|
|
| version 1.175, 2011/06/14 09:57:11 | version 1.175.2.5, 2011/07/19 18:46:35 |
|---|---|
| Line 1 | Line 1 |
| from OFS.Folder import Folder | from OFS.Folder import Folder |
| from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate | 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 ClassSecurityInfo |
| from AccessControl import getSecurityManager | from AccessControl import getSecurityManager |
| from Globals import package_home | from Globals import package_home |
| from Products.zogiLib.zogiLib import browserCheck | |
| from Ft.Xml import EMPTY_NAMESPACE, Parse | #from Ft.Xml import EMPTY_NAMESPACE, Parse |
| import Ft.Xml.Domlette | #import Ft.Xml.Domlette |
| import xml.etree.ElementTree as ET | |
| import os.path | import os.path |
| import sys | import sys |
| import urllib | import urllib |
| import urllib2 | |
| import logging | import logging |
| import math | import math |
| import urlparse | import urlparse |
| import cStringIO | |
| import re | import re |
| import string | import string |
| from SrvTxtUtils import getInt, getText, getHttpData | |
| def logger(txt,method,txt2): | def logger(txt,method,txt2): |
| """logging""" | """logging""" |
| logging.info(txt+ txt2) | 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""" | """returns a string containing node as XML""" |
| stream = cStringIO.StringIO() | s = ET.tostring(node) |
| #logging.debug("BUF: %s"%(stream)) | |
| Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) | # 4Suite: |
| s = stream.getvalue() | # stream = cStringIO.StringIO() |
| #logging.debug("BUF: %s"%(s)) | # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) |
| stream.close() | # s = stream.getvalue() |
| # stream.close() | |
| return s | return s |
| def browserCheck(self): | def browserCheck(self): |
| Line 114 def browserCheck(self): | Line 98 def browserCheck(self): |
| return bt | return bt |
| def getParentDir(path): | def getParentDir(path): |
| """returns pathname shortened by one""" | """returns pathname shortened by one""" |
| return '/'.join(path.split('/')[0:-1]) | return '/'.join(path.split('/')[0:-1]) |
| def getBibdataFromDom(dom): | |
| """returns dict with all elements from bib-tag""" | |
| bibinfo = {} | |
| bib = dom.find(".//meta/bib") | |
| if bib is not None: | |
| # put type in @type | |
| type = bib.get('type') | |
| bibinfo['@type'] = type | |
| # put all subelements in dict | |
| for e in bib: | |
| bibinfo[e.tag] = getText(e) | |
| def getHttpData(url, data=None, num_tries=3, timeout=10): | return bibinfo |
| """returns result from url+data HTTP request""" | |
| # we do GET (by appending data to url) | |
| if isinstance(data, str) or isinstance(data, unicode): | |
| # if data is string then append | |
| url = "%s?%s"%(url,data) | |
| elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple): | |
| # urlencode | |
| url = "%s?%s"%(url,urllib.urlencode(data)) | |
| response = None | |
| errmsg = None | |
| for cnt in range(num_tries): | |
| try: | |
| logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url)) | |
| if sys.version_info < (2, 6): | |
| # set timeout on socket -- ugly :-( | |
| import socket | |
| socket.setdefaulttimeout(float(timeout)) | |
| response = urllib2.urlopen(url) | |
| else: | |
| response = urllib2.urlopen(url,timeout=float(timeout)) | |
| # check result? | |
| break | |
| except urllib2.HTTPError, e: | |
| logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e)) | |
| errmsg = str(e) | |
| # stop trying | |
| break | |
| except urllib2.URLError, e: | |
| logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e)) | |
| errmsg = str(e) | |
| # stop trying | |
| #break | |
| if response is not None: | |
| data = response.read() | |
| response.close() | |
| return data | |
| raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) | |
| #return None | |
| ## | ## |
| ## documentViewer class | ## documentViewer class |
| Line 290 class documentViewer(Folder): | Line 243 class documentViewer(Folder): |
| ''' | ''' |
| logging.debug("HHHHHHHHHHHHHH:load the rss") | 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'): | if not hasattr(self, 'template'): |
| # create template folder if it doesn't exist | # create template folder if it doesn't exist |
| Line 341 class documentViewer(Folder): | Line 294 class documentViewer(Folder): |
