version 1.80.2.9, 2007/11/27 10:27:39
|
version 1.86, 2008/09/29 12:37:37
|
Line 21 from ZPublisher.HTTPRequest import HTTPR
|
Line 21 from ZPublisher.HTTPRequest import HTTPR
|
from ZPublisher.HTTPResponse import HTTPResponse |
from ZPublisher.HTTPResponse import HTTPResponse |
from ZPublisher.BaseRequest import RequestContainer |
from ZPublisher.BaseRequest import RequestContainer |
import threading |
import threading |
from BTrees.OOBTree import OOBTree |
from BTrees.OOBTree import OOBTree, OOTreeSet |
import logging |
import logging |
import transaction |
import transaction |
import copy |
import copy |
import codecs |
import codecs |
import sys |
import sys |
|
from BTrees.IOBTree import IOBTree |
import cdliSplitter |
import cdliSplitter |
|
from sets import Set |
|
import md5 |
|
|
|
|
|
def makelist(mySet): |
|
x = list(mySet) |
|
x.sort() |
|
return x |
|
|
def unicodify(s): |
def unicodify(s): |
"""decode str (utf-8 or latin-1 representation) into unicode object""" |
"""decode str (utf-8 or latin-1 representation) into unicode object""" |
Line 99 def formatAtfFullLineNum(txt, nolemma=Tr
|
Line 106 def formatAtfFullLineNum(txt, nolemma=Tr
|
ret = [] |
ret = [] |
surf = "" |
surf = "" |
col = "" |
col = "" |
for line in txt.split("\n"): |
for line in txt.splitlines(): |
line = unicodify(line) |
line = unicodify(line) |
if line and line[0] == '@': |
if line and line[0] == '@': |
# surface or column |
# surface or column |
Line 108 def formatAtfFullLineNum(txt, nolemma=Tr
|
Line 115 def formatAtfFullLineNum(txt, nolemma=Tr
|
surf = line.replace(words[0],surfaces[words[0]]).strip() |
surf = line.replace(words[0],surfaces[words[0]]).strip() |
|
|
elif words[0] == '@column': |
elif words[0] == '@column': |
col = words[1] |
col = ' '.join(words[1:]) |
|
|
elif line and line[0] in '123456789': |
elif line and line[0] in '123456789': |
# ordinary line -> add line number |
# ordinary line -> add line number |
Line 144 def generateXMLReturn(hash):
|
Line 151 def generateXMLReturn(hash):
|
return ret |
return ret |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def unique(s): |
def unique(s): |
"""Return a list of the elements in s, but without duplicates. |
"""Return a list of the elements in s, but without duplicates. |
|
|
Line 321 class uploadATFfinallyThread(Thread):
|
Line 320 class uploadATFfinallyThread(Thread):
|
self.result+="<h2>Start processing</h2>" |
self.result+="<h2>Start processing</h2>" |
|
|
#shall I only upload the changed files? |
#shall I only upload the changed files? |
logging.info("uploadATFfinally procedure: %s"%procedure) |
logging.debug("uploadATFfinally procedure: %s"%procedure) |
if procedure=="uploadchanged": |
if procedure=="uploadchanged": |
changed=[x[0] for x in SESSION.get('changed',[])] |
changed=[x[0] for x in SESSION.get('changed',[])] |
uploadFns=changed+SESSION.get('newPs',[]) |
uploadFns=changed+SESSION.get('newPs',[]) |
Line 342 class uploadATFfinallyThread(Thread):
|
Line 341 class uploadATFfinallyThread(Thread):
|
#do first the changed files |
#do first the changed files |
i=0 |
i=0 |
for fn in uploadFns: |
for fn in uploadFns: |
|
logging.debug("uploadATFfinally uploadFn=%s"%fn) |
i+=1 |
i+=1 |
founds=ctx2.CDLICatalog.search({'title':fn}) |
founds=ctx2.CDLICatalog.search({'title':fn}) |
if len(founds)>0: |
if len(founds)>0: |
SESSION['author']=str(username) |
SESSION['author']=str(username) |
self.result="<p>Changing : %s"%fn+self.result |
self.result="<p>Changing : %s"%fn+self.result |
|
logging.debug("uploadatffinallythread changing:%s"%fn+self.result) |
founds[0].getObject().manage_addCDLIFileObject('',comment,SESSION['author'],file=os.path.join(SESSION['tmpdir'],fn),from_tmp=True) |
founds[0].getObject().manage_addCDLIFileObject('',comment,SESSION['author'],file=os.path.join(SESSION['tmpdir'],fn),from_tmp=True) |
if i==200: |
if i%200==0: |
i=0 |
|
transaction.get().commit() |
transaction.get().commit() |
logging.info("changing: do commit") |
logging.debug("uploadatffinallythread changing: do commit") |
|
|
transaction.get().commit() |
transaction.get().commit() |
logging.info("changing: last commit") |
logging.debug("uploadatffinallythread changing: last commit") |
|
|
#now add the new files |
#now add the new files |
newPs=SESSION['newPs'] |
newPs=SESSION['newPs'] |
if len(newPs)>0: |
if len(newPs)>0: |
tmpDir=SESSION['tmpdir'] |
tmpDir=SESSION['tmpdir'] |
logging.info("adding start") |
logging.debug("uploadatffinallythread adding start") |
self.result="<p>Adding files</p>"+self.result |
self.result="<p>Adding files</p>"+self.result |
#TODO: make this configurable, at the moment base folder for the files has to be cdli_main |
#TODO: make this configurable, at the moment base folder for the files has to be cdli_main |
|
|
ctx2.importFiles(comment=comment,author=str(username) ,folderName=tmpDir, files=newPs,ext=self) |
ctx2.importFiles(comment=comment,author=str(username) ,folderName=tmpDir, files=newPs,ext=self) |
logging.info("adding finished") |
