1: """CDLI extensions of the filearchive"""
2: from Products.versionedFile.extVersionedFile import *
3: from Products.ZCatalog.CatalogPathAwareness import CatalogAware
4: from tempfile import mkstemp,mkdtemp
5: import os.path
6: import os
7: from types import *
8: import urlparse
9: import urllib
10: import cgi
11: from OFS.OrderedFolder import OrderedFolder
12: from OFS.SimpleItem import SimpleItem
13: import time
14: from OFS.Folder import manage_addFolder
15: import re
16: from AccessControl import ClassSecurityInfo
17: from Acquisition import Implicit
18: from Globals import Persistent
19: from threading import Thread
20: from ZPublisher.HTTPRequest import HTTPRequest
21: from ZPublisher.HTTPResponse import HTTPResponse
22: from ZPublisher.BaseRequest import RequestContainer
23: import threading
24: from BTrees.OOBTree import OOBTree, OOTreeSet
25: import logging
26: import transaction
27: import copy
28: import codecs
29: import sys
30: from BTrees.IOBTree import IOBTree
31: import cdliSplitter
32: from sets import Set
33: import md5
34:
35: def unicodify(s):
36: """decode str (utf-8 or latin-1 representation) into unicode object"""
37: if not s:
38: return u""
39: if isinstance(s, str):
40: try:
41: return s.decode('utf-8')
42: except:
43: return s.decode('latin-1')
44: else:
45: return s
46:
47: def utf8ify(s):
48: """encode unicode object or string into byte string in utf-8 representation.
49: assumes string objects to be utf-8"""
50: if not s:
51: return ""
52: if isinstance(s, str):
53: return s
54: else:
55: return s.encode('utf-8')
56:
57: def formatAtfHtml(l):
58: """escape special ATF characters for HTML"""
59: if not l:
60: return ""
61:
62: # replace &
63: l = l.replace('&','&')
64: # replace angular brackets
65: l = l.replace('<','<')
66: l = l.replace('>','>')
67: return l
68:
69: def formatAtfLineHtml(l, nolemma=True):
70: """format ATF line for HTML"""
71: if not l:
72: return ""
73:
74: if nolemma:
75: # ignore lemma lines
76: if l.lstrip().startswith('#lem:'):
77: return ""
78:
79: return formatAtfHtml(l)
80:
81:
82:
83: def formatAtfFullLineNum(txt, nolemma=True):
84: """format full line numbers in ATF text"""
85: # surface codes
86: surfaces = {'@obverse':'obv',
87: '@reverse':'rev',
88: '@surface':'surface',
89: '@edge':'edge',
90: '@left':'left',
91: '@right':'right',
92: '@top':'top',
93: '@bottom':'bottom',
94: '@face':'face',
95: '@seal':'seal'}
96:
97: if not txt:
98: return ""
99:
100: ret = []
101: surf = ""
102: col = ""
103: for line in txt.splitlines():
104: line = unicodify(line)
105: if line and line[0] == '@':
106: # surface or column
107: words = line.split(' ')
108: if words[0] in surfaces:
109: surf = line.replace(words[0],surfaces[words[0]]).strip()
110:
111: elif words[0] == '@column':
112: col = ' '.join(words[1:])
113:
114: elif line and line[0] in '123456789':
115: # ordinary line -> add line number
116: line = "%s:%s:%s"%(surf,col,line)
117:
118: ret.append(line)
119:
120: return '\n'.join(ret)
121:
122:
123: def generateXMLReturn(hash):
124: """erzeugt das xml file als returnwert fuer uploadATFRPC"""
125:
126: ret="<return>"
127:
128: ret+="<errors>"
129: for error in hash['errors']:
130: ret+="""<error atf="%s">%s</error>"""%error
131:
132: ret+="</errors>"
133:
134: ret+="<changes>"
135: for changed in hash['changed']:
136: ret+="""<change atf="%s">%s</change>"""%changed
137: ret+="</changes>"
138:
139: ret+="<newPs>"
140: for new in hash['newPs']:
141: ret+="""<new atf="%s"/>"""%new
142: ret+="</newPs>"
143:
144: ret+="</return>"
145: return ret
146:
147:
148: def unique(s):
149: """Return a list of the elements in s, but without duplicates.
150:
151: For example, unique([1,2,3,1,2,3]) is some permutation of [1,2,3],
152: unique("abcabc") some permutation of ["a", "b", "c"], and
153: unique(([1, 2], [2, 3], [1, 2])) some permutation of
154: [[2, 3], [1, 2]].
155:
156: For best speed, all sequence elements should be hashable. Then
157: unique() will usually work in linear time.
158:
159: If not possible, the sequence elements should enjoy a total
160: ordering, and if list(s).sort() doesn't raise TypeError it's
161: assumed that they do enjoy a total ordering. Then unique() will
162: usually work in O(N*log2(N)) time.
163:
164: If that's not possible either, the sequence elements must support
165: equality-testing. Then unique() will usually work in quadratic
166: time.
167: (from the python cookbook)
168: """
169:
170: n = len(s)
171: if n == 0:
172: return []
173:
174: # Try using a dict first, as that's the fastest and will usually
175: # work. If it doesn't work, it will usually fail quickly, so it
176: # usually doesn't cost much to *try* it. It requires that all the
177: # sequence elements be hashable, and support equality comparison.
178: u = {}
179: try:
180: for x in s:
181: u[x] = 1
182: except TypeError:
183: del u # move on to the next method
184: else:
185: return u.keys()
186:
187: # We can't hash all the elements. Second fastest is to sort,
188: # which brings the equal elements together; then duplicates are
189: # easy to weed out in a single pass.
190: # NOTE: Python's list.sort() was designed to be efficient in the
191: # presence of many duplicate elements. This isn't true of all
192: # sort functions in all languages or libraries, so this approach
193: # is more effective in Python than it may be elsewhere.
194: try:
195: t = list(s)
196: t.sort()
197: except TypeError:
198: del t # move on to the next method
199: else:
200: assert n > 0
201: last = t[0]
202: lasti = i = 1
203: while i < n:
204: if t[i] != last:
205: t[lasti] = last = t[i]
206: lasti += 1
207: i += 1
208: return t[:lasti]
209:
210: # Brute force is all that's left.
211: u = []
212: for x in s:
213: if x not in u:
214: u.append(x)
215: return u
216:
217:
218: class BasketContent(SimpleItem):
219: """classe fuer den Inhalt eines Baskets"""
220:
221: def __init__(self,content=[]):
222: """content"""
223: self.contentList=content[0:]
224:
225: def getContent(self):
226: """get content"""
227:
228: return self.contentList
229:
230: def setContent(self,content):
231: self.contentList=content[0:]
232:
233: def numberOfItems(self):
234: """number"""
235:
236: return len(self.getContent())
237:
238:
239: class uploadATFfinallyThread(Thread):
240: """class for adding uploaded filed (temporarily stored in the staging area at /tmp"""
241:
242: def __init__(self):
243: """init for uploadATFfinallyThread"""
244: self.continueVar=True
245: self.returnValue=None
246: self.end=False
247: Thread.__init__(self)
248:
249: def set(self,procedure,comment="",basketname='',unlock=None,SESSION=None,username=None,serverport="8080"):
250: """set start values for the thread"""
251: self.procedure=procedure
252: self.comment=comment
253: self.basketname=basketname
254: self.unlock=unlock
255: self.SESSION=SESSION
256: self.username=username
257: self.serverport=serverport
258:
259:
260: def __call__(self):
261: """call of the thread (equals run)"""
262: self.run()
263: return True
264:
265: def getContext(self, app,serverport="8080"):
266: """get the context within the ZODB"""
267:
268: resp = HTTPResponse(stdout=None)
269: env = {
270: 'SERVER_NAME':'localhost',
271: 'SERVER_PORT':serverport,
272: 'REQUEST_METHOD':'GET'
273: }
274: req = HTTPRequest(None, env, resp)
275: return app.__of__(RequestContainer(REQUEST = req))
276:
277:
278: def run(self):
279: """run"""
280:
281: self.result=""
282: #find context within ZODB
283: from Zope import DB
284: conn = DB.open()
285: root = conn.root()
286: app = root['Application']
287: ctx = self.getContext(app,serverport=self.serverport)
288:
289: #add the files
290: self.uploadATFfinallyThread(ctx,self.procedure,comment=self.comment,basketname=self.basketname,unlock=self.unlock,SESSION=self.SESSION,username=self.username)
291: #commit the transactions
292: transaction.get().commit()
293: conn.close()
294: #set flag for end of this method
295: self.end=True
296: logging.info("ended")
297: return True
298:
299: def __del__(self):
300: """delete"""
301:
302:
303:
304: def getResult(self):
305: """method for accessing result"""
306:
307: return self.result
308:
309: def uploadATFfinallyThread(self,ctx,procedure,comment="",basketname='',unlock=None,RESPONSE=None,SESSION=None,username=None):
310: """upload the files"""
311: #TODO: make this configurable, at the moment, rootFolder for cdli has to be cdliRoot
312: ctx2=ctx.cdliRoot
313:
314: self.result+="<h2>Start processing</h2>"
315:
316: #shall I only upload the changed files?
317: logging.debug("uploadATFfinally procedure: %s"%procedure)
318: if procedure=="uploadchanged":
319: changed=[x[0] for x in SESSION.get('changed',[])]
320: uploadFns=changed+SESSION.get('newPs',[])
321:
322: #or all
323: elif procedure=="uploadAll":
324: uploadFns=[]
325: for x in os.listdir(SESSION['tmpdir']):
326: if not x in SESSION['lockerrors']:
327: uploadFns.append(x)
328:
329: #or maybe nothing
330: elif procedure=="noupload":
331: return True
332: else:
333: uploadFns=[]
334:
335: #do first the changed files
336: i=0
337: for fn in uploadFns:
338: logging.debug("uploadATFfinally uploadFn=%s"%fn)
339: i+=1
340: founds=ctx2.CDLICatalog.search({'title':fn})
341: if len(founds)>0:
342: SESSION['author']=str(username)
343: self.result="<p>Changing : %s"%fn+self.result
344: logging.debug("uploadatffinallythread changing:%s"%fn+self.result)
345: founds[0].getObject().manage_addCDLIFileObject('',comment,SESSION['author'],file=os.path.join(SESSION['tmpdir'],fn),from_tmp=True)
346: if i%200==0:
347: transaction.get().commit()
348: logging.debug("uploadatffinallythread changing: do commit")
349:
350: transaction.get().commit()
351: logging.debug("uploadatffinallythread changing: last commit")
352:
353: #now add the new files
354: newPs=SESSION['newPs']
355: if len(newPs)>0:
356: tmpDir=SESSION['tmpdir']
357: logging.debug("uploadatffinallythread adding start")
358: self.result="<p>Adding files</p>"+self.result
359: #TODO: make this configurable, at the moment base folder for the files has to be cdli_main
360: ctx2.importFiles(comment=comment,author=str(username) ,folderName=tmpDir, files=newPs,ext=self)
361: logging.debug("uploadatffinallythread adding finished")
362:
363: #unlock locked files?