| # get table of contents | # get table of contents |
| docinfo = self.getToc(mode=tocMode, docinfo=docinfo) | docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
| if viewMode=="auto": # automodus gewaehlt | # auto viewMode: text_dict if text else images |
| if docinfo.has_key('textURL') or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert | if viewMode=="auto": |
| if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): | |
| #texturl gesetzt und textViewer konfiguriert | |
| viewMode="text_dict" | viewMode="text_dict" |
| else: | else: |
| viewMode="images" | 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) |
| if (docinfo.get('textURLPath',None)): | if viewMode != 'images' and docinfo.get('textURLPath', None): |
| page = self.getTextPage(docinfo=docinfo, pageinfo=pageinfo) | # get full text page |
| page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo) | |
| pageinfo['textPage'] = page | pageinfo['textPage'] = page |
| tt = getattr(self, 'template') | |
| pt = getattr(tt, 'viewer_main') | # 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)) | return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
| def generateMarks(self,mk): | def generateMarks(self,mk): |
| Line 485 class documentViewer(Folder): | Line 443 class documentViewer(Folder): |
| docinfo = {} | docinfo = {} |
| for x in range(cut): | for x in range(cut): |
| path=getParentDir(path) | path=getParentDir(path) |
| infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path | infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
| Line 496 class documentViewer(Folder): | Line 453 class documentViewer(Folder): |
| if txt is None: | if txt is None: |
| raise IOError("Unable to get dir-info from %s"%(infoUrl)) | raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
| dom = Parse(txt) | dom = ET.fromstring(txt) |
| sizes=dom.xpath("//dir/size") | #dom = Parse(txt) |
| logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) | size=getText(dom.find("size")) |
| #sizes=dom.xpath("//dir/size") | |
| logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size) | |
| if sizes: | if size: |
| docinfo['numPages'] = int(getTextFromNode(sizes[0])) | docinfo['numPages'] = int(size) |
| else: | else: |
| docinfo['numPages'] = 0 | docinfo['numPages'] = 0 |
| Line 546 class documentViewer(Folder): | Line 505 class documentViewer(Folder): |
| if txt is None: | if txt is None: |
| raise IOError("Unable to read index meta from %s"%(url)) | raise IOError("Unable to read index meta from %s"%(url)) |
| dom = Parse(txt) | dom = ET.fromstring(txt) |
| #dom = Parse(txt) | |
| return dom | return dom |
| def getPresentationInfoXML(self, url): | def getPresentationInfoXML(self, url): |
| Line 565 class documentViewer(Folder): | Line 525 class documentViewer(Folder): |
| if txt is None: | if txt is None: |
| raise IOError("Unable to read infoXMLfrom %s"%(url)) | raise IOError("Unable to read infoXMLfrom %s"%(url)) |
| dom = Parse(txt) | dom = ET.fromstring(txt) |
| #dom = Parse(txt) | |
| return dom | return dom |
| Line 583 class documentViewer(Folder): | Line 544 class documentViewer(Folder): |
| path=getParentDir(path) | path=getParentDir(path) |
| dom = self.getDomFromIndexMeta(path) | dom = self.getDomFromIndexMeta(path) |
| acctype = dom.xpath("//access-conditions/access/@type") | acc = dom.find(".//access-conditions/access") |
| if acctype and (len(acctype)>0): | if acc is not None: |
| access=acctype[0].value | acctype = acc.get('type') |
| #acctype = dom.xpath("//access-conditions/access/@type") | |
| if acctype: | |
| access=acctype | |
| if access in ['group', 'institution']: | if access in ['group', 'institution']: |
| access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() | access = dom.find(".//access-conditions/access/name").text.lower() |
| docinfo['accessType'] = access | docinfo['accessType'] = access |
| return docinfo | return docinfo |
| Line 609 class documentViewer(Folder): | Line 573 class documentViewer(Folder): |
| logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) | logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
| # put in all raw bib fields as dict "bib" | # put in all raw bib fields as dict "bib" |
| bib = dom.xpath("//bib/*") | bib = getBibdataFromDom(dom) |
| if bib and len(bib)>0: | docinfo['bib'] = bib |