logging.debug("uploadatffinallythread adding finished") |
|
|
|
|
#unlock locked files? |
#unlock locked files? |
if unlock: |
if unlock: |
logging.info("unlocking start") |
logging.debug("uploadatffinallythread unlocking start") |
self.result="<p>Unlock files</p>"+self.result |
self.result="<p>Unlock files</p>"+self.result |
unlockFns=[] |
unlockFns=[] |
for x in os.listdir(SESSION['tmpdir']): |
for x in os.listdir(SESSION['tmpdir']): |
if not x in SESSION['errors']: |
if not x in SESSION['errors']: |
unlockFns.append(x) |
unlockFns.append(x) |
logging.info("unlocking have now what to unlock") |
|
|
logging.debug("unlocking have now what to unlock") |
|
|
for fn in unlockFns: |
for fn in unlockFns: |
#logging.info("will unlock: %s"%fn) |
#logging.info("will unlock: %s"%fn) |
Line 385 class uploadATFfinallyThread(Thread):
|
Line 384 class uploadATFfinallyThread(Thread):
|
if len(founds)>0: |
if len(founds)>0: |
#logging.info("unlock: %s"%founds[0].getObject().getId()) |
#logging.info("unlock: %s"%founds[0].getObject().getId()) |
SESSION['author']=str(username) |
SESSION['author']=str(username) |
|
|
founds[0].getObject().lockedBy="" |
founds[0].getObject().lockedBy="" |
logging.info("unlocking done") |
|
|
logging.debug("uploadatffinallythread unlocking done") |
|
|
#if a basketname is given, add files to the basket |
#if a basketname is given, add files to the basket |
if not (basketname ==''): |
if not (basketname ==''): |
logging.info("add to basket %s"%basketname) |
logging.debug("uploadatffinallythread add to basket %s"%basketname) |
self.result="<p>Add to basket</p>"+self.result |
self.result="<p>Add to basket</p>"+self.result |
basketId=ctx2.basketContainer.getBasketIdfromName(basketname) |
basketId=ctx2.basketContainer.getBasketIdfromName(basketname) |
|
|
if not basketId: # create new basket |
if not basketId: # create new basket |
logging.info("create basket %s"%basketname) |
logging.debug("uploadatffinallythread create basket %s"%basketname) |
self.result="<p>Create a new basket</p>"+self.result |
self.result="<p>Create a new basket</p>"+self.result |
ob=ctx2.basketContainer.addBasket(basketname) |
ob=ctx2.basketContainer.addBasket(basketname) |
basketId=ob.getId() |
basketId=ob.getId() |
basket=getattr(ctx2.basketContainer,str(basketId)) |
basket=getattr(ctx2.basketContainer,str(basketId)) |
ids=os.listdir(SESSION['tmpdir']) |
ids=os.listdir(SESSION['tmpdir']) |
|
logging.debug("should add:"+repr(ids)) |
basket.addObjects(ids,deleteOld=True,username=str(username)) |
basket.addObjects(ids,deleteOld=True,username=str(username)) |
|
|
|
logging.debug("uploadatffinallythread uploadfinally done") |
|
|
if RESPONSE is not None: |
if RESPONSE is not None: |
RESPONSE.redirect(self.aq_parent.absolute_url()) |
RESPONSE.redirect(self.aq_parent.absolute_url()) |
|
|
|
|
logging.info("uploadfinally done") |
|
return True |
return True |
|
|
class tmpStore(SimpleItem): |
class tmpStore(SimpleItem): |
Line 640 class CDLIBasketContainer(OrderedFolder)
|
Line 640 class CDLIBasketContainer(OrderedFolder)
|
ret+=str(object[0].getData())+"\n" |
ret+=str(object[0].getData())+"\n" |
elif current=="yes": |
elif current=="yes": |
#search current object |
#search current object |
logging.info("crrent: %s"%object[1].getId().split(".")[0]) |
logging.debug("current: %s"%object[1].getId().split(".")[0]) |
founds=self.CDLICatalog.search({'title':object[1].getId().split(".")[0]}) |
founds=self.CDLICatalog.search({'title':object[1].getId().split(".")[0]}) |
if len(founds)>0: |
if len(founds)>0: |
ret+=str(founds[0].getObject().getLastVersion().getData())+"\n" |
ret+=str(founds[0].getObject().getLastVersion().getData())+"\n" |
Line 933 class CDLIBasketContainer(OrderedFolder)
|
Line 933 class CDLIBasketContainer(OrderedFolder)
|
if not ids: |
if not ids: |
ids=self.REQUEST.SESSION['fileIds'] |
ids=self.REQUEST.SESSION['fileIds'] |
|
|
if type(ids) is not ListType: |
if (type(ids) is not ListType) and (not isinstance(ids,Set)): |
ids=[ids] |
ids=[ids] |
|
|
|
if isinstance(ids,Set): |
|
ids=list(ids) |
|
|
if (submit.lower()=="store in new basket") or (submit.lower()=="new basket"): |
if (submit.lower()=="store in new basket") or (submit.lower()=="new basket"): |
basketRet=self.addBasket(newBasketName) |
basketRet=self.addBasket(newBasketName) |
self.setActiveBasket(basketRet.getId()) |
self.setActiveBasket(basketRet.getId()) |
Line 949 class CDLIBasketContainer(OrderedFolder)
|
Line 952 class CDLIBasketContainer(OrderedFolder)
|
|
|
if fromFileList: |
if fromFileList: |
|
|
return self.cdli_main.findObjectsFromList(list=self.REQUEST.SESSION['fileIds'],basketName=basket.title,numberOfObjects=added) |
return self.cdli_main.findObjectsFromList(list=ids,basketName=basket.title,numberOfObjects=added) |
|
|
if RESPONSE: |
if RESPONSE: |
|
|
Line 1028 class CDLIBasket(Folder,CatalogAware):
|
Line 1031 class CDLIBasket(Folder,CatalogAware):
|
|
|
def isActual(self,obj): |
def isActual(self,obj): |
