Annotation of documentViewer/documentViewer.py, revision 1.44
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())
1.44 ! casties 90: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
! 91: toc_text = PageTemplateFile('zpt/toc_text', globals())
! 92: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 93: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
94: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 ! casties 95: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.3 casties 96: head_main = PageTemplateFile('zpt/head_main', globals())
97: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 98: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.3 casties 99:
1.32 dwinter 100: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 101: security.declareProtected('View management screens','changeDocumentViewerForm')
102: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
103:
1.1 dwinter 104:
1.43 casties 105: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):
1.1 dwinter 106: """init document viewer"""
107: self.id=id
108: self.title=title
1.4 casties 109: self.thumbcols = thumbcols
110: self.thumbrows = thumbrows
1.8 casties 111: # authgroups is list of authorized groups (delimited by ,)
112: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 113: # create template folder so we can always use template.something
114:
115: templateFolder = Folder('template')
116: #self['template'] = templateFolder # Zope-2.12 style
117: self._setObject('template',templateFolder) # old style
118: try:
119: from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy
120: xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False)
121: #templateFolder['fulltextclient'] = xmlRpcClient
122: templateFolder._setObject('fulltextclient',xmlRpcClient)
123: except Exception, e:
124: logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e))
125: try:
126: from Products.zogiLib.zogiLib import zogiLib
127: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
128: #templateFolder['zogilib'] = zogilib
129: templateFolder._setObject('zogilib',zogilib)
130: except Exception, e:
131: logging.error("Unable to create zogiLib for zogilib: "+str(e))
132:
1.3 casties 133:
1.32 dwinter 134: security.declareProtected('View','thumbs_rss')
135: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
136: '''
137: view it
138: @param mode: defines how to access the document behind url
139: @param url: url which contains display information
140: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
141:
142: '''
1.43 casties 143: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.32 dwinter 144: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
145:
146: if not hasattr(self, 'template'):
147: # create template folder if it doesn't exist
148: self.manage_addFolder('template')
149:
150: if not self.digilibBaseUrl:
151: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
152:
153: docinfo = self.getDocinfo(mode=mode,url=url)
154: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
155: pt = getattr(self.template, 'thumbs_main_rss')
156:
157: if viewMode=="auto": # automodus gewaehlt
158: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
159: viewMode="text"
160: else:
161: viewMode="images"
162:
163: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
164:
1.3 casties 165: security.declareProtected('View','index_html')
1.44 ! casties 166: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
1.3 casties 167: '''
168: view it
1.26 casties 169: @param mode: defines how to access the document behind url
1.3 casties 170: @param url: url which contains display information
1.44 ! casties 171: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
! 172: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures)
1.3 casties 173: '''
174:
1.43 casties 175: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 176:
1.3 casties 177: if not hasattr(self, 'template'):
1.43 casties 178: # this won't work
179: logging.error("template folder missing!")
180: return "ERROR: template folder missing!"
1.3 casties 181:
1.43 casties 182: if not getattr(self, 'digilibBaseUrl', None):
1.3 casties 183: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
184:
1.4 casties 185: docinfo = self.getDocinfo(mode=mode,url=url)
1.44 ! casties 186: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
! 187: if tocMode != "thumbs":
! 188: # get table of contents
! 189: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
! 190:
1.21 dwinter 191: if viewMode=="auto": # automodus gewaehlt
1.43 casties 192: if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
1.21 dwinter 193: viewMode="text"
194: else:
195: viewMode="images"
1.44 ! casties 196:
! 197: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 198: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 199:
1.36 dwinter 200: def generateMarks(self,mk):
201: ret=""
1.44 ! casties 202: if mk is None:
! 203: return ""
! 204: if type(mk) is not ListType:
! 205: mk=[mk]
1.36 dwinter 206: for m in mk:
1.37 dwinter 207: ret+="mk=%s"%m
1.36 dwinter 208: return ret
1.43 casties 209:
1.44 ! casties 210:
1.43 casties 211: def findDigilibUrl(self):
212: """try to get the digilib URL from zogilib"""
213: url = self.template.zogilib.getDLBaseUrl()
214: return url
215:
216: def getStyle(self, idx, selected, style=""):
217: """returns a string with the given style and append 'sel' if path == selected."""