| bibinfo = {} | |
| for e in bib: | |
| bibinfo[e.localName] = getTextFromNode(e) | |
| docinfo['bib'] = bibinfo | |
| # extract some fields (author, title, year) according to their mapping | # extract some fields (author, title, year) according to their mapping |
| metaData=self.metadata.main.meta.bib | metaData=self.metadata.main.meta.bib |
| bibtype=dom.xpath("//bib/@type") | bibtype=bib.get("@type") |
| if bibtype and (len(bibtype)>0): | #bibtype=dom.xpath("//bib/@type") |
| bibtype=bibtype[0].value | if not bibtype: |
| else: | |
| bibtype="generic" | bibtype="generic" |
| bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) | bibtype=bibtype.replace("-"," ") # wrong types in index meta "-" instead of " " (not wrong! ROC) |
| docinfo['bib_type'] = bibtype | docinfo['bib_type'] = bibtype |
| bibmap=metaData.generateMappingForType(bibtype) | bibmap=metaData.generateMappingForType(bibtype) |
| logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap)) | logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap)) |
| logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype)) | logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype)) |
| # if there is no mapping bibmap is empty (mapping sometimes has empty fields) | # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
| if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: | if len(bibmap) > 0 and bibmap.get('author',None) or bibmap.get('title',None): |
| try: | try: |
| docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) | docinfo['author']=bib.get(bibmap['author'][0]) |
| except: pass | except: pass |
| try: | try: |
| docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | docinfo['title']=bib.get(bibmap['title'][0]) |
| except: pass | except: pass |
| try: | try: |
| docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | docinfo['year']=bib.get(bibmap['year'][0]) |
| except: pass | except: pass |
| logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) | |
| try: | # ROC: why is this here? |
| docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | # logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
| except: | # try: |
| docinfo['lang']='' | # docinfo['lang']=getTextFromNode(dom.find(".//bib/lang")[0]) |
| try: | # except: |
| docinfo['city']=getTextFromNode(dom.xpath("//bib/city")[0]) | # docinfo['lang']='' |
| except: | # try: |
| docinfo['city']='' | # docinfo['city']=getTextFromNode(dom.find(".//bib/city")[0]) |
| try: | # except: |
| docinfo['number_of_pages']=getTextFromNode(dom.xpath("//bib/number_of_pages")[0]) | # docinfo['city']='' |
| except: | # try: |
| docinfo['number_of_pages']='' | # docinfo['number_of_pages']=getTextFromNode(dom.find(".//bib/number_of_pages")[0]) |
| try: | # except: |
| docinfo['series_volume']=getTextFromNode(dom.xpath("//bib/series_volume")[0]) | # docinfo['number_of_pages']='' |
| except: | # try: |
| docinfo['series_volume']='' | # docinfo['series_volume']=getTextFromNode(dom.find(".//bib/series_volume")[0]) |
| try: | # except: |
| docinfo['number_of_volumes']=getTextFromNode(dom.xpath("//bib/number_of_volumes")[0]) | # docinfo['series_volume']='' |
| except: | # try: |
| docinfo['number_of_volumes']='' | # docinfo['number_of_volumes']=getTextFromNode(dom.find(".//bib/number_of_volumes")[0]) |
| try: | # except: |
| docinfo['translator']=getTextFromNode(dom.xpath("//bib/translator")[0]) | # docinfo['number_of_volumes']='' |
| except: | # try: |
| docinfo['translator']='' | # docinfo['translator']=getTextFromNode(dom.find(".//bib/translator")[0]) |
| try: | # except: |
| docinfo['edition']=getTextFromNode(dom.xpath("//bib/edition")[0]) | # docinfo['translator']='' |
| except: | # try: |
| docinfo['edition']='' | # docinfo['edition']=getTextFromNode(dom.find(".//bib/edition")[0]) |
| try: | # except: |
| docinfo['series_author']=getTextFromNode(dom.xpath("//bib/series_author")[0]) | # docinfo['edition']='' |
| except: | # try: |
| docinfo['series_author']='' | # docinfo['series_author']=getTextFromNode(dom.find(".//bib/series_author")[0]) |
| try: | # except: |
| docinfo['publisher']=getTextFromNode(dom.xpath("//bib/publisher")[0]) | # docinfo['series_author']='' |
| except: | # try: |
| docinfo['publisher']='' | # docinfo['publisher']=getTextFromNode(dom.find(".//bib/publisher")[0]) |
