Annotation of documentViewer/documentViewer.py, revision 1.46
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:
1.45 abukhman 105: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,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')
1.45 abukhman 166: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=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)
1.45 abukhman 172: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, search)
173: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph)
1.3 casties 174: '''
175:
1.43 casties 176: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 177:
1.3 casties 178: if not hasattr(self, 'template'):
1.43 casties 179: # this won't work
180: logging.error("template folder missing!")
181: return "ERROR: template folder missing!"
1.3 casties 182:
1.43 casties 183: if not getattr(self, 'digilibBaseUrl', None):
1.3 casties 184: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
185:
1.4 casties 186: docinfo = self.getDocinfo(mode=mode,url=url)
1.44 casties 187: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
188: if tocMode != "thumbs":
189: # get table of contents
190: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
191:
1.21 dwinter 192: if viewMode=="auto": # automodus gewaehlt
1.43 casties 193: if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
1.21 dwinter 194: viewMode="text"
195: else:
196: viewMode="images"
1.44 casties 197:
198: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 199: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 200:
1.36 dwinter 201: def generateMarks(self,mk):
202: ret=""
1.44 casties 203: if mk is None:
204: return ""
205: if type(mk) is not ListType:
206: mk=[mk]
1.36 dwinter 207: for m in mk:
1.37 dwinter 208: ret+="mk=%s"%m
1.36 dwinter 209: return ret
1.43 casties 210:
1.44 casties 211:
1.43 casties 212: def findDigilibUrl(self):
213: """try to get the digilib URL from zogilib"""
214: url = self.template.zogilib.getDLBaseUrl()
215: return url
216:
217: def getStyle(self, idx, selected, style=""):
218: """returns a string with the given style and append 'sel' if path == selected."""
219: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
220: if idx == selected:
221: return style + 'sel'
222: else:
223: return style
1.36 dwinter 224:
1.4 casties 225: def getLink(self,param=None,val=None):
226: """link to documentviewer with parameter param set to val"""
1.9 casties 227: params=self.REQUEST.form.copy()
1.4 casties 228: if param is not None:
1.7 casties 229: if val is None:
230: if params.has_key(param):
231: del params[param]
1.4 casties 232: else:
1.9 casties 233: params[param] = str(val)
1.43 casties 234:
235: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 236: params["mode"] = "imagepath"
237: params["url"] = getParentDir(params["url"])
1.7 casties 238:
1.9 casties 239: # quote values and assemble into query string
240: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
241: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 242: return url
243:
1.32 dwinter 244: def getLinkAmp(self,param=None,val=None):
245: """link to documentviewer with parameter param set to val"""
246: params=self.REQUEST.form.copy()
247: if param is not None:
248: if val is None:
249: if params.has_key(param):
250: del params[param]
251: else:
252: params[param] = str(val)
253:
254: # quote values and assemble into query string
255: logging.info("XYXXXXX: %s"%repr(params.items()))
256: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
257: url=self.REQUEST['URL1']+"?"+ps
258: return url
1.40 casties 259:
1.26 casties 260: def getInfo_xml(self,url,mode):
261: """returns info about the document as XML"""
262:
263: if not self.digilibBaseUrl:
264: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
265:
266: docinfo = self.getDocinfo(mode=mode,url=url)
267: pt = getattr(self.template, 'info_xml')
268: return pt(docinfo=docinfo)
269:
1.4 casties 270:
1.9 casties 271: def isAccessible(self, docinfo):
1.8 casties 272: """returns if access to the resource is granted"""
273: access = docinfo.get('accessType', None)
1.22 dwinter 274: logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
1.17 casties 275: if access is not None and access == 'free':
1.22 dwinter 276: logger("documentViewer (accessOK)", logging.INFO, "access is free")
1.8 casties 277: return True
1.17 casties 278: elif access is None or access in self.authgroups:
1.9 casties 279: # only local access -- only logged in users
280: user = getSecurityManager().getUser()
281: if user is not None:
282: #print "user: ", user
283: return (user.getUserName() != "Anonymous User")
284: else:
285: return False
1.8 casties 286:
1.22 dwinter 287: logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
1.8 casties 288: return False
1.9 casties 289:
1.8 casties 290:
1.35 dwinter 291: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 292: """gibt param von dlInfo aus"""
1.13 casties 293: num_retries = 3
1.7 casties 294: if docinfo is None:
295: docinfo = {}
1.35 dwinter 296:
297: for x in range(cut):
1.38 dwinter 298:
1.35 dwinter 299: path=getParentDir(path)
1.38 dwinter 300:
1.13 casties 301: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 302:
1.22 dwinter 303: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
1.6 casties 304:
1.13 casties 305: for cnt in range(num_retries):
1.9 casties 306: try:
1.13 casties 307: # dom = NonvalidatingReader.parseUri(imageUrl)
308: txt=urllib.urlopen(infoUrl).read()
309: dom = Parse(txt)
1.9 casties 310: break
311: except:
1.22 dwinter 312: logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
1.9 casties 313: else:
1.13 casties 314: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.6 casties 315:
1.10 casties 316: sizes=dom.xpath("//dir/size")
1.22 dwinter 317: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
1.6 casties 318:
1.10 casties 319: if sizes:
320: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 321: else:
322: docinfo['numPages'] = 0
1.43 casties 323:
324: # TODO: produce and keep list of image names and numbers
1.7 casties 325:
326: return docinfo
1.8 casties 327:
1.6 casties 328:
1.9 casties 329: def getIndexMeta(self, url):
330: """returns dom of index.meta document at url"""
1.12 casties 331: num_retries = 3
1.9 casties 332: dom = None
1.12 casties 333: metaUrl = None
1.9 casties 334: if url.startswith("http://"):
335: # real URL
1.12 casties 336: metaUrl = url
1.9 casties 337: else:
338: # online path
339: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 340: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 341: if not metaUrl.endswith("index.meta"):
342: metaUrl += "/index.meta"
1.37 dwinter 343: logging.debug("METAURL: %s"%metaUrl)
1.13 casties 344: for cnt in range(num_retries):
1.9 casties 345: try:
1.12 casties 346: # patch dirk encoding fehler treten dann nicht mehr auf
1.11 casties 347: # dom = NonvalidatingReader.parseUri(metaUrl)
1.12 casties 348: txt=urllib.urlopen(metaUrl).read()
349: dom = Parse(txt)
1.13 casties 350: break
1.9 casties 351: except:
1.44 casties 352: logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.12 casties 353:
354: if dom is None:
355: raise IOError("Unable to read index meta from %s"%(url))
1.9 casties 356:
357: return dom
1.20 dwinter 358:
359: def getPresentationInfoXML(self, url):
360: """returns dom of info.xml document at url"""
361: num_retries = 3
362: dom = None
363: metaUrl = None
364: if url.startswith("http://"):
365: # real URL
366: metaUrl = url
367: else:
368: # online path
369: server=self.digilibBaseUrl+"/servlet/Texter?fn="
370: metaUrl=server+url.replace("/mpiwg/online","")
371:
372: for cnt in range(num_retries):
373: try:
374: # patch dirk encoding fehler treten dann nicht mehr auf
375: # dom = NonvalidatingReader.parseUri(metaUrl)
376: txt=urllib.urlopen(metaUrl).read()
377: dom = Parse(txt)
378: break
379: except:
1.22 dwinter 380: logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.20 dwinter 381:
382: if dom is None:
383: raise IOError("Unable to read infoXMLfrom %s"%(url))
384:
385: return dom
1.9 casties 386:
387:
1.33 dwinter 388: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 389: """gets authorization info from the index.meta file at path or given by dom"""
1.22 dwinter 390: logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
1.8 casties 391:
392: access = None
393:
394: if docinfo is None:
395: docinfo = {}
396:
397: if dom is None:
1.38 dwinter 398: for x in range(cut):
1.33 dwinter 399: path=getParentDir(path)
400: dom = self.getIndexMeta(path)
1.18 dwinter 401:
1.8 casties 402: acctype = dom.xpath("//access-conditions/access/@type")
403: if acctype and (len(acctype)>0):
404: access=acctype[0].value
1.9 casties 405: if access in ['group', 'institution']:
1.8 casties 406: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
407:
408: docinfo['accessType'] = access
409: return docinfo
1.6 casties 410:
1.8 casties 411:
1.33 dwinter 412: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 413: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 414: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 415:
1.3 casties 416: if docinfo is None:
417: docinfo = {}
1.38 dwinter 418:
1.3 casties 419: if dom is None:
1.38 dwinter 420: for x in range(cut):
1.33 dwinter 421: path=getParentDir(path)
422: dom = self.getIndexMeta(path)
1.39 dwinter 423:
424: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 425: # put in all raw bib fields as dict "bib"
426: bib = dom.xpath("//bib/*")
427: if bib and len(bib)>0:
428: bibinfo = {}
429: for e in bib:
430: bibinfo[e.localName] = getTextFromNode(e)
431: docinfo['bib'] = bibinfo
432:
433: # extract some fields (author, title, year) according to their mapping
1.4 casties 434: metaData=self.metadata.main.meta.bib
435: bibtype=dom.xpath("//bib/@type")
436: if bibtype and (len(bibtype)>0):
437: bibtype=bibtype[0].value
1.2 dwinter 438: else:
1.4 casties 439: bibtype="generic"
1.27 casties 440:
1.4 casties 441: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 442: docinfo['bib_type'] = bibtype
1.4 casties 443: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 444: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 445: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 446: try:
447: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
448: except: pass
449: try:
450: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
451: except: pass
452: try:
453: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
454: except: pass
1.27 casties 455: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 456: try:
457: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
458: except:
459: docinfo['lang']=''
1.27 casties 460:
1.3 casties 461: return docinfo
1.42 abukhman 462:
463:
1.43 casties 464: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
465: """parse texttool tag in index meta"""
466: logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url))
467: if docinfo is None:
468: docinfo = {}
469: if docinfo.get('lang', None) is None:
470: docinfo['lang'] = '' # default keine Sprache gesetzt
471: if dom is None:
472: dom = self.getIndexMeta(url)
473:
474: archivePath = None
475: archiveName = None
476:
477: archiveNames = dom.xpath("//resource/name")
478: if archiveNames and (len(archiveNames) > 0):
479: archiveName = getTextFromNode(archiveNames[0])
480: else:
481: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url))
482:
483: archivePaths = dom.xpath("//resource/archive-path")
484: if archivePaths and (len(archivePaths) > 0):
485: archivePath = getTextFromNode(archivePaths[0])
486: # clean up archive path
487: if archivePath[0] != '/':
488: archivePath = '/' + archivePath
489: if archiveName and (not archivePath.endswith(archiveName)):
490: archivePath += "/" + archiveName
491: else:
492: # try to get archive-path from url
493: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url))
494: if (not url.startswith('http')):
495: archivePath = url.replace('index.meta', '')
496:
497: if archivePath is None:
498: # we balk without archive-path
499: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
500:
501: imageDirs = dom.xpath("//texttool/image")
502: if imageDirs and (len(imageDirs) > 0):
503: imageDir = getTextFromNode(imageDirs[0])
504:
505: else:
506: # we balk with no image tag / not necessary anymore because textmode is now standard
507: #raise IOError("No text-tool info in %s"%(url))
508: imageDir = ""
509: #xquery="//pb"
510: docinfo['imagePath'] = "" # keine Bilder
511: docinfo['imageURL'] = ""
512:
513: if imageDir and archivePath:
514: #print "image: ", imageDir, " archivepath: ", archivePath
515: imageDir = os.path.join(archivePath, imageDir)
516: imageDir = imageDir.replace("/mpiwg/online", '')
517: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
518: docinfo['imagePath'] = imageDir
519:
520: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
521:
522: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
523: if viewerUrls and (len(viewerUrls) > 0):
524: viewerUrl = getTextFromNode(viewerUrls[0])
525: docinfo['viewerURL'] = viewerUrl
526:
527: textUrls = dom.xpath("//texttool/text")
528: if textUrls and (len(textUrls) > 0):
529: textUrl = getTextFromNode(textUrls[0])
530: if urlparse.urlparse(textUrl)[0] == "": #keine url
531: textUrl = os.path.join(archivePath, textUrl)
532: # fix URLs starting with /mpiwg/online
533: if textUrl.startswith("/mpiwg/online"):
534: textUrl = textUrl.replace("/mpiwg/online", '', 1)
535:
536: docinfo['textURL'] = textUrl
537:
538: textUrls = dom.xpath("//texttool/text-url-path")
539: if textUrls and (len(textUrls) > 0):
540: textUrl = getTextFromNode(textUrls[0])
541: docinfo['textURLPath'] = textUrl
542:
543: presentationUrls = dom.xpath("//texttool/presentation")
544: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
545:
546: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
547: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
548: # durch den relativen Pfad auf die presentation infos
549: presentationPath = getTextFromNode(presentationUrls[0])
550: if url.endswith("index.meta"):
551: presentationUrl = url.replace('index.meta', presentationPath)
552: else:
553: presentationUrl = url + "/" + presentationPath
554: docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
555: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
556:
557: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 558:
1.43 casties 559: return docinfo
1.3 casties 560:
1.20 dwinter 561:
562: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
563: """gets the bibliographical information from the preseantion entry in texttools
564: """
565: dom=self.getPresentationInfoXML(url)
1.29 casties 566: try:
567: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
568: except:
569: pass
570: try:
571: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
572: except:
573: pass
574: try:
575: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
576: except:
577: pass
1.20 dwinter 578: return docinfo
579:
1.33 dwinter 580: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 581: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.22 dwinter 582: logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))
1.3 casties 583: if docinfo is None:
584: docinfo = {}
1.6 casties 585: path=path.replace("/mpiwg/online","")
1.3 casties 586: docinfo['imagePath'] = path
1.35 dwinter 587: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 588:
1.39 dwinter 589: pathorig=path
1.38 dwinter 590: for x in range(cut):
591: path=getParentDir(path)
592: logging.error("PATH:"+path)
1.7 casties 593: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 594: docinfo['imageURL'] = imageUrl
595:
1.39 dwinter 596: #path ist the path to the images it assumes that the index.meta file is one level higher.
597: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
598: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 599: return docinfo
600:
1.2 dwinter 601:
1.3 casties 602: def getDocinfo(self, mode, url):
603: """returns docinfo depending on mode"""
1.22 dwinter 604: logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))
1.3 casties 605: # look for cached docinfo in session
1.21 dwinter 606: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 607: docinfo = self.REQUEST.SESSION['docinfo']
608: # check if its still current
609: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.22 dwinter 610: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)
1.3 casties 611: return docinfo
612: # new docinfo
613: docinfo = {'mode': mode, 'url': url}
614: if mode=="texttool": #index.meta with texttool information
615: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
616: elif mode=="imagepath":
617: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 618: elif mode=="filepath":
1.37 dwinter 619: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 620: else:
1.22 dwinter 621: logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
1.44 casties 622: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 623:
1.22 dwinter 624: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
1.3 casties 625: self.REQUEST.SESSION['docinfo'] = docinfo
626: return docinfo
1.2 dwinter 627:
628:
1.44 casties 629: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 630: """returns pageinfo with the given parameters"""
631: pageinfo = {}
1.4 casties 632: current = getInt(current)
633: pageinfo['current'] = current
634: rows = int(rows or self.thumbrows)
635: pageinfo['rows'] = rows
636: cols = int(cols or self.thumbcols)
637: pageinfo['cols'] = cols
638: grpsize = cols * rows
639: pageinfo['groupsize'] = grpsize
1.28 casties 640: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
641: # int(current / grpsize) * grpsize +1))
1.3 casties 642: pageinfo['start'] = start
1.4 casties 643: pageinfo['end'] = start + grpsize
1.44 casties 644: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 645: np = int(docinfo['numPages'])
646: pageinfo['end'] = min(pageinfo['end'], np)
647: pageinfo['numgroups'] = int(np / grpsize)
648: if np % grpsize > 0:
649: pageinfo['numgroups'] += 1
1.44 casties 650:
651: pageinfo['viewMode'] = viewMode
652: pageinfo['tocMode'] = tocMode
1.45 abukhman 653: pageinfo['query'] = self.REQUEST.get('query',' ')
654: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
655: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
656: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
657: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '20')
1.44 casties 658: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.45 abukhman 659: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
660: pageinfo['sn'] =self.REQUEST.get('sn','1')
1.38 dwinter 661:
1.3 casties 662: return pageinfo
663:
1.45 abukhman 664: def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None):
665: """get search list"""
666: docpath = docinfo['textURLPath']
667: pagesize = pageinfo['queryPageSize']
668: pn = pageinfo['searchPN']
669: sn = pageinfo['sn']
670: query =pageinfo['query']
671: queryType =pageinfo['queryType']
1.46 ! abukhman 672: viewMode= pageinfo['viewMode']
! 673: tocMode = pageinfo['tocMode']
! 674: tocPN = pageinfo['tocPN']
1.45 abukhman 675: pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn) ,outputUnicode=False)
676: pagedom = Parse(pagexml)
677: #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
1.46 ! abukhman 678: selfurl = self.absolute_url()
! 679: page = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','%s?url=/mpiwg/online/permanent/library/163127KK&viewMode=%s&tocMode=%s&tocPN=%s&query=%s&queryType=%s'%(selfurl, viewMode, tocMode, tocPN, query, queryType))
! 680: text =page.replace('mode=text','mode=texttool')
! 681: return text
1.45 abukhman 682: #if len(pagedivs) > 0:
683: # pagenode = pagedom[0]
684: # return serializeNode(pagenode)
685: #else:
686: # return "xaxa"
1.43 casties 687:
688: def getNumPages(self,docinfo=None):
689: """get list of pages from fulltext and put in docinfo"""
690: xquery = '//pb'
691: text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
692: # TODO: better processing of the page list. do we need the info somewhere else also?
693: docinfo['numPages'] = text.count("<pb ")
694: return docinfo
695:
1.46 ! abukhman 696: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None,):
1.43 casties 697: """returns single page from fulltext"""
1.44 casties 698: docpath = docinfo['textURLPath']
699: if mode == "text_dict":
700: textmode = "textPollux"
701: else:
702: textmode = mode
703:
1.46 ! abukhman 704: #selfurl = self.absolute_url()
! 705: #viewMode= pageinfo['viewMode']
! 706: #tocMode = pageinfo['tocMode']
! 707: #tocPN = pageinfo['tocPN']
! 708:
1.44 casties 709: pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False)
1.45 abukhman 710: #######
1.46 ! abukhman 711: #page = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','%s?url=/mpiwg/online/permanent/library/163127KK&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl, viewMode, tocMode, tocPN))
! 712: #text =page.replace('mode=text','mode=texttool')
1.45 abukhman 713: #######
1.43 casties 714: # post-processing downloaded xml
715: pagedom = Parse(pagexml)
716: # plain text mode
717: if mode == "text":
718: # first div contains text
719: pagedivs = pagedom.xpath("/div")
1.45 abukhman 720: #queryResultPage
1.43 casties 721: if len(pagedivs) > 0:
722: pagenode = pagedivs[0]
723: return serializeNode(pagenode)
724:
725: # text-with-links mode
1.44 casties 726: if mode == "text_dict":
1.43 casties 727: # first div contains text
728: pagedivs = pagedom.xpath("/div")
729: if len(pagedivs) > 0:
730: pagenode = pagedivs[0]
731: # check all a-tags
732: links = pagenode.xpath("//a")
733: for l in links:
734: hrefNode = l.getAttributeNodeNS(None, u"href")
735: if hrefNode:
736: # is link with href
737: href = hrefNode.nodeValue
738: if href.startswith('lt/lex.xql'):
739: # is pollux link
740: selfurl = self.absolute_url()
741: # change href
1.46 ! abukhman 742: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
1.43 casties 743: # add target
744: l.setAttributeNS(None, 'target', '_blank')
1.46 ! abukhman 745:
! 746: if href.startswith('lt/lemma.xql'):
! 747: selfurl = self.absolute_url()
! 748: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
! 749: l.setAttributeNS(None, 'target', '_blank')
1.43 casties 750: return serializeNode(pagenode)
1.1 dwinter 751:
1.43 casties 752: return "no text here"
1.3 casties 753:
1.46 ! abukhman 754: def getTranslate(self, query=None, language=None):
! 755: """translate into another languages"""
! 756: pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","query=%s&language=%s"%(query,language),outputUnicode=False)
! 757: return pagexml
