Context Navigation

source: documentViewer/documentViewer.py @ 105:6bffb612cd6a

Last change on this file since 105:6bffb612cd6a was 105:6bffb612cd6a, checked in by abukhman, 14 years ago
* empty log message *
File size: 43.5 KB

Line
1
2	from OFS.Folder import Folder
3	from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
4	from Products.PageTemplates.PageTemplateFile import PageTemplateFile
5	from Products.PythonScripts.standard import url_quote
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	from xml.dom.minidom import parse, parseString
15
16
17
18	import Ft.Xml.XPath
19	import cStringIO
20	import xmlrpclib
21	import os.path
22	import sys
23	import cgi
24	import urllib
25	import logging
26	import math
27
28	import urlparse
29	from types import *
30
31	def logger(txt,method,txt2):
32	"""logging"""
33	logging.info(txt+ txt2)
34
35
36	def getInt(number, default=0):
37	"""returns always an int (0 in case of problems)"""
38	try:
39	return int(number)
40	except:
41	return int(default)
42
43	def getTextFromNode(nodename):
44	"""get the cdata content of a node"""
45	if nodename is None:
46	return ""
47	nodelist=nodename.childNodes
48	rc = ""
49	for node in nodelist:
50	if node.nodeType == node.TEXT_NODE:
51	rc = rc + node.data
52	return rc
53
54	def serializeNode(node, encoding='utf-8'):
55	"""returns a string containing node as XML"""
56	buf = cStringIO.StringIO()
57	Print(node, stream=buf, encoding=encoding)
58	s = buf.getvalue()
59	buf.close()
60	return s
61
62
63	def getParentDir(path):
64	"""returns pathname shortened by one"""
65	return '/'.join(path.split('/')[0:-1])
66
67
68	import socket
69
70	def urlopen(url,timeout=2):
71	"""urlopen mit timeout"""
72	socket.setdefaulttimeout(timeout)
73	ret=urllib.urlopen(url)
74	socket.setdefaulttimeout(5)
75	return ret
76
77
78	##
79	## documentViewer class
80	##
81	class documentViewer(Folder):
82	"""document viewer"""
83	#textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"
84
85	meta_type="Document viewer"
86
87	security=ClassSecurityInfo()
88	manage_options=Folder.manage_options+(
89	{'label':'main config','action':'changeDocumentViewerForm'},
90	)
91
92	# templates and forms
93	viewer_main = PageTemplateFile('zpt/viewer_main', globals())
94	toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
95	toc_text = PageTemplateFile('zpt/toc_text', globals())
96	toc_figures = PageTemplateFile('zpt/toc_figures', globals())
97	page_main_images = PageTemplateFile('zpt/page_main_images', globals())
98	page_main_text = PageTemplateFile('zpt/page_main_text', globals())
99	page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
100	page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
101	head_main = PageTemplateFile('zpt/head_main', globals())
102	docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
103	info_xml = PageTemplateFile('zpt/info_xml', globals())
104
105	thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
106	security.declareProtected('View management screens','changeDocumentViewerForm')
107	changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
108
109
110	def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
111	"""init document viewer"""
112	self.id=id
113	self.title=title
114	self.thumbcols = thumbcols
115	self.thumbrows = thumbrows
116	# authgroups is list of authorized groups (delimited by ,)
117	self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
118	# create template folder so we can always use template.something
119
120	templateFolder = Folder('template')
121	#self['template'] = templateFolder # Zope-2.12 style
122	self._setObject('template',templateFolder) # old style
123	try:
124	from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy
125	xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False)
126	#templateFolder['fulltextclient'] = xmlRpcClient
127	templateFolder._setObject('fulltextclient',xmlRpcClient)
128	except Exception, e:
129	logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e))
130	try:
131	from Products.zogiLib.zogiLib import zogiLib
132	zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
133	#templateFolder['zogilib'] = zogilib
134	templateFolder._setObject('zogilib',zogilib)
135	except Exception, e:
136	logging.error("Unable to create zogiLib for zogilib: "+str(e))
137
138
139	security.declareProtected('View','thumbs_rss')
140	def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
