Mercurial > hg > documentViewer

comparison documentViewer.py @ 4:e9085ba2bb51 modularisierung

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
- first fix for timeout issues - cleaned logging calls
author casties
date Wed, 16 Jun 2010 18:38:17 +0200
parents 8cc283757c39
children 3c70a7d2f35b
comparison
equal deleted inserted replaced
3:3ba8479c7aba 4:e9085ba2bb51
264 del params[param] 264 del params[param]
265 else: 265 else:
266 params[param] = str(val) 266 params[param] = str(val)
267 267
268 # quote values and assemble into query string 268 # quote values and assemble into query string
269 logging.info("XYXXXXX: %s"%repr(params.items())) 269 logging.debug("XYXXXXX: %s"%repr(params.items()))
270 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) 270 ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
271 url=self.REQUEST['URL1']+"?"+ps 271 url=self.REQUEST['URL1']+"?"+ps
272 return url 272 return url
273 273
274 def getInfo_xml(self,url,mode): 274 def getInfo_xml(self,url,mode):
283 283
284 284
285 def isAccessible(self, docinfo): 285 def isAccessible(self, docinfo):
286 """returns if access to the resource is granted""" 286 """returns if access to the resource is granted"""
287 access = docinfo.get('accessType', None) 287 access = docinfo.get('accessType', None)
288 logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access) 288 logging.debug("documentViewer (accessOK) access type %s"%access)
289 if access is not None and access == 'free': 289 if access is not None and access == 'free':
290 logger("documentViewer (accessOK)", logging.INFO, "access is free") 290 logging.debug("documentViewer (accessOK) access is free")
291 return True 291 return True
292 elif access is None or access in self.authgroups: 292 elif access is None or access in self.authgroups:
293 # only local access -- only logged in users 293 # only local access -- only logged in users
294 user = getSecurityManager().getUser() 294 user = getSecurityManager().getUser()
295 if user is not None: 295 if user is not None:
296 #print "user: ", user 296 #print "user: ", user
297 return (user.getUserName() != "Anonymous User") 297 return (user.getUserName() != "Anonymous User")
298 else: 298 else:
299 return False 299 return False
300 300
301 logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access) 301 logging.debug("documentViewer (accessOK) unknown access type %s"%access)
302 return False 302 return False
303 303
304 304
305 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): 305 def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
306 """gibt param von dlInfo aus""" 306 """gibt param von dlInfo aus"""
312 312
313 path=getParentDir(path) 313 path=getParentDir(path)
314 314
315 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path 315 infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
316 316
317 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) 317 logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
318 318
319 for cnt in range(num_retries): 319 for cnt in range(num_retries):
320 try: 320 try:
321 # dom = NonvalidatingReader.parseUri(imageUrl) 321 # dom = NonvalidatingReader.parseUri(imageUrl)
322 txt=urllib.urlopen(infoUrl).read() 322 txt=urllib.urlopen(infoUrl).read()
323 dom = Parse(txt) 323 dom = Parse(txt)
324 break 324 break
325 except: 325 except:
326 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) 326 logging.error("documentViewer (getdirinfofromdigilib) error reading %s (try %d)"%(infoUrl,cnt))
327 else: 327 else:
328 raise IOError("Unable to get dir-info from %s"%(infoUrl)) 328 raise IOError("Unable to get dir-info from %s"%(infoUrl))
329 329
330 sizes=dom.xpath("//dir/size") 330 sizes=dom.xpath("//dir/size")
331 logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) 331 logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
332 332
333 if sizes: 333 if sizes:
334 docinfo['numPages'] = int(getTextFromNode(sizes[0])) 334 docinfo['numPages'] = int(getTextFromNode(sizes[0]))
335 else: 335 else:
336 docinfo['numPages'] = 0 336 docinfo['numPages'] = 0
361 # dom = NonvalidatingReader.parseUri(metaUrl) 361 # dom = NonvalidatingReader.parseUri(metaUrl)
362 txt=urllib.urlopen(metaUrl).read() 362 txt=urllib.urlopen(metaUrl).read()
363 dom = Parse(txt) 363 dom = Parse(txt)
364 break 364 break
365 except: 365 except:
366 logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) 366 logging.error("ERROR documentViewer (getIndexMeta) %s (%s)"%sys.exc_info()[0:2])
367 367
368 if dom is None: 368 if dom is None:
369 raise IOError("Unable to read index meta from %s"%(url)) 369 raise IOError("Unable to read index meta from %s"%(url))
370 370
371 return dom 371 return dom
389 # dom = NonvalidatingReader.parseUri(metaUrl) 389 # dom = NonvalidatingReader.parseUri(metaUrl)
390 txt=urllib.urlopen(metaUrl).read() 390 txt=urllib.urlopen(metaUrl).read()
391 dom = Parse(txt) 391 dom = Parse(txt)
392 break 392 break
393 except: 393 except:
394 logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) 394 logging.error("ERROR documentViewer (getPresentationInfoXML) %s (%s)"%sys.exc_info()[0:2])
395 395
396 if dom is None: 396 if dom is None:
397 raise IOError("Unable to read infoXMLfrom %s"%(url)) 397 raise IOError("Unable to read infoXMLfrom %s"%(url))
398 398
399 return dom 399 return dom
400 400
401 401
402 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): 402 def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
403 """gets authorization info from the index.meta file at path or given by dom""" 403 """gets authorization info from the index.meta file at path or given by dom"""
404 logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) 404 logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
405 405
406 access = None 406 access = None
407 407
408 if docinfo is None: 408 if docinfo is None:
409 docinfo = {} 409 docinfo = {}
475 return docinfo 475 return docinfo
476 476
477 477
478 def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): 478 def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
479 """parse texttool tag in index meta""" 479 """parse texttool tag in index meta"""