| try: | # except: |
| docinfo['series_title']=getTextFromNode(dom.xpath("//bib/series_title")[0]) | # docinfo['publisher']='' |
| except: | # try: |
| docinfo['series_title']='' | # docinfo['series_title']=getTextFromNode(dom.find(".//bib/series_title")[0]) |
| try: | # except: |
| docinfo['isbn_issn']=getTextFromNode(dom.xpath("//bib/isbn_issn")[0]) | # docinfo['series_title']='' |
| except: | # try: |
| docinfo['isbn_issn']='' | # docinfo['isbn_issn']=getTextFromNode(dom.find(".//bib/isbn_issn")[0]) |
| # except: | |
| # docinfo['isbn_issn']='' | |
| return docinfo | return docinfo |
| # TODO: is this needed? | |
| def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): | def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
| """gets name info from the index.meta file at path or given by dom""" | """gets name info from the index.meta file at path or given by dom""" |
| if docinfo is None: | if docinfo is None: |
| Line 698 class documentViewer(Folder): | Line 660 class documentViewer(Folder): |
| path=getParentDir(path) | path=getParentDir(path) |
| dom = self.getDomFromIndexMeta(path) | dom = self.getDomFromIndexMeta(path) |
| docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0]) | docinfo['name']=getText(dom.find("name")) |
| logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) | logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) |
| return docinfo | return docinfo |
| Line 715 class documentViewer(Folder): | Line 677 class documentViewer(Folder): |
| archivePath = None | archivePath = None |
| archiveName = None | archiveName = None |
| archiveNames = dom.xpath("//resource/name") | archiveName = getText(dom.find("name")) |
| if archiveNames and (len(archiveNames) > 0): | if not archiveName: |
| archiveName = getTextFromNode(archiveNames[0]) | |
| else: | |
| logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) | logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) |
| archivePaths = dom.xpath("//resource/archive-path") | archivePath = getText(dom.find("archive-path")) |
| if archivePaths and (len(archivePaths) > 0): | if archivePath: |
| archivePath = getTextFromNode(archivePaths[0]) | |
| # clean up archive path | # clean up archive path |
| if archivePath[0] != '/': | if archivePath[0] != '/': |
| archivePath = '/' + archivePath | archivePath = '/' + archivePath |
| Line 739 class documentViewer(Folder): | Line 698 class documentViewer(Folder): |
| # we balk without archive-path | # we balk without archive-path |
| raise IOError("Missing archive-path (for text-tool) in %s" % (url)) | raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
| imageDirs = dom.xpath("//texttool/image") | imageDir = getText(dom.find(".//texttool/image")) |
| if imageDirs and (len(imageDirs) > 0): | |
| imageDir = getTextFromNode(imageDirs[0]) | |
| else: | if not imageDir: |
| # we balk with no image tag / not necessary anymore because textmode is now standard | # we balk with no image tag / not necessary anymore because textmode is now standard |
| #raise IOError("No text-tool info in %s"%(url)) | #raise IOError("No text-tool info in %s"%(url)) |
| imageDir = "" | imageDir = "" |
| Line 760 class documentViewer(Folder): | Line 717 class documentViewer(Folder): |
| docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir | docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir |
| viewerUrls = dom.xpath("//texttool/digiliburlprefix") | viewerUrl = getText(dom.find(".//texttool/digiliburlprefix")) |
| if viewerUrls and (len(viewerUrls) > 0): | if viewerUrl: |
| viewerUrl = getTextFromNode(viewerUrls[0]) | |
| docinfo['viewerURL'] = viewerUrl | docinfo['viewerURL'] = viewerUrl |
| # old style text URL | # old style text URL |
| textUrls = dom.xpath("//texttool/text") | textUrl = getText(dom.find(".//texttool/text")) |
| if textUrls and (len(textUrls) > 0): | if textUrl: |
| textUrl = getTextFromNode(textUrls[0]) | |
| if urlparse.urlparse(textUrl)[0] == "": #keine url | if urlparse.urlparse(textUrl)[0] == "": #keine url |
| textUrl = os.path.join(archivePath, textUrl) | textUrl = os.path.join(archivePath, textUrl) |
| # fix URLs starting with /mpiwg/online | # fix URLs starting with /mpiwg/online |
| Line 778 class documentViewer(Folder): | Line 733 class documentViewer(Folder): |
| docinfo['textURL'] = textUrl | docinfo['textURL'] = textUrl |
