0
|
1
|
|
2 from OFS.Folder import Folder
|
|
3 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
|
2
|
4 from Products.PageTemplates.PageTemplateFile import PageTemplateFile
|
|
5 from Products.PythonScripts.standard import url_quote
|
0
|
6 from AccessControl import ClassSecurityInfo
|
2
|
7 from AccessControl import getSecurityManager
|
0
|
8 from Globals import package_home
|
|
9
|
|
10 from Ft.Xml.Domlette import NonvalidatingReader
|
|
11 from Ft.Xml.Domlette import PrettyPrint, Print
|
2
|
12 from Ft.Xml import EMPTY_NAMESPACE, Parse
|
|
13
|
|
14 from xml.dom.minidom import parse, parseString
|
|
15
|
|
16 from extraFunction import *
|
|
17
|
0
|
18
|
|
19 import Ft.Xml.XPath
|
2
|
20 import cStringIO
|
|
21 import xmlrpclib
|
0
|
22 import os.path
|
2
|
23 import sys
|
0
|
24 import cgi
|
|
25 import urllib
|
2
|
26 import logging
|
|
27 import math
|
|
28
|
|
29 import urlparse
|
|
30 from types import *
|
|
31
|
|
32 def logger(txt,method,txt2):
|
|
33 """logging"""
|
|
34 logging.info(txt+ txt2)
|
|
35
|
|
36
|
|
37 def getInt(number, default=0):
|
|
38 """returns always an int (0 in case of problems)"""
|
|
39 try:
|
|
40 return int(number)
|
|
41 except:
|
|
42 return int(default)
|
0
|
43
|
|
44 def getTextFromNode(nodename):
|
2
|
45 """get the cdata content of a node"""
|
|
46 if nodename is None:
|
|
47 return ""
|
0
|
48 nodelist=nodename.childNodes
|
|
49 rc = ""
|
|
50 for node in nodelist:
|
|
51 if node.nodeType == node.TEXT_NODE:
|
|
52 rc = rc + node.data
|
|
53 return rc
|
|
54
|
2
|
55 def serializeNode(node, encoding='utf-8'):
|
|
56 """returns a string containing node as XML"""
|
|
57 buf = cStringIO.StringIO()
|
|
58 Print(node, stream=buf, encoding=encoding)
|
|
59 s = buf.getvalue()
|
|
60 buf.close()
|
|
61 return s
|
|
62
|
|
63
|
|
64 def getParentDir(path):
|
|
65 """returns pathname shortened by one"""
|
|
66 return '/'.join(path.split('/')[0:-1])
|
|
67
|
|
68
|
0
|
69 import socket
|
|
70
|
2
|
71 def urlopen(url,timeout=2):
|
0
|
72 """urlopen mit timeout"""
|
2
|
73 socket.setdefaulttimeout(timeout)
|
0
|
74 ret=urllib.urlopen(url)
|
|
75 socket.setdefaulttimeout(5)
|
|
76 return ret
|
|
77
|
|
78
|
2
|
79 ##
|
|
80 ## documentViewer class
|
|
81 ##
|
|
82 class documentViewer(Folder, extraFunction):
|
0
|
83 """document viewer"""
|
2
|
84 #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"
|
|
85
|
0
|
86 meta_type="Document viewer"
|
|
87
|
|
88 security=ClassSecurityInfo()
|
2
|
89 manage_options=Folder.manage_options+(
|
0
|
90 {'label':'main config','action':'changeDocumentViewerForm'},
|
|
91 )
|
|
92
|
2
|
93 # templates and forms
|
|
94 viewer_main = PageTemplateFile('zpt/viewer_main', globals())
|
|
95 toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
|
|
96 toc_text = PageTemplateFile('zpt/toc_text', globals())
|
|
97 toc_figures = PageTemplateFile('zpt/toc_figures', globals())
|
|
98 page_main_images = PageTemplateFile('zpt/page_main_images', globals())
|
|
99 page_main_text = PageTemplateFile('zpt/page_main_text', globals())
|
|
100 page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
|
|
101 page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
|
|
102 head_main = PageTemplateFile('zpt/head_main', globals())
|
|
103 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
|
|
104 info_xml = PageTemplateFile('zpt/info_xml', globals())
|
0
|
105
|
2
|
106
|
|
107 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
|
|
108 security.declareProtected('View management screens','changeDocumentViewerForm')
|
|
109 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
|
|
110
|
|
111
|
|
112 def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
|
0
|
113 """init document viewer"""
|
|
114 self.id=id
|
|
