version 1.49, 2006/10/16 13:19:34
|
version 1.57, 2007/01/09 16:06:09
|
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 |
|
import logging |
|
|
|
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): |
class BasketContent(SimpleItem): |
Line 691 class CDLIBasketContainer(OrderedFolder)
|
Line 762 class CDLIBasketContainer(OrderedFolder)
|
self.id=id |
self.id=id |
self.title=title |
self.title=title |
|
|
|
|
def getBasketsId(self): |
def getBasketsId(self): |
"""get all baskets als klartext""" |
"""get all baskets als klartext""" |
|
|
ret="" |
ret="" |
baskets=self.ZopeFind(self,obj_metatypes=['CDLIBasket']) |
baskets=self.ZopeFind(self,obj_metatypes=['CDLIBasket']) |
for basket in baskets: |
for basket in baskets: |
Line 1005 class CDLIBasket(Folder,CatalogAware):
|
Line 1078 class CDLIBasket(Folder,CatalogAware):
|
|
|
return added |
return added |
|
|
|
|
|
|
|
|
def getContentIds(self): |
def getContentIds(self): |
"""print basket content""" |
"""print basket content""" |
ret=[] |
ret=[] |
Line 1303 class CDLIFileObject(CatalogAware,extVer
|
Line 1379 class CDLIFileObject(CatalogAware,extVer
|
|
|
security.declarePublic('view') |
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): |
def view(self): |
"""view file""" |
"""view file""" |
pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','viewCDLIFile.zpt')).__of__(self) |
pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','viewCDLIFile.zpt')).__of__(self) |
Line 1384 class CDLIFile(extVersionedFile,CatalogA
|
Line 1465 class CDLIFile(extVersionedFile,CatalogA
|
default_catalog='CDLICatalog' |
default_catalog='CDLICatalog' |
|
|
#security.declarePublic('history') |
#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): |
def history(self): |
"""history""" |
"""history""" |
|
|
Line 1584 def splitatf(fh,dir=None,ext=None):
|
Line 1676 def splitatf(fh,dir=None,ext=None):
|
filename=os.path.join(dir,filename) |
filename=os.path.join(dir,filename) |
nf=file(filename,"w") |
nf=file(filename,"w") |
if nf: |
if nf: |
nf.write(line) |
nf.write(line.replace("\n","")+"\n") |
|
|
nf.close() |
nf.close() |
fh.close() |
fh.close() |
Line 1840 class CDLIRoot(Folder):
|
Line 1932 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): |
|
"""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 |
|
|
|
get_transaction().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="""<span class="found">%s</span>""" |
|
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 "<br>\n".join(ret) |
|
|
def URLquote(self,str): |
def URLquote(self,str): |
"""quote url""" |
"""quote url""" |
return urllib.quote(str) |
return urllib.quote(str) |