"""teste ob im basket die aktuelle version ist""" |
"""teste ob im basket die aktuelle version ist""" |
|
try: |
|
logging.debug("isActual:"+repr(obj)) |
actualNo=obj[1].getLastVersion().getVersionNumber() |
actualNo=obj[1].getLastVersion().getVersionNumber() |
storedNo=obj[0].getVersionNumber() |
storedNo=obj[0].getVersionNumber() |
|
|
Line 1042 class CDLIBasket(Folder,CatalogAware):
|
Line 1047 class CDLIBasket(Folder,CatalogAware):
|
return True , 0 |
return True , 0 |
else: |
else: |
return False, actualNo |
return False, actualNo |
|
except: |
|
return False, -1 |
|
|
def history(self): |
def history(self): |
"""history""" |
"""history""" |
Line 1185 class CDLIBasket(Folder,CatalogAware):
|
Line 1192 class CDLIBasket(Folder,CatalogAware):
|
|
|
def addObjects(self,ids,deleteOld=None,username=None): |
def addObjects(self,ids,deleteOld=None,username=None): |
"""generate a new version of the basket with objects added""" |
"""generate a new version of the basket with objects added""" |
|
|
|
def swap(x): |
|
return (x[1],x[0]) |
|
|
logging.info("add to basket (%s)"%(self.getId())) |
logging.info("add to basket (%s)"%(self.getId())) |
lastVersion=self.getLastVersion() |
lastVersion=self.getLastVersion() |
|
|
Line 1196 class CDLIBasket(Folder,CatalogAware):
|
Line 1207 class CDLIBasket(Folder,CatalogAware):
|
if deleteOld: |
if deleteOld: |
oldContent=[] |
oldContent=[] |
|
|
newContent=[] |
|
added=0 |
added=0 |
for id in ids: |
# for id in ids: |
try: |
# logging.debug("adding:"+id) |
founds=self.CDLICatalog.search({'title':id}) |
# try: |
except: |
# founds=self.CDLICatalog.search({'title':id}) |
founds=[] |
# except: |
|
# founds=[] |
|
# |
|
# for found in founds: |
|
# if found.getObject() not in oldContent: |
|
# #TODO: was passiert wenn, man eine Object dazufgt, das schon da ist aber eine neuere version |
|
# newContent.append((found.getObject().getLastVersion(),found.getObject())) |
|
# added+=1 |
|
|
|
hash = md5.new(repr(makelist(ids))).hexdigest() # erzeuge hash als identification |
|
#logging.debug("JJJJJJJ:"+repr(self.makelist(ids))) |
|
logging.debug("JJJJJJJ:"+repr(hash)) |
|
|
|
if hasattr(self.cdliRoot,'v_tmpStore') and self.cdliRoot.v_tmpStore.has_key(hash): |
|
logging.debug("from store!") |
|
newContent=Set(map(swap,self.cdliRoot.v_tmpStore[hash])) |
|
|
for found in founds: |
else: |
if found.getObject() not in oldContent: |
logging.debug("not from store!") |
#TODO: was passiert wenn, man eine Object dazufgt, das schon da ist aber eine neuere version |
newContent=Set([(self.getFileObjectLastVersion(x),self.getFileObject(x)) for x in ids]) |
newContent.append((found.getObject().getLastVersion(),found.getObject())) |
|
added+=1 |
|
|
|
content=oldContent+newContent |
|
|
content=Set(oldContent).union(newContent) |
|
added = len(content)-len(oldContent) |
if not username: |
if not username: |
user=self.getActualUserName() |
user=self.getActualUserName() |
else: |
else: |
user = username |
user = username |
|
|
ob=manage_addCDLIBasketVersion(self,user,comment="",basketContent=content) |
#logging.debug("content:"+repr(list(content))) |
|
ob=manage_addCDLIBasketVersion(self,user,comment="",basketContent=list(content)) |
logging.info("add to basket (%s) done"%(self.getId())) |
logging.info("add to basket (%s) done"%(self.getId())) |
return added |
return added |
|
|
Line 1353 class CDLIBasketVersion(Implicit,Persist
|
Line 1379 class CDLIBasketVersion(Implicit,Persist
|
|
|
def downloadObjectsAsOneFileFinally(self,lock=None,procedure=None,REQUEST=None,current="no"): |
def downloadObjectsAsOneFileFinally(self,lock=None,procedure=None,REQUEST=None,current="no"): |
"""print do the download""" |
"""print do the download""" |
|
logging.debug("HIHHHH") |
ret="" |
ret="" |
lockedObjects={} |
lockedObjects={} |
|
|
Line 1400 class CDLIBasketVersion(Implicit,Persist
|
Line 1426 class CDLIBasketVersion(Implicit,Persist
|
|
|
|
|
for object in self.content.getContent(): |
for object in self.content.getContent(): |
|
logging.error("ret:"+repr(object[0])) |
|
logging.error(" -"+repr(procedure)) |
|
logging.error(" -"+repr(object[1].lockedBy)) |
|
|
if (procedure=="downloadAll") or (object[1].lockedBy=='') or (object[1].lockedBy==self.REQUEST['AUTHENTICATED_USER']): |
if (procedure=="downloadAll") or (object[1].lockedBy=='') or (object[1].lockedBy==self.REQUEST['AUTHENTICATED_USER']): |
|
logging.error("ret1") |
if current=="no": #version as they are in the basket |
if current=="no": #version as they are in the basket |
|
logging.error("ret2") |
ret+=str(object[0].getData())+"\n" |
ret+=str(object[0].getData())+"\n" |
elif current=="yes": |
elif current=="yes": |
|
logging.error("ret3") |
#search current object |
#search current object |
founds=self.CDLICatalog.search({'title':object[1].getId().split(".")[0]}) |
founds=self.CDLICatalog.search({'title':object[1].getId().split(".")[0]}) |
if len(founds)>0: |
if len(founds)>0: |
Line 1412 class CDLIBasketVersion(Implicit,Persist
|
Line 1444 class CDLIBasketVersion(Implicit,Persist
