Annotation of documentViewer/documentViewer.py, revision 1.11
1.1 dwinter 1: from OFS.Folder import Folder
2: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
3: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
4: from AccessControl import ClassSecurityInfo
1.8 casties 5: from AccessControl import getSecurityManager
1.1 dwinter 6: from Globals import package_home
7:
8: from Ft.Xml.Domlette import NonvalidatingReader
9: from Ft.Xml.Domlette import PrettyPrint, Print
1.11 ! casties 10: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.1 dwinter 11:
12: import Ft.Xml.XPath
13:
14: import os.path
1.7 casties 15: import sys
1.1 dwinter 16: import cgi
17: import urllib
1.3 casties 18: import zLOG
1.1 dwinter 19:
1.4 casties 20: def getInt(number, default=0):
21: """returns always an int (0 in case of problems)"""
22: try:
23: return int(number)
24: except:
25: return default
26:
1.1 dwinter 27: def getTextFromNode(nodename):
1.8 casties 28: if nodename is None:
29: return ""
1.1 dwinter 30: nodelist=nodename.childNodes
31: rc = ""
32: for node in nodelist:
33: if node.nodeType == node.TEXT_NODE:
34: rc = rc + node.data
35: return rc
36:
1.9 casties 37:
38: def getParentDir(path):
39: """returns pathname shortened by one"""
40: return '/'.join(path.split('/')[0:-1])
41:
42:
1.1 dwinter 43: import socket
44:
1.8 casties 45: def urlopen(url,timeout=2):
1.1 dwinter 46: """urlopen mit timeout"""
1.8 casties 47: socket.setdefaulttimeout(timeout)
1.1 dwinter 48: ret=urllib.urlopen(url)
49: socket.setdefaulttimeout(5)
50: return ret
51:
52:
1.3 casties 53: ##
54: ## documentViewer class
55: ##
56: class documentViewer(Folder):
1.1 dwinter 57: """document viewer"""
58:
59: meta_type="Document viewer"
60:
61: security=ClassSecurityInfo()
1.3 casties 62: manage_options=Folder.manage_options+(
1.1 dwinter 63: {'label':'main config','action':'changeDocumentViewerForm'},
64: )
65:
1.3 casties 66: # templates and forms
67: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
68: thumbs_main = PageTemplateFile('zpt/thumbs_main', globals())
69: image_main = PageTemplateFile('zpt/image_main', globals())
70: head_main = PageTemplateFile('zpt/head_main', globals())
71: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
72:
73: security.declareProtected('View management screens','changeDocumentViewerForm')
74: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
75:
1.1 dwinter 76:
1.8 casties 77: def __init__(self,id,imageViewerUrl,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):
1.1 dwinter 78: """init document viewer"""
79: self.id=id
80: self.title=title
81: self.imageViewerUrl=imageViewerUrl
1.4 casties 82: if not digilibBaseUrl:
1.3 casties 83: self.digilibBaseUrl = self.findDigilibUrl()
1.4 casties 84: else:
85: self.digilibBaseUrl = digilibBaseUrl
86: self.thumbcols = thumbcols
87: self.thumbrows = thumbrows
1.8 casties 88: # authgroups is list of authorized groups (delimited by ,)
89: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 90: # add template folder so we can always use template.something
91: self.manage_addFolder('template')
92:
93:
94: security.declareProtected('View','index_html')
1.4 casties 95: def index_html(self,mode,url,start=None,pn=1):
1.3 casties 96: '''
97: view it
98: @param mode: defines which type of document is behind url
99: @param url: url which contains display information
100: '''
101:
102: zLOG.LOG("documentViewer (index)", zLOG.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 103:
1.3 casties 104: if not hasattr(self, 'template'):
105: # create template folder if it doesn't exist
106: self.manage_addFolder('template')
107:
108: if not self.digilibBaseUrl:
109: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
110:
1.4 casties 111: docinfo = self.getDocinfo(mode=mode,url=url)
112: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.3 casties 113: pt = getattr(self.template, 'viewer_main')
114: return pt(docinfo=docinfo,pageinfo=pageinfo)
1.1 dwinter 115:
116:
1.4 casties 117: def getLink(self,param=None,val=None):
118: """link to documentviewer with parameter param set to val"""
1.9 casties 119: params=self.REQUEST.form.copy()
1.4 casties 120: if param is not None:
1.7 casties 121: if val is None:
122: if params.has_key(param):
123: del params[param]
1.4 casties 124: else:
1.9 casties 125: params[param] = str(val)
1.7 casties 126:
1.9 casties 127: # quote values and assemble into query string
128: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
129: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 130: return url
131:
132:
1.3 casties 133: def getStyle(self, idx, selected, style=""):
1.4 casties 134: """returns a string with the given style and append 'sel' if path == selected."""
1.3 casties 135: #zLOG.LOG("documentViewer (getstyle)", zLOG.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
136: if idx == selected:
137: return style + 'sel'
138: else:
1.9 casties 139: return style
140:
1.2 dwinter 141:
1.9 casties 142: def isAccessible(self, docinfo):
1.8 casties 143: """returns if access to the resource is granted"""
144: access = docinfo.get('accessType', None)
145: if access is None:
1.9 casties 146: # no information - no access
147: #TODO: check
1.8 casties 148: return True
149: elif access == 'free':
150: return True
1.9 casties 151: elif access in self.authgroups:
152: # only local access -- only logged in users
153: user = getSecurityManager().getUser()
154: if user is not None:
155: #print "user: ", user
156: return (user.getUserName() != "Anonymous User")
157: else:
158: return False
1.8 casties 159:
1.9 casties 160: zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "unknown access type %s"%access)
1.8 casties 161: return False
1.9 casties 162:
1.8 casties 163:
1.7 casties 164: def getDirinfoFromDigilib(self,path,docinfo=None):
1.6 casties 165: """gibt param von dlInfo aus"""
1.7 casties 166: if docinfo is None:
167: docinfo = {}
168:
1.6 casties 169: imageUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
170:
1.7 casties 171: zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(imageUrl))
1.6 casties 172:
1.9 casties 173: for cnt in (1,2,3):
174: try:
175: dom = NonvalidatingReader.parseUri(imageUrl)
176: break
177: except:
178: zLOG.LOG("documentViewer (getdirinfofromdigilib)", zLOG.ERROR, "error reading %s (try %d)"%(imageUrl,cnt))
179: else:
1.10 casties 180: raise IOError("Unable to get dir-info from %s"%(imageUrl))
1.6 casties 181:
1.10 casties 182: sizes=dom.xpath("//dir/size")
183: zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:size"%sizes)
1.6 casties 184:
1.10 casties 185: if sizes:
186: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 187: else:
188: docinfo['numPages'] = 0
189:
190: return docinfo
1.8 casties 191:
1.6 casties 192:
1.9 casties 193: def getIndexMeta(self, url):
194: """returns dom of index.meta document at url"""
195: dom = None
196: if url.startswith("http://"):
197: # real URL
198: try:
199: dom = NonvalidatingReader.parseUri(url)
200: except:
201: zLOG.LOG("documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.10 casties 202: raise IOError("Unable to read index.meta from %s"%(url))
1.9 casties 203: else:
204: # online path
205: server=self.digilibBaseUrl+"/servlet/Texter?fn="
206: metaUrl=server+url
207: if not metaUrl.endswith("index.meta"):
208: metaUrl += "/index.meta"
209: try:
1.11 ! casties 210: # patch dirk encoding fehler treten dann nicht mehr auf
! 211: # dom = NonvalidatingReader.parseUri(metaUrl)
! 212: txt=urllib.urlopen(metaUrl).read()
! 213: dom = Parse(txt)
1.9 casties 214: except:
215: zLOG.LOG("documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.11 ! casties 216: raise IOError("Unable to read index meta from %s"%(metaUrl))
1.9 casties 217:
218: return dom
219:
220:
1.8 casties 221: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None):
1.9 casties 222: """gets authorization info from the index.meta file at path or given by dom"""
1.10 casties 223: zLOG.LOG("documentViewer (getauthinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))
1.8 casties 224:
225: access = None
226:
227: if docinfo is None:
228: docinfo = {}
229:
230: if dom is None:
1.9 casties 231: dom = self.getIndexMeta(getParentDir(path))
1.8 casties 232:
233: acctype = dom.xpath("//access-conditions/access/@type")
234: if acctype and (len(acctype)>0):
235: access=acctype[0].value
1.9 casties 236: if access in ['group', 'institution']:
1.8 casties 237: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
238:
239: docinfo['accessType'] = access
240: return docinfo
1.6 casties 241:
1.8 casties 242:
1.3 casties 243: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None):
1.9 casties 244: """gets bibliographical info from the index.meta file at path or given by dom"""
1.3 casties 245: zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))
1.2 dwinter 246:
1.3 casties 247: if docinfo is None:
248: docinfo = {}
249:
250: if dom is None:
1.9 casties 251: dom = self.getIndexMeta(getParentDir(path))
252:
1.4 casties 253: metaData=self.metadata.main.meta.bib
254: bibtype=dom.xpath("//bib/@type")
255: if bibtype and (len(bibtype)>0):
256: bibtype=bibtype[0].value
1.2 dwinter 257: else:
1.4 casties 258: bibtype="generic"
259: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
260: bibmap=metaData.generateMappingForType(bibtype)
1.9 casties 261: #print "bibmap: ", bibmap, " for: ", bibtype
1.8 casties 262: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 263: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.4 casties 264: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
265: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
266: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
1.3 casties 267:
268: return docinfo
269:
270:
1.8 casties 271: def getDocinfoFromTextTool(self,url,dom=None,docinfo=None):
1.3 casties 272: """parse texttool tag in index meta"""
273: zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.INFO,"url: %s"%(url))
274: if docinfo is None:
275: docinfo = {}
276:
1.8 casties 277: if dom is None:
1.9 casties 278: dom = self.getIndexMeta(url)
1.8 casties 279:
280: archiveNames=dom.xpath("//resource/name")
281: if archiveNames and (len(archiveNames)>0):
282: archiveName=getTextFromNode(archiveNames[0])
1.3 casties 283:
284: archivePaths=dom.xpath("//resource/archive-path")
285: if archivePaths and (len(archivePaths)>0):
286: archivePath=getTextFromNode(archivePaths[0])
1.8 casties 287: # clean up archive path
288: if archivePath[0] != '/':
289: archivePath = '/' + archivePath
290: if not archivePath.endswith(archiveName):
291: archivePath += "/" + archiveName
1.3 casties 292: else:
293: archivePath=None
294:
1.9 casties 295: imageDirs=dom.xpath("//texttool/image")
296: if imageDirs and (len(imageDirs)>0):
297: imageDir=getTextFromNode(imageDirs[0])
1.3 casties 298: else:
1.10 casties 299: # we balk with no image tag
300: raise IOError("No text-tool info in %s"%(url))
1.3 casties 301:
1.9 casties 302: if imageDir and archivePath:
303: #print "image: ", imageDir, " archivepath: ", archivePath
304: imageDir=os.path.join(archivePath,imageDir)
305: imageDir=imageDir.replace("/mpiwg/online",'')
306: docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo)
307: docinfo['imagePath'] = imageDir
308: docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir
1.3 casties 309:
310: viewerUrls=dom.xpath("//texttool/digiliburlprefix")
311: if viewerUrls and (len(viewerUrls)>0):
312: viewerUrl=getTextFromNode(viewerUrls[0])
1.7 casties 313: docinfo['viewerURL'] = viewerUrl
1.3 casties 314:
315: textUrls=dom.xpath("//texttool/text")
316: if textUrls and (len(textUrls)>0):
317: textUrl=getTextFromNode(textUrls[0])
1.7 casties 318: docinfo['textURL'] = textUrl
1.3 casties 319:
320: docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)
1.8 casties 321: docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)
1.3 casties 322: return docinfo
323:
324:
325: def getDocinfoFromImagePath(self,path,docinfo=None):
326: """path ist the path to the images it assumes that the index.meta file is one level higher."""
327: zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path))
328: if docinfo is None:
329: docinfo = {}
1.6 casties 330: path=path.replace("/mpiwg/online","")
1.3 casties 331: docinfo['imagePath'] = path
1.7 casties 332: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo)
333: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 334: docinfo['imageURL'] = imageUrl
335:
336: docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo)
1.8 casties 337: docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo)
1.3 casties 338: return docinfo
339:
1.2 dwinter 340:
1.3 casties 341: def getDocinfo(self, mode, url):
342: """returns docinfo depending on mode"""
343: zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"mode: %s, url: %s"%(mode,url))
344: # look for cached docinfo in session
345: if self.REQUEST.SESSION.has_key('docinfo'):
346: docinfo = self.REQUEST.SESSION['docinfo']
347: # check if its still current
348: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
349: zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo in session: %s"%docinfo)
350: return docinfo
351: # new docinfo
352: docinfo = {'mode': mode, 'url': url}
353: if mode=="texttool": #index.meta with texttool information
354: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
355: elif mode=="imagepath":
356: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
357: else:
358: zLOG.LOG("documentViewer (getdocinfo)", zLOG.ERROR,"unknown mode!")
1.10 casties 359: raise ValueError("Unknown mode %s"%(mode))
360:
1.3 casties 361: zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo: %s"%docinfo)
362: self.REQUEST.SESSION['docinfo'] = docinfo
363: return docinfo
1.2 dwinter 364:
365:
1.4 casties 366: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None):
1.3 casties 367: """returns pageinfo with the given parameters"""
368: pageinfo = {}
1.4 casties 369: current = getInt(current)
370: pageinfo['current'] = current
371: rows = int(rows or self.thumbrows)
372: pageinfo['rows'] = rows
373: cols = int(cols or self.thumbcols)
374: pageinfo['cols'] = cols
375: grpsize = cols * rows
376: pageinfo['groupsize'] = grpsize
377: start = getInt(start, default=(int(current / grpsize) * grpsize +1))
1.3 casties 378: pageinfo['start'] = start
1.4 casties 379: pageinfo['end'] = start + grpsize
380: if docinfo is not None:
381: np = int(docinfo['numPages'])
382: pageinfo['end'] = min(pageinfo['end'], np)
383: pageinfo['numgroups'] = int(np / grpsize)
384: if np % grpsize > 0:
385: pageinfo['numgroups'] += 1
386:
1.3 casties 387: return pageinfo
388:
1.1 dwinter 389: def text(self,mode,url,pn):
390: """give text"""
391: if mode=="texttool": #index.meta with texttool information
392: (viewerUrl,imagepath,textpath)=parseUrlTextTool(url)
393:
1.9 casties 394: #print textpath
1.1 dwinter 395: try:
396: dom = NonvalidatingReader.parseUri(textpath)
397: except:
398: return None
399:
400: list=[]
401: nodes=dom.xpath("//pb")
402:
403: node=nodes[int(pn)-1]
404:
405: p=node
406:
407: while p.tagName!="p":
408: p=p.parentNode
409:
410:
411: endNode=nodes[int(pn)]
412:
413:
414: e=endNode
415:
416: while e.tagName!="p":
417: e=e.parentNode
418:
419:
420: next=node.parentNode
421:
422: #sammle s
423: while next and (next!=endNode.parentNode):
424: list.append(next)
425: next=next.nextSibling
426: list.append(endNode.parentNode)
427:
428: if p==e:# beide im selben paragraphen
1.2 dwinter 429: pass
430: # else:
431: # next=p
432: # while next!=e:
433: # print next,e
434: # list.append(next)
435: # next=next.nextSibling
436: #
437: # for x in list:
438: # PrettyPrint(x)
439: #
440: # return list
1.3 casties 441: #
442:
443: def findDigilibUrl(self):
444: """try to get the digilib URL from zogilib"""
445: url = self.imageViewerUrl[:-1] + "/getScalerUrl"
446: try:
447: scaler = urlopen(url).read()
448: return scaler.replace("/servlet/Scaler?", "")
449: except:
450: return None
451:
1.8 casties 452: def changeDocumentViewer(self,imageViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):
1.3 casties 453: """init document viewer"""
454: self.title=title
455: self.imageViewerUrl=imageViewerUrl
456: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 457: self.thumbrows = thumbrows
458: self.thumbcols = thumbcols
1.8 casties 459: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 460: if RESPONSE is not None:
461: RESPONSE.redirect('manage_main')
1.1 dwinter 462:
463:
464:
465:
466: # security.declareProtected('View management screens','renameImageForm')
467:
468: def manage_AddDocumentViewerForm(self):
469: """add the viewer form"""
1.3 casties 470: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 471: return pt()
472:
473: def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None):
474: """add the viewer"""
475: newObj=documentViewer(id,imageViewerUrl,title)
476: self._setObject(id,newObj)
477:
478: if RESPONSE is not None:
479: RESPONSE.redirect('manage_main')
1.3 casties 480:
481:
482: ##
483: ## DocumentViewerTemplate class
484: ##
485: class DocumentViewerTemplate(ZopePageTemplate):
486: """Template for document viewer"""
487: meta_type="DocumentViewer Template"
488:
489:
490: def manage_addDocumentViewerTemplateForm(self):
491: """Form for adding"""
492: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
493: return pt()
494:
495: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
496: REQUEST=None, submit=None):
497: "Add a Page Template with optional file content."
498:
499: self._setObject(id, DocumentViewerTemplate(id))
500: ob = getattr(self, id)
501: ob.pt_edit(open(os.path.join(package_home(globals()),'zpt/viewer_main.zpt')).read(),None)
502: if title:
503: ob.pt_setTitle(title)
504: try:
505: u = self.DestinationURL()
506: except AttributeError:
507: u = REQUEST['URL1']
508:
509: u = "%s/%s" % (u, urllib.quote(id))
510: REQUEST.RESPONSE.redirect(u+'/manage_main')
511: return ''
512:
513:
1.1 dwinter 514:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>