Annotation of documentViewer/documentViewer.py, revision 1.43
1.18 dwinter 1:
1.1 dwinter 2: from OFS.Folder import Folder
3: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
1.22 dwinter 4: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
1.1 dwinter 5: from AccessControl import ClassSecurityInfo
1.8 casties 6: from AccessControl import getSecurityManager
1.1 dwinter 7: from Globals import package_home
8:
9: from Ft.Xml.Domlette import NonvalidatingReader
10: from Ft.Xml.Domlette import PrettyPrint, Print
1.11 casties 11: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.1 dwinter 12:
1.42 abukhman 13:
1.1 dwinter 14: import Ft.Xml.XPath
1.43 ! casties 15: import cStringIO
1.42 abukhman 16: import xmlrpclib
1.1 dwinter 17: import os.path
1.7 casties 18: import sys
1.1 dwinter 19: import cgi
20: import urllib
1.20 dwinter 21: import logging
1.28 casties 22: import math
1.22 dwinter 23:
1.18 dwinter 24: import urlparse
1.37 dwinter 25: from types import *
1.43 ! casties 26:
1.22 dwinter 27: def logger(txt,method,txt2):
28: """logging"""
29: logging.info(txt+ txt2)
30:
31:
1.4 casties 32: def getInt(number, default=0):
33: """returns always an int (0 in case of problems)"""
34: try:
35: return int(number)
36: except:
1.29 casties 37: return int(default)
1.4 casties 38:
1.1 dwinter 39: def getTextFromNode(nodename):
1.18 dwinter 40: """get the cdata content of a node"""
1.8 casties 41: if nodename is None:
42: return ""
1.1 dwinter 43: nodelist=nodename.childNodes
44: rc = ""
45: for node in nodelist:
46: if node.nodeType == node.TEXT_NODE:
47: rc = rc + node.data
48: return rc
49:
1.43 ! casties 50: def serializeNode(node, encoding='utf-8'):
! 51: """returns a string containing node as XML"""
! 52: buf = cStringIO.StringIO()
! 53: Print(node, stream=buf, encoding=encoding)
! 54: s = buf.getvalue()
! 55: buf.close()
! 56: return s
! 57:
1.9 casties 58:
59: def getParentDir(path):
60: """returns pathname shortened by one"""
61: return '/'.join(path.split('/')[0:-1])
62:
63:
1.1 dwinter 64: import socket
65:
1.8 casties 66: def urlopen(url,timeout=2):
1.1 dwinter 67: """urlopen mit timeout"""
1.8 casties 68: socket.setdefaulttimeout(timeout)
1.1 dwinter 69: ret=urllib.urlopen(url)
70: socket.setdefaulttimeout(5)
71: return ret
72:
73:
1.3 casties 74: ##
75: ## documentViewer class
76: ##
77: class documentViewer(Folder):
1.1 dwinter 78: """document viewer"""
1.20 dwinter 79: #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"
1.18 dwinter 80:
1.1 dwinter 81: meta_type="Document viewer"
82:
83: security=ClassSecurityInfo()
1.3 casties 84: manage_options=Folder.manage_options+(
1.1 dwinter 85: {'label':'main config','action':'changeDocumentViewerForm'},
86: )
87:
1.3 casties 88: # templates and forms
89: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
90: thumbs_main = PageTemplateFile('zpt/thumbs_main', globals())
1.43 ! casties 91: image_main = PageTemplateFile('zpt/image_main', globals()) # obsolete!
