Annotation of documentViewer/documentViewer.py, revision 1.69.2.2
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
1.50 abukhman 5: from Products.PythonScripts.standard import url_quote
1.1 dwinter 6: from AccessControl import ClassSecurityInfo
1.8 casties 7: from AccessControl import getSecurityManager
1.1 dwinter 8: from Globals import package_home
9:
10: from Ft.Xml.Domlette import NonvalidatingReader
11: from Ft.Xml.Domlette import PrettyPrint, Print
1.11 casties 12: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.1 dwinter 13:
1.47 abukhman 14: from xml.dom.minidom import parse, parseString
15:
1.69.2.1 abukhman 16: from extraFunction import *
1.47 abukhman 17:
1.42 abukhman 18:
1.1 dwinter 19: import Ft.Xml.XPath
1.43 casties 20: import cStringIO
1.42 abukhman 21: import xmlrpclib
1.1 dwinter 22: import os.path
1.7 casties 23: import sys
1.1 dwinter 24: import cgi
25: import urllib
1.20 dwinter 26: import logging
1.28 casties 27: import math
1.22 dwinter 28:
1.18 dwinter 29: import urlparse
1.37 dwinter 30: from types import *
1.43 casties 31:
1.22 dwinter 32: def logger(txt,method,txt2):
33: """logging"""
34: logging.info(txt+ txt2)
35:
36:
1.4 casties 37: def getInt(number, default=0):
38: """returns always an int (0 in case of problems)"""
39: try:
40: return int(number)
41: except:
1.29 casties 42: return int(default)
1.4 casties 43:
1.1 dwinter 44: def getTextFromNode(nodename):
1.18 dwinter 45: """get the cdata content of a node"""
1.8 casties 46: if nodename is None:
47: return ""
1.1 dwinter 48: nodelist=nodename.childNodes
49: rc = ""
50: for node in nodelist:
51: if node.nodeType == node.TEXT_NODE:
52: rc = rc + node.data
53: return rc
54:
1.43 casties 55: def serializeNode(node, encoding='utf-8'):
56: """returns a string containing node as XML"""
57: buf = cStringIO.StringIO()
58: Print(node, stream=buf, encoding=encoding)
59: s = buf.getvalue()
60: buf.close()
61: return s
62:
1.9 casties 63:
64: def getParentDir(path):
65: """returns pathname shortened by one"""
66: return '/'.join(path.split('/')[0:-1])
67:
68:
1.1 dwinter 69: import socket
70:
1.8 casties 71: def urlopen(url,timeout=2):
1.1 dwinter 72: """urlopen mit timeout"""
1.8 casties 73: socket.setdefaulttimeout(timeout)
1.1 dwinter 74: ret=urllib.urlopen(url)
75: socket.setdefaulttimeout(5)
76: return ret
77:
78:
1.3 casties 79: ##
80: ## documentViewer class
81: ##
1.69.2.1 abukhman 82: class documentViewer(Folder, extraFunction):
1.1 dwinter 83: """document viewer"""
1.20 dwinter 84: #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"
1.18 dwinter 85:
1.1 dwinter 86: meta_type="Document viewer"
87:
88: security=ClassSecurityInfo()
1.3 casties 89: manage_options=Folder.manage_options+(
1.1 dwinter 90: {'label':'main config','action':'changeDocumentViewerForm'},
91: )
92:
1.3 casties 93: # templates and forms
94: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 95: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
96: toc_text = PageTemplateFile('zpt/toc_text', globals())
97: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 98: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
99: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 100: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.48 abukhman 101: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 102: head_main = PageTemplateFile('zpt/head_main', globals())
103: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 104: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.69.2.1 abukhman 105:
106:
1.32 dwinter 107: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 108: security.declareProtected('View management screens','changeDocumentViewerForm')
109: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
110:
1.1 dwinter 111:
1.45 abukhman 112: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 113: """init document viewer"""
114: self.id=id
115: self.title=title
1.4 casties 116: self.thumbcols = thumbcols
117: self.thumbrows = thumbrows
1.8 casties 118: # authgroups is list of authorized groups (delimited by ,)
119: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 120: # create template folder so we can always use template.something
121:
122: templateFolder = Folder('template')
