Annotation of documentViewer/documentViewer.py, revision 1.175.2.10
1.1 dwinter 1: from OFS.Folder import Folder
2: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
1.22 dwinter 3: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
1.1 dwinter 4: from AccessControl import ClassSecurityInfo
1.8 casties 5: from AccessControl import getSecurityManager
1.1 dwinter 6: from Globals import package_home
7:
1.175.2.1 casties 8: #from Ft.Xml import EMPTY_NAMESPACE, Parse
9: #import Ft.Xml.Domlette
10:
11: import xml.etree.ElementTree as ET
12:
1.1 dwinter 13: import os.path
1.7 casties 14: import sys
1.1 dwinter 15: import urllib
1.20 dwinter 16: import logging
1.28 casties 17: import math
1.18 dwinter 18: import urlparse
1.99 dwinter 19: import re
1.149 abukhman 20: import string
1.117 abukhman 21:
1.175.2.5 casties 22: from SrvTxtUtils import getInt, getText, getHttpData
23:
1.22 dwinter 24: def logger(txt,method,txt2):
25: """logging"""
26: logging.info(txt+ txt2)
27:
28:
1.170 abukhman 29: def serializeNode(node, encoding="utf-8"):
1.43 casties 30: """returns a string containing node as XML"""
1.175.2.1 casties 31: s = ET.tostring(node)
32:
33: # 4Suite:
34: # stream = cStringIO.StringIO()
35: # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
36: # s = stream.getvalue()
37: # stream.close()
1.43 casties 38: return s
39:
1.148 abukhman 40: def browserCheck(self):
41: """check the browsers request to find out the browser type"""
42: bt = {}
43: ua = self.REQUEST.get_header("HTTP_USER_AGENT")
44: bt['ua'] = ua
45: bt['isIE'] = False
46: bt['isN4'] = False
1.165 abukhman 47: bt['versFirefox']=""
48: bt['versIE']=""
49: bt['versSafariChrome']=""
50: bt['versOpera']=""
51:
1.148 abukhman 52: if string.find(ua, 'MSIE') > -1:
53: bt['isIE'] = True
54: else:
55: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
1.165 abukhman 56: # Safari oder Chrome identification
57: try:
58: nav = ua[string.find(ua, '('):]
59: nav1=ua[string.find(ua,')'):]
60: nav2=nav1[string.find(nav1,'('):]
61: nav3=nav2[string.find(nav2,')'):]
62: ie = string.split(nav, "; ")[1]
63: ie1 =string.split(nav1, " ")[2]
64: ie2 =string.split(nav3, " ")[1]
65: ie3 =string.split(nav3, " ")[2]
66: if string.find(ie3, "Safari") >-1:
67: bt['versSafariChrome']=string.split(ie2, "/")[1]
68: except: pass
69: # IE identification
1.148 abukhman 70: try:
71: nav = ua[string.find(ua, '('):]
72: ie = string.split(nav, "; ")[1]
73: if string.find(ie, "MSIE") > -1:
74: bt['versIE'] = string.split(ie, " ")[1]
1.165 abukhman 75: except:pass
76: # Firefox identification
77: try:
78: nav = ua[string.find(ua, '('):]
79: nav1=ua[string.find(ua,')'):]
80: if string.find(ie1, "Firefox") >-1:
81: nav5= string.split(ie1, "/")[1]
82: logging.debug("FIREFOX: %s"%(nav5))
1.166 abukhman 83: bt['versFirefox']=nav5[0:3]
1.165 abukhman 84: except:pass
85: #Opera identification
86: try:
87: if string.find(ua,"Opera") >-1:
88: nav = ua[string.find(ua, '('):]
89: nav1=nav[string.find(nav,')'):]
90: bt['versOpera']=string.split(nav1,"/")[2]
91: except:pass
1.148 abukhman 92:
93: bt['isMac'] = string.find(ua, 'Macintosh') > -1
94: bt['isWin'] = string.find(ua, 'Windows') > -1
95: bt['isIEWin'] = bt['isIE'] and bt['isWin']
96: bt['isIEMac'] = bt['isIE'] and bt['isMac']
97: bt['staticHTML'] = False
98:
99: return bt
1.118 abukhman 100:
1.9 casties 101: def getParentDir(path):
102: """returns pathname shortened by one"""
103: return '/'.join(path.split('/')[0:-1])
104:
1.175.2.8 casties 105:
1.3 casties 106: ##
107: ## documentViewer class
108: ##
109: class documentViewer(Folder):
1.1 dwinter 110: """document viewer"""
111: meta_type="Document viewer"
112:
113: security=ClassSecurityInfo()
1.3 casties 114: manage_options=Folder.manage_options+(
1.1 dwinter 115: {'label':'main config','action':'changeDocumentViewerForm'},
116: )
1.175.2.10! casties 117:
! 118: metadataService = None
! 119: """MetaDataFolder instance"""
1.1 dwinter 120:
1.3 casties 121: # templates and forms
122: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 123: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
124: toc_text = PageTemplateFile('zpt/toc_text', globals())
125: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 126: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
