--- cdli/cdli_files.py 2006/08/24 09:28:29 1.44 +++ cdli/cdli_files.py 2007/01/30 14:26:42 1.61 @@ -1,11 +1,13 @@ """CDLI extensions of the filearchive""" -from Products.versionedFile.versionedFile import * +from Products.versionedFile.extVersionedFile import * from Products.ZCatalog.CatalogPathAwareness import CatalogAware from tempfile import mkstemp,mkdtemp import os.path import os from types import * import urlparse +import urllib +import cgi from OFS.OrderedFolder import OrderedFolder from OFS.SimpleItem import SimpleItem import time @@ -19,7 +21,80 @@ from ZPublisher.HTTPRequest import HTTPR from ZPublisher.HTTPResponse import HTTPResponse from ZPublisher.BaseRequest import RequestContainer import threading - +from BTrees.OOBTree import OOBTree +import logging +import transaction +import copy + +def unique(s): + """Return a list of the elements in s, but without duplicates. + + For example, unique([1,2,3,1,2,3]) is some permutation of [1,2,3], + unique("abcabc") some permutation of ["a", "b", "c"], and + unique(([1, 2], [2, 3], [1, 2])) some permutation of + [[2, 3], [1, 2]]. + + For best speed, all sequence elements should be hashable. Then + unique() will usually work in linear time. + + If not possible, the sequence elements should enjoy a total + ordering, and if list(s).sort() doesn't raise TypeError it's + assumed that they do enjoy a total ordering. Then unique() will + usually work in O(N*log2(N)) time. + + If that's not possible either, the sequence elements must support + equality-testing. Then unique() will usually work in quadratic + time. + (from the python cookbook) + """ + + n = len(s) + if n == 0: + return [] + + # Try using a dict first, as that's the fastest and will usually + # work. If it doesn't work, it will usually fail quickly, so it + # usually doesn't cost much to *try* it. It requires that all the + # sequence elements be hashable, and support equality comparison. + u = {} + try: + for x in s: + u[x] = 1 + except TypeError: + del u # move on to the next method + else: + return u.keys() + + # We can't hash all the elements. Second fastest is to sort, + # which brings the equal elements together; then duplicates are + # easy to weed out in a single pass. + # NOTE: Python's list.sort() was designed to be efficient in the + # presence of many duplicate elements. This isn't true of all + # sort functions in all languages or libraries, so this approach + # is more effective in Python than it may be elsewhere. + try: + t = list(s) + t.sort() + except TypeError: + del t # move on to the next method + else: + assert n > 0 + last = t[0] + lasti = i = 1 + while i < n: + if t[i] != last: + t[lasti] = last = t[i] + lasti += 1 + i += 1 + return t[:lasti] + + # Brute force is all that's left. + u = [] + for x in s: + if x not in u: + u.append(x) + return u + class BasketContent(SimpleItem): """classe fuer den Inhalt eines Baskets""" @@ -61,6 +136,7 @@ class uploadATFfinallyThread(Thread): self.SESSION=SESSION self.username=username self.serverport=serverport + def __call__(self): """call of the thread (equals run)""" @@ -94,11 +170,12 @@ class uploadATFfinallyThread(Thread): #add the files self.uploadATFfinallyThread(ctx,self.procedure,comment=self.comment,basketname=self.basketname,unlock=self.unlock,SESSION=self.SESSION,username=self.username) #commit the transactions - get_transaction().commit() + transaction.get().commit() conn.close() #set flag for end of this method self.end=True - return True + print "ended" + return True def __del__(self): """delete""" @@ -119,14 +196,14 @@ class uploadATFfinallyThread(Thread): #shall I only upload the changed files? if procedure=="uploadchanged": - - uploadFns=SESSION.get('changed',[])+SESSION.get('newPs',[]) + changed=[x[0] for x in SESSION.get('changed',[])] + uploadFns=changed+SESSION.get('newPs',[]) #or all elif procedure=="uploadAll": uploadFns=[] for x in os.listdir(SESSION['tmpdir']): - if not x in SESSION['errors']: + if not x in SESSION['lockerrors']: uploadFns.append(x) #or maybe nothing @@ -141,7 +218,7 @@ class uploadATFfinallyThread(Thread): if len(founds)>0: SESSION['author']=str(username) self.result+="

