Annotation of documentViewer/documentViewer.py, revision 1.159
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
1.119 abukhman 8: from Products.zogiLib.zogiLib import browserCheck
1.1 dwinter 9:
1.70 casties 10: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.73 casties 11: import Ft.Xml.Domlette
1.1 dwinter 12: import os.path
1.7 casties 13: import sys
1.1 dwinter 14: import urllib
1.70 casties 15: import urllib2
1.20 dwinter 16: import logging
1.28 casties 17: import math
1.18 dwinter 18: import urlparse
1.70 casties 19: import cStringIO
1.99 dwinter 20: import re
1.149 abukhman 21: import string
1.117 abukhman 22:
1.22 dwinter 23: def logger(txt,method,txt2):
24: """logging"""
25: logging.info(txt+ txt2)
26:
27:
1.4 casties 28: def getInt(number, default=0):
29: """returns always an int (0 in case of problems)"""
30: try:
31: return int(number)
32: except:
1.29 casties 33: return int(default)
1.4 casties 34:
1.1 dwinter 35: def getTextFromNode(nodename):
1.18 dwinter 36: """get the cdata content of a node"""
1.8 casties 37: if nodename is None:
38: return ""
1.1 dwinter 39: nodelist=nodename.childNodes
40: rc = ""
41: for node in nodelist:
42: if node.nodeType == node.TEXT_NODE:
43: rc = rc + node.data
44: return rc
45:
1.43 casties 46: def serializeNode(node, encoding='utf-8'):
47: """returns a string containing node as XML"""
48: buf = cStringIO.StringIO()
1.75 casties 49: Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
1.43 casties 50: s = buf.getvalue()
51: buf.close()
52: return s
53:
1.148 abukhman 54: def browserCheck(self):
55: """check the browsers request to find out the browser type"""
56: bt = {}
57: ua = self.REQUEST.get_header("HTTP_USER_AGENT")
58: bt['ua'] = ua
59: bt['isIE'] = False
60: bt['isN4'] = False
61: if string.find(ua, 'MSIE') > -1:
62: bt['isIE'] = True
63: else:
64: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
65:
66: try:
67: nav = ua[string.find(ua, '('):]
68: ie = string.split(nav, "; ")[1]
69: if string.find(ie, "MSIE") > -1:
70: bt['versIE'] = string.split(ie, " ")[1]
71: except: pass
72:
73: bt['isMac'] = string.find(ua, 'Macintosh') > -1
74: bt['isWin'] = string.find(ua, 'Windows') > -1
75: bt['isIEWin'] = bt['isIE'] and bt['isWin']
76: bt['isIEMac'] = bt['isIE'] and bt['isMac']
77: bt['staticHTML'] = False
78:
79: return bt
1.118 abukhman 80:
81:
1.9 casties 82: def getParentDir(path):
83: """returns pathname shortened by one"""
84: return '/'.join(path.split('/')[0:-1])
85:
86:
1.70 casties 87: def getHttpData(url, data=None, num_tries=3, timeout=10):
88: """returns result from url+data HTTP request"""
89: # we do GET (by appending data to url)
90: if isinstance(data, str) or isinstance(data, unicode):
91: # if data is string then append
92: url = "%s?%s"%(url,data)
93: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
94: # urlencode
95: url = "%s?%s"%(url,urllib.urlencode(data))
96:
97: response = None
98: errmsg = None
99: for cnt in range(num_tries):
100: try:
1.95 abukhman 101: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
1.70 casties 102: if sys.version_info < (2, 6):
103: # set timeout on socket -- ugly :-(
104: import socket
105: socket.setdefaulttimeout(float(timeout))
106: response = urllib2.urlopen(url)
107: else:
108: response = urllib2.urlopen(url,timeout=float(timeout))
109: # check result?
