Mercurial > hg > documentViewer
annotate documentViewer.py @ 70:0049d64aa464
filepath introduced
author | dwinter |
---|---|
date | Tue, 04 Nov 2008 20:51:35 +0100 |
parents | b8457fc33446 |
children | 6412c45dff58 |
rev | line source |
---|---|
46 | 1 |
2 | |
0 | 3 from OFS.Folder import Folder |
4 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate | |
52 | 5 from Products.PageTemplates.PageTemplateFile import PageTemplateFile |
0 | 6 from AccessControl import ClassSecurityInfo |
32 | 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 | |
38 | 12 from Ft.Xml import EMPTY_NAMESPACE, Parse |
0 | 13 |
14 import Ft.Xml.XPath | |
15 | |
16 import os.path | |
31 | 17 import sys |
0 | 18 import cgi |
19 import urllib | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
20 import logging |
61 | 21 import math |
52 | 22 |
46 | 23 import urlparse |
0 | 24 |
52 | 25 def logger(txt,method,txt2): |
26 """logging""" | |
27 logging.info(txt+ txt2) | |
28 | |
29 | |
25 | 30 def getInt(number, default=0): |
31 """returns always an int (0 in case of problems)""" | |
32 try: | |
33 return int(number) | |
34 except: | |
62 | 35 return int(default) |
25 | 36 |
0 | 37 def getTextFromNode(nodename): |
46 | 38 """get the cdata content of a node""" |
32 | 39 if nodename is None: |
40 return "" | |
0 | 41 nodelist=nodename.childNodes |
42 rc = "" | |
43 for node in nodelist: | |
44 if node.nodeType == node.TEXT_NODE: | |
45 rc = rc + node.data | |
46 return rc | |
47 | |
35 | 48 |
49 def getParentDir(path): | |
50 """returns pathname shortened by one""" | |
51 return '/'.join(path.split('/')[0:-1]) | |
52 | |
53 | |
0 | 54 import socket |
55 | |
32 | 56 def urlopen(url,timeout=2): |
0 | 57 """urlopen mit timeout""" |
32 | 58 socket.setdefaulttimeout(timeout) |
0 | 59 ret=urllib.urlopen(url) |
60 socket.setdefaulttimeout(5) | |
61 return ret | |
62 | |
63 | |
22 | 64 ## |
65 ## documentViewer class | |
66 ## | |
67 class documentViewer(Folder): | |
0 | 68 """document viewer""" |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
69 #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" |
46 | 70 |
0 | 71 meta_type="Document viewer" |
72 | |
73 security=ClassSecurityInfo() | |
22 | 74 manage_options=Folder.manage_options+( |
0 | 75 {'label':'main config','action':'changeDocumentViewerForm'}, |
76 ) | |
77 | |
22 | 78 # templates and forms |
79 viewer_main = PageTemplateFile('zpt/viewer_main', globals()) | |
80 thumbs_main = PageTemplateFile('zpt/thumbs_main', globals()) | |
81 image_main = PageTemplateFile('zpt/image_main', globals()) | |
82 head_main = PageTemplateFile('zpt/head_main', globals()) | |
83 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | |
57 | 84 info_xml = PageTemplateFile('zpt/info_xml', globals()) |
22 | 85 |
68 | 86 thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
22 | 87 security.declareProtected('View management screens','changeDocumentViewerForm') |
88 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
89 | |
0 | 90 |
46 | 91 def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): |
0 | 92 """init document viewer""" |
93 self.id=id | |
94 self.title=title | |
95 self.imageViewerUrl=imageViewerUrl | |
46 | 96 self.textViewerUrl=textViewerUrl |
97 | |
25 | 98 if not digilibBaseUrl: |
22 | 99 self.digilibBaseUrl = self.findDigilibUrl() |
25 | 100 else: |
101 self.digilibBaseUrl = digilibBaseUrl | |
102 self.thumbcols = thumbcols | |
103 self.thumbrows = thumbrows | |
32 | 104 # authgroups is list of authorized groups (delimited by ,) |
105 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] | |
22 | 106 # add template folder so we can always use template.something |
107 self.manage_addFolder('template') | |
108 | |
109 | |
68 | 110 security.declareProtected('View','thumbs_rss') |
111 def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): | |
112 ''' | |
113 view it | |
114 @param mode: defines how to access the document behind url | |
115 @param url: url which contains display information | |
116 @param viewMode: if images display images, if text display text, default is images (text,images or auto) | |
117 | |
118 ''' | |
119 logging.info("HHHHHHHHHHHHHH:load the rss") | |
120 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) | |
121 | |
