Mercurial > hg > documentViewer
annotate documentViewer.py @ 52:92047eaa6272
zLOG exchanged by logging
| author | dwinter |
|---|---|
| date | Wed, 24 Jan 2007 17:12:26 +0100 |
| parents | c5d3aabbf61b |
| children | f4e0af8c281d |
| 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 |
| 52 | 21 |
| 46 | 22 import urlparse |
| 0 | 23 |
| 52 | 24 def logger(txt,method,txt2): |
| 25 """logging""" | |
| 26 logging.info(txt+ txt2) | |
| 27 | |
| 28 | |
| 25 | 29 def getInt(number, default=0): |
| 30 """returns always an int (0 in case of problems)""" | |
| 31 try: | |
| 32 return int(number) | |
| 33 except: | |
| 34 return default | |
| 35 | |
| 0 | 36 def getTextFromNode(nodename): |
| 46 | 37 """get the cdata content of a node""" |
| 32 | 38 if nodename is None: |
| 39 return "" | |
| 0 | 40 nodelist=nodename.childNodes |
| 41 rc = "" | |
| 42 for node in nodelist: | |
| 43 if node.nodeType == node.TEXT_NODE: | |
| 44 rc = rc + node.data | |
| 45 return rc | |
| 46 | |
| 35 | 47 |
| 48 def getParentDir(path): | |
| 49 """returns pathname shortened by one""" | |
| 50 return '/'.join(path.split('/')[0:-1]) | |
| 51 | |
| 52 | |
| 0 | 53 import socket |
| 54 | |
| 32 | 55 def urlopen(url,timeout=2): |
| 0 | 56 """urlopen mit timeout""" |
| 32 | 57 socket.setdefaulttimeout(timeout) |
| 0 | 58 ret=urllib.urlopen(url) |
| 59 socket.setdefaulttimeout(5) | |
| 60 return ret | |
| 61 | |
| 62 | |
| 22 | 63 ## |
| 64 ## documentViewer class | |
| 65 ## | |
| 66 class documentViewer(Folder): | |
| 0 | 67 """document viewer""" |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
68 #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" |
| 46 | 69 |
| 0 | 70 meta_type="Document viewer" |
| 71 | |
| 72 security=ClassSecurityInfo() | |
| 22 | 73 manage_options=Folder.manage_options+( |
| 0 | 74 {'label':'main config','action':'changeDocumentViewerForm'}, |
| 75 ) | |
| 76 | |
| 22 | 77 # templates and forms |
| 78 viewer_main = PageTemplateFile('zpt/viewer_main', globals()) | |
| 79 thumbs_main = PageTemplateFile('zpt/thumbs_main', globals()) | |
| 80 image_main = PageTemplateFile('zpt/image_main', globals()) | |
| 81 head_main = PageTemplateFile('zpt/head_main', globals()) | |
| 82 docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | |
| 83 | |
| 84 security.declareProtected('View management screens','changeDocumentViewerForm') | |
| 85 changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
| 86 | |
| 0 | 87 |
| 46 | 88 def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): |
| 0 | 89 """init document viewer""" |
| 90 self.id=id | |
| 91 self.title=title | |
| 92 self.imageViewerUrl=imageViewerUrl | |
| 46 | 93 self.textViewerUrl=textViewerUrl |
| 94 | |
| 25 | 95 if not digilibBaseUrl: |
| 22 | 96 self.digilibBaseUrl = self.findDigilibUrl() |
| 25 | 97 else: |
| 98 self.digilibBaseUrl = digilibBaseUrl | |
| 99 self.thumbcols = thumbcols | |
| 100 self.thumbrows = thumbrows | |
| 32 | 101 # authgroups is list of authorized groups (delimited by ,) |
| 102 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] | |
| 22 | 103 # add template folder so we can always use template.something |
| 104 self.manage_addFolder('template') | |
| 105 | |
| 106 | |
| 107 security.declareProtected('View','index_html') | |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
108 def index_html(self,mode,url,viewMode="auto",start=None,pn=1): |
| 22 | 109 ''' |
| 110 view it | |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
111 @param mode: defines which type of document is behind url (text,images or auto) |
| 22 | 112 @param url: url which contains display information |
| 46 | 113 @param viewMode: if images display images, if text display text, default is images |
| 114 | |
| 22 | 115 ''' |
| 0 | 116 |
| 52 | 117 logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
| 22 | 118 |
| 119 if not hasattr(self, 'template'): | |
| 120 # create template folder if it doesn't exist | |
| 121 self.manage_addFolder('template') | |
| 122 | |
| 123 if not self.digilibBaseUrl: | |
| 124 self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | |
| 125 | |
| 25 | 126 docinfo = self.getDocinfo(mode=mode,url=url) |
| 127 pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) | |
| 22 | 128 pt = getattr(self.template, 'viewer_main') |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
129 |
|
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
