1:
2: from OFS.Folder import Folder
3: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
4: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
5: from AccessControl import ClassSecurityInfo
6: from AccessControl import getSecurityManager
7: from Globals import package_home
8:
9: from Ft.Xml.Domlette import NonvalidatingReader
10: from Ft.Xml.Domlette import PrettyPrint, Print
11: from Ft.Xml import EMPTY_NAMESPACE, Parse
12:
13:
14: import Ft.Xml.XPath
15: import xmlrpclib
16: import os.path
17: import sys
18: import cgi
19: import urllib
20: import logging
21: import math
22:
23: import urlparse
24: from types import *
25: def logger(txt,method,txt2):
26: """logging"""
27: logging.info(txt+ txt2)
28:
29:
30: def getInt(number, default=0):
31: """returns always an int (0 in case of problems)"""
32: try:
33: return int(number)
34: except:
35: return int(default)
36:
37: def getTextFromNode(nodename):
38: """get the cdata content of a node"""
39: if nodename is None:
40: return ""
41: nodelist=nodename.childNodes
42: rc = ""
43: for node in nodelist:
44: if node.nodeType == node.TEXT_NODE:
45: rc = rc + node.data
46: return rc
47:
48:
49: def getParentDir(path):
50: """returns pathname shortened by one"""
51: return '/'.join(path.split('/')[0:-1])
52:
53:
54: import socket
55:
56: def urlopen(url,timeout=2):
57: """urlopen mit timeout"""
58: socket.setdefaulttimeout(timeout)
59: ret=urllib.urlopen(url)
60: socket.setdefaulttimeout(5)
61: return ret
62:
63:
64: ##
65: ## documentViewer class
66: ##
67: class documentViewer(Folder):
68: """document viewer"""
69: #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"
70:
71: meta_type="Document viewer"
72:
73: security=ClassSecurityInfo()
74: manage_options=Folder.manage_options+(
75: {'label':'main config','action':'changeDocumentViewerForm'},
76: )
77:
78: # templates and forms
79: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
80: thumbs_main = PageTemplateFile('zpt/thumbs_main', globals())
81: image_main = PageTemplateFile('zpt/image_main', globals())
82: head_main = PageTemplateFile('zpt/head_main', globals())
83: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
84: info_xml = PageTemplateFile('zpt/info_xml', globals())
85:
86: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
87: security.declareProtected('View management screens','changeDocumentViewerForm')
88: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
89:
90:
91: def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):
92: """init document viewer"""
93: self.id=id
94: self.title=title
95: self.imageViewerUrl=imageViewerUrl
96: self.textViewerUrl=textViewerUrl
97:
98: if not digilibBaseUrl:
99: self.digilibBaseUrl = self.findDigilibUrl()
100: else:
101: self.digilibBaseUrl = digilibBaseUrl
102: self.thumbcols = thumbcols
103: self.thumbrows = thumbrows
104: # authgroups is list of authorized groups (delimited by ,)
105: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
106: # add template folder so we can always use template.something
107: self.manage_addFolder('template')
108:
109:
110: security.declareProtected('View','thumbs_rss')
111: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
112: '''
113: view it
114: @param mode: defines how to access the document behind url
115: @param url: url which contains display information
116: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
117:
118: '''
119: logging.info("HHHHHHHHHHHHHH:load the rss")
120: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
121:
122: if not hasattr(self, 'template'):
123: # create template folder if it doesn't exist
124: self.manage_addFolder('template')
125:
126: if not self.digilibBaseUrl:
127: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
128:
129: docinfo = self.getDocinfo(mode=mode,url=url)
130: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
131: pt = getattr(self.template, 'thumbs_main_rss')
132:
133: if viewMode=="auto": # automodus gewaehlt
134: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
135: viewMode="text"
136: else:
137: viewMode="images"
138:
139: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
140:
141: security.declareProtected('View','index_html')
142: def index_html(self,mode,url,viewMode="auto",start=None,pn=1,mk=None):
143: '''
144: view it
145: @param mode: defines how to access the document behind url
146: @param url: url which contains display information
147: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
148:
149: '''
150:
151: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
152:
153: if not hasattr(self, 'template'):
154: # create template folder if it doesn't exist
155: self.manage_addFolder('template')
156:
157: if not self.digilibBaseUrl:
158: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
159:
160: docinfo = self.getDocinfo(mode=mode,url=url)
161: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
162: pt = getattr(self.template, 'viewer_main')
163:
164: if viewMode=="auto": # automodus gewaehlt
165: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
166: viewMode="text"
167: else:
168: viewMode="images"
169:
170: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
171:
172: def generateMarks(self,mk):
173: ret=""
174: if mk is None:
175: return ""
176:
177: if type(mk) is not ListType:
178: mk=[mk]
179: for m in mk:
180: ret+="mk=%s"%m
181: return ret
182:
183: def getLink(self,param=None,val=None):
184: """link to documentviewer with parameter param set to val"""
185: params=self.REQUEST.form.copy()
186: if param is not None:
187: if val is None:
188: if params.has_key(param):
189: del params[param]
190: else:
191: params[param] = str(val)
192: if params["mode"] == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
193: params["mode"] = "imagepath"
194: params["url"] = getParentDir(params["url"])
195:
196: # quote values and assemble into query string
197: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
198: url=self.REQUEST['URL1']+"?"+ps
199: return url
200:
201: def getLinkAmp(self,param=None,val=None):
202: """link to documentviewer with parameter param set to val"""
203: params=self.REQUEST.form.copy()
204: if param is not None:
205: if val is None:
206: if params.has_key(param):
207: del params[param]
208: else:
209: params[param] = str(val)
210:
211: # quote values and assemble into query string
212: logging.info("XYXXXXX: %s"%repr(params.items()))
213: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
214: url=self.REQUEST['URL1']+"?"+ps
215: return url
216:
217: def getInfo_xml(self,url,mode):
218: """returns info about the document as XML"""
219:
220: if not self.digilibBaseUrl:
221: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
222:
223: docinfo = self.getDocinfo(mode=mode,url=url)
224: pt = getattr(self.template, 'info_xml')
225: return pt(docinfo=docinfo)
226:
227:
228: def getStyle(self, idx, selected, style=""):
229: """returns a string with the given style and append 'sel' if path == selected."""
230: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
231: if idx == selected:
232: return style + 'sel'
233: else:
234: return style
235:
236: def getTextLanguage(self,url,docinfo):
237: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
238: lang = urlencode({'':docinfo['lang']})
239: return lang
240:
241:
242: def isAccessible(self, docinfo):
243: """returns if access to the resource is granted"""
244: access = docinfo.get('accessType', None)
245: logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
246: if access is not None and access == 'free':
247: logger("documentViewer (accessOK)", logging.INFO, "access is free")
248: return True
249: elif access is None or access in self.authgroups:
250: # only local access -- only logged in users
251: user = getSecurityManager().getUser()
252: if user is not None:
253: #print "user: ", user
254: return (user.getUserName() != "Anonymous User")
255: else:
256: return False
257:
258: logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
259: return False
260:
261:
262: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
263: """gibt param von dlInfo aus"""
264: num_retries = 3
265: if docinfo is None:
266: docinfo = {}
267:
268: for x in range(cut):
269:
270: path=getParentDir(path)
271:
272: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
273:
274: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
275:
276: for cnt in range(num_retries):
277: try:
278: # dom = NonvalidatingReader.parseUri(imageUrl)
279: txt=urllib.urlopen(infoUrl).read()
280: dom = Parse(txt)
281: break
282: except:
283: logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
284: else:
285: raise IOError("Unable to get dir-info from %s"%(infoUrl))
286:
287: sizes=dom.xpath("//dir/size")
288: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
289:
290: if sizes:
291: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
292: else:
293: docinfo['numPages'] = 0
294:
295: return docinfo
296:
297:
298: def getIndexMeta(self, url):
299: """returns dom of index.meta document at url"""
300: num_retries = 3
301: dom = None
302: metaUrl = None
303: if url.startswith("http://"):
304: # real URL