122 if not hasattr(self, 'template'): | |
123 # create template folder if it doesn't exist | |
124 self.manage_addFolder('template') | |
125 | |
126 if not self.digilibBaseUrl: | |
127 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
128 | |
129 docinfo = self.getDocinfo(mode=mode,url=url) | |
130 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) | |
131 pt = getattr(self.template, 'thumbs_main_rss') | |
132 | |
133 if viewMode=="auto": # automodus gewaehlt | |
134 if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert | |
135 viewMode="text" | |
136 else: | |
137 viewMode="images" | |
138 | |
139 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | |
140 | |
22 | 141 security.declareProtected('View','index_html') |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
142 def index_html(self,mode,url,viewMode="auto",start=None,pn=1): |
22 | 143 ''' |
144 view it | |
57 | 145 @param mode: defines how to access the document behind url |
22 | 146 @param url: url which contains display information |
57 | 147 @param viewMode: if images display images, if text display text, default is images (text,images or auto) |
46 | 148 |
22 | 149 ''' |
0 | 150 |
52 | 151 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
22 | 152 |
153 if not hasattr(self, 'template'): | |
154 # create template folder if it doesn't exist | |
155 self.manage_addFolder('template') | |
156 | |
157 if not self.digilibBaseUrl: | |
158 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
159 | |
25 | 160 docinfo = self.getDocinfo(mode=mode,url=url) |
161 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) | |
22 | 162 pt = getattr(self.template, 'viewer_main') |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
163 |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
164 if viewMode=="auto": # automodus gewaehlt |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
165 if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
166 viewMode="text" |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
167 else: |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
168 viewMode="images" |
52 | 169 |
46 | 170 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) |
0 | 171 |
172 | |
25 | 173 def getLink(self,param=None,val=None): |
174 """link to documentviewer with parameter param set to val""" | |
35 | 175 params=self.REQUEST.form.copy() |
25 | 176 if param is not None: |
31 | 177 if val is None: |
178 if params.has_key(param): | |
179 del params[param] | |
25 | 180 else: |
35 | 181 params[param] = str(val) |
31 | 182 |
35 | 183 # quote values and assemble into query string |
184 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
185 url=self.REQUEST['URL1']+"?"+ps | |
25 | 186 return url |
187 | |
68 | 188 def getLinkAmp(self,param=None,val=None): |
189 """link to documentviewer with parameter param set to val""" | |
190 params=self.REQUEST.form.copy() | |
191 if param is not None: | |
192 if val is None: | |
193 if params.has_key(param): | |
194 del params[param] | |
195 else: | |
196 params[param] = str(val) | |
197 | |
198 # quote values and assemble into query string | |
199 logging.info("XYXXXXX: %s"%repr(params.items())) | |
200 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
201 url=self.REQUEST['URL1']+"?"+ps | |
202 return url | |
57 | 203 def getInfo_xml(self,url,mode): |
204 """returns info about the document as XML""" | |
205 | |
206 if not self.digilibBaseUrl: | |
207 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
208 | |
209 docinfo = self.getDocinfo(mode=mode,url=url) | |
210 pt = getattr(self.template, 'info_xml') | |
211 return pt(docinfo=docinfo) | |
212 | |
0 | 213 |
22 | 214 def getStyle(self, idx, selected, style=""): |
25 | 215 """returns a string with the given style and append 'sel' if path == selected.""" |
52 | 216 #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
22 | 217 if idx == selected: |
218 return style + 'sel' | |
219 else: | |
35 | 220 return style |
57 | 221 |
35 | 222 |
223 def isAccessible(self, docinfo): | |
32 | 224 """returns if access to the resource is granted""" |
225 access = docinfo.get('accessType', None) | |
52 | 226 logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) |
45 | 227 if access is not None and access == 'free': |