Changing : %s"%fn - founds[0].getObject().manage_addCDLIFileObject('',comment,SESSION['author'],file=file(os.path.join(SESSION['tmpdir'],fn))) + founds[0].getObject().manage_addCDLIFileObject('',comment,SESSION['author'],file=os.path.join(SESSION['tmpdir'],fn),from_tmp=True) #now add the new files @@ -188,7 +265,15 @@ class uploadATFfinallyThread(Thread): return True + +class tmpStore(SimpleItem): + """simple item""" + meta_type="cdli_upload" + def __init__(self,id): + """init tmp""" + self.id=id + class uploadATFThread(Thread): """class for checking the files befor uploading""" @@ -201,13 +286,14 @@ class uploadATFThread(Thread): Thread.__init__(self) - def set(self,upload,basketId,username,serverport="8080"): + def set(self,upload,basketId,username,idTmp,serverport="8080"): """set start values for the thread""" self.result="" self.upload=upload self.basketId=basketId self.username=username self.serverport=serverport + self.idTmp=idTmp def __call__(self): """call method """ @@ -226,7 +312,7 @@ class uploadATFThread(Thread): return app.__of__(RequestContainer(REQUEST = req)) def run(self): - + idTmp=self.idTmp self.result="" #find context within ZODB from Zope import DB @@ -234,15 +320,16 @@ class uploadATFThread(Thread): root = conn.root() app = root['Application'] ctx = self.getContext(app,serverport=self.serverport) - self.uploadATFThread(ctx,self.upload,self.basketId) + logging.info("run intern") + ctx.temp_folder._setObject(idTmp,tmpStore(idTmp)) + logging.info("call thread intern") + self.uploadATFThread(ctx,self.upload,idTmp,self.basketId) #ctx.cdliRoot.cdli_main.tmpStore2[self.getName()[0:]]=self.returnValue - - get_transaction().commit() - - while self.continueVar: - pass + + transaction.get().commit() + conn.close() @@ -250,10 +337,13 @@ class uploadATFThread(Thread): """method for accessing result""" return self.result - def uploadATFThread(self,ctx,upload,basketId=0): + def uploadATFThread(self,ctx,upload,idTmp,basketId=0): """upload an atf file""" #TODO: add comments #TODO: finish uploadATF + + stObj=getattr(ctx.temp_folder,idTmp) + logging.info("start, upload thread") self.result="

I got your file, start now to split it into single atf-files!

" #make sure that id is a string and not an integer @@ -268,6 +358,8 @@ class uploadATFThread(Thread): changed=[] # changed files errors=[] # files with errors + lockerrors=[] # files with errors + newPs=[] # new p filed psNotInCatalog=[] # files not in the catalog @@ -282,7 +374,7 @@ class uploadATFThread(Thread): if basketObj: basketId=basketObj.getId() - #if there is no active baske and no basketid given, id is empty, else get besketname and length + #if there is no active basket and no basketid given, id is empty, else get besketname and length if basketId == '0': basketNameFromId="" basketLen=0 @@ -290,7 +382,7 @@ class uploadATFThread(Thread): basketNameFromId=getattr(ctx2.basketContainer,basketId).title basketLen=getattr(ctx2.basketContainer,basketId).getLastVersion().numberOfItems() - + logging.info("got the file, upload thread") self.result+="""

I got the files

< p>I am computing the differences to the exisiting files

""" @@ -308,38 +400,51 @@ class uploadATFThread(Thread): founds=ctx2.CDLICatalog.search({'title':fn}) #if not than add filename to the list of newfiles - if len(founds)==0: - newPs.append(fn) - #if p file alread at the server - for found in founds: - #analyse the differences to the actual file - obj=found.getObject() + data=file(os.path.join(dir,fn)).read() + #status,msg=checkFile(fn,data,dir) + status=True + msg="" + if not status: # error + errors.append((fn,msg)) + else: + if len(founds)==0: + newPs.append(fn) + + #if p file alread at the server + for found in founds: + #analyse the differences to the actual file + obj=found.getObject() + + if (not (str(obj.lockedBy))=='') and (not (str(obj.lockedBy)==str(self.username))): + lockerrors.append(fn) + else: + + diffs=obj.diff(data) + if diffs[0]>0: + changed.append((obj,diffs)) #hochladen - if (not (str(obj.lockedBy))=='') and (not (str(obj.lockedBy)==str(self.username))): - errors.append(obj) - else: - data=file(os.path.join(dir,fn)).read() - diffs=obj.diff(data) - if diffs[0]>0: - changed.append((obj,diffs)) - #hochladen - #ready, set the returnValues self.result+="

Done

