cdli/cdli_files.py - diff

Return to cdli_files.py CVS log

Up to [Repository] / cdli

Diff for /cdli/cdli_files.py between versions 1.66 and 1.71

version 1.66, 2007/02/08 12:00:23	version 1.71, 2007/03/21 19:29:23
Line 425 class uploadATFThread(Thread):	Line 425 class uploadATFThread(Thread):
#if not than add filename to the list of newfiles	#if not than add filename to the list of newfiles

data=file(os.path.join(dir,fn)).read()	data=file(os.path.join(dir,fn)).read()
#status,msg=checkFile(fn,data,dir)	status,msg=checkFile(fn,data,dir)
status=True	#status=True
msg=""

if not status: # error	if not status: # error
errors.append((fn,msg))	errors.append((fn,msg))

else:	else:
if len(founds)==0:	if len(founds)==0:
newPs.append(fn)	newPs.append(fn)
Line 633 class CDLIBasketContainer(OrderedFolder)	Line 635 class CDLIBasketContainer(OrderedFolder)

return baskets	return baskets

	def joinBasket(self,newbasket,oldbaskets,delete=False):
	"""join two baskets
	@param newbasket: name of the new basket
	@param oldbaskets: list of baskets to be joined
	@param delete: (optional) delete the old baskets
	"""


def getNewId(self):	def getNewId(self):
Line 1183 class CDLIFileObject(CatalogAware,extVer	Line 1191 class CDLIFileObject(CatalogAware,extVer
def getFormattedData(self):	def getFormattedData(self):
"""fromat text"""	"""fromat text"""
data=self.getData()	data=self.getData()
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

def view(self):	def view(self):
"""view file"""	"""view file"""
Line 1420 def manage_addCDLIFile(self,id,title,loc	Line 1429 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):
	"""check utf 8"""
	try:
	data.encode('utf-8')
	return True
	except:
	return False


def checkFile(filename,data,folder):	def checkFile(filename,data,folder):
Line 1431 def checkFile(filename,data,folder):	Line 1447 def checkFile(filename,data,folder):
return False,"P missing in the filename"	return False,"P missing in the filename"
elif len(fn[0])!=7:	elif len(fn[0])!=7:
return False,"P number has not the right length 6"	return False,"P number has not the right length 6"
else:	elif not checkUTF8(data):
fn=os.path.join(folder,filename)	return False,"not utf-8"
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:	else:
return True,""	return True,""


def splitatf(fh,dir=None,ext=None):	def splitatf(fh,dir=None,ext=None):
"""split it"""	"""split it"""
ret=None	ret=None
Line 1537 class CDLIFileFolder(extVersionedFileFol	Line 1547 class CDLIFileFolder(extVersionedFileFol

return ret	return ret

	def getFile(self,fn):
	"""get the content of the file fn"""
	founds=self.CDLICatalog.search({'title':fn})
	if not founds:
	return []
	else:
	obj=founds[0].getObject().getLastVersion()

	return obj.getData()[0:]

def checkCatalog(self,fn):	def checkCatalog(self,fn):
"""check if fn is in the catalog"""	"""check if fn is in the catalog"""
#TODO add checkCatalog	#TODO add checkCatalog
Line 1559 class CDLIFileFolder(extVersionedFileFol	Line 1579 class CDLIFileFolder(extVersionedFileFol
return pt(search=list,author=author)	return pt(search=list,author=author)


	def getAllPNumbers(self):
	"""get a list of all files (resp their p-numbers) stored"""

	ret=[x.getId for x in self.CDLICatalog()]