52 | 228 logger("documentViewer (accessOK)", logging.INFO, "access is free") |
32 | 229 return True |
45 | 230 elif access is None or access in self.authgroups: |
35 | 231 # only local access -- only logged in users |
232 user = getSecurityManager().getUser() | |
233 if user is not None: | |
234 #print "user: ", user | |
235 return (user.getUserName() != "Anonymous User") | |
236 else: | |
237 return False | |
32 | 238 |
52 | 239 logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) |
32 | 240 return False |
35 | 241 |
32 | 242 |
31 | 243 def getDirinfoFromDigilib(self,path,docinfo=None): |
29 | 244 """gibt param von dlInfo aus""" |
40 | 245 num_retries = 3 |
31 | 246 if docinfo is None: |
247 docinfo = {} | |
248 | |
40 | 249 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
29 | 250 |
52 | 251 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) |
29 | 252 |
40 | 253 for cnt in range(num_retries): |
35 | 254 try: |
40 | 255 # dom = NonvalidatingReader.parseUri(imageUrl) |
256 txt=urllib.urlopen(infoUrl).read() | |
257 dom = Parse(txt) | |
35 | 258 break |
259 except: | |
52 | 260 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) |
35 | 261 else: |
40 | 262 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
29 | 263 |
37 | 264 sizes=dom.xpath("//dir/size") |
52 | 265 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) |
29 | 266 |
37 | 267 if sizes: |
268 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
31 | 269 else: |
270 docinfo['numPages'] = 0 | |
271 | |
272 return docinfo | |
32 | 273 |
29 | 274 |
35 | 275 def getIndexMeta(self, url): |
276 """returns dom of index.meta document at url""" | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
277 num_retries = 3 |
35 | 278 dom = None |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
279 metaUrl = None |
35 | 280 if url.startswith("http://"): |
281 # real URL | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
282 metaUrl = url |
35 | 283 else: |
284 # online path | |
285 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
40 | 286 metaUrl=server+url.replace("/mpiwg/online","") |
35 | 287 if not metaUrl.endswith("index.meta"): |
288 metaUrl += "/index.meta" | |
46 | 289 print metaUrl |
40 | 290 for cnt in range(num_retries): |
35 | 291 try: |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
292 # patch dirk encoding fehler treten dann nicht mehr auf |
38 | 293 # dom = NonvalidatingReader.parseUri(metaUrl) |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
294 txt=urllib.urlopen(metaUrl).read() |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
295 dom = Parse(txt) |
40 | 296 break |
35 | 297 except: |
52 | 298 logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
299 |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
300 if dom is None: |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
301 raise IOError("Unable to read index meta from %s"%(url)) |
35 | 302 |
303 return dom | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
304 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
305 def getPresentationInfoXML(self, url): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
306 """returns dom of info.xml document at url""" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
307 num_retries = 3 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
308 dom = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
309 metaUrl = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
310 if url.startswith("http://"): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
311 # real URL |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
312 metaUrl = url |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
313 else: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
314 # online path |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
315 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
316 metaUrl=server+url.replace("/mpiwg/online","") |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
317 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
318 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
319 for cnt in range(num_retries): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
320 try: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