364: if unlock:
365: logging.debug("uploadatffinallythread unlocking start")
366: self.result="<p>Unlock files</p>"+self.result
367: unlockFns=[]
368: for x in os.listdir(SESSION['tmpdir']):
369: if not x in SESSION['errors']:
370: unlockFns.append(x)
371:
372: logging.debug("unlocking have now what to unlock")
373:
374: for fn in unlockFns:
375: #logging.info("will unlock: %s"%fn)
376: founds=ctx2.CDLICatalog.search({'title':fn})
377: #logging.info("found it: %s"%repr(founds))
378: if len(founds)>0:
379: #logging.info("unlock: %s"%founds[0].getObject().getId())
380: SESSION['author']=str(username)
381: founds[0].getObject().lockedBy=""
382:
383: logging.debug("uploadatffinallythread unlocking done")
384:
385: #if a basketname is given, add files to the basket
386: if not (basketname ==''):
387: logging.debug("uploadatffinallythread add to basket %s"%basketname)
388: self.result="<p>Add to basket</p>"+self.result
389: basketId=ctx2.basketContainer.getBasketIdfromName(basketname)
390:
391: if not basketId: # create new basket
392: logging.debug("uploadatffinallythread create basket %s"%basketname)
393: self.result="<p>Create a new basket</p>"+self.result
394: ob=ctx2.basketContainer.addBasket(basketname)
395: basketId=ob.getId()
396: basket=getattr(ctx2.basketContainer,str(basketId))
397: ids=os.listdir(SESSION['tmpdir'])
398: basket.addObjects(ids,deleteOld=True,username=str(username))
399:
400: logging.debug("uploadatffinallythread uploadfinally done")
401:
402: if RESPONSE is not None:
403: RESPONSE.redirect(self.aq_parent.absolute_url())
404:
405: return True
406:
407: class tmpStore(SimpleItem):
408: """simple item"""
409: meta_type="cdli_upload"
410:
411: def __init__(self,id):
412: """init tmp"""
413: self.id=id
414:
415: class uploadATFThread(Thread):
416: """class for checking the files befor uploading"""
417:
418: def __init__(self):
419: """initialise"""
420:
421: self.continueVar=True
422: self.returnValue=None
423:
424: Thread.__init__(self)
425:
426:
427: def set(self,upload,basketId,username,idTmp,serverport="8080"):
428: """set start values for the thread"""
429: self.result=""
430: self.upload=upload
431: self.basketId=basketId
432: self.username=username
433: self.serverport=serverport
434: self.idTmp=idTmp
435:
436: def __call__(self):
437: """call method """
438: self.run()
439: return True
440:
441: def getContext(self, app,serverport="8080"):
442: """get the context within the ZODB"""
443: resp = HTTPResponse(stdout=None)
444: env = {
445: 'SERVER_NAME':'localhost',
446: 'SERVER_PORT':serverport,
447: 'REQUEST_METHOD':'GET'
448: }
449: req = HTTPRequest(None, env, resp)
450: return app.__of__(RequestContainer(REQUEST = req))
451:
452: def run(self):
453: idTmp=self.idTmp
454: self.result=""
455: #find context within ZODB
456: from Zope import DB
457: conn = DB.open()
458: root = conn.root()
459: app = root['Application']
460: ctx = self.getContext(app,serverport=self.serverport)
461: logging.info("run intern")
462: try:
463: logging.info("created: %s"%idTmp)
464: ctx.temp_folder._setObject(idTmp,tmpStore(idTmp))
465: except:
466: logging.error("thread upload: %s %s"%sys.exc_info()[0:2])
467:
468: logging.info("call thread intern")
469: self.uploadATFThread(ctx,self.upload,idTmp,self.basketId)
470:
471: #ctx.cdliRoot.cdli_main.tmpStore2[self.getName()[0:]]=self.returnValue
472:
473:
474: transaction.get().commit()
475:
476: conn.close()
477:
478: return getattr(ctx.temp_folder,idTmp)
479:
480: def getResult(self):
481: """method for accessing result"""
482: return self.result
483:
484: def uploadATFThread(self,ctx,upload,idTmp,basketId=0):
485: """upload an atf file"""
486: #TODO: add comments
487: #TODO: finish uploadATF
488:
489: stObj=getattr(ctx.temp_folder,idTmp)
490: logging.info("start, upload thread")
491: self.result="<html><body><h2>I got your file, start now to split it into single atf-files!</h2><p>"
492:
493: #make sure that id is a string and not an integer
494: basketId=str(basketId)
495:
496: #TODO: make this configurable, at the moment, rootFolder for cdli has to be cdliRoot
497: ctx2=ctx.cdliRoot
498:
499: #get temporary file for staging the downloaded and splitted files
500: dir=mkdtemp()
501:
502:
503: changed=[] # changed files
504: errors=[] # files with errors
505: lockerrors=[] # files with errors
506:
507: newPs=[] # new p filed
508: psNotInCatalog=[] # files not in the catalog
509:
510: #split the uploadedd atf file
511: basketNameFromFile, numberOfFiles=splitatf(upload,dir,ext=self)
512:
513: #find basketId if not set
514:
515: #get active abaket
516: if basketId == '0':
517: basketObj=ctx2.basketContainer.getActiveBasket()
518: if basketObj:
519: basketId=basketObj.getId()
520:
521: #if there is no active basket and no basketid given, id is empty, else get besketname and length
522: if basketId == '0':
523: basketNameFromId=""
524: basketLen=0
525: else:
526: basketNameFromId=getattr(ctx2.basketContainer,basketId).title
527: basketLen=getattr(ctx2.basketContainer,basketId).getLastVersion().numberOfItems()
528:
529: logging.info("got the file, upload thread")
530: self.result+="""<html><body><h2>I got the files</h2><
531: p>I am computing the differences to the exisiting files</p>"""
532:
533: #start to check the files
534: for fn in os.listdir(dir):
535:
536: self.result="<p>process:%s</p>"%fn+self.result
537:
538: # check if file is in the catalog
539: #TODO: checkCatalog is not implemented yet
540: if ctx2.cdli_main.checkCatalog(fn):
541: psNotInCatalog.append(fn)
542:
543: #check if p-file already at the server
544: founds=ctx2.CDLICatalog.search({'title':fn})
545:
546: #if not than add filename to the list of newfiles
547:
548: data=file(os.path.join(dir,fn)).read()
549: status,msg=checkFile(fn,data,dir)
550: #status=True
551:
552:
553: if not status: # error
554: errors.append((fn,msg))
555:
556: else:
557: if len(founds)==0:
558: newPs.append(fn)
559:
560: #if p file alread at the server
561: for found in founds:
562: #analyse the differences to the actual file
563: obj=found.getObject()
564:
565: if (not (str(obj.lockedBy))=='') and (not (str(obj.lockedBy)==str(self.username))):
566: lockerrors.append((fn,str(obj.lockedBy)))
567: else:
568:
569: diffs=obj.diff(data)
570: if diffs[0]>0:
571: changed.append((obj,diffs)) #hochladen
572:
573: #ready, set the returnValues
574: self.result+="<h3>Done</h3></body></html>"
575:
576: stObj.returnValue={}
577:
578: stObj.returnValue['errors']=errors
579:
580: stObj.returnValue['newPs']=newPs
581: stObj.returnValue['tmpdir']=dir
582: stObj.returnValue['basketLen']=basketLen
583: stObj.returnValue['numberOfFiles']=numberOfFiles
584: stObj.returnValue['basketNameFromId']=basketNameFromId
585: stObj.returnValue['basketNameFromFile']=basketNameFromFile
586: stObj.returnValue['basketId']=basketId
587: stObj.returnValue['dir']=dir
588: #stObj.returnValue['changed']=copy.copy(changed)
589: stObj.returnValue['changed']=[(x[0].getId(),x[1][0]) for x in changed]
590: #stObj.returnValue['lockerrors']=[x[0].getId() for x in lockerrors]
591: stObj.returnValue['lockerrors']=[x for x in lockerrors]
592: self.returnValue=True
593: #ctx2.cdli_main.setTemp('v_uploadATF_returnValue',True)
594:
595:
596: class CDLIBasketContainer(OrderedFolder):
597: """contains the baskets"""
598:
599:
600: security=ClassSecurityInfo()
601: meta_type="CDLIBasketContainer"
602:
603: def getPNumbersOfBasket(self,basketName):
604: """get all pnumbers of a basket as a list, returns an empty list if basket not found
605: @param basketName: name of the basket
606: """
607: ret=[]
608: basketId=self.getBasketIdfromName(basketName)
609: if not basketId:
610: return []
611:
612: ob=getattr(self,basketId).getContent()
613:
614: ret=[x[0].split(".")[0] for x in ob]
615:
616: return ret
617:
618: security.declareProtected('manage','getBasketAsOneFile')
619: def getBasketAsOneFile(self,basketName,current="no"):
620: """returns all files of the basket combined in one file
621: @param basketName: Name of the basket
622: @param current: (optional) if current is set to "yes" then the most current version of
623: all files are downloaded and not the versions of the files as stored in the basket
624: """
625: ret=""
626: basketId=self.getBasketIdfromName(basketName)
627: if not basketId:
628: return ""
629:
630: ob=getattr(self,basketId).getLastVersion()
631: for object in ob.getContent():
632: if current=="no": #version as they are in the basket
633: ret+=str(object[0].getData())+"\n"
634: elif current=="yes":
635: #search current object
636: logging.debug("current: %s"%object[1].getId().split(".")[0])
637: founds=self.CDLICatalog.search({'title':object[1].getId().split(".")[0]})
638: if len(founds)>0:
639: ret+=str(founds[0].getObject().getLastVersion().getData())+"\n"
640: return ret
641:
642: security.declareProtected('manage','upDateBaskets')
643: def upDateBaskets(self):
644: """update content in to objects"""
645:
646: founds=self.ZopeFind(self,obj_metatypes=['CDLIBasketVersion'],search_sub=1)
647:
648: for found in founds:
649: found[1].updateBasket()
650:
651: security.declareProtected('manage','deleteBaskets')
652: def deleteBaskets(self,ids=None):
653: """delete baskets, i.e. move them into trash folder"""
654:
655:
656: found=self.ZopeFind(self,obj_ids=['trash'])
657:
658: if len(found)<1:
659: manage_addFolder(self, 'trash')
660: trash=self._getOb('trash')
661: else:
662: trash=found[0][1]
663:
664: if type(ids) is not ListType:
665: ids=[ids]
666: cut=self.manage_cutObjects(ids)
667: trash.manage_pasteObjects(cut)
668:
669: security.declareProtected('manage','manageBaskets')
670: def manageBaskets(self,submit,ids=None,basket1="",basket2="",joinBasket="",subtractBasket="",REQUEST=None,RESPONSE=None):
671: """manage baskets, delete or copy"""
672: if submit=="delete":
673: self.deleteBaskets(ids)
674:
675: elif submit=="join":
676: flag,msg=self.joinBasket(joinBasket, ids)
677: logging.info("joining %s %s"%(flag,msg))
678:
679: elif submit=="subtract":
680: logging.info("BBBb %s %s"%(basket1,basket2))
681: flag,msg=self.subtractBasket(subtractBasket, basket1,basket2)
682: logging.info("subtract %s %s"%(flag,msg))
683:
684: if RESPONSE:
685: RESPONSE.redirect(self.absolute_url())
686:
687: security.declareProtected('View','getBasketIdfromName')
688: def getBasketIdfromName(self,basketname):
689: """get id from name"""
690:
691: for basket in self.ZopeFind(self,obj_metatypes=["CDLIBasket"]):
692: if basket[1].title==basketname:
693: return basket[0]
694: else:
695: None
696:
697: security.declareProtected('manage','uploadBasket_html')
698:
699: def uploadBasket_html(self,basketId='0'):
700: """upload an atf file, html form"""
701:
702:
703: basketId=str(basketId)
704: if not basketId=='0':
705: basketName=getattr(self.basketContainer,basketId).title
706: else:
707: basketName=""
708:
709: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadBasket_html.zpt')).__of__(self)
710: return pt(basketId=basketId,basketName=basketName)
711:
712:
713: security.declareProtected('manage','index_html')
714: def index_html(self):
715: """stanadard ansicht"""
716:
717:
718:
719: ext=self.ZopeFind(self,obj_ids=["index.html"])
720: if ext:
721: return ext[0][1]()
722:
723: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','BasketContainerMain')).__of__(self)
724: return pt()
725:
726: def getStorageFolderRoot(self):
727: """root des storage folders"""
728: return self.cdli_main
729:
730: def __init__(self,id,title):
731: """ init basket container"""
732: self.id=id
733: self.title=title
734:
735:
736: def getBasketsId(self):
737: """get all baskets als klartext"""
738:
739: ret=""
740: baskets=self.ZopeFind(self,obj_metatypes=['CDLIBasket'])
741: for basket in baskets:
742: com,user,time,values = basket[1].getContentIds()
743: ret+= "BASKET:"+com+"\t"+user+"\t"+time+"\n"
744: for x in values:
745: ret+= x[0]+"\t"+x[1]+"\n"
746: return ret
747:
748: def getBaskets(self,sortField='title'):
749: """get all baskets files"""
750:
751: def sortName(x,y):
752: return cmp(x[1].title.lower(),y[1].title.lower())
753:
754: def sortDate(x,y):
755: return cmp(y[1].getLastVersion().getTime(),x[1].getLastVersion().getTime())
756:
757:
758: def sortComment(x,y):
759:
760:
761:
762: try:
763: xc=getattr(x[1],'comment','ZZZZZZZZZZZZZ').lower()
764: except:
765: xc='ZZZZZZZZZZZZZ'.lower()
766: try:
767: yc=getattr(y[1],'comment','ZZZZZZZZZZZZZ').lower()
768: except:
769: yc='ZZZZZZZZZZZZZ'.lower()
770:
771:
772: if (xc=='') or (xc=='ZZZZZZZZZZZZZ'.lower()):
773:
774: try:
775: xc=x[1].getLastVersion().getComment().lower()
776: except:
777: xc='ZZZZZZZZZZZZZ'.lower()
778:
779: if (yc=='') or (yc=='ZZZZZZZZZZZZZ'.lower()):
780: try:
781: yc=y[1].getLastVersion().getComment().lower()
782: except:
783: yc='ZZZZZZZZZZZZZ'.lower()
784:
785:
786: return cmp(xc,yc)
787:
788: def sortAuthor(x,y):
789:
790: return cmp(x[1].getLastVersion().getUser().lower(),y[1].getLastVersion().getUser().lower())
791:
792: baskets=self.ZopeFind(self,obj_metatypes=['CDLIBasket'])
793:
794:
795: if sortField=='title':
796: baskets.sort(sortName)
797: elif sortField=='date':
798: baskets.sort(sortDate)
799: elif sortField=='author':
800: baskets.sort(sortAuthor)
801: elif sortField=='comment':
802: baskets.sort(sortComment)
803:
804: return baskets
805:
806:
807: def subtractBasket(self,newBasket,basket1,basket2):
808: """subtract basket2 from basket1
809: (i.e. newbasket will contain alle elements of basket1 which are not in basket2),
810: if basket2 contains files which are not in basket1, then theses files fill be ignored
811:
812: @param newbasket: name of the new basket
813: @param basket1: basket where basket2 will be subtracted from
814: @param basket2: see above
815:
816: """
817: logging.info("CCCCC %s %s"%(basket1,basket2))
818:
819: try:
820: newB=self.addBasket(newBasket)
821: except:
822: return False, "cannot create the new basket"
823:
824:
825:
826:
827:
828: bas2= getattr(self,basket2)
829: bas2content=bas2.getContent()
830: bas2ids=[x[0] for x in bas2content]
831:
832:
833:
834: bas1= getattr(self,basket1)
835: bas1content=bas1.getContent()
836:
837:
838: newBasketContent={}
839:
840: for id,version in bas1content:
841: if not (id in bas2ids):
842: newBasketContent[id]=version
843:
844: username=self.getActualUserName()
845:
846: logging.info("sbc %s"%newBasketContent)
847: newB.addObjectsWithVersion(newBasketContent,username=username,catalog=self.CDLICatalog)
848:
849: return True, ""
850:
851:
852: def joinBasket(self,newBasket,oldBaskets):
853: """join two baskets
854: @param newbasket: name of the new basket
855: @param oldbaskets: list of baskets to be joined
856: """
857: try:
858: newB=self.addBasket(newBasket)
859: except:
860: return False, "cannot create the new basket"
861:
862: newBasketContent={}
863: for ob in oldBaskets:
864: x= getattr(self,ob,None)
865: if x is None:
866: return False, "cannot find basket: %s"%ob
867:
868: ids=x.getContent() # hole den Inhalt
869:
870: for id,version in ids:
871: if newBasketContent.has_key(id): # p number gibt's schon
872: newBasketContent[id]=max(newBasketContent[id],version) # speichere die groessere Versionsnumber
873: else:
874: newBasketContent[id]=version
875: username=self.getActualUserName()
876:
877: logging.info("nbc %s"%newBasketContent)
878: newB.addObjectsWithVersion(newBasketContent,username=username,catalog=self.CDLICatalog)
879:
880: return True, ""
881:
882: def getNewId(self):
883: """createIds"""
884: last=getattr(self,'last',0)
885: last +=1
886: while len(self.ZopeFind(self,obj_ids=[str(last)]))>0:
887: last+=1
888:
889: self.last=last
890: return last
891:
892: def setActiveBasket(self,basketId,REQUEST=None):
893: """store active basketId in a cookie"""
894: self.REQUEST.RESPONSE.setCookie("CDLIActiveBasket",basketId,path="/")
895: try:
896: qs=cgi.parse_qs(REQUEST['QUERY_STRING'])
897: del(qs['basketId'])
898: except:
899: qs={}
900: if REQUEST:
901: REQUEST.RESPONSE.redirect(REQUEST['URL1']+'?'+urllib.urlencode(qs))
902:
903: def getActiveBasket(self):
904: """get active basket from cookie"""
905:
906: id= self.REQUEST.cookies.get('CDLIActiveBasket',None)
907: if id:
908: obj=getattr(self,str(id),None)
909: else:
910: obj=None
911: return obj
912:
913: def getActualUserName(self):
914: """get name of the actualuser"""
915: return str(self.REQUEST['AUTHENTICATED_USER'])
916:
917: security.declareProtected('manage','addBasket')
918: def addBasket(self,newBasketName):
919: """add a new basket"""
920:
921: ob=manage_addCDLIBasket(self,newBasketName)
922: return ob
923:
924: def storeInBasket(self,submit,ids=None,newBasketName=None,fromFileList=None,RESPONSE=None,REQUEST=None):
925: """store it"""
926: if not ids:
927: ids=self.REQUEST.SESSION['fileIds']
928:
929: if (type(ids) is not ListType) and (not isinstance(ids,Set)):
930: ids=[ids]
931:
932: if isinstance(ids,Set):
933: ids=list(ids)
934:
935: if (submit.lower()=="store in new basket") or (submit.lower()=="new basket"):
936: basketRet=self.addBasket(newBasketName)
937: self.setActiveBasket(basketRet.getId())
938: basket=getattr(self,basketRet.getId())
939: elif (submit.lower()=="store in active basket") or (submit.lower()=="active basket"):
940: basket=self.getActiveBasket()
941:
942: added=basket.addObjects(ids)
943: back=self.REQUEST['HTTP_REFERER'].split("?")[0]+"?basketName="+basket.title+"&numberOfObjects="+str(added)
944:
945:
946: if fromFileList:
947:
948: return self.cdli_main.findObjectsFromList(list=ids,basketName=basket.title,numberOfObjects=added)
949:
950: if RESPONSE:
951:
952: RESPONSE.redirect(back)
953:
954: return True
955:
956: def manage_addCDLIBasketContainerForm(self):
957: """add the CDLIBasketContainer form"""
958: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','addCDLIBasketContainer.zpt')).__of__(self)
959: return pt()
960:
961: def manage_addCDLIBasketContainer(self,id,title,RESPONSE=None):
962: """add the basket"""
963: ob=CDLIBasketContainer(id,title)
964:
965: self._setObject(id, ob)
966:
967: if RESPONSE is not None:
968: RESPONSE.redirect('manage_main')
969:
970: class CDLIBasket(Folder,CatalogAware):
971: """basket"""
972:
973: meta_type="CDLIBasket"
974: default_catalog="CDLIBasketCatalog"
975:
976: def searchInBasket(self,indexName,searchStr,regExp=False):
977: """searchInBasket"""
978:
979: lst=self.searchInLineIndexDocs(indexName,searchStr,uniq=True,regExp=regExp) #TODO: fix this
980: ret={}
981:
982: lv=self.getLastVersion()
983:
984:
985: for obj in lv.content.getContent():
986: id=obj[1].getId().split(".")[0]
987: if id in lst:
988:
989: ret[id]=self.showWordInFile(id,searchStr,lineList=self.getLinesFromIndex(indexName,searchStr,id,regExp=regExp),regExp=regExp,indexName=indexName)
990:
991:
992: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','searchResultsInBasket')).__of__(self)
993: return pt(result=ret,indexName=indexName,regExp=regExp,word=searchStr)
994:
995:
996:
997:
998: def searchInBasket_v1(self,searchStr):
999: """search occurences of searchStr in files im basket"""
1000: ret=[]
1001: lv=self.getLastVersion()
1002: logging.info("searching")
1003: for obj in lv.content.getContent():
1004: txt=obj[0].getData()
1005: for x in txt.split("\n"):
1006: logging.info("search %s"%x)
1007: if re.match(searchStr,x):
1008: ret.append(x)
1009:
1010: return "\n".join(ret)
1011:
1012:
1013: def getFile(self,obj):
1014: return obj[1]
1015:
1016: def getFileLastVersion(self,obj):
1017: return obj[0]
1018:
1019: def getFileNamesInLastVersion(self):
1020: """get content of the last version as list"""
1021:
1022: return [x[1].getId() for x in self.getLastVersion().getContent()]
1023:
1024:
1025: def isActual(self,obj):
1026: """teste ob im basket die aktuelle version ist"""
1027: actualNo=obj[1].getLastVersion().getVersionNumber()
1028: storedNo=obj[0].getVersionNumber()
1029:
1030: founds=self.CDLICatalog.search({'title':obj[0].getId()})
1031: if len(founds)>0:
1032: actualNo=founds[0].getObject().getLastVersion().getVersionNumber()
1033:
1034: if len(founds)>0 and founds[0].getObject().aq_parent.getId()==".trash":
1035: return False, -1
1036:
1037: if actualNo==storedNo:
1038: return True , 0
1039: else:
1040: return False, actualNo
1041:
1042: def history(self):
1043: """history"""
1044:
1045: ext=self.ZopeFind(self.aq_parent,obj_ids=["history_template.html"])
1046: if ext:
1047: return getattr(self,ext[0][1].getId())()
1048:
1049: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','BasketHistory')).__of__(self)
1050: return pt()
1051:
1052: def getStorageFolderRoot(self):
1053: """root des storage folders"""
1054: return self.aq_parent.cdli_main
1055:
1056: def __init__(self,id,title,shortDescription="",comment=""):
1057: """init a CDLIBasket"""
1058:
1059: self.id=id
1060: self.title=title
1061: self.shortDescription=shortDescription
1062: self.comment=comment
1063:
1064: def getActualUserName(self):
1065: """get name of the actualuser"""
1066:
1067: return str(self.REQUEST['AUTHENTICATED_USER'])
1068:
1069:
1070: def getLastVersion(self):
1071: """hole letzte version"""
1072:
1073: ids=[]
1074: idsTmp= self.objectIds()
1075: for x in idsTmp:
1076: try:
1077: ids.append(int(x))
1078: except:
1079: pass
1080: ids.sort()
1081:
1082: if len(ids)==0:
1083: return None
1084: else:
1085: ob=getattr(self,str(ids[-1]))
1086:
1087:
1088: return ob
1089:
1090: def getVersions(self):
1091: """get versions"""
1092: versions=self.ZopeFind(self,obj_metatypes=["CDLIBasketVersion"])
1093: return versions
1094:
1095:
1096: def updateObjects(self,ids,RESPONSE=None,REQUEST=None):
1097: """update ids, ids not in the basket the add"""
1098: if type(ids) is not ListType:
1099: ids=[ids]
1100:
1101: lastVersion=self.getLastVersion()
1102: oldContent=lastVersion.content.getContent()
1103: newContent=[]
1104:
1105: #first copy the old
1106: for obj in oldContent:
1107: if obj[1].getId() not in ids:
1108: newContent.append(obj)
1109: #now add the new
1110:
1111: for id in ids:
1112: founds=self.CDLICatalog.search({'title':id})
1113:
1114: for found in founds:
1115: if found.getObject() not in oldContent:
1116: #TODO: was passiert wenn, man eine Object dazufŸgt, das schon da ist aber eine neuere version
1117: newContent.append((found.getObject().getLastVersion(),found.getObject()))
1118:
1119:
1120: content=newContent
1121: user=self.getActualUserName()
1122:
1123: ob=manage_addCDLIBasketVersion(self,user,comment="",basketContent=newContent)
1124:
1125: obj=self._getOb(ob.getId())
1126: if RESPONSE:
1127:
1128: RESPONSE.redirect(obj.absolute_url())
1129:
1130: return obj
1131:
1132: def addObjectsWithVersion(self,ids,deleteOld=None,username=None,catalog=None):
1133: """generate a new version of the basket with objects added,
1134: hier wird jedoch nicht die letzte Version jedes Files hinzugefuegt, s
1135: ondern ids is ein Tupel mit der Id (d.h. der p-number) und der Versionsnummer.