130 if viewMode=="auto": # automodus gewaehlt |
|
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
131 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
|
132 viewMode="text" |
|
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
133 else: |
|
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
134 viewMode="images" |
| 52 | 135 |
| 136 | |
| 46 | 137 return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) |
| 0 | 138 |
| 139 | |
| 25 | 140 def getLink(self,param=None,val=None): |
| 141 """link to documentviewer with parameter param set to val""" | |
| 35 | 142 params=self.REQUEST.form.copy() |
| 25 | 143 if param is not None: |
| 31 | 144 if val is None: |
| 145 if params.has_key(param): | |
| 146 del params[param] | |
| 25 | 147 else: |
| 35 | 148 params[param] = str(val) |
| 31 | 149 |
| 35 | 150 # quote values and assemble into query string |
| 151 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) | |
| 152 url=self.REQUEST['URL1']+"?"+ps | |
| 25 | 153 return url |
| 154 | |
| 0 | 155 |
| 22 | 156 def getStyle(self, idx, selected, style=""): |
| 25 | 157 """returns a string with the given style and append 'sel' if path == selected.""" |
| 52 | 158 #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
| 22 | 159 if idx == selected: |
| 160 return style + 'sel' | |
| 161 else: | |
| 35 | 162 return style |
| 0 | 163 |
| 35 | 164 |
| 165 def isAccessible(self, docinfo): | |
| 32 | 166 """returns if access to the resource is granted""" |
| 167 access = docinfo.get('accessType', None) | |
| 52 | 168 logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) |
| 45 | 169 if access is not None and access == 'free': |
| 52 | 170 logger("documentViewer (accessOK)", logging.INFO, "access is free") |
| 32 | 171 return True |
| 45 | 172 elif access is None or access in self.authgroups: |
| 35 | 173 # only local access -- only logged in users |
| 174 user = getSecurityManager().getUser() | |
| 175 if user is not None: | |
| 176 #print "user: ", user | |
| 177 return (user.getUserName() != "Anonymous User") | |
| 178 else: | |
| 179 return False | |
| 32 | 180 |
| 52 | 181 logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) |
| 32 | 182 return False |
| 35 | 183 |
| 32 | 184 |
| 31 | 185 def getDirinfoFromDigilib(self,path,docinfo=None): |
| 29 | 186 """gibt param von dlInfo aus""" |
| 40 | 187 num_retries = 3 |
| 31 | 188 if docinfo is None: |
| 189 docinfo = {} | |
| 190 | |
| 40 | 191 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
| 29 | 192 |
| 52 | 193 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) |
| 29 | 194 |
| 40 | 195 for cnt in range(num_retries): |
| 35 | 196 try: |
| 40 | 197 # dom = NonvalidatingReader.parseUri(imageUrl) |
| 198 txt=urllib.urlopen(infoUrl).read() | |
| 199 dom = Parse(txt) | |
| 35 | 200 break |
| 201 except: | |
| 52 | 202 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) |
| 35 | 203 else: |
| 40 | 204 raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
| 29 | 205 |
| 37 | 206 sizes=dom.xpath("//dir/size") |
| 52 | 207 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) |
| 29 | 208 |
| 37 | 209 if sizes: |
| 210 docinfo['numPages'] = int(getTextFromNode(sizes[0])) | |
| 31 | 211 else: |
| 212 docinfo['numPages'] = 0 | |
| 213 | |
| 214 return docinfo | |
| 32 | 215 |
| 29 | 216 |
| 35 | 217 def getIndexMeta(self, url): |
| 218 """returns dom of index.meta document at url""" | |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
219 num_retries = 3 |
| 35 | 220 dom = None |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
221 metaUrl = None |
| 35 | 222 if url.startswith("http://"): |
| 223 # real URL | |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
224 metaUrl = url |
| 35 | 225 else: |
| 226 # online path | |
| 227 server=self.digilibBaseUrl+"/servlet/Texter?fn=" | |
| 40 | 228 metaUrl=server+url.replace("/mpiwg/online","") |
| 35 | 229 if not metaUrl.endswith("index.meta"): |
| 230 metaUrl += "/index.meta" | |
| 46 | 231 print metaUrl |
| 40 | 232 for cnt in range(num_retries): |
| 35 | 233 try: |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
234 # patch dirk encoding fehler treten dann nicht mehr auf |
| 38 | 235 # dom = NonvalidatingReader.parseUri(metaUrl) |
|
39
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
236 txt=urllib.urlopen(metaUrl).read() |
|
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
