File:  [Repository] / cdli / cdli_files.py
Revision 1.88: download - view: text, annotated - select for diffs - revision graph
Thu Oct 2 11:42:42 2008 UTC (15 years, 8 months ago) by dwinter
Branches: MAIN
CVS tags: HEAD
*** empty log message ***

    1: """CDLI extensions of the filearchive"""    
    2: from Products.versionedFile.extVersionedFile import *
    3: from Products.ZCatalog.CatalogPathAwareness import CatalogAware
    4: from tempfile import mkstemp,mkdtemp    
    5: import os.path
    6: import os
    7: from types import *
    8: import urlparse
    9: import urllib
   10: import cgi
   11: from OFS.OrderedFolder import OrderedFolder
   12: from OFS.SimpleItem import SimpleItem
   13: import time
   14: from OFS.Folder import manage_addFolder
   15: import re
   16: from AccessControl import ClassSecurityInfo
   17: from Acquisition import Implicit
   18: from Globals import Persistent
   19: from threading import Thread
   20: from ZPublisher.HTTPRequest import HTTPRequest
   21: from ZPublisher.HTTPResponse import HTTPResponse
   22: from ZPublisher.BaseRequest import RequestContainer
   23: import threading
   24: from BTrees.OOBTree import OOBTree, OOTreeSet
   25: import logging
   26: import transaction
   27: import copy
   28: import codecs
   29: import sys
   30: from BTrees.IOBTree import IOBTree 
   31: import cdliSplitter
   32: from sets import Set
   33: import md5
   34: from DownloadBasket import DownloadBasketFinallyThread
   35:                                        
   36: def makelist(mySet):
   37:         x = list(mySet)
   38:         x.sort()
   39:         return x
   40:     
   41: def unicodify(s):
   42:     """decode str (utf-8 or latin-1 representation) into unicode object"""
   43:     if not s:
   44:         return u""
   45:     if isinstance(s, str):
   46:         try:
   47:             return s.decode('utf-8')
   48:         except:
   49:             return s.decode('latin-1')
   50:     else:
   51:         return s
   52: 
   53: def utf8ify(s):
   54:     """encode unicode object or string into byte string in utf-8 representation.
   55:        assumes string objects to be utf-8"""
   56:     if not s:
   57:         return ""
   58:     if isinstance(s, str):
   59:         return s
   60:     else:
   61:         return s.encode('utf-8')
   62: 
   63: def formatAtfHtml(l):
   64:     """escape special ATF characters for HTML"""
   65:     if not l:
   66:         return ""
   67: 
   68:     # replace &
   69:     l = l.replace('&','&')
   70:     # replace angular brackets
   71:     l = l.replace('<','&lt;')
   72:     l = l.replace('>','&gt;')
   73:     return l
   74: 
   75: def formatAtfLineHtml(l, nolemma=True):
   76:     """format ATF line for HTML"""
   77:     if not l:
   78:         return ""
   79: 
   80:     if nolemma:
   81:         # ignore lemma lines
   82:         if l.lstrip().startswith('#lem:'):
   83:             return ""
   84:     
   85:     return formatAtfHtml(l)
   86: 
   87: 
   88: 
   89: def formatAtfFullLineNum(txt, nolemma=True):
   90:     """format full line numbers in ATF text"""
   91:     # surface codes
   92:     surfaces = {'@obverse':'obv',
   93:                 '@reverse':'rev',
   94:                 '@surface':'surface',
   95:                 '@edge':'edge',
   96:                 '@left':'left',
   97:                 '@right':'right',
   98:                 '@top':'top',
   99:                 '@bottom':'bottom',
  100:                 '@face':'face',
  101:                 '@seal':'seal'}
  102: 
  103:     if not txt:
  104:         return ""
  105:     
  106:     ret = []
  107:     surf = ""
  108:     col = ""
  109:     for line in txt.splitlines():
  110:         line = unicodify(line)
  111:         if line and line[0] == '@':
  112:             # surface or column
  113:             words = line.split(' ')
  114:             if words[0] in surfaces:
  115:                 surf = line.replace(words[0],surfaces[words[0]]).strip()
  116:             
  117:             elif words[0] == '@column':
  118:                 col = ' '.join(words[1:])
  119:             
  120:         elif line and line[0] in '123456789':
  121:             # ordinary line -> add line number
  122:             line = "%s:%s:%s"%(surf,col,line)
  123:             
  124:         ret.append(line)
  125:     
  126:     return '\n'.join(ret)
  127:             
  128:             
  129: def generateXMLReturn(hash):
  130:     """erzeugt das xml file als returnwert fuer uploadATFRPC"""
  131: 
  132:     ret="<return>"
  133:     
  134:     ret+="<errors>"
  135:     for error in hash['errors']:
  136:         ret+="""<error atf="%s">%s</error>"""%error
  137:     
  138:     ret+="</errors>"
  139:     
  140:     ret+="<changes>"
  141:     for changed in hash['changed']:
  142:         ret+="""<change atf="%s">%s</change>"""%changed
  143:     ret+="</changes>"
  144:     
  145:     ret+="<newPs>"
  146:     for new in hash['newPs']:
  147:         ret+="""<new atf="%s"/>"""%new
  148:     ret+="</newPs>"
  149:     
  150:     ret+="</return>"
  151:     return ret
  152:     
  153:     
  154: def unique(s):
  155:     """Return a list of the elements in s, but without duplicates.
  156: 
  157:     For example, unique([1,2,3,1,2,3]) is some permutation of [1,2,3],
  158:     unique("abcabc") some permutation of ["a", "b", "c"], and
  159:     unique(([1, 2], [2, 3], [1, 2])) some permutation of
  160:     [[2, 3], [1, 2]].
  161: 
  162:     For best speed, all sequence elements should be hashable.  Then
  163:     unique() will usually work in linear time.
  164: 
  165:     If not possible, the sequence elements should enjoy a total
  166:     ordering, and if list(s).sort() doesn't raise TypeError it's
  167:     assumed that they do enjoy a total ordering.  Then unique() will
  168:     usually work in O(N*log2(N)) time.
  169: 
  170:     If that's not possible either, the sequence elements must support
  171:     equality-testing.  Then unique() will usually work in quadratic
  172:     time.
  173:     (from the python cookbook)
  174:     """
  175: 
  176:     n = len(s)
  177:     if n == 0:
  178:         return []
  179: 
  180:     # Try using a dict first, as that's the fastest and will usually
  181:     # work.  If it doesn't work, it will usually fail quickly, so it
  182:     # usually doesn't cost much to *try* it.  It requires that all the
  183:     # sequence elements be hashable, and support equality comparison.
  184:     u = {}
  185:     try:
  186:         for x in s:
  187:             u[x] = 1
  188:     except TypeError:
  189:         del u  # move on to the next method
  190:     else:
  191:         return u.keys()
  192: 
  193:     # We can't hash all the elements.  Second fastest is to sort,
  194:     # which brings the equal elements together; then duplicates are
  195:     # easy to weed out in a single pass.
  196:     # NOTE:  Python's list.sort() was designed to be efficient in the
  197:     # presence of many duplicate elements.  This isn't true of all
  198:     # sort functions in all languages or libraries, so this approach
  199:     # is more effective in Python than it may be elsewhere.
  200:     try:
  201:         t = list(s)
  202:         t.sort()
  203:     except TypeError:
  204:         del t  # move on to the next method
  205:     else:
  206:         assert n > 0
  207:         last = t[0]
  208:         lasti = i = 1
  209:         while i < n:
  210:             if t[i] != last:
  211:                 t[lasti] = last = t[i]
  212:                 lasti += 1
  213:             i += 1
  214:         return t[:lasti]
  215: 
  216:     # Brute force is all that's left.
  217:     u = []
  218:     for x in s:
  219:         if x not in u:
  220:             u.append(x)
  221:     return u
  222: 
  223: 
  224: class BasketContent(SimpleItem):
  225:     """classe fuer den Inhalt eines Baskets"""
  226:    
  227:     def __init__(self,content=[]):
  228:         """content"""
  229:         self.contentList=content[0:]
  230:     
  231:     def getContent(self):
  232:         """get content"""
  233:         
  234:         return self.contentList
  235:     
  236:     def setContent(self,content):
  237:         self.contentList=content[0:]
  238:     
  239:     def numberOfItems(self):
  240:         """number"""
  241:         
  242:         return len(self.getContent())
  243:         
  244:     
  245: class uploadATFfinallyThread(Thread):
  246:     """class for adding uploaded filed (temporarily stored in the staging area at /tmp"""
  247:     
  248:     def __init__(self):
  249:         """init for uploadATFfinallyThread"""
  250:         self.continueVar=True
  251:         self.returnValue=None
  252:         self.end=False
  253:         Thread.__init__(self)
  254:            
  255:     def set(self,procedure,comment="",basketname='',unlock=None,SESSION=None,username=None,serverport="8080"):
  256:         """set start values for the thread"""
  257:         self.procedure=procedure
  258:         self.comment=comment
  259:         self.basketname=basketname
  260:         self.unlock=unlock
  261:         self.SESSION=SESSION
  262:         self.username=username
  263:         self.serverport=serverport
  264:        
  265:         
  266:     def __call__(self):
  267:         """call of the thread (equals run)"""
  268:         self.run()
  269:         return True
  270:     
  271:     def getContext(self, app,serverport="8080"):
  272:         """get the context within the ZODB"""
  273:         
  274:         resp = HTTPResponse(stdout=None)
  275:         env = {
  276:             'SERVER_NAME':'localhost',
  277:             'SERVER_PORT':serverport,
  278:             'REQUEST_METHOD':'GET'
  279:             }
  280:         req = HTTPRequest(None, env, resp)
  281:         return app.__of__(RequestContainer(REQUEST = req))
  282:           
  283:         
  284:     def run(self):
  285:         """run"""
  286:         
  287:         self.result=""
  288:         #find context within ZODB
  289:         from Zope import DB
  290:         conn = DB.open()
  291:         root = conn.root()
  292:         app  = root['Application']
  293:         ctx = self.getContext(app,serverport=self.serverport)
  294: 
  295:         #add the files
  296:         self.uploadATFfinallyThread(ctx,self.procedure,comment=self.comment,basketname=self.basketname,unlock=self.unlock,SESSION=self.SESSION,username=self.username)
  297:         #commit the transactions
  298:         transaction.get().commit()
  299:         conn.close()
  300:         #set flag for end of this method
  301:         self.end=True
  302:         logging.info("ended")
  303:         return True
  304:     
  305:     def __del__(self):
  306:         """delete"""
  307:         
  308:         
  309:     
  310:     def getResult(self):
  311:         """method for accessing result"""
  312:         
  313:         return self.result
  314:      
  315:     def uploadATFfinallyThread(self,ctx,procedure,comment="",basketname='',unlock=None,RESPONSE=None,SESSION=None,username=None):
  316:         """upload the files"""
  317:         #TODO: make this configurable, at the moment, rootFolder for cdli has to be cdliRoot
  318:         ctx2=ctx.cdliRoot
  319:    
  320:         self.result+="<h2>Start processing</h2>"
  321:         
  322:         #shall I only upload the changed files?
  323:         logging.debug("uploadATFfinally procedure: %s"%procedure)
  324:         if procedure=="uploadchanged":
  325:             changed=[x[0] for x in SESSION.get('changed',[])]
  326:             uploadFns=changed+SESSION.get('newPs',[])
  327:         
  328:         #or all
  329:         elif procedure=="uploadAll":
  330:             uploadFns=[]
  331:             for x in os.listdir(SESSION['tmpdir']):
  332:                 if not x in SESSION['lockerrors']:
  333:                     uploadFns.append(x)
  334:                     
  335:         #or maybe nothing
  336:         elif procedure=="noupload":
  337:             return True
  338:         else:
  339:             uploadFns=[]
  340:             
  341:         #do first the changed files    
  342:         i=0
  343:         for fn in uploadFns:
  344:             logging.debug("uploadATFfinally uploadFn=%s"%fn)
  345:             i+=1
  346:             founds=ctx2.CDLICatalog.search({'title':fn})
  347:             if len(founds)>0:
  348:                 SESSION['author']=str(username)
  349:                 self.result="<p>Changing : %s"%fn+self.result
  350:                 logging.debug("uploadatffinallythread changing:%s"%fn+self.result)
  351:                 founds[0].getObject().manage_addCDLIFileObject('',comment,SESSION['author'],file=os.path.join(SESSION['tmpdir'],fn),from_tmp=True)
  352:             if i%200==0:
  353:                 transaction.get().commit()
  354:                 logging.debug("uploadatffinallythread changing: do commit")
  355:         
  356:         transaction.get().commit()
  357:         logging.debug("uploadatffinallythread changing: last commit")
  358: 
  359:         #now add the new files        
  360:         newPs=SESSION['newPs']
  361:         if len(newPs)>0:
  362:             tmpDir=SESSION['tmpdir']
  363:             logging.debug("uploadatffinallythread adding start")
  364:             self.result="<p>Adding files</p>"+self.result
  365:             #TODO: make this configurable, at the moment base folder for the files has to be cdli_main
  366:             ctx2.importFiles(comment=comment,author=str(username) ,folderName=tmpDir, files=newPs,ext=self)
  367:             logging.debug("uploadatffinallythread adding finished")
  368:         
  369:         #unlock locked files?