115 self.title=title
|
2
|
116 self.thumbcols = thumbcols
|
|
117 self.thumbrows = thumbrows
|
|
118 # authgroups is list of authorized groups (delimited by ,)
|
|
119 self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
|
|
120 # create template folder so we can always use template.something
|
0
|
121
|
2
|
122 templateFolder = Folder('template')
|
|
123 #self['template'] = templateFolder # Zope-2.12 style
|
|
124 self._setObject('template',templateFolder) # old style
|
|
125 try:
|
|
126 from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy
|
|
127 xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False)
|
|
128 #templateFolder['fulltextclient'] = xmlRpcClient
|
|
129 templateFolder._setObject('fulltextclient',xmlRpcClient)
|
|
130 except Exception, e:
|
|
131 logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e))
|
|
132 try:
|
|
133 from Products.zogiLib.zogiLib import zogiLib
|
|
134 zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
|
|
135 #templateFolder['zogilib'] = zogilib
|
|
136 templateFolder._setObject('zogilib',zogilib)
|
|
137 except Exception, e:
|
|
138 logging.error("Unable to create zogiLib for zogilib: "+str(e))
|
|
139
|
|
140
|
|
141 security.declareProtected('View','thumbs_rss')
|
|
142 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
|
|
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 logging.debug("HHHHHHHHHHHHHH:load the rss")
|
|
151 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
|
0
|
152
|
2
|
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, 'thumbs_main_rss')
|
|
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)
|
|
171
|
|
172 security.declareProtected('View','index_html')
|
|
173 def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
|
|
174 '''
|
|
175 view it
|
|
176 @param mode: defines how to access the document behind url
|
|
177 @param url: url which contains display information
|
|
178 @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
|
|
179 @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
|
|
180 @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
|
|
181 '''
|
|
182
|
|
183 logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
|
|
184
|
|
185 if not hasattr(self, 'template'):
|
|
186 # this won't work
|
|
187 logging.error("template folder missing!")
|
|
188 return "ERROR: template folder missing!"
|
|
189
|
|
190 if not getattr(self, 'digilibBaseUrl', None):
|
|
191 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
|
|
192
|
|
193 docinfo = self.getDocinfo(mode=mode,url=url)
|
0
|
194
|
|
195
|
2
|
196 if tocMode != "thumbs":
|
|
197 # get table of contents
|
|
198 docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
|
|
199
|
|
200 if viewMode=="auto": # automodus gewaehlt
|
|
201 if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
|
|
202 viewMode="text_dict"
|
|
203 else:
|
|
204 viewMode="images"
|
|
205
|
|
206 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
|
|
207
|
|
208 pt = getattr(self.template, 'viewer_main')
|
|
209 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
|
|
210
|
|
211 def generateMarks(self,mk):
|
0
|
212 ret=""
|
2
|
213 if mk is None:
|
|
214 return ""
|
|
215 if type(mk) is not ListType:
|
|
216 mk=[mk]
|
|
217 for m in mk:
|
|
218 ret+="mk=%s"%m
|
|
219 return ret
|
0
|
220
|
|
221
|
2
|
222 def findDigilibUrl(self):
|
|
223 """try to get the digilib URL from zogilib"""
|
|
224 url = self.template.zogilib.getDLBaseUrl()
|
|
225 return url
|
|
226
|
|
227 def getDocumentViewerURL(self):
|
|
228 """returns the URL of this instance"""
|
|
229 return self.absolute_url()
|
|
230
|
|
231 def getStyle(self, idx, selected, style=""):
|
|
232 """returns a string with the given style and append 'sel' if path == selected."""
