Annotation of documentViewer/documentViewer.py, revision 1.69.2.6
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:
1.11 casties 9: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.1 dwinter 10: import os.path
1.7 casties 11: import sys
1.1 dwinter 12: import urllib
1.69.2.5 casties 13: import urllib2
1.20 dwinter 14: import logging
1.43 casties 15:
1.22 dwinter 16: def logger(txt,method,txt2):
17: """logging"""
18: logging.info(txt+ txt2)
19:
20:
1.4 casties 21: def getInt(number, default=0):
22: """returns always an int (0 in case of problems)"""
23: try:
24: return int(number)
25: except:
1.29 casties 26: return int(default)
1.4 casties 27:
1.1 dwinter 28: def getTextFromNode(nodename):
1.18 dwinter 29: """get the cdata content of a node"""
1.8 casties 30: if nodename is None:
31: return ""
1.1 dwinter 32: nodelist=nodename.childNodes
33: rc = ""
34: for node in nodelist:
35: if node.nodeType == node.TEXT_NODE:
36: rc = rc + node.data
37: return rc
38:
1.43 casties 39: def serializeNode(node, encoding='utf-8'):
40: """returns a string containing node as XML"""
41: buf = cStringIO.StringIO()
42: Print(node, stream=buf, encoding=encoding)
43: s = buf.getvalue()
44: buf.close()
45: return s
46:
1.9 casties 47:
48: def getParentDir(path):
49: """returns pathname shortened by one"""
50: return '/'.join(path.split('/')[0:-1])
51:
52:
1.69.2.3 casties 53: def getHttpData(url, data=None, num_tries=3, timeout=10):
54: """returns result from url+data HTTP request"""
55: # we do GET (by appending data to url)
56: if isinstance(data, str) or isinstance(data, unicode):
57: # if data is string then append
58: url = "%s?%s"%(url,data)
59: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
60: # urlencode
61: url = "%s?%s"%(url,urllib.urlencode(data))
62:
63: response = None
64: errmsg = None
65: for cnt in range(num_tries):
66: try:
67: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
68: if sys.version_info < (2, 6):
69: # set timeout on socket -- ugly :-(
70: import socket
71: socket.setdefaulttimeout(timeout)
72: response = urllib2.urlopen(url)
73: else:
74: response = urllib2.urlopen(url,timeout=float(timeout))
75: # check result?
76: break
77: except urllib2.HTTPError, e:
78: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
79: errmsg = str(e)
80: # stop trying
81: break
82: except urllib2.URLError, e:
83: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
84: errmsg = str(e)
85: # stop trying
86: #break
87:
88: if response is not None:
89: data = response.read()
90: response.close()
91: return data
92:
93: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
94: #return None
1.1 dwinter 95:
96:
97:
1.3 casties 98: ##
99: ## documentViewer class
100: ##
1.69.2.3 casties 101: class documentViewer(Folder):
1.1 dwinter 102: """document viewer"""
103: meta_type="Document viewer"
104:
105: security=ClassSecurityInfo()
1.3 casties 106: manage_options=Folder.manage_options+(
1.1 dwinter 107: {'label':'main config','action':'changeDocumentViewerForm'},
108: )
109:
1.3 casties 110: # templates and forms
111: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 112: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
113: toc_text = PageTemplateFile('zpt/toc_text', globals())
114: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 115: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
116: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 117: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.48 abukhman 118: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 119: head_main = PageTemplateFile('zpt/head_main', globals())
120: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 121: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.69.2.1 abukhman 122:
123:
1.32 dwinter 124: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 125: security.declareProtected('View management screens','changeDocumentViewerForm')
126: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
127:
1.1 dwinter 128:
1.45 abukhman 129: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 130: """init document viewer"""
131: self.id=id
132: self.title=title
1.4 casties 133: self.thumbcols = thumbcols
134: self.thumbrows = thumbrows
1.8 casties 135: # authgroups is list of authorized groups (delimited by ,)
136: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 137: # create template folder so we can always use template.something
138:
139: templateFolder = Folder('template')
140: #self['template'] = templateFolder # Zope-2.12 style
141: self._setObject('template',templateFolder) # old style
142: try:
1.69.2.3 casties 143: import MpdlXmlTextServer
144: textServer = MpdlXmlTextServer(id='fulltextclient')
1.43 casties 145: #templateFolder['fulltextclient'] = xmlRpcClient
1.69.2.3 casties 146: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 147: except Exception, e:
