Mercurial > hg > documentViewer

comparison documentViewer.py @ 464:19bd41d95f62 elementtree

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
first version with new getdocinfo
author casties
date Fri, 29 Jul 2011 18:27:24 +0200
parents 89ad327b4bbd
children 224aad394350
comparison
equal deleted inserted replaced
463:89ad327b4bbd 464:19bd41d95f62
96 bt['isIEMac'] = bt['isIE'] and bt['isMac'] 96 bt['isIEMac'] = bt['isIE'] and bt['isMac']
97 bt['staticHTML'] = False 97 bt['staticHTML'] = False
98 98
99 return bt 99 return bt
100 100
101 def getParentDir(path): 101 def getParentPath(path, cnt=1):
102 """returns pathname shortened by one""" 102 """returns pathname shortened by cnt"""
103 return '/'.join(path.split('/')[0:-1]) 103 # make sure path doesn't end with /
104 104 path = path.rstrip('/')
105 # split by /, shorten, and reassemble
106 return '/'.join(path.split('/')[0:-cnt])
107
105 108
106 ## 109 ##
107 ## documentViewer class 110 ## documentViewer class
108 ## 111 ##
109 class documentViewer(Folder): 112 class documentViewer(Folder):
261 264
262 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) 265 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
263 266
264 security.declareProtected('View','index_html') 267 security.declareProtected('View','index_html')
265 def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None): 268 def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
266 ''' 269 """
267 view it 270 view it
268 @param mode: defines how to access the document behind url 271 @param mode: defines how to access the document behind url
269 @param url: url which contains display information 272 @param url: url which contains display information
270 @param viewMode: if images display images, if text display text, default is auto (text,images or auto) 273 @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
271 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) 274 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
272 @param characterNormalization type of text display (reg, norm, none) 275 """
273 @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
274 '''
275 276
276 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) 277 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
277 278
278 if not hasattr(self, 'template'): 279 if not hasattr(self, 'template'):
279 # this won't work 280 # this won't work
368 urlParams[k] = v 369 urlParams[k] = v
369 370
370 # FIXME: does this belong here? 371 # FIXME: does this belong here?
371 if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath 372 if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
372 urlParams["mode"] = "imagepath" 373 urlParams["mode"] = "imagepath"
373 urlParams["url"] = getParentDir(urlParams["url"]) 374 urlParams["url"] = getParentPath(urlParams["url"])
374 375
375 # quote values and assemble into query string (not escaping '/') 376 # quote values and assemble into query string (not escaping '/')
376 ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()]) 377 ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
377 #ps = urllib.urlencode(urlParams) 378 #ps = urllib.urlencode(urlParams)
378 if baseUrl is None: 379 if baseUrl is None:
436 """gibt param von dlInfo aus""" 437 """gibt param von dlInfo aus"""
437 if docinfo is None: 438 if docinfo is None:
438 docinfo = {} 439 docinfo = {}
439 440
440 for x in range(cut): 441 for x in range(cut):
441 path=getParentDir(path) 442 path=getParentPath(path)
442 443
443 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path 444 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
444 445
445 logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) 446 logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
446 447
534 if docinfo is None: 535 if docinfo is None:
535 docinfo = {} 536 docinfo = {}
536 537
537 if dom is None: 538 if dom is None:
538 for x in range(cut): 539 for x in range(cut):
539 path=getParentDir(path) 540 path=getParentPath(path)
540 dom = self.getDomFromIndexMeta(path) 541 dom = self.getDomFromIndexMeta(path)
541 542
542 acc = dom.find(".//access-conditions/access") 543 acc = dom.find(".//access-conditions/access")
543 if acc is not None: 544 if acc is not None:
544 acctype = acc.get('type') 545 acctype = acc.get('type')
589 if docinfo is None: 590 if docinfo is None:
590 docinfo = {} 591 docinfo = {}
591 592
592 if dom is None: 593 if dom is None:
593 for x in range(cut): 594 for x in range(cut):