|
|
|
if lock and object[1].lockedBy=='': |
if lock and object[1].lockedBy=='': |
object[1].lockedBy=self.REQUEST['AUTHENTICATED_USER'] |
object[1].lockedBy=self.REQUEST['AUTHENTICATED_USER'] |
|
|
|
if (not isinstance(self.aq_parent,CDLIBasket)): |
|
basket_name=self.aq_parent.aq_parent.title+"_V"+self.getId() |
|
else: |
basket_name=self.aq_parent.title+"_V"+self.getId() |
basket_name=self.aq_parent.title+"_V"+self.getId() |
|
|
|
|
|
|
#write basketname to header of atf file |
#write basketname to header of atf file |
ret="#basket: %s\n"%basket_name+ret |
ret="#basket: %s\n"%basket_name+ret |
|
|
Line 1520 class CDLIFileObject(CatalogAware,extVer
|
Line 1558 class CDLIFileObject(CatalogAware,extVer
|
|
|
security.declareProtected('manage','index_html') |
security.declareProtected('manage','index_html') |
|
|
|
security.declarePublic('view') |
|
view = PageTemplateFile('zpt/viewCDLIFile.zpt', globals()) |
|
|
|
security.declarePublic('editATF') |
|
editATF = PageTemplateFile('zpt/editATFFile.zpt', globals()) |
|
|
def PrincipiaSearchSource(self): |
def PrincipiaSearchSource(self): |
"""Return cataloguable key for ourselves.""" |
"""Return cataloguable key for ourselves.""" |
return str(self) |
return str(self) |
|
|
def makeThisVersionCurrent_html(self): |
def makeThisVersionCurrent_html(self): |
"""form for making this version current""" |
"""form for mthis version current""" |
|
|
pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','makeThisVersionCurrent.zpt')).__of__(self) |
pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','makeThisVersionCurrent.zpt')).__of__(self) |
return pt() |
return pt() |
Line 1534 class CDLIFileObject(CatalogAware,extVer
|
Line 1578 class CDLIFileObject(CatalogAware,extVer
|
def makeThisVersionCurrent(self,comment,author,RESPONSE=None): |
def makeThisVersionCurrent(self,comment,author,RESPONSE=None): |
"""copy this version to current""" |
"""copy this version to current""" |
parent=self.aq_parent |
parent=self.aq_parent |
newversion=parent.manage_addCDLIFileObject('',comment,author) |
parent.manage_addVersionedFileObject(id=None,vC=comment,author=author,file=self.getData(),RESPONSE=RESPONSE) |
newversion.manage_upload(self.getData()) |
#newversion=parent.manage_addCDLIFileObject('',comment,author) |
|
#newversion.manage_upload(self.getData()) |
|
|
if RESPONSE is not None: |
#if RESPONSE is not None: |
RESPONSE.redirect(self.aq_parent.absolute_url()+'/history') |
# RESPONSE.redirect(self.aq_parent.absolute_url()+'/history') |
|
|
return True |
return True |
|
|
Line 1548 class CDLIFileObject(CatalogAware,extVer
|
Line 1593 class CDLIFileObject(CatalogAware,extVer
|
# return re.sub("\s\#lem"," #lem",data) #remove return vor #lem |
# return re.sub("\s\#lem"," #lem",data) #remove return vor #lem |
return re.sub("#lem"," #lem",data) #remove return vor #lem |
return re.sub("#lem"," #lem",data) #remove return vor #lem |
|
|
security.declarePublic('view') |
|
def view(self): |
|
"""view file""" |
|
pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','viewCDLIFile.zpt')).__of__(self) |
|
return pt() |
|
|
|
security.declarePublic('getPNumber') |
security.declarePublic('getPNumber') |
def getPNumber(self): |
def getPNumber(self): |
Line 1582 class CDLIFileObject(CatalogAware,extVer
|
Line 1622 class CDLIFileObject(CatalogAware,extVer
|
except: |
except: |
return "ERROR" |
return "ERROR" |
|
|
|
|
manage_addCDLIFileObjectForm=DTMLFile('dtml/fileAdd', globals(),Kind='CDLIFileObject',kind='CDLIFileObject', version='1') |
manage_addCDLIFileObjectForm=DTMLFile('dtml/fileAdd', globals(),Kind='CDLIFileObject',kind='CDLIFileObject', version='1') |
|
|
def manage_addCDLIFileObject(self,id,vC='',author='', file='',title='',versionNumber=0, |
def manage_addCDLIFileObject(self,id,vC='',author='', file='',title='',versionNumber=0, |
Line 1614 def manage_addCDLIFileObject(self,id,vC=
|
Line 1655 def manage_addCDLIFileObject(self,id,vC=
|
if content_type: |
if content_type: |
fob.content_type=content_type |
fob.content_type=content_type |
|
|
logging.debug("manage_add: lastversion=%s"%self.getData()) |
#logging.debug("manage_add: lastversion=%s"%self.getData()) |
logging.debug("reindex1: %s in %s"%(repr(self),repr(self.default_catalog))) |
logging.debug("reindex1: %s in %s"%(repr(self),repr(self.default_catalog))) |
self.reindex_object() |
self.reindex_object() |
logging.debug("manage_add: fob_data=%s"%fob.getData()) |
#logging.debug("manage_add: fob_data=%s"%fob.getData()) |
logging.debug("reindex2: %s in %s"%(repr(fob), repr(fob.default_catalog))) |
logging.debug("reindex2: %s in %s"%(repr(fob), repr(fob.default_catalog))) |
fob.index_object() |
fob.index_object() |
|
|
|
self.CDLIRoot.updateOrAddToFileBTree(ob) |
if REQUEST is not None: |
if REQUEST is not None: |
REQUEST['RESPONSE'].redirect(self.absolute_url()+'/manage_main') |
REQUEST['RESPONSE'].redirect(self.absolute_url()+'/manage_main') |
|
|
Line 1696 class CDLIFile(extVersionedFile,CatalogA
|