  370:         if unlock:
  371:             logging.debug("uploadatffinallythread unlocking start")
  372:             self.result="<p>Unlock files</p>"+self.result
  373:             unlockFns=[]
  374:             for x in os.listdir(SESSION['tmpdir']):
  375:                     if not x in SESSION['errors']:
  376:                         unlockFns.append(x)
  377:                         
  378:             logging.debug("unlocking have now what to unlock")
  379:                         
  380:             for fn in unlockFns:
  381:                 #logging.info("will unlock: %s"%fn)
  382:                 founds=ctx2.CDLICatalog.search({'title':fn})
  383:                 #logging.info("found it: %s"%repr(founds))
  384:                 if len(founds)>0:
  385:                     #logging.info("unlock: %s"%founds[0].getObject().getId())
  386:                     SESSION['author']=str(username)
  387:                     founds[0].getObject().lockedBy=""
  388: 
  389:             logging.debug("uploadatffinallythread unlocking done")
  390:                     
  391:         #if a basketname is given, add files to the basket
  392:         if not (basketname ==''):
  393:             logging.debug("uploadatffinallythread add to basket %s"%basketname)
  394:             self.result="<p>Add to basket</p>"+self.result
  395:             basketId=ctx2.basketContainer.getBasketIdfromName(basketname)
  396:             
  397:             if not basketId: # create new basket
  398:                 logging.debug("uploadatffinallythread create basket %s"%basketname)
  399:                 self.result="<p>Create a new basket</p>"+self.result
  400:                 ob=ctx2.basketContainer.addBasket(basketname)
  401:                 basketId=ob.getId()
  402:             basket=getattr(ctx2.basketContainer,str(basketId))
  403:             ids=os.listdir(SESSION['tmpdir'])
  404:             logging.debug("should add:"+repr(ids))
  405:             basket.addObjects(ids,deleteOld=True,username=str(username))    
  406:                
  407:         logging.debug("uploadatffinallythread uploadfinally done")
  408: 
  409:         if RESPONSE is not None:
  410:             RESPONSE.redirect(self.aq_parent.absolute_url())
  411:         
  412:         return True
  413: 
  414: class tmpStore(SimpleItem):
  415:     """simple item"""
  416:     meta_type="cdli_upload"
  417:     
  418:     def __init__(self,id):
  419:         """init tmp"""
  420:         self.id=id
  421:         
  422: class uploadATFThread(Thread):
  423:     """class for checking the files befor uploading"""
  424:     
  425:     def __init__(self):
  426:         """initialise"""
  427:         
  428:         self.continueVar=True
  429:         self.returnValue=None
  430:         
  431:         Thread.__init__(self)
  432:         
  433:         
  434:     def set(self,upload,basketId,username,idTmp,serverport="8080"):
  435:         """set start values for the thread"""
  436:         self.result=""
  437:         self.upload=upload
  438:         self.basketId=basketId
  439:         self.username=username
  440:         self.serverport=serverport
  441:         self.idTmp=idTmp
  442:         
  443:     def __call__(self):
  444:         """call method """
  445:         self.run()
  446:         return True
  447:     
  448:     def getContext(self, app,serverport="8080"):
  449:         """get the context within the ZODB"""
  450:         resp = HTTPResponse(stdout=None)
  451:         env = {
  452:             'SERVER_NAME':'localhost',
  453:             'SERVER_PORT':serverport,
  454:             'REQUEST_METHOD':'GET'
  455:             }
  456:         req = HTTPRequest(None, env, resp)
  457:         return app.__of__(RequestContainer(REQUEST = req))
  458:         
  459:     def run(self):
  460:         idTmp=self.idTmp
  461:         self.result=""
  462:         #find context within ZODB
  463:         from Zope import DB
  464:         conn = DB.open()
  465:         root = conn.root()
  466:         app  = root['Application']
  467:         ctx = self.getContext(app,serverport=self.serverport)
  468:         logging.info("run intern")
  469:         try:
  470:             logging.info("created: %s"%idTmp)
  471:             ctx.temp_folder._setObject(idTmp,tmpStore(idTmp))
  472:         except:
  473:             logging.error("thread upload: %s %s"%sys.exc_info()[0:2])
  474:             
  475:         logging.info("call thread intern")
  476:         self.uploadATFThread(ctx,self.upload,idTmp,self.basketId)
  477:      
  478:         #ctx.cdliRoot.cdli_main.tmpStore2[self.getName()[0:]]=self.returnValue
  479:         
  480:         
  481:         transaction.get().commit()
  482:        
  483:         conn.close()
  484:         
  485:         return getattr(ctx.temp_folder,idTmp)
  486:         
  487:     def getResult(self):
  488:         """method for accessing result"""
  489:         return self.result
  490:     
  491:     def uploadATFThread(self,ctx,upload,idTmp,basketId=0):
  492:         """upload an atf file"""
  493:         #TODO: add comments
  494:         #TODO: finish uploadATF
  495:         
  496:         stObj=getattr(ctx.temp_folder,idTmp)
  497:         logging.info("start, upload thread")
  498:         self.result="<html><body><h2>I got your file, start now to split it into single atf-files!</h2><p>"
  499:     
  500:         #make sure that id is a string and not an integer
  501:         basketId=str(basketId)
  502:         
  503:         #TODO: make this configurable, at the moment, rootFolder for cdli has to be cdliRoot
  504:         ctx2=ctx.cdliRoot
  505:         
  506:         #get temporary file for staging the downloaded and splitted files
  507:         dir=mkdtemp()
  508:         
  509:         
  510:         changed=[] # changed files
  511:         errors=[]  # files with errors
  512:         lockerrors=[]  # files with errors
  513: 
  514:         newPs=[]   # new p filed
  515:         psNotInCatalog=[] # files not in the catalog
  516:         
  517:         #split the uploadedd atf file
  518:         basketNameFromFile, numberOfFiles=splitatf(upload,dir,ext=self)
  519:         
  520:         #find basketId if not set
  521:         
  522:         #get active abaket
  523:         if basketId == '0':
  524:             basketObj=ctx2.basketContainer.getActiveBasket()
  525:             if basketObj:
  526:                 basketId=basketObj.getId()
  527:                 
  528:         #if there is no active basket and no basketid given, id is empty, else get besketname and length
  529:         if basketId == '0':
  530:             basketNameFromId=""
  531:             basketLen=0
  532:         else:
  533:             basketNameFromId=getattr(ctx2.basketContainer,basketId).title
  534:             basketLen=getattr(ctx2.basketContainer,basketId).getLastVersion().numberOfItems()
  535:             
  536:         logging.info("got the file, upload thread")
  537:         self.result+="""<html><body><h2>I got the files</h2><
  538:                         p>I am computing the differences to the exisiting files</p>"""
  539:                                    
  540:         #start to check the files
  541:         for fn in os.listdir(dir):
  542:             
  543:             self.result="<p>process:%s</p>"%fn+self.result
  544:             
  545:             # check if file is in the catalog
  546:             #TODO: checkCatalog is not implemented yet
  547:             if ctx2.cdli_main.checkCatalog(fn):
  548:                 psNotInCatalog.append(fn)
  549:                 
  550:             #check if p-file already at the server  
  551:             founds=ctx2.CDLICatalog.search({'title':fn})    
  552:       
  553:             #if not than add filename to the list of newfiles
  554:             
  555:             data=file(os.path.join(dir,fn)).read()
  556:             status,msg=checkFile(fn,data,dir)
  557:             #status=True
  558:             
  559:             
  560:             if not status: # error
  561:                 errors.append((fn,msg))
  562:             
  563:             else:
  564:                 if len(founds)==0:
  565:                     newPs.append(fn)
  566: 
  567:                 #if p file alread at the server    
  568:                 for found in founds:
  569:                     #analyse the differences to the actual file
  570:                     obj=found.getObject()
  571: 
  572:                     if (not (str(obj.lockedBy))=='') and (not (str(obj.lockedBy)==str(self.username))):
  573:                                 lockerrors.append((fn,str(obj.lockedBy)))
  574:                     else:
  575:                 
  576:                         diffs=obj.diff(data)
  577:                         if diffs[0]>0:
  578:                             changed.append((obj,diffs)) #hochladen
  579: 
  580:         #ready, set the returnValues
  581:         self.result+="<h3>Done</h3></body></html>"
  582:         
  583:         stObj.returnValue={}
  584:         
  585:         stObj.returnValue['errors']=errors
  586:         
  587:         stObj.returnValue['newPs']=newPs
  588:         stObj.returnValue['tmpdir']=dir
  589:         stObj.returnValue['basketLen']=basketLen
  590:         stObj.returnValue['numberOfFiles']=numberOfFiles
  591:         stObj.returnValue['basketNameFromId']=basketNameFromId
  592:         stObj.returnValue['basketNameFromFile']=basketNameFromFile
  593:         stObj.returnValue['basketId']=basketId
  594:         stObj.returnValue['dir']=dir
  595:         #stObj.returnValue['changed']=copy.copy(changed)
  596:         stObj.returnValue['changed']=[(x[0].getId(),x[1][0]) for x in changed]
  597:         #stObj.returnValue['lockerrors']=[x[0].getId() for x in lockerrors]
  598:         stObj.returnValue['lockerrors']=[x for x in lockerrors]
  599:         self.returnValue=True
  600:         #ctx2.cdli_main.setTemp('v_uploadATF_returnValue',True)
  601:     
  602:  
  603: class CDLIBasketContainer(OrderedFolder):
  604:     """contains the baskets"""
  605:     
  606: 
  607:     security=ClassSecurityInfo()
  608:     meta_type="CDLIBasketContainer"
  609:     
  610:     def getPNumbersOfBasket(self,basketName):
  611:         """get all pnumbers of a basket as a list, returns an empty list if basket not found
  612:         @param basketName: name of the basket
  613:         """
  614:         ret=[]
  615:         basketId=self.getBasketIdfromName(basketName)
  616:         if not basketId:
  617:             return []
  618:         
  619:         ob=getattr(self,basketId).getContent()
  620:         
  621:         ret=[x[0].split(".")[0] for x in ob]
  622:         
  623:         return ret
  624:     
  625:     security.declareProtected('manage','getBasketAsOneFile')       
  626:     def getBasketAsOneFile(self,basketName,current="no"):
  627:         """returns all files of the basket combined in one file
  628:         @param basketName: Name of the basket
  629:         @param current: (optional) if current is set to "yes" then the most current version of 
  630:                         all files are downloaded and not the versions of the files as stored in the basket
  631:         """
  632:         ret=""
  633:         basketId=self.getBasketIdfromName(basketName)
  634:         if not basketId:
  635:             return ""
  636:         
  637:         ob=getattr(self,basketId).getLastVersion()
  638:         for object in ob.getContent():
  639:             if current=="no": #version as they are in the basket
  640:                             ret+=str(object[0].getData())+"\n"
  641:             elif current=="yes":
  642:                             #search current object
  643:                             logging.debug("current: %s"%object[1].getId().split(".")[0])
  644:                             founds=self.CDLICatalog.search({'title':object[1].getId().split(".")[0]})
  645:                             if len(founds)>0:      
  646:                                 ret+=str(founds[0].getObject().getLastVersion().getData())+"\n"
  647:         return ret
  648:     
  649:     security.declareProtected('manage','upDateBaskets') 
  650:     def upDateBaskets(self):
  651:         """update content in to objects"""
  652:         
  653:         founds=self.ZopeFind(self,obj_metatypes=['CDLIBasketVersion'],search_sub=1)
  654: 
  655:         for found in founds:
  656:             found[1].updateBasket()
  657:         
  658:     security.declareProtected('manage','deleteBaskets')        
  659:     def deleteBaskets(self,ids=None):
  660:         """delete baskets, i.e. move them into trash folder"""
  661:         
  662:         
  663:         found=self.ZopeFind(self,obj_ids=['trash'])
  664:         
  665:         if len(found)<1:
  666:             manage_addFolder(self, 'trash')
  667:             trash=self._getOb('trash')
  668:         else:
  669:             trash=found[0][1]
  670:         
  671:         if type(ids) is not ListType:
  672:             ids=[ids]
  673:         cut=self.manage_cutObjects(ids)
  674:         trash.manage_pasteObjects(cut)
  675:         
  676:     security.declareProtected('manage','manageBaskets')       
  677:     def manageBaskets(self,submit,ids=None,basket1="",basket2="",joinBasket="",subtractBasket="",REQUEST=None,RESPONSE=None):
  678:         """manage baskets, delete or copy"""
  679:         if submit=="delete":
  680:             self.deleteBaskets(ids)
  681:         
  682:         elif submit=="join":
  683:             flag,msg=self.joinBasket(joinBasket, ids)
  684:             logging.info("joining %s %s"%(flag,msg))
  685:             
  686:         elif submit=="subtract":
  687:             logging.info("BBBb %s %s"%(basket1,basket2))
  688:             flag,msg=self.subtractBasket(subtractBasket, basket1,basket2)
  689:             logging.info("subtract %s %s"%(flag,msg))
  690:             
  691:         if RESPONSE:
  692:             RESPONSE.redirect(self.absolute_url())
  693:     
  694:     security.declareProtected('View','getBasketIdfromName')       
  695:     def getBasketIdfromName(self,basketname):
  696:         """get id from name"""
  697: 
  698:         for basket in self.ZopeFind(self,obj_metatypes=["CDLIBasket"]):
  699:             if basket[1].title==basketname:
  700:                 return basket[0]
  701:         else:
  702:             None
  703:     
  704:     security.declareProtected('manage','uploadBasket_html')        
  705:             
  706:     def uploadBasket_html(self,basketId='0'):
  707:         """upload an atf file, html form"""
  708:         
  709: 
  710:         basketId=str(basketId)
  711:         if not basketId=='0':
  712:             basketName=getattr(self.basketContainer,basketId).title
  713:         else:
  714:             basketName=""
  715:             
  716:         pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadBasket_html.zpt')).__of__(self)
  717:         return pt(basketId=basketId,basketName=basketName)
  718:    
  719: 
  720:     security.declareProtected('manage','index_html')    
  721:     def index_html(self):
  722:         """stanadard ansicht"""
  723:         
  724: 
  725: 
  726:         ext=self.ZopeFind(self,obj_ids=["index.html"])
  727:         if ext:
  728:             return ext[0][1]()
  729:         
  730:         pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','BasketContainerMain')).__of__(self)
  731:         return pt()
  732:     
  733:     def getStorageFolderRoot(self):
  734:         """root des storage folders"""
  735:         return self.cdli_main
  736:     
  737:     def __init__(self,id,title):
  738:         """ init basket container"""
  739:         self.id=id
  740:         self.title=title
  741:      
  742:  
  743:     def getBasketsId(self):
  744:         """get all baskets als klartext"""
  745:         
  746:         ret=""
  747:         baskets=self.ZopeFind(self,obj_metatypes=['CDLIBasket'])
  748:         for basket in baskets:
  749:             com,user,time,values = basket[1].getContentIds()
  750:             ret+= "BASKET:"+com+"\t"+user+"\t"+time+"\n"
  751:             for x in values:
  752:                 ret+= x[0]+"\t"+x[1]+"\n"
  753:                 return ret
  754: 
  755:     def getBaskets(self,sortField='title'):
  756:         """get all baskets files"""
  757: 
  758:         def sortName(x,y):
  759:             return cmp(x[1].title.lower(),y[1].title.lower())
  760: 
  761:         def sortDate(x,y):
  762:             return cmp(y[1].getLastVersion().getTime(),x[1].getLastVersion().getTime())
  763: 
  764:         
  765:         def sortComment(x,y):
  766: 
  767:         
  768:             
  769:              try:
  770:                 xc=getattr(x[1],'comment','ZZZZZZZZZZZZZ').lower()
  771:              except:
  772:                 xc='ZZZZZZZZZZZZZ'.lower()
  773:              try:
  774:                 yc=getattr(y[1],'comment','ZZZZZZZZZZZZZ').lower()
  775:              except:
  776:                 yc='ZZZZZZZZZZZZZ'.lower()
  777:     
  778:     
  779:              if (xc=='') or (xc=='ZZZZZZZZZZZZZ'.lower()):
  780:                  
  781:                  try:
  782:                      xc=x[1].getLastVersion().getComment().lower()
  783:                  except:
  784:                      xc='ZZZZZZZZZZZZZ'.lower()
  785:                      
  786:              if (yc=='') or (yc=='ZZZZZZZZZZZZZ'.lower()):
  787:                  try:
  788:                      yc=y[1].getLastVersion().getComment().lower()
  789:                  except:
  790:                      yc='ZZZZZZZZZZZZZ'.lower()
  791:     
  792:              
  793:                  return cmp(xc,yc)
  794:         
  795:         def sortAuthor(x,y):
  796:             
  797:             return cmp(x[1].getLastVersion().getUser().lower(),y[1].getLastVersion().getUser().lower())
  798:         
  799:         baskets=self.ZopeFind(self,obj_metatypes=['CDLIBasket'])
  800:         
  801:         
  802:         if sortField=='title':
  803:             baskets.sort(sortName)
  804:         elif sortField=='date':
  805:             baskets.sort(sortDate)
  806:         elif sortField=='author':
  807:             baskets.sort(sortAuthor)
  808:         elif sortField=='comment':
  809:             baskets.sort(sortComment)
  810: 
  811:         return baskets
  812:     
  813:         
  814:     def subtractBasket(self,newBasket,basket1,basket2):
  815:         """subtract basket2 from basket1 
  816:         (i.e. newbasket will contain alle elements of basket1 which are not in basket2), 
  817:         if basket2 contains files which are not in basket1, then theses files fill be ignored
  818:                
  819:         @param newbasket: name of the new basket
  820:         @param basket1: basket where basket2 will be subtracted from
  821:         @param basket2: see above
  822:       
  823:         """
  824:         logging.info("CCCCC %s %s"%(basket1,basket2))
  825:    
  826:         try:
  827:             newB=self.addBasket(newBasket)
  828:         except:
  829:             return False, "cannot create the new basket"
  830:         
  831:         
  832: 
  833:        
  834:      
  835:         bas2= getattr(self,basket2)            
  836:         bas2content=bas2.getContent()
  837:         bas2ids=[x[0] for x in bas2content]
  838:         
  839:        
  840:             
  841:         bas1= getattr(self,basket1)   
  842:         bas1content=bas1.getContent()
  843:         
  844:         
  845:         newBasketContent={}
  846:         
  847:         for id,version in bas1content:
  848:             if not (id in bas2ids):
  849:                 newBasketContent[id]=version
  850:         
  851:         username=self.getActualUserName()
  852:         
  853:         logging.info("sbc %s"%newBasketContent)
  854:         newB.addObjectsWithVersion(newBasketContent,username=username,catalog=self.CDLICatalog)
  855:         
  856:         return True, ""
  857:     
  858:             
  859:     def joinBasket(self,newBasket,oldBaskets):
  860:         """join two baskets
  861:         @param newbasket: name of the new basket
  862:         @param oldbaskets: list of baskets to be joined
  863:         """
  864:         try:
  865:             newB=self.addBasket(newBasket)
  866:         except:
  867:             return False, "cannot create the new basket"
  868:         
  869:         newBasketContent={}
  870:         for ob in oldBaskets:
  871:             x= getattr(self,ob,None)
  872:             if x is None:
  873:                 return False, "cannot find basket: %s"%ob
  874:             
  875:             ids=x.getContent() # hole den Inhalt
  876:             
  877:             for id,version in ids:
  878:                 if newBasketContent.has_key(id): # p number gibt's schon
  879:                     newBasketContent[id]=max(newBasketContent[id],version) # speichere die groessere Versionsnumber
  880:                 else:
  881:                     newBasketContent[id]=version
  882:         username=self.getActualUserName()
  883:         
  884:         logging.info("nbc %s"%newBasketContent)
  885:         newB.addObjectsWithVersion(newBasketContent,username=username,catalog=self.CDLICatalog)
  886:         
  887:         return True, ""
  888:     
  889:     def getNewId(self):
  890:         """createIds"""
  891:         last=getattr(self,'last',0)
  892:         last +=1
  893:         while len(self.ZopeFind(self,obj_ids=[str(last)]))>0:
  894:             last+=1
  895:     
  896:         self.last=last
  897:         return last
  898:     
  899:     def setActiveBasket(self,basketId,REQUEST=None):
  900:         """store active basketId in a cookie"""
  901:         self.REQUEST.RESPONSE.setCookie("CDLIActiveBasket",basketId,path="/")
  902:         try:
  903:             qs=cgi.parse_qs(REQUEST['QUERY_STRING'])
  904:             del(qs['basketId'])
  905:         except:
  906:             qs={}
  907:         if REQUEST:
  908:             REQUEST.RESPONSE.redirect(REQUEST['URL1']+'?'+urllib.urlencode(qs))
  909:             
  910:     def getActiveBasket(self):
  911:         """get active basket from cookie"""
  912:         
  913:         id= self.REQUEST.cookies.get('CDLIActiveBasket',None)
  914:         if id:
  915:             obj=getattr(self,str(id),None)
  916:         else:
  917:             obj=None
  918:         return obj
  919:     
  920:     def getActualUserName(self):
  921:         """get name of the actualuser"""
  922:         return str(self.REQUEST['AUTHENTICATED_USER'])
  923:     
  924:     security.declareProtected('manage','addBasket') 
  925:     def addBasket(self,newBasketName):
  926:         """add a new basket"""
  927:         
  928:         ob=manage_addCDLIBasket(self,newBasketName)
  929:         return ob
  930: 
  931:     def storeInBasket(self,submit,ids=None,newBasketName=None,fromFileList=None,RESPONSE=None,REQUEST=None):
  932:         """store it"""
  933:         if not ids:
  934:             ids=self.REQUEST.SESSION['fileIds']
  935:            
  936:         if (type(ids) is not ListType) and (not isinstance(ids,Set)):
  937:             ids=[ids]
  938:         
  939:         if isinstance(ids,Set):
  940:             ids=list(ids)
  941:             
  942:         if (submit.lower()=="store in new basket") or (submit.lower()=="new basket"):
  943:             basketRet=self.addBasket(newBasketName)
  944:             self.setActiveBasket(basketRet.getId())
  945:             basket=getattr(self,basketRet.getId())
  946:         elif (submit.lower()=="store in active basket") or (submit.lower()=="active basket"):
  947:             basket=self.getActiveBasket()
  948:         
  949:         added=basket.addObjects(ids)
  950:         back=self.REQUEST['HTTP_REFERER'].split("?")[0]+"?basketName="+basket.title+"&numberOfObjects="+str(added)
  951:         
  952:         
  953:         if fromFileList:
  954: 
  955:             return self.cdli_main.findObjectsFromList(list=ids,basketName=basket.title,numberOfObjects=added)
  956:        
  957:         if RESPONSE:
  958:             
  959:             RESPONSE.redirect(back)
  960:             
  961:         return True
  962:     
  963: def manage_addCDLIBasketContainerForm(self):
  964:     """add the CDLIBasketContainer form"""
  965:     pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','addCDLIBasketContainer.zpt')).__of__(self)
  966:     return pt()
  967: 
  968: def manage_addCDLIBasketContainer(self,id,title,RESPONSE=None):
  969:     """add the basket"""
  970:     ob=CDLIBasketContainer(id,title)
  971:     
  972:     self._setObject(id, ob)
  973:     
  974:     if RESPONSE is not None:
  975:         RESPONSE.redirect('manage_main')
  976: 
  977: class CDLIBasket(Folder,CatalogAware):
  978:     """basket"""
  979:     
  980:     meta_type="CDLIBasket"
  981:     default_catalog="CDLIBasketCatalog"
  982:     
  983:     def searchInBasket(self,indexName,searchStr,regExp=False):
  984:         """searchInBasket"""
  985: 
  986:         lst=self.searchInLineIndexDocs(indexName,searchStr,uniq=True,regExp=regExp) #TODO: fix this
  987:         ret={}
  988:         
  989:         lv=self.getLastVersion()
  990: 
  991: 
  992:         for obj in lv.content.getContent():
  993:             id=obj[1].getId().split(".")[0]
  994:             if id in lst:
  995:         
  996:                 ret[id]=self.showWordInFile(id,searchStr,lineList=self.getLinesFromIndex(indexName,searchStr,id,regExp=regExp),regExp=regExp,indexName=indexName)
  997:         
  998:         
  999:         pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','searchResultsInBasket')).__of__(self)
 1000:         return pt(result=ret,indexName=indexName,regExp=regExp,word=searchStr)
 1001:         
 1002:          
 1003:  
 1004:         
 1005:     def searchInBasket_v1(self,searchStr):
 1006:         """search occurences of searchStr in files im basket"""
 1007:         ret=[]
 1008:         lv=self.getLastVersion()
 1009:         logging.info("searching")
 1010:         for obj in lv.content.getContent():
 1011:             txt=obj[0].getData()
 1012:             for x in txt.split("\n"):
 1013:                 logging.info("search %s"%x)
 1014:                 if re.match(searchStr,x):
 1015:                     ret.append(x)
 1016:         
 1017:         return "\n".join(ret)
 1018:                 
 1019:             
 1020:     def getFile(self,obj):
 1021:         return obj[1]
 1022:     
 1023:     def getFileLastVersion(self,obj):
 1024:         return obj[0]
 1025:     
 1026:     def getFileNamesInLastVersion(self):
 1027:         """get content of the last version as list"""
 1028:         
 1029:         return [x[1].getId() for x in self.getLastVersion().getContent()]
 1030:     
 1031: 
 1032:     def isActual(self,obj):
 1033:         """teste ob im basket die aktuelle version ist"""
 1034:         try:
 1035:             logging.debug("isActual:"+repr(obj))
 1036:             actualNo=obj[1].getLastVersion().getVersionNumber()
 1037:             storedNo=obj[0].getVersionNumber()
 1038:             
 1039:            
 1040:             actualNo=self.getFileObjectLastVersion(obj.getId()).getVersionNumber()
 1041:                 
 1042:             #if len(founds)>0 and founds[0].getObject().aq_parent.getId()==".trash":
 1043:             #    return False, -1
 1044:             
 1045:             if actualNo==storedNo:
 1046:                 return True , 0
 1047:             else:
 1048:                 return False, actualNo
 1049:         except:
 1050:             return False, -1
 1051:             
 1052:     def history(self):
 1053:         """history"""  
 1054: 
 1055:         ext=self.ZopeFind(self.aq_parent,obj_ids=["history_template.html"])
 1056:         if ext:
 1057:             return getattr(self,ext[0][1].getId())()
 1058:         
 1059:         pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','BasketHistory')).__of__(self)
 1060:         return pt()
 1061:     
 1062:     def getStorageFolderRoot(self):
 1063:         """root des storage folders"""
 1064:         return self.aq_parent.cdli_main
 1065:     
 1066:     def __init__(self,id,title,shortDescription="",comment=""):
 1067:         """init a CDLIBasket"""
 1068:         
 1069:         self.id=id
 1070:         self.title=title
 1071:         self.shortDescription=shortDescription
 1072:         self.comment=comment
 1073:  
 1074:     def getActualUserName(self):
 1075:         """get name of the actualuser"""
 1076:        
 1077:         return str(self.REQUEST['AUTHENTICATED_USER'])
 1078:   
 1079:            
 1080:     def getLastVersion(self):
 1081:         """hole letzte version"""
 1082: 
 1083:         ids=[]
 1084:         idsTmp= self.objectIds()
 1085:         for x in idsTmp:
 1086:             try:
 1087:                 ids.append(int(x))
 1088:             except:
 1089:                 pass
 1090:         ids.sort()
 1091:       
 1092:         if len(ids)==0:
 1093:             return None
 1094:         else:    
 1095:             ob=getattr(self,str(ids[-1]))
 1096: 
 1097:             
 1098:             return ob
 1099:    
 1100:     def getVersions(self):
 1101:         """get versions"""
 1102:         versions=self.ZopeFind(self,obj_metatypes=["CDLIBasketVersion"])
 1103:         return versions
 1104: 
 1105:    
 1106:     def updateObjects(self,ids,RESPONSE=None,REQUEST=None):
 1107:         """update ids, ids not in the basket the add"""
 1108:         if type(ids) is not ListType:
 1109:             ids=[ids]
 1110:        
 1111:         lastVersion=self.getLastVersion() 
 1112:         oldContent=lastVersion.content.getContent()
 1113:         newContent=[]
 1114:         
 1115:         #first copy the old
 1116:         for obj in oldContent:
 1117:             if obj[1].getId() not in ids:
 1118:                 newContent.append(obj)
 1119:         #now add the new
 1120:                
 1121:         for id in ids:
 1122:             founds=self.CDLICatalog.search({'title':id})
 1123: 
 1124:             for found in founds:
 1125:                 if found.getObject() not in oldContent:
 1126:                     #TODO: was passiert wenn, man eine Object dazufŸgt, das schon da ist aber eine neuere version
 1127:                     newContent.append((found.getObject().getLastVersion(),found.getObject()))
 1128:         
 1129: 
 1130:         content=newContent 
 1131:         user=self.getActualUserName()
 1132:         
 1133:         ob=manage_addCDLIBasketVersion(self,user,comment="",basketContent=newContent)
 1134:         
 1135:         obj=self._getOb(ob.getId())
 1136:         if RESPONSE:
 1137:            
 1138:             RESPONSE.redirect(obj.absolute_url())
 1139:         
 1140:         return obj
 1141:     
 1142:     def addObjectsWithVersion(self,ids,deleteOld=None,username=None,catalog=None):
 1143:         """generate a new version of the basket with objects added, 
 1144:         hier wird jedoch nicht die letzte Version jedes Files hinzugefuegt, s
 1145:         ondern ids is ein Tupel mit der Id (d.h. der p-number) und der Versionsnummer.
 1146:         """
 1147:         logging.info("add to basket (%s)"%(self.getId()))
 1148:         lastVersion=self.getLastVersion()
 1149:         
 1150:         if not catalog:
 1151:             catalog=self.CDLICatalog
 1152:             
 1153:         if lastVersion is None:
 1154:             oldContent=[]
 1155:         else:
 1156:             oldContent=lastVersion.content.getContent()
 1157: 
 1158:         if deleteOld:
 1159:             oldContent=[]
 1160: 
 1161:         newContent=[]
 1162:         added=0
 1163:        
 1164:         for id,version in ids.iteritems():
 1165:             logging.info("adding %s %s"%(id,version))
 1166:             id=id.split(".")[0] # title nur die pnumber ohne atf
 1167:            
 1168:             try:
 1169:                 founds=catalog.search({'title':id})
 1170:             except:
 1171:                 founds=[]
 1172:             logging.info(" found %s "%(founds))
 1173:             for found in founds:
 1174:                 if found.getObject() not in oldContent:
 1175:                  
 1176:                     #TODO: was passiert wenn, man eine Object dazufŸgt, das schon da ist aber eine neuere version
 1177:                     newContent.append((found.getObject().getVersions()[version-1][1],found.getObject()))
 1178:                     added+=1
 1179: 
 1180:         content=oldContent+newContent
 1181:         if not username:
 1182:             logging.error("XXXXXXXXXXX %s"%repr(self))
 1183:             user=self.getActualUserName()
 1184:         else:
 1185:             user = username
 1186:             
 1187:         ob=manage_addCDLIBasketVersion(self,user,comment="",basketContent=content)
 1188:         logging.info("add to basket (%s) done"%(self.getId()))
 1189:         return added
 1190:     
 1191:     
 1192:     def addObjects(self,ids,deleteOld=None,username=None):
 1193:         """generate a new version of the basket with objects added"""
 1194:         
 1195:         def swap(x):
 1196:             return (x[1],x[0])
 1197:             
 1198:         logging.info("add to basket (%s)"%(self.getId()))
 1199:         lastVersion=self.getLastVersion()
 1200:         
 1201:         if lastVersion is None:
 1202:             oldContent=[]
 1203:         else:
 1204:             oldContent=lastVersion.content.getContent()
 1205: 
 1206:         if deleteOld:
 1207:             oldContent=[]
 1208: 
 1209:         added=0
 1210: #        for id in ids:
 1211: #            logging.debug("adding:"+id)
 1212: #            try:
 1213: #                founds=self.CDLICatalog.search({'title':id})
 1214: #            except:
 1215: #                founds=[]
 1216: #           
 1217: #            for found in founds:
 1218: #                if found.getObject() not in oldContent:
 1219: #                    #TODO: was passiert wenn, man eine Object dazufŸgt, das schon da ist aber eine neuere version
 1220: #                    newContent.append((found.getObject().getLastVersion(),found.getObject()))
 1221: #                    added+=1
 1222: 
 1223:         hash = md5.new(repr(makelist(ids))).hexdigest() # erzeuge hash als identification
 1224:         #logging.debug("JJJJJJJ:"+repr(self.makelist(ids)))
 1225:         logging.debug("JJJJJJJ:"+repr(hash))
 1226:                       
 1227:         if hasattr(self.cdliRoot,'v_tmpStore') and self.cdliRoot.v_tmpStore.has_key(hash): 
 1228:             logging.debug("from store!")