305: metaUrl = url
306: else:
307: # online path
308: server=self.digilibBaseUrl+"/servlet/Texter?fn="
309: metaUrl=server+url.replace("/mpiwg/online","")
310: if not metaUrl.endswith("index.meta"):
311: metaUrl += "/index.meta"
312: logging.debug("METAURL: %s"%metaUrl)
313: for cnt in range(num_retries):
314: try:
315: # patch dirk encoding fehler treten dann nicht mehr auf
316: # dom = NonvalidatingReader.parseUri(metaUrl)
317: txt=urllib.urlopen(metaUrl).read()
318: dom = Parse(txt)
319: break
320: except:
321: logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
322:
323: if dom is None:
324: raise IOError("Unable to read index meta from %s"%(url))
325:
326: return dom
327:
328: def getPresentationInfoXML(self, url):
329: """returns dom of info.xml document at url"""
330: num_retries = 3
331: dom = None
332: metaUrl = None
333: if url.startswith("http://"):
334: # real URL
335: metaUrl = url
336: else:
337: # online path
338: server=self.digilibBaseUrl+"/servlet/Texter?fn="
339: metaUrl=server+url.replace("/mpiwg/online","")
340:
341:
342: for cnt in range(num_retries):
343: try:
344: # patch dirk encoding fehler treten dann nicht mehr auf
345: # dom = NonvalidatingReader.parseUri(metaUrl)
346: txt=urllib.urlopen(metaUrl).read()
347: dom = Parse(txt)
348: break
349: except:
350: logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
351:
352: if dom is None:
353: raise IOError("Unable to read infoXMLfrom %s"%(url))
354:
355: return dom
356:
357:
358: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
359: """gets authorization info from the index.meta file at path or given by dom"""
360: logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
361:
362: access = None
363:
364: if docinfo is None:
365: docinfo = {}
366:
367: if dom is None:
368: for x in range(cut):
369: path=getParentDir(path)
370: dom = self.getIndexMeta(path)
371:
372: acctype = dom.xpath("//access-conditions/access/@type")
373: if acctype and (len(acctype)>0):
374: access=acctype[0].value
375: if access in ['group', 'institution']:
376: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
377:
378: docinfo['accessType'] = access
379: return docinfo
380:
381:
382: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
383: """gets bibliographical info from the index.meta file at path or given by dom"""
384: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
385:
386: if docinfo is None:
387: docinfo = {}
388:
389: if dom is None:
390: for x in range(cut):
391: path=getParentDir(path)
392: dom = self.getIndexMeta(path)
393:
394: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
395: # put in all raw bib fields as dict "bib"
396: bib = dom.xpath("//bib/*")
397: if bib and len(bib)>0:
398: bibinfo = {}
399: for e in bib:
400: bibinfo[e.localName] = getTextFromNode(e)
401: docinfo['bib'] = bibinfo
402:
403: # extract some fields (author, title, year) according to their mapping
404: metaData=self.metadata.main.meta.bib
405: bibtype=dom.xpath("//bib/@type")
406: if bibtype and (len(bibtype)>0):
407: bibtype=bibtype[0].value
408: else:
409: bibtype="generic"
410:
411: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
412: docinfo['bib_type'] = bibtype
413: bibmap=metaData.generateMappingForType(bibtype)
414: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
415: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
416: try:
417: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
418: except: pass
419: try:
420: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
421: except: pass
422: try:
423: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
424: except: pass
425: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
426: try:
427: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
428: except:
429: docinfo['lang']=''
430:
431: return docinfo
432:
433:
434: def getNumPages(self, xquery, docinfo=None): #New Method 24.02.2010
435: text=self.viewerTemplates.query.eval("/mpdl/interface/xquery.xql","document="+ docinfo['textURLPath'] +"&xquery="+str(xquery))
436: docinfo['numPages'] = text.count("<pb ")
437: return docinfo
438:
439:
440: def getDocinfoFromTextTool(self,url,dom=None,docinfo=None):
441: """parse texttool tag in index meta"""
442: logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url))
443: if docinfo is None:
444: docinfo = {}
445:
446: if docinfo.get('lang',None) is None:
447: docinfo['lang']='' # default keine Sprache gesetzt
448: if dom is None:
449: dom = self.getIndexMeta(url)
450:
451: archivePath = None
452: archiveName = None
453:
454: archiveNames=dom.xpath("//resource/name")