237 dom = Parse(txt) |
| 40 | 238 break |
| 35 | 239 except: |
| 52 | 240 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
|
241 |
|
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
242 if dom is None: |
|
1dd90aabd366
added retry when reading index meta from texter applet
casties
parents:
38
diff
changeset
|
243 raise IOError("Unable to read index meta from %s"%(url)) |
| 35 | 244 |
| 245 return dom | |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
246 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
247 def getPresentationInfoXML(self, url): |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
248 """returns dom of info.xml document at url""" |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
249 num_retries = 3 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
250 dom = None |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
251 metaUrl = None |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
252 if url.startswith("http://"): |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
253 # real URL |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
254 metaUrl = url |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
255 else: |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
256 # online path |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
257 server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
258 metaUrl=server+url.replace("/mpiwg/online","") |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
259 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
260 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
261 for cnt in range(num_retries): |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
262 try: |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
263 # patch dirk encoding fehler treten dann nicht mehr auf |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
264 # dom = NonvalidatingReader.parseUri(metaUrl) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
265 txt=urllib.urlopen(metaUrl).read() |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
266 dom = Parse(txt) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
267 break |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
268 except: |
| 52 | 269 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
|
270 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
271 if dom is None: |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
272 raise IOError("Unable to read infoXMLfrom %s"%(url)) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
273 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
274 return dom |
| 35 | 275 |
| 276 | |
| 32 | 277 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None): |
| 35 | 278 """gets authorization info from the index.meta file at path or given by dom""" |
| 52 | 279 logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
| 32 | 280 |
| 281 access = None | |
| 282 | |
| 283 if docinfo is None: | |
| 284 docinfo = {} | |
| 285 | |
| 286 if dom is None: | |
| 35 | 287 dom = self.getIndexMeta(getParentDir(path)) |
| 46 | 288 |
| 32 | 289 acctype = dom.xpath("//access-conditions/access/@type") |
| 290 if acctype and (len(acctype)>0): | |
| 291 access=acctype[0].value | |
| 35 | 292 if access in ['group', 'institution']: |
| 32 | 293 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
| 294 | |
| 295 docinfo['accessType'] = access | |
| 296 return docinfo | |
| 29 | 297 |
| 32 | 298 |
| 22 | 299 def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None): |
| 35 | 300 """gets bibliographical info from the index.meta file at path or given by dom""" |
| 52 | 301 logger("documentViewer (getbibinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
| 20 | 302 |
| 22 | 303 if docinfo is None: |
| 304 docinfo = {} | |
| 305 | |
| 306 if dom is None: | |
| 35 | 307 dom = self.getIndexMeta(getParentDir(path)) |
| 308 | |
| 25 | 309 metaData=self.metadata.main.meta.bib |
| 310 bibtype=dom.xpath("//bib/@type") | |
| 311 if bibtype and (len(bibtype)>0): | |
| 312 bibtype=bibtype[0].value | |
| 20 | 313 else: |
| 25 | 314 bibtype="generic" |
| 315 bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) | |
| 316 bibmap=metaData.generateMappingForType(bibtype) | |
| 35 | 317 #print "bibmap: ", bibmap, " for: ", bibtype |
| 32 | 318 # if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