321 # patch dirk encoding fehler treten dann nicht mehr auf |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
322 # dom = NonvalidatingReader.parseUri(metaUrl) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
323 txt=urllib.urlopen(metaUrl).read() |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
324 dom = Parse(txt) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
325 break |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
326 except: |
52 | 327 logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
328 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
329 if dom is None: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
330 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
331 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
332 return dom |
35 | 333 |
334 | |
70 | 335 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 336 """gets authorization info from the index.meta file at path or given by dom""" |
52 | 337 logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
32 | 338 |
339 access = None | |
340 | |
341 if docinfo is None: | |
342 docinfo = {} | |
343 | |
344 if dom is None: | |
70 | 345 for x in range(cut+1): |
346 path=getParentDir(path) | |
347 dom = self.getIndexMeta(path) | |
46 | 348 |
32 | 349 acctype = dom.xpath("//access-conditions/access/@type") |
350 if acctype and (len(acctype)>0): | |
351 access=acctype[0].value | |
35 | 352 if access in ['group', 'institution']: |
32 | 353 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
354 | |
355 docinfo['accessType'] = access | |
356 return docinfo | |
29 | 357 |
32 | 358 |
70 | 359 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
35 | 360 """gets bibliographical info from the index.meta file at path or given by dom""" |
59 | 361 logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
20 | 362 |
22 | 363 if docinfo is None: |
364 docinfo = {} | |
365 | |
366 if dom is None: | |
70 | 367 for x in range(cut+1): |
368 path=getParentDir(path) | |
369 dom = self.getIndexMeta(path) | |
35 | 370 |
59 | 371 # put in all raw bib fields as dict "bib" |
372 bib = dom.xpath("//bib/*") | |
373 if bib and len(bib)>0: | |
374 bibinfo = {} | |
375 for e in bib: | |
376 bibinfo[e.localName] = getTextFromNode(e) | |
377 docinfo['bib'] = bibinfo | |
378 | |
379 # extract some fields (author, title, year) according to their mapping | |
25 | 380 metaData=self.metadata.main.meta.bib |
381 bibtype=dom.xpath("//bib/@type") | |
382 if bibtype and (len(bibtype)>0): | |
383 bibtype=bibtype[0].value | |
20 | 384 else: |
25 | 385 bibtype="generic" |
59 | 386 |
25 | 387 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
59 | 388 docinfo['bib_type'] = bibtype |
25 | 389 bibmap=metaData.generateMappingForType(bibtype) |
32 | 390 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
31 | 391 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
63 | 392 try: |
393 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) | |
394 except: pass | |
395 try: | |
396 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
397 except: pass | |
398 try: | |
399 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
400 except: pass | |
59 | 401 logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
52 | 402 try: |
403 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
404 except: | |
405 docinfo['lang']='' | |
59 | 406 |
22 | 407 return docinfo |
408 | |
409 | |
32 | 410 def getDocinfoFromTextTool(self,url,dom=None,docinfo=None): |
22 | 411 """parse texttool tag in index meta""" |
52 | 412 logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url)) |
22 | 413 if docinfo is None: |
414 docinfo = {} | |
415 | |
52 | 416 if docinfo.get('lang',None) is None: |
417 docinfo['lang']='' # default keine Sprache gesetzt | |
32 | 418 if dom is None: |
35 | 419 dom = self.getIndexMeta(url) |
32 | 420 |
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
421 archivePath = None |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
422 archiveName = None |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
423 |
32 | 424 archiveNames=dom.xpath("//resource/name") |
425 if archiveNames and (len(archiveNames)>0): | |
426 archiveName=getTextFromNode(archiveNames[0]) | |
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
427 else: |