1.161 abukhman 127: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
1.43 casties 128: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 129: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77 abukhman 130: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 131: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.157 abukhman 132: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
1.3 casties 133: head_main = PageTemplateFile('zpt/head_main', globals())
134: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 135: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 136:
137:
1.32 dwinter 138: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 139:
1.1 dwinter 140:
1.45 abukhman 141: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 142: """init document viewer"""
143: self.id=id
144: self.title=title
1.4 casties 145: self.thumbcols = thumbcols
146: self.thumbrows = thumbrows
1.8 casties 147: # authgroups is list of authorized groups (delimited by ,)
148: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 149: # create template folder so we can always use template.something
150:
151: templateFolder = Folder('template')
152: #self['template'] = templateFolder # Zope-2.12 style
153: self._setObject('template',templateFolder) # old style
154: try:
1.70 casties 155: import MpdlXmlTextServer
1.71 casties 156: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 157: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 158: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 159: except Exception, e:
1.70 casties 160: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.175.2.10! casties 161:
1.43 casties 162: try:
163: from Products.zogiLib.zogiLib import zogiLib
164: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
165: #templateFolder['zogilib'] = zogilib
166: templateFolder._setObject('zogilib',zogilib)
167: except Exception, e:
168: logging.error("Unable to create zogiLib for zogilib: "+str(e))
1.175.2.10! casties 169:
! 170: try:
! 171: # assume MetaDataFolder instance is called metadata
! 172: self.metadataService = getattr(self, 'metadata')
! 173: except Exception, e:
! 174: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
! 175:
1.70 casties 176:
177: # proxy text server methods to fulltextclient
178: def getTextPage(self, **args):
179: """get page"""
180: return self.template.fulltextclient.getTextPage(**args)
1.171 abukhman 181:
182: def getOrigPages(self, **args):
183: """get page"""
184: return self.template.fulltextclient.getOrigPages(**args)
1.167 abukhman 185:
1.171 abukhman 186: def getOrigPagesNorm(self, **args):
187: """get page"""
188: return self.template.fulltextclient.getOrigPagesNorm(**args)
189:
1.70 casties 190: def getQuery(self, **args):
1.163 abukhman 191: """get query in search"""
1.70 casties 192: return self.template.fulltextclient.getQuery(**args)
1.163 abukhman 193:
1.70 casties 194: def getSearch(self, **args):
195: """get search"""
196: return self.template.fulltextclient.getSearch(**args)
1.120 abukhman 197:
198: def getGisPlaces(self, **args):
1.121 abukhman 199: """get gis places"""
1.120 abukhman 200: return self.template.fulltextclient.getGisPlaces(**args)
1.121 abukhman 201:
202: def getAllGisPlaces(self, **args):
1.122 abukhman 203: """get all gis places """
204: return self.template.fulltextclient.getAllGisPlaces(**args)
1.163 abukhman 205:
1.70 casties 206: def getTranslate(self, **args):
207: """get translate"""
208: return self.template.fulltextclient.getTranslate(**args)
209:
210: def getLemma(self, **args):
211: """get lemma"""
212: return self.template.fulltextclient.getLemma(**args)
213:
1.173 abukhman 214: def getLemmaQuery(self, **args):
215: """get query"""
216: return self.template.fulltextclient.getLemmaQuery(**args)
217:
218: def getLex(self, **args):
219: """get lex"""
220: return self.template.fulltextclient.getLex(**args)
221:
1.70 casties 222: def getToc(self, **args):
223: """get toc"""
224: return self.template.fulltextclient.getToc(**args)
225:
226: def getTocPage(self, **args):
227: """get tocpage"""
228: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 229:
1.70 casties 230:
1.32 dwinter 231: security.declareProtected('View','thumbs_rss')