141	'''
142	view it
143	@param mode: defines how to access the document behind url
144	@param url: url which contains display information
145	@param viewMode: if images display images, if text display text, default is images (text,images or auto)
146
147	'''
148	logging.debug("HHHHHHHHHHHHHH:load the rss")
149	logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
150
151	if not hasattr(self, 'template'):
152	# create template folder if it doesn't exist
153	self.manage_addFolder('template')
154
155	if not self.digilibBaseUrl:
156	self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
157
158	docinfo = self.getDocinfo(mode=mode,url=url)
159	pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
160	pt = getattr(self.template, 'thumbs_main_rss')
161
162	if viewMode=="auto": # automodus gewaehlt
163	if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
164	viewMode="text"
165	else:
166	viewMode="images"
167
168	return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
169
170	security.declareProtected('View','index_html')
171	def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
172	'''
173	view it
174	@param mode: defines how to access the document behind url
175	@param url: url which contains display information
176	@param viewMode: if images display images, if text display text, default is auto (text,images or auto)
177	@param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
178	@param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
179	'''
180
181	logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
182
183	if not hasattr(self, 'template'):
184	# this won't work
185	logging.error("template folder missing!")
186	return "ERROR: template folder missing!"
187
188	if not getattr(self, 'digilibBaseUrl', None):
189	self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
190
191	docinfo = self.getDocinfo(mode=mode,url=url)
192
193
194	if tocMode != "thumbs":
195	# get table of contents
196	docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
197
198	pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
199
200	if viewMode=="auto": # automodus gewaehlt
201	if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
202	viewMode="text"
203	else:
204	viewMode="images"
205
206	pt = getattr(self.template, 'viewer_main')
207	return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
208
209	def generateMarks(self,mk):
210	ret=""
211	if mk is None:
212	return ""
213	if type(mk) is not ListType:
214	mk=[mk]
215	for m in mk:
216	ret+="mk=%s"%m
217	return ret
218
219
220	def findDigilibUrl(self):
221	"""try to get the digilib URL from zogilib"""
222	url = self.template.zogilib.getDLBaseUrl()
223	return url
224
225	def getStyle(self, idx, selected, style=""):
226	"""returns a string with the given style and append 'sel' if path == selected."""
227	#logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
228	if idx == selected:
229	return style + 'sel'
230	else:
231	return style
232
233	def getLink(self,param=None,val=None):
234	"""link to documentviewer with parameter param set to val"""
235	params=self.REQUEST.form.copy()
236	if param is not None:
237	if val is None:
238	if params.has_key(param):
239	del params[param]
240	else:
241	params[param] = str(val)
242
243	if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
244	params["mode"] = "imagepath"
245	params["url"] = getParentDir(params["url"])
246
247	# quote values and assemble into query string
248	ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
249	url=self.REQUEST['URL1']+"?"+ps
250	return url
251
252	def getLinkAmp(self,param=None,val=None):
253	"""link to documentviewer with parameter param set to val"""
254	params=self.REQUEST.form.copy()
255	if param is not None:
256	if val is None:
257	if params.has_key(param):
258	del params[param]
259	else:
260	params[param] = str(val)
261
262	# quote values and assemble into query string
263	logging.info("XYXXXXX: %s"%repr(params.items()))
264	ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
265	url=self.REQUEST['URL1']+"?"+ps
266	return url
267
268	def getInfo_xml(self,url,mode):
269	"""returns info about the document as XML"""
270
271	if not self.digilibBaseUrl:
272	self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
273
274	docinfo = self.getDocinfo(mode=mode,url=url)
275	pt = getattr(self.template, 'info_xml')
276	return pt(docinfo=docinfo)
