--- cdli/cdli_files.py 2007/03/21 14:14:08 1.70
+++ cdli/cdli_files.py 2007/03/21 19:29:23 1.71
@@ -635,7 +635,13 @@ class CDLIBasketContainer(OrderedFolder)
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):
"""createIds"""
@@ -1446,17 +1452,6 @@ def checkFile(filename,data,folder):
else:
return True,""
-# 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"""
@@ -1687,6 +1682,7 @@ class CDLIFileFolder(extVersionedFileFol
#os.write(tf,obj.getLastVersion().data)
if RESPONSE:
RESPONSE.write(obj.getLastVersion().getData()[0:])
+ RESPONSE.write("\n")
self.temp_folder.downloadCounter-=1
self._p_changed=1
transaction.get().commit()
@@ -1771,78 +1767,113 @@ 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"""
+ def findWordRegExp(self,indexName,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=[]
- for x in self.lineIndex.iterkeys():
+ for x in self.lineIndexes[indexName].iterkeys():
if re.match(searchTerm,x):
ret.append(x)
return ret
- def searchRegExpInLineIndexDocs(self,searchTerm):
- """search in inLineIndex with regexp"""
+ def searchRegExpInLineIndexDocs(self,indexName,searchTerm):
+ """search in inLineIndex with regexp
+ @param indexName: name of the index to be searched in
+ @param searchTerm: term to be searched
+ """
if not searchTerm:
return []
ret=[]
- words=self.findWordRegExp(searchTerm) # suche nach allen Treffern
+ words=self.findWordRegExp(indexName,searchTerm) # suche nach allen Treffern
logging.info("wd:%s"%words)
for word in words:
- ret+=self.searchInLineIndexDocs(word)
+ ret+=self.searchInLineIndexDocs(indexName,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
+ for key in self.lineIndexes.keys():
+ logging.info("index:%s"%key)
+ for x in self.lineIndexes[key].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.lineIndexes
- def searchInLineIndexDocs(self,word,uniq=True,regExp=False):
- """search occurences"""
+ def searchInLineIndexDocs(self,indexName,word,uniq=True,regExp=False):
+ """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:
- return self.searchRegExpInLineIndexDocs(word)
+ return self.searchRegExpInLineIndexDocs(indexName,word)
try:
- lst=list(self.lineIndex.get(word).keys())
+
+ lst=list(self.lineIndexes[indexName].get(word).keys())
except:
+ logging.error("error: searchInLineIndexDocs (%s %s)"%(sys.exc_info()[0:2]))
lst=[]
if uniq:
return unique(lst)
else:
return lst
- def getLinesFromIndex(self,word,doc,regExp=False):
- """get lines"""
+ def getLinesFromIndex(self,indexName,word,doc,regExp=False):
+ """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:
- return self.lineIndex.get(word)[doc]
+ return self.lineIndexes[indexName].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
+ for w in self.findWordRegExp(indexName,word):
+ if self.lineIndexes[indexName].get(w): # ein word in im dex gefunden
try:
- dc=self.lineIndex.get(word)[doc]
+ dc=self.lineIndex[indexName].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()]
+ def cleanInLineIndex(self,indexName):
+ """empty an InlineIndex
+ @param indexName: name of the index
+ """
+ for x in list(self.lineIndexes[indexName].keys()):
+ del(self.lineIndexes[indexName][x])
+ print [x for x in self.lineIndexes[indexName].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
+ def storeInLineIndex(self,indexName,key,value):
+ """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')):
+
+ self.lineIndexes={}
+
+ 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):
@@ -1860,51 +1891,36 @@ class CDLIRoot(Folder):
li[key][value[0]]=[value[1]]
- self.lineIndex=li
+ self.lineIndexes=lis
transaction.get().commit()
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})
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):
+ def showWordInFile(self,fileId,word,lineList=None,regExp=True,indexName=""):
"""get lines with word fromFileId"""
file=self.showFile(fileId)
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"):
+ found=False
+ for word in wordlist:
if line.find(word)>-1:
if lineList: #liste of moeglichen Zeilennummern
num=line.split(".")[0] #Zeilenummer ist alles vor dem . in der Zeile
@@ -1914,26 +1930,40 @@ class CDLIRoot(Folder):
ret.append(line)
else: # nimm alles ohne line check
ret.append(line)
+
+ break;
return ret
- def tagWordInFile(self,fileId,word,lineList=None):
+ def tagWordInFile(self,fileId,word,lineList=None,regExp=True,indexName=""):
"""get lines with word fromFileId"""
file=self.showFile(fileId)
tagStr="""%s"""
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"):
- 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
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:
+ found=True
+ break
+ if not found: #word wurde nicht gefunden keine makierung
ret.append(line)
+
return "
\n".join(ret)
def URLquote(self,str):
@@ -1963,19 +1993,8 @@ class CDLIRoot(Folder):
ret.append((f[0],un))
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):
"""getChangesByAuthor"""
zcat=self.CDLIObjectsCatalog
@@ -2041,6 +2060,8 @@ class CDLIRoot(Folder):
def uploadATF(self,repeat=None,upload=None,basketId=0,RESPONSE=None):
"""upload an atf file / basket file"""
#self._v_uploadATF.returnValue=None
+
+ #generate an random id for the upload thread
from random import randint
if (not self.REQUEST.SESSION.get('idTmp',None)):
@@ -2049,8 +2070,10 @@ class CDLIRoot(Folder):
else:
idTmp=self.REQUEST.SESSION.get('idTmp',None)
+
threadName=repeat
if not threadName or threadName=="":
+ #new thread not called from the waiting page
tmpVar=False
thread=uploadATFThread()
@@ -2098,26 +2121,8 @@ class CDLIRoot(Folder):
return pt(txt='/uploadATF',threadName=threadName)
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
-
-
-
-
- #del(self.cdli_main.tmpStore2[threadName])
-
-
+
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'],