Line 1738 class CDLIFile(extVersionedFile,CatalogA
|
|
|
def _newContentObject(self, id, title='', versionNumber=0, versionComment=None, time=None, author=None): |
def _newContentObject(self, id, title='', versionNumber=0, versionComment=None, time=None, author=None): |
"""factory for content objects. to be overridden in derived classes.""" |
"""factory for content objects. to be overridden in derived classes.""" |
|
logging.debug("_newContentObject(CDLI)") |
return CDLIFileObject(id,title,versionNumber=versionNumber,versionComment=versionComment,time=time,author=author) |
return CDLIFileObject(id,title,versionNumber=versionNumber,versionComment=versionComment,time=time,author=author) |
|
|
|
|
Line 1733 class CDLIFile(extVersionedFile,CatalogA
|
Line 1776 class CDLIFile(extVersionedFile,CatalogA
|
except: |
except: |
pass |
pass |
|
|
|
#self.cdliRoot.updateOrAddToFileBTree(self)# now update the object in the cache |
|
|
|
|
if RESPONSE: |
if RESPONSE: |
if ob.getSize()==0: |
if ob.getSize()==0: |
self.REQUEST.SESSION['objID']=ob.getId() |
self.REQUEST.SESSION['objID']=ob.getId() |
Line 1765 def manage_addCDLIFile(self,id,title,loc
|
Line 1811 def manage_addCDLIFile(self,id,title,loc
|
if RESPONSE is not None: |
if RESPONSE is not None: |
RESPONSE.redirect('manage_main') |
RESPONSE.redirect('manage_main') |
|
|
|
|
def checkUTF8(data): |
def checkUTF8(data): |
"""check utf 8""" |
"""check utf 8""" |
try: |
try: |
Line 1795 def splitatf(fh,dir=None,ext=None):
|
Line 1842 def splitatf(fh,dir=None,ext=None):
|
nf=None |
nf=None |
i=0 |
i=0 |
|
|
|
#ROC: why split \n first and then \r??? |
if (type(fh) is StringType) or (type(fh) is UnicodeType): |
if (type(fh) is StringType) or (type(fh) is UnicodeType): |
iter=fh.split("\n") |
iter=fh.split("\n") |
else: |
else: |
Line 1856 class CDLIFileFolder(extVersionedFileFol
|
Line 1904 class CDLIFileFolder(extVersionedFileFol
|
#downloadCounter=0 # counts how many download for all files currently run, be mehr als 5 wird verweigert. |
#downloadCounter=0 # counts how many download for all files currently run, be mehr als 5 wird verweigert. |
tmpStore2={} |
tmpStore2={} |
|
|
|
def _newVersionedFile(self, id, title='', lockedBy=None, author=None): |
|
"""factory for versioned files. to be overridden in derived classes.""" |
|
logging.debug("_newVersionedFile(CDLI)") |
|
return CDLIFile(id, title, lockedBy=lockedBy, author=author) |
|
|
def setTemp(self,name,value): |
def setTemp(self,name,value): |
"""set tmp""" |
"""set tmp""" |
|
|
setattr(self,name,value) |
setattr(self,name,value) |
|
|
|
deleteFileForm = PageTemplateFile("zpt/doDeleteFile", globals()) |
|
|
def delete(self,ids): |
def delete(self,ids,REQUEST=None): |
"""delete these files""" |
"""delete these files""" |
if type(ids) is not ListType: |
if type(ids) is not ListType: |
ids=[ids] |
ids=[ids] |
|
|
self.manage_delObjects(ids) |
self.manage_delObjects(ids) |
|
|
|
if REQUEST is not None: |
|
return self.index_html() |
|
|
|
|
def getVersionNumbersFromIds(self,ids): |
def getVersionNumbersFromIds(self,ids): |
"""get the numbers of the current versions of documents described by their ids""" |
"""get the numbers of the current versions of documents described by their ids""" |
Line 1924 class CDLIFileFolder(extVersionedFileFol
|
Line 1981 class CDLIFileFolder(extVersionedFileFol
|
|
|
return ret |
return ret |
|
|
def findObjectsFromList(self,enterList=None,display=False,start=None,upload=None,list=None,basketName=None,numberOfObjects=None,RESPONSE=None): |
def expandFile(self,fileId,fileTree): |
|
"""wildcard in fileID suche alle Treffer""" |
|
founds=self.CDLICatalog({'title':fileId}) |
|
for found in founds: |
|
fileTree.add(found.getId) |
|
logging.debug("ADDD:"+found.getId) |
|
|
|
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): |
"""findObjectsFromList (, TAB oder LINE separated)""" |
"""findObjectsFromList (, TAB oder LINE separated)""" |
|
|
|
logging.debug("start: findObjectsFromList") |
|
#logging.debug("start: findObjectsFromList"+repr(list)) |
|
|
|
|
if upload: # list from file upload |
if upload: # list from file upload |
txt=upload.read() |
txt=upload.read() |
Line 1958 class CDLIFileFolder(extVersionedFileFol
|
Line 2025 class CDLIFileFolder(extVersionedFileFol
|
pt=getattr(self,'filelist.html') |
pt=getattr(self,'filelist.html') |
return pt(basketName=basketName,numberOfObjects=numberOfObjects) |
return pt(basketName=basketName,numberOfObjects=numberOfObjects) |
|
|
|
if hash is not None and hasattr(self.cdliRoot,'v_tmpStore') and self.cdliRoot.v_tmpStore.has_key(hash): |
|
|
|
logging.debug("asking for storage2") |
|
result =self.cdliRoot.v_tmpStore[hash] |
|
if result: |
|
logging.debug("give result from storage2") |
|
return hash,self.cdliRoot.v_tmpStore[hash] |
|
|
if list is not None: # got already a list |
if list is not None: # got already a list |
|
|
|
logging.debug(" ----List version") |
ret=[] |
ret=[] |
|
fileTree=Set() |
|
|
for fileId in list: |
for fileId in list: |
if fileId.find("*"): #check for wildcards |
|
fileId=fileId |
if fileId.find("*")>-1: #check for wildcards |
|
self.expandFile(fileId,fileTree) |
|
|
elif len(fileId.split("."))==1: |
elif len(fileId.split("."))==1: |
fileId=fileId+".atf" |
fileId=fileId+".atf" |
|
fileTree.add(fileId) |
|
#logging.debug(" -----:"+fileId) |
|
#ret+=self.CDLICatalog({'title':fileId}) |
|
#x =self.getFileObject(fileId) |
|
#if x is not None: |
|
# ret.append(x) |
|
|
|
|
|
|
|
ids = fileTree & self.v_file_ids |
|
#self.REQUEST.SESSION['fileIds']=ids#store fieldIds in session for further usage |
|
l=makelist(fileTree)[0:] |
|
logging.debug("l-list:"+repr(l)) |
|
self.REQUEST.SESSION['fileIds']=l#store fieldIds in session for further usage |
|
self.REQUEST.SESSION['searchList']=l |
|
#self.REQUEST.SESSION['searchList']=['P000001.atf'] |
|
|
|
|
|
hash = md5.new(repr(makelist(fileTree))).hexdigest() # erzeuge hash als identification |
|
self.REQUEST.SESSION['hash']=hash |
|
#TODO: do I need garbage collection for v_tmpStore ? |
|
|
|
#logging.debug("Hash:"+repr(hash)) |
|
# |
|
# if hasattr(self.cdliRoot,'v_tmpStore') and self.cdliRoot.v_tmpStore.has_key(hash): |
|
# logging.debug("asking for storage") |
|
# res=self.cdliRoot.v_tmpStore[hash] |
|
# if res: |
|
# if returnHash == True: |
|
# return hash,res |
|
# return res |
|
|
ret+=self.CDLICatalog({'title':fileId}) |
|
#TODO: get rid of one of these.. |
#TODO: get rid of one of these.. |
ids=[x.getObject().getId() for x in ret] |
#ids=[x.getObject().getId() for x in ret] |
self.REQUEST.SESSION['fileIds']=ids#store fieldIds in session for further usage |
ret=[(self.getFileObject(x),self.getFileObjectLastVersion(x)) for x in ids] |
self.REQUEST.SESSION['searchList']=self.REQUEST.SESSION['fileIds'] |
|
|
#self.REQUEST.SESSION['fileIds']=ids#store fieldIds in session for further usage |
|
#self.REQUEST.SESSION['searchList']=self.REQUEST.SESSION['fileIds'] |
|
|
if display: |
if display: |
pt=getattr(self,'filelist.html') |
pt=getattr(self,'filelist.html') |
|
|
return pt(search=ids) |
return pt(search=ids) |
else: |
else: |
|
#self.REQUEST.SESSION['hash'] = ret # store in session |
|
if not hasattr(self,'v_tmpStore'): |
|
self.cdliRoot.v_tmpStore={} |
|
#logging.debug("HHHHHHNEU:"+repr(self.makelist(ids))) |
|
#logging.debug("HHHHHHNEU:"+repr(hash)) |
|
self.cdliRoot.v_tmpStore[hash] = ret # store in session |
|
if returnHash == True: |
|
return hash,ret |
return ret |
return ret |
|
|
|
|
Line 1984 class CDLIFileFolder(extVersionedFileFol
|
Line 2105 class CDLIFileFolder(extVersionedFileFol
|
if start: |
if start: |
RESPONSE.redirect("filelist.html?start:int="+str(start)) |
RESPONSE.redirect("filelist.html?start:int="+str(start)) |
|
|
|
|
security.declareProtected('Manage','createAllFilesAsSingleFile') |
security.declareProtected('Manage','createAllFilesAsSingleFile') |
def createAllFilesAsSingleFile(self,RESPONSE=None): |
def createAllFilesAsSingleFile(self,RESPONSE=None): |
"""download all files""" |
"""download all files""" |
Line 2112 class CDLIRoot(Folder):
|
Line 2232 class CDLIRoot(Folder):
|
'graphemes':cdliSplitter.graphemeSplitter()} |
'graphemes':cdliSplitter.graphemeSplitter()} |
|
|
|
|
|
def viewATF(self,id,RESPONSE): |
|
"""view an Object""" |
|
ob = self.CDLICatalog({'title':id}) |
|
logging.debug(ob[0].getObject().getLastVersion().absolute_url()+"/view") |
|
if len(ob)>0: |
|
RESPONSE.redirect(ob[0].getObject().getLastVersion().absolute_url()+"/view") |
|
return "not found" |
|
|
|
def history(self,id,RESPONSE): |
|
"""view an Object""" |
|
ob = self.CDLICatalog({'title':id}) |
|
if len(ob)>0: |
|
RESPONSE.redirect(ob[0].absolute_url+"/history") |
|
return "not found" |
|
|
|
|
|
def downloadLocked(self,id,RESPONSE): |
|
"""view an Object""" |
|
ob = self.CDLICatalog({'title':id}) |
|
if len(ob)>0: |
|
RESPONSE.redirect(ob[0].absolute_url+"/downloadLocked") |
|
return "not found" |
|
|
|
def download(self,id,RESPONSE): |
|
"""view an Object""" |
|
ob = self.CDLICatalog({'title':id}) |
|
if len(ob)>0: |
|
RESPONSE.redirect(ob[0].getLastVersion().absolute_url()) |
|
return "not found" |
|
def addCDLIFileObjectForm(self,id,RESPONSE): |
|
"""view an Object""" |
|
ob = self.CDLICatalog({'title':id}) |
|
if len(ob)>0: |
|
RESPONSE.redirect(ob[0].absolute_url+"/addCDLIFileObjectForm") |
|
return "not found" |
|
|
|
def addVersionedFileObjectForm(self,id,RESPONSE): |
|
"""view an Object""" |
|
ob = self.CDLICatalog({'title':id}) |
|
if len(ob)>0: |
|
RESPONSE.redirect(ob[0].absolute_url+"/addVersionedFileObjectForm") |
|
return "not found" |
|
|
|
def unlock(self,id,RESPONSE): |
|
"""view an Object""" |
|
ob = self.CDLICatalog({'title':id}) |
|
if len(ob)>0: |
|
RESPONSE.redirect(ob[0].absolute_url+"/unlock") |
|
return "not found" |
|
|
|
def getFileObject(self,fileId): |
|
"""get an object""" |
|
x=self.v_files.get(fileId) |
|
#logging.debug(x) |
|
return x |
|
|
|
def getFileObjectLastVersion(self,fileId): |
|
"""get an object""" |
|