277
278
279	def isAccessible(self, docinfo):
280	"""returns if access to the resource is granted"""
281	access = docinfo.get('accessType', None)
282	logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
283	if access is not None and access == 'free':
284	logger("documentViewer (accessOK)", logging.INFO, "access is free")
285	return True
286	elif access is None or access in self.authgroups:
287	# only local access -- only logged in users
288	user = getSecurityManager().getUser()
289	if user is not None:
290	#print "user: ", user
291	return (user.getUserName() != "Anonymous User")
292	else:
293	return False
294
295	logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
296	return False
297
298
299	def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
300	"""gibt param von dlInfo aus"""
301	num_retries = 3
302	if docinfo is None:
303	docinfo = {}
304
305	for x in range(cut):
306
307	path=getParentDir(path)
308
309	infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
310
311	logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
312
313	for cnt in range(num_retries):
314	try:
315	# dom = NonvalidatingReader.parseUri(imageUrl)
316	txt=urllib.urlopen(infoUrl).read()
317	dom = Parse(txt)
318	break
319	except:
320	logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
321	else:
322	raise IOError("Unable to get dir-info from %s"%(infoUrl))
323
324	sizes=dom.xpath("//dir/size")
325	logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
326
327	if sizes:
328	docinfo['numPages'] = int(getTextFromNode(sizes[0]))
329	else:
330	docinfo['numPages'] = 0
331
332	# TODO: produce and keep list of image names and numbers
333
334	return docinfo
335
336
337	def getIndexMeta(self, url):
338	"""returns dom of index.meta document at url"""
339	num_retries = 3
340	dom = None
341	metaUrl = None
342	if url.startswith("http://"):
343	# real URL
344	metaUrl = url
345	else:
346	# online path
347	server=self.digilibBaseUrl+"/servlet/Texter?fn="
348	metaUrl=server+url.replace("/mpiwg/online","")
349	if not metaUrl.endswith("index.meta"):
350	metaUrl += "/index.meta"
351	logging.debug("METAURL: %s"%metaUrl)
352	for cnt in range(num_retries):
353	try:
354	# patch dirk encoding fehler treten dann nicht mehr auf
355	# dom = NonvalidatingReader.parseUri(metaUrl)
356	txt=urllib.urlopen(metaUrl).read()
357	dom = Parse(txt)
358	break
359	except:
360	logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
361
362	if dom is None:
363	raise IOError("Unable to read index meta from %s"%(url))
364
365	return dom
366
367	def getPresentationInfoXML(self, url):
368	"""returns dom of info.xml document at url"""
369	num_retries = 3
370	dom = None
371	metaUrl = None
372	if url.startswith("http://"):
373	# real URL
374	metaUrl = url
375	else:
376	# online path
377	server=self.digilibBaseUrl+"/servlet/Texter?fn="
378	metaUrl=server+url.replace("/mpiwg/online","")
379
380	for cnt in range(num_retries):
381	try:
382	# patch dirk encoding fehler treten dann nicht mehr auf
383	# dom = NonvalidatingReader.parseUri(metaUrl)
384	txt=urllib.urlopen(metaUrl).read()
385	dom = Parse(txt)
386	break
387	except:
388	logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
389
390	if dom is None:
391	raise IOError("Unable to read infoXMLfrom %s"%(url))
392
393	return dom
394
395
396	def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
397	"""gets authorization info from the index.meta file at path or given by dom"""
398	logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
399
400	access = None
401
402	if docinfo is None:
403	docinfo = {}
404
405	if dom is None:
406	for x in range(cut):
407	path=getParentDir(path)
408	dom = self.getIndexMeta(path)
409
410	acctype = dom.xpath("//access-conditions/access/@type")
411	if acctype and (len(acctype)>0):
412	access=acctype[0].value
413	if access in ['group', 'institution']:
414	access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
415
416	docinfo['accessType'] = access
417	return docinfo
418
419
420	def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
421	"""gets bibliographical info from the index.meta file at path or given by dom"""
422	logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
423
424	if docinfo is None:
425	docinfo = {}
426
427	if dom is None:
428	for x in range(cut):
429	path=getParentDir(path)
430	dom = self.getIndexMeta(path)
431
