|
|
| version 1.4, 2006/04/07 18:45:48 | version 1.39, 2009/03/09 08:37:19 |
|---|---|
| Line 1 | Line 1 |
| genericDigilib="http://nausikaa2.rz-berlin.mpg.de/digitallibrary/" | |
| 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 Globals import package_home | from Globals import package_home |
| from Ft.Xml.Domlette import NonvalidatingReader | from Ft.Xml.Domlette import NonvalidatingReader |
| from Ft.Xml.Domlette import PrettyPrint, Print | from Ft.Xml.Domlette import PrettyPrint, Print |
| from Ft.Xml import EMPTY_NAMESPACE | from Ft.Xml import EMPTY_NAMESPACE, Parse |
| import Ft.Xml.XPath | import Ft.Xml.XPath |
| import os.path | import os.path |
| import sys | |
| import cgi | import cgi |
| import urllib | import urllib |
| import zLOG | import logging |
| import math | |
| import urlparse | |
| from types import * | |
| def logger(txt,method,txt2): | |
| """logging""" | |
| logging.info(txt+ txt2) | |
| def getInt(number, default=0): | def getInt(number, default=0): |
| """returns always an int (0 in case of problems)""" | """returns always an int (0 in case of problems)""" |
| try: | try: |
| return int(number) | return int(number) |
| except: | except: |
| return default | return int(default) |
| def getTextFromNode(nodename): | def getTextFromNode(nodename): |
| """get the cdata content of a node""" | |
| if nodename is None: | |
| return "" | |
| nodelist=nodename.childNodes | nodelist=nodename.childNodes |
| rc = "" | rc = "" |
| for node in nodelist: | for node in nodelist: |
| Line 34 def getTextFromNode(nodename): | Line 45 def getTextFromNode(nodename): |
| rc = rc + node.data | rc = rc + node.data |
| return rc | return rc |
| def getParentDir(path): | |
| """returns pathname shortened by one""" | |
| return '/'.join(path.split('/')[0:-1]) | |
| import socket | import socket |
| def urlopen(url): | def urlopen(url,timeout=2): |
| """urlopen mit timeout""" | """urlopen mit timeout""" |
| socket.setdefaulttimeout(2) | socket.setdefaulttimeout(timeout) |
| ret=urllib.urlopen(url) | ret=urllib.urlopen(url) |
| socket.setdefaulttimeout(5) | socket.setdefaulttimeout(5) |
| return ret | return ret |
| def getParamFromDigilib(path,param): | |
| """gibt param von dlInfo aus""" | |
| imageUrl=genericDigilib+"/dirInfo-xml.jsp?mo=dir&fn="+path | |
| zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo (%s) from %s"%(param,imageUrl)) | |
| try: | |
| dom = NonvalidatingReader.parseUri(imageUrl) | |
| except: | |
| return None | |
| params=dom.xpath("//dir/%s"%param) | |
| zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:%s"%params) | |
| if params: | |
| return getTextFromNode(params[0]) | |
| ## | ## |
| ## documentViewer class | ## documentViewer class |
| ## | ## |
| class documentViewer(Folder): | class documentViewer(Folder): |
| """document viewer""" | """document viewer""" |
| #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" | |
| meta_type="Document viewer" | meta_type="Document viewer" |
| Line 82 class documentViewer(Folder): | Line 81 class documentViewer(Folder): |
| image_main = PageTemplateFile('zpt/image_main', globals()) | image_main = PageTemplateFile('zpt/image_main', globals()) |
| head_main = PageTemplateFile('zpt/head_main', globals()) | head_main = PageTemplateFile('zpt/head_main', globals()) |
| docuviewer_css = PageTemplateFile('css/docuviewer.css', 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') | security.declareProtected('View management screens','changeDocumentViewerForm') |
| changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
| def __init__(self,id,imageViewerUrl,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10): | def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): |
| """init document viewer""" | """init document viewer""" |
| self.id=id | self.id=id |
| self.title=title | self.title=title |
| self.imageViewerUrl=imageViewerUrl | self.imageViewerUrl=imageViewerUrl |
| self.textViewerUrl=textViewerUrl | |
| if not digilibBaseUrl: | if not digilibBaseUrl: |
| self.digilibBaseUrl = self.findDigilibUrl() | self.digilibBaseUrl = self.findDigilibUrl() |
| else: | else: |
| self.digilibBaseUrl = digilibBaseUrl | self.digilibBaseUrl = digilibBaseUrl |
| self.thumbcols = thumbcols | self.thumbcols = thumbcols |
| self.thumbrows = thumbrows | self.thumbrows = thumbrows |
| # authgroups is list of authorized groups (delimited by ,) | |
| self.authgroups = [s.strip().lower() for s in authgroups.split(',')] | |
| # add template folder so we can always use template.something | # add template folder so we can always use template.something |
| self.manage_addFolder('template') | 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') | 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,mk=None): |
| ''' | ''' |
| view it | 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 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)) |
| print "dlbaseurl:", self.digilibBaseUrl | |