110: break
111: except urllib2.HTTPError, e:
1.95 abukhman 112: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
1.70 casties 113: errmsg = str(e)
114: # stop trying
115: break
116: except urllib2.URLError, e:
1.95 abukhman 117: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
1.70 casties 118: errmsg = str(e)
119: # stop trying
120: #break
121:
122: if response is not None:
123: data = response.read()
124: response.close()
125: return data
126:
127: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
128: #return None
1.1 dwinter 129:
130:
131:
1.3 casties 132: ##
133: ## documentViewer class
134: ##
135: class documentViewer(Folder):
1.1 dwinter 136: """document viewer"""
137: meta_type="Document viewer"
138:
139: security=ClassSecurityInfo()
1.3 casties 140: manage_options=Folder.manage_options+(
1.1 dwinter 141: {'label':'main config','action':'changeDocumentViewerForm'},
142: )
143:
1.3 casties 144: # templates and forms
145: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 146: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
147: toc_text = PageTemplateFile('zpt/toc_text', globals())
148: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 149: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
150: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 151: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77 abukhman 152: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 153: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.157 abukhman 154: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
1.3 casties 155: head_main = PageTemplateFile('zpt/head_main', globals())
156: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 157: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 158:
159:
1.32 dwinter 160: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 161: security.declareProtected('View management screens','changeDocumentViewerForm')
162: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
163:
1.1 dwinter 164:
1.45 abukhman 165: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 166: """init document viewer"""
167: self.id=id
168: self.title=title
1.4 casties 169: self.thumbcols = thumbcols
170: self.thumbrows = thumbrows
1.8 casties 171: # authgroups is list of authorized groups (delimited by ,)
172: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 173: # create template folder so we can always use template.something
174:
175: templateFolder = Folder('template')
176: #self['template'] = templateFolder # Zope-2.12 style
177: self._setObject('template',templateFolder) # old style
178: try:
1.70 casties 179: import MpdlXmlTextServer
1.71 casties 180: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 181: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 182: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 183: except Exception, e:
1.70 casties 184: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 185: try:
186: from Products.zogiLib.zogiLib import zogiLib
187: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
188: #templateFolder['zogilib'] = zogilib
189: templateFolder._setObject('zogilib',zogilib)
190: except Exception, e:
191: logging.error("Unable to create zogiLib for zogilib: "+str(e))
192:
1.70 casties 193:
194: # proxy text server methods to fulltextclient
195: def getTextPage(self, **args):
196: """get page"""
197: return self.template.fulltextclient.getTextPage(**args)
198:
199: def getQuery(self, **args):
200: """get query"""
201: return self.template.fulltextclient.getQuery(**args)
1.147 abukhman 202:
1.154 abukhman 203: def getQueryResultHits(self, **args):
204: """get query"""
205: return self.template.fulltextclient.getQueryResultHits(**args)
206:
207: def getQueryResultHitsText(self, **args):
208: """get query"""
209: return self.template.fulltextclient.getQueryResultHitsText(**args)
210:
211: def getQueryResultHitsFigures(self, **args):
212: """get query"""
213: return self.template.fulltextclient.getQueryResultHitsFigures(**args)
214:
1.147 abukhman 215: def getPDF(self, **args):
216: """get query"""
217: return self.template.fulltextclient.getPDF(**args)
1.70 casties 218:
219: def getSearch(self, **args):
220: """get search"""
221: return self.template.fulltextclient.getSearch(**args)
1.120 abukhman 222:
223: def getGisPlaces(self, **args):
1.121 abukhman 224: """get gis places"""
1.120 abukhman 225: return self.template.fulltextclient.getGisPlaces(**args)
1.121 abukhman 226:
227: def getAllGisPlaces(self, **args):
1.122 abukhman 228: """get all gis places """
229: return self.template.fulltextclient.getAllGisPlaces(**args)
230:
231: def getOrigPages(self, **args):
232: """get original page number """
233: return self.template.fulltextclient.getOrigPages(**args)