	return ret

def findObjectsFromList(self,enterList=None,display=False,start=None,upload=None,list=None,basketName=None,numberOfObjects=None,RESPONSE=None):	def findObjectsFromList(self,enterList=None,display=False,start=None,upload=None,list=None,basketName=None,numberOfObjects=None,RESPONSE=None):
"""findObjectsFromList (, TAB oder LINE separated)"""	"""findObjectsFromList (, TAB oder LINE separated)"""
Line 1656 class CDLIFileFolder(extVersionedFileFol	Line 1682 class CDLIFileFolder(extVersionedFileFol
#os.write(tf,obj.getLastVersion().data)	#os.write(tf,obj.getLastVersion().data)
if RESPONSE:	if RESPONSE:
RESPONSE.write(obj.getLastVersion().getData()[0:])	RESPONSE.write(obj.getLastVersion().getData()[0:])
	RESPONSE.write("\n")
self.temp_folder.downloadCounter-=1	self.temp_folder.downloadCounter-=1
self._p_changed=1	self._p_changed=1
transaction.get().commit()	transaction.get().commit()
Line 1740 class CDLIRoot(Folder):	Line 1767 class CDLIRoot(Folder):
meta_type="CDLIRoot"	meta_type="CDLIRoot"
downloadCounterBaskets=0# counts the current basket downloads if counter > 10 no downloads are possible	downloadCounterBaskets=0# counts the current basket downloads if counter > 10 no downloads are possible

def findWordRegExp(self,searchTerm):	def findWordRegExp(self,indexName,searchTerm):
"""find all words in index which match regexp in SearchTerm"""	"""find all words in index which match regexp in SearchTerm
	@param indexName: name of the index to be searched in
	@param searchTerm: word to be searched"""

ret=[]	ret=[]
for x in self.lineIndex.iterkeys():	for x in self.lineIndexes[indexName].iterkeys():
if re.match(searchTerm,x):	if re.match(searchTerm,x):
ret.append(x)	ret.append(x)
return ret	return ret

def searchRegExpInLineIndexDocs(self,searchTerm):	def searchRegExpInLineIndexDocs(self,indexName,searchTerm):
"""search in inLineIndex with regexp"""	"""search in inLineIndex with regexp
	@param indexName: name of the index to be searched in
	@param searchTerm: term to be searched
	"""
if not searchTerm:	if not searchTerm:
return []	return []
ret=[]	ret=[]
words=self.findWordRegExp(searchTerm) # suche nach allen Treffern	words=self.findWordRegExp(indexName,searchTerm) # suche nach allen Treffern
logging.info("wd:%s"%words)	logging.info("wd:%s"%words)
for word in words:	for word in words:
ret+=self.searchInLineIndexDocs(word)	ret+=self.searchInLineIndexDocs(indexName,word)

return unique(ret)	return unique(ret)

def showInLineIndex(self):	def showInLineIndex(self):
"""get the index for debug purposes"""	"""get the index for debug purposes"""
print "show"	print "show"
for x in self.lineIndex.iterkeys():	for key in self.lineIndexes.keys():
	logging.info("index:%s"%key)
	for x in self.lineIndexes[key].iterkeys():
logging.info("word:%s"%repr(x))	logging.info("word:%s"%repr(x))
#for y in self.lineIndex[x].iterkeys():	#for y in self.lineIndex[x].iterkeys():
# print "doc",repr(y),repr(self.lineIndex[x][y])	# print "doc",repr(y),repr(self.lineIndex[x][y])

return self.lineIndex	return self.lineIndexes

def searchInLineIndexDocs(self,word,uniq=True,regExp=False):	def searchInLineIndexDocs(self,indexName,word,uniq=True,regExp=False):
"""search occurences"""	"""search occurences in an index
	@param indexName: name of the index to be searched in
	@param word: word to be searched
	@param unique: (optional) unify the list of results
	@param regExp: (optional) use regular expressions
	"""

if regExp:	if regExp:
return self.searchRegExpInLineIndexDocs(word)	return self.searchRegExpInLineIndexDocs(indexName,word)

try:	try:
lst=list(self.lineIndex.get(word).keys())
	lst=list(self.lineIndexes[indexName].get(word).keys())
except:	except:
	logging.error("error: searchInLineIndexDocs (%s %s)"%(sys.exc_info()[0:2]))
lst=[]	lst=[]
if uniq:	if uniq:
return unique(lst)	return unique(lst)
else:	else:
return lst	return lst

def getLinesFromIndex(self,word,doc,regExp=False):	def getLinesFromIndex(self,indexName,word,doc,regExp=False):
"""get lines"""	"""return all lines from a document where word is found
	@param indexName: Name of the index
	@param word: word to be searched
	@param doc: name of the document (usuallay the p-number)
	@param regExp: (optional) use regExp
	"""

