--- documentViewer/documentViewer.py 2010/06/16 16:38:17 1.69.2.2 +++ documentViewer/documentViewer.py 2011/07/28 13:00:07 1.175.2.10 @@ -1,94 +1,122 @@ - from OFS.Folder import Folder from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate from Products.PageTemplates.PageTemplateFile import PageTemplateFile -from Products.PythonScripts.standard import url_quote from AccessControl import ClassSecurityInfo from AccessControl import getSecurityManager from Globals import package_home -from Ft.Xml.Domlette import NonvalidatingReader -from Ft.Xml.Domlette import PrettyPrint, Print -from Ft.Xml import EMPTY_NAMESPACE, Parse - -from xml.dom.minidom import parse, parseString +#from Ft.Xml import EMPTY_NAMESPACE, Parse +#import Ft.Xml.Domlette -from extraFunction import * +import xml.etree.ElementTree as ET - -import Ft.Xml.XPath -import cStringIO -import xmlrpclib import os.path import sys -import cgi import urllib import logging import math - import urlparse -from types import * +import re +import string + +from SrvTxtUtils import getInt, getText, getHttpData 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 int(default) - -def getTextFromNode(nodename): - """get the cdata content of a node""" - if nodename is None: - return "" - nodelist=nodename.childNodes - rc = "" - for node in nodelist: - if node.nodeType == node.TEXT_NODE: - rc = rc + node.data - return rc - -def serializeNode(node, encoding='utf-8'): +def serializeNode(node, encoding="utf-8"): """returns a string containing node as XML""" - buf = cStringIO.StringIO() - Print(node, stream=buf, encoding=encoding) - s = buf.getvalue() - buf.close() + s = ET.tostring(node) + + # 4Suite: + # stream = cStringIO.StringIO() + # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) + # s = stream.getvalue() + # stream.close() return s - +def browserCheck(self): + """check the browsers request to find out the browser type""" + bt = {} + ua = self.REQUEST.get_header("HTTP_USER_AGENT") + bt['ua'] = ua + bt['isIE'] = False + bt['isN4'] = False + bt['versFirefox']="" + bt['versIE']="" + bt['versSafariChrome']="" + bt['versOpera']="" + + if string.find(ua, 'MSIE') > -1: + bt['isIE'] = True + else: + bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) + # Safari oder Chrome identification + try: + nav = ua[string.find(ua, '('):] + nav1=ua[string.find(ua,')'):] + nav2=nav1[string.find(nav1,'('):] + nav3=nav2[string.find(nav2,')'):] + ie = string.split(nav, "; ")[1] + ie1 =string.split(nav1, " ")[2] + ie2 =string.split(nav3, " ")[1] + ie3 =string.split(nav3, " ")[2] + if string.find(ie3, "Safari") >-1: + bt['versSafariChrome']=string.split(ie2, "/")[1] + except: pass + # IE identification + try: + nav = ua[string.find(ua, '('):] + ie = string.split(nav, "; ")[1] + if string.find(ie, "MSIE") > -1: + bt['versIE'] = string.split(ie, " ")[1] + except:pass + # Firefox identification + try: + nav = ua[string.find(ua, '('):] + nav1=ua[string.find(ua,')'):] + if string.find(ie1, "Firefox") >-1: + nav5= string.split(ie1, "/")[1] + logging.debug("FIREFOX: %s"%(nav5)) + bt['versFirefox']=nav5[0:3] + except:pass + #Opera identification + try: + if string.find(ua,"Opera") >-1: + nav = ua[string.find(ua, '('):] + nav1=nav[string.find(nav,')'):] + bt['versOpera']=string.split(nav1,"/")[2] + except:pass + + bt['isMac'] = string.find(ua, 'Macintosh') > -1 + bt['isWin'] = string.find(ua, 'Windows') > -1 + bt['isIEWin'] = bt['isIE'] and bt['isWin'] + bt['isIEMac'] = bt['isIE'] and bt['isMac'] + bt['staticHTML'] = False + + return bt + def getParentDir(path): """returns pathname shortened by one""" return '/'.join(path.split('/')[0:-1]) -import socket - -def urlopen(url,timeout=2): - """urlopen mit timeout""" - socket.setdefaulttimeout(timeout) - ret=urllib.urlopen(url) - socket.setdefaulttimeout(5) - return ret - - ## ## documentViewer class ## -class documentViewer(Folder, extraFunction): +class documentViewer(Folder): """document viewer""" - #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" - meta_type="Document viewer" security=ClassSecurityInfo() manage_options=Folder.manage_options+( {'label':'main config','action':'changeDocumentViewerForm'}, ) + + metadataService = None + """MetaDataFolder instance""" # templates and forms viewer_main = PageTemplateFile('zpt/viewer_main', globals()) @@ -96,17 +124,18 @@ class documentViewer(Folder, extraFuncti toc_text = PageTemplateFile('zpt/toc_text', globals()) toc_figures = PageTemplateFile('zpt/toc_figures', globals()) page_main_images = PageTemplateFile('zpt/page_main_images', globals()) + page_main_double = PageTemplateFile('zpt/page_main_double', globals()) page_main_text = PageTemplateFile('zpt/page_main_text', globals()) page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) + page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals()) page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) + page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', 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()) def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): @@ -123,12 +152,13 @@ class documentViewer(Folder, extraFuncti #self['template'] = templateFolder # Zope-2.12 style self._setObject('template',templateFolder) # old style try: - from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy - xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False) + import MpdlXmlTextServer + textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) #templateFolder['fulltextclient'] = xmlRpcClient - templateFolder._setObject('fulltextclient',xmlRpcClient) + templateFolder._setObject('fulltextclient',textServer) except Exception, e: - logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e)) + logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) + try: from Products.zogiLib.zogiLib import zogiLib zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") @@ -136,8 +166,68 @@ class documentViewer(Folder, extraFuncti templateFolder._setObject('zogilib',zogilib) except Exception, e: logging.error("Unable to create zogiLib for zogilib: "+str(e)) + + try: + # assume MetaDataFolder instance is called metadata + self.metadataService = getattr(self, 'metadata') + except Exception, e: + logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) + + # proxy text server methods to fulltextclient + def getTextPage(self, **args): + """get page""" + return self.template.fulltextclient.getTextPage(**args) + + def getOrigPages(self, **args): + """get page""" + return self.template.fulltextclient.getOrigPages(**args) + + def getOrigPagesNorm(self, **args): + """get page""" + return self.template.fulltextclient.getOrigPagesNorm(**args) + + def getQuery(self, **args): + """get query in search""" + return self.template.fulltextclient.getQuery(**args) + + def getSearch(self, **args): + """get search""" + return self.template.fulltextclient.getSearch(**args) + + def getGisPlaces(self, **args): + """get gis places""" + return self.template.fulltextclient.getGisPlaces(**args) + + def getAllGisPlaces(self, **args): + """get all gis places """ + return self.template.fulltextclient.getAllGisPlaces(**args) + + def getTranslate(self, **args): + """get translate""" + return self.template.fulltextclient.getTranslate(**args) + + def getLemma(self, **args): + """get lemma""" + return self.template.fulltextclient.getLemma(**args) + + def getLemmaQuery(self, **args): + """get query""" + return self.template.fulltextclient.getLemmaQuery(**args) + + def getLex(self, **args): + """get lex""" + return self.template.fulltextclient.getLex(**args) + + def getToc(self, **args): + """get toc""" + return self.template.fulltextclient.getToc(**args) + + def getTocPage(self, **args): + """get tocpage""" + return self.template.fulltextclient.getTocPage(**args) + security.declareProtected('View','thumbs_rss') def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): ''' @@ -148,7 +238,7 @@ class documentViewer(Folder, extraFuncti ''' logging.debug("HHHHHHHHHHHHHH:load the rss") - logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) + logging.debug("documentViewer (index) 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 @@ -158,11 +248,13 @@ class documentViewer(Folder, extraFuncti 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) + #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) + pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo) + ''' ZDES ''' pt = getattr(self.template, 'thumbs_main_rss') if viewMode=="auto": # automodus gewaehlt - if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert + if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert viewMode="text" else: viewMode="images" @@ -170,13 +262,14 @@ class documentViewer(Folder, extraFuncti return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) security.declareProtected('View','index_html') - def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None): + def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None): ''' 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 auto (text,images or auto) @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) + @param characterNormalization type of text display (reg, norm, none) @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma) ''' @@ -188,37 +281,51 @@ class documentViewer(Folder, extraFuncti return "ERROR: template folder missing!" if not getattr(self, 'digilibBaseUrl', None): - self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" + self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" docinfo = self.getDocinfo(mode=mode,url=url) - if tocMode != "thumbs": # get table of contents docinfo = self.getToc(mode=tocMode, docinfo=docinfo) - - if viewMode=="auto": # automodus gewaehlt - if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert + + # auto viewMode: text_dict if text else images + if viewMode=="auto": + if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): + #texturl gesetzt und textViewer konfiguriert viewMode="text_dict" else: viewMode="images" - pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) + pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, tocMode=tocMode) - pt = getattr(self.template, 'viewer_main') - return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) + if viewMode != 'images' and docinfo.get('textURLPath', None): + # get full text page + page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo) + pageinfo['textPage'] = page + + # get template /template/viewer_main + pt = getattr(self.template, 'viewer_main') + # and execute with parameters + 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] + if not isinstance(mk, list): + mk=[mk] for m in mk: ret+="mk=%s"%m return ret - - + + + def getBrowser(self): + """getBrowser the version of browser """ + bt = browserCheck(self) + logging.debug("BROWSER VERSION: %s"%(bt)) + return bt + def findDigilibUrl(self): """try to get the digilib URL from zogilib""" url = self.template.zogilib.getDLBaseUrl() @@ -236,40 +343,48 @@ class documentViewer(Folder, extraFuncti else: return style - def getLink(self,param=None,val=None): - """link to documentviewer with parameter param set to val""" - params=self.REQUEST.form.copy() + def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'): + """returns URL to documentviewer with parameter param set to val or from dict params""" + # copy existing request params + urlParams=self.REQUEST.form.copy() + # change single param if param is not None: if val is None: - if params.has_key(param): - del params[param] + if urlParams.has_key(param): + del urlParams[param] else: - params[param] = str(val) + urlParams[param] = str(val) - if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath - params["mode"] = "imagepath" - params["url"] = getParentDir(params["url"]) + # change more params + if params is not None: + for k in params.keys(): + v = params[k] + if v is None: + # val=None removes param + if urlParams.has_key(k): + del urlParams[k] + + else: + urlParams[k] = v + + # FIXME: does this belong here? + if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath + urlParams["mode"] = "imagepath" + urlParams["url"] = getParentDir(urlParams["url"]) - # quote values and assemble into query string - ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) - url=self.REQUEST['URL1']+"?"+ps + # quote values and assemble into query string (not escaping '/') + ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()]) + #ps = urllib.urlencode(urlParams) + if baseUrl is None: + baseUrl = self.REQUEST['URL1'] + + url = "%s?%s"%(baseUrl, ps) return url - def getLinkAmp(self,param=None,val=None): + + def getLinkAmp(self, param=None, val=None, params=None, baseUrl=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.debug("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 + return self.getLink(param, val, params, baseUrl, '&') def getInfo_xml(self,url,mode): """returns info about the document as XML""" @@ -281,6 +396,20 @@ class documentViewer(Folder, extraFuncti pt = getattr(self.template, 'info_xml') return pt(docinfo=docinfo) + def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True): + """returns new option state""" + if not self.REQUEST.SESSION.has_key(optionName): + # not in session -- initial + opt = {'lastState': newState, 'state': initialState} + else: + opt = self.REQUEST.SESSION.get(optionName) + if opt['lastState'] != newState: + # state in session has changed -- toggle + opt['state'] = not opt['state'] + opt['lastState'] = newState + + self.REQUEST.SESSION[optionName] = opt + return opt['state'] def isAccessible(self, docinfo): """returns if access to the resource is granted""" @@ -292,46 +421,41 @@ class documentViewer(Folder, extraFuncti elif access is None or access in self.authgroups: # only local access -- only logged in users user = getSecurityManager().getUser() + logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) if user is not None: #print "user: ", user return (user.getUserName() != "Anonymous User") else: return False - logging.debug("documentViewer (accessOK) unknown access type %s"%access) + logging.error("documentViewer (accessOK) unknown access type %s"%access) return False 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) + path=getParentDir(path) infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) - for cnt in range(num_retries): - try: - # dom = NonvalidatingReader.parseUri(imageUrl) - txt=urllib.urlopen(infoUrl).read() - dom = Parse(txt) - break - except: - logging.error("documentViewer (getdirinfofromdigilib) error reading %s (try %d)"%(infoUrl,cnt)) - else: + txt = getHttpData(infoUrl) + if txt is None: raise IOError("Unable to get dir-info from %s"%(infoUrl)) + + dom = ET.fromstring(txt) + #dom = Parse(txt) + size=getText(dom.find("size")) + #sizes=dom.xpath("//dir/size") + logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size) - sizes=dom.xpath("//dir/size") - logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) - - if sizes: - docinfo['numPages'] = int(getTextFromNode(sizes[0])) + if size: + docinfo['numPages'] = int(size) else: docinfo['numPages'] = 0 @@ -339,11 +463,20 @@ class documentViewer(Folder, extraFuncti return docinfo - - def getIndexMeta(self, url): - """returns dom of index.meta document at url""" - num_retries = 3 - dom = None + def getIndexMetaPath(self,url): + """gib nur den Pfad zurueck""" + regexp = re.compile(r".*(experimental|permanent)/(.*)") + regpath = regexp.match(url) + if (regpath==None): + return "" + logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2)) + return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2)) + + + + def getIndexMetaUrl(self,url): + """returns utr of index.meta document at url""" + metaUrl = None if url.startswith("http://"): # real URL @@ -354,25 +487,25 @@ class documentViewer(Folder, extraFuncti metaUrl=server+url.replace("/mpiwg/online","") if not metaUrl.endswith("index.meta"): metaUrl += "/index.meta" - logging.debug("METAURL: %s"%metaUrl) - 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: - logging.error("ERROR documentViewer (getIndexMeta) %s (%s)"%sys.exc_info()[0:2]) + + return metaUrl + + def getDomFromIndexMeta(self, url): + """get dom from index meta""" + dom = None + metaUrl = self.getIndexMetaUrl(url) - if dom is None: + logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl) + txt=getHttpData(metaUrl) + if txt is None: raise IOError("Unable to read index meta from %s"%(url)) - + + dom = ET.fromstring(txt) + #dom = Parse(txt) 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://"): @@ -383,19 +516,12 @@ class documentViewer(Folder, extraFuncti 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: - logging.error("ERROR documentViewer (getPresentationInfoXML) %s (%s)"%sys.exc_info()[0:2]) - - if dom is None: + txt=getHttpData(metaUrl) + if txt is None: raise IOError("Unable to read infoXMLfrom %s"%(url)) - + + dom = ET.fromstring(txt) + #dom = Parse(txt) return dom @@ -411,13 +537,16 @@ class documentViewer(Folder, extraFuncti if dom is None: for x in range(cut): path=getParentDir(path) - dom = self.getIndexMeta(path) + dom = self.getDomFromIndexMeta(path) - acctype = dom.xpath("//access-conditions/access/@type") - if acctype and (len(acctype)>0): - access=acctype[0].value - if access in ['group', 'institution']: - access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() + acc = dom.find(".//access-conditions/access") + if acc is not None: + acctype = acc.get('type') + #acctype = dom.xpath("//access-conditions/access/@type") + if acctype: + access=acctype + if access in ['group', 'institution']: + access = dom.find(".//access-conditions/access/name").text.lower() docinfo['accessType'] = access return docinfo @@ -433,48 +562,43 @@ class documentViewer(Folder, extraFuncti if dom is None: for x in range(cut): path=getParentDir(path) - dom = self.getIndexMeta(path) + dom = self.getDomFromIndexMeta(path) + + docinfo['indexMetaPath']=self.getIndexMetaPath(path); logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(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 + if self.metadataService is not None: + # put all raw bib fields in dict "bib" + bib = self.metadataService.getBibData(dom=dom) + docinfo['bib'] = bib + bibtype = bib.get('@type', None) + docinfo['bib_type'] = bibtype + # also store DC metadata for convenience + dc = self.metadataService.getDCMappedData(bib) + docinfo['creator'] = dc.get('creator',None) + docinfo['title'] = dc.get('title',None) + docinfo['date'] = dc.get('date',None) else: - bibtype="generic" - - bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) - docinfo['bib_type'] = bibtype - bibmap=metaData.generateMappingForType(bibtype) - # if there is no mapping bibmap is empty (mapping sometimes has empty fields) - if len(bibmap) > 0 and len(bibmap['author'][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']='' - + logging.error("MetadataService not found!") return docinfo + # TODO: is this needed? + def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): + """gets name info from the index.meta file at path or given by dom""" + if docinfo is None: + docinfo = {} + + if dom is None: + for x in range(cut): + path=getParentDir(path) + dom = self.getDomFromIndexMeta(path) + + docinfo['name']=getText(dom.find("name")) + logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) + return docinfo + + def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): """parse texttool tag in index meta""" logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url)) @@ -483,20 +607,19 @@ class documentViewer(Folder, extraFuncti if docinfo.get('lang', None) is None: docinfo['lang'] = '' # default keine Sprache gesetzt if dom is None: - dom = self.getIndexMeta(url) + dom = self.getDomFromIndexMeta(url) + + texttool = self.metadata.getTexttoolData(dom=dom) archivePath = None archiveName = None - archiveNames = dom.xpath("//resource/name") - if archiveNames and (len(archiveNames) > 0): - archiveName = getTextFromNode(archiveNames[0]) - else: + archiveName = getText(dom.find("name")) + if not archiveName: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) - archivePaths = dom.xpath("//resource/archive-path") - if archivePaths and (len(archivePaths) > 0): - archivePath = getTextFromNode(archivePaths[0]) + archivePath = getText(dom.find("archive-path")) + if archivePath: # clean up archive path if archivePath[0] != '/': archivePath = '/' + archivePath @@ -512,11 +635,9 @@ class documentViewer(Folder, extraFuncti # 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]) + imageDir = texttool.get('image', None) - else: + if not imageDir: # we balk with no image tag / not necessary anymore because textmode is now standard #raise IOError("No text-tool info in %s"%(url)) imageDir = "" @@ -533,14 +654,13 @@ class documentViewer(Folder, extraFuncti docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir - viewerUrls = dom.xpath("//texttool/digiliburlprefix") - if viewerUrls and (len(viewerUrls) > 0): - viewerUrl = getTextFromNode(viewerUrls[0]) + viewerUrl = texttool.get('digiliburlprefix', None) + if viewerUrl: docinfo['viewerURL'] = viewerUrl - - textUrls = dom.xpath("//texttool/text") - if textUrls and (len(textUrls) > 0): - textUrl = getTextFromNode(textUrls[0]) + + # old style text URL + textUrl = texttool.get('text', None) + if textUrl: if urlparse.urlparse(textUrl)[0] == "": #keine url textUrl = os.path.join(archivePath, textUrl) # fix URLs starting with /mpiwg/online @@ -549,21 +669,27 @@ class documentViewer(Folder, extraFuncti docinfo['textURL'] = textUrl - textUrls = dom.xpath("//texttool/text-url-path") - if textUrls and (len(textUrls) > 0): - textUrl = getTextFromNode(textUrls[0]) + # new style text-url-path + textUrl = texttool.get('text-url-path', None) + if textUrl: docinfo['textURLPath'] = textUrl - if not docinfo['imagePath']: + textUrlkurz = string.split(textUrl, ".")[0] + docinfo['textURLPathkurz'] = textUrlkurz + #if not docinfo['imagePath']: # text-only, no page images - docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht - - presentationUrls = dom.xpath("//texttool/presentation") + #docinfo = self.getNumTextPages(docinfo) + + # get bib info docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag + # TODO: is this needed here? + docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) - if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen + # TODO: what to do with presentation? + presentationUrl = texttool.get('presentation', None) + if presentationUrl: # 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 - presentationPath = getTextFromNode(presentationUrls[0]) + presentationPath = presentationUrl if url.endswith("index.meta"): presentationUrl = url.replace('index.meta', presentationPath) else: @@ -571,6 +697,7 @@ class documentViewer(Folder, extraFuncti docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom) + # get authorization docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info return docinfo @@ -580,18 +707,9 @@ class documentViewer(Folder, extraFuncti """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 + docinfo['author']=getText(dom.find(".