234:
1.72 casties 235: def getNumPages(self, docinfo):
1.70 casties 236: """get numpages"""
1.72 casties 237: return self.template.fulltextclient.getNumPages(docinfo)
1.100 abukhman 238:
239: def getNumTextPages(self, docinfo):
240: """get numpages text"""
241: return self.template.fulltextclient.getNumTextPages(docinfo)
242:
1.70 casties 243: def getTranslate(self, **args):
244: """get translate"""
245: return self.template.fulltextclient.getTranslate(**args)
246:
247: def getLemma(self, **args):
248: """get lemma"""
249: return self.template.fulltextclient.getLemma(**args)
250:
251: def getToc(self, **args):
252: """get toc"""
253: return self.template.fulltextclient.getToc(**args)
254:
255: def getTocPage(self, **args):
256: """get tocpage"""
257: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 258:
1.70 casties 259:
1.32 dwinter 260: security.declareProtected('View','thumbs_rss')
261: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
262: '''
263: view it
264: @param mode: defines how to access the document behind url
265: @param url: url which contains display information
266: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
267:
268: '''
1.95 abukhman 269: logging.debug("HHHHHHHHHHHHHH:load the rss")
270: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 271:
272: if not hasattr(self, 'template'):
273: # create template folder if it doesn't exist
274: self.manage_addFolder('template')
275:
276: if not self.digilibBaseUrl:
277: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
278:
279: docinfo = self.getDocinfo(mode=mode,url=url)
1.132 abukhman 280: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.138 abukhman 281: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
1.126 abukhman 282: ''' ZDES '''
1.32 dwinter 283: pt = getattr(self.template, 'thumbs_main_rss')
284:
285: if viewMode=="auto": # automodus gewaehlt
1.159 ! casties 286: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 287: viewMode="text"
288: else:
289: viewMode="images"
290:
291: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
292:
1.3 casties 293: security.declareProtected('View','index_html')
1.158 casties 294: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
1.3 casties 295: '''
296: view it
1.26 casties 297: @param mode: defines how to access the document behind url
1.3 casties 298: @param url: url which contains display information
1.44 casties 299: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 300: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 301: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 302: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 303: '''
304:
1.138 abukhman 305: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 306:
1.3 casties 307: if not hasattr(self, 'template'):
1.43 casties 308: # this won't work
309: logging.error("template folder missing!")
310: return "ERROR: template folder missing!"
1.3 casties 311:
1.43 casties 312: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 313: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 314:
1.4 casties 315: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 316:
1.44 casties 317: if tocMode != "thumbs":
318: # get table of contents
319: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 320:
1.21 dwinter 321: if viewMode=="auto": # automodus gewaehlt
1.159 ! casties 322: if docinfo.has_key('textURL') or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.68 casties 323: viewMode="text_dict"
1.21 dwinter 324: else:
325: viewMode="images"
1.44 casties 326:
1.138 abukhman 327: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
1.68 casties 328:
1.44 casties 329: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 330: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 331:
1.36 dwinter 332: def generateMarks(self,mk):
333: ret=""
1.44 casties 334: if mk is None:
335: return ""
1.73 casties 336: if not isinstance(mk, list):
1.71 casties 337: mk=[mk]
1.36 dwinter 338: for m in mk:
1.37 dwinter 339: ret+="mk=%s"%m
1.36 dwinter 340: return ret
1.149 abukhman 341:
342:
1.148 abukhman 343: def getBrowser(self):
344: """getBrowser the version of browser """
1.149 abukhman 345: names=""
346: names = browserCheck(self)
347: #logging.debug("XXXXXXXXXXXXXXXX: %s"%names)
348: return names
1.148 abukhman 349:
1.43 casties 350: def findDigilibUrl(self):
351: """try to get the digilib URL from zogilib"""
352: url = self.template.zogilib.getDLBaseUrl()
353: return url
1.67 casties 354:
355: def getDocumentViewerURL(self):
356: """returns the URL of this instance"""
357: return self.absolute_url()
1.43 casties 358:
359: def getStyle(self, idx, selected, style=""):
360: """returns a string with the given style and append 'sel' if path == selected."""