" - self.returnValue={} - self.returnValue['changed']=changed - self.returnValue['errors']=errors - self.returnValue['newPs']=newPs - self.returnValue['tmpdir']=dir - self.returnValue['basketLen']=basketLen - self.returnValue['numberOfFiles']=numberOfFiles - self.returnValue['basketNameFromId']=basketNameFromId - self.returnValue['basketNameFromFile']=basketNameFromFile - self.returnValue['basketId']=basketId - self.returnValue['dir']=dir + stObj.returnValue={} + stObj.returnValue['errors']=errors + + stObj.returnValue['newPs']=newPs + stObj.returnValue['tmpdir']=dir + stObj.returnValue['basketLen']=basketLen + stObj.returnValue['numberOfFiles']=numberOfFiles + stObj.returnValue['basketNameFromId']=basketNameFromId + stObj.returnValue['basketNameFromFile']=basketNameFromFile + stObj.returnValue['basketId']=basketId + stObj.returnValue['dir']=dir + #stObj.returnValue['changed']=copy.copy(changed) + stObj.returnValue['changed']=[(x[0].getId(),x[1][0]) for x in changed] + #stObj.returnValue['lockerrors']=[x[0].getId() for x in lockerrors] + print lockerrors + stObj.returnValue['lockerrors']=[x for x in lockerrors] + self.returnValue=True #ctx2.cdli_main.setTemp('v_uploadATF_returnValue',True) @@ -506,7 +611,7 @@ class BasketObject_old(Folder): """unlock all files of the testuser for debuggin""" for object in self.contents: - if str(object.lockedBy)=="test": + if str(object.lockedBy)=="dahl": object.lockedBy="" def downloadObjectsAsOneFile(self,lock=None,procedure=None,REQUEST=None): @@ -514,7 +619,10 @@ class BasketObject_old(Folder): ret="" lockedObjects={} - + + if self.temp_folder.downloadCounter > 10: + return """I am sorry, currently the server has to many requests for downloads, please come back later!""" + if lock: @@ -541,11 +649,15 @@ class BasketObject_old(Folder): elif not procedure: #keine fails gesperrt dann alle donwloaden procedure="downloadAll" - + self.temp_folder.downloadCounter+=1 + self._p_changed=1 + + transaction.get().commit() + for object in self.contents: if (procedure=="downloadAll") or (object.lockedBy=='') or (object.lockedBy==self.REQUEST['AUTHENTICATED_USER']): - ret+=object.getLastVersion().data + ret+=object.getLastVersion().getData() if lock and object.lockedBy=='': object.lockedBy=self.REQUEST['AUTHENTICATED_USER'] @@ -556,6 +668,10 @@ class BasketObject_old(Folder): length=len(ret) self.REQUEST.RESPONSE.setHeader("Content-Length",length) self.REQUEST.RESPONSE.write(ret) + self.temp_folder.downloadCounter-=1 + self._p_changed=1 + transaction.get().commit() + def manage_addBasket_oldObjectForm(self): @@ -668,7 +784,19 @@ class CDLIBasketContainer(OrderedFolder) self.id=id self.title=title - + + def getBasketsId(self): + """get all baskets als klartext""" + + ret="" + baskets=self.ZopeFind(self,obj_metatypes=['CDLIBasket']) + for basket in baskets: + com,user,time,values = basket[1].getContentIds() + ret+= "BASKET:"+com+"\t"+user+"\t"+time+"\n" + for x in values: + ret+= x[0]+"\t"+x[1]+"\n" + return ret + def getBaskets(self,sortField='title'): """get all baskets files""" @@ -742,9 +870,13 @@ class CDLIBasketContainer(OrderedFolder) def setActiveBasket(self,basketId,REQUEST=None): """store active basketId in a cookie""" self.REQUEST.RESPONSE.setCookie("CDLIActiveBasket",basketId,path="/") - + try: + qs=cgi.parse_qs(REQUEST['QUERY_STRING']) + del(qs['basketId']) + except: + qs={} if REQUEST: - REQUEST.RESPONSE.redirect(REQUEST['URL1']+'?'+REQUEST['QUERY_STRING']) + REQUEST.RESPONSE.redirect(REQUEST['URL1']+'?'+urllib.urlencode(qs)) def getActiveBasket(self): """get active basket from cookie""" @@ -948,8 +1080,10 @@ class CDLIBasket(Folder,CatalogAware): newContent=[] added=0 for id in ids: - founds=self.CDLICatalog.search({'title':id}) - + try: + founds=self.CDLICatalog.search({'title':id}) + except: + founds=[] for found in founds: if found.getObject() not in oldContent: #TODO: was passiert wenn, man eine Object dazufŸgt, das schon da ist aber eine neuere version @@ -966,6 +1100,19 @@ class CDLIBasket(Folder,CatalogAware): return added + + + + def getContentIds(self): + """print basket content""" + ret=[] + lv=self.getLastVersion() + for obj in lv.content.getContent(): + ret.append((obj[0].getId(),obj[1].getId())) + + + return lv.getComment(),lv.getUser(),lv.getTime(),ret + def changeBasket(self,ids,submit,RESPONSE=None,REQUEST=None): """change a basket""" if submit=="update": @@ -1045,19 +1192,39 @@ class CDLIBasketVersion(Implicit,Persist security.declareProtected('View','downloadObjectsAsOneFile') def downloadObjectsAsOneFile(self,lock=None,procedure=None,REQUEST=None,check="yes",current="no"): """download all selected files in one file""" - + + if self.temp_folder.downloadCounterBaskets > 10000: + return """I am sorry, currently the server has to many requests for downloads, please come back later!""" + + if (check=="yes") and self.containsNonActualFiles(): pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','downloadObjectAsOneFile_check.zpt')).