1136: """
1137: logging.info("add to basket (%s)"%(self.getId()))
1138: lastVersion=self.getLastVersion()
1139:
1140: if not catalog:
1141: catalog=self.CDLICatalog
1142:
1143: if lastVersion is None:
1144: oldContent=[]
1145: else:
1146: oldContent=lastVersion.content.getContent()
1147:
1148: if deleteOld:
1149: oldContent=[]
1150:
1151: newContent=[]
1152: added=0
1153:
1154: for id,version in ids.iteritems():
1155: logging.info("adding %s %s"%(id,version))
1156: id=id.split(".")[0] # title nur die pnumber ohne atf
1157:
1158: try:
1159: founds=catalog.search({'title':id})
1160: except:
1161: founds=[]
1162: logging.info(" found %s "%(founds))
1163: for found in founds:
1164: if found.getObject() not in oldContent:
1165:
1166: #TODO: was passiert wenn, man eine Object dazufŸgt, das schon da ist aber eine neuere version
1167: newContent.append((found.getObject().getVersions()[version-1][1],found.getObject()))
1168: added+=1
1169:
1170: content=oldContent+newContent
1171: if not username:
1172: logging.error("XXXXXXXXXXX %s"%repr(self))
1173: user=self.getActualUserName()
1174: else:
1175: user = username
1176:
1177: ob=manage_addCDLIBasketVersion(self,user,comment="",basketContent=content)
1178: logging.info("add to basket (%s) done"%(self.getId()))
1179: return added
1180:
1181:
1182: def addObjects(self,ids,deleteOld=None,username=None):
1183: """generate a new version of the basket with objects added"""
1184:
1185: def swap(x):
1186: return (x[1],x[0])
1187:
1188: logging.info("add to basket (%s)"%(self.getId()))
1189: lastVersion=self.getLastVersion()
1190:
1191: if lastVersion is None:
1192: oldContent=[]
1193: else:
1194: oldContent=lastVersion.content.getContent()
1195:
1196: if deleteOld:
1197: oldContent=[]
1198:
1199: added=0
1200: # for id in ids:
1201: # logging.debug("adding:"+id)
1202: # try:
1203: # founds=self.CDLICatalog.search({'title':id})
1204: # except:
1205: # founds=[]
1206: #
1207: # for found in founds:
1208: # if found.getObject() not in oldContent:
1209: # #TODO: was passiert wenn, man eine Object dazufŸgt, das schon da ist aber eine neuere version
1210: # newContent.append((found.getObject().getLastVersion(),found.getObject()))
1211: # added+=1
1212:
1213: hash = md5.new(repr(self.makelist(ids))).digest() # erzeuge hash als identification
1214: #logging.debug("JJJJJJJ:"+repr(self.makelist(ids)))
1215: logging.debug("JJJJJJJ:"+repr(hash))
1216:
1217: if hasattr(self.cdliRoot,'_v_tmpStore') and self.cdliRoot._v_tmpStore.has_key(hash):
1218: logging.debug("from store!")
1219: newContent=Set(map(swap,self.cdliRoot._v_tmpStore[hash]))
1220:
1221: else:
1222: logging.debug("not from store!")
1223: newContent=Set([(self.getFileObjectLastVersion(x),self.getFileObject(x)) for x in ids])
1224:
1225:
1226: content=Set(oldContent).union(newContent)
1227: added = len(content)-len(oldContent)
1228: if not username:
1229: user=self.getActualUserName()
1230: else:
1231: user = username
1232:
1233: #logging.debug("content:"+repr(list(content)))
1234: ob=manage_addCDLIBasketVersion(self,user,comment="",basketContent=list(content))
1235: logging.info("add to basket (%s) done"%(self.getId()))
1236: return added
1237:
1238:
1239:
1240: def getContent(self):
1241: """print content"""
1242: ret=[]
1243:
1244: lv=self.getLastVersion()
1245: for obj in lv.content.getContent():
1246: logging.info("XXXXXXXXXX %s"%repr(obj))
1247: ret.append((obj[1].getId(),obj[0].versionNumber))
1248:
1249: return ret
1250:
1251: def getContentIds(self):
1252: """print basket content"""
1253: ret=[]
1254: lv=self.getLastVersion()
1255: for obj in lv.content.getContent():
1256: ret.append((obj[0].getId(),obj[1].getId()))
1257:
1258:
1259: return lv.getComment(),lv.getUser(),lv.getTime(),ret
1260:
1261: def changeBasket(self,ids,submit,RESPONSE=None,REQUEST=None):
1262: """change a basket"""
1263: if submit=="update":
1264: return self.updateObjects(ids,RESPONSE=RESPONSE,REQUEST=REQUEST)
1265: elif submit=="delete":
1266: return self.deleteObjects(ids,RESPONSE=RESPONSE,REQUEST=REQUEST)
1267:
1268: def deleteObjects(self,ids,RESPONSE=None,REQUEST=None):
1269: """delete objects"""
1270:
1271: if type(ids) is not ListType:
1272: ids=[ids]
1273:
1274: lastVersion=self.getLastVersion()
1275: oldContent=lastVersion.content.getContent()
1276: newContent=[]
1277: for obj in oldContent:
1278: if obj[1].getId() not in ids:
1279: newContent.append(obj)
1280:
1281:
1282: user=self.getActualUserName()
1283:
1284: ob=manage_addCDLIBasketVersion(self,user,comment="",basketContent=newContent)
1285:
1286: if RESPONSE:
1287: obj=self._getOb(ob.getId())
1288: RESPONSE.redirect(obj.absolute_url())
1289:
1290: def manage_addCDLIBasketForm(self):
1291: """add the CDLIBasketContainer form"""
1292: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','addCDLIBasket.zpt')).__of__(self)
1293: return pt()
1294:
1295: def manage_addCDLIBasket(self,title,shortDescription="",comment="",RESPONSE=None):
1296: """add the basket"""
1297:
1298: id=str(self.getNewId())
1299:
1300: ob=CDLIBasket(id,title,shortDescription,comment)
1301:
1302: self._setObject(id, ob)
1303:
1304: if RESPONSE is not None:
1305: RESPONSE.redirect('manage_main')
1306: else:
1307: return ob
1308:
1309: class CDLIBasketVersion(Implicit,Persistent,Folder):
1310: """version of a basket"""
1311:
1312: meta_type="CDLIBasketVersion"
1313: security=ClassSecurityInfo()
1314:
1315: def updateBasket(self):
1316: """update"""
1317: try:
1318: self._setObject('content',BasketContent(self.basketContent))
1319: except:
1320: try:
1321: if len(self.basketContent)>0:
1322: self.content.setContent(self.basketContent)
1323: except:
1324: print "error",self.getId(),self.aq_parent.getId()
1325: self.basketContent=[]
1326:
1327:
1328: def containsNonActualFiles(self):
1329: """returns True if basket contains one or more non current files"""
1330:
1331: objs=self.getContent()
1332: for obj in objs:
1333: if not self.isActual(obj)[0]:
1334: return True
1335: return False
1336:
1337: def downloadListOfPnumbers(self):
1338: """download pnumbers of the basket as list"""
1339:
1340: basket_name=self.aq_parent.title
1341:
1342: ids=self.getContent() # get the list of objects
1343: logging.error(ids)
1344: ret="\n".join([x[1].getId().split(".")[0] for x in ids])
1345:
1346: self.REQUEST.RESPONSE.setHeader("Content-Disposition","""attachement; filename="%s.txt" """%basket_name)
1347: self.REQUEST.RESPONSE.setHeader("Content-Type","application/octet-stream")
1348: length=len(ret)
1349: self.REQUEST.RESPONSE.setHeader("Content-Length",length)
1350: self.REQUEST.RESPONSE.write(ret)
1351:
1352: security.declareProtected('manage','downloadObjectsAsOneFile')
1353: def downloadObjectsAsOneFile(self,lock=None,procedure=None,REQUEST=None,check="yes",current="no"):
1354: """download all selected files in one file"""
1355:
1356: if self.temp_folder.downloadCounterBaskets > 10000:
1357: return """I am sorry, currently the server has to many requests for downloads, please come back later!"""
1358:
1359:
1360: if (check=="yes") and self.containsNonActualFiles():
1361: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','downloadObjectAsOneFile_check.zpt')).__of__(self)
1362:
1363: return pt(lock=lock)
1364:
1365: else:
1366:
1367: return self.downloadObjectsAsOneFileFinally(lock=lock,procedure=procedure,REQUEST=REQUEST,current="no")
1368:
1369: def downloadObjectsAsOneFileFinally(self,lock=None,procedure=None,REQUEST=None,current="no"):
1370: """print do the download"""
1371:
1372: ret=""
1373: lockedObjects={}
1374:
1375: self.temp_folder.downloadCounterBaskets+=1
1376: self._p_changed=1
1377: transaction.get().commit()
1378:
1379: if lock:
1380:
1381: if str(self.REQUEST['AUTHENTICATED_USER'])=='Anonymous User':
1382: self.temp_folder.downloadCounterBaskets-=1
1383: self._p_changed=1
1384: transaction.get().commit()
1385: self.temp_folder.downloadCounterBaskets-=1
1386: self._p_changed=1
1387: transaction.get().commit()
1388: return "please login first"
1389:
1390: #check if a locked object exist in the basket.