| 31 | 319 if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
| 25 | 320 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) |
| 321 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | |
| 322 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | |
| 52 | 323 |
| 324 logging.info("bla") | |
| 325 try: | |
| 326 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
| 327 except: | |
| 328 docinfo['lang']='' | |
| 22 | 329 return docinfo |
| 330 | |
| 331 | |
| 32 | 332 def getDocinfoFromTextTool(self,url,dom=None,docinfo=None): |
| 22 | 333 """parse texttool tag in index meta""" |
| 52 | 334 logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url)) |
| 22 | 335 if docinfo is None: |
| 336 docinfo = {} | |
| 337 | |
| 52 | 338 if docinfo.get('lang',None) is None: |
| 339 docinfo['lang']='' # default keine Sprache gesetzt | |
| 32 | 340 if dom is None: |
| 35 | 341 dom = self.getIndexMeta(url) |
| 32 | 342 |
|
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
343 archivePath = None |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
344 archiveName = None |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
345 |
| 32 | 346 archiveNames=dom.xpath("//resource/name") |
| 347 if archiveNames and (len(archiveNames)>0): | |
| 348 archiveName=getTextFromNode(archiveNames[0]) | |
|
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
349 else: |
| 52 | 350 logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/name missing in: %s"%(url)) |
| 22 | 351 |
| 352 archivePaths=dom.xpath("//resource/archive-path") | |
| 353 if archivePaths and (len(archivePaths)>0): | |
| 354 archivePath=getTextFromNode(archivePaths[0]) | |
| 32 | 355 # clean up archive path |
| 356 if archivePath[0] != '/': | |
| 357 archivePath = '/' + archivePath | |
|
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
358 if archiveName and (not archivePath.endswith(archiveName)): |
| 32 | 359 archivePath += "/" + archiveName |
| 22 | 360 else: |
|
43
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
361 # try to get archive-path from url |
| 52 | 362 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
|
363 if (not url.startswith('http')): |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
364 archivePath = url.replace('index.meta', '') |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
365 |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
366 if archivePath is None: |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
367 # we balk without archive-path |
|
f3bc59cf64d9
fixed some problems with bad index.meta files (text-tools mode)
casties
parents:
42
diff
changeset
|
368 raise IOError("Missing archive-path (for text-tool) in %s"%(url)) |
| 22 | 369 |
| 35 | 370 imageDirs=dom.xpath("//texttool/image") |
| 371 if imageDirs and (len(imageDirs)>0): | |
| 372 imageDir=getTextFromNode(imageDirs[0]) | |
| 22 | 373 else: |
| 52 | 374 # we balk with no image tag / not necessary anymore because textmode is now standard |
| 375 #raise IOError("No text-tool info in %s"%(url)) | |
| 376 imageDir="" | |
| 377 docinfo['numPages']=1 # im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht | |
| 378 | |
| 379 docinfo['imagePath'] = "" # keine Bilder | |
| 380 docinfo['imageURL'] = "" | |
| 381 | |
| 35 | 382 if imageDir and archivePath: |
| 383 #print "image: ", imageDir, " archivepath: ", archivePath | |
| 384 imageDir=os.path.join(archivePath,imageDir) | |
| 385 imageDir=imageDir.replace("/mpiwg/online",'') | |
| 386 docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo) | |
| 387 docinfo['imagePath'] = imageDir | |
| 388 docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir | |
| 22 | 389 |
| 390 viewerUrls=dom.xpath("//texttool/digiliburlprefix") | |
| 391 if viewerUrls and (len(viewerUrls)>0): | |
| 392 viewerUrl=getTextFromNode(viewerUrls[0]) | |
| 31 | 393 docinfo['viewerURL'] = viewerUrl |
| 22 | 394 |
| 395 textUrls=dom.xpath("//texttool/text") | |
| 396 if textUrls and (len(textUrls)>0): | |
| 397 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
|
398 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
|
399 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
|
400 |
| 31 | 401 docinfo['textURL'] = textUrl |
| 22 | 402 |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
403 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
404 presentationUrls=dom.xpath("//texttool/presentation") |
