Mercurial > hg > documentViewer

comparison documentViewer.py @ 587:6000c7e24d8a

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
new parameter "pf" to specify image file name. (still some issues)
author casties
date Thu, 15 Nov 2012 17:09:45 +0100
parents 83eeed69793f
children d8d6975cebcb
comparison
equal deleted inserted replaced
586:230ba358da3c 587:6000c7e24d8a
44 """returns pathname shortened by cnt""" 44 """returns pathname shortened by cnt"""
45 # make sure path doesn't end with / 45 # make sure path doesn't end with /
46 path = path.rstrip('/') 46 path = path.rstrip('/')
47 # split by /, shorten, and reassemble 47 # split by /, shorten, and reassemble
48 return '/'.join(path.split('/')[0:-cnt]) 48 return '/'.join(path.split('/')[0:-cnt])
49
50 def getPnForPf(docinfo, pf):
51 """returns image number for image file name or 0"""
52 if 'imgFileNames' in docinfo:
53 pn = docinfo['imgFileNames'].get(pf, None)
54 if pn is None:
55 # try to cut extension
56 xi = pf.rfind('.')
57 if xi > 0:
58 pf = pf[:xi]
59 # try again, else return 0
60 pn = docinfo['imgFileNames'].get(pf, 0)
61
62 return pn
63
64 return 0
49 65
50 66
51 ## 67 ##
52 ## documentViewer class 68 ## documentViewer class
53 ## 69 ##
202 if not self.digilibBaseUrl: 218 if not self.digilibBaseUrl:
203 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" 219 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
204 220
205 docinfo = self.getDocinfo(mode=mode,url=url) 221 docinfo = self.getDocinfo(mode=mode,url=url)
206 #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) 222 #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
207 pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo) 223 pageinfo = self.getPageinfo(start=start,pn=pn, docinfo=docinfo)
208 ''' ZDES ''' 224 ''' ZDES '''
209 pt = getattr(self.template, 'thumbs_main_rss') 225 pt = getattr(self.template, 'thumbs_main_rss')
210 226
211 if viewMode=="auto": # automodus gewaehlt 227 if viewMode=="auto": # automodus gewaehlt
212 if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert 228 if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
216 232
217 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) 233 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
218 234
219 235
220 security.declareProtected('View','index_html') 236 security.declareProtected('View','index_html')
221 def index_html(self,url,mode="texttool",viewMode="auto",viewLayer=None,tocMode=None,start=1,pn=1): 237 def index_html(self,url,mode="texttool",viewMode="auto",viewLayer=None,tocMode=None,start=None,pn=None,pf=None):
222 """ 238 """
223 show page 239 show page
224 @param url: url which contains display information 240 @param url: url which contains display information
225 @param mode: defines how to access the document behind url 241 @param mode: defines how to access the document behind url
226 @param viewMode: 'images': display images, 'text': display text, 'xml': display xml, default is 'auto' 242 @param viewMode: 'images': display images, 'text': display text, 'xml': display xml, default is 'auto'
227 @param viewLayer: sub-type of viewMode, e.g. layer 'dict' for viewMode='text' 243 @param viewLayer: sub-type of viewMode, e.g. layer 'dict' for viewMode='text'
228 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) 244 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
229 """ 245 """
230 246
231 logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewLayer=%s start=%s pn=%s"%(mode,url,viewMode,viewLayer,start,pn)) 247 logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewLayer=%s start=%s pn=%s pf=%s"%(mode,url,viewMode,viewLayer,start,pn,pf))
232 248
233 if not hasattr(self, 'template'): 249 if not hasattr(self, 'template'):
234 # this won't work 250 # this won't work
235 logging.error("template folder missing!") 251 logging.error("template folder missing!")
236 return "ERROR: template folder missing!" 252 return "ERROR: template folder missing!"