432	logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
433	# put in all raw bib fields as dict "bib"
434	bib = dom.xpath("//bib/*")
435	if bib and len(bib)>0:
436	bibinfo = {}
437	for e in bib:
438	bibinfo[e.localName] = getTextFromNode(e)
439	docinfo['bib'] = bibinfo
440
441	# extract some fields (author, title, year) according to their mapping
442	metaData=self.metadata.main.meta.bib
443	bibtype=dom.xpath("//bib/@type")
444	if bibtype and (len(bibtype)>0):
445	bibtype=bibtype[0].value
446	else:
447	bibtype="generic"
448
449	bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
450	docinfo['bib_type'] = bibtype
451	bibmap=metaData.generateMappingForType(bibtype)
452	# if there is no mapping bibmap is empty (mapping sometimes has empty fields)
453	if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
454	try:
455	docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
456	except: pass
457	try:
458	docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
459	except: pass
460	try:
461	docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
462	except: pass
463	logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
464	try:
465	docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
466	except:
467	docinfo['lang']=''
468
469	return docinfo
470
471
472	def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
473	"""parse texttool tag in index meta"""
474	logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url))
475	if docinfo is None:
476	docinfo = {}
477	if docinfo.get('lang', None) is None:
478	docinfo['lang'] = '' # default keine Sprache gesetzt
479	if dom is None:
480	dom = self.getIndexMeta(url)
481
482	archivePath = None
483	archiveName = None
484
485	archiveNames = dom.xpath("//resource/name")
486	if archiveNames and (len(archiveNames) > 0):
487	archiveName = getTextFromNode(archiveNames[0])
488	else:
489	logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url))
490
491	archivePaths = dom.xpath("//resource/archive-path")
492	if archivePaths and (len(archivePaths) > 0):
493	archivePath = getTextFromNode(archivePaths[0])
494	# clean up archive path
495	if archivePath[0] != '/':
496	archivePath = '/' + archivePath
497	if archiveName and (not archivePath.endswith(archiveName)):
498	archivePath += "/" + archiveName
499	else:
500	# try to get archive-path from url
501	logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url))
502	if (not url.startswith('http')):
503	archivePath = url.replace('index.meta', '')
504
505	if archivePath is None:
506	# we balk without archive-path
507	raise IOError("Missing archive-path (for text-tool) in %s" % (url))
508
509	imageDirs = dom.xpath("//texttool/image")
510	if imageDirs and (len(imageDirs) > 0):
511	imageDir = getTextFromNode(imageDirs[0])
512
513	else:
514	# we balk with no image tag / not necessary anymore because textmode is now standard
515	#raise IOError("No text-tool info in %s"%(url))
516	imageDir = ""
517	#xquery="//pb"
518	docinfo['imagePath'] = "" # keine Bilder
519	docinfo['imageURL'] = ""
520
521	if imageDir and archivePath:
522	#print "image: ", imageDir, " archivepath: ", archivePath
523	imageDir = os.path.join(archivePath, imageDir)
524	imageDir = imageDir.replace("/mpiwg/online", '')
525	docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
526	docinfo['imagePath'] = imageDir
527
528	docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
529
530	viewerUrls = dom.xpath("//texttool/digiliburlprefix")
531	if viewerUrls and (len(viewerUrls) > 0):
532	viewerUrl = getTextFromNode(viewerUrls[0])
533	docinfo['viewerURL'] = viewerUrl
534
535	textUrls = dom.xpath("//texttool/text")
536	if textUrls and (len(textUrls) > 0):
537	textUrl = getTextFromNode(textUrls[0])
538	if urlparse.urlparse(textUrl)[0] == "": #keine url
539	textUrl = os.path.join(archivePath, textUrl)
540	# fix URLs starting with /mpiwg/online
541	if textUrl.startswith("/mpiwg/online"):
542	textUrl = textUrl.replace("/mpiwg/online", '', 1)
543
544	docinfo['textURL'] = textUrl
545
546	textUrls = dom.xpath("//texttool/text-url-path")
547	if textUrls and (len(textUrls) > 0):
548	textUrl = getTextFromNode(textUrls[0])
549	docinfo['textURLPath'] = textUrl
550	if not docinfo['imagePath']:
551	# text-only, no page images
552	docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
553
554	presentationUrls = dom.xpath("//texttool/presentation")
555	docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