 1229:             newContent=Set(map(swap,self.cdliRoot.v_tmpStore[hash]))
 1230:          
 1231:         else:
 1232:             logging.debug("not from store!")
 1233:             newContent=Set([(self.getFileObjectLastVersion(x),self.getFileObject(x)) for x in ids])
 1234:         
 1235:         
 1236:         content=Set(oldContent).union(newContent)
 1237:         added = len(content)-len(oldContent)
 1238:         if not username:
 1239:             user=self.getActualUserName()
 1240:         else:
 1241:             user = username
 1242:         
 1243:         #logging.debug("content:"+repr(list(content)))
 1244:         ob=manage_addCDLIBasketVersion(self,user,comment="",basketContent=list(content))
 1245:         logging.info("add to basket (%s) done"%(self.getId()))
 1246:         return added
 1247:     
 1248:     
 1249:                 
 1250:     def getContent(self):
 1251:         """print content"""
 1252:         ret=[]
 1253:         
 1254:         lv=self.getLastVersion()
 1255:         for obj in lv.content.getContent():
 1256:             logging.info("XXXXXXXXXX %s"%repr(obj))
 1257:             ret.append((obj[1].getId(),obj[0].versionNumber))
 1258:             
 1259:         return ret
 1260:         
 1261:     def getContentIds(self):
 1262:         """print basket content"""
 1263:         ret=[]
 1264:         lv=self.getLastVersion()
 1265:         for obj in lv.content.getContent():
 1266:             ret.append((obj[0].getId(),obj[1].getId()))
 1267:         
 1268:         
 1269:         return lv.getComment(),lv.getUser(),lv.getTime(),ret
 1270: 
 1271:     def changeBasket(self,ids,submit,RESPONSE=None,REQUEST=None):
 1272:         """change a basket"""
 1273:         if submit=="update":
 1274:             return self.updateObjects(ids,RESPONSE=RESPONSE,REQUEST=REQUEST)
 1275:         elif submit=="delete":
 1276:             return self.deleteObjects(ids,RESPONSE=RESPONSE,REQUEST=REQUEST)
 1277:             
 1278:     def deleteObjects(self,ids,RESPONSE=None,REQUEST=None):
 1279:         """delete objects"""
 1280:         
 1281:         if type(ids) is not ListType:
 1282:             ids=[ids]
 1283:        
 1284:         lastVersion=self.getLastVersion() 
 1285:         oldContent=lastVersion.content.getContent()
 1286:         newContent=[]
 1287:         for obj in oldContent:
 1288:             if obj[1].getId() not in ids:
 1289:                 newContent.append(obj)
 1290:         
 1291:                 
 1292:         user=self.getActualUserName()
 1293:         
 1294:         ob=manage_addCDLIBasketVersion(self,user,comment="",basketContent=newContent)
 1295:         
 1296:         if RESPONSE:
 1297:             obj=self._getOb(ob.getId())
 1298:             RESPONSE.redirect(obj.absolute_url())
 1299:         
 1300: def manage_addCDLIBasketForm(self):
 1301:     """add the CDLIBasketContainer form"""
 1302:     pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','addCDLIBasket.zpt')).__of__(self)
 1303:     return pt()
 1304: 
 1305: def manage_addCDLIBasket(self,title,shortDescription="",comment="",RESPONSE=None):
 1306:     """add the basket"""
 1307:     
 1308:     id=str(self.getNewId())
 1309:     
 1310:     ob=CDLIBasket(id,title,shortDescription,comment)
 1311:     
 1312:     self._setObject(id, ob)
 1313:     
 1314:     if RESPONSE is not None:
 1315:         RESPONSE.redirect('manage_main')
 1316:     else:
 1317:         return ob
 1318: 
 1319: class CDLIBasketVersion(Implicit,Persistent,Folder):
 1320:     """version of a basket"""
 1321:     
 1322:     meta_type="CDLIBasketVersion"
 1323:     security=ClassSecurityInfo()
 1324:     
 1325:     def updateBasket(self):
 1326:         """update"""
 1327:         try:
 1328:             self._setObject('content',BasketContent(self.basketContent))
 1329:         except:
 1330:             try:
 1331:                 if len(self.basketContent)>0:
 1332:                     self.content.setContent(self.basketContent)
 1333:             except:
 1334:                 print "error",self.getId(),self.aq_parent.getId()
 1335:         self.basketContent=[]
 1336: 
 1337:         
 1338:     def containsNonActualFiles(self):
 1339:         """returns True if basket contains one or more non current files"""
 1340:         
 1341:         objs=self.getContent()
 1342:         for obj in objs:
 1343:             if not self.isActual(obj)[0]:
 1344:                 return True
 1345:         return False
 1346:     
 1347:     def downloadListOfPnumbers(self):
 1348:         """download pnumbers of the basket as list"""
 1349:         
 1350:         basket_name=self.aq_parent.title
 1351:         
 1352:         ids=self.getContent() # get the list of objects
 1353:         logging.error(ids)
 1354:         ret="\n".join([x[1].getId().split(".")[0] for x in ids])
 1355:         
 1356:         self.REQUEST.RESPONSE.setHeader("Content-Disposition","""attachement; filename="%s.txt" """%basket_name)
 1357:         self.REQUEST.RESPONSE.setHeader("Content-Type","application/octet-stream")
 1358:         length=len(ret)
 1359:         self.REQUEST.RESPONSE.setHeader("Content-Length",length)
 1360:         self.REQUEST.RESPONSE.write(ret)    
 1361:         
 1362:     security.declareProtected('manage','downloadObjectsAsOneFile')
 1363:     def downloadObjectsAsOneFile(self,lock=None,procedure=None,REQUEST=None,check="yes",current="no"):
 1364:         """download all selected files in one file"""
 1365:         logging.debug("doasof")
 1366:         if self.temp_folder.downloadCounterBaskets > 10000:
 1367:             return """I am sorry, currently the server has to many requests for downloads, please come back later!"""
 1368: 
 1369: 
 1370:         if (check=="yes") and self.containsNonActualFiles():
 1371:             pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','downloadObjectAsOneFile_check.zpt')).__of__(self)
 1372:             
 1373:             return pt(lock=lock)
 1374:             
 1375:         else:
 1376:             
 1377:             return self.downloadObjectsAsOneFileFinally(lock=lock,procedure=procedure,REQUEST=REQUEST,current="no")
 1378:         
 1379:     def downloadObjectsAsOneFileFinally(self,lock=None,procedure=None,REQUEST=None,current="no",repeat=None):
 1380:         """print do the download"""
 1381:  
 1382:         logging.debug("HIHHHH")
 1383:         ret=""
 1384:         lockedObjects={}
 1385: 
 1386:            
 1387:         logging.debug("lock:"+repr(lock))
 1388:         if lock:
 1389:             logging.debug("------lock:"+repr(lock))
 1390:             if str(self.REQUEST['AUTHENTICATED_USER'])=='Anonymous User':
 1391:                 
 1392:                 return "please login first"
 1393: 
 1394:             #check if a locked object exist in the basket.
 1395:             lockedObjects={}
 1396:             for object in self.content.getContent():
 1397: 
 1398:                 if (not str(object[1].lockedBy)=="") and (not (str(object[1].lockedBy)==str(self.REQUEST['AUTHENTICATED_USER']))):
 1399:                     lockedObjects[object[1].title]=repr(object[1].lockedBy)
 1400:                    
 1401:                     
 1402:             keys=lockedObjects.keys()
 1403:             
 1404:             
 1405:             if len(keys)>0 and (not procedure):
 1406:                 self.REQUEST.SESSION['lockedObjects']=lockedObjects
 1407:                 pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','lockedObjects.zpt')).__of__(self)
 1408:                 
 1409:                
 1410:                 return pt()
 1411:          
 1412:             elif not procedure: #keine fails gesperrt dann alle donwloaden
 1413:                 procedure="downloadAll" 
 1414:         
 1415:         
 1416:        
 1417:        
 1418:         threadName=repeat
 1419:         if not threadName or threadName=="":
 1420:             thread=DownloadBasketFinallyThread()
 1421:             threadName=thread.getName()[0:]
 1422: 
 1423:             if (not hasattr(self,'_v_downloadBasket')):
 1424:                                 self._v_downloadBasket={}
 1425: 
 1426: 
 1427:             self._v_downloadBasket[threadName]=thread
 1428:             logging.debug("dwonloadfinally:"+repr(self))
 1429:             basketID=self.aq_parent.aq_parent.getId()
 1430:             versionNumber=self.aq_parent.getId()
 1431:          
 1432:             if lock:
 1433:                 logging.debug("-----start locking")
 1434:                 for object in self.content.getContent():
 1435:                          if object[1].lockedBy =='':
 1436:                              object[1].lockedBy=self.REQUEST['AUTHENTICATED_USER']
 1437:                 logging.debug("-----finished locking")
 1438:                 
 1439:                     #obj.lockedBy=user
 1440:             self._v_downloadBasket[threadName].set(lock,procedure,self.REQUEST['AUTHENTICATED_USER'],current,basketID,versionNumber)
 1441: 
 1442:             self._v_downloadBasket[threadName].start()
 1443: 
 1444:             
 1445:             
 1446:             wait_template=self.aq_parent.ZopeFind(self.aq_parent,obj_ids=['wait_template'])
 1447: 
 1448:             if wait_template:
 1449:                 return wait_template[0][1]()
 1450:             pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','downloadBasketWait.zpt')).__of__(self)
 1451: 
 1452:             return pt(txt=self.absolute_url()+'/downloadObjectsAsOneFileFinally',threadName=threadName,
 1453:                                 counter=self._v_downloadBasket[threadName].getCounter(),
 1454:                                 number=self._v_downloadBasket[threadName].getNumberOfFiles())
 1455:             #_v_xmltrans.run()
 1456:         
 1457:         else:
 1458:             #recover thread, if lost
 1459:             if not hasattr(self,'_v_downloadBasket'):
 1460:                self._v_downloadBasket={}
 1461:             if not self._v_downloadBasket.get(threadName,None):
 1462:                  for thread in threading.enumerate():
 1463:                          if threadName == thread.getName():
 1464:                                        self._v_downloadBasket[threadName]=thread
 1465:                                        
 1466:             if self._v_downloadBasket.get(threadName,None) and (self._v_downloadBasket[threadName] is not None) and (not self._v_downloadBasket[threadName].end) :
 1467: 
 1468:                 wait_template=self.aq_parent.ZopeFind(self.aq_parent,obj_ids=['wait_template'])
 1469:                 if wait_template:
 1470:                         return wait_template[0][1]()
 1471:                 
 1472:                 pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','downloadBasketWait.zpt')).__of__(self)
 1473:                 return pt(txt=self.absolute_url()+'/downloadObjectsAsOneFileFinally',threadName=threadName,
 1474:                           counter=self._v_downloadBasket[threadName].getCounter(),
 1475:                           number=self._v_downloadBasket[threadName].getNumberOfFiles())
 1476:             else:
 1477:               
 1478:              
 1479:               logging.debug("FINISHED")
 1480:               if not self._v_downloadBasket.get(threadName,None):
 1481:                  for thread in threading.enumerate():
 1482:                          if threadName == thread.getName():
 1483:                                        self._v_downloadBasket[threadName]=thread
 1484:                                        
 1485:               #files = self._v_downloadBasket[threadName].result
 1486:               files=self.basketContainer.resultHash[threadName]
 1487:              # fh=file("/var/tmp/test")
 1488:               #ret =fh.read()
 1489:          
 1490:               if (not isinstance(self.aq_parent,CDLIBasket)):
 1491:                   basket_name=self.aq_parent.aq_parent.title+"_V"+self.getId()
 1492:               else:
 1493:                   basket_name=self.aq_parent.title+"_V"+self.getId()
 1494:         
 1495:         
 1496:     
 1497:                   #write basketname to header of atf file
 1498:               
 1499: 
 1500:               self.REQUEST.RESPONSE.setHeader("Content-Disposition","""attachement; filename="%s.atf" """%basket_name)
 1501:               self.REQUEST.RESPONSE.setHeader("Content-Type","application/octet-stream")
 1502:               #length=len(ret)
 1503:               #self.REQUEST.RESPONSE.setHeader("Content-Length",length)
 1504:               ret="#basket: %s\n"%basket_name
 1505:               self.REQUEST.RESPONSE.write(ret)    
 1506:               for fileName in files:
 1507:                   self.REQUEST.RESPONSE.write(file(fileName).read())
 1508:  
 1509:               del self.basketContainer.resultHash[threadName]
 1510:              
 1511:     def numberOfItems(self):
 1512:         """return anzahl der elemente im basket"""
 1513:         return self.content.numberOfItems()
 1514:     
 1515:     def getTime(self):
 1516:         """getTime"""
 1517:         #return self.bobobase_modification_time().ISO()
 1518:       
 1519:         if hasattr(self,'time'):
 1520:             return time.strftime("%Y-%m-%d %H:%M:%S",self.time)
 1521:         elif hasattr(self,'timefixed'):
 1522:             return self.timefixed
 1523:         else:
 1524:             setattr(self,'timefixed',self.bobobase_modification_time().ISO())
 1525:             return self.bobobase_modification_time().ISO()
 1526:     
 1527:     def getContent(self):
 1528:         """get Basket Content"""
 1529:         return self.content.getContent()
 1530: 
 1531:     
 1532:     def __init__(self,id,user,comment="",basketContent=[]):
 1533:         """ init a basket version"""
 1534:         self.id=id
 1535:         self.comment=comment
 1536:         self._setObject('content',BasketContent(basketContent))
 1537:         #self.basketContent=basketContent[0:]a
 1538:         self.user=user
 1539:         self.time=time.localtime()
 1540:         
 1541:     def getUser(self):
 1542:         """get user"""
 1543:         return self.user
 1544:     
 1545:     def getComment(self):
 1546:         """get Comment"""
 1547:         return self.comment
 1548:  
 1549:     security.declareProtected('manage','index_html')
 1550:     def index_html(self):
 1551:             """view the basket"""
 1552: 
 1553:             if self.REQUEST.get('change',False):
 1554:                     ob=self.aq_parent.updateObjects(self.REQUEST['change'])
 1555:                    
 1556:                     self.REQUEST.RESPONSE.redirect(ob.absolute_url())#go to new basket, because changing generates a new basket
 1557:                                         
 1558:             pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','BasketVersionMain.zpt')).__of__(self)
 1559:             return pt()
 1560:      
 1561:     def getObjUrl(self,result):
 1562:         """getUrl of the version of the object"""
 1563:         objId=result[1].getTitle()
 1564:         founds=self.CDLICatalog.search({'title':objId})
 1565:         if len(founds)>0:
 1566:              return founds[0].getObject().getLastVersion().absolute_url()
 1567:          
 1568:         else: #assume version number
 1569:             splitted=objId.split("_")
 1570:             founds=self.CDLICatalog.search({'title':splitted[1]})        
 1571:             return founds[0].getObject().getLastVersion().absolute_url()+'/'+objId
 1572:    
 1573: def manage_addCDLIBasketVersion(self,user,comment="",basketContent=[],RESPONSE=None):
 1574:     """add a version"""
 1575:     
 1576:     #check for already existing versions
 1577:  
 1578:     lastVersion=self.getLastVersion()
 1579:     if lastVersion is None:
 1580:         newId=str(1)
 1581:     else:
 1582:         newId=str(int(lastVersion.getId())+1)
 1583:     
 1584:     ob=CDLIBasketVersion(newId,user,comment,basketContent)
 1585:     
 1586:     self._setObject(newId, ob)
 1587:     
 1588:     if RESPONSE is not None:
 1589:         RESPONSE.redirect('manage_main')
 1590:     else:
 1591:         return ob
 1592:     
 1593: class CDLIFileObject(CatalogAware,extVersionedFileObject):
 1594:     """CDLI file object"""
 1595:     
 1596:     meta_type="CDLI File Object"
 1597:     default_catalog='CDLIObjectsCatalog'
 1598:     
 1599:     security=ClassSecurityInfo()
 1600:     
 1601:     security.declareProtected('manage','index_html')
 1602: 
 1603:     security.declarePublic('view')
 1604:     view = PageTemplateFile('zpt/viewCDLIFile.zpt', globals())
 1605: 
 1606:     security.declarePublic('editATF')
 1607:     editATF = PageTemplateFile('zpt/editATFFile.zpt', globals())
 1608: 
 1609:     def PrincipiaSearchSource(self):
 1610:            """Return cataloguable key for ourselves."""
