Mercurial > hg > documentViewer

comparison documentViewer.py @ 22:b139f9937e97

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
preliminary version 0.2 - lots of stuff rewritten - new template system - still no access control
author casties
date Thu, 06 Apr 2006 19:13:43 +0200
parents 9884703dae70
children e93fb8cadd3a
comparison
equal deleted inserted replaced
21:0af46e75de3c 22:b139f9937e97
14 import Ft.Xml.XPath 14 import Ft.Xml.XPath
15 15
16 import os.path 16 import os.path
17 import cgi 17 import cgi
18 import urllib 18 import urllib
19 import zLOG
19 20
20 def getTextFromNode(nodename): 21 def getTextFromNode(nodename):
21 nodelist=nodename.childNodes 22 nodelist=nodename.childNodes
22 rc = "" 23 rc = ""
23 for node in nodelist: 24 for node in nodelist:
34 socket.setdefaulttimeout(5) 35 socket.setdefaulttimeout(5)
35 return ret 36 return ret
36 37
37 def getParamFromDigilib(path,param): 38 def getParamFromDigilib(path,param):
38 """gibt param von dlInfo aus""" 39 """gibt param von dlInfo aus"""
39 imageUrl=genericDigilib+"/dlInfo-xml.jsp?fn="+path 40 imageUrl=genericDigilib+"/dirInfo-xml.jsp?mo=dir&fn="+path
40 41
42 zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo (%s) from %s"%(param,imageUrl))
43
41 try: 44 try:
42 dom = NonvalidatingReader.parseUri(imageUrl) 45 dom = NonvalidatingReader.parseUri(imageUrl)
43 except: 46 except:
44 return None 47 return None
45 48
46 49 params=dom.xpath("//dir/%s"%param)
47 params=dom.xpath("//document-parameters/parameter[@name='%s']/@value"%param) 50 zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:%s"%params)
48 51
49 if params: 52 if params:
50 return params[0].value 53 return getTextFromNode(params[0])
51 54
52 def parseUrlTextTool(url): 55
53 """parse index meta""" 56
54 57
55 try: 58 ##
56 dom = NonvalidatingReader.parseUri(url) 59 ## documentViewer class
57 except: 60 ##
58 zLOG.LOG("documentViewer (parseUrlTexttool)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2]) 61 class documentViewer(Folder):
59 return (None,None,None)
60
61 archivePaths=dom.xpath("//resource/archive-path")
62
63 if archivePaths and (len(archivePaths)>0):
64 archivePath=getTextFromNode(archivePaths[0])
65 else:
66 archivePath=None
67
68
69 images=dom.xpath("//texttool/image")
70
71 if images and (len(images)>0):
72 image=getTextFromNode(images[0])
73 else:
74 image=None
75
76 if image and archivePath:
77 image=os.path.join(archivePath,image)
78 image=image.replace("/mpiwg/online",'')
79 pt=getParamFromDigilib(image,'pt')
80
81 else:
82 image=None
83
84 viewerUrls=dom.xpath("//texttool/digiliburlprefix")
85
86 if viewerUrls and (len(viewerUrls)>0):
87 viewerUrl=getTextFromNode(viewerUrls[0])
88 else:
89 viewerUrl=None
90
91
92 textUrls=dom.xpath("//texttool/text")
93
94 if textUrls and (len(textUrls)>0):
95 textUrl=getTextFromNode(textUrls[0])
96 else:
97 textUrl=None
98 return viewerUrl,(image,pt),textUrl
99
100
101 class documentViewer(ZopePageTemplate):
102 """document viewer""" 62 """document viewer"""
103 63
104 meta_type="Document viewer" 64 meta_type="Document viewer"
105 65
106 security=ClassSecurityInfo() 66 security=ClassSecurityInfo()
107 manage_options=ZopePageTemplate.manage_options+( 67 manage_options=Folder.manage_options+(
108 {'label':'main config','action':'changeDocumentViewerForm'}, 68 {'label':'main config','action':'changeDocumentViewerForm'},
