Mercurial > hg > documentViewer

comparison documentViewer.py @ 463:89ad327b4bbd elementtree

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
more renovation
author casties
date Thu, 28 Jul 2011 15:00:07 +0200
parents 0d378e8ebcc3
children 19bd41d95f62
comparison
equal deleted inserted replaced
462:0d378e8ebcc3 463:89ad327b4bbd
100 100
101 def getParentDir(path): 101 def getParentDir(path):
102 """returns pathname shortened by one""" 102 """returns pathname shortened by one"""
103 return '/'.join(path.split('/')[0:-1]) 103 return '/'.join(path.split('/')[0:-1])
104 104
105 def normalizeBibField(bt, underscore=True):
106 """returns normalised bib type for looking up mappings"""
107 bt = bt.strip().replace(' ', '-').lower()
108 if underscore:
109 bt = bt.replace('_', '-')
110
111 return bt
112
113 def getBibdataFromDom(dom):
114 """returns dict with all elements from bib-tag"""
115 bibinfo = {}
116 bib = dom.find(".//meta/bib")
117 if bib is not None:
118 # put type in @type
119 type = bib.get('type')
120 bibinfo['@type'] = normalizeBibField(type)
121 # put all subelements in dict
122 for e in bib:
123 bibinfo[normalizeBibField(e.tag)] = getText(e)
124
125 return bibinfo
126
127 105
128 ## 106 ##
129 ## documentViewer class 107 ## documentViewer class
130 ## 108 ##
131 class documentViewer(Folder): 109 class documentViewer(Folder):
134 112
135 security=ClassSecurityInfo() 113 security=ClassSecurityInfo()
136 manage_options=Folder.manage_options+( 114 manage_options=Folder.manage_options+(
137 {'label':'main config','action':'changeDocumentViewerForm'}, 115 {'label':'main config','action':'changeDocumentViewerForm'},
138 ) 116 )
117
118 metadataService = None
119 """MetaDataFolder instance"""
139 120
140 # templates and forms 121 # templates and forms
141 viewer_main = PageTemplateFile('zpt/viewer_main', globals()) 122 viewer_main = PageTemplateFile('zpt/viewer_main', globals())
142 toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals()) 123 toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
143 toc_text = PageTemplateFile('zpt/toc_text', globals()) 124 toc_text = PageTemplateFile('zpt/toc_text', globals())
153 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) 134 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
154 info_xml = PageTemplateFile('zpt/info_xml', globals()) 135 info_xml = PageTemplateFile('zpt/info_xml', globals())
155 136
156 137
157 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) 138 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
158 security.declareProtected('View management screens','changeDocumentViewerForm')
159 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
160 139
161 140
162 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): 141 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
163 """init document viewer""" 142 """init document viewer"""
164 self.id=id 143 self.id=id
177 textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) 156 textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
178 #templateFolder['fulltextclient'] = xmlRpcClient 157 #templateFolder['fulltextclient'] = xmlRpcClient
179 templateFolder._setObject('fulltextclient',textServer) 158 templateFolder._setObject('fulltextclient',textServer)
180 except Exception, e: 159 except Exception, e:
181 logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) 160 logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
161
182 try: 162 try:
183 from Products.zogiLib.zogiLib import zogiLib 163 from Products.zogiLib.zogiLib import zogiLib
184 zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") 164 zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
185 #templateFolder['zogilib'] = zogilib 165 #templateFolder['zogilib'] = zogilib
186 templateFolder._setObject('zogilib',zogilib) 166 templateFolder._setObject('zogilib',zogilib)
187 except Exception, e: 167 except Exception, e:
188 logging.error("Unable to create zogiLib for zogilib: "+str(e)) 168 logging.error("Unable to create zogiLib for zogilib: "+str(e))
189 169
170 try:
171 # assume MetaDataFolder instance is called metadata
172 self.metadataService = getattr(self, 'metadata')
173 except Exception, e:
174 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
175
190 176
191 # proxy text server methods to fulltextclient 177 # proxy text server methods to fulltextclient
192 def getTextPage(self, **args): 178 def getTextPage(self, **args):
193 """get page""" 179 """get page"""