|
|
233 #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
|
|
234 if idx == selected:
|
|
235 return style + 'sel'
|
|
236 else:
|
|
237 return style
|
|
238
|
|
239 def getLink(self,param=None,val=None):
|
|
240 """link to documentviewer with parameter param set to val"""
|
|
241 params=self.REQUEST.form.copy()
|
|
242 if param is not None:
|
|
243 if val is None:
|
|
244 if params.has_key(param):
|
|
245 del params[param]
|
0
|
246 else:
|
2
|
247 params[param] = str(val)
|
|
248
|
|
249 if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
|
|
250 params["mode"] = "imagepath"
|
|
251 params["url"] = getParentDir(params["url"])
|
|
252
|
|
253 # quote values and assemble into query string
|
|
254 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
|
|
255 url=self.REQUEST['URL1']+"?"+ps
|
|
256 return url
|
|
257
|
|
258 def getLinkAmp(self,param=None,val=None):
|
|
259 """link to documentviewer with parameter param set to val"""
|
|
260 params=self.REQUEST.form.copy()
|
|
261 if param is not None:
|
|
262 if val is None:
|
|
263 if params.has_key(param):
|
|
264 del params[param]
|
|
265 else:
|
|
266 params[param] = str(val)
|
|
267
|
|
268 # quote values and assemble into query string
|
4
|
269 logging.debug("XYXXXXX: %s"%repr(params.items()))
|
2
|
270 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
|
|
271 url=self.REQUEST['URL1']+"?"+ps
|
|
272 return url
|
|
273
|
|
274 def getInfo_xml(self,url,mode):
|
|
275 """returns info about the document as XML"""
|
|
276
|
|
277 if not self.digilibBaseUrl:
|
|
278 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
|
0
|
279
|
2
|
280 docinfo = self.getDocinfo(mode=mode,url=url)
|
|
281 pt = getattr(self.template, 'info_xml')
|
|
282 return pt(docinfo=docinfo)
|
|
283
|
|
284
|
|
285 def isAccessible(self, docinfo):
|
|
286 """returns if access to the resource is granted"""
|
|
287 access = docinfo.get('accessType', None)
|
4
|
288 logging.debug("documentViewer (accessOK) access type %s"%access)
|
2
|
289 if access is not None and access == 'free':
|
4
|
290 logging.debug("documentViewer (accessOK) access is free")
|
2
|
291 return True
|
|
292 elif access is None or access in self.authgroups:
|
|
293 # only local access -- only logged in users
|
|
294 user = getSecurityManager().getUser()
|
|
295 if user is not None:
|
|
296 #print "user: ", user
|
|
297 return (user.getUserName() != "Anonymous User")
|
|
298 else:
|
|
299 return False
|
0
|
300
|
4
|
301 logging.debug("documentViewer (accessOK) unknown access type %s"%access)
|
2
|
302 return False
|
0
|
303
|
2
|
304
|
|
305 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
|
|
306 """gibt param von dlInfo aus"""
|
|
307 num_retries = 3
|
|
308 if docinfo is None:
|
|
309 docinfo = {}
|
0
|
310
|
2
|
311 for x in range(cut):
|
|
312
|
|
313 path=getParentDir(path)
|
|
314
|
|
315 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
|
0
|
316
|
4
|
317 logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
|
0
|
318
|
2
|
319 for cnt in range(num_retries):
|
|
320 try:
|
|
321 # dom = NonvalidatingReader.parseUri(imageUrl)
|
|
322 txt=urllib.urlopen(infoUrl).read()
|
|
323 dom = Parse(txt)
|
|
324 break
|
|
325 except:
|
4
|
326 logging.error("documentViewer (getdirinfofromdigilib) error reading %s (try %d)"%(infoUrl,cnt))
|
2
|
327 else:
|
|
328 raise IOError("Unable to get dir-info from %s"%(infoUrl))
|
|
329
|
|
330 sizes=dom.xpath("//dir/size")
|
4