1391: lockedObjects={}
1392: for object in self.content.getContent():
1393:
1394: if (not str(object[1].lockedBy)=="") and (not (str(object[1].lockedBy)==str(self.REQUEST['AUTHENTICATED_USER']))):
1395: lockedObjects[object[1].title]=repr(object[1].lockedBy)
1396:
1397:
1398: keys=lockedObjects.keys()
1399:
1400:
1401: if len(keys)>0 and (not procedure):
1402: self.REQUEST.SESSION['lockedObjects']=lockedObjects
1403: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','lockedObjects.zpt')).__of__(self)
1404:
1405: self.temp_folder.downloadCounterBaskets-=1
1406: self._p_changed=1
1407: transaction.get().commit()
1408:
1409: return pt()
1410:
1411: elif not procedure: #keine fails gesperrt dann alle donwloaden
1412: procedure="downloadAll"
1413:
1414:
1415:
1416:
1417: for object in self.content.getContent():
1418: logging.error("ret:"+repr(object[0]))
1419: logging.error(" -"+repr(procedure))
1420: logging.error(" -"+repr(object[1].lockedBy))
1421:
1422: if (procedure=="downloadAll") or (object[1].lockedBy=='') or (object[1].lockedBy==self.REQUEST['AUTHENTICATED_USER']):
1423: logging.error("ret1")
1424: if current=="no": #version as they are in the basket
1425: logging.error("ret2")
1426: ret+=str(object[0].getData())+"\n"
1427: elif current=="yes":
1428: logging.error("ret3")
1429: #search current object
1430: founds=self.CDLICatalog.search({'title':object[1].getId().split(".")[0]})
1431: if len(founds)>0:
1432: ret+=str(founds[0].getObject().getLastVersion().getData())+"\n"
1433:
1434: if lock and object[1].lockedBy=='':
1435: object[1].lockedBy=self.REQUEST['AUTHENTICATED_USER']
1436: basket_name=self.aq_parent.title+"_V"+self.getId()
1437:
1438: #write basketname to header of atf file
1439: ret="#basket: %s\n"%basket_name+ret
1440:
1441: self.temp_folder.downloadCounterBaskets-=1
1442: self._p_changed=1
1443: transaction.get().commit()
1444:
1445: self.REQUEST.RESPONSE.setHeader("Content-Disposition","""attachement; filename="%s.atf" """%basket_name)
1446: self.REQUEST.RESPONSE.setHeader("Content-Type","application/octet-stream")
1447: length=len(ret)
1448: self.REQUEST.RESPONSE.setHeader("Content-Length",length)
1449: self.REQUEST.RESPONSE.write(ret)
1450: return True
1451:
1452: def numberOfItems(self):
1453: """return anzahl der elemente im basket"""
1454: return self.content.numberOfItems()
1455:
1456: def getTime(self):
1457: """getTime"""
1458: #return self.bobobase_modification_time().ISO()
1459:
1460: if hasattr(self,'time'):
1461: return time.strftime("%Y-%m-%d %H:%M:%S",self.time)
1462: elif hasattr(self,'timefixed'):
1463: return self.timefixed
1464: else:
1465: setattr(self,'timefixed',self.bobobase_modification_time().ISO())
1466: return self.bobobase_modification_time().ISO()
1467:
1468: def getContent(self):
1469: """get Basket Content"""
1470: return self.content.getContent()
1471:
1472:
1473: def __init__(self,id,user,comment="",basketContent=[]):
1474: """ init a basket version"""
1475: self.id=id
1476: self.comment=comment
1477: self._setObject('content',BasketContent(basketContent))
1478: #self.basketContent=basketContent[0:]a
1479: self.user=user
1480: self.time=time.localtime()
1481:
1482: def getUser(self):
1483: """get user"""
1484: return self.user
1485:
1486: def getComment(self):
1487: """get Comment"""
1488: return self.comment
1489:
1490: security.declareProtected('manage','index_html')
1491: def index_html(self):
1492: """view the basket"""
1493:
1494: if self.REQUEST.get('change',False):
1495: ob=self.aq_parent.updateObjects(self.REQUEST['change'])
1496:
1497: self.REQUEST.RESPONSE.redirect(ob.absolute_url())#go to new basket, because changing generates a new basket
1498:
1499: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','BasketVersionMain.zpt')).__of__(self)
1500: return pt()
1501:
1502: def getObjUrl(self,result):
1503: """getUrl of the version of the object"""
1504: objId=result[1].getTitle()
1505: founds=self.CDLICatalog.search({'title':objId})
1506: if len(founds)>0:
1507: return founds[0].getObject().getLastVersion().absolute_url()
1508:
1509: else: #assume version number
1510: splitted=objId.split("_")
1511: founds=self.CDLICatalog.search({'title':splitted[1]})
1512: return founds[0].getObject().getLastVersion().absolute_url()+'/'+objId
1513:
1514: def manage_addCDLIBasketVersion(self,user,comment="",basketContent=[],RESPONSE=None):
1515: """add a version"""
1516:
1517: #check for already existing versions
1518:
1519: lastVersion=self.getLastVersion()
1520: if lastVersion is None:
1521: newId=str(1)
1522: else:
1523: newId=str(int(lastVersion.getId())+1)
1524:
1525: ob=CDLIBasketVersion(newId,user,comment,basketContent)
1526:
1527: self._setObject(newId, ob)
1528:
1529: if RESPONSE is not None:
1530: RESPONSE.redirect('manage_main')
1531: else:
1532: return ob
1533:
1534: class CDLIFileObject(CatalogAware,extVersionedFileObject):
1535: """CDLI file object"""
1536:
1537: meta_type="CDLI File Object"
1538: default_catalog='CDLIObjectsCatalog'
1539:
1540: security=ClassSecurityInfo()
1541:
1542: security.declareProtected('manage','index_html')
1543:
1544: security.declarePublic('view')
1545: view = PageTemplateFile('zpt/viewCDLIFile.zpt', globals())
1546:
1547: security.declarePublic('editATF')
1548: editATF = PageTemplateFile('zpt/editATFFile.zpt', globals())
1549:
1550: def PrincipiaSearchSource(self):
1551: """Return cataloguable key for ourselves."""
1552: return str(self)
1553:
1554: def makeThisVersionCurrent_html(self):
1555: """form for making this version current"""
1556:
1557: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','makeThisVersionCurrent.zpt')).__of__(self)
1558: return pt()
1559:
1560: security.declarePublic('makeThisVersionCurrent')
1561: def makeThisVersionCurrent(self,comment,author,RESPONSE=None):
1562: """copy this version to current"""
1563: parent=self.aq_parent
1564: parent.manage_addVersionedFileObject(id=None,vC=comment,author=author,file=self.getData(),RESPONSE=RESPONSE)
1565: #newversion=parent.manage_addCDLIFileObject('',comment,author)
1566: #newversion.manage_upload(self.getData())
1567:
1568: #if RESPONSE is not None:
1569: # RESPONSE.redirect(self.aq_parent.absolute_url()+'/history')
1570:
1571: return True
1572:
1573: def getFormattedData(self):
1574: """fromat text"""
1575: data=self.getData()
1576: # return re.sub("\s\#lem"," #lem",data) #remove return vor #lem
1577: return re.sub("#lem"," #lem",data) #remove return vor #lem
1578:
1579:
1580: security.declarePublic('getPNumber')
1581: def getPNumber(self):
1582: """get the pnumber"""
1583: try:
1584: txt=re.match("&[Pp](\d*)\s*=([^\r\n]*)",self.getData()[0:])
1585: except:
1586: txt=self.getData()[0:]
1587:
1588: return "ERROR"
1589: try:
1590: return "P"+txt.group(1)
1591: except:
1592: return "ERROR"
1593:
1594: security.declarePublic('getDesignation')
1595: def getDesignation(self):
1596: """get the designation out of the file"""
1597: try:
1598: txt=re.match("&[Pp](\d*)\s*=([^\r\n]*)",self.getData()[0:])
1599: except:
1600: txt=self.getData()[0:]
1601:
1602: return "ERROR"
1603: try:
1604: return txt.group(2)
1605: except:
1606: return "ERROR"
1607:
1608:
1609: manage_addCDLIFileObjectForm=DTMLFile('dtml/fileAdd', globals(),Kind='CDLIFileObject',kind='CDLIFileObject', version='1')
1610:
1611: def manage_addCDLIFileObject(self,id,vC='',author='', file='',title='',versionNumber=0,
1612: precondition='', content_type='',
1613: from_tmp=False,REQUEST=None):
1614: """Add a new File object.
1615: Creates a new File object 'id' with the contents of 'file'"""
1616:
1617: id=str(id)
1618: title=str(title)
1619: content_type=str(content_type)
1620: precondition=str(precondition)
1621:
1622: id, title = cookId(id, title, file)
1623:
1624: self=self.this()
1625:
1626: # First, we create the file without data:
1627: self._setObject(id, CDLIFileObject(id,title,versionNumber=versionNumber,versionComment=vC,time=time.localtime(),author=author))
1628: fob = self._getOb(id)
1629:
1630: # Now we "upload" the data. By doing this in two steps, we
1631: # can use a database trick to make the upload more efficient.
1632:
1633: if file and not from_tmp:
1634: fob.manage_upload(file)
1635: elif file and from_tmp:
1636: fob.manage_file_upload(file) # manage_upload_from_tmp doesn't exist in ExtFile2
1637: # fob.manage_upload_from_tmp(file) # manage_upload_from_tmp doesn't exist in ExtFile2
1638: if content_type:
1639: fob.content_type=content_type
1640:
1641: #logging.debug("manage_add: lastversion=%s"%self.getData())
1642: logging.debug("reindex1: %s in %s"%(repr(self),repr(self.default_catalog)))
1643: self.reindex_object()
1644: #logging.debug("manage_add: fob_data=%s"%fob.getData())
1645: logging.debug("reindex2: %s in %s"%(repr(fob), repr(fob.default_catalog)))
1646: fob.index_object()
1647:
1648: if REQUEST is not None:
1649: REQUEST['RESPONSE'].redirect(self.absolute_url()+'/manage_main')
1650:
1651:
1652: class CDLIFile(extVersionedFile,CatalogAware):
1653: """CDLI file"""
1654:
1655: security=ClassSecurityInfo()
1656: meta_type="CDLI file"
1657: content_meta_type = ["CDLI File Object"]
1658:
1659: default_catalog='CDLICatalog'
1660:
1661: security.declareProtected('manage','index_html')
1662:
1663: def getLastVersionData(self):
1664: """get last version data"""
1665: return self.getData()
1666:
1667: def getLastVersionFormattedData(self):
1668: """get last version data"""
1669: return self.getContentObject().getFormattedData()
1670:
1671: def getTextId(self):
1672: """returns P-number of text"""
1673: # assuming that its the beginning of the title
1674: return self.title[:7]
1675:
1676: #security.declarePublic('history')
1677: def history(self):
1678: """history"""
1679:
1680: ext=self.ZopeFind(self.aq_parent,obj_ids=["history_template.html"])
1681: if ext:
1682: return getattr(self,ext[0][1].getId())()
1683:
1684: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','versionHistory')).__of__(self)
1685: return pt()
1686:
1687:
1688: def getBasketFromId(self,basketid, context=None):
1689: """get basket from id"""
1690:
1691: if not context:
1692: context=self
1693:
1694: for basket in self.ZopeFind(context,obj_metatypes=["CDLIBasket"]):
1695: if basket[0]==basketid:
1696: return basket[1]
1697: else:
1698: None
1699:
1700:
1701: def isContainedInBaskets(self,context=None):
1702: """check is this file is part of any basket
1703: @param context: (optional) necessessary if CDLIBasketCatalog is not an (inherited) attribute of self, context.CDLIBasketCatalog
1704: has to exist.
1705: """
1706:
1707: if not context:
1708: context=self
1709:
1710: ret=[]
1711: for x in context.CDLIBasketCatalog.search({'getFileNamesInLastVersion':self.getId()}):
1712: #if the basket x is deleted it seemes to be that x is sometimes still in the Catalog, why?
1713: try:
1714: ret.append(x.getObject())
1715: except:
1716: pass
1717: return ret
1718: #return [x.getObject() for x in context.CDLIBasketCatalog.search({'getFileNamesInLastVersion':self.getId()})]
1719:
1720:
1721: def _newContentObject(self, id, title='', versionNumber=0, versionComment=None, time=None, author=None):
1722: """factory for content objects. to be overridden in derived classes."""
1723: logging.debug("_newContentObject(CDLI)")
1724: return CDLIFileObject(id,title,versionNumber=versionNumber,versionComment=versionComment,time=time,author=author)
1725:
1726:
1727: def addCDLIFileObjectForm(self):
1728: """add a new version"""
1729:
1730: if str(self.REQUEST['AUTHENTICATED_USER']) in ["Anonymous User"]:
1731: return "please login first"
1732: if (self.lockedBy==self.REQUEST['AUTHENTICATED_USER']) or (self.lockedBy==''):
1733: out=DTMLFile('dtml/fileAdd', globals(),Kind='CDLIFileObject',kind='CDLIFileObject',version=self.getVersion()).__of__(self)
1734: return out()
1735: else:
1736: return "Sorry file is locked by somebody else"
1737:
1738: def manage_addCDLIFileObject(self,id,vC,author,
1739: file='',title='',
1740: precondition='',
1741: content_type='',
1742: changeName='no',newName='',
1743: come_from=None,
1744: from_tmp=False,RESPONSE=None):
1745: """add"""
1746:
1747: try: #TODO: der ganze vC unsinn muss ueberarbeitet werden
1748: vC=self.REQUEST['vC']
1749: except:
1750: pass
1751:
1752: ob = self.addContentObject(id, vC, author, file, title, changeName=changeName, newName=newName, from_tmp=from_tmp,
1753: precondition=precondition, content_type=content_type)
1754:
1755: try:
1756: #FIXME: wozu ist das gut?