556
557	if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
558	# presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
559	# durch den relativen Pfad auf die presentation infos
560	presentationPath = getTextFromNode(presentationUrls[0])
561	if url.endswith("index.meta"):
562	presentationUrl = url.replace('index.meta', presentationPath)
563	else:
564	presentationUrl = url + "/" + presentationPath
565
566	docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
567
568	docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
569
570	return docinfo
571
572
573	def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
574	"""gets the bibliographical information from the preseantion entry in texttools
575	"""
576	dom=self.getPresentationInfoXML(url)
577	try:
578	docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
579	except:
580	pass
581	try:
582	docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
583	except:
584	pass
585	try:
586	docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
587	except:
588	pass
589	return docinfo
590
591	def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
592	"""path ist the path to the images it assumes that the index.meta file is one level higher."""
593	logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))
594	if docinfo is None:
595	docinfo = {}
596	path=path.replace("/mpiwg/online","")
597	docinfo['imagePath'] = path
598	docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
599
600	pathorig=path
601	for x in range(cut):
602	path=getParentDir(path)
603	logging.error("PATH:"+path)
604	imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
605	docinfo['imageURL'] = imageUrl
606
607	#path ist the path to the images it assumes that the index.meta file is one level higher.
608	docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
609	docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
610	return docinfo
611
612
613	def getDocinfo(self, mode, url):
614	"""returns docinfo depending on mode"""
615	logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))
616	# look for cached docinfo in session
617	if self.REQUEST.SESSION.has_key('docinfo'):
618	docinfo = self.REQUEST.SESSION['docinfo']
619	# check if its still current
620	if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
621	logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)
622	return docinfo
623	# new docinfo
624	docinfo = {'mode': mode, 'url': url}
625	if mode=="texttool": #index.meta with texttool information
626	docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
627	elif mode=="imagepath":
628	docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
629	elif mode=="filepath":
630	docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
631	else:
632	logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
633	raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
634
635	logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
636	self.REQUEST.SESSION['docinfo'] = docinfo
637	return docinfo
638
639
640	def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
641	"""returns pageinfo with the given parameters"""
642	pageinfo = {}
643	current = getInt(current)
644	pageinfo['current'] = current
645	rows = int(rows or self.thumbrows)
646	pageinfo['rows'] = rows
647	cols = int(cols or self.thumbcols)
648	pageinfo['cols'] = cols
649	grpsize = cols * rows
650	pageinfo['groupsize'] = grpsize
651	start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
652	# int(current / grpsize) * grpsize +1))
653	pageinfo['start'] = start
654	pageinfo['end'] = start + grpsize
655	if (docinfo is not None) and ('numPages' in docinfo):
656	np = int(docinfo['numPages'])
657	pageinfo['end'] = min(pageinfo['end'], np)
658	pageinfo['numgroups'] = int(np / grpsize)
659	if np % grpsize > 0:
660	pageinfo['numgroups'] += 1
661
662
663	pageinfo['viewMode'] = viewMode
664	pageinfo['tocMode'] = tocMode
665	pageinfo['query'] = self.REQUEST.get('query',' ')
666	pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
667	pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
668
669	pageinfo['textPN'] = self.REQUEST.get('textPN','1')
670
671	pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
672	pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
673	pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
674	toc = int (pageinfo['tocPN'])
675	pageinfo['textPages'] =int (toc)
