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