| 52 | 405 docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get info von bib tag |
| 406 | |
| 407 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
|
408 # 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
|
409 # durch den relativen Pfad auf die presentation infos |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
410 presentationUrl=url.replace('index.meta',getTextFromNode(presentationUrls[0])) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
411 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
412 docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom) |
| 52 | 413 |
| 414 | |
| 415 | |
| 22 | 416 return docinfo |
| 417 | |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
418 |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
419 def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
420 """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
|
421 """ |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
422 dom=self.getPresentationInfoXML(url) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
423 docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
424 docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
425 docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
426 return docinfo |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
427 |
| 22 | 428 def getDocinfoFromImagePath(self,path,docinfo=None): |
| 429 """path ist the path to the images it assumes that the index.meta file is one level higher.""" | |
| 52 | 430 logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) |
| 22 | 431 if docinfo is None: |
| 432 docinfo = {} | |
| 29 | 433 path=path.replace("/mpiwg/online","") |
| 22 | 434 docinfo['imagePath'] = path |
| 31 | 435 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo) |
| 436 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path | |
| 22 | 437 docinfo['imageURL'] = imageUrl |
| 438 | |
| 439 docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo) | |
| 32 | 440 docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo) |
| 22 | 441 return docinfo |
| 20 | 442 |
| 22 | 443 |
| 444 def getDocinfo(self, mode, url): | |
| 445 """returns docinfo depending on mode""" | |
| 52 | 446 logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) |
| 22 | 447 # look for cached docinfo in session |
|
51
c5d3aabbf61b
textviewer now integrated, new modus auto introduced as standard for viewing
dwinter
parents:
50
diff
changeset
|
448 if self.REQUEST.SESSION.has_key('docinfo'): |
| 22 | 449 docinfo = self.REQUEST.SESSION['docinfo'] |
| 450 # check if its still current | |
| 451 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: | |
| 52 | 452 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) |
| 22 | 453 return docinfo |
| 454 # new docinfo | |
| 455 docinfo = {'mode': mode, 'url': url} | |
| 456 if mode=="texttool": #index.meta with texttool information | |
| 457 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
| 458 elif mode=="imagepath": | |
| 459 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
| 460 else: | |
| 52 | 461 logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") |
| 37 | 462 raise ValueError("Unknown mode %s"%(mode)) |
| 463 | |
| 52 | 464 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
| 22 | 465 self.REQUEST.SESSION['docinfo'] = docinfo |
| 466 return docinfo | |
| 20 | 467 |
| 468 | |
| 25 | 469 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None): |
| 22 | 470 """returns pageinfo with the given parameters""" |
| 471 pageinfo = {} | |
| 25 | 472 current = getInt(current) |
| 473 pageinfo['current'] = current | |
| 474 rows = int(rows or self.thumbrows) | |
| 475 pageinfo['rows'] = rows | |
| 476 cols = int(cols or self.thumbcols) | |
| 477 pageinfo['cols'] = cols | |
| 478 grpsize = cols * rows | |
| 479 pageinfo['groupsize'] = grpsize | |
| 480 start = getInt(start, default=(int(current / grpsize) * grpsize +1)) | |
| 22 | 481 pageinfo['start'] = start |
| 25 | 482 pageinfo['end'] = start + grpsize |
| 483 if docinfo is not None: | |
| 484 np = int(docinfo['numPages']) | |
| 485 pageinfo['end'] = min(pageinfo['end'], np) | |
| 486 pageinfo['numgroups'] = int(np / grpsize) | |
| 487 if np % grpsize > 0: | |
| 488 pageinfo['numgroups'] += 1 | |
| 489 | |
| 22 | 490 return pageinfo |
| 491 | |
| 0 | 492 def text(self,mode,url,pn): |
| 493 """give text""" | |
| 494 if mode=="texttool": #index.meta with texttool information | |