 1611:            return str(self)
 1612:        
 1613:     def makeThisVersionCurrent_html(self):
 1614:         """form for mthis version current"""
 1615:         
 1616:         pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','makeThisVersionCurrent.zpt')).__of__(self)
 1617:         return pt()                 
 1618: 
 1619:     security.declarePublic('makeThisVersionCurrent')
 1620:     def makeThisVersionCurrent(self,comment,author,RESPONSE=None):
 1621:         """copy this version to current"""
 1622:         parent=self.aq_parent
 1623:         parent.manage_addVersionedFileObject(id=None,vC=comment,author=author,file=self.getData(),RESPONSE=RESPONSE)
 1624:         #newversion=parent.manage_addCDLIFileObject('',comment,author)
 1625:         #newversion.manage_upload(self.getData())
 1626:                                         
 1627:         #if RESPONSE is not None:
 1628:         #    RESPONSE.redirect(self.aq_parent.absolute_url()+'/history')
 1629: 
 1630:         return True
 1631:     
 1632:     def getFormattedData(self):
 1633:         """fromat text"""
 1634:         data=self.getData()
 1635: #        return re.sub("\s\#lem"," #lem",data) #remove return vor #lem
 1636:         return re.sub("#lem","       #lem",data) #remove return vor #lem
 1637:         
 1638:     
 1639:     security.declarePublic('getPNumber')
 1640:     def getPNumber(self):
 1641:         """get the pnumber"""
 1642:         try:
 1643:                 txt=re.match("&[Pp](\d*)\s*=([^\r\n]*)",self.getData()[0:])
 1644:         except:
 1645:                 txt=self.getData()[0:]
 1646:                 
 1647:                 return "ERROR"
 1648:         try:
 1649:             return "P"+txt.group(1)
 1650:         except:
 1651:             return "ERROR"
 1652: 
 1653:     security.declarePublic('getDesignation')
 1654:     def getDesignation(self):
 1655:         """get the designation out of the file"""
 1656:         try:
 1657:                 txt=re.match("&[Pp](\d*)\s*=([^\r\n]*)",self.getData()[0:])
 1658:         except:
 1659:                 txt=self.getData()[0:]
 1660:                 
 1661:                 return "ERROR"
 1662:         try:
 1663:             return txt.group(2)
 1664:         except:
 1665:             return "ERROR"
 1666: 
 1667:         
 1668: manage_addCDLIFileObjectForm=DTMLFile('dtml/fileAdd', globals(),Kind='CDLIFileObject',kind='CDLIFileObject', version='1')
 1669: 
 1670: def manage_addCDLIFileObject(self,id,vC='',author='', file='',title='',versionNumber=0,
 1671:                              precondition='', content_type='',
 1672:                              from_tmp=False,REQUEST=None):
 1673:     """Add a new File object.
 1674:     Creates a new File object 'id' with the contents of 'file'"""
 1675:  
 1676:     id=str(id)
 1677:     title=str(title)
 1678:     content_type=str(content_type)
 1679:     precondition=str(precondition)
 1680:     
 1681:     id, title = cookId(id, title, file)
 1682: 
 1683:     self=self.this()
 1684: 
 1685:     # First, we create the file without data:
 1686:     self._setObject(id, CDLIFileObject(id,title,versionNumber=versionNumber,versionComment=vC,time=time.localtime(),author=author))
 1687:     fob = self._getOb(id)
 1688:     
 1689:     # Now we "upload" the data.  By doing this in two steps, we
 1690:     # can use a database trick to make the upload more efficient.
 1691: 
 1692:     if file and not from_tmp:
 1693:         fob.manage_upload(file)
 1694:     elif file and from_tmp:
 1695:         fob.manage_file_upload(file) # manage_upload_from_tmp doesn't exist in ExtFile2
 1696:     #    fob.manage_upload_from_tmp(file) # manage_upload_from_tmp doesn't exist in ExtFile2
 1697:     if content_type:
 1698:         fob.content_type=content_type
 1699: 
 1700:     #logging.debug("manage_add: lastversion=%s"%self.getData())
 1701:     logging.debug("reindex1: %s in %s"%(repr(self),repr(self.default_catalog)))
 1702:     self.reindex_object()
 1703:     #logging.debug("manage_add: fob_data=%s"%fob.getData())
 1704:     logging.debug("reindex2: %s in %s"%(repr(fob), repr(fob.default_catalog)))
 1705:     fob.index_object()
 1706: 
 1707:     self.CDLIRoot.updateOrAddToFileBTree(ob)
 1708:     if REQUEST is not None:
 1709:         REQUEST['RESPONSE'].redirect(self.absolute_url()+'/manage_main')
 1710:     
 1711: 
 1712: class CDLIFile(extVersionedFile,CatalogAware):
 1713:     """CDLI file"""
 1714:     
 1715:     security=ClassSecurityInfo()
 1716:     meta_type="CDLI file"
 1717:     content_meta_type = ["CDLI File Object"]
 1718:     
 1719:     default_catalog='CDLICatalog'
 1720:     
 1721:     security.declareProtected('manage','index_html')
 1722:     
 1723:     def getLastVersionData(self):
 1724:         """get last version data"""
 1725:         return self.getData()
 1726: 
 1727:     def getLastVersionFormattedData(self):
 1728:         """get last version data"""
 1729:         return self.getContentObject().getFormattedData()
 1730: 
 1731:     def getTextId(self):
 1732:         """returns P-number of text"""
 1733:         # assuming that its the beginning of the title
 1734:         return self.title[:7]
 1735: 
 1736:     #security.declarePublic('history')
 1737:     def history(self):
 1738:         """history"""  
 1739: 
 1740:         ext=self.ZopeFind(self.aq_parent,obj_ids=["history_template.html"])
 1741:         if ext:
 1742:             return getattr(self,ext[0][1].getId())()
 1743:         
 1744:         pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','versionHistory')).__of__(self)
 1745:         return pt()
 1746: 
 1747: 
 1748:     def getBasketFromId(self,basketid, context=None):
 1749:         """get basket from id"""
 1750: 
 1751:         if not context:
 1752:             context=self
 1753:             
 1754:         for basket in self.ZopeFind(context,obj_metatypes=["CDLIBasket"]):
 1755:             if basket[0]==basketid:
 1756:                 return basket[1]
 1757:         else:
 1758:             None
 1759: 
 1760:  
 1761:     def isContainedInBaskets(self,context=None):
 1762:         """check is this file is part of any basket
 1763:         @param context: (optional) necessessary if CDLIBasketCatalog is not an (inherited) attribute of self, context.CDLIBasketCatalog
 1764:                         has to exist.
 1765:         """
 1766: 
 1767:         if not context:
 1768:             context=self
 1769:         
 1770:         ret=[]
 1771:         for x in context.CDLIBasketCatalog.search({'getFileNamesInLastVersion':self.getId()}):
 1772:             #if the basket x is deleted it seemes to be that x is sometimes still in the Catalog, why?
 1773:             try:
 1774:                 ret.append(x.getObject())
 1775:             except:
 1776:                 pass
 1777:         return ret
 1778:         #return [x.getObject() for x in context.CDLIBasketCatalog.search({'getFileNamesInLastVersion':self.getId()})]
 1779:         
 1780:         
 1781:     def _newContentObject(self, id, title='', versionNumber=0, versionComment=None, time=None, author=None):
 1782:         """factory for content objects. to be overridden in derived classes."""
 1783:         logging.debug("_newContentObject(CDLI)")
 1784:         return CDLIFileObject(id,title,versionNumber=versionNumber,versionComment=versionComment,time=time,author=author)
 1785: 
 1786: 
 1787:     def addCDLIFileObjectForm(self):
 1788:         """add a new version"""
 1789:         
 1790:         if str(self.REQUEST['AUTHENTICATED_USER']) in ["Anonymous User"]:
 1791:             return "please login first"
 1792:         if (self.lockedBy==self.REQUEST['AUTHENTICATED_USER']) or (self.lockedBy==''):
 1793:             out=DTMLFile('dtml/fileAdd', globals(),Kind='CDLIFileObject',kind='CDLIFileObject',version=self.getVersion()).__of__(self)
 1794:             return out()
 1795:         else:
 1796:             return "Sorry file is locked by somebody else"
 1797:         
 1798:     def manage_addCDLIFileObject(self,id,vC,author,
 1799:                                  file='',title='',
 1800:                                  precondition='', 
 1801:                                  content_type='',
 1802:                                  changeName='no',newName='', 
 1803:                                  come_from=None,
 1804:                                  from_tmp=False,RESPONSE=None):
 1805:         """add"""
 1806:       
 1807:         try: #TODO: der ganze vC unsinn muss ueberarbeitet werden
 1808:             vC=self.REQUEST['vC']
 1809:         except:
 1810:             pass
 1811:         
 1812:         ob = self.addContentObject(id, vC, author, file, title, changeName=changeName, newName=newName, from_tmp=from_tmp,
 1813:                                    precondition=precondition, content_type=content_type)
 1814: 
 1815:         try:
 1816:             #FIXME: wozu ist das gut?
 1817:             self.REQUEST.SESSION['objID_parent']=self.getId()
 1818:         except:
 1819:             pass
 1820:   
 1821:         #self.cdliRoot.updateOrAddToFileBTree(self)# now update the object in the cache
 1822:       
 1823:         
 1824:         if RESPONSE:
 1825:             if ob.getSize()==0:
 1826:                 self.REQUEST.SESSION['objID']=ob.getId()
 1827:                 pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','errorUploadFile')).__of__(self)
 1828:                 return pt()
 1829:             else:
 1830:                 if come_from and (come_from!=""):
 1831:                     RESPONSE.redirect(come_from+"?change="+self.getId())
 1832:                 else:
 1833:                     RESPONSE.redirect(self.REQUEST['URL2']+'?uploaded=%s'%self.title)
 1834:         else:
 1835:             return ob
 1836:         
 1837:         
 1838: def manage_addCDLIFileForm(self):
 1839:     """interface for adding the OSAS_root"""
 1840:     pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','addCDLIFile.zpt')).__of__(self)
 1841:     return pt()
 1842: 
 1843: def manage_addCDLIFile(self,id,title,lockedBy, author=None, RESPONSE=None):
 1844:     """add the OSAS_root"""
 1845:     newObj=CDLIFile(id,title,lockedBy,author)
 1846:                                         
 1847:     tryToggle=True
 1848:     tryCount=0
 1849: 
 1850:     self._setObject(id,newObj)                  
 1851:     getattr(self,id).reindex_object()
 1852:         
 1853:     if RESPONSE is not None:
 1854:         RESPONSE.redirect('manage_main')
 1855: 
 1856: 
 1857: def checkUTF8(data):
 1858:     """check utf 8"""
 1859:     try:
 1860:         data.encode('utf-8')
 1861:         return True
 1862:     except:
 1863:         return False
 1864:     
 1865: 
 1866: def checkFile(filename,data,folder):
 1867:     """check the files"""
 1868:     # first check the file name
 1869:     fn=filename.split(".") # no extension
 1870: 
 1871:     if not fn[0][0]=="P":
 1872:         return False,"P missing in the filename"
 1873:     elif len(fn[0])!=7:
 1874:         return False,"P number has not the right length 6"
 1875:     elif not checkUTF8(data):
 1876:         return False,"not utf-8"
 1877:     else:
 1878:         return True,""
 1879:     
 1880:     
 1881: def splitatf(fh,dir=None,ext=None):
 1882:     """split it"""
 1883:     ret=None
 1884:     nf=None
 1885:     i=0
 1886: 
 1887:     #ROC: why split \n first and then \r???
 1888:     if (type(fh) is StringType) or (type(fh) is UnicodeType):
 1889:         iter=fh.split("\n")
 1890:     else:
 1891:         iter=fh.readlines()
 1892:         
 1893:     for lineTmp in iter:
 1894:         lineTmp=lineTmp.replace(codecs.BOM_UTF8,'') # make sure that all BOM are removed..