//author")) + docinfo['title']=getText(dom.find(".//title")) + docinfo['year']=getText(dom.find(".//date")) return docinfo def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): @@ -610,6 +728,7 @@ class documentViewer(Folder, extraFuncti imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path docinfo['imageURL'] = imageUrl + #TODO: use getDocinfoFromIndexMeta #path ist the path to the images it assumes that the index.meta file is one level higher. docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) @@ -624,21 +743,29 @@ class documentViewer(Folder, extraFuncti 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: - logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo) + logging.debug("documentViewer (getdocinfo) docinfo in session. keys=%s"%docinfo.keys()) return docinfo + # new docinfo docinfo = {'mode': mode, 'url': url} - if mode=="texttool": #index.meta with texttool information + # add self url + docinfo['viewerUrl'] = self.getDocumentViewerURL() + if mode=="texttool": + # index.meta with texttool information docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) elif mode=="imagepath": + # folder with images, index.meta optional docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) elif mode=="filepath": + # filename docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) else: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) - - logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) + + logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) + #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) + # store in session self.REQUEST.SESSION['docinfo'] = docinfo return docinfo @@ -646,6 +773,7 @@ class documentViewer(Folder, extraFuncti """returns pageinfo with the given parameters""" pageinfo = {} current = getInt(current) + pageinfo['current'] = current rows = int(rows or self.thumbrows) pageinfo['rows'] = rows @@ -653,6 +781,7 @@ class documentViewer(Folder, extraFuncti pageinfo['cols'] = cols grpsize = cols * rows pageinfo['groupsize'] = grpsize + # what does this do? start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) # int(current / grpsize) * grpsize +1)) pageinfo['start'] = start @@ -662,20 +791,25 @@ class documentViewer(Folder, extraFuncti pageinfo['end'] = min(pageinfo['end'], np) pageinfo['numgroups'] = int(np / grpsize) if np % grpsize > 0: - pageinfo['numgroups'] += 1 + pageinfo['numgroups'] += 1 + pageinfo['viewMode'] = viewMode pageinfo['tocMode'] = tocMode - pageinfo['query'] = self.REQUEST.get('query',' ') - pageinfo['queryType'] = self.REQUEST.get('queryType',' ') + pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') + #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1') + pageinfo['query'] = self.REQUEST.get('query','') + pageinfo['queryType'] = self.REQUEST.get('queryType','') pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') pageinfo['textPN'] = self.REQUEST.get('textPN','1') pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10') pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') - toc = int (pageinfo['tocPN']) - pageinfo['textPages'] =int (toc) + # WTF?: + toc = int(pageinfo['tocPN']) + pageinfo['textPages'] =int(toc) + # What does this do? if 'tocSize_%s'%tocMode in docinfo: tocSize = int(docinfo['tocSize_%s'%tocMode]) tocPageSize = int(pageinfo['tocPageSize']) @@ -684,18 +818,30 @@ class documentViewer(Folder, extraFuncti tocPages=tocSize/tocPageSize+1 else: tocPages=tocSize/tocPageSize - pageinfo['tocPN'] = min (tocPages,toc) + + pageinfo['tocPN'] = min(tocPages,toc) + pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') pageinfo['sn'] =self.REQUEST.get('sn','') return pageinfo + + + security.declareProtected('View management screens','changeDocumentViewerForm') + changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) -def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): + def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): """init document viewer""" self.title=title self.digilibBaseUrl = digilibBaseUrl self.thumbrows = thumbrows self.thumbcols = thumbcols self.authgroups = [s.strip().lower() for s in authgroups.split(',')] + try: + # assume MetaDataFolder instance is called metadata + self.metadataService = getattr(self, 'metadata') + except Exception, e: + logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) + if RESPONSE is not None: RESPONSE.redirect('manage_main')