Annotation of documentViewer/documentViewer.py, revision 1.86
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:
1.70 casties 9: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.73 casties 10: import Ft.Xml.Domlette
1.1 dwinter 11: import os.path
1.7 casties 12: import sys
1.1 dwinter 13: import urllib
1.70 casties 14: import urllib2
1.20 dwinter 15: import logging
1.28 casties 16: import math
1.18 dwinter 17: import urlparse
1.70 casties 18: import cStringIO
1.43 casties 19:
1.22 dwinter 20: def logger(txt,method,txt2):
21: """logging"""
22: logging.info(txt+ txt2)
23:
24:
1.4 casties 25: def getInt(number, default=0):
26: """returns always an int (0 in case of problems)"""
27: try:
28: return int(number)
29: except:
1.29 casties 30: return int(default)
1.4 casties 31:
1.1 dwinter 32: def getTextFromNode(nodename):
1.18 dwinter 33: """get the cdata content of a node"""
1.8 casties 34: if nodename is None:
35: return ""
1.1 dwinter 36: nodelist=nodename.childNodes
37: rc = ""
38: for node in nodelist:
39: if node.nodeType == node.TEXT_NODE:
40: rc = rc + node.data
41: return rc
42:
1.43 casties 43: def serializeNode(node, encoding='utf-8'):
44: """returns a string containing node as XML"""
45: buf = cStringIO.StringIO()
1.75 casties 46: Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
1.43 casties 47: s = buf.getvalue()
48: buf.close()
49: return s
50:
1.9 casties 51:
52: def getParentDir(path):
53: """returns pathname shortened by one"""
54: return '/'.join(path.split('/')[0:-1])
55:
56:
1.70 casties 57: def getHttpData(url, data=None, num_tries=3, timeout=10):
58: """returns result from url+data HTTP request"""
59: # we do GET (by appending data to url)
60: if isinstance(data, str) or isinstance(data, unicode):
61: # if data is string then append
62: url = "%s?%s"%(url,data)
63: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
64: # urlencode
65: url = "%s?%s"%(url,urllib.urlencode(data))
66:
67: response = None
68: errmsg = None
69: for cnt in range(num_tries):
70: try:
71: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
72: if sys.version_info < (2, 6):
73: # set timeout on socket -- ugly :-(
74: import socket
75: socket.setdefaulttimeout(float(timeout))
76: response = urllib2.urlopen(url)
77: else:
78: response = urllib2.urlopen(url,timeout=float(timeout))
79: # check result?
80: break
81: except urllib2.HTTPError, e:
82: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
83: errmsg = str(e)
84: # stop trying
85: break
86: except urllib2.URLError, e:
87: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
88: errmsg = str(e)
89: # stop trying
90: #break
91:
92: if response is not None:
93: data = response.read()
94: response.close()
95: return data
96:
97: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
98: #return None
1.1 dwinter 99:
100:
101:
1.3 casties 102: ##
103: ## documentViewer class
104: ##
105: class documentViewer(Folder):
1.1 dwinter 106: """document viewer"""
107: meta_type="Document viewer"
108:
109: security=ClassSecurityInfo()
1.3 casties 110: manage_options=Folder.manage_options+(
1.1 dwinter 111: {'label':'main config','action':'changeDocumentViewerForm'},
112: )
113:
1.3 casties 114: # templates and forms
115: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 116: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
117: toc_text = PageTemplateFile('zpt/toc_text', globals())
118: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 119: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
120: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 121: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77 abukhman 122: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 123: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 124: head_main = PageTemplateFile('zpt/head_main', globals())
125: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 126: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 127:
128:
1.32 dwinter 129: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 130: security.declareProtected('View management screens','changeDocumentViewerForm')
131: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
132:
1.1 dwinter 133:
1.45 abukhman 134: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 135: """init document viewer"""
136: self.id=id
137: self.title=title
1.4 casties 138: self.thumbcols = thumbcols
139: self.thumbrows = thumbrows
1.8 casties 140: # authgroups is list of authorized groups (delimited by ,)
141: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 142: # create template folder so we can always use template.something
143:
144: templateFolder = Folder('template')
145: #self['template'] = templateFolder # Zope-2.12 style
146: self._setObject('template',templateFolder) # old style
147: try:
1.70 casties 148: import MpdlXmlTextServer
1.71 casties 149: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 150: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 151: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 152: except Exception, e:
1.70 casties 153: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 154: try:
155: from Products.zogiLib.zogiLib import zogiLib
156: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
157: #templateFolder['zogilib'] = zogilib
158: templateFolder._setObject('zogilib',zogilib)
159: except Exception, e:
160: logging.error("Unable to create zogiLib for zogilib: "+str(e))
161:
1.70 casties 162:
163: # proxy text server methods to fulltextclient
164: def getTextPage(self, **args):
165: """get page"""
166: return self.template.fulltextclient.getTextPage(**args)
167:
168: def getQuery(self, **args):
169: """get query"""
170: return self.template.fulltextclient.getQuery(**args)
171:
172: def getSearch(self, **args):
173: """get search"""
174: return self.template.fulltextclient.getSearch(**args)
175:
1.72 casties 176: def getNumPages(self, docinfo):
1.70 casties 177: """get numpages"""
1.72 casties 178: return self.template.fulltextclient.getNumPages(docinfo)
1.70 casties 179:
180: def getTranslate(self, **args):
181: """get translate"""
182: return self.template.fulltextclient.getTranslate(**args)
183:
184: def getLemma(self, **args):
185: """get lemma"""
186: return self.template.fulltextclient.getLemma(**args)
187:
188: def getToc(self, **args):
189: """get toc"""
190: return self.template.fulltextclient.getToc(**args)
191:
192: def getTocPage(self, **args):
193: """get tocpage"""
194: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 195:
1.70 casties 196:
1.32 dwinter 197: security.declareProtected('View','thumbs_rss')
198: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
199: '''
200: view it
201: @param mode: defines how to access the document behind url
202: @param url: url which contains display information
203: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
204:
205: '''
1.43 casties 206: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.32 dwinter 207: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
208:
209: if not hasattr(self, 'template'):
210: # create template folder if it doesn't exist
211: self.manage_addFolder('template')
212:
213: if not self.digilibBaseUrl:
214: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
215:
216: docinfo = self.getDocinfo(mode=mode,url=url)
217: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
218: pt = getattr(self.template, 'thumbs_main_rss')
219:
220: if viewMode=="auto": # automodus gewaehlt
1.70 casties 221: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 222: viewMode="text"
223: else:
224: viewMode="images"
225:
226: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
227:
1.3 casties 228: security.declareProtected('View','index_html')
1.81 abukhman 229: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
1.3 casties 230: '''
231: view it
1.26 casties 232: @param mode: defines how to access the document behind url
1.3 casties 233: @param url: url which contains display information
1.44 casties 234: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 235: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 236: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 237: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 238: '''
239:
1.43 casties 240: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 241:
1.3 casties 242: if not hasattr(self, 'template'):
1.43 casties 243: # this won't work
244: logging.error("template folder missing!")
245: return "ERROR: template folder missing!"
1.3 casties 246:
1.43 casties 247: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 248: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 249:
1.4 casties 250: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 251:
1.44 casties 252: if tocMode != "thumbs":
253: # get table of contents
254: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 255:
1.21 dwinter 256: if viewMode=="auto": # automodus gewaehlt
1.71 casties 257: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.68 casties 258: viewMode="text_dict"
1.21 dwinter 259: else:
260: viewMode="images"
1.44 casties 261:
1.68 casties 262: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
263:
1.44 casties 264: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 265: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 266:
1.36 dwinter 267: def generateMarks(self,mk):
268: ret=""
1.44 casties 269: if mk is None:
270: return ""
1.73 casties 271: if not isinstance(mk, list):
1.71 casties 272: mk=[mk]
1.36 dwinter 273: for m in mk:
1.37 dwinter 274: ret+="mk=%s"%m
1.36 dwinter 275: return ret
1.43 casties 276:
1.44 casties 277:
1.43 casties 278: def findDigilibUrl(self):
279: """try to get the digilib URL from zogilib"""
280: url = self.template.zogilib.getDLBaseUrl()
281: return url
1.67 casties 282:
283: def getDocumentViewerURL(self):
284: """returns the URL of this instance"""
285: return self.absolute_url()
1.43 casties 286:
287: def getStyle(self, idx, selected, style=""):
288: """returns a string with the given style and append 'sel' if path == selected."""
