--- cdli/cdli_files.py 2006/12/22 16:43:42 1.54 +++ cdli/cdli_files.py 2007/01/24 18:05:24 1.58 @@ -22,6 +22,78 @@ from ZPublisher.HTTPResponse import HTTP from ZPublisher.BaseRequest import RequestContainer import threading from BTrees.OOBTree import OOBTree +import logging +import transaction + +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""" @@ -96,7 +168,7 @@ 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 @@ -240,9 +312,9 @@ class uploadATFThread(Thread): self.uploadATFThread(ctx,self.upload,self.basketId) #ctx.cdliRoot.cdli_main.tmpStore2[self.getName()[0:]]=self.returnValue - - get_transaction().commit() - + + + transaction.get().commit() while self.continueVar: pass @@ -559,8 +631,8 @@ class BasketObject_old(Folder): self.temp_folder.downloadCounter+=1 self._p_changed=1 - get_transaction().commit() - + + transaction.get().commit() for object in self.contents: @@ -578,7 +650,8 @@ class BasketObject_old(Folder): self.REQUEST.RESPONSE.write(ret) self.temp_folder.downloadCounter-=1 self._p_changed=1 - get_transaction().commit() + transaction.get().commit() + def manage_addBasket_oldObjectForm(self): @@ -1128,10 +1201,10 @@ class CDLIBasketVersion(Implicit,Persist if str(self.REQUEST['AUTHENTICATED_USER'])=='Anonymous User': self.temp_folder.downloadCounterBaskets-=1 self._p_changed=1 - get_transaction().commit() + transaction.get().commit() self.temp_folder.downloadCounterBaskets-=1 self._p_changed=1 - get_transaction().commit() + transaction.get().commit() return "please login first" #check if a locked object exist in the basket. @@ -1151,7 +1224,7 @@ class CDLIBasketVersion(Implicit,Persist self.temp_folder.downloadCounterBaskets-=1 self._p_changed=1 - get_transaction().commit() + transaction.get().commit() return pt() @@ -1181,7 +1254,7 @@ class CDLIBasketVersion(Implicit,Persist self.temp_folder.downloadCounterBaskets-=1 self._p_changed=1 - get_transaction().commit() + transaction.get().commit() self.REQUEST.RESPONSE.setHeader("Content-Disposition","""attachement; filename="%s.atf" """%basket_name) self.REQUEST.RESPONSE.setHeader("Content-Type","application/octet-stream") @@ -1760,7 +1833,7 @@ class CDLIFileFolder(extVersionedFileFol self.temp_folder.downloadCounter+=1 self._p_changed=1 - get_transaction().commit() + transaction.get().commit() list=[(x.getId,x) for x in catalog()] list.sort(sortF) @@ -1780,7 +1853,7 @@ class CDLIFileFolder(extVersionedFileFol RESPONSE.write(obj.getLastVersion().getData()[0:]) self.temp_folder.downloadCounter-=1 self._p_changed=1 - get_transaction().commit() + transaction.get().commit() #os.close(tf) #RESPONSE.redirect(self.absolute_url()+"/downloadFile?fn="%tfilename) return True @@ -1862,24 +1935,64 @@ class CDLIRoot(Folder): 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(): - print "word:",x - for y in self.lineIndex[x].iterkeys(): - print "doc",y,self.lineIndex[x][y] + 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): + def searchInLineIndexDocs(self,word,uniq=True,regExp=False): """search occurences""" - return list(self.lineIndex.get(word.upper()).keys()) - def getLinesFromIndex(self,word,doc): + 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""" - return self.lineIndex[word][doc] - + 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()): @@ -1913,7 +2026,7 @@ class CDLIRoot(Folder): self.lineIndex=li - get_transaction().commit() + transaction.get().commit() def showFile(self,fileId): @@ -1923,7 +2036,70 @@ class CDLIRoot(Folder): 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) @@ -1932,6 +2108,14 @@ 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" @@ -2164,7 +2348,7 @@ 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] @@ -2192,9 +2376,9 @@ class CDLIRoot(Folder): if count > 1000: print "committing" - get_transaction().commit() + transaction.get().commit() count=0 - get_transaction().commit() + transaction.get().commit() return "ok"