232: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
233: '''
234: view it
235: @param mode: defines how to access the document behind url
236: @param url: url which contains display information
237: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
238:
239: '''
1.95 abukhman 240: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.175.2.5 casties 241: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 242:
243: if not hasattr(self, 'template'):
244: # create template folder if it doesn't exist
245: self.manage_addFolder('template')
246:
247: if not self.digilibBaseUrl:
248: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
249:
250: docinfo = self.getDocinfo(mode=mode,url=url)
1.132 abukhman 251: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.138 abukhman 252: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
1.126 abukhman 253: ''' ZDES '''
1.32 dwinter 254: pt = getattr(self.template, 'thumbs_main_rss')
255:
256: if viewMode=="auto": # automodus gewaehlt
1.159 casties 257: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 258: viewMode="text"
259: else:
260: viewMode="images"
261:
262: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
263:
1.3 casties 264: security.declareProtected('View','index_html')
1.158 casties 265: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
1.3 casties 266: '''
267: view it
1.26 casties 268: @param mode: defines how to access the document behind url
1.3 casties 269: @param url: url which contains display information
1.44 casties 270: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 271: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 272: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 273: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 274: '''
275:
1.138 abukhman 276: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 277:
1.3 casties 278: if not hasattr(self, 'template'):
1.43 casties 279: # this won't work
280: logging.error("template folder missing!")
281: return "ERROR: template folder missing!"
1.3 casties 282:
1.43 casties 283: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 284: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 285:
1.4 casties 286: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 287:
1.44 casties 288: if tocMode != "thumbs":
289: # get table of contents
290: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.175.2.3 casties 291:
292: # auto viewMode: text_dict if text else images
293: if viewMode=="auto":
294: if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):
295: #texturl gesetzt und textViewer konfiguriert
1.68 casties 296: viewMode="text_dict"
1.21 dwinter 297: else:
298: viewMode="images"
1.44 casties 299:
1.175.2.3 casties 300: pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, tocMode=tocMode)
1.68 casties 301:
1.175.2.3 casties 302: if viewMode != 'images' and docinfo.get('textURLPath', None):
303: # get full text page
304: page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo)
1.163 abukhman 305: pageinfo['textPage'] = page
1.175.2.3 casties 306:
307: # get template /template/viewer_main
308: pt = getattr(self.template, 'viewer_main')
309: # and execute with parameters
310: return pt(docinfo=docinfo, pageinfo=pageinfo, viewMode=viewMode, mk=self.generateMarks(mk))
1.1 dwinter 311:
1.36 dwinter 312: def generateMarks(self,mk):
313: ret=""
1.44 casties 314: if mk is None:
315: return ""
1.73 casties 316: if not isinstance(mk, list):
1.71 casties 317: mk=[mk]
1.36 dwinter 318: for m in mk:
1.37 dwinter 319: ret+="mk=%s"%m
1.36 dwinter 320: return ret
1.149 abukhman 321:
322:
1.148 abukhman 323: def getBrowser(self):
324: """getBrowser the version of browser """
1.162 casties 325: bt = browserCheck(self)
1.164 abukhman 326: logging.debug("BROWSER VERSION: %s"%(bt))
1.162 casties 327: return bt
1.148 abukhman 328:
1.43 casties 329: def findDigilibUrl(self):
330: """try to get the digilib URL from zogilib"""
331: url = self.template.zogilib.getDLBaseUrl()
332: return url
1.67 casties 333:
334: def getDocumentViewerURL(self):
335: """returns the URL of this instance"""
336: return self.absolute_url()
1.43 casties 337:
338: def getStyle(self, idx, selected, style=""):
339: """returns a string with the given style and append 'sel' if path == selected."""