289: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
290: if idx == selected:
291: return style + 'sel'
292: else:
293: return style
1.36 dwinter 294:
1.4 casties 295: def getLink(self,param=None,val=None):
296: """link to documentviewer with parameter param set to val"""
1.9 casties 297: params=self.REQUEST.form.copy()
1.4 casties 298: if param is not None:
1.7 casties 299: if val is None:
300: if params.has_key(param):
301: del params[param]
1.4 casties 302: else:
1.9 casties 303: params[param] = str(val)
1.43 casties 304:
305: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 306: params["mode"] = "imagepath"
307: params["url"] = getParentDir(params["url"])
1.7 casties 308:
1.9 casties 309: # quote values and assemble into query string
1.74 casties 310: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
311: ps = urllib.urlencode(params)
1.9 casties 312: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 313: return url
314:
1.32 dwinter 315: def getLinkAmp(self,param=None,val=None):
316: """link to documentviewer with parameter param set to val"""
317: params=self.REQUEST.form.copy()
318: if param is not None:
319: if val is None:
320: if params.has_key(param):
321: del params[param]
322: else:
323: params[param] = str(val)
324:
325: # quote values and assemble into query string
1.70 casties 326: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 327: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
328: url=self.REQUEST['URL1']+"?"+ps
329: return url
1.40 casties 330:
1.26 casties 331: def getInfo_xml(self,url,mode):
332: """returns info about the document as XML"""
333:
334: if not self.digilibBaseUrl:
335: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
336:
337: docinfo = self.getDocinfo(mode=mode,url=url)
338: pt = getattr(self.template, 'info_xml')
339: return pt(docinfo=docinfo)
340:
1.4 casties 341:
1.9 casties 342: def isAccessible(self, docinfo):
1.8 casties 343: """returns if access to the resource is granted"""
344: access = docinfo.get('accessType', None)
1.70 casties 345: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 346: if access is not None and access == 'free':
1.70 casties 347: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 348: return True
1.17 casties 349: elif access is None or access in self.authgroups:
1.9 casties 350: # only local access -- only logged in users
351: user = getSecurityManager().getUser()
1.76 casties 352: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 353: if user is not None:
354: #print "user: ", user
355: return (user.getUserName() != "Anonymous User")
356: else:
357: return False
1.8 casties 358:
1.76 casties 359: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 360: return False
1.9 casties 361:
1.8 casties 362:
1.35 dwinter 363: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 364: """gibt param von dlInfo aus"""
1.7 casties 365: if docinfo is None:
366: docinfo = {}
1.35 dwinter 367:
368: for x in range(cut):
1.38 dwinter 369:
1.35 dwinter 370: path=getParentDir(path)
1.38 dwinter 371:
1.13 casties 372: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 373:
1.70 casties 374: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 375:
1.70 casties 376: txt = getHttpData(infoUrl)
377: if txt is None:
1.13 casties 378: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 379:
380: dom = Parse(txt)
1.10 casties 381: sizes=dom.xpath("//dir/size")
1.70 casties 382: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 383:
1.10 casties 384: if sizes:
385: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 386: else:
387: docinfo['numPages'] = 0
1.43 casties 388:
389: # TODO: produce and keep list of image names and numbers
1.7 casties 390:
391: return docinfo
1.8 casties 392:
1.6 casties 393:
1.9 casties 394: def getIndexMeta(self, url):
395: """returns dom of index.meta document at url"""
396: dom = None
1.12 casties 397: metaUrl = None
1.9 casties 398: if url.startswith("http://"):
399: # real URL
1.12 casties 400: metaUrl = url
1.9 casties 401: else:
402: # online path
403: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 404: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 405: if not metaUrl.endswith("index.meta"):
406: metaUrl += "/index.meta"
1.12 casties 407:
1.70 casties 408: logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)