! 92: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
! 93: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.3 casties 94: head_main = PageTemplateFile('zpt/head_main', globals())
95: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 96: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.3 casties 97:
1.32 dwinter 98: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 99: security.declareProtected('View management screens','changeDocumentViewerForm')
100: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
101:
1.1 dwinter 102:
1.43 ! casties 103: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):
1.1 dwinter 104: """init document viewer"""
105: self.id=id
106: self.title=title
1.4 casties 107: self.thumbcols = thumbcols
108: self.thumbrows = thumbrows
1.8 casties 109: # authgroups is list of authorized groups (delimited by ,)
110: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 ! casties 111: # create template folder so we can always use template.something
! 112:
! 113: templateFolder = Folder('template')
! 114: #self['template'] = templateFolder # Zope-2.12 style
! 115: self._setObject('template',templateFolder) # old style
! 116: try:
! 117: from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy
! 118: xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False)
! 119: #templateFolder['fulltextclient'] = xmlRpcClient
! 120: templateFolder._setObject('fulltextclient',xmlRpcClient)
! 121: except Exception, e:
! 122: logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e))
! 123: try:
! 124: from Products.zogiLib.zogiLib import zogiLib
! 125: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
! 126: #templateFolder['zogilib'] = zogilib
! 127: templateFolder._setObject('zogilib',zogilib)
! 128: except Exception, e:
! 129: logging.error("Unable to create zogiLib for zogilib: "+str(e))
! 130:
1.3 casties 131:
1.32 dwinter 132: security.declareProtected('View','thumbs_rss')
133: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
134: '''
135: view it
136: @param mode: defines how to access the document behind url
137: @param url: url which contains display information
138: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
139:
140: '''
1.43 ! casties 141: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.32 dwinter 142: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
143:
144: if not hasattr(self, 'template'):
145: # create template folder if it doesn't exist
146: self.manage_addFolder('template')
147:
148: if not self.digilibBaseUrl:
149: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
150:
151: docinfo = self.getDocinfo(mode=mode,url=url)
152: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
153: pt = getattr(self.template, 'thumbs_main_rss')
154:
155: if viewMode=="auto": # automodus gewaehlt
156: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
157: viewMode="text"
158: else:
159: viewMode="images"
160:
161: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
162:
1.3 casties 163: security.declareProtected('View','index_html')
1.43 ! casties 164: def index_html(self,url,mode="texttool",viewMode="auto",start=None,pn=1,mk=None):
1.3 casties 165: '''
166: view it
1.26 casties 167: @param mode: defines how to access the document behind url
1.3 casties 168: @param url: url which contains display information
1.26 casties 169: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
1.18 dwinter 170:
1.3 casties 171: '''
172:
1.43 ! casties 173: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 174:
1.3 casties 175: if not hasattr(self, 'template'):
1.43 ! casties 176: # this won't work
! 177: logging.error("template folder missing!")
! 178: return "ERROR: template folder missing!"
1.3 casties 179:
1.43 ! casties 180: if not getattr(self, 'digilibBaseUrl', None):
1.3 casties 181: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
182:
1.4 casties 183: docinfo = self.getDocinfo(mode=mode,url=url)
184: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.3 casties 185: pt = getattr(self.template, 'viewer_main')
1.21 dwinter 186:
187: if viewMode=="auto": # automodus gewaehlt
1.43 ! casties 188: if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
1.21 dwinter 189: viewMode="text"
190: else:
191: viewMode="images"
1.22 dwinter 192:
1.37 dwinter 193: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 194:
1.36 dwinter 195: def generateMarks(self,mk):
196: ret=""
1.37 dwinter 197: if mk is None:
198: return ""
199:
200: if type(mk) is not ListType:
201: mk=[mk]
1.36 dwinter 202: for m in mk:
1.37 dwinter 203: ret+="mk=%s"%m
1.36 dwinter 204: return ret
1.43 ! casties 205:
! 206: def findDigilibUrl(self):
! 207: """try to get the digilib URL from zogilib"""
! 208: url = self.template.zogilib.getDLBaseUrl()
! 209: return url
! 210:
! 211: def getStyle(self, idx, selected, style=""):
! 212: """returns a string with the given style and append 'sel' if path == selected."""