x=self.v_files_lastVersion.get(fileId) |
|
#logging.debug(x) |
|
return x |
|
|
|
def showFileIds(self): |
|
"""showIds""" |
|
return self.v_file_ids |
|
|
|
def generateFileBTree(self): |
|
"""erzeuge einen Btree aus allen Files""" |
|
self.v_files = OOBTree() |
|
self.v_files_lastVersion = OOBTree() |
|
self.v_file_ids = Set() |
|
|
|
for x in self.CDLICatalog.searchResults(): |
|
|
|
self.v_files.update({x.getId:x.getObject()}) |
|
self.v_files_lastVersion.update({x.getId:x.getObject().getLastVersion()}) |
|
self.v_file_ids.add(x.getId) |
|
logging.debug("add:"+x.getId+"XXX"+repr(x.getObject())) |
|
|
|
return True |
|
|
|
|
|
def updateOrAddToFileBTree(self,obj): |
|
"""update a BTree""" |
|
self.v_files.update({obj.getId():obj}) |
|
self.v_files_lastVersion.update({obj.getId():obj.getLastVersion()}) |
|
|
|
self.v_file_ids.add(obj.getId()) |
|
logging.debug("update:"+obj.getId()+"XXX"+repr(obj)) |
|
|
|
def deleteFromBTree(self,objId): |
|
"""delete an obj""" |
|
self.v_files.pop(objId) |
|
self.v_files_lastVersion.pop(objId) |
|
self.v_file_ids.remove(objId) |
|
|
|
|
|
|
def deleteFiles(self,ids): |
def deleteFiles(self,ids): |
"""delete files""" |
"""delete files""" |
for id in ids: |
for id in ids: |
Line 2137 class CDLIRoot(Folder):
|
Line 2355 class CDLIRoot(Folder):
|
resultset = idx.search(query_request=idxQuery,sort_index='textid') |
resultset = idx.search(query_request=idxQuery,sort_index='textid') |
# put only the P-Number in the result |
# put only the P-Number in the result |
results = [res.getId[:7] for res in resultset] |
results = [res.getId[:7] for res in resultset] |
|
logging.debug("searchtext: found %d texts"%len(results)) |
return results |
return results |
|
|
|
|
Line 2149 class CDLIRoot(Folder):
|
Line 2368 class CDLIRoot(Folder):
|
return f[0].getObject().getData() |
return f[0].getObject().getData() |
|
|
|
|
|
|
def showFile(self,fileId,wholePage=False): |
def showFile(self,fileId,wholePage=False): |
"""show a file |
"""show a file |
@param fileId: P-Number of the document to be displayed |
@param fileId: P-Number of the document to be displayed |
Line 2175 class CDLIRoot(Folder):
|
Line 2393 class CDLIRoot(Folder):
|
# add whitespace before and whitespace and line-end to splitter bounds expressions |
# add whitespace before and whitespace and line-end to splitter bounds expressions |
bounds = self.splitter[indexName].bounds |
bounds = self.splitter[indexName].bounds |
splitexp = "(%s|\s)(%%s)(%s|\s|\Z)"%(bounds,bounds) |
splitexp = "(%s|\s)(%%s)(%s|\s|\Z)"%(bounds,bounds) |
# compile into regexp objects |
# clean word expression |
wordlist = [re.compile(splitexp%w) for w in word.split(' ')] |
# TODO: this should use QueryParser itself |
|
# take out double quotes |
|
word = word.replace('"','') |
|
# take out ignorable signs |
|
ignorable = self.splitter[indexName].ignorex |
|
word = ignorable.sub('', word) |
|
# compile into regexp objects and escape parens |
|
wordlist = [re.compile(splitexp%re.escape(w)) for w in word.split(' ')] |
|
|
for line in file.split("\n"): |
for line in file.splitlines(): |
for word in wordlist: |
for word in wordlist: |
#logging.debug("showwordinfile: searching for %s in %s"%(word.pattern,line)) |
#logging.debug("showwordinfile: searching for %s in %s"%(word.pattern,ignoreable.sub('',line))) |
if word.search(line): |
if word.search(ignorable.sub('',line)): |
line = formatAtfLineHtml(line) |
line = formatAtfLineHtml(line) |
ret.append(line) |
ret.append(line) |
break |
break |
Line 2212 class CDLIRoot(Folder):
|
Line 2437 class CDLIRoot(Folder):
|
# add whitespace to splitter bounds expressions and compile into regexp object |
# add whitespace to splitter bounds expressions and compile into regexp object |
bounds = self.splitter[indexName].bounds |
bounds = self.splitter[indexName].bounds |
wordsplit = re.compile("(%s|\s)"%bounds) |
wordsplit = re.compile("(%s|\s)"%bounds) |
|
# clean word expression |
|
# TODO: this should use QueryParser itself |
|
word = word.replace('"','') # take out double quotes |
|
# take out ignoreable signs |
|
ignorable = self.splitter[indexName].ignorex |
|
word = ignorable.sub('', word) |
# split search terms by blanks |
# split search terms by blanks |
words = word.split(' ') |
words = word.split(' ') |
|
# split search terms again (for grapheme search with words) |
|
splitwords = dict(((w,self.splitter[indexName].process([w])) for w in words)) |
|
|
for line in file.split("\n"): |
for line in file.splitlines(): |
line = unicodify(line) |
line = unicodify(line) |
# ignore lemma lines |
# ignore lemma and other lines |
if line.lstrip().startswith('#lem:'): |
if line.lstrip().startswith('#lem:'): |
continue |
continue |
|
# ignore p-num line |
|
if line.startswith('&P'): |
|
continue |
|
# ignore version lines |
|
if line.startswith('#version'): |
|
continue |
|
# ignore atf type lines |
|
if line.startswith('#atf:'): |
|
continue |
|
|
# first scan |
# first scan |
hitwords = [] |
hitwords = [] |
for w in words: |