 1895:         for line in lineTmp.split("\r"):
 1896:             #logging.log("Deal with: %s"%line)
 1897:             if ext:
 1898:                 i+=1
 1899:                 if (i%100)==0:
 1900:                     ext.result+="."
 1901:                 if i==10000:
 1902:                     i=0
 1903:                     ext.result+="<br>"
 1904:             #check if basket name is in the first line
 1905:             if line.find("#atf basket")>=0: #old convention
 1906:                 ret=line.replace('#atf basket ','')
 1907:                 ret=ret.split('_')[0]
 1908:             elif line.find("#basket:")>=0: #new convention
 1909:                 ret=line.replace('#basket: ','')
 1910:                 ret=ret.split('_')[0]
 1911: 
 1912:             else:
 1913:                 if (len(line.lstrip())>0) and (line.lstrip()[0]=="&"): #newfile
 1914:                     if nf:
 1915:                         nf.close() #close last file
 1916: 
 1917: 
 1918:                     filename=line[1:].split("=")[0].rstrip()+".atf"
 1919:                     if dir:
 1920:                         filename=os.path.join(dir,filename)
 1921:                     nf=file(filename,"w")
 1922:                     logging.info("open %s"%filename)
 1923:                 if nf:    
 1924:                     nf.write(line.replace("\n","")+"\n")
 1925: 
 1926:     try:        
 1927:         nf.close()
 1928:     except:
 1929:         pass
 1930:     
 1931:     if not((type(fh) is StringType) or (type(fh) is UnicodeType)):
 1932:         fh.close()
 1933:     return ret,len(os.listdir(dir))
 1934: 
 1935: 
 1936: class CDLIFileFolder(extVersionedFileFolder):
 1937:     """CDLI File Folder"""
 1938:     
 1939:     security=ClassSecurityInfo()
 1940:     meta_type="CDLI Folder"
 1941:     file_meta_type=['CDLI file']
 1942:     folder_meta_type=['CDLI Folder']
 1943: 
 1944:     file_catalog='CDLICatalog'
 1945: 
 1946:     #downloadCounter=0 # counts how many download for all files currently run, be mehr als 5 wird verweigert.
 1947:     tmpStore2={}
 1948: 
 1949:     def _newVersionedFile(self, id, title='', lockedBy=None, author=None):
 1950:         """factory for versioned files. to be overridden in derived classes."""
 1951:         logging.debug("_newVersionedFile(CDLI)")
 1952:         return CDLIFile(id, title, lockedBy=lockedBy, author=author)
 1953: 
 1954:     def setTemp(self,name,value):
 1955:         """set tmp"""
 1956: 
 1957:         setattr(self,name,value)
 1958:                                         
 1959:     deleteFileForm = PageTemplateFile("zpt/doDeleteFile", globals())
 1960:                                        
 1961:     def delete(self,ids,REQUEST=None):
 1962:         """delete these files"""
 1963:         if type(ids) is not ListType:
 1964:             ids=[ids]
 1965: 
 1966:         self.manage_delObjects(ids)
 1967:         
 1968:         if REQUEST is not None:
 1969:             return self.index_html()
 1970: 
 1971: 
 1972:     def getVersionNumbersFromIds(self,ids):
 1973:         """get the numbers of the current versions of documents described by their ids"""
 1974:         
 1975:         ret=[]
 1976:         searchStr=" OR ".join(ids)
 1977:         
 1978:         founds=self.CDLICatalog.search({'title':searchStr})
 1979:         
 1980:         for found in founds:
 1981:             lastVersion=found.getObject().getContentObject()
 1982:             ret.append((found.getId,lastVersion))
 1983:         
 1984:         return ret
 1985:     
 1986:     def getFile(self,fn):
 1987:         """get the content of the file fn"""
 1988:         logging.debug("getFile: %s"%repr(fn))
 1989:         if not self.hasObject(fn):
 1990:             # search deeper
 1991:             founds=getattr(self, self.file_catalog).search({'textid':fn})
 1992:             if founds:
 1993:                 obj=founds[0].getObject().getContentObject()
 1994:             else:
 1995:                 return "" 
 1996:         else:
 1997:             obj = self[fn].getContentObject()
 1998: 
 1999:         return obj.getData()[0:] 
 2000:  
 2001:     
 2002:     def checkCatalog(self,fn):
 2003:         """check if fn is in the catalog"""
 2004:         #TODO add checkCatalog
 2005:         
 2006:                                    
 2007:     def findObjectsFromListWithVersion(self,list,author=None):
 2008:         """find objects from a list with versions
 2009:         @param list: list of tuples  (cdliFile,version)
 2010:         """
 2011:         #self.REQUEST.SESSION['fileIds']=list#store fieldIds in session for further usage
 2012:         #self.REQUEST.SESSION['searchList']=self.REQUEST.SESSION['fileIds']
 2013:         
 2014:         pt=getattr(self,'filelistVersioned.html')
 2015:             
 2016:         return pt(search=list,author=author)
 2017:     
 2018:     
 2019:     def getAllPNumbers(self):
 2020:         """get a list of all files (resp their p-numbers) stored"""
 2021:         
 2022:         ret=[x.getId for x in  self.CDLICatalog()]
 2023:      
 2024:         return ret
 2025:     
 2026:     def expandFile(self,fileId,fileTree):
 2027:         """wildcard in fileID suche alle Treffer"""
 2028:         founds=self.CDLICatalog({'title':fileId})
 2029:         for found in founds:
 2030:             fileTree.add(found.getId)
 2031:             logging.debug("ADDD:"+found.getId)
 2032:          
 2033:     def findObjectsFromList(self,enterList=None,display=False,start=None,upload=None,list=None,basketName=None,numberOfObjects=None,RESPONSE=None,REQUEST=None,returnHash=False,hash=None):
 2034:         """findObjectsFromList (, TAB oder LINE separated)"""
 2035:                                        
 2036:         logging.debug("start: findObjectsFromList")
 2037:         #logging.debug("start: findObjectsFromList"+repr(list))
 2038:         
 2039:             
 2040:         if upload: # list from file upload
 2041:             txt=upload.read()
 2042:                                        
 2043:         if enterList:
 2044:             txt=enterList
 2045:             
 2046:         if upload or enterList:
 2047:             txt=txt.replace(",","\n")
 2048:             txt=txt.replace("\t","\n")
 2049:             txt=txt.replace("\r","\n")
 2050:             idsTmp=txt.split("\n")
 2051:             ids=[]
 2052:             for id in idsTmp: # make sure that no empty lines
 2053:                 idTmp=id.lstrip().rstrip()
 2054:                 if len(idTmp)>0:
 2055:                     
 2056:                     ids.append(idTmp)
 2057:                     
 2058:             #self.REQUEST.SESSION['ids']=" OR ".join(ids)
 2059: 
 2060:             pt=getattr(self,'filelist.html')
 2061:             self.REQUEST.SESSION['searchList']=ids
 2062:             return pt(search=ids)
 2063:         
 2064:         if basketName:
 2065:             #TODO: get rid of one of these..
 2066:             
 2067:             pt=getattr(self,'filelist.html')
 2068:             return pt(basketName=basketName,numberOfObjects=numberOfObjects)
 2069:         
 2070:         if hash is not None and hasattr(self.cdliRoot,'v_tmpStore') and self.cdliRoot.v_tmpStore.has_key(hash): 
 2071:                
 2072:                logging.debug("asking for storage2")
 2073:                result =self.cdliRoot.v_tmpStore[hash]
 2074:                if result:
 2075:                    logging.debug("give result from storage2")
 2076:                    return hash,self.cdliRoot.v_tmpStore[hash]
 2077:           
 2078:         if list is not None: # got already a list
 2079:             
 2080:             logging.debug(" ----List version")
 2081:             ret=[]
 2082:             fileTree=Set()
 2083:             
 2084:             for fileId in list:
 2085:                
 2086:                 if fileId.find("*")>-1: #check for wildcards
 2087:                         self.expandFile(fileId,fileTree)
 2088:                         
 2089:                 elif len(fileId.split("."))==1:
 2090:                         fileId=fileId+".atf"
 2091:                         fileTree.add(fileId)
 2092:                 #logging.debug("   -----:"+fileId)
 2093:                 #ret+=self.CDLICatalog({'title':fileId})
 2094:                 #x =self.getFileObject(fileId)
 2095:                 #if x is not None:
 2096:                 #    ret.append(x)
 2097:                 
 2098:             
 2099:             
 2100:             ids = fileTree & self.v_file_ids
 2101:             #self.REQUEST.SESSION['fileIds']=ids#store fieldIds in session for further usage
 2102:             l=makelist(fileTree)[0:]
 2103:             logging.debug("l-list:"+repr(l))
 2104:             self.REQUEST.SESSION['fileIds']=l#store fieldIds in session for further usage
 2105:             self.REQUEST.SESSION['searchList']=l
 2106:             #self.REQUEST.SESSION['searchList']=['P000001.atf']
 2107:           
 2108:             
 2109:             hash = md5.new(repr(makelist(fileTree))).hexdigest() # erzeuge hash als identification
 2110:             self.REQUEST.SESSION['hash']=hash
 2111:             #TODO: do I need garbage collection for v_tmpStore ?
 2112:             
 2113:             #logging.debug("Hash:"+repr(hash))
 2114: #        
 2115: #            if hasattr(self.cdliRoot,'v_tmpStore') and self.cdliRoot.v_tmpStore.has_key(hash): 
 2116: #               logging.debug("asking for storage")
 2117: #               res=self.cdliRoot.v_tmpStore[hash]
 2118: #               if res:
 2119: #                   if returnHash == True:
 2120: #                       return hash,res
 2121: #                   return res
 2122:           
 2123:             #TODO: get rid of one of these..
 2124:             #ids=[x.getObject().getId() for x in ret]
 2125:             ret=[(self.getFileObject(x),self.getFileObjectLastVersion(x)) for x in ids]
 2126:             
 2127:             #self.REQUEST.SESSION['fileIds']=ids#store fieldIds in session for further usage
 2128:             #self.REQUEST.SESSION['searchList']=self.REQUEST.SESSION['fileIds']
 2129:            
 2130:             if display:
 2131:                 pt=getattr(self,'filelist.html')
 2132:                 
 2133:                 return pt(search=ids)
 2134:             else:     
 2135:                 #self.REQUEST.SESSION['hash'] = ret # store in session 
 2136:                 if not hasattr(self,'v_tmpStore'):
 2137:                     self.cdliRoot.v_tmpStore={}
 2138:                 #logging.debug("HHHHHHNEU:"+repr(self.makelist(ids)))
 2139:                 #logging.debug("HHHHHHNEU:"+repr(hash))
 2140:                 self.cdliRoot.v_tmpStore[hash] = ret # store in session 
 2141:                 if returnHash == True:
 2142:                     return hash,ret
 2143:                 return ret
 2144:         
 2145:         
 2146:         
 2147:         if start:
 2148:             RESPONSE.redirect("filelist.html?start:int="+str(start))
 2149: 
 2150:     security.declareProtected('Manage','createAllFilesAsSingleFile')
 2151:     def createAllFilesAsSingleFile(self,RESPONSE=None):
 2152:         """download all files"""
 2153:         
 2154:         def sortF(x,y):
 2155:             return cmp(x[0],y[0])
 2156:         
 2157:         catalog=getattr(self,self.file_catalog)
 2158:         #tf,tfilename=mkstemp()
 2159:         if not hasattr(self.temp_folder,'downloadCounter'):
 2160:             self.temp_folder.downloadCounter=0
 2161: 
 2162:         if getattr(self.temp_folder,'downloadCounter',0) > 5:
 2163:             return """I am sorry, currently the server has to many requests for downloads, please come back later!"""
 2164: 
 2165:         self.temp_folder.downloadCounter+=1
 2166:         self._p_changed=1
 2167:         transaction.get().commit()
 2168:        
 2169:         list=[(x.getId,x) for x in catalog()]
 2170:         list.sort(sortF)
 2171:         
 2172: 
 2173:         
 2174:         RESPONSE.setHeader("Content-Disposition","""attachement; filename=%s"""%"all.atf")
 2175:         RESPONSE.setHeader("Content-Type","application/octet-stream")
 2176:         tmp=""
 2177:         for l in list:
 2178:             obj=l[1].getObject()
 2179:             
 2180:             if obj.meta_type=="CDLI file":
 2181:                 
 2182:                 #os.write(tf,obj.getLastVersion().data)
 2183:                 if RESPONSE:
 2184:                     RESPONSE.write(obj.getData()[0:])
 2185:                     RESPONSE.write("\n")
 2186:                 self.temp_folder.downloadCounter-=1 
 2187:                 self._p_changed=1
 2188:         transaction.get().commit()
 2189:         #os.close(tf)
 2190:         #RESPONSE.redirect(self.absolute_url()+"/downloadFile?fn="%tfilename)
 2191:         return True
 2192:     
 2193:     def downloadFile(self,fn):
 2194:         """download fn - not used yet"""
 2195:         self.REQUEST.RESPONSE.setHeader("Content-Disposition","""attachement; filename=%s"""%self.getLastVersion().getId())
 2196:         self.REQUEST.RESPONSE.setHeader("Content-Type","application/octet-stream")
 2197:         self.REQUEST.RESPONSE.write(file(fn).read())
 2198:         
 2199:       
 2200:                 
 2201:     def hasParent(self):
 2202:         """returns true falls subfolder"""
 2203:       
 2204:         if self.aq_parent.meta_type in self.folder_meta_type:
 2205:             return True
 2206:         else:
 2207:             return False
 2208:         
 2209:     def getFolders(self):
 2210:         """get all subfolders"""
 2211:         ret=[]
 2212:         folders=self.ZopeFind(self,obj_metatypes=self.folder_meta_type)
 2213:         for folder in folders:
 2214:             ret.append((folder[1],
 2215:                         len(self.ZopeFind(folder[1],obj_metatypes=self.folder_meta_type)),
 2216:                         len(self.ZopeFind(folder[1],obj_metatypes=self.file_meta_type))
 2217:                         ))
 2218:         return ret
 2219:     
 2220:             
 2221:     security.declareProtected('manage','index_html')
 2222:     def index_html(self):
 2223:         """main"""
 2224:         ext=self.ZopeFind(self,obj_ids=["index.html"])
 2225:         if ext:
 2226:             return ext[0][1]()
 2227:         
 2228:         pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','CDLIFileFolderMain')).__of__(self)
 2229:         return pt()
 2230:     
 2231:     
 2232: manage_addCDLIFileFolderForm=DTMLFile('dtml/folderAdd', globals())
 2233: 
 2234:     
 2235: def manage_addCDLIFileFolder(self, id, title='',
 2236:                      createPublic=0,
 2237:                      createUserF=0,
 2238:                      REQUEST=None):
 2239:     """Add a new Folder object with id *id*.