__of__(self) + return pt(lock=lock) + else: + + return self.downloadObjectsAsOneFileFinally(lock=lock,procedure=procedure,REQUEST=REQUEST,current="no") + + def downloadObjectsAsOneFileFinally(self,lock=None,procedure=None,REQUEST=None,current="no"): + """print do the download""" + ret="" lockedObjects={} - + self.temp_folder.downloadCounterBaskets+=1 + self._p_changed=1 + transaction.get().commit() + if lock: if str(self.REQUEST['AUTHENTICATED_USER'])=='Anonymous User': - + self.temp_folder.downloadCounterBaskets-=1 + self._p_changed=1 + transaction.get().commit() + self.temp_folder.downloadCounterBaskets-=1 + self._p_changed=1 + transaction.get().commit() return "please login first" #check if a locked object exist in the basket. @@ -1074,38 +1241,48 @@ class CDLIBasketVersion(Implicit,Persist if len(keys)>0 and (not procedure): self.REQUEST.SESSION['lockedObjects']=lockedObjects pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','lockedObjects.zpt')).__of__(self) + + self.temp_folder.downloadCounterBaskets-=1 + self._p_changed=1 + transaction.get().commit() + return pt() elif not procedure: #keine fails gesperrt dann alle donwloaden procedure="downloadAll" + + for object in self.content.getContent(): - + if (procedure=="downloadAll") or (object[1].lockedBy=='') or (object[1].lockedBy==self.REQUEST['AUTHENTICATED_USER']): if current=="no": #version as they are in the basket - ret+=str(object[0].data)+"\n" + ret+=str(object[0].getData())+"\n" elif current=="yes": #search current object founds=self.CDLICatalog.search({'title':object[0].getId()}) if len(founds)>0: - ret+=str(founds[0].getObject().getLastVersion().data)+"\n" + ret+=str(founds[0].getObject().getLastVersion().getData())+"\n" if lock and object[1].lockedBy=='': object[1].lockedBy=self.REQUEST['AUTHENTICATED_USER'] - basket_name=self.aq_parent.title+"_V"+self.getId() #write basketname to header of atf file - ret="#atf basket %s\n"%basket_name+ret + ret="#basket: %s\n"%basket_name+ret + + self.temp_folder.downloadCounterBaskets-=1 + self._p_changed=1 + transaction.get().commit() self.REQUEST.RESPONSE.setHeader("Content-Disposition","""attachement; filename="%s.atf" """%basket_name) self.REQUEST.RESPONSE.setHeader("Content-Type","application/octet-stream") length=len(ret) self.REQUEST.RESPONSE.setHeader("Content-Length",length) self.REQUEST.RESPONSE.write(ret) + return True - def numberOfItems(self): """return anzahl der elemente im basket""" return self.content.numberOfItems() @@ -1188,7 +1365,7 @@ def manage_addCDLIBasketVersion(self,use else: return ob -class CDLIFileObject(CatalogAware,versionedFileObject): +class CDLIFileObject(CatalogAware,extVersionedFileObject): """CDLI file object""" meta_type="CDLI File Object" @@ -1223,7 +1400,12 @@ class CDLIFileObject(CatalogAware,versio return True security.declarePublic('view') - + + def getFormattedData(self): + """fromat text""" + data=self.getData() + return re.sub("\s\#lem"," #lem",data) #remove return vor #lem + def view(self): """view file""" pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','viewCDLIFile.zpt')).__of__(self) @@ -1231,11 +1413,11 @@ class CDLIFileObject(CatalogAware,versio security.declarePublic('getPNumber') def getPNumber(self): - """get the pnumber""" - try: - txt=re.match("&[Pp](\d*)\s*=([^\r\n]*)",self.data[0:]) + """get the pnumber""" + try: + txt=re.match("&[Pp](\d*)\s*=([^\r\n]*)",self.getData()[0:]) except: - txt=self.data[0:] + txt=self.getData()[0:] return "ERROR" try: @@ -1247,9 +1429,9 @@ class CDLIFileObject(CatalogAware,versio def getDesignation(self): """get the designation out of the file""" try: - txt=re.match("&[Pp](\d*)\s*=([^\r\n]*)",self.data[0:]) + txt=re.match("&[Pp](\d*)\s*=([^\r\n]*)",self.getData()[0:]) except: - txt=self.data[0:] + txt=self.getData()[0:] return "ERROR" try: @@ -1260,11 +1442,11 @@ class CDLIFileObject(CatalogAware,versio manage_addCDLIFileObjectForm=DTMLFile('dtml/fileAdd', globals(),Kind='CDLIFileObject',kind='CDLIFileObject', version='1') def manage_addCDLIFileObject(self,id,vC='',author='', file='',title='',precondition='', content_type='', - REQUEST=None): + from_tmp=False,REQUEST=None): """Add a new File object. Creates a new File object 'id' with the contents of 'file'""" - + id=str(id) title=str(title) content_type=str(content_type) @@ -1281,23 +1463,41 @@ def manage_addCDLIFileObject(self,id,vC= setattr(self._getOb(id),'author',author) + # Now we "upload" the data. By doing this in two steps, we # can use a database trick to make the upload more efficient. - if file: + + if file and not from_tmp: self._getOb(id).manage_upload(file) + elif file and from_tmp: + self._getOb(id).manage_upload_from_tmp(file) if content_type: self._getOb(id).content_type=content_type + self.reindex_object() + self._getOb(id).reindex_object() + if REQUEST is not None: REQUEST['RESPONSE'].redirect(self.absolute_url()+'/manage_main') -class CDLIFile(versionedFile,CatalogAware): +class CDLIFile(extVersionedFile,CatalogAware): """CDLI file""" meta_type="CDLI file" default_catalog='CDLICatalog' #security.declarePublic('history') + def getLastVersionData(self): + """get last version data""" + return self.getLastVersion().getData() + + def getLastVersionFormattedData(self): + """get last version data""" + return self.getLastVersion().getFormattedData() + + #security.declarePublic('history') + + def history(self): """history""" @@ -1358,8 +1558,10 @@ class CDLIFile(versionedFile,CatalogAwar precondition='', content_type='', changeName='no',newName='', - come_from=None,RESPONSE=None): + come_from=None, + from_tmp=False,RESPONSE=None): """add""" + try: #TODO: der ganze vC unsinn muss ueberarbeitet werden vC=self.REQUEST['vC'] except: @@ -1392,8 +1594,9 @@ class CDLIFile(versionedFile,CatalogAwar id=tmp[0]+"_V%i"%self.getVersion() - manage_addCDLIFileObject(self,id,vC,author,file,id,precondition, content_type) - objs=self.ZopeFind(self,obj_ids=[id])[0][1].setVersionNumber(int(self.getVersion())) + manage_addCDLIFileObject(self,id,vC,author,file,id,precondition, content_type,from_tmp=from_tmp) + #objs=self.ZopeFind(self,obj_ids=[id])[0][1].setVersionNumber(int(self.getVersion())) + objs=getattr(self,id).setVersionNumber(int(self.getVersion())) try: #FIXME: wozu ist das gut? self.REQUEST.SESSION['objID_parent']=self.getId() @@ -1433,50 +1636,80 @@ def manage_addCDLIFile(self,id,title,loc self._setObject(id,newObj) - + getattr(self,id).reindex_object() if RESPONSE is not None: RESPONSE.redirect('manage_main') +def checkFile(filename,data,folder): + """check the files""" + # first check the file name + fn=filename.split(".") # no extension + + if not fn[0][0]=="P": + return False,"P missing in the filename" + elif len(fn[0])!=7: + return False,"P number has not the right length 6" + else: + fn=os.path.join(folder,filename) + stin,out=os.popen4("/usr/bin/atfcheck.plx %s"%fn) + value=out.read() + ret= out.close() + if value: + + return False,"atf checker error: %s"%value + else: + return True,"" + def splitatf(fh,dir=None,ext=None): """split it""" ret=None nf=None i=0 - for line in fh.readlines(): - if ext: - i+=1 - if (i%100)==0: - ext.result+="." - if i==10000: - i=0 - ext.result+="
" - #check if basket name is in the first line - if line.find("#atf basket")>=0: - ret=line.replace('#atf basket ','') - ret=ret.split('_')[0] - else: - if (len(line.lstrip())>0) and (line.lstrip()[0]=="&"): #newfile - if nf: - nf.close() #close last file - - - filename=line[1:].split("=")[0].rstrip()+".atf" - if dir: - filename=os.path.join(dir,filename) - nf=file(filename,"w") - if nf: - nf.write(line) - - nf.close() + + for lineTmp in fh.readlines(): + for line in lineTmp.split("\r"): + if ext: + i+=1 + if (i%100)==0: + ext.result+="." + if i==10000: + i=0 + ext.result+="
" + #check if basket name is in the first line + if line.find("#atf basket")>=0: #old convention + ret=line.replace('#atf basket ','') + ret=ret.split('_')[0] + elif line.find("#basket:")>=0: #new convention + ret=line.replace('#basket: ','') + ret=ret.split('_')[0] + + else: + if (len(line.lstrip())>0) and (line.lstrip()[0]=="&"): #newfile + if nf: + nf.close() #close last file + + + filename=line[1:].split("=")[0].rstrip()+".atf" + if dir: + filename=os.path.join(dir,filename) + nf=file(filename,"w") + logging.info("open %s"%filename) + if nf: + nf.write(line.replace("\n","")+"\n") + + try: + nf.close() + except: + pass fh.close() return ret,len(os.listdir(dir)) -class CDLIFileFolder(versionedFileFolder): +class CDLIFileFolder(extVersionedFileFolder): """CDLI File Folder""" security=ClassSecurityInfo() @@ -1485,7 +1718,7 @@ class CDLIFileFolder(versionedFileFolder folderMetaType=['CDLI Folder'] default_catalog='CDLICatalog' defaultFileCatalog=default_catalog #wenn dieses definiert ist, wird beim hinzufŸgen einer neuen version eines files dieser catalog neuiniziert - + #downloadCounter=0 # counts how many download for all files currently run, be mehr als 5 wird verweigert. tmpStore2={} def setTemp(self,name,value): """set tmp""" @@ -1529,7 +1762,7 @@ class CDLIFileFolder(versionedFileFolder - def