for w in words: |
if line.find(w) > -1: |
if ignorable.sub('',line).find(w) > -1: |
# word is in line |
# word is in line |
hitwords.append(w) |
# append split word for grapheme search with words |
|
hitwords.extend(splitwords[w]) |
|
#hitwords.extend(wordsplit.split(w)) |
|
|
# examine hits closer |
# examine hits closer |
if hitwords: |
if hitwords: |
Line 2234 class CDLIRoot(Folder):
|
Line 2478 class CDLIRoot(Folder):
|
parts = wordsplit.split(line) |
parts = wordsplit.split(line) |
line = "" |
line = "" |
for p in parts: |
for p in parts: |
|
#logging.debug("tagwordinfile: searching for %s in %s"%(p,hitwords)) |
# reassemble line |
# reassemble line |
if p in hitwords: |
if ignorable.sub('', p) in hitwords: |
|
#logging.debug("tagwordinfile: found %s in %s"%(p,hitwords)) |
# this part was found |
# this part was found |
line += tagStart + formatAtfHtml(p) + tagEnd |
line += tagStart + formatAtfHtml(p) + tagEnd |
else: |
else: |
Line 2260 class CDLIRoot(Folder):
|
Line 2506 class CDLIRoot(Folder):
|
return dict([(id,self.tagWordInFile(id, word, indexName, regExp)) for id in fileIds]) |
return dict([(id,self.tagWordInFile(id, word, indexName, regExp)) for id in fileIds]) |
|
|
|
|
|
def getFileVersionList(self, pnum): |
|
"""get the version history as a list for the translit file with the given pnum""" |
|
f = getattr(self, self.file_catalog).search({'textid':pnum}) |
|
if not f: |
|
return [] |
|
|
|
return f[0].getObject().getVersionList() |
|
|
|
|
def URLquote(self,str): |
def URLquote(self,str): |
"""quote url""" |
"""quote url""" |
return urllib.quote(str) |
return urllib.quote(str) |
Line 2508 class CDLIRoot(Folder):
|
Line 2763 class CDLIRoot(Folder):
|
pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadATFWait.zpt')).__of__(self) |
pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadATFWait.zpt')).__of__(self) |
return pt(txt='/uploadATFfinally',threadName=threadName) |
return pt(txt='/uploadATFfinally',threadName=threadName) |
else: |
else: |
|
|
|
|
|
idTmp=self.REQUEST.SESSION['idTmp'] |
|
stObj=getattr(self.temp_folder,idTmp) |
self.REQUEST.SESSION['idTmp']=None |
self.REQUEST.SESSION['idTmp']=None |
|
|
|
#update changed |
|
logging.debug("dir:"+repr(stObj.returnValue['changed'])) |
|
for x in stObj.returnValue['changed']: |
|
ob=self.CDLICatalog.search({'title':x[0]}) |
|
|
|
self.cdliRoot.updateOrAddToFileBTree(ob[0].getObject()) |
if RESPONSE is not None: |
if RESPONSE is not None: |
RESPONSE.redirect(self.absolute_url()) |
RESPONSE.redirect(self.absolute_url()) |
|
|
def importFiles(self,comment="",author="" ,folderName="/Users/dwinter/atf", files=None,ext=None): |
def importFiles(self,comment="",author="" ,folderName="/Users/dwinter/atf", files=None,ext=None): |
"""import files""" |
"""import files""" |
|
logging.debug("importFiles folderName=%s files=%s ext=%s"%(folderName,files,ext)) |
root=self.cdli_main |
root=self.cdli_main |
count=0 |
count=0 |
if not files: |
if not files: |
Line 2522 class CDLIRoot(Folder):
|
Line 2789 class CDLIRoot(Folder):
|
for f in files: |
for f in files: |
folder=f[0:3] |
folder=f[0:3] |
f2=f[0:5] |
f2=f[0:5] |
|
|
|
#check if main folder PXX already exists |
obj=self.ZopeFind(root,obj_ids=[folder]) |
obj=self.ZopeFind(root,obj_ids=[folder]) |
|
logging.debug("importFiles: folder=%s f2=%s obj=%s"%(folder,f2,obj)) |
if ext: |
if ext: |
|
|
ext.result="<p>adding: %s </p>"%f+ext.result |
ext.result="<p>adding: %s </p>"%f+ext.result |
if not obj: |
|
|
|
|
if not obj: # if not create it |
manage_addCDLIFileFolder(root,folder,folder) |
manage_addCDLIFileFolder(root,folder,folder) |
fobj=getattr(root,folder) |
fobj=getattr(root,folder) |
#transaction.get().commit() |
#transaction.get().commit() |
|
|
else: |
else: |
fobj=obj[0][1] |
fobj=obj[0][1] |
|
|
|
#check IF PYYYYY already exist |
obj2=fobj.ZopeFind(fobj,obj_ids=[f2]) |
obj2=fobj.ZopeFind(fobj,obj_ids=[f2]) |
|
logging.debug("importFiles: fobj=%s obj2=%s"%(fobj,obj2)) |
|
|
if not obj2: |
if not obj2:# if not create it |
manage_addCDLIFileFolder(fobj,f2,f2) |
manage_addCDLIFileFolder(fobj,f2,f2) |
fobj2=getattr(fobj,f2) |
fobj2=getattr(fobj,f2) |
|
|
else: |
else: |
fobj2=obj2[0][1] |
fobj2=obj2[0][1] |
|
|
|
# not add the file |
file2=os.path.join(folderName,f) |
file2=os.path.join(folderName,f) |
id=f |
id=f |
manage_addCDLIFile(fobj2,f,'','') |
logging.debug("importFiles: addCDLIFile fobj2=%s, f=%s file2=%s"%(fobj2,repr(f),repr(file2))) |
id=f |
fobj2.addFile(vC='',file=file(file2),author=author,newName=f) |
ob=fobj2._getOb(f) |
|
ob.title=id |
|
|
|
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 |
count+=1 |
|
|
if count > 1000: |
#now add the file to the storage |
print "committing" |
ob = getattr(fobj2,f) |
|
self.cdliRoot.updateOrAddToFileBTree(ob) |
|
|
|
if count%100==0: |
|
logging.debug("importfiles: committing") |
transaction.get().commit() |
transaction.get().commit() |
count=0 |
|
transaction.get().commit() |
transaction.get().commit() |
return "ok" |
return "ok" |
|
|