 2240: 
 2241:     If the 'createPublic' and 'createUserF' parameters are set to any true
 2242:     value, an 'index_html' and a 'UserFolder' objects are created respectively
 2243:     in the new folder.
 2244:     """
 2245:     ob=CDLIFileFolder()
 2246:     ob.id=str(id)
 2247:     ob.title=title
 2248:     self._setObject(id, ob)
 2249:     ob=self._getOb(id)
 2250: 
 2251:     checkPermission=getSecurityManager().checkPermission
 2252: 
 2253:     if createUserF:
 2254:         if not checkPermission('Add User Folders', ob):
 2255:             raise Unauthorized, (
 2256:                   'You are not authorized to add User Folders.'
 2257:                   )
 2258:         ob.manage_addUserFolder()
 2259: 
 2260:   
 2261:     if REQUEST is not None:
 2262:         return self.manage_main(self, REQUEST, update_menu=1)
 2263:     
 2264: class CDLIRoot(Folder):
 2265:     """main folder for cdli"""
 2266:     
 2267:     meta_type="CDLIRoot"
 2268:     downloadCounterBaskets=0 # counts the current basket downloads if counter > 10 no downloads are possible
 2269:     
 2270:     file_catalog = 'CDLICatalog'
 2271:     
 2272:     # word splitter for search
 2273:     splitter = {'words':cdliSplitter.wordSplitter(),
 2274:                 'graphemes':cdliSplitter.graphemeSplitter()}
 2275:     
 2276:     
 2277:     def viewATF(self,id,RESPONSE):
 2278:         """view an Object"""
 2279:         ob = self.CDLICatalog({'title':id})
 2280:         logging.debug(ob[0].getObject().getLastVersion().absolute_url()+"/view")
 2281:         if len(ob)>0:
 2282:             RESPONSE.redirect(ob[0].getObject().getLastVersion().absolute_url()+"/view")
 2283:         return "not found"
 2284:     
 2285:     def history(self,id,RESPONSE):
 2286:         """view an Object"""
 2287:         ob = self.CDLICatalog({'title':id})
 2288:         if len(ob)>0:
 2289:             RESPONSE.redirect(ob[0].absolute_url+"/history")
 2290:         return "not found"
 2291:     
 2292: 
 2293:     def downloadLocked(self,id,RESPONSE):
 2294:         """view an Object"""
 2295:         ob = self.CDLICatalog({'title':id})
 2296:         if len(ob)>0:
 2297:             RESPONSE.redirect(ob[0].absolute_url+"/downloadLocked")
 2298:         return "not found"
 2299:     
 2300:     def download(self,id,RESPONSE):
 2301:         """view an Object"""
 2302:         ob = self.CDLICatalog({'title':id})
 2303:         if len(ob)>0:
 2304:             RESPONSE.redirect(ob[0].getLastVersion().absolute_url())
 2305:         return "not found"
 2306:     def addCDLIFileObjectForm(self,id,RESPONSE):
 2307:         """view an Object"""
 2308:         ob = self.CDLICatalog({'title':id})
 2309:         if len(ob)>0:
 2310:             RESPONSE.redirect(ob[0].absolute_url+"/addCDLIFileObjectForm")
 2311:         return "not found"
 2312:     
 2313:     def addVersionedFileObjectForm(self,id,RESPONSE):
 2314:         """view an Object"""
 2315:         ob = self.CDLICatalog({'title':id})
 2316:         if len(ob)>0:
 2317:             RESPONSE.redirect(ob[0].absolute_url+"/addVersionedFileObjectForm")
 2318:         return "not found"
 2319:     
 2320:     def unlock(self,id,RESPONSE):
 2321:         """view an Object"""
 2322:         ob = self.CDLICatalog({'title':id})
 2323:         if len(ob)>0:
 2324:             RESPONSE.redirect(ob[0].absolute_url+"/unlock")
 2325:         return "not found"
 2326:     
 2327:     def getFileObject(self,fileId):
 2328:         """get an object"""
 2329:         x=self.v_files.get(fileId)
 2330:         #logging.debug(x)
 2331:         return x
 2332:     
 2333:     def getFileObjectLastVersion(self,fileId):
 2334:         """get an object"""
 2335:         x=self.v_files_lastVersion.get(fileId)
 2336:         #logging.debug(x)
 2337:         return x
 2338:     
 2339:     def showFileIds(self):
 2340:         """showIds"""
 2341:         return self.v_file_ids
 2342:     
 2343:     def generateFileBTree(self):
 2344:         """erzeuge einen Btree aus allen Files"""
 2345:         self.v_files = OOBTree()
 2346:         self.v_files_lastVersion = OOBTree()
 2347:         self.v_file_ids = Set()
 2348:         
 2349:         for x in self.CDLICatalog.searchResults():
 2350:             
 2351:             self.v_files.update({x.getId:x.getObject()})
 2352:             self.v_files_lastVersion.update({x.getId:x.getObject().getLastVersion()})
 2353:             self.v_file_ids.add(x.getId)
 2354:             logging.debug("add:"+x.getId+"XXX"+repr(x.getObject()))
 2355:         
 2356:         return True
 2357:     
 2358:     
 2359:     def updateOrAddToFileBTree(self,obj):
 2360:         """update a BTree"""
 2361:         self.v_files.update({obj.getId():obj})
 2362:         self.v_files_lastVersion.update({obj.getId():obj.getLastVersion()})
 2363:         
 2364:         self.v_file_ids.add(obj.getId())
 2365:         logging.debug("update:"+obj.getId()+"XXX"+repr(obj))
 2366:         
 2367:     def deleteFromBTree(self,objId):
 2368:         """delete an obj"""
 2369:         self.v_files.pop(objId)
 2370:         self.v_files_lastVersion.pop(objId)
 2371:         self.v_file_ids.remove(objId)
 2372:         
 2373: 
 2374:  
 2375:     def deleteFiles(self,ids):
 2376:         """delete files"""
 2377:         for id in ids:
 2378:             founds=self.CDLICatalog.search({'title':id.split(".")[0]})
 2379:             if founds:
 2380:                 logging.debug("deleting %s"%founds)
 2381:                 folder=founds[0].getObject().aq_parent #get the parent folder of the object
 2382:                 logging.debug("deleting from %s"%folder)
 2383:                 cut=folder.delete([founds[0].getId]) #cut it out
 2384: 
 2385: 
 2386: 
 2387:     def searchText(self, query, index='graphemes'):
 2388:         """searches query in the fulltext index and returns a list of file ids/P-numbers"""
 2389:         # see also: http://www.plope.com/Books/2_7Edition/SearchingZCatalog.stx#2-13
 2390:         logging.debug("searchtext for '%s' in index %s"%(query,index))
 2391:         #import Products.ZCTextIndex.QueryParser
 2392:         #qp = QueryParser.QueryParser()
 2393:         #logging.debug()
 2394:         idxQuery = {index:{'query':query}}
 2395:         idx = getattr(self, self.file_catalog)
 2396:         # do search
 2397:         resultset = idx.search(query_request=idxQuery,sort_index='textid')
 2398:         # put only the P-Number in the result 
 2399:         results = [res.getId[:7] for res in resultset]
 2400:         logging.debug("searchtext: found %d texts"%len(results))
 2401:         return results
 2402: 
 2403: 
 2404:     def getFile(self, pnum):
 2405:         """get the translit file with the given pnum"""
 2406:         f = getattr(self, self.file_catalog).search({'textid':pnum})
 2407:         if not f:
 2408:             return ""
 2409:         
 2410:         return f[0].getObject().getData()
 2411:          
 2412: 
 2413:     def showFile(self,fileId,wholePage=False):
 2414:         """show a file
 2415:         @param fileId: P-Number of the document to be displayed
 2416:         """
 2417:         f=getattr(self, self.file_catalog).search({'textid':fileId})
 2418:         if not f:
 2419:             return ""
 2420:         
 2421:         if wholePage:
 2422:             logging.debug("show whole page")
 2423:             return f[0].getObject().getContentObject().view()
 2424:         else:
 2425:             return f[0].getObject().getLastVersionFormattedData()
 2426:     
 2427: 
 2428:     def showWordInFile(self,fileId,word,indexName='graphemes',regExp=False,):
 2429:         """get lines with word from FileId"""
 2430:         logging.debug("showwordinfile word='%s' index=%s file=%s"%(word,indexName,fileId)) 
 2431:         
 2432:         file = formatAtfFullLineNum(self.getFile(fileId))
 2433:         ret=[]
 2434:         
 2435:         # add whitespace before and whitespace and line-end to splitter bounds expressions
 2436:         bounds = self.splitter[indexName].bounds
 2437:         splitexp = "(%s|\s)(%%s)(%s|\s|\Z)"%(bounds,bounds)
 2438:         # clean word expression 
 2439:         # TODO: this should use QueryParser itself
 2440:         # take out double quotes
 2441:         word = word.replace('"','')
 2442:         # take out ignorable signs
 2443:         ignorable = self.splitter[indexName].ignorex
 2444:         word = ignorable.sub('', word)
 2445:         # compile into regexp objects and escape parens
 2446:         wordlist = [re.compile(splitexp%re.escape(w)) for w in word.split(' ')]
 2447:             
 2448:         for line in file.splitlines():
 2449:             for word in wordlist:
 2450:                 #logging.debug("showwordinfile: searching for %s in %s"%(word.pattern,ignoreable.sub('',line)))
 2451:                 if word.search(ignorable.sub('',line)):
 2452:                     line = formatAtfLineHtml(line)
 2453:                     ret.append(line)
 2454:                     break
 2455:                     
 2456:         return ret
 2457: 
 2458:     
 2459:     def showWordInFiles(self,fileIds,word,indexName='graphemes',regExp=False):
 2460:         """
 2461:         get lines with word from all ids in list FileIds.
 2462:         returns dict with id:lines pairs.
 2463:         """
 2464:         logging.debug("showwordinfiles word='%s' index=%s file=%s"%(word,indexName,fileIds))
 2465:         
 2466:         return dict([(id,self.showWordInFile(id, word, indexName, regExp)) for id in fileIds])
 2467:     
 2468: 
 2469:     def tagWordInFile(self,fileId,word,indexName='graphemes',regExp=False):
 2470:         """get text with word highlighted from FileId"""
 2471:         logging.debug("tagwordinfile word='%s' index=%s file=%s"%(word,indexName,fileId)) 
 2472:         
 2473:         file=self.getFile(fileId)
 2474:         tagStart=u'<span class="found">'
 2475:         tagEnd=u'</span>'
 2476:         tagStr=tagStart + u'%%s' + tagEnd
 2477:         ret=[]
 2478:         
 2479:         # add whitespace to splitter bounds expressions and compile into regexp object
 2480:         bounds = self.splitter[indexName].bounds
 2481:         wordsplit = re.compile("(%s|\s)"%bounds)
 2482:         # clean word expression 
 2483:         # TODO: this should use QueryParser itself
 2484:         word = word.replace('"','') # take out double quotes
 2485:         # take out ignoreable signs
 2486:         ignorable = self.splitter[indexName].ignorex
 2487:         word = ignorable.sub('', word)
 2488:         # split search terms by blanks
 2489:         words = word.split(' ')
 2490:         # split search terms again (for grapheme search with words)
 2491:         splitwords = dict(((w,self.splitter[indexName].process([w])) for w in words))
 2492:             
 2493:         for line in file.splitlines():
 2494:             line = unicodify(line)
 2495:             # ignore lemma and other lines
 2496:             if line.lstrip().startswith('#lem:'):
 2497:                 continue
 2498:             # ignore p-num line
 2499:             if line.startswith('&P'):
 2500:                 continue
 2501:             # ignore version lines
 2502:             if line.startswith('#version'):
 2503:                 continue
 2504:             # ignore atf type lines
 2505:             if line.startswith('#atf:'):
 2506:                 continue
 2507: 
 2508:             # first scan
 2509:             hitwords = []
 2510:             for w in words:
 2511:                 if ignorable.sub('',line).find(w) > -1:
 2512:                     # word is in line
 2513:                     # append split word for grapheme search with words
 2514:                     hitwords.extend(splitwords[w])
 2515:                     #hitwords.extend(wordsplit.split(w))
 2516:                    
 2517:             # examine hits closer
 2518:             if hitwords:
 2519:                 # split line into words
 2520:                 parts = wordsplit.split(line)
 2521:                 line = ""
 2522:                 for p in parts:
 2523:                     #logging.debug("tagwordinfile: searching for %s in %s"%(p,hitwords))
 2524:                     # reassemble line
 2525:                     if ignorable.sub('', p) in hitwords:
 2526:                         #logging.debug("tagwordinfile: found %s in %s"%(p,hitwords))
 2527:                         # this part was found
 2528:                         line += tagStart + formatAtfHtml(p) + tagEnd
 2529:                     else:
 2530:                         line += formatAtfHtml(p)
 2531:                 
 2532:             else:
 2533:                 # no hits
 2534:                 line = formatAtfHtml(line)
 2535:             
 2536:             ret.append(line)
 2537:                         
 2538:         return u'<br>\n'.join(ret)
 2539: 
 2540: 
 2541: 
 2542:     def tagWordInFiles(self,fileIds,word,indexName='graphemes',regExp=False):
 2543:         """
 2544:         get texts with highlighted word from all ids in list FileIds.
 2545:         returns dict with id:text pairs.