1.69.2.3 casties 148: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 149: try:
150: from Products.zogiLib.zogiLib import zogiLib
151: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
152: #templateFolder['zogilib'] = zogilib
153: templateFolder._setObject('zogilib',zogilib)
154: except Exception, e:
155: logging.error("Unable to create zogiLib for zogilib: "+str(e))
156:
1.69.2.3 casties 157:
158: # proxy text server methods to fulltextclient
159: def getTextPage(self, **args):
160: """get page"""
161: return self.template.fulltextclient.getTextPage(**args)
162:
163: def getQuery(self, **args):
164: """get query"""
165: return self.template.fulltextclient.getQuery(**args)
166:
167: def getSearch(self, **args):
168: """get search"""
169: return self.template.fulltextclient.getSearch(**args)
170:
171: def getNumPages(self, **args):
172: """get numpages"""
173: return self.template.fulltextclient.getNumPages(**args)
174:
175: def getTranslate(self, **args):
176: """get translate"""
177: return self.template.fulltextclient.getTranslate(**args)
178:
179: def getLemma(self, **args):
180: """get lemma"""
181: return self.template.fulltextclient.getLemma(**args)
182:
183: def getToc(self, **args):
184: """get toc"""
185: return self.template.fulltextclient.getToc(**args)
186:
187: def getTocPage(self, **args):
188: """get tocpage"""
189: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 190:
1.69.2.3 casties 191:
1.32 dwinter 192: security.declareProtected('View','thumbs_rss')
193: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
194: '''
195: view it
196: @param mode: defines how to access the document behind url
197: @param url: url which contains display information
198: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
199:
200: '''
1.43 casties 201: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.32 dwinter 202: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
203:
204: if not hasattr(self, 'template'):
205: # create template folder if it doesn't exist
206: self.manage_addFolder('template')
207:
208: if not self.digilibBaseUrl:
209: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
210:
211: docinfo = self.getDocinfo(mode=mode,url=url)
212: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
213: pt = getattr(self.template, 'thumbs_main_rss')
214:
215: if viewMode=="auto": # automodus gewaehlt
216: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
217: viewMode="text"
218: else:
219: viewMode="images"
220:
221: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
222:
1.3 casties 223: security.declareProtected('View','index_html')
1.45 abukhman 224: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
1.3 casties 225: '''
226: view it
1.26 casties 227: @param mode: defines how to access the document behind url
1.3 casties 228: @param url: url which contains display information
1.44 casties 229: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 230: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.49 abukhman 231: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 232: '''
233:
1.43 casties 234: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 235:
1.3 casties 236: if not hasattr(self, 'template'):
1.43 casties 237: # this won't work
238: logging.error("template folder missing!")
239: return "ERROR: template folder missing!"
1.3 casties 240:
1.43 casties 241: if not getattr(self, 'digilibBaseUrl', None):
1.3 casties 242: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
243:
1.4 casties 244: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 245:
246:
1.44 casties 247: if tocMode != "thumbs":
248: # get table of contents
249: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 250:
1.21 dwinter 251: if viewMode=="auto": # automodus gewaehlt
1.43 casties 252: if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
1.68 casties 253: viewMode="text_dict"
1.21 dwinter 254: else:
255: viewMode="images"
1.44 casties 256:
1.68 casties 257: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
258:
1.44 casties 259: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 260: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 261:
1.36 dwinter 262: def generateMarks(self,mk):
263: ret=""
1.44 casties 264: if mk is None:
265: return ""
266: if type(mk) is not ListType:
267: mk=[mk]
1.36 dwinter 268: for m in mk:
1.37 dwinter 269: ret+="mk=%s"%m
1.36 dwinter 270: return ret
1.43 casties 271:
1.44 casties 272:
1.43 casties 273: def findDigilibUrl(self):
274: """try to get the digilib URL from zogilib"""
275: url = self.template.zogilib.getDLBaseUrl()
276: return url
1.67 casties 277:
278: def getDocumentViewerURL(self):
279: """returns the URL of this instance"""
280: return self.absolute_url()
1.43 casties 281:
282: def getStyle(self, idx, selected, style=""):
283: """returns a string with the given style and append 'sel' if path == selected."""