361: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
362: if idx == selected:
363: return style + 'sel'
364: else:
365: return style
1.36 dwinter 366:
1.4 casties 367: def getLink(self,param=None,val=None):
368: """link to documentviewer with parameter param set to val"""
1.9 casties 369: params=self.REQUEST.form.copy()
1.4 casties 370: if param is not None:
1.7 casties 371: if val is None:
372: if params.has_key(param):
373: del params[param]
1.4 casties 374: else:
1.9 casties 375: params[param] = str(val)
1.43 casties 376:
377: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 378: params["mode"] = "imagepath"
379: params["url"] = getParentDir(params["url"])
1.7 casties 380:
1.9 casties 381: # quote values and assemble into query string
1.74 casties 382: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
383: ps = urllib.urlencode(params)
1.9 casties 384: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 385: return url
386:
1.32 dwinter 387: def getLinkAmp(self,param=None,val=None):
388: """link to documentviewer with parameter param set to val"""
389: params=self.REQUEST.form.copy()
390: if param is not None:
391: if val is None:
392: if params.has_key(param):
393: del params[param]
394: else:
395: params[param] = str(val)
396:
397: # quote values and assemble into query string
1.95 abukhman 398: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 399: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
400: url=self.REQUEST['URL1']+"?"+ps
401: return url
1.40 casties 402:
1.26 casties 403: def getInfo_xml(self,url,mode):
404: """returns info about the document as XML"""
405:
406: if not self.digilibBaseUrl:
407: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
408:
409: docinfo = self.getDocinfo(mode=mode,url=url)
410: pt = getattr(self.template, 'info_xml')
411: return pt(docinfo=docinfo)
412:
1.153 casties 413: def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
414: """returns new option state"""
1.155 casties 415: if not self.REQUEST.SESSION.has_key(optionName):
1.153 casties 416: # not in session -- initial
417: opt = {'lastState': newState, 'state': initialState}
418: else:
1.155 casties 419: opt = self.REQUEST.SESSION.get(optionName)
1.153 casties 420: if opt['lastState'] != newState:
421: # state in session has changed -- toggle
422: opt['state'] = not opt['state']
423: opt['lastState'] = newState
424:
425: self.REQUEST.SESSION[optionName] = opt
426: return opt['state']
1.4 casties 427:
1.9 casties 428: def isAccessible(self, docinfo):
1.8 casties 429: """returns if access to the resource is granted"""
430: access = docinfo.get('accessType', None)
1.95 abukhman 431: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 432: if access is not None and access == 'free':
1.95 abukhman 433: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 434: return True
1.17 casties 435: elif access is None or access in self.authgroups:
1.9 casties 436: # only local access -- only logged in users
437: user = getSecurityManager().getUser()
1.95 abukhman 438: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 439: if user is not None:
440: #print "user: ", user
441: return (user.getUserName() != "Anonymous User")
442: else:
443: return False
1.8 casties 444:
1.95 abukhman 445: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 446: return False
1.9 casties 447:
1.8 casties 448:
1.35 dwinter 449: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 450: """gibt param von dlInfo aus"""
1.7 casties 451: if docinfo is None:
452: docinfo = {}
1.35 dwinter 453:
454: for x in range(cut):
1.38 dwinter 455:
1.35 dwinter 456: path=getParentDir(path)
1.38 dwinter 457:
1.13 casties 458: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 459:
1.95 abukhman 460: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 461:
1.70 casties 462: txt = getHttpData(infoUrl)
463: if txt is None:
1.13 casties 464: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 465:
466: dom = Parse(txt)
1.10 casties 467: sizes=dom.xpath("//dir/size")
1.95 abukhman 468: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 469:
1.10 casties 470: if sizes:
471: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 472: else:
473: docinfo['numPages'] = 0
1.43 casties 474:
475: # TODO: produce and keep list of image names and numbers
1.7 casties 476:
477: return docinfo
1.8 casties 478:
1.99 dwinter 479: def getIndexMetaPath(self,url):
480: """gib nur den Pfad zurueck"""
481: regexp = re.compile(r".*(experimental|permanent)/(.*)")
482: regpath = regexp.match(url)
483: if (regpath==None):
484: return ""
1.110 abukhman 485: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 486: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
487:
1.111 abukhman 488:
489:
1.99 dwinter 490: def getIndexMetaUrl(self,url):
491: """returns utr of index.meta document at url"""
492:
1.12 casties 493: metaUrl = None
1.9 casties 494: if url.startswith("http://"):
495: # real URL
1.12 casties 496: metaUrl = url
1.9 casties 497: else:
498: # online path