 2546:         """
 2547:         logging.debug("tagwordinfiles word='%s' index=%s file=%s"%(word,indexName,fileIds)) 
 2548:         return dict([(id,self.tagWordInFile(id, word, indexName, regExp)) for id in fileIds])
 2549:     
 2550: 
 2551:     def getFileVersionList(self, pnum):
 2552:         """get the version history as a list for the translit file with the given pnum"""
 2553:         f = getattr(self, self.file_catalog).search({'textid':pnum})
 2554:         if not f:
 2555:             return []
 2556:         
 2557:         return f[0].getObject().getVersionList()
 2558:          
 2559: 
 2560:     def URLquote(self,str):
 2561:         """quote url"""
 2562:         return urllib.quote(str)
 2563:     
 2564:     def URLunquote(self,str):
 2565:         """unquote url"""
 2566:         return urllib.unquote(str)
 2567:     
 2568:     def URLquote_plus(self,str):
 2569:         """quote url"""
 2570:         return urllib.quote_plus(str)
 2571:     
 2572:     def URLunquote_plus(self,str):
 2573:         """unquote url"""
 2574:         return urllib.unquote_plus(str)
 2575:     
 2576:     
 2577:     def forceunlock(self):
 2578:         "break all locks"
 2579:         ret=[]
 2580:         for f in self.ZopeFind(self,obj_metatypes="CDLI file",search_sub=1):
 2581:            un=f[1].forceunlock()
 2582: 
 2583:            if un and un !="":
 2584:                ret.append((f[0],un))
 2585: 
 2586:         return ret
 2587:                                         
 2588: 
 2589:     def getChangesByAuthor(self,author,n=100):
 2590:         """getChangesByAuthor"""
 2591:         zcat=self.CDLIObjectsCatalog
 2592:         res=zcat({'lastEditor':author,
 2593:                      'sort_on':'getTime',
 2594:                      'sort_order':'descending',
 2595:                      'sort_limit':n})[:n ]
 2596:                        
 2597:         return res
 2598:     
 2599:     def getChangesByAuthor_html(self,author,n=100):
 2600:         """html output for changes by author"""
 2601:         tmp={}
 2602:         list=[]                         
 2603:         for x in self.getChangesByAuthor(author):
 2604:            nr=x.getObject().getVersionNumber()
 2605:            id=x.getObject().aq_parent.getId()
 2606:            #hinzufuegen, wenn Version neuer als die 
 2607:            if tmp.get(id,(0,0))[1] < nr:
 2608:                 tmp[id]=(x.getObject().aq_parent,nr)
 2609: 
 2610:      
 2611:         return self.cdli_main.findObjectsFromListWithVersion(list=tmp.values(),author=author)           
 2612:         
 2613:     def getLastChanges(self,n=100):
 2614:         """get the last n changes""" 
 2615:         n=int(n)                   
 2616:         zcat=self.CDLICatalog
 2617:         return zcat({'sort_on':'getLastChangeDate',
 2618:                      'sort_order':'descending',
 2619:                      'sort_limit':n})[:n ]
 2620:      
 2621:     
 2622:     def getLastChanges_html(self,n=100):
 2623:         """get the last n changes"""
 2624:         list = [x.getId for x in self.getLastChanges(n)]
 2625:         return self.cdli_main.findObjectsFromList(list=list,display=True)
 2626:                                        
 2627:     def refreshTxt(self,txt="",threadName=None):
 2628:         """txt fuer refresh"""
 2629:   
 2630:         return """ 2;url=%s?repeat=%s """%(self.absolute_url()+txt,threadName)
 2631: 
 2632:     def refreshTxtBasket(self,txt="",threadName=None):
 2633:         """txt fuer refresh"""
 2634:   
 2635:         return """ 2;url=%s?repeat=%s """%(txt,threadName)
 2636: 
 2637:     
 2638:     def getResult(self,threadName=None):
 2639:        """result of thread"""
 2640:        try:
 2641:         return self._v_uploadATF[threadName].getResult()
 2642:        except:
 2643:         return "One moment, please"
 2644:     
 2645:         
 2646:     def checkThreads(self):
 2647:         """check threads"""
 2648:         ret="<html><body>"
 2649:         for thread in threading.enumerate():
 2650:            ret+="<p>%s (%s): %s</p>"%(repr(thread),thread.getName(),thread.isAlive())
 2651:        
 2652:         return ret
 2653:                                        
 2654:                                            
 2655:     def uploadATFRPC(self,data,username):
 2656:         """upload an atffile via xml-rpc"""
 2657:         uploader=uploadATFThread()
 2658:         
 2659:         #generate an random id for the upload object
 2660:         from random import randint
 2661:         if (not self.REQUEST.SESSION.get('idTmp',None)):
 2662: 
 2663:             idTmp=str(randint(0,1000000000))
 2664:             self.REQUEST.SESSION['idTmp']=idTmp
 2665:         else:
 2666:             idTmp=self.REQUEST.SESSION.get('idTmp',None)
 2667:             
 2668:         
 2669:         uploader.set(data,0,username,idTmp)
 2670:         
 2671:         stObj=uploader.run()
 2672:         
 2673:         processor=uploadATFfinallyThread()
 2674:         
 2675:         basketname=stObj.returnValue['basketNameFromFile']
 2676:         
 2677:         processor.set("uploadchanged",basketname=basketname,SESSION=stObj.returnValue,username=username,serverport=self.REQUEST['SERVER_PORT'])
 2678:         
 2679:         processor.run()
 2680:         
 2681:         
 2682:         return generateXMLReturn(stObj.returnValue)
 2683:         
 2684:     def uploadATF(self,repeat=None,upload=None,basketId=0,RESPONSE=None):
 2685:         """upload an atf file / basket file"""
 2686:         #self._v_uploadATF.returnValue=None
 2687:         
 2688:         #generate an random id for the upload thread
 2689:         from random import randint
 2690:         if (not self.REQUEST.SESSION.get('idTmp',None)):
 2691: 
 2692:             idTmp=str(randint(0,1000000000))
 2693:             self.REQUEST.SESSION['idTmp']=idTmp
 2694:         else:
 2695:             idTmp=self.REQUEST.SESSION.get('idTmp',None)
 2696:             
 2697:     
 2698:         threadName=repeat
 2699:         if not threadName or threadName=="":
 2700:             #new thread not called from the waiting page
 2701:             tmpVar=False
 2702:        
 2703:             thread=uploadATFThread()
 2704:             threadName=thread.getName()[0:]                                
 2705:             if (not hasattr(self,'_v_uploadATF')):
 2706:                    self._v_uploadATF={}
 2707:                                        
 2708:             self._v_uploadATF[threadName]=thread
 2709:             #self._xmltrans.start()
 2710:             #thread=Thread(target=self._v_uploadATF)
 2711:             logging.info("set thread. extern")
 2712:             self._v_uploadATF[threadName].set(upload,basketId,self.REQUEST['AUTHENTICATED_USER'],idTmp,serverport=self.REQUEST['SERVER_PORT'])
 2713:             #thread.start()
 2714:             logging.info("start thread. extern")
 2715:             self._v_uploadATF[threadName].start()
 2716: 
 2717:             
 2718:             self.threadName=self._v_uploadATF[threadName].getName()[0:]
 2719:             wait_template=self.aq_parent.ZopeFind(self.aq_parent,obj_ids=['wait_template'])
 2720: 
 2721:             if wait_template:
 2722:                 return wait_template[0][1]()
 2723:             pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadATFWait.zpt')).__of__(self)
 2724:             return pt(txt='/uploadATF',threadName=threadName)
 2725:             #_v_xmltrans.run()
 2726:             
 2727:         else:
 2728:             #recover thread, if lost
 2729:             if (not hasattr(self,'_v_uploadATF')):
 2730:                self._v_uploadATF={}
 2731:             if not self._v_uploadATF.get(threadName,None):
 2732:                  for thread in threading.enumerate():
 2733:                          if threadName == thread.getName():
 2734:                                        self._v_uploadATF[threadName]=thread
 2735:                                        
 2736:             if self._v_uploadATF.get(threadName,None) and (not self._v_uploadATF[threadName].returnValue):
 2737:         
 2738: 
 2739:                 wait_template=self.aq_parent.ZopeFind(self.aq_parent,obj_ids=['wait_template'])
 2740:                 if wait_template:
 2741:                         return wait_template[0][1]()
 2742:                 
 2743:                 pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadATFWait.zpt')).__of__(self)
 2744: 
 2745:                 return pt(txt='/uploadATF',threadName=threadName)
 2746:                 
 2747:             else:
 2748:                 tmp=getattr(self.temp_folder,idTmp).returnValue
 2749:  
 2750:                 pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadCheck.zpt')).__of__(self)
 2751: 
 2752:                 return pt(changed=tmp['changed'],lockerrors=tmp['lockerrors'],errors=tmp['errors'],dir=tmp['dir'],newPs=tmp['newPs'],basketLen=tmp['basketLen'],numberOfFiles=tmp['numberOfFiles'],
 2753:                   basketNameFromId=tmp['basketNameFromId'],basketNameFromFile=tmp['basketNameFromFile'],basketId=tmp['basketId'])
 2754:                      
 2755:     def redoUpload(self,threadName):
 2756:        """redo the upload"""
 2757:        tmp=self.cdli_main.tmpStore2[threadName]
 2758:        pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadCheck.zpt')).__of__(self)
 2759:        return pt(changed=tmp['changed'],lockerrors=tmp['lockerrors'],errors=tmp['errors'],dir=tmp['dir'],newPs=tmp['newPs'],basketLen=tmp['basketLen'],numberOfFiles=tmp['numberOfFiles'],
 2760:                   basketNameFromId=tmp['basketNameFromId'],basketNameFromFile=tmp['basketNameFromFile'],basketId=tmp['basketId'])
 2761:                  
 2762:     def uploadATFfinally(self,procedure='',comment="",basketname='',unlock=None,repeat=None,RESPONSE=None):
 2763:         """nowupload the files"""
 2764:        
 2765:        
 2766:        
 2767:         threadName=repeat
 2768:         if not threadName or threadName=="":
 2769:             thread=uploadATFfinallyThread()
 2770:             threadName=thread.getName()[0:]
 2771: 
 2772:             if (not hasattr(self,'_v_uploadATF')):
 2773:                                 self._v_uploadATF={}
 2774: 
 2775: 
 2776:             self._v_uploadATF[threadName]=thread
 2777: 
 2778:             idTmp=self.REQUEST.SESSION['idTmp']
 2779:             stObj=getattr(self.temp_folder,idTmp)
 2780:             self._v_uploadATF[threadName].set(procedure,comment=comment,basketname=basketname,unlock=unlock,SESSION=stObj.returnValue,username=self.REQUEST['AUTHENTICATED_USER'],serverport=self.REQUEST['SERVER_PORT'])
 2781: 
 2782:             self._v_uploadATF[threadName].start()
 2783: 
 2784:             
 2785:             
 2786:             wait_template=self.aq_parent.ZopeFind(self.aq_parent,obj_ids=['wait_template'])
 2787: 
 2788:             if wait_template:
 2789:                 return wait_template[0][1]()
 2790:             pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadATFWait.zpt')).__of__(self)
 2791: 
 2792:             return pt(txt='/uploadATFfinally',threadName=threadName)
 2793:             #_v_xmltrans.run()
 2794:         
 2795:         else:
 2796:             #recover thread, if lost
 2797:             if not hasattr(self,'_v_uploadATF'):
 2798:                self._v_uploadATF={}
 2799:             if not self._v_uploadATF.get(threadName,None):
 2800:                  for thread in threading.enumerate():
 2801:                          if threadName == thread.getName():
 2802:                                        self._v_uploadATF[threadName]=thread
 2803:                                        
 2804:             if self._v_uploadATF.get(threadName,None) and (self._v_uploadATF[threadName] is not None) and (not self._v_uploadATF[threadName].end) :
 2805: 
 2806:                 wait_template=self.aq_parent.ZopeFind(self.aq_parent,obj_ids=['wait_template'])
 2807:                 if wait_template:
 2808:                         return wait_template[0][1]()
 2809:                 
 2810:                 pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadATFWait.zpt')).__of__(self)
 2811:                 return pt(txt='/uploadATFfinally',threadName=threadName)
 2812:             else:
 2813:               
 2814:              
 2815:               idTmp=self.REQUEST.SESSION['idTmp']
 2816:               stObj=getattr(self.temp_folder,idTmp) 
 2817:               self.REQUEST.SESSION['idTmp']=None
 2818:              
 2819:               #update changed
 2820:               logging.debug("dir:"+repr(stObj.returnValue['changed']))
 2821:               for x in stObj.returnValue['changed']:
 2822:                     ob=self.CDLICatalog.search({'title':x[0]})
 2823:                    
 2824:                     self.cdliRoot.updateOrAddToFileBTree(ob[0].getObject())
 2825:               if RESPONSE is not None:
 2826:                   RESPONSE.redirect(self.absolute_url())
 2827: 
 2828:     def importFiles(self,comment="",author="" ,folderName="/Users/dwinter/atf", files=None,ext=None):
 2829:         """import files"""
 2830:         logging.debug("importFiles folderName=%s files=%s ext=%s"%(folderName,files,ext))
 2831:         root=self.cdli_main
 2832:         count=0
 2833:         if not files:
 2834:             files=os.listdir(folderName)
 2835:             
 2836:         for f in files:
 2837:             folder=f[0:3]
 2838:             f2=f[0:5]
 2839:             
 2840:             #check if main folder PXX already exists
 2841:             obj=self.ZopeFind(root,obj_ids=[folder])
 2842:             logging.debug("importFiles: folder=%s f2=%s obj=%s"%(folder,f2,obj)) 
 2843:             if ext:
 2844:                 ext.result="<p>adding: %s </p>"%f+ext.result
 2845: 
 2846:             
 2847:             if not obj: # if not create it
 2848:                 manage_addCDLIFileFolder(root,folder,folder)
 2849:                 fobj=getattr(root,folder)
 2850:                 #transaction.get().commit()                           
 2851: 
 2852:             else:
 2853:                 fobj=obj[0][1]
 2854:             
 2855:             #check IF PYYYYY already exist
 2856:             obj2=fobj.ZopeFind(fobj,obj_ids=[f2])
 2857:             logging.debug("importFiles: fobj=%s obj2=%s"%(fobj,obj2)) 
 2858:         
 2859:             if not obj2:# if not create it
 2860:                 manage_addCDLIFileFolder(fobj,f2,f2)
 2861:                 fobj2=getattr(fobj,f2)
 2862:         
 2863:             else:
 2864:                 fobj2=obj2[0][1]
 2865:               
 2866:             # not add the file
 2867:             file2=os.path.join(folderName,f)  
 2868:             id=f
 2869:             logging.debug("importFiles: addCDLIFile fobj2=%s, f=%s file2=%s"%(fobj2,repr(f),repr(file2)))
 2870:             fobj2.addFile(vC='',file=file(file2),author=author,newName=f)
 2871:             count+=1
 2872:             
 2873:             #now add the file to the storage
 2874:             ob = getattr(fobj2,f)
 2875:             self.cdliRoot.updateOrAddToFileBTree(ob)
 2876:             
 2877:             if count%100==0:
 2878:                 logging.debug("importfiles: committing")
 2879:                 transaction.get().commit()
 2880: 
 2881:         transaction.get().commit()
 2882:         return "ok"
 2883:          
 2884: 
 2885: manage_addCDLIRootForm=DTMLFile('dtml/rootAdd', globals())
 2886: 
 2887:     
 2888: def manage_addCDLIRoot(self, id, title='',
 2889:                      createPublic=0,
 2890:                      createUserF=0,
 2891:                      REQUEST=None):
 2892:     """Add a new Folder object with id *id*.
 2893: 
 2894:     If the 'createPublic' and 'createUserF' parameters are set to any true
 2895:     value, an 'index_html' and a 'UserFolder' objects are created respectively
 2896:     in the new folder.
 2897:     """
 2898:     ob=CDLIRoot()
 2899:     ob.id=str(id)
 2900:     ob.title=title
 2901:     try:
 2902:         self._setObject(id, ob)
 2903:     except:
 2904:         pass
 2905:     ob=self._getOb(id)
 2906: 
 2907:     checkPermission=getSecurityManager().checkPermission
 2908: 
 2909:     if createUserF:
 2910:         if not checkPermission('Add User Folders', ob):
 2911:             raise Unauthorized, (
 2912:                   'You are not authorized to add User Folders.'
 2913:                   )
 2914:         ob.manage_addUserFolder()
 2915: 
 2916:   
 2917:     if REQUEST is not None:
 2918:         return self.manage_main(self, REQUEST, update_menu=1)    
 2919:  

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>