284: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
285: if idx == selected:
286: return style + 'sel'
287: else:
288: return style
1.36 dwinter 289:
1.4 casties 290: def getLink(self,param=None,val=None):
291: """link to documentviewer with parameter param set to val"""
1.9 casties 292: params=self.REQUEST.form.copy()
1.4 casties 293: if param is not None:
1.7 casties 294: if val is None:
295: if params.has_key(param):
296: del params[param]
1.4 casties 297: else:
1.9 casties 298: params[param] = str(val)
1.43 casties 299:
300: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 301: params["mode"] = "imagepath"
302: params["url"] = getParentDir(params["url"])
1.7 casties 303:
1.9 casties 304: # quote values and assemble into query string
305: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
306: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 307: return url
308:
1.32 dwinter 309: def getLinkAmp(self,param=None,val=None):
310: """link to documentviewer with parameter param set to val"""
311: params=self.REQUEST.form.copy()
312: if param is not None:
313: if val is None:
314: if params.has_key(param):
315: del params[param]
316: else:
317: params[param] = str(val)
318:
319: # quote values and assemble into query string
1.69.2.2 casties 320: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 321: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
322: url=self.REQUEST['URL1']+"?"+ps
323: return url
1.40 casties 324:
1.26 casties 325: def getInfo_xml(self,url,mode):
326: """returns info about the document as XML"""
327:
328: if not self.digilibBaseUrl:
329: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
330:
331: docinfo = self.getDocinfo(mode=mode,url=url)
332: pt = getattr(self.template, 'info_xml')
333: return pt(docinfo=docinfo)
334:
1.4 casties 335:
1.9 casties 336: def isAccessible(self, docinfo):
1.8 casties 337: """returns if access to the resource is granted"""
338: access = docinfo.get('accessType', None)
1.69.2.2 casties 339: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 340: if access is not None and access == 'free':
1.69.2.2 casties 341: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 342: return True
1.17 casties 343: elif access is None or access in self.authgroups:
1.9 casties 344: # only local access -- only logged in users
345: user = getSecurityManager().getUser()
346: if user is not None:
347: #print "user: ", user
348: return (user.getUserName() != "Anonymous User")
349: else:
350: return False
1.8 casties 351:
1.69.2.2 casties 352: logging.debug("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 353: return False
1.9 casties 354:
1.8 casties 355:
1.35 dwinter 356: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 357: """gibt param von dlInfo aus"""
1.7 casties 358: if docinfo is None:
359: docinfo = {}
1.35 dwinter 360:
361: for x in range(cut):
1.38 dwinter 362:
1.35 dwinter 363: path=getParentDir(path)
1.38 dwinter 364:
1.13 casties 365: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 366:
1.69.2.2 casties 367: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 368:
1.69.2.3 casties 369: txt = getHttpData(infoUrl)
370: if txt is None:
1.13 casties 371: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.69.2.3 casties 372:
373: dom = Parse(txt)
1.10 casties 374: sizes=dom.xpath("//dir/size")
1.69.2.2 casties 375: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 376:
1.10 casties 377: if sizes:
378: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 379: else:
380: docinfo['numPages'] = 0
1.43 casties 381:
382: # TODO: produce and keep list of image names and numbers
1.7 casties 383:
384: return docinfo
1.8 casties 385:
1.6 casties 386:
1.9 casties 387: def getIndexMeta(self, url):
388: """returns dom of index.meta document at url"""
389: dom = None
1.12 casties 390: metaUrl = None
1.9 casties 391: if url.startswith("http://"):
392: # real URL
1.12 casties 393: metaUrl = url
1.9 casties 394: else:
395: # online path
396: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 397: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 398: if not metaUrl.endswith("index.meta"):
399: metaUrl += "/index.meta"
1.12 casties 400:
1.69.2.3 casties 401: logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)
402: txt=getHttpData(metaUrl)
403: if txt is None:
1.12 casties 404: raise IOError("Unable to read index meta from %s"%(url))
1.69.2.3 casties 405:
406: dom = Parse(txt)
1.9 casties 407: return dom
1.20 dwinter 408:
409: def getPresentationInfoXML(self, url):
410: """returns dom of info.xml document at url"""
411: dom = None
412: metaUrl = None
413: if url.startswith("http://"):
414: # real URL
415: metaUrl = url
416: else:
417: # online path
418: server=self.digilibBaseUrl+"/servlet/Texter?fn="
419: metaUrl=server+url.replace("/mpiwg/online","")
420:
1.69.2.3 casties 421: txt=getHttpData(metaUrl)
422: if txt is None:
1.20 dwinter 423: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.69.2.3 casties 424:
425: dom = Parse(txt)
1.20 dwinter 426: return dom
1.9 casties 427:
428:
1.33 dwinter 429: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 430: """gets authorization info from the index.meta file at path or given by dom"""
1.69.2.2 casties 431: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 432:
433: access = None
434:
435: if docinfo is None:
436: docinfo = {}
437:
438: if dom is None:
1.38 dwinter 439: for x in range(cut):
1.33 dwinter 440: path=getParentDir(path)
441: dom = self.getIndexMeta(path)
1.18 dwinter 442:
1.8 casties 443: acctype = dom.xpath("//access-conditions/access/@type")
444: if acctype and (len(acctype)>0):
445: access=acctype[0].value
1.9 casties 446: if access in ['group', 'institution']:
1.8 casties 447: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
448:
449: docinfo['accessType'] = access
450: return docinfo
1.6 casties 451:
1.8 casties 452:
1.33 dwinter 453: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 454: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 455: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 456:
1.3 casties 457: if docinfo is None:
458: docinfo = {}
1.38 dwinter 459:
1.3 casties 460: if dom is None:
1.38 dwinter 461: for x in range(cut):
1.33 dwinter 462: path=getParentDir(path)
463: dom = self.getIndexMeta(path)
1.39 dwinter 464:
465: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 466: # put in all raw bib fields as dict "bib"
467: bib = dom.xpath("//bib/*")
468: if bib and len(bib)>0:
469: bibinfo = {}
470: for e in bib:
471: bibinfo[e.localName] = getTextFromNode(e)
472: docinfo['bib'] = bibinfo
473:
474: # extract some fields (author, title, year) according to their mapping
1.4 casties 475: metaData=self.metadata.main.meta.bib
476: bibtype=dom.xpath("//bib/@type")
477: if bibtype and (len(bibtype)>0):
478: bibtype=bibtype[0].value
1.2 dwinter 479: else:
1.4 casties 480: bibtype="generic"
1.27 casties 481:
1.4 casties 482: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 483: docinfo['bib_type'] = bibtype
1.4 casties 484: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 485: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 486: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 487: try:
488: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
489: except: pass
490: try:
491: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
492: except: pass
493: try:
494: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
495: except: pass
1.27 casties 496: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 497: try:
498: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
499: except:
500: docinfo['lang']=''
1.27 casties 501:
1.3 casties 502: return docinfo
1.42 abukhman 503:
504:
1.43 casties 505: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
506: """parse texttool tag in index meta"""
1.69.2.2 casties 507: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 508: if docinfo is None:
509: docinfo = {}
510: if docinfo.get('lang', None) is None:
511: docinfo['lang'] = '' # default keine Sprache gesetzt
512: if dom is None:
513: dom = self.getIndexMeta(url)
514:
515: archivePath = None
516: archiveName = None
517:
518: archiveNames = dom.xpath("//resource/name")
519: if archiveNames and (len(archiveNames) > 0):
520: archiveName = getTextFromNode(archiveNames[0])
521: else:
1.69.2.2 casties 522: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 523:
524: archivePaths = dom.xpath("//resource/archive-path")
525: if archivePaths and (len(archivePaths) > 0):
526: archivePath = getTextFromNode(archivePaths[0])
527: # clean up archive path
528: if archivePath[0] != '/':