218: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
219: if idx == selected:
220: return style + 'sel'
221: else:
222: return style
1.36 dwinter 223:
1.4 casties 224: def getLink(self,param=None,val=None):
225: """link to documentviewer with parameter param set to val"""
1.9 casties 226: params=self.REQUEST.form.copy()
1.4 casties 227: if param is not None:
1.7 casties 228: if val is None:
229: if params.has_key(param):
230: del params[param]
1.4 casties 231: else:
1.9 casties 232: params[param] = str(val)
1.43 casties 233:
234: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 235: params["mode"] = "imagepath"
236: params["url"] = getParentDir(params["url"])
1.7 casties 237:
1.9 casties 238: # quote values and assemble into query string
239: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
240: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 241: return url
242:
1.32 dwinter 243: def getLinkAmp(self,param=None,val=None):
244: """link to documentviewer with parameter param set to val"""
245: params=self.REQUEST.form.copy()
246: if param is not None:
247: if val is None:
248: if params.has_key(param):
249: del params[param]
250: else:
251: params[param] = str(val)
252:
253: # quote values and assemble into query string
254: logging.info("XYXXXXX: %s"%repr(params.items()))
255: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
256: url=self.REQUEST['URL1']+"?"+ps
257: return url
1.40 casties 258:
1.26 casties 259: def getInfo_xml(self,url,mode):
260: """returns info about the document as XML"""
261:
262: if not self.digilibBaseUrl:
263: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
264:
265: docinfo = self.getDocinfo(mode=mode,url=url)
266: pt = getattr(self.template, 'info_xml')
267: return pt(docinfo=docinfo)
268:
1.4 casties 269:
1.9 casties 270: def isAccessible(self, docinfo):
1.8 casties 271: """returns if access to the resource is granted"""
272: access = docinfo.get('accessType', None)
1.22 dwinter 273: logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
1.17 casties 274: if access is not None and access == 'free':
1.22 dwinter 275: logger("documentViewer (accessOK)", logging.INFO, "access is free")
1.8 casties 276: return True
1.17 casties 277: elif access is None or access in self.authgroups:
1.9 casties 278: # only local access -- only logged in users
279: user = getSecurityManager().getUser()
280: if user is not None:
281: #print "user: ", user
282: return (user.getUserName() != "Anonymous User")
283: else:
284: return False
1.8 casties 285:
1.22 dwinter 286: logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
1.8 casties 287: return False
1.9 casties 288:
1.8 casties 289:
1.35 dwinter 290: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 291: """gibt param von dlInfo aus"""
1.13 casties 292: num_retries = 3
1.7 casties 293: if docinfo is None:
294: docinfo = {}
1.35 dwinter 295:
296: for x in range(cut):
1.38 dwinter 297:
1.35 dwinter 298: path=getParentDir(path)
1.38 dwinter 299:
1.13 casties 300: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 301:
1.22 dwinter 302: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
1.6 casties 303:
1.13 casties 304: for cnt in range(num_retries):
1.9 casties 305: try:
1.13 casties 306: # dom = NonvalidatingReader.parseUri(imageUrl)
307: txt=urllib.urlopen(infoUrl).read()
308: dom = Parse(txt)
1.9 casties 309: break
310: except:
1.22 dwinter 311: logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
1.9 casties 312: else:
1.13 casties 313: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.6 casties 314:
1.10 casties 315: sizes=dom.xpath("//dir/size")
1.22 dwinter 316: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
1.6 casties 317:
1.10 casties 318: if sizes:
319: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 320: else:
321: docinfo['numPages'] = 0
1.43 casties 322:
323: # TODO: produce and keep list of image names and numbers
1.7 casties 324:
325: return docinfo
1.8 casties 326:
1.6 casties 327:
1.9 casties 328: def getIndexMeta(self, url):
329: """returns dom of index.meta document at url"""
1.12 casties 330: num_retries = 3
1.9 casties 331: dom = None
1.12 casties 332: metaUrl = None
1.9 casties 333: if url.startswith("http://"):
334: # real URL
1.12 casties 335: metaUrl = url
1.9 casties 336: else:
337: # online path
338: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 339: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 340: if not metaUrl.endswith("index.meta"):
341: metaUrl += "/index.meta"
1.37 dwinter 342: logging.debug("METAURL: %s"%metaUrl)
1.13 casties 343: for cnt in range(num_retries):
1.9 casties 344: try:
1.12 casties 345: # patch dirk encoding fehler treten dann nicht mehr auf
1.11 casties 346: # dom = NonvalidatingReader.parseUri(metaUrl)
1.12 casties 347: txt=urllib.urlopen(metaUrl).read()
348: dom = Parse(txt)
1.13 casties 349: break
1.9 casties 350: except:
1.44 ! casties 351: logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.12 casties 352:
353: if dom is None:
354: raise IOError("Unable to read index meta from %s"%(url))
1.9 casties 355:
356: return dom
1.20 dwinter 357:
358: def getPresentationInfoXML(self, url):
359: """returns dom of info.xml document at url"""
360: num_retries = 3
361: dom = None
362: metaUrl = None
363: if url.startswith("http://"):
364: # real URL
365: metaUrl = url
366: else:
367: # online path
368: server=self.digilibBaseUrl+"/servlet/Texter?fn="
369: metaUrl=server+url.replace("/mpiwg/online","")
370:
371: for cnt in range(num_retries):
372: try:
373: # patch dirk encoding fehler treten dann nicht mehr auf
374: # dom = NonvalidatingReader.parseUri(metaUrl)
375: txt=urllib.urlopen(metaUrl).read()
376: dom = Parse(txt)
377: break
378: except:
1.22 dwinter 379: logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.20 dwinter 380:
381: if dom is None:
382: raise IOError("Unable to read infoXMLfrom %s"%(url))
383:
384: return dom
1.9 casties 385:
386:
1.33 dwinter 387: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 388: """gets authorization info from the index.meta file at path or given by dom"""
1.22 dwinter 389: logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
1.8 casties 390:
391: access = None
392:
393: if docinfo is None:
394: docinfo = {}
395:
396: if dom is None:
1.38 dwinter 397: for x in range(cut):
1.33 dwinter 398: path=getParentDir(path)
399: dom = self.getIndexMeta(path)
1.18 dwinter 400:
1.8 casties 401: acctype = dom.xpath("//access-conditions/access/@type")
402: if acctype and (len(acctype)>0):
403: access=acctype[0].value
1.9 casties 404: if access in ['group', 'institution']:
1.8 casties 405: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
406:
407: docinfo['accessType'] = access
408: return docinfo
1.6 casties 409:
1.8 casties 410:
1.33 dwinter 411: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 412: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 413: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 414:
1.3 casties 415: if docinfo is None:
416: docinfo = {}
1.38 dwinter 417:
1.3 casties 418: if dom is None:
1.38 dwinter 419: for x in range(cut):
1.33 dwinter 420: path=getParentDir(path)
421: dom = self.getIndexMeta(path)
1.39 dwinter 422:
423: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 424: # put in all raw bib fields as dict "bib"
425: bib = dom.xpath("//bib/*")
426: if bib and len(bib)>0:
427: bibinfo = {}
428: for e in bib:
429: bibinfo[e.localName] = getTextFromNode(e)
430: docinfo['bib'] = bibinfo
431:
432: # extract some fields (author, title, year) according to their mapping
1.4 casties 433: metaData=self.metadata.main.meta.bib
434: bibtype=dom.xpath("//bib/@type")
435: if bibtype and (len(bibtype)>0):
436: bibtype=bibtype[0].value
1.2 dwinter 437: else:
1.4 casties 438: bibtype="generic"
1.27 casties 439:
1.4 casties 440: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 441: docinfo['bib_type'] = bibtype
1.4 casties 442: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 443: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 444: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 445: try:
446: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
447: except: pass
448: try:
449: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
450: except: pass
451: try:
452: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
453: except: pass
1.27 casties 454: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 455: try:
456: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
457: except:
458: docinfo['lang']=''
1.27 casties 459:
1.3 casties 460: return docinfo
1.42 abukhman 461:
462:
1.43 casties 463: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
464: """parse texttool tag in index meta"""
465: logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url))
466: if docinfo is None:
467: docinfo = {}
468: if docinfo.get('lang', None) is None:
469: docinfo['lang'] = '' # default keine Sprache gesetzt
470: if dom is None:
471: dom = self.getIndexMeta(url)
472:
473: archivePath = None
474: archiveName = None
475:
476: archiveNames = dom.xpath("//resource/name")
477: if archiveNames and (len(archiveNames) > 0):
478: archiveName = getTextFromNode(archiveNames[0])
479: else:
480: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url))
481:
482: archivePaths = dom.xpath("//resource/archive-path")
483: if archivePaths and (len(archivePaths) > 0):
484: archivePath = getTextFromNode(archivePaths[0])
485: # clean up archive path
486: if archivePath[0] != '/':
487: archivePath = '/' + archivePath
488: if archiveName and (not archivePath.endswith(archiveName)):
489: archivePath += "/" + archiveName
490: else:
491: # try to get archive-path from url
492: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url))
493: if (not url.startswith('http')):
494: archivePath = url.replace('index.meta', '')
495:
496: if archivePath is None:
497: # we balk without archive-path
498: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
499:
500: imageDirs = dom.xpath("//texttool/image")
501: if imageDirs and (len(imageDirs) > 0):
502: imageDir = getTextFromNode(imageDirs[0])
503:
504: else:
505: # we balk with no image tag / not necessary anymore because textmode is now standard
506: #raise IOError("No text-tool info in %s"%(url))
507: imageDir = ""
508: #xquery="//pb"
509: docinfo['imagePath'] = "" # keine Bilder
510: docinfo['imageURL'] = ""
511:
512: if imageDir and archivePath:
513: #print "image: ", imageDir, " archivepath: ", archivePath
514: imageDir = os.path.join(archivePath, imageDir)
515: imageDir = imageDir.replace("/mpiwg/online", '')
516: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
517: docinfo['imagePath'] = imageDir
518:
519: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
520:
521: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
522: if viewerUrls and (len(viewerUrls) > 0):
523: viewerUrl = getTextFromNode(viewerUrls[0])
524: docinfo['viewerURL'] = viewerUrl
525:
526: textUrls = dom.xpath("//texttool/text")
527: if textUrls and (len(textUrls) > 0):
528: textUrl = getTextFromNode(textUrls[0])
529: if urlparse.urlparse(textUrl)[0] == "": #keine url
530: textUrl = os.path.join(archivePath, textUrl)
531: # fix URLs starting with /mpiwg/online
532: if textUrl.startswith("/mpiwg/online"):
533: textUrl = textUrl.replace("/mpiwg/online", '', 1)
534:
535: docinfo['textURL'] = textUrl
536:
537: textUrls = dom.xpath("//texttool/text-url-path")
538: if textUrls and (len(textUrls) > 0):
539: textUrl = getTextFromNode(textUrls[0])
540: docinfo['textURLPath'] = textUrl
541:
542: presentationUrls = dom.xpath("//texttool/presentation")
543: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
544:
545: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
546: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
547: # durch den relativen Pfad auf die presentation infos
548: presentationPath = getTextFromNode(presentationUrls[0])
549: if url.endswith("index.meta"):
550: presentationUrl = url.replace('index.meta', presentationPath)
551: else:
552: presentationUrl = url + "/" + presentationPath
553: docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
554: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
555:
556: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 557:
1.43 casties 558: return docinfo
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!")
1.44 ! casties 621: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 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:
1.44 ! casties 628: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=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
1.44 ! casties 643: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 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
1.44 ! casties 649:
! 650: pageinfo['viewMode'] = viewMode
! 651: pageinfo['tocMode'] = tocMode
! 652: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '10')
! 653: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.38 dwinter 654:
1.3 casties 655: return pageinfo
656:
1.1 dwinter 657:
1.43 casties 658:
659: def getNumPages(self,docinfo=None):
660: """get list of pages from fulltext and put in docinfo"""
661: xquery = '//pb'
662: text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
663: # TODO: better processing of the page list. do we need the info somewhere else also?