676
677	if 'tocSize_%s'%tocMode in docinfo:
678	tocSize = int(docinfo['tocSize_%s'%tocMode])
679	tocPageSize = int(pageinfo['tocPageSize'])
680	# cached toc
681
682	if tocSize%tocPageSize>0:
683	tocPages=tocSize/tocPageSize+1
684	else:
685	tocPages=tocSize/tocPageSize
686	pageinfo['tocPN'] = min (tocPages,toc)
687
688	pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
689	pageinfo['sn'] =self.REQUEST.get('sn','1')
690
691	return pageinfo
692
693	def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None):
694	"""get search list"""
695	docpath = docinfo['textURLPath']
696	url = docinfo['url']
697	logging.debug("documentViewer (gettoc) docpath: %s"%(docpath))
698	logging.debug("documentViewer (gettoc) url: %s"%(url))
699	pagesize = pageinfo['queryPageSize']
700	pn = pageinfo['searchPN']
701	sn = pageinfo['sn']
702	query =pageinfo['query']
703	queryType =pageinfo['queryType']
704	viewMode= pageinfo['viewMode']
705	tocMode = pageinfo['tocMode']
706	tocPN = pageinfo['tocPN']
707	selfurl = self.absolute_url()
708	logging.debug("documentViewer (gettoc) /mpdl/interface/doc-query.xql?document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode))
709	page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode) ,outputUnicode=False)
710	pagexml = page.replace('?document=%s'%str(docpath),'?url=%s'%url)
711	pagedom = Parse(pagexml)
712	if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
713	pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
714	if len(pagedivs)>0:
715	pagenode=pagedivs[0]
716	links=pagenode.xpath("//a")
717	for l in links:
718	hrefNode = l.getAttributeNodeNS(None, u"href")
719	if hrefNode:
720	href = hrefNode.nodeValue
721	if href.startswith('page-fragment.xql'):
722	selfurl = self.absolute_url()
723	#l.setAttributeNS(None, "span class = 'hit highlight'", "background-color: #77DD77;")
724	pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN))
725	hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
726	l.setAttributeNS(None, "onClick", "id='highlighting'")
727	l.setAttributeNS(None, "highlightQuery", "id='highlighting'")
728	return serializeNode(pagenode)
729
730	if (queryType=="fulltextMorph"):
731	pagedivs = pagedom.xpath("//div[@class='queryResult']")
732
733	if len(pagedivs)>0:
734	pagenode=pagedivs[0]
735	links=pagenode.xpath("//a")
736	for l in links:
737	hrefNode = l.getAttributeNodeNS(None, u"href")
738	if hrefNode:
739	href = hrefNode.nodeValue
740	if href.startswith('page-fragment.xql'):
741	selfurl = self.absolute_url()
742	pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN))
743	hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
744	if href.startswith('../lt/lemma.xql'):
745	selfurl = self.absolute_url()
746	hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
747	l.setAttributeNS(None, 'target', '_blank')
748	l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
749	l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
750	return serializeNode(pagenode)
751
752	if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
753	pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
754	if len(pagedivs)>0:
755	pagenode=pagedivs[0]
756	links=pagenode.xpath("//a")
757	for l in links:
758	hrefNode = l.getAttributeNodeNS(None, u"href")
759	if hrefNode:
760	href = hrefNode.nodeValue
761	hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))
762
763	if href.startswith('../lt/lex.xql'):
764	# selfurl = self.absolute_url()
765	hrefNode.nodeValue = href.replace('../lt/lex.xql','%s../template/head_main_voc'%selfurl)
766	l.setAttributeNS(None, 'target', '_blank')
767	l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
768	l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
769	if href.startswith('../lt/lemma.xql'):
770	#selfurl = self.absolute_url()
771	hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s../template/head_main_lemma'%selfurl)
772	l.setAttributeNS(None, 'target', '_blank')
773	l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
774	l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
775	return serializeNode(pagenode)
776	return "no text here"
777
778	def getNumPages(self,docinfo=None):
779	"""get list of pages from fulltext and put in docinfo"""
780	xquery = '//pb'
781	text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
782	# TODO: better processing of the page list. do we need the info somewhere else also?
