Mercurial > hg > documentViewer
annotate documentViewer.py @ 62:8a16ea8db858
fixed bug in getInt
author | casties |
---|---|
date | Fri, 15 Jun 2007 16:16:27 +0200 |
parents | f3d2f240692c |
children | 4a17b755bfc7 |
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 |
86 security.declareProtected('View management screens','changeDocumentViewerForm') | |
87 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
88 | |
0 | 89 |
46 | 90 def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): |
0 | 91 """init document viewer""" |
92 self.id=id | |
93 self.title=title | |
94 self.imageViewerUrl=imageViewerUrl | |
46 | 95 self.textViewerUrl=textViewerUrl |
96 | |
25 | 97 if not digilibBaseUrl: |
22 | 98 self.digilibBaseUrl = self.findDigilibUrl() |
25 | 99 else: |
100 self.digilibBaseUrl = digilibBaseUrl | |
101 self.thumbcols = thumbcols | |
102 self.thumbrows = thumbrows | |
32 | 103 # authgroups is list of authorized groups (delimited by ,) |
104 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] | |
22 | 105 # add template folder so we can always use template.something |
106 self.manage_addFolder('template') | |
107 | |
108 | |
109 security.declareProtected('View','index_html') | |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
110 def index_html(self,mode,url,viewMode="auto",start=None,pn=1): |
22 | 111 ''' |
112 view it | |
57 | 113 @param mode: defines how to access the document behind url |
22 | 114 @param url: url which contains display information |
57 | 115 @param viewMode: if images display images, if text display text, default is images (text,images or auto) |
46 | 116 |
22 | 117 ''' |
0 | 118 |
52 | 119 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
22 | 120 |
121 if not hasattr(self, 'template'): | |
122 # create template folder if it doesn't exist | |
123 self.manage_addFolder('template') | |
124 | |
125 if not self.digilibBaseUrl: | |
126 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
127 | |
25 | 128 docinfo = self.getDocinfo(mode=mode,url=url) |
129 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) | |
22 | 130 pt = getattr(self.template, 'viewer_main') |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
131 |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
132 if viewMode=="auto": # automodus gewaehlt |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
133 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
|
134 viewMode="text" |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
135 else: |
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
136 viewMode="images" |
52 | 137 |
46 | 138 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) |
0 | 139 |
140 | |
25 | 141 def getLink(self,param=None,val=None): |
142 """link to documentviewer with parameter param set to val""" | |
35 | 143 params=self.REQUEST.form.copy() |
25 | 144 if param is not None: |
31 | 145 if val is None: |
146 if params.has_key(param): | |
147 del params[param] | |
25 | 148 else: |
35 | 149 params[param] = str(val) |
31 | 150 |
35 | 151 # quote values and assemble into query string |
152 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
153 url=self.REQUEST['URL1']+"?"+ps | |
25 | 154 return url |
155 | |
57 | 156 |
157 def getInfo_xml(self,url,mode): | |
158 """returns info about the document as XML""" | |
159 | |
160 if not self.digilibBaseUrl: | |
161 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
162 | |
163 docinfo = self.getDocinfo(mode=mode,url=url) | |
164 pt = getattr(self.template, 'info_xml') | |
165 return pt(docinfo=docinfo) | |
166 | |
0 | 167 |
22 | 168 def getStyle(self, idx, selected, style=""): |
25 | 169 """returns a string with the given style and append 'sel' if path == selected.""" |
52 | 170 #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
22 | 171 if idx == selected: |
172 return style + 'sel' | |
173 else: | |
35 | 174 return style |
57 | 175 |
35 | 176 |
177 def isAccessible(self, docinfo): | |
32 | 178 """returns if access to the resource is granted""" |
179 access = docinfo.get('accessType', None) | |
52 | 180 logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) |
45 | 181 if access is not None and access == 'free': |
52 | 182 logger("documentViewer (accessOK)", logging.INFO, "access is free") |
32 | 183 return True |
45 | 184 elif access is None or access in self.authgroups: |
35 | 185 # only local access -- only logged in users |
186 user = getSecurityManager().getUser() | |
187 if user is not None: | |
188 #print "user: ", user | |
189 return (user.getUserName() != "Anonymous User") | |
190 else: | |
191 return False | |
32 | 192 |
52 | 193 logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) |
32 | 194 return False |
35 | 195 |
32 | 196 |
31 | 197 def getDirinfoFromDigilib(self,path,docinfo=None): |
29 | 198 """gibt param von dlInfo aus""" |
40 | 199 num_retries = 3 |
31 | 200 if docinfo is None: |