194 return self.template.fulltextclient.getTextPage(**args) 180 return self.template.fulltextclient.getTextPage(**args)
579 dom = self.getDomFromIndexMeta(path) 565 dom = self.getDomFromIndexMeta(path)
580 566
581 docinfo['indexMetaPath']=self.getIndexMetaPath(path); 567 docinfo['indexMetaPath']=self.getIndexMetaPath(path);
582 568
583 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) 569 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
584 # try to get MetaDataFolder 570 if self.metadataService is not None:
585 metadata = getattr(self, 'metadata')
586 if metadata is not None:
587 # put all raw bib fields in dict "bib" 571 # put all raw bib fields in dict "bib"
588 bib = metadata.getBibdataFromDom(dom) 572 bib = self.metadataService.getBibData(dom=dom)
589 docinfo['bib'] = bib 573 docinfo['bib'] = bib
590 bibtype = bib.get('@type', None) 574 bibtype = bib.get('@type', None)
591 docinfo['bib_type'] = bibtype 575 docinfo['bib_type'] = bibtype
592 # also store DC metadata for convenience 576 # also store DC metadata for convenience
593 dc = metadata.getDCMappedData(bib) 577 dc = self.metadataService.getDCMappedData(bib)
594 docinfo['creator'] = dc.get('creator',None) 578 docinfo['creator'] = dc.get('creator',None)
595 docinfo['title'] = dc.get('title',None) 579 docinfo['title'] = dc.get('title',None)
596 docinfo['date'] = dc.get('date',None) 580 docinfo['date'] = dc.get('date',None)
597 else: 581 else:
598 logging.error("MetaDataFolder 'metadata' not found!") 582 logging.error("MetadataService not found!")
599 #TODO: remove
600 bib = getBibdataFromDom(dom)
601 return docinfo 583 return docinfo
602 584
603 585
604 # TODO: is this needed? 586 # TODO: is this needed?
605 def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): 587 def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
613 dom = self.getDomFromIndexMeta(path) 595 dom = self.getDomFromIndexMeta(path)
614 596
615 docinfo['name']=getText(dom.find("name")) 597 docinfo['name']=getText(dom.find("name"))
616 logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) 598 logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
617 return docinfo 599 return docinfo
600
618 601
619 def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): 602 def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
620 """parse texttool tag in index meta""" 603 """parse texttool tag in index meta"""
621 logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url)) 604 logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
622 if docinfo is None: 605 if docinfo is None:
623 docinfo = {} 606 docinfo = {}
624 if docinfo.get('lang', None) is None: 607 if docinfo.get('lang', None) is None:
625 docinfo['lang'] = '' # default keine Sprache gesetzt 608 docinfo['lang'] = '' # default keine Sprache gesetzt
626 if dom is None: 609 if dom is None:
627 dom = self.getDomFromIndexMeta(url) 610 dom = self.getDomFromIndexMeta(url)
611
612 texttool = self.metadata.getTexttoolData(dom=dom)
628 613
629 archivePath = None 614 archivePath = None
630 archiveName = None 615 archiveName = None
631 616
632 archiveName = getText(dom.find("name")) 617 archiveName = getText(dom.find("name"))
648 633
649 if archivePath is None: 634 if archivePath is None:
650 # we balk without archive-path 635 # we balk without archive-path
651 raise IOError("Missing archive-path (for text-tool) in %s" % (url)) 636 raise IOError("Missing archive-path (for text-tool) in %s" % (url))
652 637
653 imageDir = getText(dom.find(".//texttool/image")) 638 imageDir = texttool.get('image', None)
654 639
655 if not imageDir: 640 if not imageDir:
656 # we balk with no image tag / not necessary anymore because textmode is now standard 641 # we balk with no image tag / not necessary anymore because textmode is now standard
657 #raise IOError("No text-tool info in %s"%(url)) 642 #raise IOError("No text-tool info in %s"%(url))
658 imageDir = "" 643 imageDir = ""
667 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) 652 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
668 docinfo['imagePath'] = imageDir 653 docinfo['imagePath'] = imageDir
669 654
670 docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir 655 docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
671 656
672 viewerUrl = getText(dom.find(".//texttool/digiliburlprefix")) 657 viewerUrl = texttool.get('digiliburlprefix', None)
673 if viewerUrl: 658 if viewerUrl:
674 docinfo['viewerURL'] = viewerUrl 659 docinfo['viewerURL'] = viewerUrl
