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