else: + params[param] = str(val) + + # quote values and assemble into query string + logging.info("XYXXXXX: %s"%repr(params.items())) + ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) + 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) - zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "access type %s"%access) + logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) if access is not None and access == 'free': - zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "access is free") + logger("documentViewer (accessOK)", logging.INFO, "access is free") return True elif access is None or access in self.authgroups: # only local access -- only logged in users @@ -164,19 +246,21 @@ 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): + def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): """gibt param von dlInfo aus""" num_retries = 3 if docinfo is None: docinfo = {} - + + for x in range(cut): + path=getParentDir(path) infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path - zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(infoUrl)) + logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) for cnt in range(num_retries): try: @@ -185,12 +269,12 @@ class documentViewer(Folder): dom = Parse(txt) break except: - zLOG.LOG("documentViewer (getdirinfofromdigilib)", zLOG.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) + logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) else: 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])) @@ -214,7 +298,7 @@ class documentViewer(Folder): metaUrl=server+url.replace("/mpiwg/online","") if not metaUrl.endswith("index.meta"): metaUrl += "/index.meta" - print metaUrl + logging.debug("METAURL: %s"%metaUrl) for cnt in range(num_retries): try: # patch dirk encoding fehler treten dann nicht mehr auf @@ -223,17 +307,46 @@ class documentViewer(Folder): dom = Parse(txt) break except: - zLOG.LOG("ERROR documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2]) + 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): + def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): """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 @@ -241,7 +354,9 @@ class documentViewer(Folder): docinfo = {} if dom is None: - dom = self.getIndexMeta(getParentDir(path)) + for x in range(cut+1): + path=getParentDir(path) + dom = self.getIndexMeta(path) acctype = dom.xpath("//access-conditions/access/@type") if acctype and (len(acctype)>0): @@ -253,40 +368,65 @@ class documentViewer(Folder): return docinfo - def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None): + def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): """gets bibliographical info from the index.meta file at path or given by dom""" - zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path)) + logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) if docinfo is None: docinfo = {} if dom is None: - dom = self.getIndexMeta(getParentDir(path)) + for x in range(cut+1): + path=getParentDir(path) + dom = self.getIndexMeta(path) + # put in all raw bib fields as dict "bib" + bib = dom.xpath("//bib/*") + if bib and len(bib)>0: + bibinfo = {} + for e in bib: + bibinfo[e.localName] = getTextFromNode(e) + docinfo['bib'] = bibinfo + + # extract some fields (author, title, year) according to their mapping metaData=self.metadata.main.meta.bib bibtype=dom.xpath("//bib/@type") if bibtype and (len(bibtype)>0): bibtype=bibtype[0].value else: bibtype="generic" + bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) + docinfo['bib_type'] = bibtype bibmap=metaData.generateMappingForType(bibtype) - #print "bibmap: ", bibmap, " for: ", bibtype # if there is no mapping bibmap is empty (mapping sometimes has empty fields) if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: - 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]) - + try: + docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) + except: pass + try: + docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) + except: pass + try: + docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) + except: pass + logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) + 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) @@ -297,7 +437,7 @@ class documentViewer(Folder): if archiveNames and (len(archiveNames)>0): archiveName=getTextFromNode(archiveNames[0]) else: - zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.WARNING,"resource/name missing in: %s"%(url)) + logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/name missing in: %s"%(url)) archivePaths=dom.xpath("//resource/archive-path") if archivePaths and (len(archivePaths)>0): @@ -309,7 +449,7 @@ class documentViewer(Folder): archivePath += "/" + archiveName else: # try to get archive-path from url - zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.WARNING,"resource/archive-path missing in: %s"%(url)) + logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/archive-path missing in: %s"%(url)) if (not url.startswith('http')): archivePath = url.replace('index.meta', '') @@ -321,9 +461,14 @@ class documentViewer(Folder): 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) @@ -342,39 +487,68 @@ class documentViewer(Folder): textUrl=getTextFromNode(textUrls[0]) if urlparse.urlparse(textUrl)[0]=="": #keine url textUrl=os.path.join(archivePath,textUrl) - + # fix URLs starting with /mpiwg/online + if textUrl.startswith("/mpiwg/online"): + textUrl = textUrl.replace("/mpiwg/online",'',1) + 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 fuer 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) - def getDocinfoFromImagePath(self,path,docinfo=None): + 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) + try: + docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) + except: + pass + try: + docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) + except: + pass + try: + docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) + except: + pass + return docinfo + + def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): """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","") docinfo['imagePath'] = path - docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo) + docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path docinfo['imageURL'] = imageUrl - docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo) - docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo) + docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo,cut=cut) + docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo,cut=cut) return docinfo 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} @@ -382,11 +556,13 @@ class documentViewer(Folder): docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) elif mode=="imagepath": docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) + elif mode=="filepath": + docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) 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 @@ -402,7 +578,8 @@ class documentViewer(Folder): pageinfo['cols'] = cols grpsize = cols * rows pageinfo['groupsize'] = grpsize - start = getInt(start, default=(int(current / grpsize) * grpsize +1)) + start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) + # int(current / grpsize) * grpsize +1)) pageinfo['start'] = start pageinfo['end'] = start + grpsize if docinfo is not None: @@ -411,7 +588,7 @@ class documentViewer(Folder): pageinfo['numgroups'] = int(np / grpsize) if np % grpsize > 0: pageinfo['numgroups'] += 1 - + logging.debug("getPageInfo: %s"%repr(pageinfo)) return pageinfo def text(self,mode,url,pn): @@ -471,8 +648,11 @@ 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) + #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) @@ -532,7 +712,9 @@ 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: