Annotation of documentViewer/documentViewer.py, revision 1.47
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:
1.47 ! abukhman 13: from xml.dom.minidom import parse, parseString
! 14:
! 15:
1.42 abukhman 16:
1.1 dwinter 17: import Ft.Xml.XPath
1.43 casties 18: import cStringIO
1.42 abukhman 19: import xmlrpclib
1.1 dwinter 20: import os.path
1.7 casties 21: import sys
1.1 dwinter 22: import cgi
23: import urllib
1.20 dwinter 24: import logging
1.28 casties 25: import math
1.22 dwinter 26:
1.18 dwinter 27: import urlparse
1.37 dwinter 28: from types import *
1.43 casties 29:
1.22 dwinter 30: def logger(txt,method,txt2):
31: """logging"""
32: logging.info(txt+ txt2)
33:
34:
1.4 casties 35: def getInt(number, default=0):
36: """returns always an int (0 in case of problems)"""
37: try:
38: return int(number)
39: except:
1.29 casties 40: return int(default)
1.4 casties 41:
1.1 dwinter 42: def getTextFromNode(nodename):
1.18 dwinter 43: """get the cdata content of a node"""
1.8 casties 44: if nodename is None:
45: return ""
1.1 dwinter 46: nodelist=nodename.childNodes
47: rc = ""
48: for node in nodelist:
49: if node.nodeType == node.TEXT_NODE:
50: rc = rc + node.data
51: return rc
52:
1.43 casties 53: def serializeNode(node, encoding='utf-8'):
54: """returns a string containing node as XML"""
55: buf = cStringIO.StringIO()
56: Print(node, stream=buf, encoding=encoding)
57: s = buf.getvalue()
58: buf.close()
59: return s
60:
1.9 casties 61:
62: def getParentDir(path):
63: """returns pathname shortened by one"""
64: return '/'.join(path.split('/')[0:-1])
65:
66:
1.1 dwinter 67: import socket
68:
1.8 casties 69: def urlopen(url,timeout=2):
1.1 dwinter 70: """urlopen mit timeout"""
1.8 casties 71: socket.setdefaulttimeout(timeout)
1.1 dwinter 72: ret=urllib.urlopen(url)
73: socket.setdefaulttimeout(5)
74: return ret
75:
76:
1.3 casties 77: ##
78: ## documentViewer class
79: ##
80: class documentViewer(Folder):
1.1 dwinter 81: """document viewer"""
1.20 dwinter 82: #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"
1.18 dwinter 83:
1.1 dwinter 84: meta_type="Document viewer"
85:
86: security=ClassSecurityInfo()
1.3 casties 87: manage_options=Folder.manage_options+(
1.1 dwinter 88: {'label':'main config','action':'changeDocumentViewerForm'},
89: )
90:
1.3 casties 91: # templates and forms
92: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 93: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
94: toc_text = PageTemplateFile('zpt/toc_text', globals())
95: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 96: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
97: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 98: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.3 casties 99: head_main = PageTemplateFile('zpt/head_main', globals())
100: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 101: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.3 casties 102:
1.32 dwinter 103: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 104: security.declareProtected('View management screens','changeDocumentViewerForm')
105: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
106:
1.1 dwinter 107:
1.45 abukhman 108: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 109: """init document viewer"""
110: self.id=id
111: self.title=title
1.4 casties 112: self.thumbcols = thumbcols
113: self.thumbrows = thumbrows
1.8 casties 114: # authgroups is list of authorized groups (delimited by ,)
115: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 116: # create template folder so we can always use template.something
117:
118: templateFolder = Folder('template')
119: #self['template'] = templateFolder # Zope-2.12 style
120: self._setObject('template',templateFolder) # old style
121: try:
122: from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy
123: xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False)
124: #templateFolder['fulltextclient'] = xmlRpcClient
125: templateFolder._setObject('fulltextclient',xmlRpcClient)
126: except Exception, e:
127: logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e))
128: try:
129: from Products.zogiLib.zogiLib import zogiLib
130: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
131: #templateFolder['zogilib'] = zogilib
132: templateFolder._setObject('zogilib',zogilib)
133: except Exception, e:
134: logging.error("Unable to create zogiLib for zogilib: "+str(e))
135:
1.3 casties 136:
1.32 dwinter 137: security.declareProtected('View','thumbs_rss')
138: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
139: '''
140: view it
141: @param mode: defines how to access the document behind url
142: @param url: url which contains display information
143: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
144:
145: '''
1.43 casties 146: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.32 dwinter 147: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
148:
149: if not hasattr(self, 'template'):
150: # create template folder if it doesn't exist
151: self.manage_addFolder('template')
152:
153: if not self.digilibBaseUrl:
154: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
155:
156: docinfo = self.getDocinfo(mode=mode,url=url)
157: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
158: pt = getattr(self.template, 'thumbs_main_rss')
159:
160: if viewMode=="auto": # automodus gewaehlt
161: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
162: viewMode="text"
163: else:
164: viewMode="images"
165:
166: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
167:
1.3 casties 168: security.declareProtected('View','index_html')
1.45 abukhman 169: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
1.3 casties 170: '''
171: view it
1.26 casties 172: @param mode: defines how to access the document behind url
1.3 casties 173: @param url: url which contains display information
1.44 casties 174: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.45 abukhman 175: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, search)
176: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph)
1.3 casties 177: '''
178:
1.43 casties 179: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 180:
1.3 casties 181: if not hasattr(self, 'template'):
1.43 casties 182: # this won't work
183: logging.error("template folder missing!")
184: return "ERROR: template folder missing!"
1.3 casties 185:
1.43 casties 186: if not getattr(self, 'digilibBaseUrl', None):
1.3 casties 187: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
188:
1.4 casties 189: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 ! abukhman 190:
! 191:
1.44 casties 192: if tocMode != "thumbs":
193: # get table of contents
194: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 ! abukhman 195:
! 196: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
! 197:
1.21 dwinter 198: if viewMode=="auto": # automodus gewaehlt
1.43 casties 199: if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
1.21 dwinter 200: viewMode="text"
201: else:
202: viewMode="images"
1.44 casties 203:
204: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 205: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 206:
1.36 dwinter 207: def generateMarks(self,mk):
208: ret=""
1.44 casties 209: if mk is None:
210: return ""
211: if type(mk) is not ListType:
212: mk=[mk]
1.36 dwinter 213: for m in mk:
1.37 dwinter 214: ret+="mk=%s"%m
1.36 dwinter 215: return ret
1.43 casties 216:
1.44 casties 217:
1.43 casties 218: def findDigilibUrl(self):
219: """try to get the digilib URL from zogilib"""
220: url = self.template.zogilib.getDLBaseUrl()
221: return url
222:
223: def getStyle(self, idx, selected, style=""):
224: """returns a string with the given style and append 'sel' if path == selected."""
225: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
226: if idx == selected:
227: return style + 'sel'
228: else:
229: return style
1.36 dwinter 230:
1.4 casties 231: def getLink(self,param=None,val=None):
232: """link to documentviewer with parameter param set to val"""
1.9 casties 233: params=self.REQUEST.form.copy()
1.4 casties 234: if param is not None:
1.7 casties 235: if val is None:
236: if params.has_key(param):
237: del params[param]
1.4 casties 238: else:
1.9 casties 239: params[param] = str(val)
1.43 casties 240:
241: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 242: params["mode"] = "imagepath"
243: params["url"] = getParentDir(params["url"])
1.7 casties 244:
1.9 casties 245: # quote values and assemble into query string
246: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
247: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 248: return url
249:
1.32 dwinter 250: def getLinkAmp(self,param=None,val=None):
251: """link to documentviewer with parameter param set to val"""
252: params=self.REQUEST.form.copy()
253: if param is not None:
254: if val is None:
255: if params.has_key(param):
256: del params[param]
257: else:
258: params[param] = str(val)
259:
260: # quote values and assemble into query string
261: logging.info("XYXXXXX: %s"%repr(params.items()))
262: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
263: url=self.REQUEST['URL1']+"?"+ps
264: return url
1.40 casties 265:
1.26 casties 266: def getInfo_xml(self,url,mode):
267: """returns info about the document as XML"""
268:
269: if not self.digilibBaseUrl:
270: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
271:
272: docinfo = self.getDocinfo(mode=mode,url=url)
273: pt = getattr(self.template, 'info_xml')
274: return pt(docinfo=docinfo)
275:
1.4 casties 276:
1.9 casties 277: def isAccessible(self, docinfo):
1.8 casties 278: """returns if access to the resource is granted"""
279: access = docinfo.get('accessType', None)
1.22 dwinter 280: logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
1.17 casties 281: if access is not None and access == 'free':
1.22 dwinter 282: logger("documentViewer (accessOK)", logging.INFO, "access is free")
1.8 casties 283: return True
1.17 casties 284: elif access is None or access in self.authgroups:
1.9 casties 285: # only local access -- only logged in users
286: user = getSecurityManager().getUser()
287: if user is not None:
288: #print "user: ", user
289: return (user.getUserName() != "Anonymous User")
290: else:
291: return False
1.8 casties 292:
1.22 dwinter 293: logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
1.8 casties 294: return False
1.9 casties 295:
1.8 casties 296:
1.35 dwinter 297: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 298: """gibt param von dlInfo aus"""
1.13 casties 299: num_retries = 3
1.7 casties 300: if docinfo is None:
301: docinfo = {}
1.35 dwinter 302:
303: for x in range(cut):
1.38 dwinter 304:
1.35 dwinter 305: path=getParentDir(path)
1.38 dwinter 306:
1.13 casties 307: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 308:
1.22 dwinter 309: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
1.6 casties 310:
1.13 casties 311: for cnt in range(num_retries):
1.9 casties 312: try:
1.13 casties 313: # dom = NonvalidatingReader.parseUri(imageUrl)
314: txt=urllib.urlopen(infoUrl).read()
315: dom = Parse(txt)
1.9 casties 316: break
317: except:
1.22 dwinter 318: logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
1.9 casties 319: else:
1.13 casties 320: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.6 casties 321:
1.10 casties 322: sizes=dom.xpath("//dir/size")
1.22 dwinter 323: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
1.6 casties 324:
1.10 casties 325: if sizes:
326: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 327: else:
328: docinfo['numPages'] = 0
1.43 casties 329:
330: # TODO: produce and keep list of image names and numbers
1.7 casties 331:
332: return docinfo
1.8 casties 333:
1.6 casties 334:
1.9 casties 335: def getIndexMeta(self, url):
336: """returns dom of index.meta document at url"""
1.12 casties 337: num_retries = 3
1.9 casties 338: dom = None
1.12 casties 339: metaUrl = None
1.9 casties 340: if url.startswith("http://"):
341: # real URL
1.12 casties 342: metaUrl = url
1.9 casties 343: else:
344: # online path
345: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 346: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 347: if not metaUrl.endswith("index.meta"):
348: metaUrl += "/index.meta"
1.37 dwinter 349: logging.debug("METAURL: %s"%metaUrl)
1.13 casties 350: for cnt in range(num_retries):
1.9 casties 351: try:
1.12 casties 352: # patch dirk encoding fehler treten dann nicht mehr auf
1.11 casties 353: # dom = NonvalidatingReader.parseUri(metaUrl)
1.12 casties 354: txt=urllib.urlopen(metaUrl).read()
355: dom = Parse(txt)
1.13 casties 356: break
1.9 casties 357: except:
1.44 casties 358: logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.12 casties 359:
360: if dom is None:
361: raise IOError("Unable to read index meta from %s"%(url))
1.9 casties 362:
363: return dom
1.20 dwinter 364:
365: def getPresentationInfoXML(self, url):
366: """returns dom of info.xml document at url"""
367: num_retries = 3
368: dom = None
369: metaUrl = None
370: if url.startswith("http://"):
371: # real URL
372: metaUrl = url
373: else:
374: # online path
375: server=self.digilibBaseUrl+"/servlet/Texter?fn="
376: metaUrl=server+url.replace("/mpiwg/online","")
377:
378: for cnt in range(num_retries):
379: try:
380: # patch dirk encoding fehler treten dann nicht mehr auf
381: # dom = NonvalidatingReader.parseUri(metaUrl)
382: txt=urllib.urlopen(metaUrl).read()
383: dom = Parse(txt)
384: break
385: except:
1.22 dwinter 386: logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
1.20 dwinter 387:
388: if dom is None:
389: raise IOError("Unable to read infoXMLfrom %s"%(url))
390:
391: return dom
1.9 casties 392:
393:
1.33 dwinter 394: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 395: """gets authorization info from the index.meta file at path or given by dom"""
1.22 dwinter 396: logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
1.8 casties 397:
398: access = None
399:
400: if docinfo is None:
401: docinfo = {}
402:
403: if dom is None:
1.38 dwinter 404: for x in range(cut):
1.33 dwinter 405: path=getParentDir(path)
406: dom = self.getIndexMeta(path)
1.18 dwinter 407:
1.8 casties 408: acctype = dom.xpath("//access-conditions/access/@type")
409: if acctype and (len(acctype)>0):
410: access=acctype[0].value
1.9 casties 411: if access in ['group', 'institution']:
1.8 casties 412: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
413:
414: docinfo['accessType'] = access
415: return docinfo
1.6 casties 416:
1.8 casties 417:
1.33 dwinter 418: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 419: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 420: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 421:
1.3 casties 422: if docinfo is None:
423: docinfo = {}
1.38 dwinter 424:
1.3 casties 425: if dom is None:
1.38 dwinter 426: for x in range(cut):
1.33 dwinter 427: path=getParentDir(path)
428: dom = self.getIndexMeta(path)
1.39 dwinter 429:
430: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 431: # put in all raw bib fields as dict "bib"
432: bib = dom.xpath("//bib/*")
433: if bib and len(bib)>0:
434: bibinfo = {}
435: for e in bib:
436: bibinfo[e.localName] = getTextFromNode(e)
437: docinfo['bib'] = bibinfo
438:
439: # extract some fields (author, title, year) according to their mapping
1.4 casties 440: metaData=self.metadata.main.meta.bib
441: bibtype=dom.xpath("//bib/@type")
442: if bibtype and (len(bibtype)>0):
443: bibtype=bibtype[0].value
1.2 dwinter 444: else:
1.4 casties 445: bibtype="generic"
1.27 casties 446:
1.4 casties 447: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 448: docinfo['bib_type'] = bibtype
1.4 casties 449: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 450: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 451: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 452: try:
453: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
454: except: pass
455: try:
456: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
457: except: pass
458: try:
459: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
460: except: pass
1.27 casties 461: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 462: try:
463: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
464: except:
465: docinfo['lang']=''
1.27 casties 466:
1.3 casties 467: return docinfo
1.42 abukhman 468:
469:
1.43 casties 470: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
471: """parse texttool tag in index meta"""
472: logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url))
473: if docinfo is None:
474: docinfo = {}
475: if docinfo.get('lang', None) is None:
476: docinfo['lang'] = '' # default keine Sprache gesetzt
477: if dom is None:
478: dom = self.getIndexMeta(url)
479:
480: archivePath = None
481: archiveName = None
482:
483: archiveNames = dom.xpath("//resource/name")
