1:
2:
3: from OFS.Folder import Folder
4: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
5: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
6: from AccessControl import ClassSecurityInfo
7: from AccessControl import getSecurityManager
8: from Globals import package_home
9:
10: from Ft.Xml.Domlette import NonvalidatingReader
11: from Ft.Xml.Domlette import PrettyPrint, Print
12: from Ft.Xml import EMPTY_NAMESPACE, Parse
13:
14: import Ft.Xml.XPath
15:
16: import os.path
17: import sys
18: import cgi
19: import urllib
20: import logging
21: import math
22:
23: import urlparse
24: from types import *
25: def logger(txt,method,txt2):
26: """logging"""
27: logging.info(txt+ txt2)
28:
29:
30: def getInt(number, default=0):
31: """returns always an int (0 in case of problems)"""
32: try:
33: return int(number)
34: except:
35: return int(default)
36:
37: def getTextFromNode(nodename):
38: """get the cdata content of a node"""
39: if nodename is None:
40: return ""
41: nodelist=nodename.childNodes
42: rc = ""
43: for node in nodelist:
44: if node.nodeType == node.TEXT_NODE:
45: rc = rc + node.data
46: return rc
47:
48:
49: def getParentDir(path):
50: """returns pathname shortened by one"""
51: return '/'.join(path.split('/')[0:-1])
52:
53:
54: import socket
55:
56: def urlopen(url,timeout=2):
57: """urlopen mit timeout"""
58: socket.setdefaulttimeout(timeout)
59: ret=urllib.urlopen(url)
60: socket.setdefaulttimeout(5)
61: return ret
62:
63:
64: ##
65: ## documentViewer class
66: ##
67: class documentViewer(Folder):
68: """document viewer"""
69: #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"
70:
71: meta_type="Document viewer"
72:
73: security=ClassSecurityInfo()
74: manage_options=Folder.manage_options+(
75: {'label':'main config','action':'changeDocumentViewerForm'},
76: )
77:
78: # templates and forms
79: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
80: thumbs_main = PageTemplateFile('zpt/thumbs_main', globals())
81: image_main = PageTemplateFile('zpt/image_main', globals())
82: head_main = PageTemplateFile('zpt/head_main', globals())
83: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
84: info_xml = PageTemplateFile('zpt/info_xml', globals())
85:
86: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
87: security.declareProtected('View management screens','changeDocumentViewerForm')
88: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
89:
90:
91: def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):
92: """init document viewer"""
93: self.id=id
94: self.title=title
95: self.imageViewerUrl=imageViewerUrl
96: self.textViewerUrl=textViewerUrl
97:
98: if not digilibBaseUrl:
99: self.digilibBaseUrl = self.findDigilibUrl()
100: else:
101: self.digilibBaseUrl = digilibBaseUrl
102: self.thumbcols = thumbcols
103: self.thumbrows = thumbrows
104: # authgroups is list of authorized groups (delimited by ,)
105: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
106: # add template folder so we can always use template.something
107: self.manage_addFolder('template')
108:
109:
110: security.declareProtected('View','thumbs_rss')
111: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
112: '''
113: view it
114: @param mode: defines how to access the document behind url
115: @param url: url which contains display information
116: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
117:
118: '''
119: logging.info("HHHHHHHHHHHHHH:load the rss")
120: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
121:
122: if not hasattr(self, 'template'):
123: # create template folder if it doesn't exist
124: self.manage_addFolder('template')
125:
126: if not self.digilibBaseUrl:
127: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
128:
129: docinfo = self.getDocinfo(mode=mode,url=url)
130: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
131: pt = getattr(self.template, 'thumbs_main_rss')
132:
133: if viewMode=="auto": # automodus gewaehlt
134: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
135: viewMode="text"
136: else:
137: viewMode="images"
138:
139: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
140:
141: security.declareProtected('View','index_html')
142: def index_html(self,mode,url,viewMode="auto",start=None,pn=1,mk=None):
143: '''
144: view it
145: @param mode: defines how to access the document behind url
146: @param url: url which contains display information
147: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
148:
149: '''
150:
151: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
152:
153: if not hasattr(self, 'template'):
154: # create template folder if it doesn't exist
155: self.manage_addFolder('template')
156:
157: if not self.digilibBaseUrl:
158: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
159:
160: docinfo = self.getDocinfo(mode=mode,url=url)
161: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
162: pt = getattr(self.template, 'viewer_main')
163:
164: if viewMode=="auto": # automodus gewaehlt
165: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
166: viewMode="text"
167: else:
168: viewMode="images"
169:
170: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
171:
172: def generateMarks(self,mk):
173: ret=""
174: if mk is None:
175: return ""
176:
177: if type(mk) is not ListType:
178: mk=[mk]
179: for m in mk:
180: ret+="mk=%s"%m
181: return ret
182:
183: def getLink(self,param=None,val=None):
184: """link to documentviewer with parameter param set to val"""
185: params=self.REQUEST.form.copy()
186: if param is not None:
187: if val is None:
188: if params.has_key(param):
189: del params[param]
190: else:
191: params[param] = str(val)
192: if params["mode"] == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
193: params["mode"] = "imagepath"
194: params["url"] = getParentDir(params["url"])
195:
196: # quote values and assemble into query string
197: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
198: url=self.REQUEST['URL1']+"?"+ps
199: return url
200:
201: def getLinkAmp(self,param=None,val=None):
202: """link to documentviewer with parameter param set to val"""
203: params=self.REQUEST.form.copy()
204: if param is not None:
205: if val is None:
206: if params.has_key(param):
207: del params[param]
208: else:
209: params[param] = str(val)
210:
211: # quote values and assemble into query string
212: logging.info("XYXXXXX: %s"%repr(params.items()))
213: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
214: url=self.REQUEST['URL1']+"?"+ps
215: return url
216:
217: def getInfo_xml(self,url,mode):
218: """returns info about the document as XML"""
219:
220: if not self.digilibBaseUrl:
221: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
222:
223: docinfo = self.getDocinfo(mode=mode,url=url)
224: pt = getattr(self.template, 'info_xml')
225: return pt(docinfo=docinfo)
226:
227:
228: def getStyle(self, idx, selected, style=""):
229: """returns a string with the given style and append 'sel' if path == selected."""
230: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
231: if idx == selected:
232: return style + 'sel'
233: else:
234: return style
235:
236:
237: def isAccessible(self, docinfo):
238: """returns if access to the resource is granted"""
239: access = docinfo.get('accessType', None)
240: logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
241: if access is not None and access == 'free':
242: logger("documentViewer (accessOK)", logging.INFO, "access is free")
243: return True
244: elif access is None or access in self.authgroups:
245: # only local access -- only logged in users
246: user = getSecurityManager().getUser()
247: if user is not None:
248: #print "user: ", user
249: return (user.getUserName() != "Anonymous User")
250: else:
251: return False
252:
253: logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
254: return False
255:
256:
257: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
258: """gibt param von dlInfo aus"""
259: num_retries = 3
260: if docinfo is None:
261: docinfo = {}
262:
263: for x in range(cut):
264:
265: path=getParentDir(path)
266:
267: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
268:
269: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
270:
271: for cnt in range(num_retries):
272: try:
273: # dom = NonvalidatingReader.parseUri(imageUrl)
274: txt=urllib.urlopen(infoUrl).read()
275: dom = Parse(txt)
276: break
277: except:
278: logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
279: else:
280: raise IOError("Unable to get dir-info from %s"%(infoUrl))
281:
282: sizes=dom.xpath("//dir/size")
283: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
284:
285: if sizes:
286: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
287: else:
288: docinfo['numPages'] = 0
289:
290: return docinfo
291:
292:
293: def getIndexMeta(self, url):
294: """returns dom of index.meta document at url"""
295: num_retries = 3
296: dom = None
297: metaUrl = None
298: if url.startswith("http://"):
299: # real URL
300: metaUrl = url
301: else:
302: # online path
303: server=self.digilibBaseUrl+"/servlet/Texter?fn="
304: metaUrl=server+url.replace("/mpiwg/online","")
305: if not metaUrl.endswith("index.meta"):
306: metaUrl += "/index.meta"
307: logging.debug("METAURL: %s"%metaUrl)
308: for cnt in range(num_retries):
309: try:
310: # patch dirk encoding fehler treten dann nicht mehr auf
311: # dom = NonvalidatingReader.parseUri(metaUrl)
312: txt=urllib.urlopen(metaUrl).read()
313: dom = Parse(txt)
314: break
315: except:
316: logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
317:
318: if dom is None:
319: raise IOError("Unable to read index meta from %s"%(url))
320:
321: return dom
322:
323: def getPresentationInfoXML(self, url):
324: """returns dom of info.xml document at url"""
325: num_retries = 3
326: dom = None
327: metaUrl = None
328: if url.startswith("http://"):
329: # real URL
330: metaUrl = url
331: else:
332: # online path
333: server=self.digilibBaseUrl+"/servlet/Texter?fn="
334: metaUrl=server+url.replace("/mpiwg/online","")
335:
336:
337: for cnt in range(num_retries):
338: try:
339: # patch dirk encoding fehler treten dann nicht mehr auf
340: # dom = NonvalidatingReader.parseUri(metaUrl)
341: txt=urllib.urlopen(metaUrl).read()
342: dom = Parse(txt)
343: break
344: except:
345: logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
346:
347: if dom is None:
348: raise IOError("Unable to read infoXMLfrom %s"%(url))
349:
350: return dom
351:
352:
353: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
354: """gets authorization info from the index.meta file at path or given by dom"""
355: logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
356:
357: access = None
358:
359: if docinfo is None:
360: docinfo = {}
361:
362: if dom is None:
363: for x in range(cut):
364: path=getParentDir(path)
365: dom = self.getIndexMeta(path)
366:
367: acctype = dom.xpath("//access-conditions/access/@type")
368: if acctype and (len(acctype)>0):
369: access=acctype[0].value
370: if access in ['group', 'institution']:
371: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
372:
373: docinfo['accessType'] = access
374: return docinfo
375:
376:
377: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
378: """gets bibliographical info from the index.meta file at path or given by dom"""
379: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
380:
381: if docinfo is None:
382: docinfo = {}
383:
384: if dom is None:
385: for x in range(cut):
386: path=getParentDir(path)
387: dom = self.getIndexMeta(path)
388:
389: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
390: # put in all raw bib fields as dict "bib"
391: bib = dom.xpath("//bib/*")
392: if bib and len(bib)>0:
393: bibinfo = {}
394: for e in bib:
395: bibinfo[e.localName] = getTextFromNode(e)
396: docinfo['bib'] = bibinfo
397:
398: # extract some fields (author, title, year) according to their mapping
399: metaData=self.metadata.main.meta.bib
400: bibtype=dom.xpath("//bib/@type")
401: if bibtype and (len(bibtype)>0):
402: bibtype=bibtype[0].value
403: else:
404: bibtype="generic"
405:
406: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
407: docinfo['bib_type'] = bibtype
408: bibmap=metaData.generateMappingForType(bibtype)
409: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
410: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
411: try:
412: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
413: except: pass
414: try:
415: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
416: except: pass
417: try:
418: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
419: except: pass
420: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
421: try:
422: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
423: except:
424: docinfo['lang']=''
425:
426: return docinfo
427:
428:
429: def getDocinfoFromTextTool(self,url,dom=None,docinfo=None):
430: """parse texttool tag in index meta"""
431: logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url))
432: if docinfo is None:
433: docinfo = {}
434:
435: if docinfo.get('lang',None) is None:
436: docinfo['lang']='' # default keine Sprache gesetzt
437: if dom is None:
438: dom = self.getIndexMeta(url)
439:
440: archivePath = None
441: archiveName = None
442:
443: archiveNames=dom.xpath("//resource/name")
444: if archiveNames and (len(archiveNames)>0):
445: archiveName=getTextFromNode(archiveNames[0])