409: txt=getHttpData(metaUrl)
410: if txt is None:
1.12 casties 411: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 412:
413: dom = Parse(txt)
1.9 casties 414: return dom
1.20 dwinter 415:
416: def getPresentationInfoXML(self, url):
417: """returns dom of info.xml document at url"""
418: dom = None
419: metaUrl = None
420: if url.startswith("http://"):
421: # real URL
422: metaUrl = url
423: else:
424: # online path
425: server=self.digilibBaseUrl+"/servlet/Texter?fn="
426: metaUrl=server+url.replace("/mpiwg/online","")
427:
1.70 casties 428: txt=getHttpData(metaUrl)
429: if txt is None:
1.20 dwinter 430: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 431:
432: dom = Parse(txt)
1.20 dwinter 433: return dom
1.9 casties 434:
435:
1.33 dwinter 436: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 437: """gets authorization info from the index.meta file at path or given by dom"""
1.70 casties 438: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 439:
440: access = None
441:
442: if docinfo is None:
443: docinfo = {}
444:
445: if dom is None:
1.38 dwinter 446: for x in range(cut):
1.33 dwinter 447: path=getParentDir(path)
448: dom = self.getIndexMeta(path)
1.18 dwinter 449:
1.8 casties 450: acctype = dom.xpath("//access-conditions/access/@type")
451: if acctype and (len(acctype)>0):
452: access=acctype[0].value
1.9 casties 453: if access in ['group', 'institution']:
1.8 casties 454: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
455:
456: docinfo['accessType'] = access
457: return docinfo
1.6 casties 458:
1.8 casties 459:
1.33 dwinter 460: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 461: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 462: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 463:
1.3 casties 464: if docinfo is None:
465: docinfo = {}
1.38 dwinter 466:
1.3 casties 467: if dom is None:
1.38 dwinter 468: for x in range(cut):
1.33 dwinter 469: path=getParentDir(path)
470: dom = self.getIndexMeta(path)
1.39 dwinter 471:
472: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 473: # put in all raw bib fields as dict "bib"
474: bib = dom.xpath("//bib/*")
475: if bib and len(bib)>0:
476: bibinfo = {}
477: for e in bib:
478: bibinfo[e.localName] = getTextFromNode(e)
479: docinfo['bib'] = bibinfo
480:
481: # extract some fields (author, title, year) according to their mapping
1.4 casties 482: metaData=self.metadata.main.meta.bib
483: bibtype=dom.xpath("//bib/@type")
484: if bibtype and (len(bibtype)>0):
485: bibtype=bibtype[0].value
1.2 dwinter 486: else:
1.4 casties 487: bibtype="generic"
1.27 casties 488:
1.4 casties 489: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 490: docinfo['bib_type'] = bibtype
1.4 casties 491: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 492: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 493: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 494: try:
495: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
496: except: pass
497: try:
498: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
499: except: pass
500: try:
501: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
502: except: pass
1.27 casties 503: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 504: try:
505: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
506: except:
507: docinfo['lang']=''
1.27 casties 508:
1.3 casties 509: return docinfo
1.42 abukhman 510:
511:
1.43 casties 512: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
513: """parse texttool tag in index meta"""
1.70 casties 514: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 515: if docinfo is None:
516: docinfo = {}
517: if docinfo.get('lang', None) is None:
518: docinfo['lang'] = '' # default keine Sprache gesetzt
519: if dom is None:
520: dom = self.getIndexMeta(url)
521:
522: archivePath = None
523: archiveName = None
524:
525: archiveNames = dom.xpath("//resource/name")
526: if archiveNames and (len(archiveNames) > 0):
527: archiveName = getTextFromNode(archiveNames[0])
528: else:
1.70 casties 529: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 530:
531: archivePaths = dom.xpath("//resource/archive-path")
532: if archivePaths and (len(archivePaths) > 0):
533: archivePath = getTextFromNode(archivePaths[0])
534: # clean up archive path
535: if archivePath[0] != '/':
536: archivePath = '/' + archivePath