52 | 428 logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/name missing in: %s"%(url)) |
22 | 429 |
430 archivePaths=dom.xpath("//resource/archive-path") | |
431 if archivePaths and (len(archivePaths)>0): | |
432 archivePath=getTextFromNode(archivePaths[0]) | |
32 | 433 # clean up archive path |
434 if archivePath[0] != '/': | |
435 archivePath = '/' + archivePath | |
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
436 if archiveName and (not archivePath.endswith(archiveName)): |
32 | 437 archivePath += "/" + archiveName |
22 | 438 else: |
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
439 # try to get archive-path from url |
52 | 440 logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/archive-path missing in: %s"%(url)) |
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
441 if (not url.startswith('http')): |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
442 archivePath = url.replace('index.meta', '') |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
443 |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
444 if archivePath is None: |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
445 # we balk without archive-path |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
446 raise IOError("Missing archive-path (for text-tool) in %s"%(url)) |
22 | 447 |
35 | 448 imageDirs=dom.xpath("//texttool/image") |
449 if imageDirs and (len(imageDirs)>0): | |
450 imageDir=getTextFromNode(imageDirs[0]) | |
22 | 451 else: |
52 | 452 # we balk with no image tag / not necessary anymore because textmode is now standard |
453 #raise IOError("No text-tool info in %s"%(url)) | |
454 imageDir="" | |
455 docinfo['numPages']=1 # im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht | |
456 | |
457 docinfo['imagePath'] = "" # keine Bilder | |
458 docinfo['imageURL'] = "" | |
459 | |
35 | 460 if imageDir and archivePath: |
461 #print "image: ", imageDir, " archivepath: ", archivePath | |
462 imageDir=os.path.join(archivePath,imageDir) | |
463 imageDir=imageDir.replace("/mpiwg/online",'') | |
464 docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo) | |
465 docinfo['imagePath'] = imageDir | |
466 docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir | |
22 | 467 |
468 viewerUrls=dom.xpath("//texttool/digiliburlprefix") | |
469 if viewerUrls and (len(viewerUrls)>0): | |
470 viewerUrl=getTextFromNode(viewerUrls[0]) | |
31 | 471 docinfo['viewerURL'] = viewerUrl |
22 | 472 |
473 textUrls=dom.xpath("//texttool/text") | |
474 if textUrls and (len(textUrls)>0): | |
475 textUrl=getTextFromNode(textUrls[0]) | |
49
a10fff6199b0
verbesserung f?r text unterst?tzung, text kann jetzt aus url kommen, sprache bisher nur deutsch
dwinter
parents:
46
diff
changeset
|
476 if urlparse.urlparse(textUrl)[0]=="": #keine url |
a10fff6199b0
verbesserung f?r text unterst?tzung, text kann jetzt aus url kommen, sprache bisher nur deutsch
dwinter
parents:
46
diff
changeset
|
477 textUrl=os.path.join(archivePath,textUrl) |
65
c048559460a3
fix problems with full text paths starting with /mpiwg/online
casties
parents:
63
diff
changeset
|
478 # fix URLs starting with /mpiwg/online |
c048559460a3
fix problems with full text paths starting with /mpiwg/online
casties
parents:
63
diff
changeset
|
479 if textUrl.startswith("/mpiwg/online"): |
c048559460a3
fix problems with full text paths starting with /mpiwg/online
casties
parents:
63
diff
changeset
|
480 textUrl = textUrl.replace("/mpiwg/online",'',1) |
c048559460a3
fix problems with full text paths starting with /mpiwg/online
casties
parents:
63
diff
changeset
|
481 |
31 | 482 docinfo['textURL'] = textUrl |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
483 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
484 presentationUrls=dom.xpath("//texttool/presentation") |
52 | 485 docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get info von bib tag |
486 | |
487 if presentationUrls and (len(presentationUrls)>0): # ueberschreibe diese durch presentation informationen | |
63 | 488 # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
489 # durch den relativen Pfad auf die presentation infos |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
490 presentationUrl=url.replace('index.meta',getTextFromNode(presentationUrls[0])) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