109 ) 69 )
110 70
111 _default_content_fn = os.path.join(package_home(globals()),'zpt','documentViewer_template.zpt') 71 # templates and forms
112 72 viewer_main = PageTemplateFile('zpt/viewer_main', globals())
113 def __init__(self,id,imageViewerUrl,title=""): 73 thumbs_main = PageTemplateFile('zpt/thumbs_main', globals())
74 image_main = PageTemplateFile('zpt/image_main', globals())
75 head_main = PageTemplateFile('zpt/head_main', globals())
76 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
77
78 security.declareProtected('View management screens','changeDocumentViewerForm')
79 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
80
81
82 def __init__(self,id,imageViewerUrl,title="",digilibBaseUrl=None):
114 """init document viewer""" 83 """init document viewer"""
115 self.id=id 84 self.id=id
116 self.title=title 85 self.title=title
117 self.imageViewerUrl=imageViewerUrl 86 self.imageViewerUrl=imageViewerUrl
118 87 self.digilibBaseUrl = digilibBaseUrl
119 security.declareProtected('View management screens','changeDocumentViewerForm') 88 if not self.digilibBaseUrl:
120 def changeDocumentViewerForm(self): 89 self.digilibBaseUrl = self.findDigilibUrl()
121 """change it""" 90 # add template folder so we can always use template.something
122 pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','changeDocumentViewer.zpt')).__of__(self) 91 self.manage_addFolder('template')
123 return pt() 92
93
94 security.declareProtected('View','index_html')
95 def index_html(self,mode,url,start=0,pn=1):
96 '''
97 view it
98 @param mode: defines which type of document is behind url
99 @param url: url which contains display information
100 '''
101
102 zLOG.LOG("documentViewer (index)", zLOG.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
103 print "dlbaseurl:", self.digilibBaseUrl
104
105 if not hasattr(self, 'template'):
106 # create template folder if it doesn't exist
107 print "no template folder -- creating"
108 self.manage_addFolder('template')
109
110 if not self.digilibBaseUrl:
111 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
112
113 print "dlbaseurl:", self.digilibBaseUrl
114
115 docinfo = self.getDocinfo(mode=mode, url=url)
116 pageinfo = self.getPageinfo(start=start,current=pn)
117 pt = getattr(self.template, 'viewer_main')
118 return pt(docinfo=docinfo,pageinfo=pageinfo)
124 119
125 120
126 def changeDocumentViewer(self,imageViewerUrl,title="",RESPONSE=None):
127 """init document viewer"""
128 self.title=title
129 self.imageViewerUrl=imageViewerUrl
130
131 if RESPONSE is not None:
132 RESPONSE.redirect('manage_main')
133
134
135 def imageLink(self,nr): 121 def imageLink(self,nr):
136 """link hinter den images""" 122 """link hinter den images"""
137 paramsTmp=cgi.parse_qs(self.REQUEST['QUERY_STRING']) 123 paramsTmp=cgi.parse_qs(self.REQUEST['QUERY_STRING'])
138 params={} 124 params={}
139 for x in paramsTmp.iteritems(): 125 for x in paramsTmp.iteritems():
141 127
142 params['pn']=nr 128 params['pn']=nr
143 newUrl=self.REQUEST['URL']+"?"+urllib.urlencode(params) 129 newUrl=self.REQUEST['URL']+"?"+urllib.urlencode(params)
144 return newUrl 130 return newUrl
145 131
146 132 def getStyle(self, idx, selected, style=""):
133 """returns a string with the given style + 'sel' if path == selected."""