|
331 logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
|
0
|
332
|
2
|
333 if sizes:
|
|
334 docinfo['numPages'] = int(getTextFromNode(sizes[0]))
|
|
335 else:
|
|
336 docinfo['numPages'] = 0
|
|
337
|
|
338 # TODO: produce and keep list of image names and numbers
|
|
339
|
|
340 return docinfo
|
|
341
|
|
342
|
|
343 def getIndexMeta(self, url):
|
|
344 """returns dom of index.meta document at url"""
|
|
345 num_retries = 3
|
|
346 dom = None
|
|
347 metaUrl = None
|
|
348 if url.startswith("http://"):
|
|
349 # real URL
|
|
350 metaUrl = url
|
|
351 else:
|
|
352 # online path
|
|
353 server=self.digilibBaseUrl+"/servlet/Texter?fn="
|
|
354 metaUrl=server+url.replace("/mpiwg/online","")
|
|
355 if not metaUrl.endswith("index.meta"):
|
|
356 metaUrl += "/index.meta"
|
|
357 logging.debug("METAURL: %s"%metaUrl)
|
|
358 for cnt in range(num_retries):
|
|
359 try:
|
|
360 # patch dirk encoding fehler treten dann nicht mehr auf
|
|
361 # dom = NonvalidatingReader.parseUri(metaUrl)
|
|
362 txt=urllib.urlopen(metaUrl).read()
|
|
363 dom = Parse(txt)
|
|
364 break
|
|
365 except:
|
4
|
366 logging.error("ERROR documentViewer (getIndexMeta) %s (%s)"%sys.exc_info()[0:2])
|
2
|
367
|
|
368 if dom is None:
|
|
369 raise IOError("Unable to read index meta from %s"%(url))
|
|
370
|
|
371 return dom
|
|
372
|
|
373 def getPresentationInfoXML(self, url):
|
|
374 """returns dom of info.xml document at url"""
|
|
375 num_retries = 3
|
|
376 dom = None
|
|
377 metaUrl = None
|
|
378 if url.startswith("http://"):
|
|
379 # real URL
|
|
380 metaUrl = url
|
|
381 else:
|
|
382 # online path
|
|
383 server=self.digilibBaseUrl+"/servlet/Texter?fn="
|
|
384 metaUrl=server+url.replace("/mpiwg/online","")
|
0
|
385
|
2
|
386 for cnt in range(num_retries):
|
|
387 try:
|
|
388 # patch dirk encoding fehler treten dann nicht mehr auf
|
|
389 # dom = NonvalidatingReader.parseUri(metaUrl)
|
|
390 txt=urllib.urlopen(metaUrl).read()
|
|
391 dom = Parse(txt)
|
|
392 break
|
|
393 except:
|
4
|
394 logging.error("ERROR documentViewer (getPresentationInfoXML) %s (%s)"%sys.exc_info()[0:2])
|
2
|
395
|
|
396 if dom is None:
|
|
397 raise IOError("Unable to read infoXMLfrom %s"%(url))
|
|
398
|
|
399 return dom
|
|
400
|
0
|
401
|
2
|
402 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
|
|
403 """gets authorization info from the index.meta file at path or given by dom"""
|
4
|
404 logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
|
2
|
405
|
|
406 access = None
|
|
407
|
|
408 if docinfo is None:
|
|
409 docinfo = {}
|
0
|
410
|
2
|
411 if dom is None:
|
|
412 for x in range(cut):
|
|
413 path=getParentDir(path)
|
|
414 dom = self.getIndexMeta(path)
|
|
415
|
|
416 acctype = dom.xpath("//access-conditions/access/@type")
|
|
417 if acctype and (len(acctype)>0):
|
|
418 access=acctype[0].value
|
|
419 if access in ['group', 'institution']:
|
|
420 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
|
|
421
|
|
422 docinfo['accessType'] = access
|
|
423 return docinfo
|
0
|
424
|
2
|
425
|
|
426 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
|
|
427 """gets bibliographical info from the index.meta file at path or given by dom"""
|
|
428 logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
|
|
429
|
|
430 if docinfo is None:
|
|
431 docinfo = {}
|
|
432
|
|
433 if dom is None:
|
|
434 for x in range(cut):
|
|
435 path=getParentDir(path)
|
|
436 dom = self.getIndexMeta(path)
|
|
437
|