if not regExp:	if not regExp:
return self.lineIndex.get(word)[doc]	return self.lineIndexes[indexName].get(word)[doc]
else: # wenn regexp, suche welches word	else: # wenn regexp, suche welches word
for w in self.findWordRegExp(word):	for w in self.findWordRegExp(indexName,word):
if self.lineIndex.get(w): # ein word in im dex gefunden	if self.lineIndexes[indexName].get(w): # ein word in im dex gefunden
try:	try:
dc=self.lineIndex.get(word)[doc]	dc=self.lineIndex[indexName].get(word)[doc]
return dc # und ein document dann gib es zurueck	return dc # und ein document dann gib es zurueck
except:	except:
pass #andernfalls weiter	pass #andernfalls weiter

def cleanInLineIndex(self):	def cleanInLineIndex(self,indexName):
"""delete InlineIndex"""	"""empty an InlineIndex
for x in list(self.lineIndex.keys()):	@param indexName: name of the index
del(self.lineIndex[x])	"""
print [x for x in self.lineIndex.keys()]	for x in list(self.lineIndexes[indexName].keys()):
	del(self.lineIndexes[indexName][x])
	print [x for x in self.lineIndexes[indexName].keys()]

return "ok"	return "ok"

def storeInLineIndex(self,key,value):	def storeInLineIndex(self,indexName,key,value):
"""store in index"""	"""store in index, key is normally a word or grapheme
	and value is a tuple (documentname, line) where the word can be found
	@param indexName: name of the index
	@param key: key in index
	@param value: value in index, value is a tuple (document name, line)
	"""
	logging.error("indexing: %s %s"%(indexName,key))
	if (not hasattr(self,'lineIndexes')):

if (not hasattr(self,'lineIndex')) or (type(self.lineIndex) is DictType):	self.lineIndexes={}
self.lineIndex=OOBTree()
li=self.lineIndex	if self.lineIndexes.get(indexName,None) is None:
	#index exisitiert noch nicht dann anlegen

	self.lineIndexes[indexName]=OOBTree()
	lis=self.lineIndexes
	li=lis[indexName]

if li.has_key(key):	if li.has_key(key):

Line 1829 class CDLIRoot(Folder):	Line 1891 class CDLIRoot(Folder):
li[key][value[0]]=[value[1]]	li[key][value[0]]=[value[1]]


self.lineIndex=li	self.lineIndexes=lis

transaction.get().commit()	transaction.get().commit()


def showFile(self,fileId):	def showFile(self,fileId):
"""show a file"""	"""show a file
	@param fileId: P-Number of the document to be displayed
	"""
f=self.CDLICatalog({'title':fileId})	f=self.CDLICatalog({'title':fileId})
if not f:	if not f:
return ""	return ""

return f[0].getObject().getLastVersionFormattedData()	return f[0].getObject().getLastVersionFormattedData()

def showLineFromFile(self,fileId,lineNum,word):
"""get line lineNum fromFileId"""

file=self.showFile(fileId)	def showWordInFile(self,fileId,word,lineList=None,regExp=True,indexName=""):
#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"""	"""get lines with word fromFileId"""

file=self.showFile(fileId)	file=self.showFile(fileId)

ret=[]	ret=[]
	if regExp: # wenn regexp dann generiere alle worte aus der list die der regexp entsprechen
	wordlist=self.findWordRegExp(indexName,word)
	else:
	wordlist=[word]

for line in file.split("\n"):	for line in file.split("\n"):
	found=False
	for word in wordlist:
if line.find(word)>-1:	if line.find(word)>-1:
if lineList: #liste of moeglichen Zeilennummern	if lineList: #liste of moeglichen Zeilennummern
num=line.split(".")[0] #Zeilenummer ist alles vor dem . in der Zeile	num=line.split(".")[0] #Zeilenummer ist alles vor dem . in der Zeile
Line 1883 class CDLIRoot(Folder):	Line 1930 class CDLIRoot(Folder):
ret.append(line)	ret.append(line)
else: # nimm alles ohne line check	else: # nimm alles ohne line check
ret.append(line)	ret.append(line)