! 758:
! 759: def getLemma(self):
! 760: """lemma"""
! 761: pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","query=%s&language=%s"%(query,language),outputUnicode=False)
! 762: return pagexml
! 763:
1.44 casties 764: def getToc(self, mode="text", docinfo=None):
765: """loads table of contents and stores in docinfo"""
766: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
767: if 'tocSize_%s'%mode in docinfo:
768: # cached toc
769: return docinfo
770:
771: docpath = docinfo['textURLPath']
772: # we need to set a result set size
773: pagesize = 1000
774: pn = 1
775: if mode == "text":
776: queryType = "toc"
777: else:
778: queryType = mode
779: # number of entries in toc
780: tocSize = 0
781: tocDiv = None
782: pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
783: # post-processing downloaded xml
784: pagedom = Parse(pagexml)
785: # get number of entries
786: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
787: if len(numdivs) > 0:
788: tocSize = int(getTextFromNode(numdivs[0]))
789: # div contains text
790: #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
791: #if len(pagedivs) > 0:
792: # tocDiv = pagedivs[0]
793:
794: docinfo['tocSize_%s'%mode] = tocSize
795: #docinfo['tocDiv_%s'%mode] = tocDiv
796: return docinfo
797:
1.45 abukhman 798: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
1.44 casties 799: """returns single page from the table of contents"""
800: # TODO: this should use the cached TOC
801: if mode == "text":
802: queryType = "toc"
803: else:
804: queryType = mode
805: docpath = docinfo['textURLPath']
806: pagesize = pageinfo['tocPageSize']
807: pn = pageinfo['tocPN']
1.46 ! abukhman 808:
! 809: selfurl = self.absolute_url()
! 810: viewMode= pageinfo['viewMode']
! 811: tocMode = pageinfo['tocMode']
! 812: tocPN = pageinfo['tocPN']
! 813:
1.45 abukhman 814: pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn), outputUnicode=False)
1.46 ! abukhman 815: page = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','%s?url=/mpiwg/online/permanent/library/163127KK&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl, viewMode, tocMode, tocPN))
! 816: text = page.replace('mode=image','mode=texttool')
! 817: return text
1.44 casties 818: # post-processing downloaded xml
1.46 ! abukhman 819: #pagedom = Parse(text)
1.44 casties 820: # div contains text
1.46 ! abukhman 821: #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
! 822: #if len(pagedivs) > 0:
! 823: # pagenode = pagedivs[0]
! 824: # return serializeNode(pagenode)
! 825: #else:
! 826: # return "No TOC!"
1.44 casties 827:
1.3 casties 828:
1.45 abukhman 829: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 830: """init document viewer"""
831: self.title=title
832: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 833: self.thumbrows = thumbrows
834: self.thumbcols = thumbcols
1.8 casties 835: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 836: if RESPONSE is not None:
837: RESPONSE.redirect('manage_main')
1.1 dwinter 838:
839:
840:
841: def manage_AddDocumentViewerForm(self):
842: """add the viewer form"""
1.3 casties 843: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 844: return pt()
845:
1.43 casties 846: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 847: """add the viewer"""
1.43 casties 848: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 849: self._setObject(id,newObj)
850:
851: if RESPONSE is not None:
852: RESPONSE.redirect('manage_main')
1.3 casties 853:
854:
855: ##
856: ## DocumentViewerTemplate class
857: ##
858: class DocumentViewerTemplate(ZopePageTemplate):
859: """Template for document viewer"""
860: meta_type="DocumentViewer Template"
861:
862:
863: def manage_addDocumentViewerTemplateForm(self):
864: """Form for adding"""
865: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
866: return pt()
867:
868: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
869: REQUEST=None, submit=None):
870: "Add a Page Template with optional file content."
871:
872: self._setObject(id, DocumentViewerTemplate(id))
873: ob = getattr(self, id)
1.23 dwinter 874: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
875: logging.info("txt %s:"%txt)
876: ob.pt_edit(txt,"text/html")
1.3 casties 877: if title:
878: ob.pt_setTitle(title)
879: try:
880: u = self.DestinationURL()
881: except AttributeError:
882: u = REQUEST['URL1']
883:
884: u = "%s/%s" % (u, urllib.quote(id))
885: REQUEST.RESPONSE.redirect(u+'/manage_main')
886: return ''
887:
888:
1.14 casties 889:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>