0
|
1 from OFS.Folder import Folder
|
|
2 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
|
|
3 from Products.PageTemplates.PageTemplateFile import PageTemplateFile
|
|
4 from AccessControl import ClassSecurityInfo
|
32
|
5 from AccessControl import getSecurityManager
|
0
|
6 from Globals import package_home
|
|
7
|
|
8 from Ft.Xml.Domlette import NonvalidatingReader
|
|
9 from Ft.Xml.Domlette import PrettyPrint, Print
|
|
10 from Ft.Xml import EMPTY_NAMESPACE
|
|
11
|
|
12 import Ft.Xml.XPath
|
|
13
|
|
14 import os.path
|
31
|
15 import sys
|
0
|
16 import cgi
|
|
17 import urllib
|
22
|
18 import zLOG
|
0
|
19
|
25
|
20 def getInt(number, default=0):
|
|
21 """returns always an int (0 in case of problems)"""
|
|
22 try:
|
|
23 return int(number)
|
|
24 except:
|
|
25 return default
|
|
26
|
|
27
|
0
|
28 def getTextFromNode(nodename):
|
32
|
29 if nodename is None:
|
|
30 return ""
|
0
|
31 nodelist=nodename.childNodes
|
|
32 rc = ""
|
|
33 for node in nodelist:
|
|
34 if node.nodeType == node.TEXT_NODE:
|
|
35 rc = rc + node.data
|
|
36 return rc
|
|
37
|
|
38 import socket
|
|
39
|
32
|
40 def urlopen(url,timeout=2):
|
0
|
41 """urlopen mit timeout"""
|
32
|
42 socket.setdefaulttimeout(timeout)
|
0
|
43 ret=urllib.urlopen(url)
|
|
44 socket.setdefaulttimeout(5)
|
|
45 return ret
|
|
46
|
|
47
|
22
|
48 ##
|
|
49 ## documentViewer class
|
|
50 ##
|
|
51 class documentViewer(Folder):
|
0
|
52 """document viewer"""
|
|
53
|
|
54 meta_type="Document viewer"
|
|
55
|
|
56 security=ClassSecurityInfo()
|
22
|
57 manage_options=Folder.manage_options+(
|
0
|
58 {'label':'main config','action':'changeDocumentViewerForm'},
|
|
59 )
|
|
60
|
22
|
61 # templates and forms
|
|
62 viewer_main = PageTemplateFile('zpt/viewer_main', globals())
|
|
63 thumbs_main = PageTemplateFile('zpt/thumbs_main', globals())
|
|
64 image_main = PageTemplateFile('zpt/image_main', globals())
|
|
65 head_main = PageTemplateFile('zpt/head_main', globals())
|
|
66 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
|
|
67
|
|
68 security.declareProtected('View management screens','changeDocumentViewerForm')
|
|
69 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
|
|
70
|
0
|
71
|
32
|
72 def __init__(self,id,imageViewerUrl,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):
|
0
|
73 """init document viewer"""
|
|
74 self.id=id
|
|
75 self.title=title
|
|
76 self.imageViewerUrl=imageViewerUrl
|
25
|
77 if not digilibBaseUrl:
|
22
|
78 self.digilibBaseUrl = self.findDigilibUrl()
|
25
|
79 else:
|
|
80 self.digilibBaseUrl = digilibBaseUrl
|
|
81 self.thumbcols = thumbcols
|
|
82 self.thumbrows = thumbrows
|
32
|
83 # authgroups is list of authorized groups (delimited by ,)
|
|
84 self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
|
22
|
85 # add template folder so we can always use template.something
|
|
86 self.manage_addFolder('template')
|
|
87
|
|
88
|
|
89 security.declareProtected('View','index_html')
|
25
|
90 def index_html(self,mode,url,start=None,pn=1):
|
22
|
91 '''
|
|
92 view it
|
|
93 @param mode: defines which type of document is behind url
|
|
94 @param url: url which contains display information
|
|
95 '''
|
0
|
96
|
22
|
97 zLOG.LOG("documentViewer (index)", zLOG.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
|
|
98
|
|
99 if not hasattr(self, 'template'):
|
|
100 # create template folder if it doesn't exist
|
|
101 self.manage_addFolder('template')
|
|
102
|
|
103 if not self.digilibBaseUrl:
|
|
104 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
|
|
105
|
25
|
106 docinfo = self.getDocinfo(mode=mode,url=url)
|
|
107 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
|
22
|
108 pt = getattr(self.template, 'viewer_main')
|
|
109 return pt(docinfo=docinfo,pageinfo=pageinfo)
|
0
|
110
|
|
111
|
25
|
112 def getLink(self,param=None,val=None):
|
|
113 """link to documentviewer with parameter param set to val"""
|
|
114 params=cgi.parse_qs(self.REQUEST['QUERY_STRING'])
|
|
115 if param is not None:
|
31
|
116 if val is None:
|
|
117 if params.has_key(param):
|
|
118 del params[param]
|
25
|
119 else:
|
31
|
120 params[param] = [str(val)]
|
|
121
|
|
122 ps = "&".join(["%s=%s"%(k,urllib.quote(v[0])) for (k, v) in params.items()])
|
|
123 url=self.REQUEST['URL']+"?"+ps
|
|
124 #url=self.REQUEST['URL']+"?"+urllib.urlencode(params, doseq=True)
|
25
|
125 return url
|
|
126
|
0
|
127
|
22
|
128 def getStyle(self, idx, selected, style=""):
|
25
|
129 """returns a string with the given style and append 'sel' if path == selected."""
|
22
|
130 #zLOG.LOG("documentViewer (getstyle)", zLOG.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
|
|
131 if idx == selected:
|
|
132 return style + 'sel'
|
|
133 else:
|
|
134 return style
|
0
|
135
|
32
|
136 def accessOK(self, docinfo):
|
|
137 """returns if access to the resource is granted"""
|
|
138 access = docinfo.get('accessType', None)
|
|
139 if access is None:
|
|
140 # no information - no access (not yet)
|
|
141 return True
|
|
142 elif access == 'free':
|
|
143 return True
|
|
144
|
|
145 print "access: ", access, " authgroups: ", self.authgroups
|
|
146 if access in self.authgroups:
|
|
147 # local access OK
|
|
148 user = getSecurityManager().getUser().getUserName()
|
|
149 print "user: ", user
|
|
150 return (user != "Anonymous User")
|
|
151
|
|
152 zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "unknown access group %s"%access)
|
|
153 return False
|
|
154
|
0
|
155
|
31
|
156 def getDirinfoFromDigilib(self,path,docinfo=None):
|
29
|
157 """gibt param von dlInfo aus"""
|
31
|
158 if docinfo is None:
|
|
159 docinfo = {}
|
|
160
|
29
|
161 imageUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
|
|
162
|
31
|
163 zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(imageUrl))
|
29
|
164
|
|
165 try:
|
|
166 dom = NonvalidatingReader.parseUri(imageUrl)
|
|
167 except:
|
31
|
168 zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.ERROR, "error reading %s"%(imageUrl))
|
|
169 raise IOError("Unable to get dirinfo from %s"%(imageUrl))
|
29
|
170
|
31
|
171 params=dom.xpath("//dir/size")
|
|
172 zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:size"%params)
|
29
|
173
|
|
174 if params:
|
32
|
175 docinfo['numPages'] = int(getTextFromNode(params[0]))
|
31
|
176 else:
|
|
177 docinfo['numPages'] = 0
|
|
178
|
|
179 return docinfo
|
32
|
180
|
29
|
181
|
32
|
182 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None):
|
|
183 """gets authorization info from the index.meta file at url or given by dom"""
|
|
184 zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))
|
|
185
|
|
186 access = None
|
|
187
|
|
188 if docinfo is None:
|
|
189 docinfo = {}
|
|
190
|
|
191 if dom is None:
|
|
192 server=self.digilibBaseUrl+"/servlet/Texter?fn="
|
|
193 path="/".join(path.split("/")[0:-1])
|
|
194 metaUrl=server+path+"/index.meta"
|
|
195 try:
|
|
196 dom = NonvalidatingReader.parseUri(metaUrl)
|
|
197 except:
|
|
198 return docinfo
|
|
199
|
|
200 acctype = dom.xpath("//access-conditions/access/@type")
|
|
201 if acctype and (len(acctype)>0):
|
|
202 access=acctype[0].value
|
|
203 if access == 'group':
|
|
204 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
|
|
205
|
|
206 docinfo['accessType'] = access
|
|
207 return docinfo
|
29
|
208
|
32
|
209
|
22
|
210 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None):
|
|
211 """gets bibliographical info from the index.meta file at url or given by dom"""
|
|
212 zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))
|
20
|
213
|
22
|
214 if docinfo is None:
|
|
215 docinfo = {}
|
|
216
|
|
217 if dom is None:
|
31
|
218 server=self.digilibBaseUrl+"/servlet/Texter?fn="
|
22
|
219 path="/".join(path.split("/")[0:-1])
|
|
220 metaUrl=server+path+"/index.meta"
|
|
221 try:
|
|
222 dom = NonvalidatingReader.parseUri(metaUrl)
|
|
223 except:
|
|
224 return docinfo
|
20
|
225
|
25
|
226 metaData=self.metadata.main.meta.bib
|
|
227 bibtype=dom.xpath("//bib/@type")
|
|
228 if bibtype and (len(bibtype)>0):
|
|
229 bibtype=bibtype[0].value
|
20
|
230 else:
|
25
|
231 bibtype="generic"
|
|
232 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
|
|
233 bibmap=metaData.generateMappingForType(bibtype)
|
31
|
234 print "bibmap: ", bibmap, " for: ", bibtype
|
32
|
235 # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
|
31
|
236 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
|
25
|
237 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
|
|
238 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
|
|
239 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
|
22
|
240
|
|
241 return docinfo
|
|
242
|
|
243
|
32
|
244 def getDocinfoFromTextTool(self,url,dom=None,docinfo=None):
|
22
|
245 """parse texttool tag in index meta"""
|
|
246 zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.INFO,"url: %s"%(url))
|
|
247 if docinfo is None:
|
|
248 docinfo = {}
|
|
249
|
32
|
250 if dom is None:
|
|
251 try:
|
|
252 dom = NonvalidatingReader.parseUri(url)
|
|
253 except:
|
|
254 zLOG.LOG("documentViewer (parseUrlTexttool)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])
|
|
255 raise IOError("Unable to get texttool info from %s"%(url))
|
|
256
|
|
257 archiveNames=dom.xpath("//resource/name")
|
|
258 if archiveNames and (len(archiveNames)>0):
|
|
259 archiveName=getTextFromNode(archiveNames[0])
|
22
|
260
|
|
261 archivePaths=dom.xpath("//resource/archive-path")
|
|
262 if archivePaths and (len(archivePaths)>0):
|
|
263 archivePath=getTextFromNode(archivePaths[0])
|
32
|
264 # clean up archive path
|
|
265 if archivePath[0] != '/':
|
|
266 archivePath = '/' + archivePath
|
|
267 if not archivePath.endswith(archiveName):
|
|
268 archivePath += "/" + archiveName
|
22
|
269 else:
|
|
270 archivePath=None
|
|
271
|
|
272 images=dom.xpath("//texttool/image")
|
|
273 if images and (len(images)>0):
|
|
274 image=getTextFromNode(images[0])
|
|
275 else:
|
|
276 image=None
|
|
277
|
|
278 if image and archivePath:
|
32
|
279 print "image: ", image, " archivepath: ", archivePath
|
22
|
280 image=os.path.join(archivePath,image)
|
|
281 image=image.replace("/mpiwg/online",'')
|
31
|
282 docinfo=self.getDirinfoFromDigilib(image,docinfo=docinfo)
|
22
|
283 docinfo['imagePath'] = image
|
31
|
284 docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+image
|
22
|
285
|
|
286 viewerUrls=dom.xpath("//texttool/digiliburlprefix")
|
|
287 if viewerUrls and (len(viewerUrls)>0):
|
|
288 viewerUrl=getTextFromNode(viewerUrls[0])
|
31
|
289 docinfo['viewerURL'] = viewerUrl
|
22
|
290
|
|
291 textUrls=dom.xpath("//texttool/text")
|
|
292 if textUrls and (len(textUrls)>0):
|
|
293 textUrl=getTextFromNode(textUrls[0])
|
31
|
294 docinfo['textURL'] = textUrl
|
22
|
295
|
|
296 docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)
|
32
|
297 docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)
|
22
|
298 return docinfo
|
|
299
|
|
300
|
|
301 def getDocinfoFromImagePath(self,path,docinfo=None):
|
|
302 """path ist the path to the images it assumes that the index.meta file is one level higher."""
|
|
303 zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path))
|
|
304 if docinfo is None:
|
|
305 docinfo = {}
|
29
|
306 path=path.replace("/mpiwg/online","")
|
22
|
307 docinfo['imagePath'] = path
|
31
|
308 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo)
|
|
309 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
|
22
|
310 docinfo['imageURL'] = imageUrl
|
|
311
|
|
312 docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo)
|
32
|
313 docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo)
|
22
|
314 return docinfo
|
20
|
315
|
22
|
316
|
|
317 def getDocinfo(self, mode, url):
|
|
318 """returns docinfo depending on mode"""
|
|
319 zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"mode: %s, url: %s"%(mode,url))
|
|
320 # look for cached docinfo in session
|
|
321 if self.REQUEST.SESSION.has_key('docinfo'):
|
|
322 docinfo = self.REQUEST.SESSION['docinfo']
|
|
323 # check if its still current
|
|
324 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
|
|
325 zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo in session: %s"%docinfo)
|
|
326 return docinfo
|
|
327 # new docinfo
|
|
328 docinfo = {'mode': mode, 'url': url}
|
|
329 if mode=="texttool": #index.meta with texttool information
|
|
330 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
|
|
331 elif mode=="imagepath":
|
|
332 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
|
|
333 else:
|
|
334 zLOG.LOG("documentViewer (getdocinfo)", zLOG.ERROR,"unknown mode!")
|
|
335 zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo: %s"%docinfo)
|
|
336 self.REQUEST.SESSION['docinfo'] = docinfo
|
|
337 return docinfo
|
20
|
338
|
|
339
|
25
|
340 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None):
|
22
|
341 """returns pageinfo with the given parameters"""
|
|
342 pageinfo = {}
|
25
|
343 current = getInt(current)
|
|
344 pageinfo['current'] = current
|
|
345 rows = int(rows or self.thumbrows)
|
|
346 pageinfo['rows'] = rows
|
|
347 cols = int(cols or self.thumbcols)
|
|
348 pageinfo['cols'] = cols
|
|
349 grpsize = cols * rows
|
|
350 pageinfo['groupsize'] = grpsize
|
|
351 start = getInt(start, default=(int(current / grpsize) * grpsize +1))
|
22
|
352 pageinfo['start'] = start
|
25
|
353 pageinfo['end'] = start + grpsize
|
|
354 if docinfo is not None:
|
|
355 np = int(docinfo['numPages'])
|
|
356 pageinfo['end'] = min(pageinfo['end'], np)
|
|
357 pageinfo['numgroups'] = int(np / grpsize)
|
|
358 if np % grpsize > 0:
|
|
359 pageinfo['numgroups'] += 1
|
|
360
|
22
|
361 return pageinfo
|
|
362
|
0
|
363 def text(self,mode,url,pn):
|
|
364 """give text"""
|
|
365 if mode=="texttool": #index.meta with texttool information
|
|
366 (viewerUrl,imagepath,textpath)=parseUrlTextTool(url)
|
|
367
|
|
368 print textpath
|
|
369 try:
|
|
370 dom = NonvalidatingReader.parseUri(textpath)
|
|
371 except:
|
|
372 return None
|
|
373
|
|
374 list=[]
|
|
375 nodes=dom.xpath("//pb")
|
|
376
|
|
377 node=nodes[int(pn)-1]
|
|
378
|
|
379 p=node
|
|
380
|
|
381 while p.tagName!="p":
|
|
382 p=p.parentNode
|
|
383
|
|
384
|
|