! 213: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
! 214: if idx == selected:
! 215: return style + 'sel'
! 216: else:
! 217: return style
1.36 dwinter 218:
1.4 casties 219: def getLink(self,param=None,val=None):
220: """link to documentviewer with parameter param set to val"""
1.9 casties 221: params=self.REQUEST.form.copy()
1.4 casties 222: if param is not None:
1.7 casties 223: if val is None:
224: if params.has_key(param):
225: del params[param]
1.4 casties 226: else:
1.9 casties 227: params[param] = str(val)
1.43 ! casties 228:
! 229: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 230: params["mode"] = "imagepath"
231: params["url"] = getParentDir(params["url"])
1.7 casties 232:
1.9 casties 233: # quote values and assemble into query string
234: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
235: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 236: return url
237:
1.32 dwinter 238: def getLinkAmp(self,param=None,val=None):
239: """link to documentviewer with parameter param set to val"""
240: params=self.REQUEST.form.copy()
241: if param is not None:
242: if val is None:
243: if params.has_key(param):
244: del params[param]
245: else:
246: params[param] = str(val)
247:
248: # quote values and assemble into query string
249: logging.info("XYXXXXX: %s"%repr(params.items()))
250: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
251: url=self.REQUEST['URL1']+"?"+ps
252: return url
1.40 casties 253:
1.26 casties 254: def getInfo_xml(self,url,mode):
255: """returns info about the document as XML"""
256:
257: if not self.digilibBaseUrl:
258: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
259:
260: docinfo = self.getDocinfo(mode=mode,url=url)
261: pt = getattr(self.template, 'info_xml')
262: return pt(docinfo=docinfo)
263:
1.4 casties 264:
1.9 casties 265: def isAccessible(self, docinfo):
1.8 casties 266: """returns if access to the resource is granted"""
267: access = docinfo.get('accessType', None)
1.22 dwinter 268: logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
1.17 casties 269: if access is not None and access == 'free':
1.22 dwinter 270: logger("documentViewer (accessOK)", logging.INFO, "access is free")
1.8 casties 271: return True
1.17 casties 272: elif access is None or access in self.authgroups:
1.9 casties 273: # only local access -- only logged in users
274: user = getSecurityManager().getUser()
275: if user is not None:
276: #print "user: ", user
277: return (user.getUserName() != "Anonymous User")
278: else:
279: return False
1.8 casties 280:
1.22 dwinter 281: logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
1.8 casties 282: return False
1.9 casties 283:
1.8 casties 284:
1.35 dwinter 285: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 286: """gibt param von dlInfo aus"""
1.13 casties 287: num_retries = 3
1.7 casties 288: if docinfo is None:
289: docinfo = {}
1.35 dwinter 290:
291: for x in range(cut):
1.38 dwinter 292:
1.35 dwinter 293: path=getParentDir(path)
1.38 dwinter 294:
1.13 casties 295: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 296:
1.22 dwinter 297: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
1.6 casties 298:
1.13 casties 299: for cnt in range(num_retries):
1.9 casties 300: try:
1.13 casties 301: # dom = NonvalidatingReader.parseUri(imageUrl)
302: txt=urllib.urlopen(infoUrl).read()
303: dom = Parse(txt)
1.9 casties 304: break
305: except:
1.22 dwinter 306: logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
1.9 casties 307: else:
1.13 casties 308: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.6 casties 309:
1.10 casties 310: sizes=dom.xpath("//dir/size")
1.22 dwinter 311: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
1.6 casties 312:
1.10 casties 313: if sizes:
314: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 315: else:
316: docinfo['numPages'] = 0
1.43 ! casties 317:
! 318: # TODO: produce and keep list of image names and numbers
1.7 casties 319:
320: return docinfo
1.8 casties 321:
1.6 casties 322:
1.9 casties 323: def getIndexMeta(self, url):
324: """returns dom of index.meta document at url"""
1.12 casties 325: num_retries = 3
1.9 casties 326: dom = None
1.12 casties 327: metaUrl = None
1.9 casties 328: if url.startswith("http://"):
329: # real URL
1.12 casties 330: metaUrl = url
1.9 casties 331: else:
332: # online path
333: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 334: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 335: if not metaUrl.endswith("index.meta"):
336: metaUrl += "/index.meta"
1.37 dwinter 337: logging.debug("METAURL: %s"%metaUrl)
1.13 casties 338: for cnt in range(num_retries):
1.9 casties 339: try:
1.12 casties 340: # patch dirk encoding fehler treten dann nicht mehr auf
1.11 casties 341: # dom = NonvalidatingReader.parseUri(metaUrl)
1.12 casties 342: txt=urllib.urlopen(metaUrl).read()
343: dom = Parse(txt)
1.13 casties 344: break
1.9 casties 345: except:
1.22 dwinter 346: logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.12 casties 347:
348: if dom is None:
349: raise IOError("Unable to read index meta from %s"%(url))
1.9 casties 350:
351: return dom
1.20 dwinter 352:
353: def getPresentationInfoXML(self, url):
354: """returns dom of info.xml document at url"""
355: num_retries = 3
356: dom = None
357: metaUrl = None
358: if url.startswith("http://"):
359: # real URL
360: metaUrl = url
361: else:
362: # online path
363: server=self.digilibBaseUrl+"/servlet/Texter?fn="
364: metaUrl=server+url.replace("/mpiwg/online","")
365:
366:
367: for cnt in range(num_retries):
368: try:
369: # patch dirk encoding fehler treten dann nicht mehr auf
370: # dom = NonvalidatingReader.parseUri(metaUrl)
371: txt=urllib.urlopen(metaUrl).read()
372: dom = Parse(txt)
373: break
374: except:
1.22 dwinter 375: logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.20 dwinter 376:
377: if dom is None:
378: raise IOError("Unable to read infoXMLfrom %s"%(url))
379:
380: return dom
1.9 casties 381:
382:
1.33 dwinter 383: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 384: """gets authorization info from the index.meta file at path or given by dom"""
1.22 dwinter 385: logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
1.8 casties 386:
387: access = None
388:
389: if docinfo is None:
390: docinfo = {}
391:
392: if dom is None:
1.38 dwinter 393: for x in range(cut):
1.33 dwinter 394: path=getParentDir(path)
395: dom = self.getIndexMeta(path)
1.18 dwinter 396:
1.8 casties 397: acctype = dom.xpath("//access-conditions/access/@type")
398: if acctype and (len(acctype)>0):
399: access=acctype[0].value
1.9 casties 400: if access in ['group', 'institution']:
1.8 casties 401: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
402:
403: docinfo['accessType'] = access
404: return docinfo
1.6 casties 405:
1.8 casties 406:
1.33 dwinter 407: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 408: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 409: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 410:
1.3 casties 411: if docinfo is None:
412: docinfo = {}
1.38 dwinter 413:
1.3 casties 414: if dom is None:
1.38 dwinter 415: for x in range(cut):
1.33 dwinter 416: path=getParentDir(path)
417: dom = self.getIndexMeta(path)
1.39 dwinter 418:
419: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 420: # put in all raw bib fields as dict "bib"
421: bib = dom.xpath("//bib/*")
422: if bib and len(bib)>0:
423: bibinfo = {}
424: for e in bib:
425: bibinfo[e.localName] = getTextFromNode(e)
426: docinfo['bib'] = bibinfo
427:
428: # extract some fields (author, title, year) according to their mapping
1.4 casties 429: metaData=self.metadata.main.meta.bib
430: bibtype=dom.xpath("//bib/@type")
431: if bibtype and (len(bibtype)>0):
432: bibtype=bibtype[0].value
1.2 dwinter 433: else:
1.4 casties 434: bibtype="generic"
1.27 casties 435:
1.4 casties 436: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 437: docinfo['bib_type'] = bibtype
1.4 casties 438: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 439: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 440: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 441: try:
442: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
443: except: pass
444: try:
445: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
446: except: pass
447: try:
448: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
449: except: pass
1.27 casties 450: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 451: try:
452: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
453: except:
454: docinfo['lang']=''
1.27 casties 455:
1.3 casties 456: return docinfo
1.42 abukhman 457:
458:
1.43 ! casties 459: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
! 460: """parse texttool tag in index meta"""
! 461: logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url))
! 462: if docinfo is None:
! 463: docinfo = {}
! 464:
! 465: if docinfo.get('lang', None) is None:
! 466: docinfo['lang'] = '' # default keine Sprache gesetzt
! 467: if dom is None:
! 468: dom = self.getIndexMeta(url)
! 469:
! 470: archivePath = None
! 471: archiveName = None
! 472:
! 473: archiveNames = dom.xpath("//resource/name")
! 474: if archiveNames and (len(archiveNames) > 0):
! 475: archiveName = getTextFromNode(archiveNames[0])
! 476: else:
! 477: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url))
! 478:
! 479: archivePaths = dom.xpath("//resource/archive-path")
! 480: if archivePaths and (len(archivePaths) > 0):
! 481: archivePath = getTextFromNode(archivePaths[0])
! 482: # clean up archive path
! 483: if archivePath[0] != '/':
! 484: archivePath = '/' + archivePath
! 485: if archiveName and (not archivePath.endswith(archiveName)):
! 486: archivePath += "/" + archiveName
! 487: else:
! 488: # try to get archive-path from url
! 489: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url))
! 490: if (not url.startswith('http')):
! 491: archivePath = url.replace('index.meta', '')
! 492:
! 493: if archivePath is None:
! 494: # we balk without archive-path
! 495: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
! 496:
! 497: imageDirs = dom.xpath("//texttool/image")
! 498: if imageDirs and (len(imageDirs) > 0):
! 499: imageDir = getTextFromNode(imageDirs[0])
! 500:
! 501: else:
! 502: # we balk with no image tag / not necessary anymore because textmode is now standard
! 503: #raise IOError("No text-tool info in %s"%(url))
! 504: imageDir = ""
! 505: #xquery="//pb"
! 506: docinfo['imagePath'] = "" # keine Bilder
! 507: docinfo['imageURL'] = ""
! 508:
! 509: if imageDir and archivePath:
! 510: #print "image: ", imageDir, " archivepath: ", archivePath
! 511: imageDir = os.path.join(archivePath, imageDir)
! 512: imageDir = imageDir.replace("/mpiwg/online", '')
! 513: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
! 514: docinfo['imagePath'] = imageDir
! 515:
! 516: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
! 517:
! 518: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
! 519: if viewerUrls and (len(viewerUrls) > 0):
! 520: viewerUrl = getTextFromNode(viewerUrls[0])