| # new style text-url-path | # new style text-url-path |
| textUrls = dom.xpath("//texttool/text-url-path") | textUrl = getText(dom.find(".//texttool/text-url-path")) |
| if textUrls and (len(textUrls) > 0): | if textUrl: |
| textUrl = getTextFromNode(textUrls[0]) | |
| docinfo['textURLPath'] = textUrl | docinfo['textURLPath'] = textUrl |
| textUrlkurz = string.split(textUrl, ".")[0] | textUrlkurz = string.split(textUrl, ".")[0] |
| docinfo['textURLPathkurz'] = textUrlkurz | docinfo['textURLPathkurz'] = textUrlkurz |
| Line 789 class documentViewer(Folder): | Line 743 class documentViewer(Folder): |
| #docinfo = self.getNumTextPages(docinfo) | #docinfo = self.getNumTextPages(docinfo) |
| presentationUrls = dom.xpath("//texttool/presentation") | presentationUrl = getText(dom.find(".//texttool/presentation")) |
| docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag | 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) | docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) |
| if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen | if presentationUrl: # ueberschreibe diese durch presentation informationen |
| # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten | # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten |
| # durch den relativen Pfad auf die presentation infos | # durch den relativen Pfad auf die presentation infos |
| presentationPath = getTextFromNode(presentationUrls[0]) | presentationPath = presentationUrl |
| if url.endswith("index.meta"): | if url.endswith("index.meta"): |
| presentationUrl = url.replace('index.meta', presentationPath) | presentationUrl = url.replace('index.meta', presentationPath) |
| else: | else: |
| Line 814 class documentViewer(Folder): | Line 769 class documentViewer(Folder): |
| """gets the bibliographical information from the preseantion entry in texttools | """gets the bibliographical information from the preseantion entry in texttools |
| """ | """ |
| dom=self.getPresentationInfoXML(url) | dom=self.getPresentationInfoXML(url) |
| try: | docinfo['author']=getText(dom.find(".//author")) |
| docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) | docinfo['title']=getText(dom.find(".//title")) |
| except: | docinfo['year']=getText(dom.find(".//date")) |
| pass | |
| try: | |
| docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) | |
| except: | |
| pass | |
| try: | |
| docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) | |
| except: | |
| pass | |
| return docinfo | return docinfo |
| def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): | def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
| Line 858 class documentViewer(Folder): | Line 804 class documentViewer(Folder): |
| docinfo = self.REQUEST.SESSION['docinfo'] | docinfo = self.REQUEST.SESSION['docinfo'] |
| # check if its still current | # check if its still current |
| if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | 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 | return docinfo |
| # new docinfo | # new docinfo |
| docinfo = {'mode': mode, 'url': url} | 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) | docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) |
| elif mode=="imagepath": | elif mode=="imagepath": |
| # folder with images, index.meta optional | |
| docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) |
| elif mode=="filepath": | elif mode=="filepath": |
| # filename | |
| docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) | docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
| else: | else: |
| logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) | logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) |
| Line 876 class documentViewer(Folder): | Line 828 class documentViewer(Folder): |
| if not docinfo.has_key('textURLPath'): | if not docinfo.has_key('textURLPath'): |
| docinfo['textURLPath'] = None | docinfo['textURLPath'] = None |
| logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) | logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
| #logging.debug("documentViewer (getdocinfo) docinfo: %s"%) | #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) |
| self.REQUEST.SESSION['docinfo'] = docinfo | self.REQUEST.SESSION['docinfo'] = docinfo |
| return docinfo | return docinfo |