findObjectsFromListWithVersion(self,list): + def findObjectsFromListWithVersion(self,list,author=None): """find objects from a list with versions @param list: list of tuples (cdliFile,version) """ @@ -1542,7 +1775,7 @@ class CDLIFileFolder(versionedFileFolder pt=getattr(self,'filelistVersioned.html') - return pt(search=list) + return pt(search=list,author=author) @@ -1607,7 +1840,6 @@ class CDLIFileFolder(versionedFileFolder RESPONSE.redirect("filelist.html?start:int="+str(start)) - security.declareProtected('Manage','createAllFilesAsSingleFile') def createAllFilesAsSingleFile(self,RESPONSE=None): """download all files""" @@ -1617,14 +1849,24 @@ class CDLIFileFolder(versionedFileFolder catalog=getattr(self,self.default_catalog) #tf,tfilename=mkstemp() - - + if not hasattr(self.temp_folder,'downloadCounter'): + self.temp_folder.downloadCounter=0 + + if getattr(self.temp_folder,'downloadCounter',0) > 5: + return """I am sorry, currently the server has to many requests for downloads, please come back later!""" + + self.temp_folder.downloadCounter+=1 + self._p_changed=1 + transaction.get().commit() + list=[(x.getId,x) for x in catalog()] list.sort(sortF) + + RESPONSE.setHeader("Content-Disposition","""attachement; filename=%s"""%"all.atf") RESPONSE.setHeader("Content-Type","application/octet-stream") - + tmp="" for l in list: obj=l[1].getObject() @@ -1632,7 +1874,10 @@ class CDLIFileFolder(versionedFileFolder #os.write(tf,obj.getLastVersion().data) if RESPONSE: - RESPONSE.write(obj.getLastVersion().data[0:]) + RESPONSE.write(obj.getLastVersion().getData()[0:]) + self.temp_folder.downloadCounter-=1 + self._p_changed=1 + transaction.get().commit() #os.close(tf) #RESPONSE.redirect(self.absolute_url()+"/downloadFile?fn="%tfilename) return True @@ -1665,16 +1910,6 @@ class CDLIFileFolder(versionedFileFolder return ret - def getFolders_OLD(self): - """get all subfolders""" - ret=[] - folders=self.ZopeFind(self,obj_metatypes=self.folderMetaType) - for folder in folders: - ret.append((folder[1], - len(self.ZopeFind(folder[1],obj_metatypes=self.folderMetaType)), - len(getattr(self,self.default_catalog)({'path':folder[0]})) - )) - return ret security.declareProtected('View','index_html') def index_html(self): """main""" @@ -1722,7 +1957,173 @@ class CDLIRoot(Folder): """main folder for cdli""" meta_type="CDLIRoot" + downloadCounterBaskets=0# counts the current basket downloads if counter > 10 no downloads are possible + + def findWordRegExp(self,searchTerm): + """find all words in index which match regexp in SearchTerm""" + ret=[] + for x in self.lineIndex.iterkeys(): + if re.match(searchTerm,x): + ret.append(x) + return ret + def searchRegExpInLineIndexDocs(self,searchTerm): + """search in inLineIndex with regexp""" + if not searchTerm: + return [] + ret=[] + words=self.findWordRegExp(searchTerm) # suche nach allen Treffern + logging.info("wd:%s"%words) + for word in words: + ret+=self.searchInLineIndexDocs(word) + + return unique(ret) + + def showInLineIndex(self): + """get the index for debug purposes""" + print "show" + for x in self.lineIndex.iterkeys(): + logging.info("word:%s"%repr(x)) + #for y in self.lineIndex[x].iterkeys(): + # print "doc",repr(y),repr(self.lineIndex[x][y]) + + return self.lineIndex + + def searchInLineIndexDocs(self,word,uniq=True,regExp=False): + """search occurences""" + + if regExp: + return self.searchRegExpInLineIndexDocs(word) + + try: + lst=list(self.lineIndex.get(word).keys()) + except: + lst=[] + if uniq: + return unique(lst) + else: + return lst + + def getLinesFromIndex(self,word,doc,regExp=False): + """get lines""" + if not regExp: + return self.lineIndex.get(word)[doc] + else: # wenn regexp, suche welches word + for w in self.findWordRegExp(word): + if self.lineIndex.get(w): # ein word in im dex gefunden + try: + dc=self.lineIndex.get(word)[doc] + return dc # und ein document dann gib es zurueck + except: + pass #andernfalls weiter + + def cleanInLineIndex(self): + """delete InlineIndex""" + for x in list(self.lineIndex.keys()): + del(self.lineIndex[x]) + print [x for x in self.lineIndex.keys()] + + return "ok" + + def storeInLineIndex(self,key,value): + """store in index""" + + if (not hasattr(self,'lineIndex')) or (type(self.lineIndex) is DictType): + self.lineIndex=OOBTree() + li=self.lineIndex + + if li.has_key(key): + +# if li[key].has_key(value[0]) and (not (value[1] in li[key][value[0]])): + if li[key].has_key(value[0]): + tmp=li[key][value[0]] + tmp.append(value[1]) # add it if now in the array + li[key][value[0]]=tmp[0:] + else: + li[key][value[0]]=[value[1]] # new array for lines + + else: + + li[key]=OOBTree()# new btree for lines + li[key][value[0]]=[value[1]] + + + self.lineIndex=li + + transaction.get().commit() + + + def showFile(self,fileId): + """show a file""" + f=self.CDLICatalog({'title':fileId}) + if not f: + return "" + + return f[0].getObject().getLastVersionFormattedData() + + def showLineFromFile(self,fileId,lineNum,word): + """get line lineNum fromFileId""" + + file=self.showFile(fileId) + #str="^%s\.