! 521: docinfo['viewerURL'] = viewerUrl
! 522:
! 523: textUrls = dom.xpath("//texttool/text")
! 524: if textUrls and (len(textUrls) > 0):
! 525: textUrl = getTextFromNode(textUrls[0])
! 526: if urlparse.urlparse(textUrl)[0] == "": #keine url
! 527: textUrl = os.path.join(archivePath, textUrl)
! 528: # fix URLs starting with /mpiwg/online
! 529: if textUrl.startswith("/mpiwg/online"):
! 530: textUrl = textUrl.replace("/mpiwg/online", '', 1)
! 531:
! 532: docinfo['textURL'] = textUrl
! 533:
! 534: textUrls = dom.xpath("//texttool/text-url-path")
! 535: if textUrls and (len(textUrls) > 0):
! 536: textUrl = getTextFromNode(textUrls[0])
! 537: docinfo['textURLPath'] = textUrl
! 538:
! 539: presentationUrls = dom.xpath("//texttool/presentation")
! 540: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
! 541:
! 542: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
! 543: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
! 544: # durch den relativen Pfad auf die presentation infos
! 545: presentationPath = getTextFromNode(presentationUrls[0])
! 546: if url.endswith("index.meta"):
! 547: presentationUrl = url.replace('index.meta', presentationPath)
! 548: else:
! 549: presentationUrl = url + "/" + presentationPath
! 550: docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
! 551: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
! 552:
! 553: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 554:
1.43 ! casties 555: return docinfo
! 556:
1.16 casties 557:
1.22 dwinter 558:
1.3 casties 559:
1.20 dwinter 560:
561: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
562: """gets the bibliographical information from the preseantion entry in texttools
563: """
564: dom=self.getPresentationInfoXML(url)
1.29 casties 565: try:
566: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
567: except:
568: pass
569: try:
570: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
571: except:
572: pass
573: try:
574: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
575: except:
576: pass
1.20 dwinter 577: return docinfo
578:
1.33 dwinter 579: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 580: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.22 dwinter 581: logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))
1.3 casties 582: if docinfo is None:
583: docinfo = {}
1.6 casties 584: path=path.replace("/mpiwg/online","")
1.3 casties 585: docinfo['imagePath'] = path
1.35 dwinter 586: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 587:
1.39 dwinter 588: pathorig=path
1.38 dwinter 589: for x in range(cut):
590: path=getParentDir(path)
591: logging.error("PATH:"+path)
1.7 casties 592: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 593: docinfo['imageURL'] = imageUrl
594:
1.39 dwinter 595: #path ist the path to the images it assumes that the index.meta file is one level higher.
596: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
597: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 598: return docinfo
599:
1.2 dwinter 600:
1.3 casties 601: def getDocinfo(self, mode, url):
602: """returns docinfo depending on mode"""
1.22 dwinter 603: logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))
1.3 casties 604: # look for cached docinfo in session
1.21 dwinter 605: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 606: docinfo = self.REQUEST.SESSION['docinfo']
607: # check if its still current
608: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.22 dwinter 609: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)
1.3 casties 610: return docinfo
611: # new docinfo
612: docinfo = {'mode': mode, 'url': url}
613: if mode=="texttool": #index.meta with texttool information
614: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
615: elif mode=="imagepath":
616: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 617: elif mode=="filepath":
1.37 dwinter 618: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 619: else:
1.22 dwinter 620: logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
1.10 casties 621: raise ValueError("Unknown mode %s"%(mode))
622:
1.22 dwinter 623: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
1.3 casties 624: self.REQUEST.SESSION['docinfo'] = docinfo
625: return docinfo
1.2 dwinter 626:
627:
1.4 casties 628: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None):
1.3 casties 629: """returns pageinfo with the given parameters"""
630: pageinfo = {}
1.4 casties 631: current = getInt(current)
632: pageinfo['current'] = current
633: rows = int(rows or self.thumbrows)
634: pageinfo['rows'] = rows
635: cols = int(cols or self.thumbcols)
636: pageinfo['cols'] = cols
637: grpsize = cols * rows
638: pageinfo['groupsize'] = grpsize
1.28 casties 639: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
640: # int(current / grpsize) * grpsize +1))
1.3 casties 641: pageinfo['start'] = start
1.4 casties 642: pageinfo['end'] = start + grpsize
643: if docinfo is not None:
644: np = int(docinfo['numPages'])
645: pageinfo['end'] = min(pageinfo['end'], np)
646: pageinfo['numgroups'] = int(np / grpsize)
647: if np % grpsize > 0:
648: pageinfo['numgroups'] += 1
1.38 dwinter 649:
1.3 casties 650: return pageinfo
651:
1.1 dwinter 652:
1.43 ! casties 653:
! 654: def getNumPages(self,docinfo=None):
! 655: """get list of pages from fulltext and put in docinfo"""
! 656: xquery = '//pb'
! 657: text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
! 658: # TODO: better processing of the page list. do we need the info somewhere else also?