269 285
270 # safe viewLayer in userinfo 286 # safe viewLayer in userinfo
271 userinfo['viewLayer'] = viewLayer 287 userinfo['viewLayer'] = viewLayer
272 288
273 # pageinfo: information about page (not cached) 289 # pageinfo: information about page (not cached)
274 pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, userinfo=userinfo, viewMode=viewMode, viewLayer=viewLayer, tocMode=tocMode) 290 pageinfo = self.getPageinfo(start=start, pn=pn, pf=pf, docinfo=docinfo, userinfo=userinfo, viewMode=viewMode, viewLayer=viewLayer, tocMode=tocMode)
275 291
276 # get template /template/viewer_$viewMode 292 # get template /template/viewer_$viewMode
277 pt = getattr(self.template, 'viewer_%s'%viewMode, None) 293 pt = getattr(self.template, 'viewer_%s'%viewMode, None)
278 if pt is None: 294 if pt is None:
279 logging.error("No template for viewMode=%s!"%viewMode) 295 logging.error("No template for viewMode=%s!"%viewMode)
449 return (user is not None) 465 return (user is not None)
450 466
451 logging.error("documentViewer (accessOK) unknown access type %s"%access) 467 logging.error("documentViewer (accessOK) unknown access type %s"%access)
452 return False 468 return False
453 469
454
455 def getUserinfo(self): 470 def getUserinfo(self):
456 """returns userinfo object""" 471 """returns userinfo object"""
457 logging.debug("getUserinfo") 472 logging.debug("getUserinfo")
458 userinfo = {} 473 userinfo = {}
459 # look for cached userinfo in session 474 # look for cached userinfo in session
731 pass 746 pass
732 747
733 return docinfo 748 return docinfo
734 749
735 def getDocinfoFromDigilib(self, docinfo, path): 750 def getDocinfoFromDigilib(self, docinfo, path):
736 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path 751 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?fn="+path
737 # fetch data 752 # fetch data
738 txt = getHttpData(infoUrl) 753 txt = getHttpData(infoUrl)
739 if not txt: 754 if not txt:
740 logging.error("Unable to get dir-info from %s"%(infoUrl)) 755 logging.error("Unable to get dir-info from %s"%(infoUrl))
741 return docinfo 756 return docinfo
742 757
743 dom = ET.fromstring(txt) 758 dom = ET.fromstring(txt)
744 size = getText(dom.find("size")) 759 dir = dom
760 # save size
761 size = dir.findtext('size')
745 logging.debug("getDocinfoFromDigilib: size=%s"%size) 762 logging.debug("getDocinfoFromDigilib: size=%s"%size)
746 if size: 763 if size:
747 docinfo['numPages'] = int(size) 764 docinfo['numPages'] = int(size)
748 else: 765 else:
749 docinfo['numPages'] = 0 766 docinfo['numPages'] = 0
750 767 return docinfo
751 # TODO: produce and keep list of image names and numbers 768
769 # save list of image names and numbers
770 imgNames = {}
771 for f in dir:
772 fn = f.findtext('name')
773 pn = f.findtext('index')
774 imgNames[fn] = getInt(pn)
775
776 docinfo['imgFileNames'] = imgNames
752 return docinfo 777 return docinfo
753 778
754 779
755 def getDocinfoFromPresentationInfoXml(self,docinfo): 780 def getDocinfoFromPresentationInfoXml(self,docinfo):
756 """gets DC-like bibliographical information from the presentation entry in texttools""" 781 """gets DC-like bibliographical information from the presentation entry in texttools"""
764 if url.startswith("http://"): 789 if url.startswith("http://"):
765 # real URL 790 # real URL
766 metaUrl = url 791 metaUrl = url
767 else: 792 else:
768 # online path 793 # online path
769
770 server=self.digilibBaseUrl+"/servlet/Texter?fn=" 794 server=self.digilibBaseUrl+"/servlet/Texter?fn="
771 metaUrl=server+url 795 metaUrl=server+url
772 796
773 txt=getHttpData(metaUrl) 797 txt=getHttpData(metaUrl)
774 if txt is None: 798 if txt is None:
780 docinfo['title']=getText(dom.find(".//title")) 804 docinfo['title']=getText(dom.find(".//title"))
781 docinfo['date']=getText(dom.find(".//date")) 805 docinfo['date']=getText(dom.find(".//date"))
782 return docinfo 806 return docinfo
783 807
784 808
785 def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, userinfo=None, viewMode=None, viewLayer=None, tocMode=None): 809 def getPageinfo(self, pn=None, pf=None, start=None, rows=None, cols=None, docinfo=None, userinfo=None, viewMode=None, viewLayer=None, tocMode=None):
786 """returns pageinfo with the given parameters""" 810 """returns pageinfo with the given parameters"""
787 logging.debug("getPageInfo(current=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewLayer=%s, tocMode=%s)"%(current,start,rows,cols,viewMode,viewLayer,tocMode)) 811 logging.debug("getPageInfo(pn=%s, pf=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewLayer=%s, tocMode=%s)"%(pn,pf,start,rows,cols,viewMode,viewLayer,tocMode))
788 pageinfo = {} 812 pageinfo = {}
789 pageinfo['viewMode'] = viewMode 813 pageinfo['viewMode'] = viewMode
790 # split viewLayer if necessary 814 # split viewLayer if necessary
791 if isinstance(viewLayer,basestring): 815 if isinstance(viewLayer,basestring):
792 viewLayer = viewLayer.split(',') 816 viewLayer = viewLayer.split(',')
805 829
806 pageinfo['viewLayer'] = viewLayer 830 pageinfo['viewLayer'] = viewLayer
807 pageinfo['tocMode'] = tocMode 831 pageinfo['tocMode'] = tocMode
808 832
809 # TODO: unify current and pn! 833 # TODO: unify current and pn!
810 current = getInt(current) 834 #pageinfo['current'] = current
811 pageinfo['current'] = current 835 # pf takes precedence over pn
812 pageinfo['pn'] = current 836 if pf:
837 pageinfo['pf'] = pf
838 pn = getPnForPf(docinfo, pf)
839 else:
840 pn = getInt(pn, 1)
841
842 pageinfo['pn'] = pn
813 rows = int(rows or self.thumbrows) 843 rows = int(rows or self.thumbrows)
814 pageinfo['rows'] = rows 844 pageinfo['rows'] = rows
815 cols = int(cols or self.thumbcols) 845 cols = int(cols or self.thumbcols)
816 pageinfo['cols'] = cols 846 pageinfo['cols'] = cols
817 grpsize = cols * rows 847 grpsize = cols * rows
818 pageinfo['groupsize'] = grpsize 848 pageinfo['groupsize'] = grpsize
819 # is start is empty use one around current 849 # is start is empty use one around pn
820 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) 850 start = getInt(start, default=(math.ceil(float(pn)/float(grpsize))*grpsize-(grpsize-1)))
821 # int(current / grpsize) * grpsize +1)) 851 # int(current / grpsize) * grpsize +1))
822 pageinfo['start'] = start 852 pageinfo['start'] = start
823 # get number of pages 853 # get number of pages
824 np = int(docinfo.get('numPages', 0)) 854 np = int(docinfo.get('numPages', 0))
825 if np == 0: 855 if np == 0:
842 pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np) 872 pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np)
843 # more page parameters 873 # more page parameters
844 pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') 874 pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
845 if docinfo.get('pageNumbers'): 875 if docinfo.get('pageNumbers'):
846 # get original page numbers 876 # get original page numbers
847 pageNumber = docinfo['pageNumbers'].get(current, None) 877 pageNumber = docinfo['pageNumbers'].get(pn, None)
848 if pageNumber is not None: 878 if pageNumber is not None:
849 pageinfo['pageNumberOrig'] = pageNumber['no'] 879 pageinfo['pageNumberOrig'] = pageNumber['no']
850 pageinfo['pageNumberOrigNorm'] = pageNumber['non'] 880 pageinfo['pageNumberOrigNorm'] = pageNumber['non']
851 881
852 # cache search results 882 # cache search results