[^%s\.]*%s[^\n]*\n"%(lineNum,lineNum,word) + #str="^%s\..*?%s[^\n]*\n"%(lineNum,word) + + #print str + #m=re.search(str,file,flags=re.M|re.DOTALL) + #if m: + # return m.group() + #else: + # return "" + #ret=lineNum+"." + #splitted=file.split(lineNum+".") + #if len(splitted)>1: + #for part in splitted[1:]: + #if part.find(word)>-1: + # for x in part.split("\n"): + #ret+=x + #if x.find(word)>-1: + #break + #break; + #return ret + + def showWordInFile(self,fileId,word,lineList=None): + """get lines with word fromFileId""" + + file=self.showFile(fileId) + + ret=[] + for line in file.split("\n"): + if line.find(word)>-1: + if lineList: #liste of moeglichen Zeilennummern + num=line.split(".")[0] #Zeilenummer ist alles vor dem . in der Zeile + + if num in lineList: + + ret.append(line) + else: # nimm alles ohne line check + ret.append(line) + return ret + + def tagWordInFile(self,fileId,word,lineList=None): + """get lines with word fromFileId""" + + file=self.showFile(fileId) + tagStr="""%s""" + ret=[] + for line in file.split("\n"): + if line.find(word)>-1: + if lineList: #liste of moeglichen Zeilennummern + num=line.split(".")[0] #Zeilenummer ist alles vor dem . in der Zeile + + if num in lineList: + + ret.append(line.replace(word,tagStr%word)) + else: # nimm alles ohne line check + ret.append(line.replace(word,tagStr%word)) + else: + ret.append(line) + return "
\n".join(ret) + def URLquote(self,str): """quote url""" return urllib.quote(str) @@ -1731,6 +2132,14 @@ class CDLIRoot(Folder): """unquote url""" return urllib.unquote(str) + def URLquote_plus(self,str): + """quote url""" + return urllib.quote_plus(str) + + def URLunquote_plus(self,str): + """unquote url""" + return urllib.unquote_plus(str) + def forceunlock(self): "break all locks" @@ -1740,7 +2149,19 @@ class CDLIRoot(Folder): if un and un !="": ret.append((f[0],un)) - print ret + + return ret + + def forceDahl(self): + "break all locks" + ret=[] + for f in self.ZopeFind(self,obj_metatypes="CDLI file",search_sub=1): + if str(f[1].lockedBy)=="dahl": + un=f[1].forceunlock() + + if un and un !="": + ret.append((f[0],un)) + return ret def getChangesByAuthor(self,author,n=100): @@ -1765,7 +2186,7 @@ class CDLIRoot(Folder): tmp[id]=(x.getObject().aq_parent,nr) - return self.cdli_main.findObjectsFromListWithVersion(list=tmp.values()) + return self.cdli_main.findObjectsFromListWithVersion(list=tmp.values(),author=author) def getLastChanges(self,n=100): """get the last n changes""" @@ -1799,7 +2220,7 @@ class CDLIRoot(Folder): """check threads""" ret="" for thread in threading.enumerate(): - ret+="

%s : %s

"%(repr(thread),thread.isAlive()) + ret+="

%s (%s): %s

"%(repr(thread),thread.getName(),thread.isAlive()) return ret @@ -1808,7 +2229,14 @@ class CDLIRoot(Folder): def uploadATF(self,repeat=None,upload=None,basketId=0,RESPONSE=None): """standard ausgabe""" #self._v_uploadATF.returnValue=None + from random import randint + if (not self.REQUEST.SESSION.get('idTmp',None)): + idTmp=str(randint(0,1000000000)) + self.REQUEST.SESSION['idTmp']=idTmp + else: + idTmp=self.REQUEST.SESSION.get('idTmp',None) + threadName=repeat if not threadName or threadName=="": tmpVar=False @@ -1821,9 +2249,10 @@ class CDLIRoot(Folder): self._v_uploadATF[threadName]=thread #self._xmltrans.start() #thread=Thread(target=self._v_uploadATF) - - self._v_uploadATF[threadName].set(upload,basketId,self.REQUEST['AUTHENTICATED_USER'],serverport=self.REQUEST['SERVER_PORT']) + logging.info("set thread. extern") + self._v_uploadATF[threadName].set(upload,basketId,self.REQUEST['AUTHENTICATED_USER'],idTmp,serverport=self.REQUEST['SERVER_PORT']) #thread.start() + logging.info("start thread. extern") self._v_uploadATF[threadName].start() @@ -1845,7 +2274,7 @@ class CDLIRoot(Folder): if threadName == thread.getName(): self._v_uploadATF[threadName]=thread - if not self._v_uploadATF[threadName].returnValue: + if self._v_uploadATF.get(threadName,None) and (not