| 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 |
| print "no template folder -- creating" | |
| self.manage_addFolder('template') | self.manage_addFolder('template') |
| if not self.digilibBaseUrl: | if not self.digilibBaseUrl: |
| self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
| print "dlbaseurl:", self.digilibBaseUrl | |
| docinfo = self.getDocinfo(mode=mode,url=url) | 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) |
| pt = getattr(self.template, 'viewer_main') | 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,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): | def getLink(self,param=None,val=None): |
| """link to documentviewer with parameter param set to val""" | """link to documentviewer with parameter param set to val""" |
| params=cgi.parse_qs(self.REQUEST['QUERY_STRING']) | params=self.REQUEST.form.copy() |
| if param is not None: | if param is not None: |
| if val is None and params.has_key(param): | if val is None: |
| if params.has_key(param): | |
| del params[param] | del params[param] |
| else: | else: |
| params[param] = val | params[param] = str(val) |
| if params["mode"] == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath | |
| params["mode"] = "imagepath" | |
| params["url"] = getParentDir(params["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 | |
| return url | |
| url=self.REQUEST['URL']+"?"+urllib.urlencode(params, doseq=True) | 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 | 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=""): | def getStyle(self, idx, selected, style=""): |
| """returns a string with the given style and append 'sel' if path == selected.""" | """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: | if idx == selected: |
| return style + 'sel' | return style + 'sel' |
| else: | else: |
| return style | return style |
| def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None): | def isAccessible(self, docinfo): |
| """gets bibliographical info from the index.meta file at url or given by dom""" | """returns if access to the resource is granted""" |
| zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path)) | access = docinfo.get('accessType', None) |
| 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 is None or access in self.authgroups: | |
| # only local access -- only logged in users | |
| user = getSecurityManager().getUser() | |
| if user is not None: | |
| #print "user: ", user | |
| return (user.getUserName() != "Anonymous User") | |
| else: | |
| return False | |
| logger("documentViewer (accessOK)", logging.INFO, "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: | if docinfo is None: |
| docinfo = {} | docinfo = {} |
| for x in range(cut): | |
| path=getParentDir(path) | |
| infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path | |
| logger("documentViewer (getparamfromdigilib)", logging.INFO, "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: | |
| 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") | |
| logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) | |
| if sizes: | |
| docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
| else: | |
| docinfo['numPages'] = 0 | |
| return docinfo | |
| 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 | |
| metaUrl = url | |
| else: | |
| # online path | |
| server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
| 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: | |
| logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) | |
| if dom is None: | if dom is None: |
| server="http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary/servlet/Texter?fn=" | raise IOError("Unable to read index meta from %s"%(url)) |
| path="/".join(path.split("/")[0:-1]) | |
| metaUrl=server+path+"/index.meta" | 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: | try: |
| dom = NonvalidatingReader.parseUri(metaUrl) | # patch dirk encoding fehler treten dann nicht mehr auf |
| # dom = NonvalidatingReader.parseUri(metaUrl) | |
| txt=urllib.urlopen(metaUrl).read() | |
| dom = Parse(txt) | |
| break | |
| except: | 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,cut=0): | |
| """gets authorization info from the index.meta file at path or given by dom""" | |
| logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) | |
| access = None | |
| if docinfo is None: | |
| docinfo = {} | |
| if dom is None: | |
| for x in range(cut): | |
| path=getParentDir(path) | |
| dom = self.getIndexMeta(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() | |
| docinfo['accessType'] = access | |
| return docinfo | return docinfo |
| def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): | |
| """gets bibliographical info from the index.meta file at path or given by dom""" | |
| logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) | |
| if docinfo is None: | |
| docinfo = {} | |
| if dom is None: | |
| for x in range(cut): | |