594 path=getParentDir(path) 595 path=getParentPath(path)
595 dom = self.getDomFromIndexMeta(path) 596 dom = self.getDomFromIndexMeta(path)
596 597
597 docinfo['name']=getText(dom.find("name")) 598 docinfo['name']=getText(dom.find("name"))
598 logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) 599 logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
599 return docinfo 600 return docinfo
721 docinfo['imagePath'] = path 722 docinfo['imagePath'] = path
722 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) 723 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
723 724
724 pathorig=path 725 pathorig=path
725 for x in range(cut): 726 for x in range(cut):
726 path=getParentDir(path) 727 path=getParentPath(path)
727 logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path) 728 logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
728 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path 729 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
729 docinfo['imageURL'] = imageUrl 730 docinfo['imageURL'] = imageUrl
730 731
731 #TODO: use getDocinfoFromIndexMeta 732 #TODO: use getDocinfoFromIndexMeta
733 docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) 734 docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
734 docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) 735 docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
735 return docinfo 736 return docinfo
736 737
737 738
738 def getDocinfo(self, mode, url): 739 def OLDgetDocinfo(self, mode, url):
739 """returns docinfo depending on mode""" 740 """returns docinfo depending on mode"""
740 logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url)) 741 logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
741 # look for cached docinfo in session 742 # look for cached docinfo in session
742 if self.REQUEST.SESSION.has_key('docinfo'): 743 if self.REQUEST.SESSION.has_key('docinfo'):
743 docinfo = self.REQUEST.SESSION['docinfo'] 744 docinfo = self.REQUEST.SESSION['docinfo']
766 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) 767 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
767 #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) 768 #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
768 # store in session 769 # store in session
769 self.REQUEST.SESSION['docinfo'] = docinfo 770 self.REQUEST.SESSION['docinfo'] = docinfo
770 return docinfo 771 return docinfo
771 772
773
774 def getDocinfo(self, mode, url):
775 """returns docinfo depending on mode"""
776 logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
777 # look for cached docinfo in session
778 if self.REQUEST.SESSION.has_key('docinfo'):
779 docinfo = self.REQUEST.SESSION['docinfo']
780 # check if its still current
781 if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:
782 logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())
783 return docinfo
784
785 # new docinfo
786 docinfo = {'mode': mode, 'url': url}
787 # add self url
788 docinfo['viewerUrl'] = self.getDocumentViewerURL()
789 # get index.meta DOM
790 docUrl = None
791 metaDom = None
792 if mode=="texttool":
793 # url points to document dir or index.meta
794 metaDom = self.metadataService.getDomFromPathOrUrl(url)
795 docUrl = url.replace('/index.meta', '')
796 if metaDom is None:
797 raise IOError("Unable to find index.meta for mode=texttool!")
798
799 elif mode=="imagepath":
800 # url points to folder with images, index.meta optional
801 # asssume index.meta in parent dir
802 docUrl = getParentPath(url)
803 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
804
805 elif mode=="filepath":
806 # url points to image file, index.meta optional
807 # asssume index.meta is two path segments up
808 docUrl = getParentPath(url, 2)
809 metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
810
811 else:
812 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
813 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
814
815 docinfo['documentUrl'] = docUrl
816 # process index.meta contents
817 if metaDom is not None:
818 # document directory name and path
819 resource = self.metadataService.getResourceData(dom=metaDom)
820 if resource:
821 docinfo = self.getDocinfoFromResource(docinfo, resource)
822
823 # texttool info
824 texttool = self.metadataService.getTexttoolData(dom=metaDom)
825 if texttool:
826 docinfo = self.getDocinfoFromTexttool(docinfo, texttool)
827
828 # bib info
829 bib = self.metadataService.getBibData(dom=metaDom)