446: else:
447: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/name missing in: %s"%(url))
448:
449: archivePaths=dom.xpath("//resource/archive-path")
450: if archivePaths and (len(archivePaths)>0):
451: archivePath=getTextFromNode(archivePaths[0])
452: # clean up archive path
453: if archivePath[0] != '/':
454: archivePath = '/' + archivePath
455: if archiveName and (not archivePath.endswith(archiveName)):
456: archivePath += "/" + archiveName
457: else:
458: # try to get archive-path from url
459: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/archive-path missing in: %s"%(url))
460: if (not url.startswith('http')):
461: archivePath = url.replace('index.meta', '')
462:
463: if archivePath is None:
464: # we balk without archive-path
465: raise IOError("Missing archive-path (for text-tool) in %s"%(url))
466:
467: imageDirs=dom.xpath("//texttool/image")
468: if imageDirs and (len(imageDirs)>0):
469: imageDir=getTextFromNode(imageDirs[0])
470: else:
471: # we balk with no image tag / not necessary anymore because textmode is now standard
472: #raise IOError("No text-tool info in %s"%(url))
473: imageDir=""
474: docinfo['numPages']=1 # im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
475:
476: docinfo['imagePath'] = "" # keine Bilder
477: docinfo['imageURL'] = ""
478:
479: if imageDir and archivePath:
480: #print "image: ", imageDir, " archivepath: ", archivePath
481: imageDir=os.path.join(archivePath,imageDir)
482: imageDir=imageDir.replace("/mpiwg/online",'')
483: docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo)
484: docinfo['imagePath'] = imageDir
485:
486: docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir
487:
488: viewerUrls=dom.xpath("//texttool/digiliburlprefix")
489: if viewerUrls and (len(viewerUrls)>0):
490: viewerUrl=getTextFromNode(viewerUrls[0])
491: docinfo['viewerURL'] = viewerUrl
492:
493: textUrls=dom.xpath("//texttool/text")
494: if textUrls and (len(textUrls)>0):
495: textUrl=getTextFromNode(textUrls[0])
496: if urlparse.urlparse(textUrl)[0]=="": #keine url
497: textUrl=os.path.join(archivePath,textUrl)
498: # fix URLs starting with /mpiwg/online
499: if textUrl.startswith("/mpiwg/online"):
500: textUrl = textUrl.replace("/mpiwg/online",'',1)
501:
502: docinfo['textURL'] = textUrl
503:
504: textUrls=dom.xpath("//texttool/text-url-path")
505: if textUrls and (len(textUrls)>0):
506: textUrl=getTextFromNode(textUrls[0])
507:
508: docinfo['textURLPath'] = textUrl
509:
510: presentationUrls=dom.xpath("//texttool/presentation")
511: docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get info von bib tag
512:
513: if presentationUrls and (len(presentationUrls)>0): # ueberschreibe diese durch presentation informationen
514: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
515: # durch den relativen Pfad auf die presentation infos
516: presentationPath = getTextFromNode(presentationUrls[0])
517: if url.endswith("index.meta"):
518: presentationUrl=url.replace('index.meta',presentationPath)
519: else:
520: presentationUrl=url + "/" + presentationPath
521:
522: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom)
523:
524: docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info
525: return docinfo
526:
527:
528: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
529: """gets the bibliographical information from the preseantion entry in texttools
530: """
531: dom=self.getPresentationInfoXML(url)
532: try:
533: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
534: except:
535: pass
536: try:
537: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
538: except:
539: pass
540: try:
541: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
542: except:
543: pass
544: return docinfo
545:
546: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
547: """path ist the path to the images it assumes that the index.meta file is one level higher."""
548: logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))
549: if docinfo is None:
550: docinfo = {}
551: path=path.replace("/mpiwg/online","")
552: docinfo['imagePath'] = path
553: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
554:
555: pathorig=path
556: for x in range(cut):
557: path=getParentDir(path)
558: logging.error("PATH:"+path)
559: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
560: docinfo['imageURL'] = imageUrl
561:
562: #path ist the path to the images it assumes that the index.meta file is one level higher.