491 docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom) |
52 | 492 |
55
ba8917b93c84
fixed bug in fix for missing getauthinfo in getdocinfofromtexttool
casties
parents:
54
diff
changeset
|
493 docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info |
22 | 494 return docinfo |
495 | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
496 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
497 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
498 """gets the bibliographical information from the preseantion entry in texttools |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
499 """ |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
500 dom=self.getPresentationInfoXML(url) |
62 | 501 try: |
502 docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) | |
503 except: | |
504 pass | |
505 try: | |
506 docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) | |
507 except: | |
508 pass | |
509 try: | |
510 docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) | |
511 except: | |
512 pass | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
513 return docinfo |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
514 |
70 | 515 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
22 | 516 """path ist the path to the images it assumes that the index.meta file is one level higher.""" |
52 | 517 logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) |
22 | 518 if docinfo is None: |
519 docinfo = {} | |
29 | 520 path=path.replace("/mpiwg/online","") |
22 | 521 docinfo['imagePath'] = path |
31 | 522 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo) |
523 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path | |
22 | 524 docinfo['imageURL'] = imageUrl |
525 | |
70 | 526 docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo,cut=cut) |
527 docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo,cut=cut) | |
22 | 528 return docinfo |
20 | 529 |
22 | 530 |
531 def getDocinfo(self, mode, url): | |
532 """returns docinfo depending on mode""" | |
52 | 533 logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) |
22 | 534 # look for cached docinfo in session |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
535 if self.REQUEST.SESSION.has_key('docinfo'): |
22 | 536 docinfo = self.REQUEST.SESSION['docinfo'] |
537 # check if its still current | |
538 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
52 | 539 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) |
22 | 540 return docinfo |
541 # new docinfo | |
542 docinfo = {'mode': mode, 'url': url} | |
543 if mode=="texttool": #index.meta with texttool information | |
544 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
545 elif mode=="imagepath": | |
546 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
70 | 547 elif mode=="filepath": |
548 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) | |
22 | 549 else: |
52 | 550 logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") |
37 | 551 raise ValueError("Unknown mode %s"%(mode)) |
552 | |
52 | 553 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
22 | 554 self.REQUEST.SESSION['docinfo'] = docinfo |
555 return docinfo | |
20 | 556 |
557 | |
25 | 558 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None): |
22 | 559 """returns pageinfo with the given parameters""" |
560 pageinfo = {} | |
25 | 561 current = getInt(current) |
562 pageinfo['current'] = current | |
563 rows = int(rows or self.thumbrows) | |
564 pageinfo['rows'] = rows | |
565 cols = int(cols or self.thumbcols) | |
566 pageinfo['cols'] = cols | |
567 grpsize = cols * rows | |
568 pageinfo['groupsize'] = grpsize | |
61 | 569 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
570 # int(current / grpsize) * grpsize +1)) | |
22 | 571 pageinfo['start'] = start |
25 | 572 pageinfo['end'] = start + grpsize |
573 if docinfo is not None: | |
574 np = int(docinfo['numPages']) | |
575 pageinfo['end'] = min(pageinfo['end'], np) | |
576 pageinfo['numgroups'] = int(np / grpsize) | |
577 if np % grpsize > 0: | |
578 pageinfo['numgroups'] += 1 | |
579 | |
22 | 580 return pageinfo |
581 | |
0 | 582 def text(self,mode,url,pn): |
583 """give text""" | |
584 if mode=="texttool": #index.meta with texttool information | |
585 (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) | |