783	docinfo['numPages'] = text.count("<pb ")
784	return docinfo
785
786	def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None,):
787	"""returns single page from fulltext"""
788	docpath = docinfo['textURLPath']
789	if mode == "text_dict":
790	textmode = "textPollux"
791	else:
792	textmode = mode
793
794	#selfurl = self.absolute_url()
795	#viewMode= pageinfo['viewMode']
796	#tocMode = pageinfo['tocMode']
797	#tocPN = pageinfo['tocPN']
798
799	pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False)
800	# post-processing downloaded xml
801	pagedom = Parse(pagexml)
802	# plain text mode
803	if mode == "text":
804	# first div contains text
805	pagedivs = pagedom.xpath("/div")
806	#queryResultPage
807	if len(pagedivs) > 0:
808
809	pagenode = pagedivs[0]
810	links = pagenode.xpath("//a")
811	for l in links:
812	hrefNode = l.getAttributeNodeNS(None, u"href")
813	if hrefNode:
814	href= hrefNode.nodeValue
815	if href.startswith('#note-0006-01'):
816	selfurl = self.absolute_url()
817	hrefNode.nodeValue = href.replace("href='#note-'",'xaxa/%s/'%selfurl)
818	return serializeNode(pagenode)
819	if mode == "xml":
820	# first div contains text
821	pagedivs = pagedom.xpath("/div")
822	if len(pagedivs) > 0:
823	pagenode = pagedivs[0]
824	return serializeNode(pagenode)
825	# text-with-links mode
826	if mode == "text_dict":
827	# first div contains text
828	pagedivs = pagedom.xpath("/div")
829	if len(pagedivs) > 0:
830	pagenode = pagedivs[0]
831	# check all a-tags
832	links = pagenode.xpath("//a")
833	for l in links:
834	hrefNode = l.getAttributeNodeNS(None, u"href")
835	if hrefNode:
836	# is link with href
837	href = hrefNode.nodeValue
838	if href.startswith('lt/lex.xql'):
839	# is pollux link
840	selfurl = self.absolute_url()
841	# change href
842	hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
843	# add target
844	l.setAttributeNS(None, 'target', '_blank')
845	l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
846	l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
847
848	if href.startswith('lt/lemma.xql'):
849	selfurl = self.absolute_url()
850	hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
851	l.setAttributeNS(None, 'target', '_blank')
852	l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
853	l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
854	return serializeNode(pagenode)
855
856	return "no text here"
857
858	def getTranslate(self, query=None, language=None):
859	"""translate into another languages"""
860	pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
861	return pagexml
862
863	def getLemma(self, lemma=None, language=None):
864	"""simular words lemma """
865	pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
866	#pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","lemma=%s&language=%s"%(lemma,language),outputUnicode=False)
867	return pagexml
868
869	def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
870	"""number of"""
871	docpath = docinfo['textURLPath']
872	pagesize = pageinfo['queryPageSize']
873	pn = pageinfo['searchPN']
874	query =pageinfo['query']
875	queryType =pageinfo['queryType']
876
877	tocSearch = 0
878	tocDiv = None
879	pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn) ,outputUnicode=False)
880
881	pagedom = Parse(pagexml)
882	numdivs = pagedom.xpath("//div[@class='queryResultHits']")
883	tocSearch = int(getTextFromNode(numdivs[0]))
884	tc=int((tocSearch/10)+1)
885	logging.debug("documentViewer (gettoc) tc: %s"%(tc))
886	return tc
887
888	def getToc(self, mode="text", docinfo=None):
889	"""loads table of contents and stores in docinfo"""
890	logging.debug("documentViewer (gettoc) mode: %s"%(mode))
891	if 'tocSize_%s'%mode in docinfo:
892	# cached toc
893	return docinfo