134 #zLOG.LOG("documentViewer (getstyle)", zLOG.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
135 if idx == selected:
136 return style + 'sel'
137 else:
138 return style
139
140
147 def thumbruler(self,cols,rows,start,maximum): 141 def thumbruler(self,cols,rows,start,maximum):
148 """ruler for thumbs""" 142 """ruler for thumbs"""
149 ret="" 143 ret=""
150 paramsTmp=cgi.parse_qs(self.REQUEST['QUERY_STRING']) 144 paramsTmp=cgi.parse_qs(self.REQUEST['QUERY_STRING'])
151 params={} 145 params={}
160 params['start']=newStart 154 params['start']=newStart
161 newUrl=self.REQUEST['URL']+"?"+urllib.urlencode(params) 155 newUrl=self.REQUEST['URL']+"?"+urllib.urlencode(params)
162 ret+="""<a href="%s">prev</a>"""%newUrl 156 ret+="""<a href="%s">prev</a>"""%newUrl
163 157
164 158
165 ret+="""<select onChange="location.href='%s&start='+this.options[this.selectedIndex].value" """%newUrlSelect 159 ret+="""<select onChange="location.href='%s&start='+this.options[this.selectedIndex].value">"""%newUrlSelect
166 nr,rest=divmod(maximum,cols*rows) 160 nr,rest=divmod(maximum,cols*rows)
167 if rest > 0: 161 if rest > 0:
168 nr+=1 162 nr+=1
169 for i in range(nr): 163 for i in range(nr):
170 nr=i*cols*rows 164 nr=i*cols*rows
180 params['start']=newStart 174 params['start']=newStart
181 newUrl=self.REQUEST['URL']+"?"+urllib.urlencode(params) 175 newUrl=self.REQUEST['URL']+"?"+urllib.urlencode(params)
182 ret+="""<a href="%s">next</a>"""%newUrl 176 ret+="""<a href="%s">next</a>"""%newUrl
183 177
184 return ret 178 return ret
185 179
186 def textToolThumb(self,url,start=0): 180
187 """understands the texttool format 181
188 @param url: url to index.meta with texttool tag 182 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None):
189 """ 183 """gets bibliographical info from the index.meta file at url or given by dom"""
190 (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) 184 zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))
191 185
192 imageUrl=genericDigilib+"/servlet/Scaler?fn=%s"%imagepath[0] 186 if docinfo is None:
193 187 docinfo = {}
194 pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','thumbs.zpt')).__of__(self) 188
195 return pt(imageUrl=imageUrl,pt=imagepath[1],start=start)
196
197 def imagePathThumb(self,path,start=0):
198 """path ist the path to the images it is assumes that the index.meta file is one level higher."""
199
200 path=path.replace("/mpiwg/online","")
201 pt=getParamFromDigilib(path,'pt')
202 imageUrl=genericDigilib+"/servlet/Scaler?fn=%s"%path
203
204 pageT=PageTemplateFile(os.path.join(package_home(globals()),'zpt','thumbs.zpt')).__of__(self)
205 return pageT(imageUrl=imageUrl,pt=pt,start=start)
206
207 def headerFromIndexMeta(self,path):
208 """gibt header from index meta out"""
209
210 metaData=self.metadata.main.meta.bib 189 metaData=self.metadata.main.meta.bib
211 server="http://foxridge.mpiwg-berlin.mpg.de" 190 if dom is None:
212 path="/".join(path.split("/")[0:-1]) 191 server="http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary/servlet/Texter?fn="
213 metaUrl=server+path+"/index.meta" 192 path="/".join(path.split("/")[0:-1])
214 193 metaUrl=server+path+"/index.meta"
215 dom = NonvalidatingReader.parseUri(metaUrl) 194 try:
195 dom = NonvalidatingReader.parseUri(metaUrl)
196 except:
197 return docinfo
198
216 type=dom.xpath("//bib/@type") 199 type=dom.xpath("//bib/@type")
217 if type and (len(type)>0): 200 if type and (len(type)>0):
218 type=type[0].value 201 type=type[0].value
219 else: 202 else:
220 type="generic" 203 type="generic"