484: if archiveNames and (len(archiveNames) > 0):
485: archiveName = getTextFromNode(archiveNames[0])
486: else:
487: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url))
488:
489: archivePaths = dom.xpath("//resource/archive-path")
490: if archivePaths and (len(archivePaths) > 0):
491: archivePath = getTextFromNode(archivePaths[0])
492: # clean up archive path
493: if archivePath[0] != '/':
494: archivePath = '/' + archivePath
495: if archiveName and (not archivePath.endswith(archiveName)):
496: archivePath += "/" + archiveName
497: else:
498: # try to get archive-path from url
499: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url))
500: if (not url.startswith('http')):
501: archivePath = url.replace('index.meta', '')
502:
503: if archivePath is None:
504: # we balk without archive-path
505: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
506:
507: imageDirs = dom.xpath("//texttool/image")
508: if imageDirs and (len(imageDirs) > 0):
509: imageDir = getTextFromNode(imageDirs[0])
510:
511: else:
512: # we balk with no image tag / not necessary anymore because textmode is now standard
513: #raise IOError("No text-tool info in %s"%(url))
514: imageDir = ""
515: #xquery="//pb"
516: docinfo['imagePath'] = "" # keine Bilder
517: docinfo['imageURL'] = ""
518:
519: if imageDir and archivePath:
520: #print "image: ", imageDir, " archivepath: ", archivePath
521: imageDir = os.path.join(archivePath, imageDir)
522: imageDir = imageDir.replace("/mpiwg/online", '')
523: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
524: docinfo['imagePath'] = imageDir
525:
526: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
527:
528: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
529: if viewerUrls and (len(viewerUrls) > 0):
530: viewerUrl = getTextFromNode(viewerUrls[0])
531: docinfo['viewerURL'] = viewerUrl
532:
533: textUrls = dom.xpath("//texttool/text")
534: if textUrls and (len(textUrls) > 0):
535: textUrl = getTextFromNode(textUrls[0])
536: if urlparse.urlparse(textUrl)[0] == "": #keine url
537: textUrl = os.path.join(archivePath, textUrl)
538: # fix URLs starting with /mpiwg/online
539: if textUrl.startswith("/mpiwg/online"):
540: textUrl = textUrl.replace("/mpiwg/online", '', 1)
541:
542: docinfo['textURL'] = textUrl
543:
544: textUrls = dom.xpath("//texttool/text-url-path")
545: if textUrls and (len(textUrls) > 0):
546: textUrl = getTextFromNode(textUrls[0])
547: docinfo['textURLPath'] = textUrl
548:
549: presentationUrls = dom.xpath("//texttool/presentation")
550: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
551:
552: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
553: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
554: # durch den relativen Pfad auf die presentation infos
555: presentationPath = getTextFromNode(presentationUrls[0])
556: if url.endswith("index.meta"):
557: presentationUrl = url.replace('index.meta', presentationPath)
558: else:
559: presentationUrl = url + "/" + presentationPath
560: docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
561: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
562:
563: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 564:
1.43 casties 565: return docinfo
1.3 casties 566:
1.20 dwinter 567:
568: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
569: """gets the bibliographical information from the preseantion entry in texttools
570: """
571: dom=self.getPresentationInfoXML(url)
1.29 casties 572: try:
573: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
574: except:
575: pass
576: try:
577: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
578: except:
579: pass
580: try:
581: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
582: except:
583: pass
1.20 dwinter 584: return docinfo
585:
1.33 dwinter 586: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 587: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.22 dwinter 588: logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))
1.3 casties 589: if docinfo is None:
590: docinfo = {}
1.6 casties 591: path=path.replace("/mpiwg/online","")
1.3 casties 592: docinfo['imagePath'] = path
1.35 dwinter 593: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 594:
1.39 dwinter 595: pathorig=path
1.38 dwinter 596: for x in range(cut):
597: path=getParentDir(path)
598: logging.error("PATH:"+path)
1.7 casties 599: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 600: docinfo['imageURL'] = imageUrl
601:
1.39 dwinter 602: #path ist the path to the images it assumes that the index.meta file is one level higher.
603: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
604: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 605: return docinfo
606:
1.2 dwinter 607:
1.3 casties 608: def getDocinfo(self, mode, url):
609: """returns docinfo depending on mode"""
1.22 dwinter 610: logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))
1.3 casties 611: # look for cached docinfo in session
1.21 dwinter 612: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 613: docinfo = self.REQUEST.SESSION['docinfo']
614: # check if its still current
615: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.22 dwinter 616: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)
1.3 casties 617: return docinfo
618: # new docinfo
619: docinfo = {'mode': mode, 'url': url}
620: if mode=="texttool": #index.meta with texttool information
621: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
622: elif mode=="imagepath":
623: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 624: elif mode=="filepath":
1.37 dwinter 625: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 626: else:
1.22 dwinter 627: logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
1.44 casties 628: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 629:
1.22 dwinter 630: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
1.3 casties 631: self.REQUEST.SESSION['docinfo'] = docinfo
632: return docinfo
1.2 dwinter 633:
634:
1.44 casties 635: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 636: """returns pageinfo with the given parameters"""
637: pageinfo = {}
1.4 casties 638: current = getInt(current)
639: pageinfo['current'] = current
640: rows = int(rows or self.thumbrows)
641: pageinfo['rows'] = rows
642: cols = int(cols or self.thumbcols)
643: pageinfo['cols'] = cols
644: grpsize = cols * rows
645: pageinfo['groupsize'] = grpsize
1.28 casties 646: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
647: # int(current / grpsize) * grpsize +1))
1.3 casties 648: pageinfo['start'] = start
1.4 casties 649: pageinfo['end'] = start + grpsize
1.44 casties 650: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 651: np = int(docinfo['numPages'])
652: pageinfo['end'] = min(pageinfo['end'], np)
653: pageinfo['numgroups'] = int(np / grpsize)
654: if np % grpsize > 0:
655: pageinfo['numgroups'] += 1
1.44 casties 656:
657: pageinfo['viewMode'] = viewMode
658: pageinfo['tocMode'] = tocMode
1.45 abukhman 659: pageinfo['query'] = self.REQUEST.get('query',' ')
660: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
661: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
662: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
663: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '20')
1.44 casties 664: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.47 ! abukhman 665: #if 'tocSize_%s'%tocMode in docinfo:
! 666: # cached toc
! 667: # pageinfo['tocPN'] = min (int (docinfo['tocSize_%s'%tocMode])/int(pageinfo['tocPageSize']),int(pageinfo['tocPN']))
! 668:
1.45 abukhman 669: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
670: pageinfo['sn'] =self.REQUEST.get('sn','1')
1.38 dwinter 671:
1.3 casties 672: return pageinfo
673:
1.45 abukhman 674: def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None):
675: """get search list"""
676: docpath = docinfo['textURLPath']
677: pagesize = pageinfo['queryPageSize']
678: pn = pageinfo['searchPN']
679: sn = pageinfo['sn']
680: query =pageinfo['query']
681: queryType =pageinfo['queryType']
1.46 abukhman 682: viewMode= pageinfo['viewMode']
683: tocMode = pageinfo['tocMode']
684: tocPN = pageinfo['tocPN']
1.45 abukhman 685: 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)
686: pagedom = Parse(pagexml)
1.47 ! abukhman 687: pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
! 688:
1.46 abukhman 689: selfurl = self.absolute_url()
1.47 ! abukhman 690:
1.46 abukhman 691: 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))
692: text =page.replace('mode=text','mode=texttool')
1.47 ! abukhman 693: href = text.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
! 694: lemma= href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
! 695: #logging.debug("documentViewer (gettoc) lemma: %s"%(lemma))
! 696:
! 697: return lemma
! 698:
! 699:
1.45 abukhman 700: #if len(pagedivs) > 0:
701: # pagenode = pagedom[0]
702: # return serializeNode(pagenode)
703: #else:
704: # return "xaxa"
1.43 casties 705:
706: def getNumPages(self,docinfo=None):
707: """get list of pages from fulltext and put in docinfo"""
708: xquery = '//pb'
709: text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
710: # TODO: better processing of the page list. do we need the info somewhere else also?
711: docinfo['numPages'] = text.count("<pb ")
712: return docinfo
713:
1.46 abukhman 714: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None,):
1.43 casties 715: """returns single page from fulltext"""
1.44 casties 716: docpath = docinfo['textURLPath']
717: if mode == "text_dict":
718: textmode = "textPollux"
719: else:
720: textmode = mode
721:
1.46 abukhman 722: #selfurl = self.absolute_url()
723: #viewMode= pageinfo['viewMode']
724: #tocMode = pageinfo['tocMode']
725: #tocPN = pageinfo['tocPN']
726:
1.44 casties 727: pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False)
1.45 abukhman 728: #######
1.46 abukhman 729: #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))
730: #text =page.replace('mode=text','mode=texttool')
1.45 abukhman 731: #######
1.43 casties 732: # post-processing downloaded xml
733: pagedom = Parse(pagexml)
734: # plain text mode
735: if mode == "text":
736: # first div contains text
737: pagedivs = pagedom.xpath("/div")
1.45 abukhman 738: #queryResultPage
1.43 casties 739: if len(pagedivs) > 0:
740: pagenode = pagedivs[0]
741: return serializeNode(pagenode)
742:
743: # text-with-links mode
1.44 casties 744: if mode == "text_dict":
1.43 casties 745: # first div contains text
746: pagedivs = pagedom.xpath("/div")
747: if len(pagedivs) > 0:
748: pagenode = pagedivs[0]
749: # check all a-tags
750: links = pagenode.xpath("//a")
751: for l in links:
752: hrefNode = l.getAttributeNodeNS(None, u"href")
753: if hrefNode:
754: # is link with href
755: href = hrefNode.nodeValue
756: if href.startswith('lt/lex.xql'):
757: # is pollux link
758: selfurl = self.absolute_url()
759: # change href
1.46 abukhman 760: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
1.43 casties 761: # add target
762: l.setAttributeNS(None, 'target', '_blank')
1.46 abukhman 763:
764: if href.startswith('lt/lemma.xql'):
765: selfurl = self.absolute_url()
766: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
767: l.setAttributeNS(None, 'target', '_blank')
1.43 casties 768: return serializeNode(pagenode)
1.1 dwinter 769:
1.43 casties 770: return "no text here"
1.3 casties 771:
1.46 abukhman 772: def getTranslate(self, query=None, language=None):
773: """translate into another languages"""
774: pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","query=%s&language=%s"%(query,language),outputUnicode=False)
775: return pagexml
776:
1.47 ! abukhman 777: def getLemma(self, lemma=None, language=None):
1.46 abukhman 778: """lemma"""
1.47 ! abukhman 779: pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","lemma=%s&language=%s"%(lemma,language),outputUnicode=False)
1.46 abukhman 780: return pagexml
781:
1.47 ! abukhman 782: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
! 783: """number of"""
! 784: docpath = docinfo['textURLPath']
! 785: pagesize = pageinfo['queryPageSize']
! 786: pn = pageinfo['searchPN']
! 787: query =pageinfo['query']
! 788: queryType =pageinfo['queryType']
! 789:
! 790: tocSearch = 0
! 791: tocDiv = None
! 792: pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn) ,outputUnicode=False)
! 793:
! 794: pagedom = Parse(pagexml)
! 795: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
! 796: tocSearch = int(getTextFromNode(numdivs[0]))
! 797: tc=int((tocSearch/20)+1)
! 798: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
! 799: return tc
! 800:
1.44 casties 801: def getToc(self, mode="text", docinfo=None):
802: """loads table of contents and stores in docinfo"""
803: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
804: if 'tocSize_%s'%mode in docinfo:
805: # cached toc
1.47 ! abukhman 806: return docinfo
1.44 casties 807: docpath = docinfo['textURLPath']
808: # we need to set a result set size
809: pagesize = 1000
810: pn = 1