	break;
return ret	return ret

def tagWordInFile(self,fileId,word,lineList=None):	def tagWordInFile(self,fileId,word,lineList=None,regExp=True,indexName=""):
"""get lines with word fromFileId"""	"""get lines with word fromFileId"""

file=self.showFile(fileId)	file=self.showFile(fileId)
tagStr="""<span class="found">%s</span>"""	tagStr="""<span class="found">%s</span>"""
ret=[]	ret=[]

	if regExp: # wenn regexp dann generiere alle worte aus der list die der regexp entsprechen
	wordlist=self.findWordRegExp(indexName,word)
	else:
	wordlist=[word]

for line in file.split("\n"):	for line in file.split("\n"):
if line.find(word)>-1:	found=False
	for word in wordlist:
	if line.find(word)>-1: #word ist gefunden dann makiere und breche die Schleife ab
if lineList: #liste of moeglichen Zeilennummern	if lineList: #liste of moeglichen Zeilennummern
num=line.split(".")[0] #Zeilenummer ist alles vor dem . in der Zeile	num=line.split(".")[0] #Zeilenummer ist alles vor dem . in der Zeile

if num in lineList:	if num in lineList:

ret.append(line.replace(word,tagStr%word))	ret.append(line.replace(word,tagStr%word))

else: # nimm alles ohne line check	else: # nimm alles ohne line check
ret.append(line.replace(word,tagStr%word))	ret.append(line.replace(word,tagStr%word))
else:	found=True
	break
	if not found: #word wurde nicht gefunden keine makierung
ret.append(line)	ret.append(line)

return "<br>\n".join(ret)	return "<br>\n".join(ret)

def URLquote(self,str):	def URLquote(self,str):
Line 1933 class CDLIRoot(Folder):	Line 1994 class CDLIRoot(Folder):

return 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):	def getChangesByAuthor(self,author,n=100):
"""getChangesByAuthor"""	"""getChangesByAuthor"""
Line 2008 class CDLIRoot(Folder):	Line 2058 class CDLIRoot(Folder):


def uploadATF(self,repeat=None,upload=None,basketId=0,RESPONSE=None):	def uploadATF(self,repeat=None,upload=None,basketId=0,RESPONSE=None):
"""standard ausgabe"""	"""upload an atf file / basket file"""
#self._v_uploadATF.returnValue=None	#self._v_uploadATF.returnValue=None

	#generate an random id for the upload thread
from random import randint	from random import randint
if (not self.REQUEST.SESSION.get('idTmp',None)):	if (not self.REQUEST.SESSION.get('idTmp',None)):

Line 2018 class CDLIRoot(Folder):	Line 2070 class CDLIRoot(Folder):
else:	else:
idTmp=self.REQUEST.SESSION.get('idTmp',None)	idTmp=self.REQUEST.SESSION.get('idTmp',None)


threadName=repeat	threadName=repeat
if not threadName or threadName=="":	if not threadName or threadName=="":
	#new thread not called from the waiting page
tmpVar=False	tmpVar=False

thread=uploadATFThread()	thread=uploadATFThread()
Line 2067 class CDLIRoot(Folder):	Line 2121 class CDLIRoot(Folder):
return pt(txt='/uploadATF',threadName=threadName)	return pt(txt='/uploadATF',threadName=threadName)

else:	else:
# tmp={}
# for key in self._v_uploadATF[threadName].returnValue.keys():
# t=self._v_uploadATF[threadName].returnValue[key]
# if type(t) is ListType:
# tmp[key]=self._v_uploadATF[threadName].returnValue[key][0:]
# else:
# tmp[key]=self._v_uploadATF[threadName].returnValue[key]
# repr(tmp[key]),repr(key)
#
# #
#tmp=self.cdli_main.tmpStore2[threadName]

tmp=getattr(self.temp_folder,idTmp).returnValue	tmp=getattr(self.temp_folder,idTmp).returnValue




#del(self.cdli_main.tmpStore2[threadName])


pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadCheck.zpt')).__of__(self)	pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadCheck.zpt')).__of__(self)

return pt(changed=tmp['changed'],lockerrors=tmp['lockerrors'],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'],

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

Removed from v.1.66
changed lines
	Added in v.1.71