|
438 logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
|
|
439 # put in all raw bib fields as dict "bib"
|
|
440 bib = dom.xpath("//bib/*")
|
|
441 if bib and len(bib)>0:
|
|
442 bibinfo = {}
|
|
443 for e in bib:
|
|
444 bibinfo[e.localName] = getTextFromNode(e)
|
|
445 docinfo['bib'] = bibinfo
|
0
|
446
|
2
|
447 # extract some fields (author, title, year) according to their mapping
|
|
448 metaData=self.metadata.main.meta.bib
|
|
449 bibtype=dom.xpath("//bib/@type")
|
|
450 if bibtype and (len(bibtype)>0):
|
|
451 bibtype=bibtype[0].value
|
|
452 else:
|
|
453 bibtype="generic"
|
|
454
|
|
455 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
|
|
456 docinfo['bib_type'] = bibtype
|
|
457 bibmap=metaData.generateMappingForType(bibtype)
|
|
458 # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
|
|
459 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
|
|
460 try:
|
|
461 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
|
|
462 except: pass
|
|
463 try:
|
|
464 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
|
|
465 except: pass
|
|
466 try:
|
|
467 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
|
|
468 except: pass
|
|
469 logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
|
|
470 try:
|
|
471 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
|
|
472 except:
|
|
473 docinfo['lang']=''
|
|
474
|
|
475 return docinfo
|
0
|
476
|
|
477
|
2
|
478 def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
|
|
479 """parse texttool tag in index meta"""
|
4
|
480 logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
|
2
|
481 if docinfo is None:
|
|
482 docinfo = {}
|
|
483 if docinfo.get('lang', None) is None:
|
|
484 docinfo['lang'] = '' # default keine Sprache gesetzt
|
|
485 if dom is None:
|
|
486 dom = self.getIndexMeta(url)
|
|
487
|
|
488 archivePath = None
|
|
489 archiveName = None
|
|
490
|
|
491 archiveNames = dom.xpath("//resource/name")
|
|
492 if archiveNames and (len(archiveNames) > 0):
|
|
493 archiveName = getTextFromNode(archiveNames[0])
|
|
494 else:
|
4
|
495 logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
|
2
|
496
|
|
497 archivePaths = dom.xpath("//resource/archive-path")
|
|
498 if archivePaths and (len(archivePaths) > 0):
|
|
499 archivePath = getTextFromNode(archivePaths[0])
|
|
500 # clean up archive path
|
|
501 if archivePath[0] != '/':
|
|
502 archivePath = '/' + archivePath
|
|
503 if archiveName and (not archivePath.endswith(archiveName)):
|
|
504 archivePath += "/" + archiveName
|
|
505 else:
|
|
506 # try to get archive-path from url
|
4
|
507 logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
|
2
|
508 if (not url.startswith('http')):
|
|
509 archivePath = url.replace('index.meta', '')
|
|
510
|
|
511 if archivePath is None:
|
|
512 # we balk without archive-path
|
|
513 raise IOError("Missing archive-path (for text-tool) in %s" % (url))
|
0
|
514
|
2
|
515 imageDirs = dom.xpath("//texttool/image")
|
|
516 if imageDirs and (len(imageDirs) > 0):
|
|
517 imageDir = getTextFromNode(imageDirs[0])
|
|
518
|
|
519 else:
|
|
520 # we balk with no image tag / not necessary anymore because textmode is now standard
|
|
521 #raise IOError("No text-tool info in %s"%(url))
|
|
522 imageDir = ""
|
|
523 #xquery="//pb"
|
|
524 docinfo['imagePath'] = "" # keine Bilder
|
|
525 docinfo['imageURL'] = ""
|
|
526
|
|
527 if imageDir and archivePath:
|
|
528 #print "image: ", imageDir, " archivepath: ", archivePath