529: archivePath = '/' + archivePath
530: if archiveName and (not archivePath.endswith(archiveName)):
531: archivePath += "/" + archiveName
532: else:
533: # try to get archive-path from url
1.69.2.2 casties 534: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 535: if (not url.startswith('http')):
536: archivePath = url.replace('index.meta', '')
537:
538: if archivePath is None:
539: # we balk without archive-path
540: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
541:
542: imageDirs = dom.xpath("//texttool/image")
543: if imageDirs and (len(imageDirs) > 0):
544: imageDir = getTextFromNode(imageDirs[0])
545:
546: else:
547: # we balk with no image tag / not necessary anymore because textmode is now standard
548: #raise IOError("No text-tool info in %s"%(url))
549: imageDir = ""
550: #xquery="//pb"
551: docinfo['imagePath'] = "" # keine Bilder
552: docinfo['imageURL'] = ""
553:
554: if imageDir and archivePath:
555: #print "image: ", imageDir, " archivepath: ", archivePath
556: imageDir = os.path.join(archivePath, imageDir)
557: imageDir = imageDir.replace("/mpiwg/online", '')
558: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
559: docinfo['imagePath'] = imageDir
560:
561: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
562:
563: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
564: if viewerUrls and (len(viewerUrls) > 0):
565: viewerUrl = getTextFromNode(viewerUrls[0])
566: docinfo['viewerURL'] = viewerUrl
567:
568: textUrls = dom.xpath("//texttool/text")
569: if textUrls and (len(textUrls) > 0):
570: textUrl = getTextFromNode(textUrls[0])
571: if urlparse.urlparse(textUrl)[0] == "": #keine url
572: textUrl = os.path.join(archivePath, textUrl)
573: # fix URLs starting with /mpiwg/online
574: if textUrl.startswith("/mpiwg/online"):
575: textUrl = textUrl.replace("/mpiwg/online", '', 1)
576:
577: docinfo['textURL'] = textUrl
578:
579: textUrls = dom.xpath("//texttool/text-url-path")
580: if textUrls and (len(textUrls) > 0):
581: textUrl = getTextFromNode(textUrls[0])
1.51 casties 582: docinfo['textURLPath'] = textUrl
583: if not docinfo['imagePath']:
584: # text-only, no page images
585: docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
1.43 casties 586:
587: presentationUrls = dom.xpath("//texttool/presentation")
588: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
589:
590: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
591: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
592: # durch den relativen Pfad auf die presentation infos
593: presentationPath = getTextFromNode(presentationUrls[0])
594: if url.endswith("index.meta"):
595: presentationUrl = url.replace('index.meta', presentationPath)
596: else:
597: presentationUrl = url + "/" + presentationPath
1.51 casties 598:
1.43 casties 599: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
600:
601: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 602:
1.43 casties 603: return docinfo
1.3 casties 604:
1.20 dwinter 605:
606: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
607: """gets the bibliographical information from the preseantion entry in texttools
608: """
609: dom=self.getPresentationInfoXML(url)
1.29 casties 610: try:
611: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
612: except:
613: pass
614: try:
615: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
616: except:
617: pass
618: try:
619: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
620: except:
621: pass
1.20 dwinter 622: return docinfo
623:
1.33 dwinter 624: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 625: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.69.2.2 casties 626: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 627: if docinfo is None:
628: docinfo = {}
1.6 casties 629: path=path.replace("/mpiwg/online","")
1.3 casties 630: docinfo['imagePath'] = path
1.35 dwinter 631: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 632:
1.39 dwinter 633: pathorig=path
1.38 dwinter 634: for x in range(cut):
635: path=getParentDir(path)
1.69.2.2 casties 636: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 637: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 638: docinfo['imageURL'] = imageUrl
639:
1.39 dwinter 640: #path ist the path to the images it assumes that the index.meta file is one level higher.