| path=getParentDir(path) | |
| dom = self.getIndexMeta(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 | metaData=self.metadata.main.meta.bib |
| bibtype=dom.xpath("//bib/@type") | bibtype=dom.xpath("//bib/@type") |
| if bibtype and (len(bibtype)>0): | if bibtype and (len(bibtype)>0): |
| bibtype=bibtype[0].value | bibtype=bibtype[0].value |
| else: | else: |
| bibtype="generic" | bibtype="generic" |
| bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) | bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
| docinfo['bib_type'] = bibtype | |
| bibmap=metaData.generateMappingForType(bibtype) | bibmap=metaData.generateMappingForType(bibtype) |
| if len(bibmap) > 0: | # 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]) | 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]) | 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]) | 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 | return docinfo |
| def getDocinfoFromTextTool(self,url,docinfo=None): | def getDocinfoFromTextTool(self,url,dom=None,docinfo=None): |
| """parse texttool tag in index meta""" | """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: | if docinfo is None: |
| docinfo = {} | docinfo = {} |
| try: | if docinfo.get('lang',None) is None: |
| dom = NonvalidatingReader.parseUri(url) | docinfo['lang']='' # default keine Sprache gesetzt |
| except: | if dom is None: |
| zLOG.LOG("documentViewer (parseUrlTexttool)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2]) | dom = self.getIndexMeta(url) |
| return docinfo | |
| archivePaths=dom.xpath("//resource/archive-path") | 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): | if archivePaths and (len(archivePaths)>0): |
| archivePath=getTextFromNode(archivePaths[0]) | archivePath=getTextFromNode(archivePaths[0]) |
| # clean up archive path | |
| if archivePath[0] != '/': | |
| archivePath = '/' + archivePath | |
| if archiveName and (not archivePath.endswith(archiveName)): | |
| archivePath += "/" + archiveName | |
| else: | else: |
| archivePath=None | # try to get archive-path from url |
| logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/archive-path missing in: %s"%(url)) | |
| images=dom.xpath("//texttool/image") | if (not url.startswith('http')): |
| archivePath = url.replace('index.meta', '') | |
| if images and (len(images)>0): | |
| image=getTextFromNode(images[0]) | 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: | else: |
| image=None | # 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) | |
| imageDir=imageDir.replace("/mpiwg/online",'') | |
| docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo) | |
| docinfo['imagePath'] = imageDir | |
| if image and archivePath: | docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir |
| image=os.path.join(archivePath,image) | |
| image=image.replace("/mpiwg/online",'') | |
| pt=getParamFromDigilib(image,'size') | |
| docinfo['imagePath'] = image | |
| docinfo['numPages'] = pt | |
| viewerUrls=dom.xpath("//texttool/digiliburlprefix") | viewerUrls=dom.xpath("//texttool/digiliburlprefix") |
| if viewerUrls and (len(viewerUrls)>0): | if viewerUrls and (len(viewerUrls)>0): |
| viewerUrl=getTextFromNode(viewerUrls[0]) | viewerUrl=getTextFromNode(viewerUrls[0]) |
| docinfo['imageURL'] = viewerURL | docinfo['viewerURL'] = viewerUrl |
| textUrls=dom.xpath("//texttool/text") | textUrls=dom.xpath("//texttool/text") |
| if textUrls and (len(textUrls)>0): | if textUrls and (len(textUrls)>0): |
| textUrl=getTextFromNode(textUrls[0]) | textUrl=getTextFromNode(textUrls[0]) |
| docinfo['textURL'] = textURL | 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 | |
| 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) | |
| docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) | docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info |
| return docinfo | return docinfo |
| def getDocinfoFromImagePath(self,path,docinfo=None): | 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.""" | """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: | if docinfo is None: |
| docinfo = {} | docinfo = {} |
| docinfo['imagePath'] = path | |
| path=path.replace("/mpiwg/online","") | path=path.replace("/mpiwg/online","") |
| pt=getParamFromDigilib(path,'size') | docinfo['imagePath'] = path |
| docinfo['numPages'] = pt | docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) |
| imageUrl=genericDigilib+"/servlet/Scaler?fn=%s"%path | |
| pathorig=path | |
| for x in range(cut): | |
| path=getParentDir(path) | |
| logging.error("PATH:"+path) | |
| imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path | |
| docinfo['imageURL'] = imageUrl | docinfo['imageURL'] = imageUrl |
| docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo) | #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) | |
| return docinfo | return docinfo |
| def getDocinfo(self, mode, url): | def getDocinfo(self, mode, url): |