455: if archiveNames and (len(archiveNames)>0):
456: archiveName=getTextFromNode(archiveNames[0])
457: else:
458: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/name missing in: %s"%(url))
459:
460: archivePaths=dom.xpath("//resource/archive-path")
461: if archivePaths and (len(archivePaths)>0):
462: archivePath=getTextFromNode(archivePaths[0])
463: # clean up archive path
464: if archivePath[0] != '/':
465: archivePath = '/' + archivePath
466: if archiveName and (not archivePath.endswith(archiveName)):
467: archivePath += "/" + archiveName
468: else:
469: # try to get archive-path from url
470: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/archive-path missing in: %s"%(url))
471: if (not url.startswith('http')):
472: archivePath = url.replace('index.meta', '')
473:
474: if archivePath is None:
475: # we balk without archive-path
476: raise IOError("Missing archive-path (for text-tool) in %s"%(url))
477:
478: imageDirs=dom.xpath("//texttool/image")
479: if imageDirs and (len(imageDirs)>0):
480: imageDir=getTextFromNode(imageDirs[0])
481:
482: else:
483: # we balk with no image tag / not necessary anymore because textmode is now standard
484: #raise IOError("No text-tool info in %s"%(url))
485: imageDir=""
486: #xquery="//pb"
487: docinfo['imagePath'] = "" # keine Bilder
488: docinfo['imageURL'] = ""
489:
490: if imageDir and archivePath:
491: #print "image: ", imageDir, " archivepath: ", archivePath
492: imageDir=os.path.join(archivePath,imageDir)
493: imageDir=imageDir.replace("/mpiwg/online",'')
494: docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo)
495: docinfo['imagePath'] = imageDir
496:
497: docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir
498:
499: viewerUrls=dom.xpath("//texttool/digiliburlprefix")
500: if viewerUrls and (len(viewerUrls)>0):
501: viewerUrl=getTextFromNode(viewerUrls[0])
502: docinfo['viewerURL'] = viewerUrl
503:
504: textUrls=dom.xpath("//texttool/text")
505: if textUrls and (len(textUrls)>0):
506: textUrl=getTextFromNode(textUrls[0])
507: if urlparse.urlparse(textUrl)[0]=="": #keine url
508: textUrl=os.path.join(archivePath,textUrl)
509: # fix URLs starting with /mpiwg/online
510: if textUrl.startswith("/mpiwg/online"):
511: textUrl = textUrl.replace("/mpiwg/online",'',1)
512:
513: docinfo['textURL'] = textUrl
514:
515: textUrls=dom.xpath("//texttool/text-url-path")
516: if textUrls and (len(textUrls)>0):
517: textUrl=getTextFromNode(textUrls[0])
518: docinfo['textURLPath'] = textUrl
519:
520: presentationUrls=dom.xpath("//texttool/presentation")
521: docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get info von bib tag
522:
523: if presentationUrls and (len(presentationUrls)>0): # ueberschreibe diese durch presentation informationen
524: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
525: # durch den relativen Pfad auf die presentation infos
526: presentationPath = getTextFromNode(presentationUrls[0])
527: if url.endswith("index.meta"):
528: presentationUrl=url.replace('index.meta',presentationPath)
529: else:
530: presentationUrl=url + "/" + presentationPath
531: docinfo=self.getNumPages('//pb', docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
532: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom)
533:
534: docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info
535:
536: return docinfo
537:
538:
539: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
540: """gets the bibliographical information from the preseantion entry in texttools
541: """
542: dom=self.getPresentationInfoXML(url)
543: try:
544: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
545: except:
546: pass
547: try:
548: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
549: except:
550: pass
551: try:
552: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
553: except:
554: pass
555: return docinfo
556:
557: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
558: """path ist the path to the images it assumes that the index.meta file is one level higher."""
559: logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))
560: if docinfo is None:
561: docinfo = {}
562: path=path.replace("/mpiwg/online","")
563: docinfo['imagePath'] = path
564: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
565:
566: pathorig=path
567: for x in range(cut):
568: path=getParentDir(path)
569: logging.error("PATH:"+path)
570: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
571: docinfo['imageURL'] = imageUrl
572:
573: #path ist the path to the images it assumes that the index.meta file is one level higher.
574: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
575: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
576: return docinfo
577:
578:
579: def getDocinfo(self, mode, url):
580: """returns docinfo depending on mode"""
581: logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))
582: # look for cached docinfo in session
583: if self.REQUEST.SESSION.has_key('docinfo'):
584: docinfo = self.REQUEST.SESSION['docinfo']
585: # check if its still current
586: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
587: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)
588: return docinfo
589: # new docinfo
590: docinfo = {'mode': mode, 'url': url}
591: if mode=="texttool": #index.meta with texttool information
592: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
593: elif mode=="imagepath":
594: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
595: elif mode=="filepath":
596: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
597: else:
598: logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
599: raise ValueError("Unknown mode %s"%(mode))
600:
601: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
602: self.REQUEST.SESSION['docinfo'] = docinfo
603: return docinfo
604:
605:
606: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None):
607: """returns pageinfo with the given parameters"""
608: pageinfo = {}
609: current = getInt(current)
610: pageinfo['current'] = current
611: rows = int(rows or self.thumbrows)
612: pageinfo['rows'] = rows
613: cols = int(cols or self.thumbcols)
614: pageinfo['cols'] = cols
615: grpsize = cols * rows
616: pageinfo['groupsize'] = grpsize
617: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
618: # int(current / grpsize) * grpsize +1))
619: pageinfo['start'] = start
620: pageinfo['end'] = start + grpsize
621: if docinfo is not None:
622:
623: np = int(docinfo['numPages'])
624: pageinfo['end'] = min(pageinfo['end'], np)
625: pageinfo['numgroups'] = int(np / grpsize)
626: if np % grpsize > 0:
627: pageinfo['numgroups'] += 1
628:
629: return pageinfo
630:
631: def text(self,mode,url,pn):
632: """give text"""
633: if mode=="texttool": #index.meta with texttool information
634: (viewerUrl,imagepath,textpath)=parseUrlTextTool(url)
635:
636: #print textpath
637: try:
638: dom = NonvalidatingReader.parseUri(textpath)
639: except:
640: return None
641:
642: list=[]
643: nodes=dom.xpath("//pb")
644:
645: node=nodes[int(pn)-1]
646:
647: p=node
648:
649: while p.tagName!="p":
650: p=p.parentNode
651:
652:
653: endNode=nodes[int(pn)]
654:
655:
656: e=endNode
657:
658: while e.tagName!="p":
659: e=e.parentNode
660:
661:
662: next=node.parentNode
663:
664: #sammle s
665: while next and (next!=endNode.parentNode):
666: list.append(next)
667: next=next.nextSibling
668: list.append(endNode.parentNode)
669:
670: if p==e:# beide im selben paragraphen
671: pass
672: # else:
673: # next=p
674: # while next!=e:
675: # print next,e
676: # list.append(next)
677: # next=next.nextSibling
678: #
679: # for x in list:
680: # PrettyPrint(x)
681: #
682: # return list
683: #
684:
685: def findDigilibUrl(self):
686: """try to get the digilib URL from zogilib"""
687: url = self.imageViewerUrl[:-1] + "/getScalerUrl"
688: #print urlparse.urlparse(url)[0]
689: #print urlparse.urljoin(self.absolute_url(),url)
690: logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0])
691: logging.info("finddigiliburl: %s"%urlparse.urljoin(self.absolute_url(),url))
692:
693: try:
694: if urlparse.urlparse(url)[0]=='': #relative path
695: url=urlparse.urljoin(self.absolute_url()+"/",url)
696:
697: scaler = urlopen(url).read()
698: return scaler.replace("/servlet/Scaler?", "")
699: except:
700: return None
701:
702: def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):
703: """init document viewer"""
704: self.title=title
705: self.imageViewerUrl=imageViewerUrl
706: self.textViewerUrl=textViewerUrl
707: self.digilibBaseUrl = digilibBaseUrl
708: self.thumbrows = thumbrows
709: self.thumbcols = thumbcols
710: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
711: if RESPONSE is not None:
712: RESPONSE.redirect('manage_main')
713:
714:
715:
716:
717: # security.declareProtected('View management screens','renameImageForm')
718:
719: def manage_AddDocumentViewerForm(self):
720: """add the viewer form"""
721: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
722: return pt()
723:
724: def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None):
725: """add the viewer"""
726: newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl)
727: self._setObject(id,newObj)
728:
729: if RESPONSE is not None:
730: RESPONSE.redirect('manage_main')
731:
732:
733: ##
734: ## DocumentViewerTemplate class
735: ##
736: class DocumentViewerTemplate(ZopePageTemplate):
737: """Template for document viewer"""
738: meta_type="DocumentViewer Template"
739:
740:
741: def manage_addDocumentViewerTemplateForm(self):
742: """Form for adding"""
743: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
744: return pt()
745:
746: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
747: REQUEST=None, submit=None):
748: "Add a Page Template with optional file content."
749:
750: self._setObject(id, DocumentViewerTemplate(id))
751: ob = getattr(self, id)
752: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
753: logging.info("txt %s:"%txt)
754: ob.pt_edit(txt,"text/html")
755: if title:
756: ob.pt_setTitle(title)
757: try:
758: u = self.DestinationURL()
759: except AttributeError:
760: u = REQUEST['URL1']
761:
762: u = "%s/%s" % (u, urllib.quote(id))
763: REQUEST.RESPONSE.redirect(u+'/manage_main')
764: return ''
765:
766:
767:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>