221 type=type.replace("-"," ")# wrong typesiin index meta "-" instead of " " 204 type=type.replace("-"," ")# wrong typesiin index meta "-" instead of " "
222 hash=metaData.generateMappingForType(type) 205 hash=metaData.generateMappingForType(type)
223 206
224 author=getTextFromNode(dom.xpath("//bib/%s"%hash['author'][0])[0]) 207 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%hash['author'][0])[0])
225 title=getTextFromNode(dom.xpath("//bib/%s"%hash['title'][0])[0]) 208 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%hash['title'][0])[0])
226 year=getTextFromNode(dom.xpath("//bib/%s"%hash['year'][0])[0]) 209 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%hash['year'][0])[0])
227 210
228 return author,title,year 211 return docinfo
229 212
213
214 def getDocinfoFromTextTool(self,url,docinfo=None):
215 """parse texttool tag in index meta"""
216 zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.INFO,"url: %s"%(url))
217 if docinfo is None:
218 docinfo = {}
219
220 try:
221 dom = NonvalidatingReader.parseUri(url)
222 except:
223 zLOG.LOG("documentViewer (parseUrlTexttool)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])
224 return docinfo
225
226 archivePaths=dom.xpath("//resource/archive-path")
227
228 if archivePaths and (len(archivePaths)>0):
229 archivePath=getTextFromNode(archivePaths[0])
230 else:
231 archivePath=None
232
233 images=dom.xpath("//texttool/image")
234
235 if images and (len(images)>0):
236 image=getTextFromNode(images[0])
237 else:
238 image=None
239
240 if image and archivePath:
241 image=os.path.join(archivePath,image)
242 image=image.replace("/mpiwg/online",'')
243 pt=getParamFromDigilib(image,'size')
244 docinfo['imagePath'] = image
245 docinfo['numberOfPages'] = pt
246
247 viewerUrls=dom.xpath("//texttool/digiliburlprefix")
248
249 if viewerUrls and (len(viewerUrls)>0):
250 viewerUrl=getTextFromNode(viewerUrls[0])
251 docinfo['imageURL'] = viewerURL
252
253 textUrls=dom.xpath("//texttool/text")
254
255 if textUrls and (len(textUrls)>0):
256 textUrl=getTextFromNode(textUrls[0])
257 docinfo['textURL'] = textURL
258
259 docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)
260 return docinfo
261
262
263 def getDocinfoFromImagePath(self,path,docinfo=None):
264 """path ist the path to the images it assumes that the index.meta file is one level higher."""
265 zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path))
266 if docinfo is None:
267 docinfo = {}
268 docinfo['imagePath'] = path
269 path=path.replace("/mpiwg/online","")
270 pt=getParamFromDigilib(path,'size')
271 docinfo['numberOfPages'] = pt
272 imageUrl=genericDigilib+"/servlet/Scaler?fn=%s"%path
273 docinfo['imageURL'] = imageUrl
274
275 docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo)
276 return docinfo
277
278
279 def getDocinfo(self, mode, url):
280 """returns docinfo depending on mode"""
281 zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"mode: %s, url: %s"%(mode,url))
282 # look for cached docinfo in session
283 if self.REQUEST.SESSION.has_key('docinfo'):
284 docinfo = self.REQUEST.SESSION['docinfo']
285 # check if its still current
286 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
287 zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo in session: %s"%docinfo)
288 return docinfo
289 # new docinfo
290 docinfo = {'mode': mode, 'url': url}
291 if mode=="texttool": #index.meta with texttool information
292 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
293 elif mode=="imagepath":
294 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
295 else:
296 zLOG.LOG("documentViewer (getdocinfo)", zLOG.ERROR,"unknown mode!")