664: docinfo['numPages'] = text.count("<pb ")
665: return docinfo
666:
667: def getTextPage(self, mode="text", pn=1, docinfo=None):
668: """returns single page from fulltext"""
1.44 ! casties 669: docpath = docinfo['textURLPath']
! 670: if mode == "text_dict":
! 671: textmode = "textPollux"
! 672: else:
! 673: textmode = mode
! 674:
! 675: pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False)
1.43 casties 676: # post-processing downloaded xml
677: pagedom = Parse(pagexml)
678: # plain text mode
679: if mode == "text":
680: # first div contains text
681: pagedivs = pagedom.xpath("/div")
682: if len(pagedivs) > 0:
683: pagenode = pagedivs[0]
684: return serializeNode(pagenode)
685:
686: # text-with-links mode
1.44 ! casties 687: if mode == "text_dict":
1.43 casties 688: # first div contains text
689: pagedivs = pagedom.xpath("/div")
690: if len(pagedivs) > 0:
691: pagenode = pagedivs[0]
692: # check all a-tags
693: links = pagenode.xpath("//a")
694: for l in links:
695: hrefNode = l.getAttributeNodeNS(None, u"href")
696: if hrefNode:
697: # is link with href
698: href = hrefNode.nodeValue
699: if href.startswith('lt/lex.xql'):
700: # is pollux link
701: selfurl = self.absolute_url()
702: # change href
703: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/head_main_voc'%selfurl)
704: # add target
705: l.setAttributeNS(None, 'target', '_blank')
706: return serializeNode(pagenode)
1.1 dwinter 707:
1.43 casties 708: return "no text here"
1.3 casties 709:
1.44 ! casties 710: def getToc(self, mode="text", docinfo=None):
! 711: """loads table of contents and stores in docinfo"""
! 712: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
! 713: if 'tocSize_%s'%mode in docinfo:
! 714: # cached toc
! 715: return docinfo
! 716:
! 717: docpath = docinfo['textURLPath']
! 718: # we need to set a result set size
! 719: pagesize = 1000
! 720: pn = 1
! 721: if mode == "text":
! 722: queryType = "toc"
! 723: else:
! 724: queryType = mode
! 725: # number of entries in toc
! 726: tocSize = 0
! 727: tocDiv = None
! 728: pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
! 729: # post-processing downloaded xml
! 730: pagedom = Parse(pagexml)
! 731: # get number of entries
! 732: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
! 733: if len(numdivs) > 0:
! 734: tocSize = int(getTextFromNode(numdivs[0]))
! 735: # div contains text
! 736: #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
! 737: #if len(pagedivs) > 0:
! 738: # tocDiv = pagedivs[0]
! 739:
! 740: docinfo['tocSize_%s'%mode] = tocSize
! 741: #docinfo['tocDiv_%s'%mode] = tocDiv
! 742: return docinfo
! 743:
! 744: def getTocPage(self, mode="toc", pn=1, pageinfo=None, docinfo=None):
! 745: """returns single page from the table of contents"""
! 746: # TODO: this should use the cached TOC
! 747: if mode == "text":
! 748: queryType = "toc"
! 749: else:
! 750: queryType = mode
! 751: docpath = docinfo['textURLPath']
! 752: pagesize = pageinfo['tocPageSize']
! 753: pn = pageinfo['tocPN']
! 754: pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
! 755: # post-processing downloaded xml
! 756: pagedom = Parse(pagexml)
! 757: # div contains text
! 758: pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
! 759: if len(pagedivs) > 0:
! 760: pagenode = pagedivs[0]
! 761: return serializeNode(pagenode)
! 762: else:
! 763: return "No TOC!"
! 764:
1.3 casties 765:
1.43 casties 766: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):
1.3 casties 767: """init document viewer"""
768: self.title=title
769: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 770: self.thumbrows = thumbrows
771: self.thumbcols = thumbcols
1.8 casties 772: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 773: if RESPONSE is not None:
774: RESPONSE.redirect('manage_main')
1.1 dwinter 775:
776:
777:
778: def manage_AddDocumentViewerForm(self):
779: """add the viewer form"""
1.3 casties 780: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 781: return pt()
782:
1.43 casties 783: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 784: """add the viewer"""
1.43 casties 785: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 786: self._setObject(id,newObj)
787:
788: if RESPONSE is not None:
789: RESPONSE.redirect('manage_main')
1.3 casties 790:
791:
792: ##
793: ## DocumentViewerTemplate class
794: ##
795: class DocumentViewerTemplate(ZopePageTemplate):
796: """Template for document viewer"""
797: meta_type="DocumentViewer Template"
798:
799:
800: def manage_addDocumentViewerTemplateForm(self):
801: """Form for adding"""
802: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
803: return pt()
804:
805: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
806: REQUEST=None, submit=None):
807: "Add a Page Template with optional file content."
808:
809: self._setObject(id, DocumentViewerTemplate(id))
810: ob = getattr(self, id)
1.23 dwinter 811: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
812: logging.info("txt %s:"%txt)
813: ob.pt_edit(txt,"text/html")
1.3 casties 814: if title:
815: ob.pt_setTitle(title)
816: try:
817: u = self.DestinationURL()
818: except AttributeError:
819: u = REQUEST['URL1']
820:
821: u = "%s/%s" % (u, urllib.quote(id))
822: REQUEST.RESPONSE.redirect(u+'/manage_main')
823: return ''
824:
825:
1.14 casties 826:
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