563: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
564: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
565: return docinfo
566:
567:
568: def getDocinfo(self, mode, url):
569: """returns docinfo depending on mode"""
570: logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))
571: # look for cached docinfo in session
572: if self.REQUEST.SESSION.has_key('docinfo'):
573: docinfo = self.REQUEST.SESSION['docinfo']
574: # check if its still current
575: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
576: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)
577: return docinfo
578: # new docinfo
579: docinfo = {'mode': mode, 'url': url}
580: if mode=="texttool": #index.meta with texttool information
581: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
582: elif mode=="imagepath":
583: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
584: elif mode=="filepath":
585: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
586: else:
587: logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
588: raise ValueError("Unknown mode %s"%(mode))
589:
590: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
591: self.REQUEST.SESSION['docinfo'] = docinfo
592: return docinfo
593:
594:
595: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None):
596: """returns pageinfo with the given parameters"""
597: pageinfo = {}
598: current = getInt(current)
599: pageinfo['current'] = current
600: rows = int(rows or self.thumbrows)
601: pageinfo['rows'] = rows
602: cols = int(cols or self.thumbcols)
603: pageinfo['cols'] = cols
604: grpsize = cols * rows
605: pageinfo['groupsize'] = grpsize
606: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
607: # int(current / grpsize) * grpsize +1))
608: pageinfo['start'] = start
609: pageinfo['end'] = start + grpsize
610: if docinfo is not None:
611: np = int(docinfo['numPages'])
612: pageinfo['end'] = min(pageinfo['end'], np)
613: pageinfo['numgroups'] = int(np / grpsize)
614: if np % grpsize > 0:
615: pageinfo['numgroups'] += 1
616:
617: return pageinfo
618:
619: def text(self,mode,url,pn):
620: """give text"""
621: if mode=="texttool": #index.meta with texttool information
622: (viewerUrl,imagepath,textpath)=parseUrlTextTool(url)
623:
624: #print textpath
625: try:
626: dom = NonvalidatingReader.parseUri(textpath)
627: except:
628: return None
629:
630: list=[]
631: nodes=dom.xpath("//pb")
632:
633: node=nodes[int(pn)-1]
634:
635: p=node
636:
637: while p.tagName!="p":
638: p=p.parentNode
639:
640:
641: endNode=nodes[int(pn)]
642:
643:
644: e=endNode
645:
646: while e.tagName!="p":
647: e=e.parentNode
648:
649:
650: next=node.parentNode
651:
652: #sammle s
653: while next and (next!=endNode.parentNode):
654: list.append(next)
655: next=next.nextSibling
656: list.append(endNode.parentNode)
657:
658: if p==e:# beide im selben paragraphen
659: pass
660: # else:
661: # next=p
662: # while next!=e:
663: # print next,e
664: # list.append(next)
665: # next=next.nextSibling
666: #
667: # for x in list:
668: # PrettyPrint(x)
669: #
670: # return list
671: #
672:
673: def findDigilibUrl(self):
674: """try to get the digilib URL from zogilib"""
675: url = self.imageViewerUrl[:-1] + "/getScalerUrl"
676: #print urlparse.urlparse(url)[0]
677: #print urlparse.urljoin(self.absolute_url(),url)
678: logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0])
679: logging.info("finddigiliburl: %s"%urlparse.urljoin(self.absolute_url(),url))
680:
681: try:
682: if urlparse.urlparse(url)[0]=='': #relative path
683: url=urlparse.urljoin(self.absolute_url()+"/",url)
684:
685: scaler = urlopen(url).read()
686: return scaler.replace("/servlet/Scaler?", "")
687: except:
688: return None
689:
690: def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):
691: """init document viewer"""
692: self.title=title
693: self.imageViewerUrl=imageViewerUrl
694: self.textViewerUrl=textViewerUrl
695: self.digilibBaseUrl = digilibBaseUrl
696: self.thumbrows = thumbrows
697: self.thumbcols = thumbcols
698: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
699: if RESPONSE is not None:
700: RESPONSE.redirect('manage_main')
701:
702:
703:
704:
705: # security.declareProtected('View management screens','renameImageForm')
706:
707: def manage_AddDocumentViewerForm(self):
708: """add the viewer form"""
709: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
710: return pt()
711:
712: def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None):
713: """add the viewer"""
714: newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl)
715: self._setObject(id,newObj)
716:
717: if RESPONSE is not None:
718: RESPONSE.redirect('manage_main')
719:
720:
721: ##
722: ## DocumentViewerTemplate class
723: ##
724: class DocumentViewerTemplate(ZopePageTemplate):
725: """Template for document viewer"""
726: meta_type="DocumentViewer Template"
727:
728:
729: def manage_addDocumentViewerTemplateForm(self):
730: """Form for adding"""
731: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
732: return pt()
733:
734: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
735: REQUEST=None, submit=None):
736: "Add a Page Template with optional file content."
737:
738: self._setObject(id, DocumentViewerTemplate(id))
739: ob = getattr(self, id)
740: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
741: logging.info("txt %s:"%txt)
742: ob.pt_edit(txt,"text/html")
743: if title:
744: ob.pt_setTitle(title)
745: try:
746: u = self.DestinationURL()
747: except AttributeError:
748: u = REQUEST['URL1']
749:
750: u = "%s/%s" % (u, urllib.quote(id))
751: REQUEST.RESPONSE.redirect(u+'/manage_main')
752: return ''
753:
754:
755:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>