499: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 500: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 501: if not metaUrl.endswith("index.meta"):
502: metaUrl += "/index.meta"
1.99 dwinter 503:
504: return metaUrl
505:
506: def getDomFromIndexMeta(self, url):
507: """get dom from index meta"""
508: dom = None
509: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 510:
1.99 dwinter 511: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 512: txt=getHttpData(metaUrl)
513: if txt is None:
1.12 casties 514: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 515:
516: dom = Parse(txt)
1.9 casties 517: return dom
1.20 dwinter 518:
519: def getPresentationInfoXML(self, url):
520: """returns dom of info.xml document at url"""
521: dom = None
522: metaUrl = None
523: if url.startswith("http://"):
524: # real URL
525: metaUrl = url
526: else:
527: # online path
528: server=self.digilibBaseUrl+"/servlet/Texter?fn="
529: metaUrl=server+url.replace("/mpiwg/online","")
530:
1.70 casties 531: txt=getHttpData(metaUrl)
532: if txt is None:
1.20 dwinter 533: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 534:
535: dom = Parse(txt)
1.20 dwinter 536: return dom
1.9 casties 537:
538:
1.33 dwinter 539: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 540: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 541: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 542:
543: access = None
544:
545: if docinfo is None:
546: docinfo = {}
547:
548: if dom is None:
1.38 dwinter 549: for x in range(cut):
1.33 dwinter 550: path=getParentDir(path)
1.99 dwinter 551: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 552:
1.8 casties 553: acctype = dom.xpath("//access-conditions/access/@type")
554: if acctype and (len(acctype)>0):
555: access=acctype[0].value
1.9 casties 556: if access in ['group', 'institution']:
1.8 casties 557: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
558:
559: docinfo['accessType'] = access
560: return docinfo
1.6 casties 561:
1.8 casties 562:
1.33 dwinter 563: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 564: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 565: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 566:
1.3 casties 567: if docinfo is None:
568: docinfo = {}
1.38 dwinter 569:
1.3 casties 570: if dom is None:
1.38 dwinter 571: for x in range(cut):
1.33 dwinter 572: path=getParentDir(path)
1.99 dwinter 573: dom = self.getDomFromIndexMeta(path)
574:
575: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 576:
1.95 abukhman 577: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 578: # put in all raw bib fields as dict "bib"
579: bib = dom.xpath("//bib/*")
580: if bib and len(bib)>0:
581: bibinfo = {}
582: for e in bib:
583: bibinfo[e.localName] = getTextFromNode(e)
584: docinfo['bib'] = bibinfo
585:
586: # extract some fields (author, title, year) according to their mapping
1.4 casties 587: metaData=self.metadata.main.meta.bib
588: bibtype=dom.xpath("//bib/@type")
589: if bibtype and (len(bibtype)>0):
590: bibtype=bibtype[0].value
1.2 dwinter 591: else:
1.4 casties 592: bibtype="generic"
1.27 casties 593:
1.4 casties 594: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 595: docinfo['bib_type'] = bibtype
1.4 casties 596: bibmap=metaData.generateMappingForType(bibtype)
1.99 dwinter 597: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
598: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
1.8 casties 599: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 600: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 601: try:
602: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
603: except: pass
604: try:
605: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
606: except: pass
607: try:
608: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
609: except: pass
1.95 abukhman 610: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 611: try:
612: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
613: except:
614: docinfo['lang']=''
1.113 abukhman 615:
1.3 casties 616: return docinfo
1.42 abukhman 617:
1.104 abukhman 618:
619: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
620: """gets name info from the index.meta file at path or given by dom"""
621: if docinfo is None:
622: docinfo = {}
623:
624: if dom is None:
625: for x in range(cut):
626: path=getParentDir(path)
627: dom = self.getDomFromIndexMeta(path)
1.125 abukhman 628:
1.115 abukhman 629: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
1.116 abukhman 630: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.104 abukhman 631: return docinfo
1.42 abukhman 632:
1.43 casties 633: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
634: """parse texttool tag in index meta"""
1.95 abukhman 635: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 636: if docinfo is None:
637: docinfo = {}
638: if docinfo.get('lang', None) is None:
639: docinfo['lang'] = '' # default keine Sprache gesetzt
640: if dom is None:
1.99 dwinter 641: dom = self.getDomFromIndexMeta(url)