385 endNode=nodes[int(pn)]
|
|
386
|
|
387
|
|
388 e=endNode
|
|
389
|
|
390 while e.tagName!="p":
|
|
391 e=e.parentNode
|
|
392
|
|
393
|
|
394 next=node.parentNode
|
|
395
|
|
396 #sammle s
|
|
397 while next and (next!=endNode.parentNode):
|
|
398 list.append(next)
|
|
399 next=next.nextSibling
|
|
400 list.append(endNode.parentNode)
|
|
401
|
|
402 if p==e:# beide im selben paragraphen
|
20
|
403 pass
|
|
404 # else:
|
|
405 # next=p
|
|
406 # while next!=e:
|
|
407 # print next,e
|
|
408 # list.append(next)
|
|
409 # next=next.nextSibling
|
|
410 #
|
|
411 # for x in list:
|
|
412 # PrettyPrint(x)
|
|
413 #
|
|
414 # return list
|
22
|
415 #
|
|
416
|
|
417 def findDigilibUrl(self):
|
|
418 """try to get the digilib URL from zogilib"""
|
|
419 url = self.imageViewerUrl[:-1] + "/getScalerUrl"
|
|
420 try:
|
|
421 scaler = urlopen(url).read()
|
|
422 return scaler.replace("/servlet/Scaler?", "")
|
|
423 except:
|
|
424 return None
|
|
425
|
32
|
426 def changeDocumentViewer(self,imageViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):
|
22
|
427 """init document viewer"""
|
|
428 self.title=title
|
|
429 self.imageViewerUrl=imageViewerUrl
|
|
430 self.digilibBaseUrl = digilibBaseUrl
|
25
|
431 self.thumbrows = thumbrows
|
|
432 self.thumbcols = thumbcols
|
32
|
433 self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
|
22
|
434 if RESPONSE is not None:
|
|
435 RESPONSE.redirect('manage_main')
|
0
|
436
|
|
437
|
|
438
|
|
439
|
|
440 # security.declareProtected('View management screens','renameImageForm')
|
|
441
|
|
442 def manage_AddDocumentViewerForm(self):
|
|
443 """add the viewer form"""
|
22
|
444 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
|
0
|
445 return pt()
|
|
446
|
|
447 def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None):
|
|
448 """add the viewer"""
|
|
449 newObj=documentViewer(id,imageViewerUrl,title)
|
|
450 self._setObject(id,newObj)
|
|
451
|
|
452 if RESPONSE is not None:
|
|
453 RESPONSE.redirect('manage_main')
|
22
|
454
|
|
455
|
|
456 ##
|
|
457 ## DocumentViewerTemplate class
|
|
458 ##
|
|
459 class DocumentViewerTemplate(ZopePageTemplate):
|
|
460 """Template for document viewer"""
|
|
461 meta_type="DocumentViewer Template"
|
|
462
|
|
463
|
|
464 def manage_addDocumentViewerTemplateForm(self):
|
|
465 """Form for adding"""
|
|
466 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
|
|
467 return pt()
|
|
468
|
|
469 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
|
|
470 REQUEST=None, submit=None):
|
|
471 "Add a Page Template with optional file content."
|
|
472
|
|
473 self._setObject(id, DocumentViewerTemplate(id))
|
|
474 ob = getattr(self, id)
|
|
475 ob.pt_edit(open(os.path.join(package_home(globals()),'zpt/viewer_main.zpt')).read(),None)
|
|
476 if title:
|
|
477 ob.pt_setTitle(title)
|
|
478 try:
|
|
479 u = self.DestinationURL()
|
|
480 except AttributeError:
|
|
481 u = REQUEST['URL1']
|
|
482
|
|
483 u = "%s/%s" % (u, urllib.quote(id))
|
|
484 REQUEST.RESPONSE.redirect(u+'/manage_main')
|
|
485 return ''
|
|
486
|
|
487
|
0
|
488 |