641: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
642: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 643: return docinfo
644:
1.2 dwinter 645:
1.3 casties 646: def getDocinfo(self, mode, url):
647: """returns docinfo depending on mode"""
1.69.2.2 casties 648: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 649: # look for cached docinfo in session
1.21 dwinter 650: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 651: docinfo = self.REQUEST.SESSION['docinfo']
652: # check if its still current
653: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.69.2.2 casties 654: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 655: return docinfo
656: # new docinfo
657: docinfo = {'mode': mode, 'url': url}
658: if mode=="texttool": #index.meta with texttool information
659: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
660: elif mode=="imagepath":
661: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 662: elif mode=="filepath":
1.37 dwinter 663: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 664: else:
1.69.2.2 casties 665: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 666: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 667:
1.69.2.2 casties 668: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 669: self.REQUEST.SESSION['docinfo'] = docinfo
670: return docinfo
1.69 abukhman 671:
1.44 casties 672: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 673: """returns pageinfo with the given parameters"""
674: pageinfo = {}
1.4 casties 675: current = getInt(current)
676: pageinfo['current'] = current
677: rows = int(rows or self.thumbrows)
678: pageinfo['rows'] = rows
679: cols = int(cols or self.thumbcols)
680: pageinfo['cols'] = cols
681: grpsize = cols * rows
682: pageinfo['groupsize'] = grpsize
1.28 casties 683: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
684: # int(current / grpsize) * grpsize +1))
1.3 casties 685: pageinfo['start'] = start
1.4 casties 686: pageinfo['end'] = start + grpsize
1.44 casties 687: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 688: np = int(docinfo['numPages'])
689: pageinfo['end'] = min(pageinfo['end'], np)
690: pageinfo['numgroups'] = int(np / grpsize)
691: if np % grpsize > 0:
1.69 abukhman 692: pageinfo['numgroups'] += 1
1.44 casties 693: pageinfo['viewMode'] = viewMode
694: pageinfo['tocMode'] = tocMode
1.45 abukhman 695: pageinfo['query'] = self.REQUEST.get('query',' ')
696: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
697: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 698: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 699: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 700: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 701: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 702: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 703: toc = int (pageinfo['tocPN'])
704: pageinfo['textPages'] =int (toc)
705:
706: if 'tocSize_%s'%tocMode in docinfo:
707: tocSize = int(docinfo['tocSize_%s'%tocMode])
708: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 709: # cached toc
1.48 abukhman 710: if tocSize%tocPageSize>0:
711: tocPages=tocSize/tocPageSize+1
712: else:
713: tocPages=tocSize/tocPageSize
1.69 abukhman 714: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 715: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 716: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 717: return pageinfo
718:
1.69 abukhman 719: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 720: """init document viewer"""
721: self.title=title
722: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 723: self.thumbrows = thumbrows
724: self.thumbcols = thumbcols
1.8 casties 725: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 726: if RESPONSE is not None:
727: RESPONSE.redirect('manage_main')
1.1 dwinter 728:
729: def manage_AddDocumentViewerForm(self):
730: """add the viewer form"""
1.3 casties 731: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 732: return pt()
733:
1.43 casties 734: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 735: """add the viewer"""
1.43 casties 736: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 737: self._setObject(id,newObj)
738:
739: if RESPONSE is not None:
740: RESPONSE.redirect('manage_main')
1.3 casties 741:
742: ## DocumentViewerTemplate class
743: class DocumentViewerTemplate(ZopePageTemplate):
744: """Template for document viewer"""
745: meta_type="DocumentViewer Template"
746:
747:
748: def manage_addDocumentViewerTemplateForm(self):
749: """Form for adding"""
750: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
751: return pt()
752:
753: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
754: REQUEST=None, submit=None):
755: "Add a Page Template with optional file content."
756:
757: self._setObject(id, DocumentViewerTemplate(id))
758: ob = getattr(self, id)
1.23 dwinter 759: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
760: logging.info("txt %s:"%txt)
761: ob.pt_edit(txt,"text/html")
1.3 casties 762: if title:
763: ob.pt_setTitle(title)
764: try:
765: u = self.DestinationURL()
766: except AttributeError:
767: u = REQUEST['URL1']
768:
769: u = "%s/%s" % (u, urllib.quote(id))
770: REQUEST.RESPONSE.redirect(u+'/manage_main')
771: return ''
772:
773:
1.14 casties 774:
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