1.43 casties 642:
643: archivePath = None
644: archiveName = None
645:
646: archiveNames = dom.xpath("//resource/name")
647: if archiveNames and (len(archiveNames) > 0):
648: archiveName = getTextFromNode(archiveNames[0])
649: else:
1.70 casties 650: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 651:
652: archivePaths = dom.xpath("//resource/archive-path")
653: if archivePaths and (len(archivePaths) > 0):
654: archivePath = getTextFromNode(archivePaths[0])
655: # clean up archive path
656: if archivePath[0] != '/':
657: archivePath = '/' + archivePath
658: if archiveName and (not archivePath.endswith(archiveName)):
659: archivePath += "/" + archiveName
660: else:
661: # try to get archive-path from url
1.95 abukhman 662: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 663: if (not url.startswith('http')):
664: archivePath = url.replace('index.meta', '')
665:
666: if archivePath is None:
667: # we balk without archive-path
668: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
669:
670: imageDirs = dom.xpath("//texttool/image")
671: if imageDirs and (len(imageDirs) > 0):
672: imageDir = getTextFromNode(imageDirs[0])
673:
674: else:
675: # we balk with no image tag / not necessary anymore because textmode is now standard
676: #raise IOError("No text-tool info in %s"%(url))
677: imageDir = ""
678: #xquery="//pb"
679: docinfo['imagePath'] = "" # keine Bilder
680: docinfo['imageURL'] = ""
681:
682: if imageDir and archivePath:
683: #print "image: ", imageDir, " archivepath: ", archivePath
684: imageDir = os.path.join(archivePath, imageDir)
685: imageDir = imageDir.replace("/mpiwg/online", '')
686: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
687: docinfo['imagePath'] = imageDir
688:
689: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
690:
691: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
692: if viewerUrls and (len(viewerUrls) > 0):
693: viewerUrl = getTextFromNode(viewerUrls[0])
694: docinfo['viewerURL'] = viewerUrl
1.70 casties 695:
696: # old style text URL
1.43 casties 697: textUrls = dom.xpath("//texttool/text")
698: if textUrls and (len(textUrls) > 0):
699: textUrl = getTextFromNode(textUrls[0])
700: if urlparse.urlparse(textUrl)[0] == "": #keine url
701: textUrl = os.path.join(archivePath, textUrl)
702: # fix URLs starting with /mpiwg/online
703: if textUrl.startswith("/mpiwg/online"):
704: textUrl = textUrl.replace("/mpiwg/online", '', 1)
705:
706: docinfo['textURL'] = textUrl
707:
1.70 casties 708: # new style text-url-path
1.43 casties 709: textUrls = dom.xpath("//texttool/text-url-path")
710: if textUrls and (len(textUrls) > 0):
711: textUrl = getTextFromNode(textUrls[0])
1.51 casties 712: docinfo['textURLPath'] = textUrl
713: if not docinfo['imagePath']:
714: # text-only, no page images
1.103 abukhman 715: docinfo = self.getNumTextPages(docinfo)
1.43 casties 716:
717: presentationUrls = dom.xpath("//texttool/presentation")
718: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.114 abukhman 719: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.147 abukhman 720:
1.43 casties 721:
722: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
723: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
724: # durch den relativen Pfad auf die presentation infos
725: presentationPath = getTextFromNode(presentationUrls[0])
726: if url.endswith("index.meta"):
727: presentationUrl = url.replace('index.meta', presentationPath)
728: else:
729: presentationUrl = url + "/" + presentationPath
1.51 casties 730:
1.43 casties 731: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
732:
733: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 734:
1.43 casties 735: return docinfo
1.3 casties 736:
1.20 dwinter 737:
738: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
739: """gets the bibliographical information from the preseantion entry in texttools
740: """
741: dom=self.getPresentationInfoXML(url)
1.29 casties 742: try:
743: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
744: except:
745: pass
746: try:
747: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
748: except:
749: pass
750: try:
751: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
752: except:
753: pass
1.20 dwinter 754: return docinfo
755:
1.33 dwinter 756: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 757: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 758: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 759: if docinfo is None:
760: docinfo = {}
1.6 casties 761: path=path.replace("/mpiwg/online","")
1.3 casties 762: docinfo['imagePath'] = path
1.35 dwinter 763: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 764:
1.39 dwinter 765: pathorig=path
1.38 dwinter 766: for x in range(cut):
767: path=getParentDir(path)
1.95 abukhman 768: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 769: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 770: docinfo['imageURL'] = imageUrl
771:
1.39 dwinter 772: #path ist the path to the images it assumes that the index.meta file is one level higher.