480 logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url)) 480 logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
481 if docinfo is None: 481 if docinfo is None:
482 docinfo = {} 482 docinfo = {}
483 if docinfo.get('lang', None) is None: 483 if docinfo.get('lang', None) is None:
484 docinfo['lang'] = '' # default keine Sprache gesetzt 484 docinfo['lang'] = '' # default keine Sprache gesetzt
485 if dom is None: 485 if dom is None:
490 490
491 archiveNames = dom.xpath("//resource/name") 491 archiveNames = dom.xpath("//resource/name")
492 if archiveNames and (len(archiveNames) > 0): 492 if archiveNames and (len(archiveNames) > 0):
493 archiveName = getTextFromNode(archiveNames[0]) 493 archiveName = getTextFromNode(archiveNames[0])
494 else: 494 else:
495 logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url)) 495 logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
496 496
497 archivePaths = dom.xpath("//resource/archive-path") 497 archivePaths = dom.xpath("//resource/archive-path")
498 if archivePaths and (len(archivePaths) > 0): 498 if archivePaths and (len(archivePaths) > 0):
499 archivePath = getTextFromNode(archivePaths[0]) 499 archivePath = getTextFromNode(archivePaths[0])
500 # clean up archive path 500 # clean up archive path
502 archivePath = '/' + archivePath 502 archivePath = '/' + archivePath
503 if archiveName and (not archivePath.endswith(archiveName)): 503 if archiveName and (not archivePath.endswith(archiveName)):
504 archivePath += "/" + archiveName 504 archivePath += "/" + archiveName
505 else: 505 else:
506 # try to get archive-path from url 506 # try to get archive-path from url
507 logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url)) 507 logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
508 if (not url.startswith('http')): 508 if (not url.startswith('http')):
509 archivePath = url.replace('index.meta', '') 509 archivePath = url.replace('index.meta', '')
510 510
511 if archivePath is None: 511 if archivePath is None:
512 # we balk without archive-path 512 # we balk without archive-path
594 pass 594 pass
595 return docinfo 595 return docinfo
596 596
597 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): 597 def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
598 """path ist the path to the images it assumes that the index.meta file is one level higher.""" 598 """path ist the path to the images it assumes that the index.meta file is one level higher."""
599 logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) 599 logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
600 if docinfo is None: 600 if docinfo is None:
601 docinfo = {} 601 docinfo = {}
602 path=path.replace("/mpiwg/online","") 602 path=path.replace("/mpiwg/online","")
603 docinfo['imagePath'] = path 603 docinfo['imagePath'] = path
604 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) 604 docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
605 605
606 pathorig=path 606 pathorig=path
607 for x in range(cut): 607 for x in range(cut):
608 path=getParentDir(path) 608 path=getParentDir(path)
609 logging.error("PATH:"+path) 609 logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
610 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path 610 imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
611 docinfo['imageURL'] = imageUrl 611 docinfo['imageURL'] = imageUrl
612 612
613 #path ist the path to the images it assumes that the index.meta file is one level higher. 613 #path ist the path to the images it assumes that the index.meta file is one level higher.
614 docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) 614 docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
616 return docinfo 616 return docinfo
617 617
618 618
619 def getDocinfo(self, mode, url): 619 def getDocinfo(self, mode, url):
620 """returns docinfo depending on mode""" 620 """returns docinfo depending on mode"""
621 logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) 621 logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
622 # look for cached docinfo in session 622 # look for cached docinfo in session
623 if self.REQUEST.SESSION.has_key('docinfo'): 623 if self.REQUEST.SESSION.has_key('docinfo'):
624 docinfo = self.REQUEST.SESSION['docinfo'] 624 docinfo = self.REQUEST.SESSION['docinfo']
625 # check if its still current 625 # check if its still current
626 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url: 626 if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
627 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo) 627 logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
628 return docinfo 628 return docinfo
629 # new docinfo 629 # new docinfo
630 docinfo = {'mode': mode, 'url': url} 630 docinfo = {'mode': mode, 'url': url}
631 if mode=="texttool": #index.meta with texttool information 631 if mode=="texttool": #index.meta with texttool information
632 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) 632 docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
633 elif mode=="imagepath": 633 elif mode=="imagepath":
634 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) 634 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
635 elif mode=="filepath": 635 elif mode=="filepath":
636 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) 636 docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
637 else: 637 else:
638 logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") 638 logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
639 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) 639 raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
640 640
641 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) 641 logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
642 self.REQUEST.SESSION['docinfo'] = docinfo 642 self.REQUEST.SESSION['docinfo'] = docinfo
643 return docinfo 643 return docinfo
644 644
645 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): 645 def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
646 """returns pageinfo with the given parameters""" 646 """returns pageinfo with the given parameters"""