123: #self['template'] = templateFolder # Zope-2.12 style
124: self._setObject('template',templateFolder) # old style
125: try:
126: from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy
127: xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False)
128: #templateFolder['fulltextclient'] = xmlRpcClient
129: templateFolder._setObject('fulltextclient',xmlRpcClient)
130: except Exception, e:
131: logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e))
132: try:
133: from Products.zogiLib.zogiLib import zogiLib
134: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
135: #templateFolder['zogilib'] = zogilib
136: templateFolder._setObject('zogilib',zogilib)
137: except Exception, e:
138: logging.error("Unable to create zogiLib for zogilib: "+str(e))
139:
1.3 casties 140:
1.32 dwinter 141: security.declareProtected('View','thumbs_rss')
142: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
143: '''
144: view it
145: @param mode: defines how to access the document behind url
146: @param url: url which contains display information
147: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
148:
149: '''
1.43 casties 150: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.32 dwinter 151: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
152:
153: if not hasattr(self, 'template'):
154: # create template folder if it doesn't exist
155: self.manage_addFolder('template')
156:
157: if not self.digilibBaseUrl:
158: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
159:
160: docinfo = self.getDocinfo(mode=mode,url=url)
161: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
162: pt = getattr(self.template, 'thumbs_main_rss')
163:
164: if viewMode=="auto": # automodus gewaehlt
165: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
166: viewMode="text"
167: else:
168: viewMode="images"
169:
170: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
171:
1.3 casties 172: security.declareProtected('View','index_html')
1.45 abukhman 173: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
1.3 casties 174: '''
175: view it
1.26 casties 176: @param mode: defines how to access the document behind url
1.3 casties 177: @param url: url which contains display information
1.44 casties 178: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 179: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.49 abukhman 180: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 181: '''
182:
1.43 casties 183: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 184:
1.3 casties 185: if not hasattr(self, 'template'):
1.43 casties 186: # this won't work
187: logging.error("template folder missing!")
188: return "ERROR: template folder missing!"
1.3 casties 189:
1.43 casties 190: if not getattr(self, 'digilibBaseUrl', None):
1.3 casties 191: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
192:
1.4 casties 193: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 194:
195:
1.44 casties 196: if tocMode != "thumbs":
197: # get table of contents
198: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 199:
1.21 dwinter 200: if viewMode=="auto": # automodus gewaehlt
1.43 casties 201: if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
1.68 casties 202: viewMode="text_dict"
1.21 dwinter 203: else:
204: viewMode="images"
1.44 casties 205:
1.68 casties 206: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
207:
1.44 casties 208: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 209: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 210:
1.36 dwinter 211: def generateMarks(self,mk):
212: ret=""
1.44 casties 213: if mk is None:
214: return ""
215: if type(mk) is not ListType:
216: mk=[mk]
1.36 dwinter 217: for m in mk:
1.37 dwinter 218: ret+="mk=%s"%m
1.36 dwinter 219: return ret
1.43 casties 220:
1.44 casties 221:
1.43 casties 222: def findDigilibUrl(self):
223: """try to get the digilib URL from zogilib"""
224: url = self.template.zogilib.getDLBaseUrl()
225: return url
1.67 casties 226:
227: def getDocumentViewerURL(self):
228: """returns the URL of this instance"""
229: return self.absolute_url()
1.43 casties 230:
231: def getStyle(self, idx, selected, style=""):
232: """returns a string with the given style and append 'sel' if path == selected."""
233: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
234: if idx == selected:
235: return style + 'sel'
236: else:
237: return style
1.36 dwinter 238:
1.4 casties 239: def getLink(self,param=None,val=None):
240: """link to documentviewer with parameter param set to val"""
1.9 casties 241: params=self.REQUEST.form.copy()
1.4 casties 242: if param is not None:
1.7 casties 243: if val is None:
244: if params.has_key(param):
245: del params[param]
1.4 casties 246: else:
1.9 casties 247: params[param] = str(val)
1.43 casties 248:
249: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 250: params["mode"] = "imagepath"
251: params["url"] = getParentDir(params["url"])
1.7 casties 252:
1.9 casties 253: # quote values and assemble into query string
254: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
255: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 256: return url
257:
1.32 dwinter 258: def getLinkAmp(self,param=None,val=None):
259: """link to documentviewer with parameter param set to val"""
260: params=self.REQUEST.form.copy()
261: if param is not None:
262: if val is None:
263: if params.has_key(param):
264: del params[param]
265: else:
266: params[param] = str(val)
267:
268: # quote values and assemble into query string
1.69.2.2! casties 269: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 270: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
271: url=self.REQUEST['URL1']+"?"+ps
272: return url
1.40 casties 273:
1.26 casties 274: def getInfo_xml(self,url,mode):
275: """returns info about the document as XML"""
276:
277: if not self.digilibBaseUrl:
278: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
279:
280: docinfo = self.getDocinfo(mode=mode,url=url)
281: pt = getattr(self.template, 'info_xml')
282: return pt(docinfo=docinfo)
283:
1.4 casties 284:
1.9 casties 285: def isAccessible(self, docinfo):
1.8 casties 286: """returns if access to the resource is granted"""
287: access = docinfo.get('accessType', None)
1.69.2.2! casties 288: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 289: if access is not None and access == 'free':
1.69.2.2! casties 290: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 291: return True
1.17 casties 292: elif access is None or access in self.authgroups:
1.9 casties 293: # only local access -- only logged in users
294: user = getSecurityManager().getUser()
295: if user is not None:
296: #print "user: ", user
297: return (user.getUserName() != "Anonymous User")
298: else:
299: return False
1.8 casties 300:
1.69.2.2! casties 301: logging.debug("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 302: return False
1.9 casties 303:
1.8 casties 304:
1.35 dwinter 305: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 306: """gibt param von dlInfo aus"""
1.13 casties 307: num_retries = 3
1.7 casties 308: if docinfo is None:
309: docinfo = {}
1.35 dwinter 310:
311: for x in range(cut):
1.38 dwinter 312:
1.35 dwinter 313: path=getParentDir(path)
1.38 dwinter 314:
1.13 casties 315: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 316:
1.69.2.2! casties 317: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 318:
1.13 casties 319: for cnt in range(num_retries):
1.9 casties 320: try:
1.13 casties 321: # dom = NonvalidatingReader.parseUri(imageUrl)
322: txt=urllib.urlopen(infoUrl).read()
323: dom = Parse(txt)
1.9 casties 324: break
325: except:
1.69.2.2! casties 326: logging.error("documentViewer (getdirinfofromdigilib) error reading %s (try %d)"%(infoUrl,cnt))
1.9 casties 327: else:
1.13 casties 328: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.6 casties 329:
1.10 casties 330: sizes=dom.xpath("//dir/size")
1.69.2.2! casties 331: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 332:
1.10 casties 333: if sizes:
334: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 335: else:
336: docinfo['numPages'] = 0
1.43 casties 337:
338: # TODO: produce and keep list of image names and numbers
1.7 casties 339:
340: return docinfo
1.8 casties 341:
1.6 casties 342:
1.9 casties 343: def getIndexMeta(self, url):
344: """returns dom of index.meta document at url"""
1.12 casties 345: num_retries = 3
1.9 casties 346: dom = None
1.12 casties 347: metaUrl = None
1.9 casties 348: if url.startswith("http://"):
349: # real URL
1.12 casties 350: metaUrl = url
1.9 casties 351: else:
352: # online path
353: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 354: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 355: if not metaUrl.endswith("index.meta"):
356: metaUrl += "/index.meta"
1.37 dwinter 357: logging.debug("METAURL: %s"%metaUrl)
1.13 casties 358: for cnt in range(num_retries):
1.9 casties 359: try:
1.12 casties 360: # patch dirk encoding fehler treten dann nicht mehr auf
1.11 casties 361: # dom = NonvalidatingReader.parseUri(metaUrl)
1.12 casties 362: txt=urllib.urlopen(metaUrl).read()
363: dom = Parse(txt)
1.13 casties 364: break
1.9 casties 365: except:
1.69.2.2! casties 366: logging.error("ERROR documentViewer (getIndexMeta) %s (%s)"%sys.exc_info()[0:2])
1.12 casties 367:
368: if dom is None:
369: raise IOError("Unable to read index meta from %s"%(url))
1.9 casties 370:
371: return dom
1.20 dwinter 372:
373: def getPresentationInfoXML(self, url):
374: """returns dom of info.xml document at url"""
375: num_retries = 3
376: dom = None
377: metaUrl = None
378: if url.startswith("http://"):
379: # real URL
380: metaUrl = url
381: else:
382: # online path
383: server=self.digilibBaseUrl+"/servlet/Texter?fn="
384: metaUrl=server+url.replace("/mpiwg/online","")
385:
386: for cnt in range(num_retries):
387: try:
388: # patch dirk encoding fehler treten dann nicht mehr auf
389: # dom = NonvalidatingReader.parseUri(metaUrl)
390: txt=urllib.urlopen(metaUrl).read()
391: dom = Parse(txt)
392: break
393: except:
1.69.2.2! casties 394: logging.error("ERROR documentViewer (getPresentationInfoXML) %s (%s)"%sys.exc_info()[0:2])
1.20 dwinter 395:
396: if dom is None:
397: raise IOError("Unable to read infoXMLfrom %s"%(url))
398:
399: return dom
1.9 casties 400:
401:
1.33 dwinter 402: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 403: """gets authorization info from the index.meta file at path or given by dom"""
1.69.2.2! casties 404: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 405:
406: access = None
407:
408: if docinfo is None:
409: docinfo = {}
410:
411: if dom is None:
1.38 dwinter 412: for x in range(cut):
1.33 dwinter 413: path=getParentDir(path)
414: dom = self.getIndexMeta(path)
1.18 dwinter 415:
1.8 casties 416: acctype = dom.xpath("//access-conditions/access/@type")
417: if acctype and (len(acctype)>0):
418: access=acctype[0].value
1.9 casties 419: if access in ['group', 'institution']:
1.8 casties 420: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
421:
422: docinfo['accessType'] = access
423: return docinfo
1.6 casties 424:
1.8 casties 425:
1.33 dwinter 426: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 427: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 428: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 429:
1.3 casties 430: if docinfo is None:
431: docinfo = {}
1.38 dwinter 432:
1.3 casties 433: if dom is None:
1.38 dwinter 434: for x in range(cut):
1.33 dwinter 435: path=getParentDir(path)
436: dom = self.getIndexMeta(path)
1.39 dwinter 437:
438: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 439: # put in all raw bib fields as dict "bib"
440: bib = dom.xpath("//bib/*")
441: if bib and len(bib)>0:
442: bibinfo = {}
443: for e in bib:
444: bibinfo[e.localName] = getTextFromNode(e)
445: docinfo['bib'] = bibinfo
446:
447: # extract some fields (author, title, year) according to their mapping
1.4 casties 448: metaData=self.metadata.main.meta.bib
449: bibtype=dom.xpath("//bib/@type")
450: if bibtype and (len(bibtype)>0):
451: bibtype=bibtype[0].value
1.2 dwinter 452: else:
1.4 casties 453: bibtype="generic"
1.27 casties 454:
1.4 casties 455: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 456: docinfo['bib_type'] = bibtype
1.4 casties 457: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 458: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 459: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 460: try:
461: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
462: except: pass
463: try:
464: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
465: except: pass
466: try:
467: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
468: except: pass
1.27 casties 469: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 470: try:
471: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
472: except:
473: docinfo['lang']=''
1.27 casties 474:
1.3 casties 475: return docinfo
1.42 abukhman 476:
477:
1.43 casties 478: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
479: """parse texttool tag in index meta"""
1.69.2.2! casties 480: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 481: if docinfo is None:
482: docinfo = {}
483: if docinfo.get('lang', None) is None:
484: docinfo['lang'] = '' # default keine Sprache gesetzt
485: if dom is None:
486: dom = self.getIndexMeta(url)
487:
488: archivePath = None
489: archiveName = None
490:
491: archiveNames = dom.xpath("//resource/name")
492: if archiveNames and (len(archiveNames) > 0):
493: archiveName = getTextFromNode(archiveNames[0])
494: else:
1.69.2.2! casties 495: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 496:
497: archivePaths = dom.xpath("//resource/archive-path")
498: if archivePaths and (len(archivePaths) > 0):
499: archivePath = getTextFromNode(archivePaths[0])
500: # clean up archive path
501: if archivePath[0] != '/':
502: archivePath = '/' + archivePath
503: if archiveName and (not archivePath.endswith(archiveName)):
504: archivePath += "/" + archiveName
505: else:
506: # try to get archive-path from url
1.69.2.2! casties 507: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 508: if (not url.startswith('http')):
509: archivePath = url.replace('index.meta', '')
510:
511: if archivePath is None:
512: # we balk without archive-path
513: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
514:
515: imageDirs = dom.xpath("//texttool/image")
516: if imageDirs and (len(imageDirs) > 0):
517: imageDir = getTextFromNode(imageDirs[0])
518:
519: else:
520: # we balk with no image tag / not necessary anymore because textmode is now standard
521: #raise IOError("No text-tool info in %s"%(url))
522: imageDir = ""
523: #xquery="//pb"
524: docinfo['imagePath'] = "" # keine Bilder
525: docinfo['imageURL'] = ""
526:
527: if imageDir and archivePath:
528: #print "image: ", imageDir, " archivepath: ", archivePath
529: imageDir = os.path.join(archivePath, imageDir)
530: imageDir = imageDir.replace("/mpiwg/online", '')
531: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
532: docinfo['imagePath'] = imageDir
533:
534: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
535:
536: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
537: if viewerUrls and (len(viewerUrls) > 0):
538: viewerUrl = getTextFromNode(viewerUrls[0])
539: docinfo['viewerURL'] = viewerUrl
540:
541: textUrls = dom.xpath("//texttool/text")
542: if textUrls and (len(textUrls) > 0):
543: textUrl = getTextFromNode(textUrls[0])
544: if urlparse.urlparse(textUrl)[0] == "": #keine url
545: textUrl = os.path.join(archivePath, textUrl)
546: # fix URLs starting with /mpiwg/online
547: if textUrl.startswith("/mpiwg/online"):
548: textUrl = textUrl.replace("/mpiwg/online", '', 1)
549:
550: docinfo['textURL'] = textUrl
551:
552: textUrls = dom.xpath("//texttool/text-url-path")
553: if textUrls and (len(textUrls) > 0):
554: textUrl = getTextFromNode(textUrls[0])
1.51 casties 555: docinfo['textURLPath'] = textUrl
556: if not docinfo['imagePath']:
557: # text-only, no page images
558: docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
1.43 casties 559:
560: presentationUrls = dom.xpath("//texttool/presentation")
561: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
562:
563: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
564: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
565: # durch den relativen Pfad auf die presentation infos
566: presentationPath = getTextFromNode(presentationUrls[0])
567: if url.endswith("index.meta"):
568: presentationUrl = url.replace('index.meta', presentationPath)
569: else:
570: presentationUrl = url + "/" + presentationPath
1.51 casties 571:
1.43 casties 572: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
573:
574: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 575:
1.43 casties 576: return docinfo
1.3 casties 577:
1.20 dwinter 578:
579: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
580: """gets the bibliographical information from the preseantion entry in texttools
581: """
582: dom=self.getPresentationInfoXML(url)
1.29 casties 583: try:
584: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
585: except:
586: pass
587: try:
588: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
589: except:
590: pass
591: try:
592: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
593: except:
594: pass
1.20 dwinter 595: return docinfo
596:
1.33 dwinter 597: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 598: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.69.2.2! casties 599: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 600: if docinfo is None:
601: docinfo = {}
1.6 casties 602: path=path.replace("/mpiwg/online","")
1.3 casties 603: docinfo['imagePath'] = path
1.35 dwinter 604: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 605:
1.39 dwinter 606: pathorig=path
1.38 dwinter 607: for x in range(cut):
608: path=getParentDir(path)
1.69.2.2! casties 609: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 610: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 611: docinfo['imageURL'] = imageUrl
612:
1.39 dwinter 613: #path ist the path to the images it assumes that the index.meta file is one level higher.
614: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
615: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 616: return docinfo
617:
1.2 dwinter 618:
1.3 casties 619: def getDocinfo(self, mode, url):
620: """returns docinfo depending on mode"""
1.69.2.2! casties 621: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 622: # look for cached docinfo in session
1.21 dwinter 623: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 624: docinfo = self.REQUEST.SESSION['docinfo']
625: # check if its still current
626: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.69.2.2! casties 627: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 628: return docinfo
629: # new docinfo
630: docinfo = {'mode': mode, 'url': url}
631: if mode=="texttool": #index.meta with texttool information
632: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
633: elif mode=="imagepath":
634: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 635: elif mode=="filepath":
1.37 dwinter 636: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 637: else:
1.69.2.2! casties 638: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 639: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 640:
1.69.2.2! casties 641: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 642: self.REQUEST.SESSION['docinfo'] = docinfo
643: return docinfo
1.69 abukhman 644:
1.44 casties 645: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 646: """returns pageinfo with the given parameters"""
647: pageinfo = {}
1.4 casties 648: current = getInt(current)
649: pageinfo['current'] = current
650: rows = int(rows or self.thumbrows)
651: pageinfo['rows'] = rows
652: cols = int(cols or self.thumbcols)
653: pageinfo['cols'] = cols
654: grpsize = cols * rows
655: pageinfo['groupsize'] = grpsize
1.28 casties 656: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
657: # int(current / grpsize) * grpsize +1))
1.3 casties 658: pageinfo['start'] = start
1.4 casties 659: pageinfo['end'] = start + grpsize
1.44 casties 660: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 661: np = int(docinfo['numPages'])
662: pageinfo['end'] = min(pageinfo['end'], np)
663: pageinfo['numgroups'] = int(np / grpsize)
664: if np % grpsize > 0:
1.69 abukhman 665: pageinfo['numgroups'] += 1
1.44 casties 666: pageinfo['viewMode'] = viewMode
667: pageinfo['tocMode'] = tocMode
1.45 abukhman 668: pageinfo['query'] = self.REQUEST.get('query',' ')
669: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
670: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 671: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 672: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 673: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 674: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 675: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 676: toc = int (pageinfo['tocPN'])
677: pageinfo['textPages'] =int (toc)
678:
679: if 'tocSize_%s'%tocMode in docinfo:
680: tocSize = int(docinfo['tocSize_%s'%tocMode])
681: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 682: # cached toc
1.48 abukhman 683: if tocSize%tocPageSize>0:
684: tocPages=tocSize/tocPageSize+1
685: else:
686: tocPages=tocSize/tocPageSize
1.69 abukhman 687: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 688: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 689: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 690: return pageinfo
691:
1.69 abukhman 692: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 693: """init document viewer"""
694: self.title=title
695: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 696: self.thumbrows = thumbrows
697: self.thumbcols = thumbcols
1.8 casties 698: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 699: if RESPONSE is not None:
700: RESPONSE.redirect('manage_main')
1.1 dwinter 701:
702: def manage_AddDocumentViewerForm(self):
703: """add the viewer form"""
1.3 casties 704: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 705: return pt()
706:
1.43 casties 707: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 708: """add the viewer"""
1.43 casties 709: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 710: self._setObject(id,newObj)
711:
712: if RESPONSE is not None:
713: RESPONSE.redirect('manage_main')
1.3 casties 714:
715: ## DocumentViewerTemplate class
716: class DocumentViewerTemplate(ZopePageTemplate):
717: """Template for document viewer"""
718: meta_type="DocumentViewer Template"
719:
720:
721: def manage_addDocumentViewerTemplateForm(self):
722: """Form for adding"""
723: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
724: return pt()
725:
726: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
727: REQUEST=None, submit=None):
728: "Add a Page Template with optional file content."
729:
730: self._setObject(id, DocumentViewerTemplate(id))
731: ob = getattr(self, id)
1.23 dwinter 732: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
733: logging.info("txt %s:"%txt)
734: ob.pt_edit(txt,"text/html")
1.3 casties 735: if title:
736: ob.pt_setTitle(title)
737: try:
738: u = self.DestinationURL()
739: except AttributeError:
740: u = REQUEST['URL1']
741:
742: u = "%s/%s" % (u, urllib.quote(id))
743: REQUEST.RESPONSE.redirect(u+'/manage_main')
744: return ''
745:
746:
1.14 casties 747:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>