586 | |
35 | 587 #print textpath |
0 | 588 try: |
589 dom = NonvalidatingReader.parseUri(textpath) | |
590 except: | |
591 return None | |
592 | |
593 list=[] | |
594 nodes=dom.xpath("//pb") | |
595 | |
596 node=nodes[int(pn)-1] | |
597 | |
598 p=node | |
599 | |
600 while p.tagName!="p": | |
601 p=p.parentNode | |
602 | |
603 | |
604 endNode=nodes[int(pn)] | |
605 | |
606 | |
607 e=endNode | |
608 | |
609 while e.tagName!="p": | |
610 e=e.parentNode | |
611 | |
612 | |
613 next=node.parentNode | |
614 | |
615 #sammle s | |
616 while next and (next!=endNode.parentNode): | |
617 list.append(next) | |
618 next=next.nextSibling | |
619 list.append(endNode.parentNode) | |
620 | |
621 if p==e:# beide im selben paragraphen | |
20 | 622 pass |
623 # else: | |
624 # next=p | |
625 # while next!=e: | |
626 # print next,e | |
627 # list.append(next) | |
628 # next=next.nextSibling | |
629 # | |
630 # for x in list: | |
631 # PrettyPrint(x) | |
632 # | |
633 # return list | |
22 | 634 # |
635 | |
636 def findDigilibUrl(self): | |
637 """try to get the digilib URL from zogilib""" | |
638 url = self.imageViewerUrl[:-1] + "/getScalerUrl" | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
639 #print urlparse.urlparse(url)[0] |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
640 #print urlparse.urljoin(self.absolute_url(),url) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
641 logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0]) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
642 logging.info("finddigiliburl: %s"%urlparse.urljoin(self.absolute_url(),url)) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
643 |
22 | 644 try: |
46 | 645 if urlparse.urlparse(url)[0]=='': #relative path |
646 url=urlparse.urljoin(self.absolute_url()+"/",url) | |
647 | |
22 | 648 scaler = urlopen(url).read() |
649 return scaler.replace("/servlet/Scaler?", "") | |
650 except: | |
651 return None | |
652 | |
46 | 653 def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): |
22 | 654 """init document viewer""" |
655 self.title=title | |
656 self.imageViewerUrl=imageViewerUrl | |
46 | 657 self.textViewerUrl=textViewerUrl |
22 | 658 self.digilibBaseUrl = digilibBaseUrl |
25 | 659 self.thumbrows = thumbrows |
660 self.thumbcols = thumbcols | |
32 | 661 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
22 | 662 if RESPONSE is not None: |
663 RESPONSE.redirect('manage_main') | |
0 | 664 |
665 | |
666 | |
667 | |
668 # security.declareProtected('View management screens','renameImageForm') | |
669 | |
670 def manage_AddDocumentViewerForm(self): | |
671 """add the viewer form""" | |
22 | 672 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 673 return pt() |
674 | |
46 | 675 def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None): |
0 | 676 """add the viewer""" |
46 | 677 newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl) |
0 | 678 self._setObject(id,newObj) |
679 | |
680 if RESPONSE is not None: | |
681 RESPONSE.redirect('manage_main') | |
22 | 682 |
683 | |
684 ## | |
685 ## DocumentViewerTemplate class | |
686 ## | |
687 class DocumentViewerTemplate(ZopePageTemplate): | |
688 """Template for document viewer""" | |
689 meta_type="DocumentViewer Template" | |
690 | |
691 | |
692 def manage_addDocumentViewerTemplateForm(self): | |
693 """Form for adding""" | |
694 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
695 return pt() | |
696 | |
697 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
698 REQUEST=None, submit=None): | |
699 "Add a Page Template with optional file content." | |
700 | |
701 self._setObject(id, DocumentViewerTemplate(id)) | |
702 ob = getattr(self, id) | |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
703 txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() |
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
704 logging.info("txt %s:"%txt) |
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
705 ob.pt_edit(txt,"text/html") |
22 | 706 if title: |
707 ob.pt_setTitle(title) | |
708 try: | |
709 u = self.DestinationURL() | |
710 except AttributeError: | |
711 u = REQUEST['URL1'] | |
712 | |
713 u = "%s/%s" % (u, urllib.quote(id)) | |
714 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
715 return '' | |
716 | |
717 | |
41 | 718 |