773: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
774: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 775: return docinfo
776:
1.2 dwinter 777:
1.3 casties 778: def getDocinfo(self, mode, url):
779: """returns docinfo depending on mode"""
1.95 abukhman 780: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 781: # look for cached docinfo in session
1.21 dwinter 782: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 783: docinfo = self.REQUEST.SESSION['docinfo']
784: # check if its still current
785: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.95 abukhman 786: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 787: return docinfo
788: # new docinfo
789: docinfo = {'mode': mode, 'url': url}
790: if mode=="texttool": #index.meta with texttool information
791: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
792: elif mode=="imagepath":
793: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 794: elif mode=="filepath":
1.37 dwinter 795: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 796: else:
1.95 abukhman 797: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 798: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.159 ! casties 799:
! 800: # FIXME: fake texturlpath
! 801: if not docinfo.has_key('textURLPath'):
! 802: docinfo['textURLPath'] = None
! 803:
1.95 abukhman 804: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.142 abukhman 805: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
1.3 casties 806: self.REQUEST.SESSION['docinfo'] = docinfo
807: return docinfo
1.69 abukhman 808:
1.158 casties 809: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 810: """returns pageinfo with the given parameters"""
811: pageinfo = {}
1.4 casties 812: current = getInt(current)
1.132 abukhman 813:
1.4 casties 814: pageinfo['current'] = current
815: rows = int(rows or self.thumbrows)
816: pageinfo['rows'] = rows
817: cols = int(cols or self.thumbcols)
818: pageinfo['cols'] = cols
819: grpsize = cols * rows
820: pageinfo['groupsize'] = grpsize
1.28 casties 821: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
822: # int(current / grpsize) * grpsize +1))
1.3 casties 823: pageinfo['start'] = start
1.4 casties 824: pageinfo['end'] = start + grpsize
1.44 casties 825: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 826: np = int(docinfo['numPages'])
827: pageinfo['end'] = min(pageinfo['end'], np)
828: pageinfo['numgroups'] = int(np / grpsize)
829: if np % grpsize > 0:
1.69 abukhman 830: pageinfo['numgroups'] += 1
1.44 casties 831: pageinfo['viewMode'] = viewMode
832: pageinfo['tocMode'] = tocMode
1.158 casties 833: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','regPlusNorm')
1.156 abukhman 834: pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','')
835: pageinfo['query'] = self.REQUEST.get('query','')
1.146 abukhman 836: pageinfo['queryType'] = self.REQUEST.get('queryType','')
1.45 abukhman 837: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 838: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.146 abukhman 839: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 840: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 841: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 842: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 843: toc = int (pageinfo['tocPN'])
844: pageinfo['textPages'] =int (toc)
1.90 abukhman 845:
1.142 abukhman 846:
1.123 abukhman 847:
1.48 abukhman 848: if 'tocSize_%s'%tocMode in docinfo:
849: tocSize = int(docinfo['tocSize_%s'%tocMode])
850: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 851: # cached toc
1.48 abukhman 852: if tocSize%tocPageSize>0:
853: tocPages=tocSize/tocPageSize+1
854: else:
855: tocPages=tocSize/tocPageSize
1.69 abukhman 856: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 857: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 858: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 859: return pageinfo
860:
1.69 abukhman 861: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 862: """init document viewer"""
863: self.title=title
864: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 865: self.thumbrows = thumbrows
866: self.thumbcols = thumbcols
1.8 casties 867: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 868: if RESPONSE is not None:
869: RESPONSE.redirect('manage_main')
1.1 dwinter 870:
871: def manage_AddDocumentViewerForm(self):
872: """add the viewer form"""
1.3 casties 873: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 874: return pt()
875:
1.43 casties 876: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 877: """add the viewer"""
1.43 casties 878: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 879: self._setObject(id,newObj)
880:
881: if RESPONSE is not None:
882: RESPONSE.redirect('manage_main')
1.3 casties 883:
884: ## DocumentViewerTemplate class
885: class DocumentViewerTemplate(ZopePageTemplate):
886: """Template for document viewer"""
887: meta_type="DocumentViewer Template"
888:
889:
890: def manage_addDocumentViewerTemplateForm(self):
891: """Form for adding"""
892: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
893: return pt()
894:
895: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
896: REQUEST=None, submit=None):
897: "Add a Page Template with optional file content."
898:
899: self._setObject(id, DocumentViewerTemplate(id))
900: ob = getattr(self, id)
1.23 dwinter 901: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 902: logging.info("txt %s:"%txt)
1.23 dwinter 903: ob.pt_edit(txt,"text/html")
1.3 casties 904: if title:
905: ob.pt_setTitle(title)
906: try:
907: u = self.DestinationURL()
908: except AttributeError:
909: u = REQUEST['URL1']
910:
911: u = "%s/%s" % (u, urllib.quote(id))
912: REQUEST.RESPONSE.redirect(u+'/manage_main')
913: return ''
914:
915:
1.14 casties 916:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>