|
|
529 imageDir = os.path.join(archivePath, imageDir)
|
|
530 imageDir = imageDir.replace("/mpiwg/online", '')
|
|
531 docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
|
|
532 docinfo['imagePath'] = imageDir
|
|
533
|
|
534 docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
|
|
535
|
|
536 viewerUrls = dom.xpath("//texttool/digiliburlprefix")
|
|
537 if viewerUrls and (len(viewerUrls) > 0):
|
|
538 viewerUrl = getTextFromNode(viewerUrls[0])
|
|
539 docinfo['viewerURL'] = viewerUrl
|
|
540
|
|
541 textUrls = dom.xpath("//texttool/text")
|
|
542 if textUrls and (len(textUrls) > 0):
|
|
543 textUrl = getTextFromNode(textUrls[0])
|
|
544 if urlparse.urlparse(textUrl)[0] == "": #keine url
|
|
545 textUrl = os.path.join(archivePath, textUrl)
|
|
546 # fix URLs starting with /mpiwg/online
|
|
547 if textUrl.startswith("/mpiwg/online"):
|
|
548 textUrl = textUrl.replace("/mpiwg/online", '', 1)
|
|
549
|
|
550 docinfo['textURL'] = textUrl
|
|
551
|
|
552 textUrls = dom.xpath("//texttool/text-url-path")
|
|
553 if textUrls and (len(textUrls) > 0):
|
|
554 textUrl = getTextFromNode(textUrls[0])
|
|
555 docinfo['textURLPath'] = textUrl
|
|
556 if not docinfo['imagePath']:
|
|
557 # text-only, no page images
|
|
558 docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
|
|
559
|
|
560 presentationUrls = dom.xpath("//texttool/presentation")
|
|
561 docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
|
|
562
|
|
563 if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
|
|
564 # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
|
|
565 # durch den relativen Pfad auf die presentation infos
|
|
566 presentationPath = getTextFromNode(presentationUrls[0])
|
|
567 if url.endswith("index.meta"):
|
|
568 presentationUrl = url.replace('index.meta', presentationPath)
|
|
569 else:
|
|
570 presentationUrl = url + "/" + presentationPath
|
|
571
|
|
572 docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
|
0
|
573
|
2
|
574 docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
|
0
|
575
|
2
|
576 return docinfo
|
|
577
|
|
578
|
|
579 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
|
|
580 """gets the bibliographical information from the preseantion entry in texttools
|
|
581 """
|
|
582 dom=self.getPresentationInfoXML(url)
|
|
583 try:
|
|
584 docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
|
|
585 except:
|
|
586 pass
|
|
587 try:
|
|
588 docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
|
|
589 except:
|
|
590 pass
|
|
591 try:
|
|
592 docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
|
|
593 except:
|
|
594 pass
|
|
595 return docinfo
|
|
596
|
|
597 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
|
|
598 """path ist the path to the images it assumes that the index.meta file is one level higher."""
|
4
|
599 logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
|
2
|
600 if docinfo is None:
|
|
601 docinfo = {}
|
|
602 path=path.replace("/mpiwg/online","")
|
|
603 docinfo['imagePath'] = path
|
|
604 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
|
|
605
|
|
606 pathorig=path
|
|
607 for x in range(cut):
|
|
608 path=getParentDir(path)
|
4
|
609 logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
|
2
|
610 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
|
|
611 docinfo['imageURL'] = imageUrl
|
0
|
612
|
2
|
613 #path ist the path to the images it assumes that the index.meta file is one level higher.