201 docinfo = {} | |
202 | |
40 | 203 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
29 | 204 |
52 | 205 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) |
29 | 206 |
40 | 207 for cnt in range(num_retries): |
35 | 208 try: |
40 | 209 # dom = NonvalidatingReader.parseUri(imageUrl) |
210 txt=urllib.urlopen(infoUrl).read() | |
211 dom = Parse(txt) | |
35 | 212 break |
213 except: | |
52 | 214 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) |
35 | 215 else: |
40 | 216 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
29 | 217 |
37 | 218 sizes=dom.xpath("//dir/size") |
52 | 219 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) |
29 | 220 |
37 | 221 if sizes: |
222 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
31 | 223 else: |
224 docinfo['numPages'] = 0 | |
225 | |
226 return docinfo | |
32 | 227 |
29 | 228 |
35 | 229 def getIndexMeta(self, url): |
230 """returns dom of index.meta document at url""" | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
231 num_retries = 3 |
35 | 232 dom = None |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
233 metaUrl = None |
35 | 234 if url.startswith("http://"): |
235 # real URL | |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
236 metaUrl = url |
35 | 237 else: |
238 # online path | |
239 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
40 | 240 metaUrl=server+url.replace("/mpiwg/online","") |
35 | 241 if not metaUrl.endswith("index.meta"): |
242 metaUrl += "/index.meta" | |
46 | 243 print metaUrl |
40 | 244 for cnt in range(num_retries): |
35 | 245 try: |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
246 # patch dirk encoding fehler treten dann nicht mehr auf |
38 | 247 # dom = NonvalidatingReader.parseUri(metaUrl) |
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
248 txt=urllib.urlopen(metaUrl).read() |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
249 dom = Parse(txt) |
40 | 250 break |
35 | 251 except: |
52 | 252 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
|
253 |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
254 if dom is None: |
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
255 raise IOError("Unable to read index meta from %s"%(url)) |
35 | 256 |
257 return dom | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
258 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
259 def getPresentationInfoXML(self, url): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
260 """returns dom of info.xml document at url""" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
261 num_retries = 3 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
262 dom = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
263 metaUrl = None |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
264 if url.startswith("http://"): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
265 # real URL |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
266 metaUrl = url |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
267 else: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
268 # online path |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
269 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
270 metaUrl=server+url.replace("/mpiwg/online","") |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
271 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
272 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
273 for cnt in range(num_retries): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
274 try: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
275 # patch dirk encoding fehler treten dann nicht mehr auf |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
276 # dom = NonvalidatingReader.parseUri(metaUrl) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
277 txt=urllib.urlopen(metaUrl).read() |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
278 dom = Parse(txt) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
279 break |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
280 except: |
52 | 281 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
|
282 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
283 if dom is None: |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
284 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
285 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
286 return dom |
35 | 287 |
288 | |
32 | 289 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None): |
35 | 290 """gets authorization info from the index.meta file at path or given by dom""" |
52 | 291 logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
32 | 292 |
293 access = None | |
294 | |
295 if docinfo is None: | |
296 docinfo = {} | |
297 | |
298 if dom is None: | |
35 | 299 dom = self.getIndexMeta(getParentDir(path)) |
46 | 300 |
32 | 301 acctype = dom.xpath("//access-conditions/access/@type") |
302 if acctype and (len(acctype)>0): | |