! 659: docinfo['numPages'] = text.count("<pb ")
! 660: return docinfo
! 661:
! 662: def getTextPage(self, mode="text", pn=1, docinfo=None):
! 663: """returns single page from fulltext"""
! 664: pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'],mode,pn), outputUnicode=False)
! 665: # post-processing downloaded xml
! 666: pagedom = Parse(pagexml)
! 667: # plain text mode
! 668: if mode == "text":
! 669: # first div contains text
! 670: pagedivs = pagedom.xpath("/div")
! 671: if len(pagedivs) > 0:
! 672: pagenode = pagedivs[0]
! 673: return serializeNode(pagenode)
! 674:
! 675: # text-with-links mode
! 676: if mode == "textPollux":
! 677: # first div contains text
! 678: pagedivs = pagedom.xpath("/div")
! 679: if len(pagedivs) > 0:
! 680: pagenode = pagedivs[0]
! 681: # check all a-tags
! 682: links = pagenode.xpath("//a")
! 683: for l in links:
! 684: hrefNode = l.getAttributeNodeNS(None, u"href")
! 685: if hrefNode:
! 686: # is link with href
! 687: href = hrefNode.nodeValue
! 688: if href.startswith('lt/lex.xql'):
! 689: # is pollux link
! 690: selfurl = self.absolute_url()
! 691: # change href
! 692: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/head_main_voc'%selfurl)
! 693: # add target
! 694: l.setAttributeNS(None, 'target', '_blank')
! 695: return serializeNode(pagenode)
1.1 dwinter 696:
1.43 ! casties 697: return "no text here"
1.3 casties 698:
699:
1.43 ! casties 700: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):
1.3 casties 701: """init document viewer"""
702: self.title=title
703: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 704: self.thumbrows = thumbrows
705: self.thumbcols = thumbcols
1.8 casties 706: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 707: if RESPONSE is not None:
708: RESPONSE.redirect('manage_main')
1.1 dwinter 709:
710:
711:
712: def manage_AddDocumentViewerForm(self):
713: """add the viewer form"""
1.3 casties 714: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 715: return pt()
716:
1.43 ! casties 717: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 718: """add the viewer"""
1.43 ! casties 719: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 720: self._setObject(id,newObj)
721:
722: if RESPONSE is not None:
723: RESPONSE.redirect('manage_main')
1.3 casties 724:
725:
726: ##
727: ## DocumentViewerTemplate class
728: ##
729: class DocumentViewerTemplate(ZopePageTemplate):
730: """Template for document viewer"""
731: meta_type="DocumentViewer Template"
732:
733:
734: def manage_addDocumentViewerTemplateForm(self):
735: """Form for adding"""
736: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
737: return pt()
738:
739: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
740: REQUEST=None, submit=None):
741: "Add a Page Template with optional file content."
742:
743: self._setObject(id, DocumentViewerTemplate(id))
744: ob = getattr(self, id)
1.23 dwinter 745: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
746: logging.info("txt %s:"%txt)
747: ob.pt_edit(txt,"text/html")
1.3 casties 748: if title:
749: ob.pt_setTitle(title)
750: try:
751: u = self.DestinationURL()
752: except AttributeError:
753: u = REQUEST['URL1']
754:
755: u = "%s/%s" % (u, urllib.quote(id))
756: REQUEST.RESPONSE.redirect(u+'/manage_main')
757: return ''
758:
759:
1.14 casties 760:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>