self._v_uploadATF[threadName].returnValue): wait_template=self.aq_parent.ZopeFind(self.aq_parent,obj_ids=['wait_template']) @@ -1864,31 +2293,29 @@ class CDLIRoot(Folder): # tmp[key]=self._v_uploadATF[threadName].returnValue[key][0:] # else: # tmp[key]=self._v_uploadATF[threadName].returnValue[key] -# print repr(tmp[key]),repr(key) +# repr(tmp[key]),repr(key) # # # #tmp=self.cdli_main.tmpStore2[threadName] - tmp=self._v_uploadATF[threadName].returnValue - #self._v_uploadATF[threadName].continueVar=False + tmp=getattr(self.temp_folder,idTmp).returnValue + + - self.REQUEST.SESSION['changed']=[x[0].getId() for x in tmp['changed']] - self.REQUEST.SESSION['errors']=[x.getId() for x in tmp['errors']] - self.REQUEST.SESSION['newPs']=tmp['newPs'] - self.REQUEST.SESSION['tmpdir']=tmp['dir'] + #del(self.cdli_main.tmpStore2[threadName]) pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadCheck.zpt')).__of__(self) - return pt(changed=tmp['changed'],errors=tmp['errors'],dir=tmp['dir'],newPs=tmp['newPs'],basketLen=tmp['basketLen'],numberOfFiles=tmp['numberOfFiles'], + return pt(changed=tmp['changed'],lockerrors=tmp['lockerrors'],errors=tmp['errors'],dir=tmp['dir'],newPs=tmp['newPs'],basketLen=tmp['basketLen'],numberOfFiles=tmp['numberOfFiles'], basketNameFromId=tmp['basketNameFromId'],basketNameFromFile=tmp['basketNameFromFile'],basketId=tmp['basketId']) def redoUpload(self,threadName): """redo the upload""" tmp=self.cdli_main.tmpStore2[threadName] pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadCheck.zpt')).__of__(self) - return pt(changed=tmp['changed'],errors=tmp['errors'],dir=tmp['dir'],newPs=tmp['newPs'],basketLen=tmp['basketLen'],numberOfFiles=tmp['numberOfFiles'], + return pt(changed=tmp['changed'],lockerrors=tmp['lockerrors'],errors=tmp['errors'],dir=tmp['dir'],newPs=tmp['newPs'],basketLen=tmp['basketLen'],numberOfFiles=tmp['numberOfFiles'], basketNameFromId=tmp['basketNameFromId'],basketNameFromFile=tmp['basketNameFromFile'],basketId=tmp['basketId']) def uploadATFfinally(self,procedure='',comment="",basketname='',unlock=None,repeat=None,RESPONSE=None): @@ -1902,13 +2329,14 @@ class CDLIRoot(Folder): threadName=thread.getName()[0:] if (not hasattr(self,'_v_uploadATF')): - self._v_uploadATF={} + self._v_uploadATF={} self._v_uploadATF[threadName]=thread - - self._v_uploadATF[threadName].set(procedure,comment=comment,basketname=basketname,unlock=unlock,SESSION=self.REQUEST.SESSION,username=self.REQUEST['AUTHENTICATED_USER'],serverport=self.REQUEST['SERVER_PORT']) + idTmp=self.REQUEST.SESSION['idTmp'] + stObj=getattr(self.temp_folder,idTmp) + 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']) self._v_uploadATF[threadName].start() @@ -1941,14 +2369,14 @@ class CDLIRoot(Folder): pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadATFWait.zpt')).__of__(self) return pt(txt='/uploadATFfinally',threadName=threadName) else: - + self.REQUEST.SESSION['idTmp']=None if RESPONSE is not None: RESPONSE.redirect(self.absolute_url()) - def importFiles(self,comment="",author="" ,folderName="/Users/dwinter/Documents/workspace/cdli/atf", files=None,ext=None): + def importFiles(self,comment="",author="" ,folderName="/Users/dwinter/atf", files=None,ext=None): """import files""" root=self.cdli_main - + count=0 if not files: files=os.listdir(folderName) @@ -1962,7 +2390,7 @@ class CDLIRoot(Folder): if not obj: manage_addCDLIFileFolder(root,folder,folder) fobj=getattr(root,folder) - #get_transaction().commit() + #transaction.get().commit() else: fobj=obj[0][1] @@ -1975,18 +2403,24 @@ class CDLIRoot(Folder): else: fobj2=obj2[0][1] - file2=file(os.path.join(folderName,f)) + file2=os.path.join(folderName,f) id=f manage_addCDLIFile(fobj2,f,'','') id=f ob=fobj2._getOb(f) ob.title=id - manage_addCDLIFileObject(ob,id,comment,author,file2,content_type='') + manage_addCDLIFileObject(ob,id,comment,author,file2,content_type='',from_tmp=True) self.CDLICatalog.catalog_object(ob) #self.CDLICatalog.manage_catalogFoundItems(obj_ids=[id],search_sub=1) #self.CDLICatalog.manage_catalogObject(self.REQUEST, self.REQUEST.RESPONSE, 'CDLICatalog', urlparse.urlparse(ob.absolute_url())[1]) - + count+=1 + + if count > 1000: + print "committing" + transaction.get().commit() + count=0 + transaction.get().commit() return "ok" @@ -2006,7 +2440,10 @@ def manage_addCDLIRoot(self, id, title=' ob=CDLIRoot() ob.id=str(id) ob.title=title - self._setObject(id, ob) + try: + self._setObject(id, ob) + except: + pass ob=self._getOb(id) checkPermission=getSecurityManager().checkPermission