297 zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo: %s"%docinfo)
298 self.REQUEST.SESSION['docinfo'] = docinfo
299 return docinfo
300
301
302 def getPageinfo(self, start, current):
303 """returns pageinfo with the given parameters"""
304 pageinfo = {}
305 pageinfo['start'] = start
306 pageinfo['current'] = current
307 return pageinfo
308
230 def text(self,mode,url,pn): 309 def text(self,mode,url,pn):
231 """give text""" 310 """give text"""
232 if mode=="texttool": #index.meta with texttool information 311 if mode=="texttool": #index.meta with texttool information
233 (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) 312 (viewerUrl,imagepath,textpath)=parseUrlTextTool(url)
234 313
277 # 356 #
278 # for x in list: 357 # for x in list:
279 # PrettyPrint(x) 358 # PrettyPrint(x)
280 # 359 #
281 # return list 360 # return list
282 # 361 #
362
283 def image(self,mode,url,pn): 363 def image(self,mode,url,pn):
284 """give image out""" 364 """give image out"""
285 if mode=="texttool": #index.meta with texttool information 365 if mode=="texttool": #index.meta with texttool information
286 (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) 366 (viewerUrl,imagepath,textpath)=parseUrlTextTool(url)
287 if not viewerUrl: 367 if not viewerUrl:
294 url=self.imageViewerUrl+"pn=%s&fn=%s"%(pn,url) 374 url=self.imageViewerUrl+"pn=%s&fn=%s"%(pn,url)
295 ret="""<iframe height="100%%" width="100%%" src="%s"/>"""%url 375 ret="""<iframe height="100%%" width="100%%" src="%s"/>"""%url
296 return url 376 return url
297 377
298 378
299 def thumbs(self,mode,url,start): 379 def findDigilibUrl(self):
300 """give thumbs out""" 380 """try to get the digilib URL from zogilib"""
301 if mode=="texttool": #index.meta with texttool information 381 url = self.imageViewerUrl[:-1] + "/getScalerUrl"
302 return self.textToolThumb(url,int(start)) 382 try:
303 elif mode=="imagepath": 383 scaler = urlopen(url).read()
304 return self.imagePathThumb(url,int(start)) 384 return scaler.replace("/servlet/Scaler?", "")
305 385 except:
306 security.declareProtected('View','index_html') 386 return None
307 387
308 388 def changeDocumentViewer(self,imageViewerUrl,title="",digilibBaseUrl=None,RESPONSE=None):
309 def index_html(self,mode,url,start=0,pn=1): 389 """init document viewer"""
310 ''' 390 self.title=title
311 view it 391 self.imageViewerUrl=imageViewerUrl
312 @param mode: defines which type of document is behind url 392 self.digilibBaseUrl = digilibBaseUrl
313 @param url: url which contains display information 393
314 ''' 394 if RESPONSE is not None:
315 395 RESPONSE.redirect('manage_main')
316 396
317 pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','documentViewer_template.zpt')).__of__(self) 397
318 return pt(mode=mode,url=url,start=start,pn=pn)
319
320 398
321 399
322 # security.declareProtected('View management screens','renameImageForm') 400 # security.declareProtected('View management screens','renameImageForm')
323 401
324 def manage_AddDocumentViewerForm(self): 402 def manage_AddDocumentViewerForm(self):
325 """add the viewer form""" 403 """add the viewer form"""
326 pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','addDocumentViewer.zpt')).__of__(self) 404 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
327 return pt() 405 return pt()
328 406
329 def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None): 407 def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None):
330 """add the viewer""" 408 """add the viewer"""
331 newObj=documentViewer(id,imageViewerUrl,title) 409 newObj=documentViewer(id,imageViewerUrl,title)
332 self._setObject(id,newObj) 410 self._setObject(id,newObj)
333 411
334 if RESPONSE is not None: 412 if RESPONSE is not None:
335 RESPONSE.redirect('manage_main') 413 RESPONSE.redirect('manage_main')
336 414
415
416 ##
417 ## DocumentViewerTemplate class
418 ##
419 class DocumentViewerTemplate(ZopePageTemplate):
420 """Template for document viewer"""
421 meta_type="DocumentViewer Template"
422
423
424 def manage_addDocumentViewerTemplateForm(self):
425 """Form for adding"""
426 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
427 return pt()
428
429 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
430 REQUEST=None, submit=None):
431 "Add a Page Template with optional file content."
432
433 self._setObject(id, DocumentViewerTemplate(id))
434 ob = getattr(self, id)
435 ob.pt_edit(open(os.path.join(package_home(globals()),'zpt/viewer_main.zpt')).read(),None)
436 if title:
437 ob.pt_setTitle(title)
438 try:
439 u = self.DestinationURL()
440 except AttributeError:
441 u = REQUEST['URL1']
442
443 u = "%s/%s" % (u, urllib.quote(id))
444 REQUEST.RESPONSE.redirect(u+'/manage_main')
445 return ''
446
447
448