1757: self.REQUEST.SESSION['objID_parent']=self.getId()
1758: except:
1759: pass
1760:
1761: if RESPONSE:
1762: if ob.getSize()==0:
1763: self.REQUEST.SESSION['objID']=ob.getId()
1764: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','errorUploadFile')).__of__(self)
1765: return pt()
1766: else:
1767: if come_from and (come_from!=""):
1768: RESPONSE.redirect(come_from+"?change="+self.getId())
1769: else:
1770: RESPONSE.redirect(self.REQUEST['URL2']+'?uploaded=%s'%self.title)
1771: else:
1772: return ob
1773:
1774:
1775: def manage_addCDLIFileForm(self):
1776: """interface for adding the OSAS_root"""
1777: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','addCDLIFile.zpt')).__of__(self)
1778: return pt()
1779:
1780: def manage_addCDLIFile(self,id,title,lockedBy, author=None, RESPONSE=None):
1781: """add the OSAS_root"""
1782: newObj=CDLIFile(id,title,lockedBy,author)
1783:
1784: tryToggle=True
1785: tryCount=0
1786:
1787: self._setObject(id,newObj)
1788: getattr(self,id).reindex_object()
1789:
1790: if RESPONSE is not None:
1791: RESPONSE.redirect('manage_main')
1792:
1793:
1794: def checkUTF8(data):
1795: """check utf 8"""
1796: try:
1797: data.encode('utf-8')
1798: return True
1799: except:
1800: return False
1801:
1802:
1803: def checkFile(filename,data,folder):
1804: """check the files"""
1805: # first check the file name
1806: fn=filename.split(".") # no extension
1807:
1808: if not fn[0][0]=="P":
1809: return False,"P missing in the filename"
1810: elif len(fn[0])!=7:
1811: return False,"P number has not the right length 6"
1812: elif not checkUTF8(data):
1813: return False,"not utf-8"
1814: else:
1815: return True,""
1816:
1817:
1818: def splitatf(fh,dir=None,ext=None):
1819: """split it"""
1820: ret=None
1821: nf=None
1822: i=0
1823:
1824: #ROC: why split \n first and then \r???
1825: if (type(fh) is StringType) or (type(fh) is UnicodeType):
1826: iter=fh.split("\n")
1827: else:
1828: iter=fh.readlines()
1829:
1830: for lineTmp in iter:
1831: lineTmp=lineTmp.replace(codecs.BOM_UTF8,'') # make sure that all BOM are removed..
1832: for line in lineTmp.split("\r"):
1833: #logging.log("Deal with: %s"%line)
1834: if ext:
1835: i+=1
1836: if (i%100)==0:
1837: ext.result+="."
1838: if i==10000:
1839: i=0
1840: ext.result+="<br>"
1841: #check if basket name is in the first line
1842: if line.find("#atf basket")>=0: #old convention
1843: ret=line.replace('#atf basket ','')
1844: ret=ret.split('_')[0]
1845: elif line.find("#basket:")>=0: #new convention
1846: ret=line.replace('#basket: ','')
1847: ret=ret.split('_')[0]
1848:
1849: else:
1850: if (len(line.lstrip())>0) and (line.lstrip()[0]=="&"): #newfile
1851: if nf:
1852: nf.close() #close last file
1853:
1854:
1855: filename=line[1:].split("=")[0].rstrip()+".atf"
1856: if dir:
1857: filename=os.path.join(dir,filename)
1858: nf=file(filename,"w")
1859: logging.info("open %s"%filename)
1860: if nf:
1861: nf.write(line.replace("\n","")+"\n")
1862:
1863: try:
1864: nf.close()
1865: except:
1866: pass
1867:
1868: if not((type(fh) is StringType) or (type(fh) is UnicodeType)):
1869: fh.close()
1870: return ret,len(os.listdir(dir))
1871:
1872:
1873: class CDLIFileFolder(extVersionedFileFolder):
1874: """CDLI File Folder"""
1875:
1876: security=ClassSecurityInfo()
1877: meta_type="CDLI Folder"
1878: file_meta_type=['CDLI file']
1879: folder_meta_type=['CDLI Folder']
1880:
1881: file_catalog='CDLICatalog'
1882:
1883: #downloadCounter=0 # counts how many download for all files currently run, be mehr als 5 wird verweigert.
1884: tmpStore2={}
1885:
1886: def _newVersionedFile(self, id, title='', lockedBy=None, author=None):
1887: """factory for versioned files. to be overridden in derived classes."""
1888: logging.debug("_newVersionedFile(CDLI)")
1889: return CDLIFile(id, title, lockedBy=lockedBy, author=author)
1890:
1891: def setTemp(self,name,value):
1892: """set tmp"""
1893:
1894: setattr(self,name,value)
1895:
1896: deleteFileForm = PageTemplateFile("zpt/doDeleteFile", globals())
1897:
1898: def delete(self,ids,REQUEST=None):
1899: """delete these files"""
1900: if type(ids) is not ListType:
1901: ids=[ids]
1902:
1903: self.manage_delObjects(ids)
1904:
1905: if REQUEST is not None:
1906: return self.index_html()
1907:
1908:
1909: def getVersionNumbersFromIds(self,ids):
1910: """get the numbers of the current versions of documents described by their ids"""
1911:
1912: ret=[]
1913: searchStr=" OR ".join(ids)
1914:
1915: founds=self.CDLICatalog.search({'title':searchStr})
1916:
1917: for found in founds:
1918: lastVersion=found.getObject().getContentObject()
1919: ret.append((found.getId,lastVersion))
1920:
1921: return ret
1922:
1923: def getFile(self,fn):
1924: """get the content of the file fn"""
1925: logging.debug("getFile: %s"%repr(fn))
1926: if not self.hasObject(fn):
1927: # search deeper
1928: founds=getattr(self, self.file_catalog).search({'textid':fn})
1929: if founds:
1930: obj=founds[0].getObject().getContentObject()
1931: else:
1932: return ""
1933: else:
1934: obj = self[fn].getContentObject()
1935:
1936: return obj.getData()[0:]
1937:
1938:
1939: def checkCatalog(self,fn):
1940: """check if fn is in the catalog"""
1941: #TODO add checkCatalog
1942:
1943:
1944: def findObjectsFromListWithVersion(self,list,author=None):
1945: """find objects from a list with versions
1946: @param list: list of tuples (cdliFile,version)
1947: """
1948: #self.REQUEST.SESSION['fileIds']=list#store fieldIds in session for further usage
1949: #self.REQUEST.SESSION['searchList']=self.REQUEST.SESSION['fileIds']
1950:
1951: pt=getattr(self,'filelistVersioned.html')
1952:
1953: return pt(search=list,author=author)
1954:
1955:
1956: def getAllPNumbers(self):
1957: """get a list of all files (resp their p-numbers) stored"""
1958:
1959: ret=[x.getId for x in self.CDLICatalog()]
1960:
1961: return ret
1962:
1963: def expandFile(self,fileId,fileTree):
1964: """wildcard in fileID suche alle Treffer"""
1965: founds=self.CDLICatalog({'title':fileId})
1966: for found in founds:
1967: fileTree.add(found.getId)
1968: logging.debug("ADDD:"+found.getId)
1969:
1970: def findObjectsFromList(self,enterList=None,display=False,start=None,upload=None,list=None,basketName=None,numberOfObjects=None,RESPONSE=None,REQUEST=None):
1971: """findObjectsFromList (, TAB oder LINE separated)"""
1972:
1973: logging.debug("start: findObjectsFromList")
1974: if upload: # list from file upload
1975: txt=upload.read()
1976:
1977: if enterList:
1978: txt=enterList
1979:
1980: if upload or enterList:
1981: txt=txt.replace(",","\n")
1982: txt=txt.replace("\t","\n")
1983: txt=txt.replace("\r","\n")
1984: idsTmp=txt.split("\n")
1985: ids=[]
1986: for id in idsTmp: # make sure that no empty lines
1987: idTmp=id.lstrip().rstrip()
1988: if len(idTmp)>0:
1989:
1990: ids.append(idTmp)
1991:
1992: #self.REQUEST.SESSION['ids']=" OR ".join(ids)
1993:
1994: pt=getattr(self,'filelist.html')
1995: self.REQUEST.SESSION['searchList']=ids
1996: return pt(search=ids)
1997:
1998: if basketName:
1999: #TODO: get rid of one of these..
2000:
2001: pt=getattr(self,'filelist.html')
2002: return pt(basketName=basketName,numberOfObjects=numberOfObjects)
2003:
2004: if list is not None: # got already a list
2005:
2006: logging.debug(" ----List version")
2007: ret=[]
2008: fileTree=Set()
2009:
2010: for fileId in list:
2011:
2012: if fileId.find("*")>-1: #check for wildcards
2013: self.expandFile(fileId,fileTree)
2014:
2015: elif len(fileId.split("."))==1:
2016: fileId=fileId+".atf"
2017: fileTree.add(fileId)
2018: #logging.debug(" -----:"+fileId)
2019: #ret+=self.CDLICatalog({'title':fileId})
2020: #x =self.getFileObject(fileId)
2021: #if x is not None:
2022: # ret.append(x)
2023:
2024:
2025:
2026: ids = fileTree & self.v_file_ids
2027:
2028:
2029: hash = md5.new(repr(self.makelist(ids))).digest() # erzeuge hash als identification
2030: #TODO: do I need garbage collection for _v_tmpStore ?
2031: #logging.debug("list:"+repr(self.makelist(ids)))
2032: #logging.debug("Hash:"+repr(hash))
2033: if hasattr(self.cdliRoot,'_v_tmpStore') and self.cdliRoot._v_tmpStore.has_key(hash):
2034: logging.debug("asking for storage")
2035: return self.cdliRoot._v_tmpStore[hash]
2036:
2037: #TODO: get rid of one of these..
2038: #ids=[x.getObject().getId() for x in ret]
2039: ret=[(self.getFileObject(x),self.getFileObjectLastVersion(x)) for x in ids]
2040:
2041: #self.REQUEST.SESSION['fileIds']=ids#store fieldIds in session for further usage
2042: #self.REQUEST.SESSION['searchList']=self.REQUEST.SESSION['fileIds']
2043: self.REQUEST.SESSION['fileIds']=list#store fieldIds in session for further usage
2044: self.REQUEST.SESSION['searchList']=self.REQUEST.SESSION['fileIds']
2045:
2046: if display:
2047: pt=getattr(self,'filelist.html')
2048:
2049: return pt(search=ids)
2050: else:
2051: #self.REQUEST.SESSION['hash'] = ret # store in session
2052: if not hasattr(self,'_v_tmpStore'):
2053: self.cdliRoot._v_tmpStore={}
2054: #logging.debug("HHHHHHNEU:"+repr(self.makelist(ids)))
2055: #logging.debug("HHHHHHNEU:"+repr(hash))
2056: self.cdliRoot._v_tmpStore[hash] = ret # store in session
2057: return ret
2058:
2059:
2060:
2061: if start:
2062: RESPONSE.redirect("filelist.html?start:int="+str(start))
2063:
2064: def makelist(self,mySet):
2065: x = list(mySet)
2066: x.sort()
2067: return x
2068:
2069: security.declareProtected('Manage','createAllFilesAsSingleFile')
2070: def createAllFilesAsSingleFile(self,RESPONSE=None):
2071: """download all files"""
2072:
2073: def sortF(x,y):
2074: return cmp(x[0],y[0])
2075:
2076: catalog=getattr(self,self.file_catalog)
2077: #tf,tfilename=mkstemp()
2078: if not hasattr(self.temp_folder,'downloadCounter'):
2079: self.temp_folder.downloadCounter=0
2080:
2081: if getattr(self.temp_folder,'downloadCounter',0) > 5:
2082: return """I am sorry, currently the server has to many requests for downloads, please come back later!"""
2083:
2084: self.temp_folder.downloadCounter+=1
2085: self._p_changed=1
2086: transaction.get().commit()
2087:
2088: list=[(x.getId,x) for x in catalog()]
2089: list.sort(sortF)
2090:
2091:
2092:
2093: RESPONSE.setHeader("Content-Disposition","""attachement; filename=%s"""%"all.atf")
2094: RESPONSE.setHeader("Content-Type","application/octet-stream")
2095: tmp=""
2096: for l in list:
2097: obj=l[1].getObject()
2098:
2099: if obj.meta_type=="CDLI file":
2100:
2101: #os.write(tf,obj.getLastVersion().data)
2102: if RESPONSE:
2103: RESPONSE.write(obj.getData()[0:])
2104: RESPONSE.write("\n")
2105: self.temp_folder.downloadCounter-=1
2106: self._p_changed=1
2107: transaction.get().commit()
2108: #os.close(tf)
2109: #RESPONSE.redirect(self.absolute_url()+"/downloadFile?fn="%tfilename)
2110: return True
2111:
2112: def downloadFile(self,fn):
2113: """download fn - not used yet"""
2114: self.REQUEST.RESPONSE.setHeader("Content-Disposition","""attachement; filename=%s"""%self.getLastVersion().getId())
2115: self.REQUEST.RESPONSE.setHeader("Content-Type","application/octet-stream")
2116: self.REQUEST.RESPONSE.write(file(fn).read())
2117:
2118:
2119:
2120: def hasParent(self):
2121: """returns true falls subfolder"""
2122:
2123: if self.aq_parent.meta_type in self.folder_meta_type:
2124: return True
2125: else:
2126: return False
2127:
2128: def getFolders(self):
2129: """get all subfolders"""
2130: ret=[]
2131: folders=self.ZopeFind(self,obj_metatypes=self.folder_meta_type)
2132: for folder in folders:
2133: ret.append((folder[1],
2134: len(self.ZopeFind(folder[1],obj_metatypes=self.folder_meta_type)),
2135: len(self.ZopeFind(folder[1],obj_metatypes=self.file_meta_type))
2136: ))
2137: return ret
2138:
2139:
2140: security.declareProtected('manage','index_html')
2141: def index_html(self):
2142: """main"""
2143: ext=self.ZopeFind(self,obj_ids=["index.html"])
2144: if ext:
2145: return ext[0][1]()
2146:
2147: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','CDLIFileFolderMain')).__of__(self)
2148: return pt()
2149:
2150:
2151: manage_addCDLIFileFolderForm=DTMLFile('dtml/folderAdd', globals())
2152:
2153:
2154: def manage_addCDLIFileFolder(self, id, title='',
2155: createPublic=0,
2156: createUserF=0,
2157: REQUEST=None):
2158: """Add a new Folder object with id *id*.
2159:
2160: If the 'createPublic' and 'createUserF' parameters are set to any true
2161: value, an 'index_html' and a 'UserFolder' objects are created respectively
2162: in the new folder.
2163: """
2164: ob=CDLIFileFolder()
2165: ob.id=str(id)
2166: ob.title=title
2167: self._setObject(id, ob)
2168: ob=self._getOb(id)
2169:
2170: checkPermission=getSecurityManager().checkPermission
2171:
2172: if createUserF:
2173: if not checkPermission('Add User Folders', ob):
2174: raise Unauthorized, (
2175: 'You are not authorized to add User Folders.'
2176: )
2177: ob.manage_addUserFolder()
2178:
2179:
2180: if REQUEST is not None:
2181: return self.manage_main(self, REQUEST, update_menu=1)
2182:
2183: class CDLIRoot(Folder):
2184: """main folder for cdli"""
2185:
2186: meta_type="CDLIRoot"
2187: downloadCounterBaskets=0 # counts the current basket downloads if counter > 10 no downloads are possible
2188:
2189: file_catalog = 'CDLICatalog'
2190:
2191: # word splitter for search
2192: splitter = {'words':cdliSplitter.wordSplitter(),
2193: 'graphemes':cdliSplitter.graphemeSplitter()}
2194:
2195:
2196: def getFileObject(self,fileId):
2197: x=self.v_files.get(fileId)
2198: #logging.debug(x)
2199: return x
2200:
2201: def getFileObjectLastVersion(self,fileId):
2202: x=self.v_files_lastVersion.get(fileId)
2203: #logging.debug(x)
2204: return x
2205:
2206: def generateFileBTree(self):
2207: """erzeuge einen Btree aus allen Files"""
2208: self.v_files = OOBTree()
2209: self.v_files_lastVersion = OOBTree()
2210: self.v_file_ids = Set()
2211:
2212: for x in self.CDLICatalog.searchResults():
2213:
2214: self.v_files.update({x.getId:x.getObject()})
2215: self.v_files_lastVersion.update({x.getId:x.getObject().getLastVersion()})
2216: self.v_file_ids.add(x.getId)
2217: logging.debug("add:"+x.getId+"XXX"+repr(x.getObject()))
2218:
2219: return "done"
2220: def deleteFiles(self,ids):
2221: """delete files"""
2222: for id in ids:
2223: founds=self.CDLICatalog.search({'title':id.split(".")[0]})
2224: if founds:
2225: logging.debug("deleting %s"%founds)
2226: folder=founds[0].getObject().aq_parent #get the parent folder of the object
2227: logging.debug("deleting from %s"%folder)
2228: cut=folder.delete([founds[0].getId]) #cut it out
2229:
2230:
2231:
2232: def searchText(self, query, index='graphemes'):
2233: """searches query in the fulltext index and returns a list of file ids/P-numbers"""
2234: # see also: http://www.plope.com/Books/2_7Edition/SearchingZCatalog.stx#2-13
2235: logging.debug("searchtext for '%s' in index %s"%(query,index))
2236: #import Products.ZCTextIndex.QueryParser
2237: #qp = QueryParser.QueryParser()
2238: #logging.debug()
2239: idxQuery = {index:{'query':query}}
2240: idx = getattr(self, self.file_catalog)
2241: # do search
2242: resultset = idx.search(query_request=idxQuery,sort_index='textid')
2243: # put only the P-Number in the result
2244: results = [res.getId[:7] for res in resultset]
2245: logging.debug("searchtext: found %d texts"%len(results))
2246: return results
2247:
2248:
2249: def getFile(self, pnum):
2250: """get the translit file with the given pnum"""
2251: f = getattr(self, self.file_catalog).search({'textid':pnum})
2252: if not f:
2253: return ""
2254:
2255: return f[0].getObject().getData()
2256:
2257:
2258: def showFile(self,fileId,wholePage=False):
2259: """show a file
2260: @param fileId: P-Number of the document to be displayed
2261: """
2262: f=getattr(self, self.file_catalog).search({'textid':fileId})
2263: if not f:
2264: return ""
2265:
2266: if wholePage:
2267: logging.debug("show whole page")
2268: return f[0].getObject().getContentObject().view()
2269: else:
2270: return f[0].getObject().getLastVersionFormattedData()
2271:
2272:
2273: def showWordInFile(self,fileId,word,indexName='graphemes',regExp=False,):
2274: """get lines with word from FileId"""
2275: logging.debug("showwordinfile word='%s' index=%s file=%s"%(word,indexName,fileId))
2276:
2277: file = formatAtfFullLineNum(self.getFile(fileId))
2278: ret=[]
2279:
2280: # add whitespace before and whitespace and line-end to splitter bounds expressions
2281: bounds = self.splitter[indexName].bounds
2282: splitexp = "(%s|\s)(%%s)(%s|\s|\Z)"%(bounds,bounds)
2283: # clean word expression
2284: # TODO: this should use QueryParser itself
2285: # take out double quotes
2286: word = word.replace('"','')
2287: # take out ignorable signs
2288: ignorable = self.splitter[indexName].ignorex
2289: word = ignorable.sub('', word)
2290: # compile into regexp objects and escape parens
2291: wordlist = [re.compile(splitexp%re.escape(w)) for w in word.split(' ')]
2292:
2293: for line in file.splitlines():
2294: for word in wordlist:
2295: #logging.debug("showwordinfile: searching for %s in %s"%(word.pattern,ignoreable.sub('',line)))
2296: if word.search(ignorable.sub('',line)):
2297: line = formatAtfLineHtml(line)
2298: ret.append(line)
2299: break
2300:
2301: return ret
2302:
2303:
2304: def showWordInFiles(self,fileIds,word,indexName='graphemes',regExp=False):
2305: """
2306: get lines with word from all ids in list FileIds.
2307: returns dict with id:lines pairs.
2308: """
2309: logging.debug("showwordinfiles word='%s' index=%s file=%s"%(word,indexName,fileIds))
2310:
2311: return dict([(id,self.showWordInFile(id, word, indexName, regExp)) for id in fileIds])
2312:
2313:
2314: def tagWordInFile(self,fileId,word,indexName='graphemes',regExp=False):
2315: """get text with word highlighted from FileId"""
2316: logging.debug("tagwordinfile word='%s' index=%s file=%s"%(word,indexName,fileId))
2317:
2318: file=self.getFile(fileId)
2319: tagStart=u'<span class="found">'
2320: tagEnd=u'</span>'
2321: tagStr=tagStart + u'%%s' + tagEnd
2322: ret=[]
2323:
2324: # add whitespace to splitter bounds expressions and compile into regexp object
2325: bounds = self.splitter[indexName].bounds
2326: wordsplit = re.compile("(%s|\s)"%bounds)
2327: # clean word expression
2328: # TODO: this should use QueryParser itself
2329: word = word.replace('"','') # take out double quotes
2330: # take out ignoreable signs
2331: ignorable = self.splitter[indexName].ignorex
2332: word = ignorable.sub('', word)
2333: # split search terms by blanks
2334: words = word.split(' ')
2335: # split search terms again (for grapheme search with words)
2336: splitwords = dict(((w,self.splitter[indexName].process([w])) for w in words))
2337:
2338: for line in file.splitlines():
2339: line = unicodify(line)
2340: # ignore lemma and other lines
2341: if line.lstrip().startswith('#lem:'):
2342: continue
2343: # ignore p-num line
2344: if line.startswith('&P'):
2345: continue
2346: # ignore version lines
2347: if line.startswith('#version'):
2348: continue
2349: # ignore atf type lines
2350: if line.startswith('#atf:'):
2351: continue
2352:
2353: # first scan
2354: hitwords = []
2355: for w in words:
2356: if ignorable.sub('',line).find(w) > -1:
2357: # word is in line
2358: # append split word for grapheme search with words
2359: hitwords.extend(splitwords[w])
2360: #hitwords.extend(wordsplit.split(w))
2361:
2362: # examine hits closer
2363: if hitwords:
2364: # split line into words
2365: parts = wordsplit.split(line)
2366: line = ""
2367: for p in parts:
2368: #logging.debug("tagwordinfile: searching for %s in %s"%(p,hitwords))
2369: # reassemble line
2370: if ignorable.sub('', p) in hitwords:
2371: #logging.debug("tagwordinfile: found %s in %s"%(p,hitwords))
2372: # this part was found
2373: line += tagStart + formatAtfHtml(p) + tagEnd
2374: else:
2375: line += formatAtfHtml(p)
2376:
2377: else:
2378: # no hits
2379: line = formatAtfHtml(line)
2380:
2381: ret.append(line)
2382:
2383: return u'<br>\n'.join(ret)
2384:
2385:
2386:
2387: def tagWordInFiles(self,fileIds,word,indexName='graphemes',regExp=False):
2388: """
2389: get texts with highlighted word from all ids in list FileIds.
2390: returns dict with id:text pairs.