|
|
614 docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
|
|
615 docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
|
|
616 return docinfo
|
|
617
|
|
618
|
|
619 def getDocinfo(self, mode, url):
|
|
620 """returns docinfo depending on mode"""
|
4
|
621 logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
|
2
|
622 # look for cached docinfo in session
|
|
623 if self.REQUEST.SESSION.has_key('docinfo'):
|
|
624 docinfo = self.REQUEST.SESSION['docinfo']
|
|
625 # check if its still current
|
|
626 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
|
4
|
627 logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
|
2
|
628 return docinfo
|
|
629 # new docinfo
|
|
630 docinfo = {'mode': mode, 'url': url}
|
|
631 if mode=="texttool": #index.meta with texttool information
|
|
632 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
|
|
633 elif mode=="imagepath":
|
|
634 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
|
|
635 elif mode=="filepath":
|
|
636 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
|
|
637 else:
|
4
|
638 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
|
2
|
639 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
|
|
640
|
4
|
641 logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
|
2
|
642 self.REQUEST.SESSION['docinfo'] = docinfo
|
|
643 return docinfo
|
|
644
|
|
645 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
|
|
646 """returns pageinfo with the given parameters"""
|
|
647 pageinfo = {}
|
|
648 current = getInt(current)
|
|
649 pageinfo['current'] = current
|
|
650 rows = int(rows or self.thumbrows)
|
|
651 pageinfo['rows'] = rows
|
|
652 cols = int(cols or self.thumbcols)
|
|
653 pageinfo['cols'] = cols
|
|
654 grpsize = cols * rows
|
|
655 pageinfo['groupsize'] = grpsize
|
|
656 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
|
|
657 # int(current / grpsize) * grpsize +1))
|
|
658 pageinfo['start'] = start
|
|
659 pageinfo['end'] = start + grpsize
|
|
660 if (docinfo is not None) and ('numPages' in docinfo):
|
|
661 np = int(docinfo['numPages'])
|
|
662 pageinfo['end'] = min(pageinfo['end'], np)
|
|
663 pageinfo['numgroups'] = int(np / grpsize)
|
|
664 if np % grpsize > 0:
|
|
665 pageinfo['numgroups'] += 1
|
|
666 pageinfo['viewMode'] = viewMode
|
|
667 pageinfo['tocMode'] = tocMode
|
|
668 pageinfo['query'] = self.REQUEST.get('query',' ')
|
|
669 pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
|
|
670 pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
|
|
671 pageinfo['textPN'] = self.REQUEST.get('textPN','1')
|
|
672 pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
|
|
673 pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
|
|
674 pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
|
|
675 pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
|
|
676 toc = int (pageinfo['tocPN'])
|
|
677 pageinfo['textPages'] =int (toc)
|
0
|
678
|
2
|
679 if 'tocSize_%s'%tocMode in docinfo:
|
|
680 tocSize = int(docinfo['tocSize_%s'%tocMode])
|
|
681 tocPageSize = int(pageinfo['tocPageSize'])
|
|
682 # cached toc
|
|
683 if tocSize%tocPageSize>0:
|
|
684 tocPages=tocSize/tocPageSize+1
|
|
685 else:
|
|
686 tocPages=tocSize/tocPageSize
|
|
687 pageinfo['tocPN'] = min (tocPages,toc)
|
|
688 pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
|
|
689 pageinfo['sn'] =self.REQUEST.get('sn','')
|
|
690 return pageinfo
|
|
691
|
|
692 def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
|
|
693 """init document viewer"""
|
|
694 self.title=title
|
|
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
|
0
|
702 def manage_AddDocumentViewerForm(self):
|
|
703 """add the viewer form"""
|
2
|
704 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
|
0
|
705 return pt()
|
|
706
|
2
|
707 def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
|
0
|
708 """add the viewer"""
|
2
|
709 newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
|
0
|
710 self._setObject(id,newObj)
|
|
711
|
|
712 if RESPONSE is not None:
|
|
713 RESPONSE.redirect('manage_main')
|
2
|
714
|
|
715 ## DocumentViewerTemplate class
|
|
716 class DocumentViewerTemplate(ZopePageTemplate):
|
|
717 """Template for document viewer"""
|
|
718 meta_type="DocumentViewer Template"
|
|
719
|
|
720
|
|
721 def manage_addDocumentViewerTemplateForm(self):
|
|
722 """Form for adding"""
|
|
723 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
|
|
724 return pt()
|
|
725
|
|
726 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
|
|
727 REQUEST=None, submit=None):
|
|
728 "Add a Page Template with optional file content."
|
|
729
|
|
730 self._setObject(id, DocumentViewerTemplate(id))
|
|
731 ob = getattr(self, id)
|
|
732 txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
|
|
733 logging.info("txt %s:"%txt)
|
|
734 ob.pt_edit(txt,"text/html")
|
|
735 if title:
|
|
736 ob.pt_setTitle(title)
|
|
737 try:
|
|
738 u = self.DestinationURL()
|
|
739 except AttributeError:
|
|
740 u = REQUEST['URL1']
|
|
741
|
|
742 u = "%s/%s" % (u, urllib.quote(id))
|
|
743 REQUEST.RESPONSE.redirect(u+'/manage_main')
|
|
744 return ''
|
|
745
|
|
746
|
|
747
|