537: if archiveName and (not archivePath.endswith(archiveName)):
538: archivePath += "/" + archiveName
539: else:
540: # try to get archive-path from url
1.70 casties 541: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 542: if (not url.startswith('http')):
543: archivePath = url.replace('index.meta', '')
544:
545: if archivePath is None:
546: # we balk without archive-path
547: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
548:
549: imageDirs = dom.xpath("//texttool/image")
550: if imageDirs and (len(imageDirs) > 0):
551: imageDir = getTextFromNode(imageDirs[0])
552:
553: else:
554: # we balk with no image tag / not necessary anymore because textmode is now standard
555: #raise IOError("No text-tool info in %s"%(url))
556: imageDir = ""
557: #xquery="//pb"
558: docinfo['imagePath'] = "" # keine Bilder
559: docinfo['imageURL'] = ""
560:
561: if imageDir and archivePath:
562: #print "image: ", imageDir, " archivepath: ", archivePath
563: imageDir = os.path.join(archivePath, imageDir)
564: imageDir = imageDir.replace("/mpiwg/online", '')
565: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
566: docinfo['imagePath'] = imageDir
567:
568: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
569:
570: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
571: if viewerUrls and (len(viewerUrls) > 0):
572: viewerUrl = getTextFromNode(viewerUrls[0])
573: docinfo['viewerURL'] = viewerUrl
1.70 casties 574:
575: # old style text URL
1.43 casties 576: textUrls = dom.xpath("//texttool/text")
577: if textUrls and (len(textUrls) > 0):
578: textUrl = getTextFromNode(textUrls[0])
579: if urlparse.urlparse(textUrl)[0] == "": #keine url
580: textUrl = os.path.join(archivePath, textUrl)
581: # fix URLs starting with /mpiwg/online
582: if textUrl.startswith("/mpiwg/online"):
583: textUrl = textUrl.replace("/mpiwg/online", '', 1)
584:
585: docinfo['textURL'] = textUrl
586:
1.70 casties 587: # new style text-url-path
1.43 casties 588: textUrls = dom.xpath("//texttool/text-url-path")
589: if textUrls and (len(textUrls) > 0):
590: textUrl = getTextFromNode(textUrls[0])
1.51 casties 591: docinfo['textURLPath'] = textUrl
592: if not docinfo['imagePath']:
593: # text-only, no page images
1.72 casties 594: docinfo = self.getNumPages(docinfo)
1.43 casties 595:
596: presentationUrls = dom.xpath("//texttool/presentation")
597: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
598:
599: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
600: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
601: # durch den relativen Pfad auf die presentation infos
602: presentationPath = getTextFromNode(presentationUrls[0])
603: if url.endswith("index.meta"):
604: presentationUrl = url.replace('index.meta', presentationPath)
605: else:
606: presentationUrl = url + "/" + presentationPath
1.51 casties 607:
1.43 casties 608: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
609:
610: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 611:
1.43 casties 612: return docinfo
1.3 casties 613:
1.20 dwinter 614:
615: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
616: """gets the bibliographical information from the preseantion entry in texttools
617: """
618: dom=self.getPresentationInfoXML(url)
1.29 casties 619: try:
620: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
621: except:
622: pass
623: try:
624: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
625: except:
626: pass
627: try:
628: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
629: except:
630: pass
1.20 dwinter 631: return docinfo
632:
1.33 dwinter 633: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 634: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.70 casties 635: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 636: if docinfo is None:
637: docinfo = {}
1.6 casties 638: path=path.replace("/mpiwg/online","")
1.3 casties 639: docinfo['imagePath'] = path
1.35 dwinter 640: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 641:
1.39 dwinter 642: pathorig=path
1.38 dwinter 643: for x in range(cut):
644: path=getParentDir(path)
1.70 casties 645: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 646: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 647: docinfo['imageURL'] = imageUrl
648:
1.39 dwinter 649: #path ist the path to the images it assumes that the index.meta file is one level higher.