| """returns docinfo depending on mode""" | """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 | # look for cached docinfo in session |
| if self.REQUEST.SESSION.has_key('docinfo'): | if self.REQUEST.SESSION.has_key('docinfo'): |
| 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: |
| zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo in session: %s"%docinfo) | logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) |
| return docinfo | return docinfo |
| # new docinfo | # new docinfo |
| docinfo = {'mode': mode, 'url': url} | docinfo = {'mode': mode, 'url': url} |
| Line 264 class documentViewer(Folder): | Line 569 class documentViewer(Folder): |
| docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) |
| elif mode=="imagepath": | elif mode=="imagepath": |
| docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) |
| elif mode=="filepath": | |
| docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) | |
| else: | else: |
| zLOG.LOG("documentViewer (getdocinfo)", zLOG.ERROR,"unknown mode!") | logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") |
| zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo: %s"%docinfo) | raise ValueError("Unknown mode %s"%(mode)) |
| logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) | |
| self.REQUEST.SESSION['docinfo'] = docinfo | self.REQUEST.SESSION['docinfo'] = docinfo |
| return docinfo | return docinfo |
| Line 282 class documentViewer(Folder): | Line 591 class documentViewer(Folder): |
| pageinfo['cols'] = cols | pageinfo['cols'] = cols |
| grpsize = cols * rows | grpsize = cols * rows |
| pageinfo['groupsize'] = grpsize | 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))) |
| print "start3:", start | # int(current / grpsize) * grpsize +1)) |
| pageinfo['start'] = start | pageinfo['start'] = start |
| pageinfo['end'] = start + grpsize | pageinfo['end'] = start + grpsize |
| if docinfo is not None: | if docinfo is not None: |
| Line 300 class documentViewer(Folder): | Line 609 class documentViewer(Folder): |
| if mode=="texttool": #index.meta with texttool information | if mode=="texttool": #index.meta with texttool information |
| (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) | (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) |
| print textpath | #print textpath |
| try: | try: |
| dom = NonvalidatingReader.parseUri(textpath) | dom = NonvalidatingReader.parseUri(textpath) |
| except: | except: |
| Line 352 class documentViewer(Folder): | Line 661 class documentViewer(Folder): |
| def findDigilibUrl(self): | def findDigilibUrl(self): |
| """try to get the digilib URL from zogilib""" | """try to get the digilib URL from zogilib""" |
| url = self.imageViewerUrl[:-1] + "/getScalerUrl" | 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: | try: |
| if urlparse.urlparse(url)[0]=='': #relative path | |
| url=urlparse.urljoin(self.absolute_url()+"/",url) | |
| scaler = urlopen(url).read() | scaler = urlopen(url).read() |
| return scaler.replace("/servlet/Scaler?", "") | return scaler.replace("/servlet/Scaler?", "") |
| except: | except: |
| return None | return None |
| def changeDocumentViewer(self,imageViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,RESPONSE=None): | def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): |
| """init document viewer""" | """init document viewer""" |
| self.title=title | self.title=title |
| self.imageViewerUrl=imageViewerUrl | self.imageViewerUrl=imageViewerUrl |
| self.textViewerUrl=textViewerUrl | |
| self.digilibBaseUrl = digilibBaseUrl | self.digilibBaseUrl = digilibBaseUrl |
| self.thumbrows = thumbrows | self.thumbrows = thumbrows |
| self.thumbcols = thumbcols | self.thumbcols = thumbcols |
| self.authgroups = [s.strip().lower() for s in authgroups.split(',')] | |
| if RESPONSE is not None: | if RESPONSE is not None: |
| RESPONSE.redirect('manage_main') | RESPONSE.redirect('manage_main') |
| Line 379 def manage_AddDocumentViewerForm(self): | Line 697 def manage_AddDocumentViewerForm(self): |
| pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) | pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
| return pt() | return pt() |
| def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None): | def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None): |
| """add the viewer""" | """add the viewer""" |
| newObj=documentViewer(id,imageViewerUrl,title) | newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl) |
| self._setObject(id,newObj) | self._setObject(id,newObj) |
| if RESPONSE is not None: | if RESPONSE is not None: |
| Line 407 def manage_addDocumentViewerTemplate(sel | Line 725 def manage_addDocumentViewerTemplate(sel |
| self._setObject(id, DocumentViewerTemplate(id)) | self._setObject(id, DocumentViewerTemplate(id)) |
| ob = getattr(self, 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: | if title: |
| ob.pt_setTitle(title) | ob.pt_setTitle(title) |
| try: | try: |