303 access=acctype[0].value | |
35 | 304 if access in ['group', 'institution']: |
32 | 305 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
306 | |
307 docinfo['accessType'] = access | |
308 return docinfo | |
29 | 309 |
32 | 310 |
22 | 311 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None): |
35 | 312 """gets bibliographical info from the index.meta file at path or given by dom""" |
59 | 313 logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
20 | 314 |
22 | 315 if docinfo is None: |
316 docinfo = {} | |
317 | |
318 if dom is None: | |
35 | 319 dom = self.getIndexMeta(getParentDir(path)) |
320 | |
59 | 321 # put in all raw bib fields as dict "bib" |
322 bib = dom.xpath("//bib/*") | |
323 if bib and len(bib)>0: | |
324 bibinfo = {} | |
325 for e in bib: | |
326 bibinfo[e.localName] = getTextFromNode(e) | |
327 docinfo['bib'] = bibinfo | |
328 | |
329 # extract some fields (author, title, year) according to their mapping | |
25 | 330 metaData=self.metadata.main.meta.bib |
331 bibtype=dom.xpath("//bib/@type") | |
332 if bibtype and (len(bibtype)>0): | |
333 bibtype=bibtype[0].value | |
20 | 334 else: |
25 | 335 bibtype="generic" |
59 | 336 |
25 | 337 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
59 | 338 docinfo['bib_type'] = bibtype |
25 | 339 bibmap=metaData.generateMappingForType(bibtype) |
32 | 340 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
31 | 341 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
25 | 342 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) |
343 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
344 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
59 | 345 logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
52 | 346 try: |
347 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
348 except: | |
349 docinfo['lang']='' | |
59 | 350 |
22 | 351 return docinfo |
352 | |
353 | |
32 | 354 def getDocinfoFromTextTool(self,url,dom=None,docinfo=None): |
22 | 355 """parse texttool tag in index meta""" |
52 | 356 logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url)) |
22 | 357 if docinfo is None: |
358 docinfo = {} | |
359 | |
52 | 360 if docinfo.get('lang',None) is None: |
361 docinfo['lang']='' # default keine Sprache gesetzt | |
32 | 362 if dom is None: |
35 | 363 dom = self.getIndexMeta(url) |
32 | 364 |
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
365 archivePath = None |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
366 archiveName = None |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
367 |
32 | 368 archiveNames=dom.xpath("//resource/name") |
369 if archiveNames and (len(archiveNames)>0): | |
370 archiveName=getTextFromNode(archiveNames[0]) | |
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
371 else: |
52 | 372 logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/name missing in: %s"%(url)) |
22 | 373 |
374 archivePaths=dom.xpath("//resource/archive-path") | |
375 if archivePaths and (len(archivePaths)>0): | |
376 archivePath=getTextFromNode(archivePaths[0]) | |
32 | 377 # clean up archive path |
378 if archivePath[0] != '/': | |
379 archivePath = '/' + archivePath | |
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
380 if archiveName and (not archivePath.endswith(archiveName)): |
32 | 381 archivePath += "/" + archiveName |
22 | 382 else: |
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
383 # try to get archive-path from url |
52 | 384 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
|
385 if (not url.startswith('http')): |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
386 archivePath = url.replace('index.meta', '') |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
387 |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
388 if archivePath is None: |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
389 # we balk without archive-path |
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
390 raise IOError("Missing archive-path (for text-tool) in %s"%(url)) |
22 | 391 |
35 | 392 imageDirs=dom.xpath("//texttool/image") |
393 if imageDirs and (len(imageDirs)>0): | |
394 imageDir=getTextFromNode(imageDirs[0]) | |
22 | 395 else: |
52 | 396 # we balk with no image tag / not necessary anymore because textmode is now standard |
397 #raise IOError("No text-tool info in %s"%(url)) | |
398 imageDir="" | |
399 docinfo['numPages']=1 # im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht | |
400 | |
401 docinfo['imagePath'] = "" # keine Bilder | |
402 docinfo['imageURL'] = "" | |
403 | |
35 | 404 if imageDir and archivePath: |
405 #print "image: ", imageDir, " archivepath: ", archivePath | |
406 imageDir=os.path.join(archivePath,imageDir) | |
407 imageDir=imageDir.replace("/mpiwg/online",'') | |
408 docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo) | |
409 docinfo['imagePath'] = imageDir | |
410 docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir | |
22 | 411 |
412 viewerUrls=dom.xpath("//texttool/digiliburlprefix") | |
413 if viewerUrls and (len(viewerUrls)>0): | |
414 viewerUrl=getTextFromNode(viewerUrls[0]) | |
31 | 415 docinfo['viewerURL'] = viewerUrl |
22 | 416 |
417 textUrls=dom.xpath("//texttool/text") | |
418 if textUrls and (len(textUrls)>0): | |
419 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
|
420 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
|
421 textUrl=os.path.join(archivePath,textUrl) |
a10fff6199b0
verbesserung f?r text unterst?tzung, text kann jetzt aus url kommen, sprache bisher nur deutsch
dwinter
parents:
46
diff
changeset
|
422 |
31 | 423 docinfo['textURL'] = textUrl |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
424 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
425 presentationUrls=dom.xpath("//texttool/presentation") |
52 | 426 docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get info von bib tag |
427 | |
428 if presentationUrls and (len(presentationUrls)>0): # ueberschreibe diese durch presentation informationen | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
429 # presentation url ergiebt sich ersetzen von index.meta in der url der fŸr die Metadaten |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
430 # durch den relativen Pfad auf die presentation infos |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
431 presentationUrl=url.replace('index.meta',getTextFromNode(presentationUrls[0])) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
432 docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom) |
52 | 433 |
55
ba8917b93c84
fixed bug in fix for missing getauthinfo in getdocinfofromtexttool
casties
parents:
54
diff
changeset
|
434 docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info |
22 | 435 return docinfo |
436 | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
437 |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
438 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
439 """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
|
440 """ |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
441 dom=self.getPresentationInfoXML(url) |
62 | 442 try: |
443 docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) | |
444 except: | |
445 pass | |
446 try: | |
447 docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) | |
448 except: | |
449 pass | |
450 try: | |
451 docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) | |
452 except: | |
453 pass | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
454 return docinfo |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
455 |
22 | 456 def getDocinfoFromImagePath(self,path,docinfo=None): |
457 """path ist the path to the images it assumes that the index.meta file is one level higher.""" | |
52 | 458 logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) |
22 | 459 if docinfo is None: |
460 docinfo = {} | |
29 | 461 path=path.replace("/mpiwg/online","") |
22 | 462 docinfo['imagePath'] = path |
31 | 463 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo) |
464 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path | |
22 | 465 docinfo['imageURL'] = imageUrl |
466 | |
467 docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo) | |
32 | 468 docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo) |
22 | 469 return docinfo |
20 | 470 |
22 | 471 |
472 def getDocinfo(self, mode, url): | |
473 """returns docinfo depending on mode""" | |
52 | 474 logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) |
22 | 475 # look for cached docinfo in session |
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
476 if self.REQUEST.SESSION.has_key('docinfo'): |
22 | 477 docinfo = self.REQUEST.SESSION['docinfo'] |
478 # check if its still current | |
479 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
52 | 480 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) |
22 | 481 return docinfo |
482 # new docinfo | |
483 docinfo = {'mode': mode, 'url': url} | |
484 if mode=="texttool": #index.meta with texttool information | |
485 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
486 elif mode=="imagepath": | |
487 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
488 else: | |
52 | 489 logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") |
37 | 490 raise ValueError("Unknown mode %s"%(mode)) |
491 | |
52 | 492 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
22 | 493 self.REQUEST.SESSION['docinfo'] = docinfo |
494 return docinfo | |
20 | 495 |
496 | |
25 | 497 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None): |
22 | 498 """returns pageinfo with the given parameters""" |
499 pageinfo = {} | |
25 | 500 current = getInt(current) |
501 pageinfo['current'] = current | |
502 rows = int(rows or self.thumbrows) | |
503 pageinfo['rows'] = rows | |
504 cols = int(cols or self.thumbcols) | |
505 pageinfo['cols'] = cols | |
506 grpsize = cols * rows | |