650: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
651: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 652: return docinfo
653:
1.2 dwinter 654:
1.3 casties 655: def getDocinfo(self, mode, url):
656: """returns docinfo depending on mode"""
1.70 casties 657: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 658: # look for cached docinfo in session
1.21 dwinter 659: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 660: docinfo = self.REQUEST.SESSION['docinfo']
661: # check if its still current
662: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.70 casties 663: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 664: return docinfo
665: # new docinfo
666: docinfo = {'mode': mode, 'url': url}
667: if mode=="texttool": #index.meta with texttool information
668: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
669: elif mode=="imagepath":
670: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 671: elif mode=="filepath":
1.37 dwinter 672: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 673: else:
1.70 casties 674: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 675: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 676:
1.70 casties 677: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 678: self.REQUEST.SESSION['docinfo'] = docinfo
679: return docinfo
1.69 abukhman 680:
1.83 abukhman 681: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None, characterNormalization=None):
1.3 casties 682: """returns pageinfo with the given parameters"""
683: pageinfo = {}
1.4 casties 684: current = getInt(current)
685: pageinfo['current'] = current
686: rows = int(rows or self.thumbrows)
687: pageinfo['rows'] = rows
688: cols = int(cols or self.thumbcols)
689: pageinfo['cols'] = cols
690: grpsize = cols * rows
691: pageinfo['groupsize'] = grpsize
1.28 casties 692: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
693: # int(current / grpsize) * grpsize +1))
1.3 casties 694: pageinfo['start'] = start
1.4 casties 695: pageinfo['end'] = start + grpsize
1.44 casties 696: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 697: np = int(docinfo['numPages'])
698: pageinfo['end'] = min(pageinfo['end'], np)
699: pageinfo['numgroups'] = int(np / grpsize)
700: if np % grpsize > 0:
1.69 abukhman 701: pageinfo['numgroups'] += 1
1.44 casties 702: pageinfo['viewMode'] = viewMode
703: pageinfo['tocMode'] = tocMode
1.86 ! abukhman 704: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','')
1.45 abukhman 705: pageinfo['query'] = self.REQUEST.get('query',' ')
706: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
707: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 708: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 709: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 710: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 711: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 712: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 713: toc = int (pageinfo['tocPN'])
714: pageinfo['textPages'] =int (toc)
715:
1.85 abukhman 716:
1.82 abukhman 717:
1.48 abukhman 718: if 'tocSize_%s'%tocMode in docinfo:
719: tocSize = int(docinfo['tocSize_%s'%tocMode])
720: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 721: # cached toc
1.48 abukhman 722: if tocSize%tocPageSize>0:
723: tocPages=tocSize/tocPageSize+1
724: else:
725: tocPages=tocSize/tocPageSize
1.69 abukhman 726: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 727: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 728: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 729: return pageinfo
730:
1.69 abukhman 731: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 732: """init document viewer"""
733: self.title=title
734: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 735: self.thumbrows = thumbrows
736: self.thumbcols = thumbcols
1.8 casties 737: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 738: if RESPONSE is not None:
739: RESPONSE.redirect('manage_main')
1.1 dwinter 740:
741: def manage_AddDocumentViewerForm(self):
742: """add the viewer form"""
1.3 casties 743: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 744: return pt()
745:
1.43 casties 746: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 747: """add the viewer"""
1.43 casties 748: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 749: self._setObject(id,newObj)
750:
751: if RESPONSE is not None:
752: RESPONSE.redirect('manage_main')
1.3 casties 753:
754: ## DocumentViewerTemplate class
755: class DocumentViewerTemplate(ZopePageTemplate):
756: """Template for document viewer"""
757: meta_type="DocumentViewer Template"
758:
759:
760: def manage_addDocumentViewerTemplateForm(self):
761: """Form for adding"""
762: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
763: return pt()
764:
765: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
766: REQUEST=None, submit=None):
767: "Add a Page Template with optional file content."
768:
769: self._setObject(id, DocumentViewerTemplate(id))
770: ob = getattr(self, id)
1.23 dwinter 771: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
772: logging.info("txt %s:"%txt)
773: ob.pt_edit(txt,"text/html")
1.3 casties 774: if title:
775: ob.pt_setTitle(title)
776: try:
777: u = self.DestinationURL()
778: except AttributeError:
779: u = REQUEST['URL1']
780:
781: u = "%s/%s" % (u, urllib.quote(id))
782: REQUEST.RESPONSE.redirect(u+'/manage_main')
783: return ''
784:
785:
1.14 casties 786:
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