| 495 (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) | |
| 496 | |
| 35 | 497 #print textpath |
| 0 | 498 try: |
| 499 dom = NonvalidatingReader.parseUri(textpath) | |
| 500 except: | |
| 501 return None | |
| 502 | |
| 503 list=[] | |
| 504 nodes=dom.xpath("//pb") | |
| 505 | |
| 506 node=nodes[int(pn)-1] | |
| 507 | |
| 508 p=node | |
| 509 | |
| 510 while p.tagName!="p": | |
| 511 p=p.parentNode | |
| 512 | |
| 513 | |
| 514 endNode=nodes[int(pn)] | |
| 515 | |
| 516 | |
| 517 e=endNode | |
| 518 | |
| 519 while e.tagName!="p": | |
| 520 e=e.parentNode | |
| 521 | |
| 522 | |
| 523 next=node.parentNode | |
| 524 | |
| 525 #sammle s | |
| 526 while next and (next!=endNode.parentNode): | |
| 527 list.append(next) | |
| 528 next=next.nextSibling | |
| 529 list.append(endNode.parentNode) | |
| 530 | |
| 531 if p==e:# beide im selben paragraphen | |
| 20 | 532 pass |
| 533 # else: | |
| 534 # next=p | |
| 535 # while next!=e: | |
| 536 # print next,e | |
| 537 # list.append(next) | |
| 538 # next=next.nextSibling | |
| 539 # | |
| 540 # for x in list: | |
| 541 # PrettyPrint(x) | |
| 542 # | |
| 543 # return list | |
| 22 | 544 # |
| 545 | |
| 546 def findDigilibUrl(self): | |
| 547 """try to get the digilib URL from zogilib""" | |
| 548 url = self.imageViewerUrl[:-1] + "/getScalerUrl" | |
|
50
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
549 #print urlparse.urlparse(url)[0] |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
550 #print urlparse.urljoin(self.absolute_url(),url) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
551 logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0]) |
|
6c0f20cecc60
added evaluation of the presentation/info.xml in texttools
dwinter
parents:
49
diff
changeset
|
552 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
|
553 |
| 22 | 554 try: |
| 46 | 555 if urlparse.urlparse(url)[0]=='': #relative path |
| 556 url=urlparse.urljoin(self.absolute_url()+"/",url) | |
| 557 | |
| 22 | 558 scaler = urlopen(url).read() |
| 559 return scaler.replace("/servlet/Scaler?", "") | |
| 560 except: | |
| 561 return None | |
| 562 | |
| 46 | 563 def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): |
| 22 | 564 """init document viewer""" |
| 565 self.title=title | |
| 566 self.imageViewerUrl=imageViewerUrl | |
| 46 | 567 self.textViewerUrl=textViewerUrl |
| 22 | 568 self.digilibBaseUrl = digilibBaseUrl |
| 25 | 569 self.thumbrows = thumbrows |
| 570 self.thumbcols = thumbcols | |
| 32 | 571 self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
| 22 | 572 if RESPONSE is not None: |
| 573 RESPONSE.redirect('manage_main') | |
| 0 | 574 |
| 575 | |
| 576 | |
| 577 | |
| 578 # security.declareProtected('View management screens','renameImageForm') | |
| 579 | |
| 580 def manage_AddDocumentViewerForm(self): | |
| 581 """add the viewer form""" | |
| 22 | 582 pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
| 0 | 583 return pt() |
| 584 | |
| 46 | 585 def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None): |
| 0 | 586 """add the viewer""" |
| 46 | 587 newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl) |
| 0 | 588 self._setObject(id,newObj) |
| 589 | |
| 590 if RESPONSE is not None: | |
| 591 RESPONSE.redirect('manage_main') | |
| 22 | 592 |
| 593 | |
| 594 ## | |
| 595 ## DocumentViewerTemplate class | |
| 596 ## | |
| 597 class DocumentViewerTemplate(ZopePageTemplate): | |
| 598 """Template for document viewer""" | |
| 599 meta_type="DocumentViewer Template" | |
| 600 | |
| 601 | |
| 602 def manage_addDocumentViewerTemplateForm(self): | |
| 603 """Form for adding""" | |
| 604 pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) | |
| 605 return pt() | |
| 606 | |
| 607 def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, | |
| 608 REQUEST=None, submit=None): | |
| 609 "Add a Page Template with optional file content." | |
| 610 | |
| 611 self._setObject(id, DocumentViewerTemplate(id)) | |
| 612 ob = getattr(self, id) | |
| 613 ob.pt_edit(open(os.path.join(package_home(globals()),'zpt/viewer_main.zpt')).read(),None) | |
| 614 if title: | |
| 615 ob.pt_setTitle(title) | |
| 616 try: | |
| 617 u = self.DestinationURL() | |
| 618 except AttributeError: | |
| 619 u = REQUEST['URL1'] | |
| 620 | |
| 621 u = "%s/%s" % (u, urllib.quote(id)) | |
| 622 REQUEST.RESPONSE.redirect(u+'/manage_main') | |
| 623 return '' | |
| 624 | |
| 625 | |
| 41 | 626 |