830 if bib:
831 docinfo = self.getDocinfoFromBib(docinfo, bib)
832
833 # auth info
834 access = self.metadataService.getAccessData(dom=metaDom)
835 if access:
836 docinfo = self.getDocinfoFromAccess(docinfo, access)
837
838 # image path
839 if mode != 'texttool':
840 # override image path from texttool
841 docinfo['imagePath'] = url
842
843 # number of images from digilib
844 if docinfo.get('imagePath', None):
845 docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath']
846 docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath'])
847
848 logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
849 #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
850 # store in session
851 self.REQUEST.SESSION['docinfo'] = docinfo
852 return docinfo
853
854 def getDocinfoFromResource(self, docinfo, resource):
855 """reads contents of resource element into docinfo"""
856 docName = resource.get('name', None)
857 docinfo['documentName'] = docName
858 docPath = resource.get('archive-path', None)
859 if docPath:
860 # clean up document path
861 if docPath[0] != '/':
862 docPath = '/' + docPath
863
864 if docName and (not docPath.endswith(docName)):
865 docPath += "/" + docName
866
867 else:
868 # use docUrl as docPath
869 docUrl = docinfo['documentURL']
870 if not docUrl.startswith('http:'):
871 docPath = docUrl
872
873 docinfo['documentPath'] = docPath
874 return docinfo
875
876 def getDocinfoFromTexttool(self, docinfo, texttool):
877 """reads contents of texttool element into docinfo"""
878 # image dir
879 imageDir = texttool.get('image', None)
880 docPath = docinfo.get('documentPath', None)
881 if imageDir and docPath:
882 #print "image: ", imageDir, " archivepath: ", archivePath
883 imageDir = os.path.join(docPath, imageDir)
884 imageDir = imageDir.replace('/mpiwg/online', '', 1)
885 docinfo['imagePath'] = imageDir
886
887 # old style text URL
888 textUrl = texttool.get('text', None)
889 if textUrl and docPath:
890 if urlparse.urlparse(textUrl)[0] == "": #keine url
891 textUrl = os.path.join(docPath, textUrl)
892 # fix URLs starting with /mpiwg/online
893 textUrl = textUrl.replace('/mpiwg/online', '', 1)
894
895 docinfo['textURL'] = textUrl
896
897 # new style text-url-path
898 textUrl = texttool.get('text-url-path', None)
899 if textUrl:
900 docinfo['textURLPath'] = textUrl
901 #TODO: ugly:
902 #textUrlkurz = string.split(textUrl, ".")[0]
903 #docinfo['textURLPathkurz'] = textUrlkurz
904
905 # old presentation stuff
906 presentation = texttool.get('presentation', None)
907 if presentation and docPath:
908 docinfo['presentationPath'] = os.path.join(docPath, presentation)
909
910 return docinfo
911
912 def getDocinfoFromBib(self, docinfo, bib):
913 """reads contents of bib element into docinfo"""
914 # put all raw bib fields in dict "bib"
915 docinfo['bib'] = bib
916 bibtype = bib.get('@type', None)
917 docinfo['bibType'] = bibtype
918 # also store DC metadata for convenience
919 dc = self.metadataService.getDCMappedData(bib)
920 docinfo['creator'] = dc.get('creator',None)
921 docinfo['title'] = dc.get('title',None)
922 docinfo['date'] = dc.get('date',None)
923 return docinfo
924
925 def getDocinfoFromAccess(self, docinfo, acc):
926 """reads contents of access element into docinfo"""
927 #TODO: also read resource type
928 try:
929 acctype = accc['@attr']['type']
930 if acctype:
931 access=acctype
932 if access in ['group', 'institution']:
933 access = acc['name'].lower()
934
935 docinfo['accessType'] = access
936
937 except:
938 pass
939
940 return docinfo
941
942 def getDocinfoFromDigilib(self, docinfo, path):
943 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
944 # fetch data
945 txt = getHttpData(infoUrl)
946 if not txt:
947 logging.error("Unable to get dir-info from %s"%(infoUrl))
948 return docinfo
949
950 dom = ET.fromstring(txt)
951 size = getText(dom.find("size"))
952 logging.debug("getDocinfoFromDigilib: size=%s"%size)
953 if size:
954 docinfo['numPages'] = int(size)
955 else:
956 docinfo['numPages'] = 0
957
958 # TODO: produce and keep list of image names and numbers
959 return docinfo
960
961
772 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): 962 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
773 """returns pageinfo with the given parameters""" 963 """returns pageinfo with the given parameters"""
774 pageinfo = {} 964 pageinfo = {}
775 current = getInt(current) 965 current = getInt(current)
776 966