675 660
676 # old style text URL 661 # old style text URL
677 textUrl = getText(dom.find(".//texttool/text")) 662 textUrl = texttool.get('text', None)
678 if textUrl: 663 if textUrl:
679 if urlparse.urlparse(textUrl)[0] == "": #keine url 664 if urlparse.urlparse(textUrl)[0] == "": #keine url
680 textUrl = os.path.join(archivePath, textUrl) 665 textUrl = os.path.join(archivePath, textUrl)
681 # fix URLs starting with /mpiwg/online 666 # fix URLs starting with /mpiwg/online
682 if textUrl.startswith("/mpiwg/online"): 667 if textUrl.startswith("/mpiwg/online"):
683 textUrl = textUrl.replace("/mpiwg/online", '', 1) 668 textUrl = textUrl.replace("/mpiwg/online", '', 1)
684 669
685 docinfo['textURL'] = textUrl 670 docinfo['textURL'] = textUrl
686 671
687 # new style text-url-path 672 # new style text-url-path
688 textUrl = getText(dom.find(".//texttool/text-url-path")) 673 textUrl = texttool.get('text-url-path', None)
689 if textUrl: 674 if textUrl:
690 docinfo['textURLPath'] = textUrl 675 docinfo['textURLPath'] = textUrl
691 textUrlkurz = string.split(textUrl, ".")[0] 676 textUrlkurz = string.split(textUrl, ".")[0]
692 docinfo['textURLPathkurz'] = textUrlkurz 677 docinfo['textURLPathkurz'] = textUrlkurz
693 #if not docinfo['imagePath']: 678 #if not docinfo['imagePath']:
694 # text-only, no page images 679 # text-only, no page images
695 #docinfo = self.getNumTextPages(docinfo) 680 #docinfo = self.getNumTextPages(docinfo)
696 681
697 682 # get bib info
698 presentationUrl = getText(dom.find(".//texttool/presentation"))
699 docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag 683 docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
700 # TODO: is this needed here? 684 # TODO: is this needed here?
701 docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) 685 docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
702 686
703 687 # TODO: what to do with presentation?
688 presentationUrl = texttool.get('presentation', None)
704 if presentationUrl: # ueberschreibe diese durch presentation informationen 689 if presentationUrl: # ueberschreibe diese durch presentation informationen
705 # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten 690 # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
706 # durch den relativen Pfad auf die presentation infos 691 # durch den relativen Pfad auf die presentation infos
707 presentationPath = presentationUrl 692 presentationPath = presentationUrl
708 if url.endswith("index.meta"): 693 if url.endswith("index.meta"):
710 else: 695 else:
711 presentationUrl = url + "/" + presentationPath 696 presentationUrl = url + "/" + presentationPath
712 697
713 docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom) 698 docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
714 699
700 # get authorization
715 docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info 701 docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
716 702
717 return docinfo 703 return docinfo
718 704
719 705
837 823
838 pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') 824 pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
839 pageinfo['sn'] =self.REQUEST.get('sn','') 825 pageinfo['sn'] =self.REQUEST.get('sn','')
840 return pageinfo 826 return pageinfo
841 827
828
829 security.declareProtected('View management screens','changeDocumentViewerForm')
830 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
842 831
843 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): 832 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
844 """init document viewer""" 833 """init document viewer"""
845 self.title=title 834 self.title=title
846 self.digilibBaseUrl = digilibBaseUrl 835 self.digilibBaseUrl = digilibBaseUrl
847 self.thumbrows = thumbrows 836 self.thumbrows = thumbrows
848 self.thumbcols = thumbcols 837 self.thumbcols = thumbcols
849 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] 838 self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
839 try:
840 # assume MetaDataFolder instance is called metadata
841 self.metadataService = getattr(self, 'metadata')
842 except Exception, e:
843 logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
844
850 if RESPONSE is not None: 845 if RESPONSE is not None:
851 RESPONSE.redirect('manage_main') 846 RESPONSE.redirect('manage_main')
852 847
853 def manage_AddDocumentViewerForm(self): 848 def manage_AddDocumentViewerForm(self):
854 """add the viewer form""" 849 """add the viewer form"""