507 pageinfo['groupsize'] = grpsize | |
61 | 508 start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
509 # int(current / grpsize) * grpsize +1)) | |
22 | 510 pageinfo['start'] = start |
25 | 511 pageinfo['end'] = start + grpsize |
512 if docinfo is not None: | |
513 np = int(docinfo['numPages']) | |
514 pageinfo['end'] = min(pageinfo['end'], np) | |
515 pageinfo['numgroups'] = int(np / grpsize) | |
516 if np % grpsize > 0: | |
517 pageinfo['numgroups'] += 1 | |
518 | |
22 | 519 return pageinfo |
520 | |
0 | 521 def text(self,mode,url,pn): |
522 """give text""" | |
523 if mode=="texttool": #index.meta with texttool information | |
524 (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) | |
525 | |
35 | 526 #print textpath |
0 | 527 try: |
528 dom = NonvalidatingReader.parseUri(textpath) | |
529 except: | |
530 return None | |
531 | |
532 list=[] | |
533 nodes=dom.xpath("//pb") | |
534 | |
535 node=nodes[int(pn)-1] | |
536 | |
537 p=node | |
538 | |
539 while p.tagName!="p": | |
540 p=p.parentNode | |
541 | |
542 | |
543 endNode=nodes[int(pn)] | |
544 | |
545 | |
546 e=endNode | |
547 | |
548 while e.tagName!="p": | |
549 e=e.parentNode | |
550 | |
551 | |
552 next=node.parentNode | |
553 | |
554 #sammle s | |
555 while next and (next!=endNode.parentNode): | |
556 list.append(next) | |
557 next=next.nextSibling | |
558 list.append(endNode.parentNode) | |
559 | |
560 if p==e:# beide im selben paragraphen | |
20 | 561 pass |
562 # else: | |
563 # next=p | |
564 # while next!=e: | |
565 # print next,e | |
566 # list.append(next) | |
567 # next=next.nextSibling | |
568 # | |
569 # for x in list: | |
570 # PrettyPrint(x) | |
571 # | |
572 # return list | |
22 | 573 # |
574 | |
575 def findDigilibUrl(self): | |
576 """try to get the digilib URL from zogilib""" | |
577 url = self.imageViewerUrl[:-1] + "/getScalerUrl" | |
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
578 #print urlparse.urlparse(url)[0] |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
579 #print urlparse.urljoin(self.absolute_url(),url) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
580 logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0]) |
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
581 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
|
582 |
22 | 583 try: |
46 | 584 if urlparse.urlparse(url)[0]=='': #relative path |
585 url=urlparse.urljoin(self.absolute_url()+"/",url) | |
586 | |
22 | 587 scaler = urlopen(url).read() |
588 return scaler.replace("/servlet/Scaler?", "") | |
589 except: | |
590 return None | |
591 | |
46 | 592 def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): |
22 | 593 """init document viewer""" |
594 self.title=title | |
595 self.imageViewerUrl=imageViewerUrl | |
46 | 596 self.textViewerUrl=textViewerUrl |
22 | 597 self.digilibBaseUrl = digilibBaseUrl |
25 | 598 self.thumbrows = thumbrows |
599 self.thumbcols = thumbcols | |
32 | 600 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
22 | 601 if RESPONSE is not None: |
602 RESPONSE.redirect('manage_main') | |
0 | 603 |
604 | |
605 | |
606 | |
607 # security.declareProtected('View management screens','renameImageForm') | |
608 | |
609 def manage_AddDocumentViewerForm(self): | |
610 """add the viewer form""" | |
22 | 611 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
0 | 612 return pt() |
613 | |
46 | 614 def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None): |
0 | 615 """add the viewer""" |
46 | 616 newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl) |
0 | 617 self._setObject(id,newObj) |
618 | |
619 if RESPONSE is not None: | |
620 RESPONSE.redirect('manage_main') | |
22 | 621 |
622 | |
623 ## | |
624 ## DocumentViewerTemplate class | |
625 ## | |
626 class DocumentViewerTemplate(ZopePageTemplate): | |
627 """Template for document viewer""" | |
628 meta_type="DocumentViewer Template" | |
629 | |
630 | |
631 def manage_addDocumentViewerTemplateForm(self): | |
632 """Form for adding""" | |
633 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
634 return pt() | |
635 | |
636 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
637 REQUEST=None, submit=None): | |
638 "Add a Page Template with optional file content." | |
639 | |
640 self._setObject(id, DocumentViewerTemplate(id)) | |
641 ob = getattr(self, id) | |
53
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
642 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
|
643 logging.info("txt %s:"%txt) |
f4e0af8c281d
NEW - # 44: ECHO - vollst?ndige bibliographische Angabe
dwinter
parents:
52
diff
changeset
|
644 ob.pt_edit(txt,"text/html") |
22 | 645 if title: |
646 ob.pt_setTitle(title) | |
647 try: | |
648 u = self.DestinationURL() | |
649 except AttributeError: | |
650 u = REQUEST['URL1'] | |
651 | |
652 u = "%s/%s" % (u, urllib.quote(id)) | |
653 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
654 return '' | |
655 | |
656 | |
41 | 657 |