894	docpath = docinfo['textURLPath']
895	# we need to set a result set size
896	pagesize = 1000
897	pn = 1
898	if mode == "text":
899	queryType = "toc"
900	else:
901	queryType = mode
902	# number of entries in toc
903	tocSize = 0
904	tocDiv = None
905	pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
906	# post-processing downloaded xml
907	pagedom = Parse(pagexml)
908	# get number of entries
909	numdivs = pagedom.xpath("//div[@class='queryResultHits']")
910	if len(numdivs) > 0:
911	tocSize = int(getTextFromNode(numdivs[0]))
912	# div contains text
913	#pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
914	#if len(pagedivs) > 0:
915	# tocDiv = pagedivs[0]
916
917	docinfo['tocSize_%s'%mode] = tocSize
918	#docinfo['tocDiv_%s'%mode] = tocDiv
919	return docinfo
920
921	def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
922	"""returns single page from the table of contents"""
923	# TODO: this should use the cached TOC
924	if mode == "text":
925	queryType = "toc"
926	else:
927	queryType = mode
928	docpath = docinfo['textURLPath']
929	path = docinfo['textURLPath']
930	#logging.debug("documentViewer (gettoc) pathNomer: %s"%(pathNomer))
931	pagesize = pageinfo['tocPageSize']
932	pn = pageinfo['tocPN']
933	url = docinfo['url']
934	selfurl = self.absolute_url()
935	viewMode= pageinfo['viewMode']
936	tocMode = pageinfo['tocMode']
937	tocPN = pageinfo['tocPN']
938
939	pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn), outputUnicode=False)
940	page = pagexml.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN))
941	text = page.replace('mode=image','mode=texttool')
942	return text
943	# post-processing downloaded xml
944	#pagedom = Parse(text)
945	# div contains text
946	#pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
947	#if len(pagedivs) > 0:
948	# pagenode = pagedivs[0]
949	# return serializeNode(pagenode)
950	#else:
951	# return "No TOC!"
952
953
954	def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
955	"""init document viewer"""
956	self.title=title
957	self.digilibBaseUrl = digilibBaseUrl
958	self.thumbrows = thumbrows
959	self.thumbcols = thumbcols
960	self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
961	if RESPONSE is not None:
962	RESPONSE.redirect('manage_main')
963
964
965
966	def manage_AddDocumentViewerForm(self):
967	"""add the viewer form"""
968	pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
969	return pt()
970
971	def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
972	"""add the viewer"""
973	newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
974	self._setObject(id,newObj)
975
976	if RESPONSE is not None:
977	RESPONSE.redirect('manage_main')
978
979
980	##
981	## DocumentViewerTemplate class
982	##
983	class DocumentViewerTemplate(ZopePageTemplate):
984	"""Template for document viewer"""
985	meta_type="DocumentViewer Template"
986
987
988	def manage_addDocumentViewerTemplateForm(self):
989	"""Form for adding"""
990	pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
991	return pt()
992
993	def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
994	REQUEST=None, submit=None):
995	"Add a Page Template with optional file content."
996
997	self._setObject(id, DocumentViewerTemplate(id))
998	ob = getattr(self, id)
999	txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1000	logging.info("txt %s:"%txt)
1001	ob.pt_edit(txt,"text/html")
1002	if title:
1003	ob.pt_setTitle(title)
1004	try:
1005	u = self.DestinationURL()
1006	except AttributeError:
1007	u = REQUEST['URL1']
1008
1009	u = "%s/%s" % (u, urllib.quote(id))
1010	REQUEST.RESPONSE.redirect(u+'/manage_main')
1011	return ''
1012
1013
1014

Note: See TracBrowser for help on using the repository browser.

Download in other formats: