Annotation of documentViewer/documentViewer.py, revision 1.16
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)
1.14 casties 145: zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "access type %s"%access)
1.8 casties 146: if access is None:
1.9 casties 147: # no information - no access
1.15 casties 148: return False
1.8 casties 149: elif access == 'free':
1.15 casties 150: zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "access is free")
1.8 casties 151: return True
1.9 casties 152: elif access in self.authgroups:
153: # only local access -- only logged in users
154: user = getSecurityManager().getUser()
155: if user is not None:
156: #print "user: ", user
157: return (user.getUserName() != "Anonymous User")
158: else:
159: return False
1.8 casties 160:
1.9 casties 161: zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "unknown access type %s"%access)
1.8 casties 162: return False
1.9 casties 163:
1.8 casties 164:
1.7 casties 165: def getDirinfoFromDigilib(self,path,docinfo=None):
1.6 casties 166: """gibt param von dlInfo aus"""
1.13 casties 167: num_retries = 3
1.7 casties 168: if docinfo is None:
169: docinfo = {}
170:
1.13 casties 171: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 172:
1.13 casties 173: zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(infoUrl))
1.6 casties 174:
1.13 casties 175: for cnt in range(num_retries):
1.9 casties 176: try:
1.13 casties 177: # dom = NonvalidatingReader.parseUri(imageUrl)
178: txt=urllib.urlopen(infoUrl).read()
179: dom = Parse(txt)
1.9 casties 180: break
181: except:
1.13 casties 182: zLOG.LOG("documentViewer (getdirinfofromdigilib)", zLOG.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
1.9 casties 183: else:
1.13 casties 184: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.6 casties 185:
1.10 casties 186: sizes=dom.xpath("//dir/size")
187: zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:size"%sizes)
1.6 casties 188:
1.10 casties 189: if sizes:
190: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 191: else:
192: docinfo['numPages'] = 0
193:
194: return docinfo
1.8 casties 195:
1.6 casties 196:
1.9 casties 197: def getIndexMeta(self, url):
198: """returns dom of index.meta document at url"""
1.12 casties 199: num_retries = 3
1.9 casties 200: dom = None
1.12 casties 201: metaUrl = None
1.9 casties 202: if url.startswith("http://"):
203: # real URL
1.12 casties 204: metaUrl = url
1.9 casties 205: else:
206: # online path
207: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 208: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 209: if not metaUrl.endswith("index.meta"):
210: metaUrl += "/index.meta"
1.12 casties 211:
1.13 casties 212: for cnt in range(num_retries):
1.9 casties 213: try:
1.12 casties 214: # patch dirk encoding fehler treten dann nicht mehr auf
1.11 casties 215: # dom = NonvalidatingReader.parseUri(metaUrl)
1.12 casties 216: txt=urllib.urlopen(metaUrl).read()
217: dom = Parse(txt)
1.13 casties 218: break
1.9 casties 219: except:
1.12 casties 220: zLOG.LOG("ERROR documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])
221:
222: if dom is None:
223: raise IOError("Unable to read index meta from %s"%(url))
1.9 casties 224:
225: return dom
226:
227:
1.8 casties 228: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None):
1.9 casties 229: """gets authorization info from the index.meta file at path or given by dom"""
1.10 casties 230: zLOG.LOG("documentViewer (getauthinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))
1.8 casties 231:
232: access = None
233:
234: if docinfo is None:
235: docinfo = {}
236:
237: if dom is None:
1.9 casties 238: dom = self.getIndexMeta(getParentDir(path))
1.8 casties 239:
240: acctype = dom.xpath("//access-conditions/access/@type")
241: if acctype and (len(acctype)>0):
242: access=acctype[0].value
1.9 casties 243: if access in ['group', 'institution']:
1.8 casties 244: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
245:
246: docinfo['accessType'] = access
247: return docinfo
1.6 casties 248:
1.8 casties 249:
1.3 casties 250: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None):
1.9 casties 251: """gets bibliographical info from the index.meta file at path or given by dom"""
1.3 casties 252: zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))
1.2 dwinter 253:
1.3 casties 254: if docinfo is None:
255: docinfo = {}
256:
257: if dom is None:
1.9 casties 258: dom = self.getIndexMeta(getParentDir(path))
259:
1.4 casties 260: metaData=self.metadata.main.meta.bib
261: bibtype=dom.xpath("//bib/@type")
262: if bibtype and (len(bibtype)>0):
263: bibtype=bibtype[0].value
1.2 dwinter 264: else:
1.4 casties 265: bibtype="generic"
266: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
267: bibmap=metaData.generateMappingForType(bibtype)
1.9 casties 268: #print "bibmap: ", bibmap, " for: ", bibtype
1.8 casties 269: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 270: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.4 casties 271: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
272: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
273: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
1.3 casties 274:
275: return docinfo
276:
277:
1.8 casties 278: def getDocinfoFromTextTool(self,url,dom=None,docinfo=None):
1.3 casties 279: """parse texttool tag in index meta"""
280: zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.INFO,"url: %s"%(url))
281: if docinfo is None:
282: docinfo = {}
283:
1.8 casties 284: if dom is None:
1.9 casties 285: dom = self.getIndexMeta(url)
1.8 casties 286:
1.16 ! casties 287: archivePath = None
! 288: archiveName = None
! 289:
1.8 casties 290: archiveNames=dom.xpath("//resource/name")
291: if archiveNames and (len(archiveNames)>0):
292: archiveName=getTextFromNode(archiveNames[0])
1.16 ! casties 293: else:
! 294: zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.WARNING,"resource/name missing in: %s"%(url))
1.3 casties 295:
296: archivePaths=dom.xpath("//resource/archive-path")
297: if archivePaths and (len(archivePaths)>0):
298: archivePath=getTextFromNode(archivePaths[0])
1.8 casties 299: # clean up archive path
300: if archivePath[0] != '/':
301: archivePath = '/' + archivePath
1.16 ! casties 302: if archiveName and (not archivePath.endswith(archiveName)):
1.8 casties 303: archivePath += "/" + archiveName
1.3 casties 304: else:
1.16 ! casties 305: # try to get archive-path from url
! 306: zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.WARNING,"resource/archive-path missing in: %s"%(url))
! 307: if (not url.startswith('http')):
! 308: archivePath = url.replace('index.meta', '')
! 309:
! 310: if archivePath is None:
! 311: # we balk without archive-path
! 312: raise IOError("Missing archive-path (for text-tool) in %s"%(url))
1.3 casties 313:
1.9 casties 314: imageDirs=dom.xpath("//texttool/image")
315: if imageDirs and (len(imageDirs)>0):
316: imageDir=getTextFromNode(imageDirs[0])
1.3 casties 317: else:
1.10 casties 318: # we balk with no image tag
319: raise IOError("No text-tool info in %s"%(url))
1.3 casties 320:
1.9 casties 321: if imageDir and archivePath:
322: #print "image: ", imageDir, " archivepath: ", archivePath
323: imageDir=os.path.join(archivePath,imageDir)
324: imageDir=imageDir.replace("/mpiwg/online",'')
325: docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo)
326: docinfo['imagePath'] = imageDir
327: docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir
1.3 casties 328:
329: viewerUrls=dom.xpath("//texttool/digiliburlprefix")
330: if viewerUrls and (len(viewerUrls)>0):
331: viewerUrl=getTextFromNode(viewerUrls[0])
1.7 casties 332: docinfo['viewerURL'] = viewerUrl
1.3 casties 333:
334: textUrls=dom.xpath("//texttool/text")
335: if textUrls and (len(textUrls)>0):
336: textUrl=getTextFromNode(textUrls[0])
1.7 casties 337: docinfo['textURL'] = textUrl
1.3 casties 338:
339: docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)
1.8 casties 340: docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)
1.3 casties 341: return docinfo
342:
343:
344: def getDocinfoFromImagePath(self,path,docinfo=None):
345: """path ist the path to the images it assumes that the index.meta file is one level higher."""
346: zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path))
347: if docinfo is None:
348: docinfo = {}
1.6 casties 349: path=path.replace("/mpiwg/online","")
1.3 casties 350: docinfo['imagePath'] = path
1.7 casties 351: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo)
352: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 353: docinfo['imageURL'] = imageUrl
354:
355: docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo)
1.8 casties 356: docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo)
1.3 casties 357: return docinfo
358:
1.2 dwinter 359:
1.3 casties 360: def getDocinfo(self, mode, url):
361: """returns docinfo depending on mode"""
362: zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"mode: %s, url: %s"%(mode,url))
363: # look for cached docinfo in session
364: if self.REQUEST.SESSION.has_key('docinfo'):
365: docinfo = self.REQUEST.SESSION['docinfo']
366: # check if its still current
367: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
368: zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo in session: %s"%docinfo)
369: return docinfo
370: # new docinfo
371: docinfo = {'mode': mode, 'url': url}
372: if mode=="texttool": #index.meta with texttool information
373: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
374: elif mode=="imagepath":
375: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
376: else:
377: zLOG.LOG("documentViewer (getdocinfo)", zLOG.ERROR,"unknown mode!")
1.10 casties 378: raise ValueError("Unknown mode %s"%(mode))
379:
1.3 casties 380: zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo: %s"%docinfo)
381: self.REQUEST.SESSION['docinfo'] = docinfo
382: return docinfo
1.2 dwinter 383:
384:
1.4 casties 385: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None):
1.3 casties 386: """returns pageinfo with the given parameters"""
387: pageinfo = {}
1.4 casties 388: current = getInt(current)
389: pageinfo['current'] = current
390: rows = int(rows or self.thumbrows)
391: pageinfo['rows'] = rows
392: cols = int(cols or self.thumbcols)
393: pageinfo['cols'] = cols
394: grpsize = cols * rows
395: pageinfo['groupsize'] = grpsize
396: start = getInt(start, default=(int(current / grpsize) * grpsize +1))
1.3 casties 397: pageinfo['start'] = start
1.4 casties 398: pageinfo['end'] = start + grpsize
399: if docinfo is not None:
400: np = int(docinfo['numPages'])
401: pageinfo['end'] = min(pageinfo['end'], np)
402: pageinfo['numgroups'] = int(np / grpsize)
403: if np % grpsize > 0:
404: pageinfo['numgroups'] += 1
405:
1.3 casties 406: return pageinfo
407:
1.1 dwinter 408: def text(self,mode,url,pn):
409: """give text"""
410: if mode=="texttool": #index.meta with texttool information
411: (viewerUrl,imagepath,textpath)=parseUrlTextTool(url)
412:
1.9 casties 413: #print textpath
1.1 dwinter 414: try:
415: dom = NonvalidatingReader.parseUri(textpath)
416: except:
417: return None
418:
419: list=[]
420: nodes=dom.xpath("//pb")
421:
422: node=nodes[int(pn)-1]
423:
424: p=node
425:
426: while p.tagName!="p":
427: p=p.parentNode
428:
429:
430: endNode=nodes[int(pn)]
431:
432:
433: e=endNode
434:
435: while e.tagName!="p":
436: e=e.parentNode
437:
438:
439: next=node.parentNode
440:
441: #sammle s
442: while next and (next!=endNode.parentNode):
443: list.append(next)
444: next=next.nextSibling
445: list.append(endNode.parentNode)
446:
447: if p==e:# beide im selben paragraphen
1.2 dwinter 448: pass
449: # else:
450: # next=p
451: # while next!=e:
452: # print next,e
453: # list.append(next)
454: # next=next.nextSibling
455: #
456: # for x in list:
457: # PrettyPrint(x)
458: #
459: # return list
1.3 casties 460: #
461:
462: def findDigilibUrl(self):
463: """try to get the digilib URL from zogilib"""
464: url = self.imageViewerUrl[:-1] + "/getScalerUrl"
465: try:
466: scaler = urlopen(url).read()
467: return scaler.replace("/servlet/Scaler?", "")
468: except:
469: return None
470:
1.8 casties 471: def changeDocumentViewer(self,imageViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):
1.3 casties 472: """init document viewer"""
473: self.title=title
474: self.imageViewerUrl=imageViewerUrl
475: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 476: self.thumbrows = thumbrows
477: self.thumbcols = thumbcols
1.8 casties 478: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 479: if RESPONSE is not None:
480: RESPONSE.redirect('manage_main')
1.1 dwinter 481:
482:
483:
484:
485: # security.declareProtected('View management screens','renameImageForm')
486:
487: def manage_AddDocumentViewerForm(self):
488: """add the viewer form"""
1.3 casties 489: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 490: return pt()
491:
492: def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None):
493: """add the viewer"""
494: newObj=documentViewer(id,imageViewerUrl,title)
495: self._setObject(id,newObj)
496:
497: if RESPONSE is not None:
498: RESPONSE.redirect('manage_main')
1.3 casties 499:
500:
501: ##
502: ## DocumentViewerTemplate class
503: ##
504: class DocumentViewerTemplate(ZopePageTemplate):
505: """Template for document viewer"""
506: meta_type="DocumentViewer Template"
507:
508:
509: def manage_addDocumentViewerTemplateForm(self):
510: """Form for adding"""
511: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
512: return pt()
513:
514: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
515: REQUEST=None, submit=None):
516: "Add a Page Template with optional file content."
517:
518: self._setObject(id, DocumentViewerTemplate(id))
519: ob = getattr(self, id)
520: ob.pt_edit(open(os.path.join(package_home(globals()),'zpt/viewer_main.zpt')).read(),None)
521: if title:
522: ob.pt_setTitle(title)
523: try:
524: u = self.DestinationURL()
525: except AttributeError:
526: u = REQUEST['URL1']
527:
528: u = "%s/%s" % (u, urllib.quote(id))
529: REQUEST.RESPONSE.redirect(u+'/manage_main')
530: return ''
531:
532:
1.14 casties 533:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/cvs/cvsweb/icons/back.gif){kind=icon}
Return to documentViewer.py CVS log ![[TXT]](/cvs/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvs/cvsweb/icons/dir.gif){kind=icon}
Up to [Repository] / documentViewer