2391: """
2392: logging.debug("tagwordinfiles word='%s' index=%s file=%s"%(word,indexName,fileIds))
2393: return dict([(id,self.tagWordInFile(id, word, indexName, regExp)) for id in fileIds])
2394:
2395:
2396: def getFileVersionList(self, pnum):
2397: """get the version history as a list for the translit file with the given pnum"""
2398: f = getattr(self, self.file_catalog).search({'textid':pnum})
2399: if not f:
2400: return []
2401:
2402: return f[0].getObject().getVersionList()
2403:
2404:
2405: def URLquote(self,str):
2406: """quote url"""
2407: return urllib.quote(str)
2408:
2409: def URLunquote(self,str):
2410: """unquote url"""
2411: return urllib.unquote(str)
2412:
2413: def URLquote_plus(self,str):
2414: """quote url"""
2415: return urllib.quote_plus(str)
2416:
2417: def URLunquote_plus(self,str):
2418: """unquote url"""
2419: return urllib.unquote_plus(str)
2420:
2421:
2422: def forceunlock(self):
2423: "break all locks"
2424: ret=[]
2425: for f in self.ZopeFind(self,obj_metatypes="CDLI file",search_sub=1):
2426: un=f[1].forceunlock()
2427:
2428: if un and un !="":
2429: ret.append((f[0],un))
2430:
2431: return ret
2432:
2433:
2434: def getChangesByAuthor(self,author,n=100):
2435: """getChangesByAuthor"""
2436: zcat=self.CDLIObjectsCatalog
2437: res=zcat({'lastEditor':author,
2438: 'sort_on':'getTime',
2439: 'sort_order':'descending',
2440: 'sort_limit':n})[:n ]
2441:
2442: return res
2443:
2444: def getChangesByAuthor_html(self,author,n=100):
2445: """html output for changes by author"""
2446: tmp={}
2447: list=[]
2448: for x in self.getChangesByAuthor(author):
2449: nr=x.getObject().getVersionNumber()
2450: id=x.getObject().aq_parent.getId()
2451: #hinzufuegen, wenn Version neuer als die
2452: if tmp.get(id,(0,0))[1] < nr:
2453: tmp[id]=(x.getObject().aq_parent,nr)
2454:
2455:
2456: return self.cdli_main.findObjectsFromListWithVersion(list=tmp.values(),author=author)
2457:
2458: def getLastChanges(self,n=100):
2459: """get the last n changes"""
2460: n=int(n)
2461: zcat=self.CDLICatalog
2462: return zcat({'sort_on':'getLastChangeDate',
2463: 'sort_order':'descending',
2464: 'sort_limit':n})[:n ]
2465:
2466:
2467: def getLastChanges_html(self,n=100):
2468: """get the last n changes"""
2469: list = [x.getId for x in self.getLastChanges(n)]
2470: return self.cdli_main.findObjectsFromList(list=list,display=True)
2471:
2472: def refreshTxt(self,txt="",threadName=None):
2473: """txt fuer refresh"""
2474:
2475: return """ 2;url=%s?repeat=%s """%(self.absolute_url()+txt,threadName)
2476:
2477:
2478: def getResult(self,threadName=None):
2479: """result of thread"""
2480: try:
2481: return self._v_uploadATF[threadName].getResult()
2482: except:
2483: return "One moment, please"
2484:
2485:
2486: def checkThreads(self):
2487: """check threads"""
2488: ret="<html><body>"
2489: for thread in threading.enumerate():
2490: ret+="<p>%s (%s): %s</p>"%(repr(thread),thread.getName(),thread.isAlive())
2491:
2492: return ret
2493:
2494:
2495: def uploadATFRPC(self,data,username):
2496: """upload an atffile via xml-rpc"""
2497: uploader=uploadATFThread()
2498:
2499: #generate an random id for the upload object
2500: from random import randint
2501: if (not self.REQUEST.SESSION.get('idTmp',None)):
2502:
2503: idTmp=str(randint(0,1000000000))
2504: self.REQUEST.SESSION['idTmp']=idTmp
2505: else:
2506: idTmp=self.REQUEST.SESSION.get('idTmp',None)
2507:
2508:
2509: uploader.set(data,0,username,idTmp)
2510:
2511: stObj=uploader.run()
2512:
2513: processor=uploadATFfinallyThread()
2514:
2515: basketname=stObj.returnValue['basketNameFromFile']
2516:
2517: processor.set("uploadchanged",basketname=basketname,SESSION=stObj.returnValue,username=username,serverport=self.REQUEST['SERVER_PORT'])
2518:
2519: processor.run()
2520:
2521:
2522: return generateXMLReturn(stObj.returnValue)
2523:
2524: def uploadATF(self,repeat=None,upload=None,basketId=0,RESPONSE=None):
2525: """upload an atf file / basket file"""
2526: #self._v_uploadATF.returnValue=None
2527:
2528: #generate an random id for the upload thread
2529: from random import randint
2530: if (not self.REQUEST.SESSION.get('idTmp',None)):
2531:
2532: idTmp=str(randint(0,1000000000))
2533: self.REQUEST.SESSION['idTmp']=idTmp
2534: else:
2535: idTmp=self.REQUEST.SESSION.get('idTmp',None)
2536:
2537:
2538: threadName=repeat
2539: if not threadName or threadName=="":
2540: #new thread not called from the waiting page
2541: tmpVar=False
2542:
2543: thread=uploadATFThread()
2544: threadName=thread.getName()[0:]
2545: if (not hasattr(self,'_v_uploadATF')):
2546: self._v_uploadATF={}
2547:
2548: self._v_uploadATF[threadName]=thread
2549: #self._xmltrans.start()
2550: #thread=Thread(target=self._v_uploadATF)
2551: logging.info("set thread. extern")
2552: self._v_uploadATF[threadName].set(upload,basketId,self.REQUEST['AUTHENTICATED_USER'],idTmp,serverport=self.REQUEST['SERVER_PORT'])
2553: #thread.start()
2554: logging.info("start thread. extern")
2555: self._v_uploadATF[threadName].start()
2556:
2557:
2558: self.threadName=self._v_uploadATF[threadName].getName()[0:]
2559: wait_template=self.aq_parent.ZopeFind(self.aq_parent,obj_ids=['wait_template'])
2560:
2561: if wait_template:
2562: return wait_template[0][1]()
2563: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadATFWait.zpt')).__of__(self)
2564: return pt(txt='/uploadATF',threadName=threadName)
2565: #_v_xmltrans.run()
2566:
2567: else:
2568: #recover thread, if lost
2569: if (not hasattr(self,'_v_uploadATF')):
2570: self._v_uploadATF={}
2571: if not self._v_uploadATF.get(threadName,None):
2572: for thread in threading.enumerate():
2573: if threadName == thread.getName():
2574: self._v_uploadATF[threadName]=thread
2575:
2576: if self._v_uploadATF.get(threadName,None) and (not self._v_uploadATF[threadName].returnValue):
2577:
2578:
2579: wait_template=self.aq_parent.ZopeFind(self.aq_parent,obj_ids=['wait_template'])
2580: if wait_template:
2581: return wait_template[0][1]()
2582:
2583: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadATFWait.zpt')).__of__(self)
2584:
2585: return pt(txt='/uploadATF',threadName=threadName)
2586:
2587: else:
2588: tmp=getattr(self.temp_folder,idTmp).returnValue
2589:
2590: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadCheck.zpt')).__of__(self)
2591:
2592: return pt(changed=tmp['changed'],lockerrors=tmp['lockerrors'],errors=tmp['errors'],dir=tmp['dir'],newPs=tmp['newPs'],basketLen=tmp['basketLen'],numberOfFiles=tmp['numberOfFiles'],
2593: basketNameFromId=tmp['basketNameFromId'],basketNameFromFile=tmp['basketNameFromFile'],basketId=tmp['basketId'])
2594:
2595: def redoUpload(self,threadName):
2596: """redo the upload"""
2597: tmp=self.cdli_main.tmpStore2[threadName]
2598: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadCheck.zpt')).__of__(self)
2599: return pt(changed=tmp['changed'],lockerrors=tmp['lockerrors'],errors=tmp['errors'],dir=tmp['dir'],newPs=tmp['newPs'],basketLen=tmp['basketLen'],numberOfFiles=tmp['numberOfFiles'],
2600: basketNameFromId=tmp['basketNameFromId'],basketNameFromFile=tmp['basketNameFromFile'],basketId=tmp['basketId'])
2601:
2602: def uploadATFfinally(self,procedure='',comment="",basketname='',unlock=None,repeat=None,RESPONSE=None):
2603: """nowupload the files"""
2604:
2605:
2606:
2607: threadName=repeat
2608: if not threadName or threadName=="":
2609: thread=uploadATFfinallyThread()
2610: threadName=thread.getName()[0:]
2611:
2612: if (not hasattr(self,'_v_uploadATF')):
2613: self._v_uploadATF={}
2614:
2615:
2616: self._v_uploadATF[threadName]=thread
2617:
2618: idTmp=self.REQUEST.SESSION['idTmp']
2619: stObj=getattr(self.temp_folder,idTmp)
2620: self._v_uploadATF[threadName].set(procedure,comment=comment,basketname=basketname,unlock=unlock,SESSION=stObj.returnValue,username=self.REQUEST['AUTHENTICATED_USER'],serverport=self.REQUEST['SERVER_PORT'])
2621:
2622: self._v_uploadATF[threadName].start()
2623:
2624:
2625:
2626: wait_template=self.aq_parent.ZopeFind(self.aq_parent,obj_ids=['wait_template'])
2627:
2628: if wait_template:
2629: return wait_template[0][1]()
2630: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadATFWait.zpt')).__of__(self)
2631:
2632: return pt(txt='/uploadATFfinally',threadName=threadName)
2633: #_v_xmltrans.run()
2634:
2635: else:
2636: #recover thread, if lost
2637: if not hasattr(self,'_v_uploadATF'):
2638: self._v_uploadATF={}
2639: if not self._v_uploadATF.get(threadName,None):
2640: for thread in threading.enumerate():
2641: if threadName == thread.getName():
2642: self._v_uploadATF[threadName]=thread
2643:
2644: if self._v_uploadATF.get(threadName,None) and (self._v_uploadATF[threadName] is not None) and (not self._v_uploadATF[threadName].end) :
2645:
2646: wait_template=self.aq_parent.ZopeFind(self.aq_parent,obj_ids=['wait_template'])
2647: if wait_template:
2648: return wait_template[0][1]()
2649:
2650: pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','uploadATFWait.zpt')).__of__(self)
2651: return pt(txt='/uploadATFfinally',threadName=threadName)
2652: else:
2653: self.REQUEST.SESSION['idTmp']=None
2654: if RESPONSE is not None:
2655: RESPONSE.redirect(self.absolute_url())
2656:
2657: def importFiles(self,comment="",author="" ,folderName="/Users/dwinter/atf", files=None,ext=None):
2658: """import files"""
2659: logging.debug("importFiles folderName=%s files=%s ext=%s"%(folderName,files,ext))
2660: root=self.cdli_main
2661: count=0
2662: if not files:
2663: files=os.listdir(folderName)
2664:
2665: for f in files:
2666: folder=f[0:3]
2667: f2=f[0:5]
2668: obj=self.ZopeFind(root,obj_ids=[folder])
2669: logging.debug("importFiles: folder=%s f2=%s obj=%s"%(folder,f2,obj))
2670: if ext:
2671: ext.result="<p>adding: %s </p>"%f+ext.result
2672:
2673: if not obj:
2674: manage_addCDLIFileFolder(root,folder,folder)
2675: fobj=getattr(root,folder)
2676: #transaction.get().commit()
2677:
2678: else:
2679: fobj=obj[0][1]
2680:
2681: obj2=fobj.ZopeFind(fobj,obj_ids=[f2])
2682: logging.debug("importFiles: fobj=%s obj2=%s"%(fobj,obj2))
2683:
2684: if not obj2:
2685: manage_addCDLIFileFolder(fobj,f2,f2)
2686: fobj2=getattr(fobj,f2)
2687:
2688: else:
2689: fobj2=obj2[0][1]
2690:
2691: file2=os.path.join(folderName,f)
2692: id=f
2693: logging.debug("importFiles: addCDLIFile fobj2=%s, f=%s file2=%s"%(fobj2,repr(f),repr(file2)))
2694: fobj2.addFile(vC='',file=file(file2),author=author,newName=f)
2695: count+=1
2696:
2697: if count%100==0:
2698: logging.debug("importfiles: committing")
2699: transaction.get().commit()
2700:
2701: transaction.get().commit()
2702: return "ok"
2703:
2704:
2705: manage_addCDLIRootForm=DTMLFile('dtml/rootAdd', globals())
2706:
2707:
2708: def manage_addCDLIRoot(self, id, title='',
2709: createPublic=0,
2710: createUserF=0,
2711: REQUEST=None):
2712: """Add a new Folder object with id *id*.
2713:
2714: If the 'createPublic' and 'createUserF' parameters are set to any true
2715: value, an 'index_html' and a 'UserFolder' objects are created respectively
2716: in the new folder.
2717: """
2718: ob=CDLIRoot()
2719: ob.id=str(id)
2720: ob.title=title
2721: try:
2722: self._setObject(id, ob)
2723: except:
2724: pass
2725: ob=self._getOb(id)
2726:
2727: checkPermission=getSecurityManager().checkPermission
2728:
2729: if createUserF:
2730: if not checkPermission('Add User Folders', ob):
2731: raise Unauthorized, (
2732: 'You are not authorized to add User Folders.'
2733: )
2734: ob.manage_addUserFolder()
2735:
2736:
2737: if REQUEST is not None:
2738: return self.manage_main(self, REQUEST, update_menu=1)
2739:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>