811: if mode == "text":
812: queryType = "toc"
813: else:
814: queryType = mode
815: # number of entries in toc
816: tocSize = 0
817: tocDiv = None
818: pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
819: # post-processing downloaded xml
820: pagedom = Parse(pagexml)
821: # get number of entries
822: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
823: if len(numdivs) > 0:
824: tocSize = int(getTextFromNode(numdivs[0]))
825: # div contains text
826: #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
827: #if len(pagedivs) > 0:
828: # tocDiv = pagedivs[0]
829:
830: docinfo['tocSize_%s'%mode] = tocSize
831: #docinfo['tocDiv_%s'%mode] = tocDiv
832: return docinfo
833:
1.45 abukhman 834: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
1.44 casties 835: """returns single page from the table of contents"""
836: # TODO: this should use the cached TOC
837: if mode == "text":
838: queryType = "toc"
839: else:
840: queryType = mode
841: docpath = docinfo['textURLPath']
842: pagesize = pageinfo['tocPageSize']
843: pn = pageinfo['tocPN']
1.46 abukhman 844:
845: selfurl = self.absolute_url()
846: viewMode= pageinfo['viewMode']
847: tocMode = pageinfo['tocMode']
848: tocPN = pageinfo['tocPN']
849:
1.45 abukhman 850: 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 851: 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))
852: text = page.replace('mode=image','mode=texttool')
853: return text
1.44 casties 854: # post-processing downloaded xml
1.46 abukhman 855: #pagedom = Parse(text)
1.44 casties 856: # div contains text
1.46 abukhman 857: #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
858: #if len(pagedivs) > 0:
859: # pagenode = pagedivs[0]
860: # return serializeNode(pagenode)
861: #else:
862: # return "No TOC!"
1.44 casties 863:
1.3 casties 864:
1.45 abukhman 865: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 866: """init document viewer"""
867: self.title=title
868: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 869: self.thumbrows = thumbrows
870: self.thumbcols = thumbcols
1.8 casties 871: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 872: if RESPONSE is not None:
873: RESPONSE.redirect('manage_main')
1.1 dwinter 874:
875:
876:
877: def manage_AddDocumentViewerForm(self):
878: """add the viewer form"""
1.3 casties 879: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 880: return pt()
881:
1.43 casties 882: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 883: """add the viewer"""
1.43 casties 884: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 885: self._setObject(id,newObj)
886:
887: if RESPONSE is not None:
888: RESPONSE.redirect('manage_main')
1.3 casties 889:
890:
891: ##
892: ## DocumentViewerTemplate class
893: ##
894: class DocumentViewerTemplate(ZopePageTemplate):
895: """Template for document viewer"""
896: meta_type="DocumentViewer Template"
897:
898:
899: def manage_addDocumentViewerTemplateForm(self):
900: """Form for adding"""
901: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
902: return pt()
903:
904: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
905: REQUEST=None, submit=None):
906: "Add a Page Template with optional file content."
907:
908: self._setObject(id, DocumentViewerTemplate(id))
909: ob = getattr(self, id)
1.23 dwinter 910: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
911: logging.info("txt %s:"%txt)
912: ob.pt_edit(txt,"text/html")
1.3 casties 913: if title:
914: ob.pt_setTitle(title)
915: try:
916: u = self.DestinationURL()
917: except AttributeError:
918: u = REQUEST['URL1']
919:
920: u = "%s/%s" % (u, urllib.quote(id))
921: REQUEST.RESPONSE.redirect(u+'/manage_main')
922: return ''
923:
924:
1.14 casties 925:
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