340: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
341: if idx == selected:
342: return style + 'sel'
343: else:
344: return style
1.36 dwinter 345:
1.162 casties 346: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
347: """returns URL to documentviewer with parameter param set to val or from dict params"""
348: # copy existing request params
349: urlParams=self.REQUEST.form.copy()
350: # change single param
1.4 casties 351: if param is not None:
1.7 casties 352: if val is None:
1.162 casties 353: if urlParams.has_key(param):
354: del urlParams[param]
1.4 casties 355: else:
1.162 casties 356: urlParams[param] = str(val)
1.43 casties 357:
1.162 casties 358: # change more params
359: if params is not None:
360: for k in params.keys():
361: v = params[k]
362: if v is None:
363: # val=None removes param
364: if urlParams.has_key(k):
365: del urlParams[k]
366:
367: else:
368: urlParams[k] = v
369:
370: # FIXME: does this belong here?
371: if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
372: urlParams["mode"] = "imagepath"
373: urlParams["url"] = getParentDir(urlParams["url"])
1.7 casties 374:
1.162 casties 375: # quote values and assemble into query string (not escaping '/')
376: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
377: #ps = urllib.urlencode(urlParams)
378: if baseUrl is None:
379: baseUrl = self.REQUEST['URL1']
380:
381: url = "%s?%s"%(baseUrl, ps)
1.4 casties 382: return url
383:
1.162 casties 384:
385: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
1.32 dwinter 386: """link to documentviewer with parameter param set to val"""
1.162 casties 387: return self.getLink(param, val, params, baseUrl, '&')
1.40 casties 388:
1.26 casties 389: def getInfo_xml(self,url,mode):
390: """returns info about the document as XML"""
391:
392: if not self.digilibBaseUrl:
393: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
394:
395: docinfo = self.getDocinfo(mode=mode,url=url)
396: pt = getattr(self.template, 'info_xml')
397: return pt(docinfo=docinfo)
398:
1.153 casties 399: def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
400: """returns new option state"""
1.155 casties 401: if not self.REQUEST.SESSION.has_key(optionName):
1.153 casties 402: # not in session -- initial
403: opt = {'lastState': newState, 'state': initialState}
404: else:
1.155 casties 405: opt = self.REQUEST.SESSION.get(optionName)
1.153 casties 406: if opt['lastState'] != newState:
407: # state in session has changed -- toggle
408: opt['state'] = not opt['state']
409: opt['lastState'] = newState
410:
411: self.REQUEST.SESSION[optionName] = opt
412: return opt['state']
1.4 casties 413:
1.9 casties 414: def isAccessible(self, docinfo):
1.8 casties 415: """returns if access to the resource is granted"""
416: access = docinfo.get('accessType', None)
1.95 abukhman 417: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 418: if access is not None and access == 'free':
1.95 abukhman 419: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 420: return True
1.17 casties 421: elif access is None or access in self.authgroups:
1.9 casties 422: # only local access -- only logged in users
423: user = getSecurityManager().getUser()
1.95 abukhman 424: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 425: if user is not None:
426: #print "user: ", user
427: return (user.getUserName() != "Anonymous User")
428: else:
429: return False
1.8 casties 430:
1.95 abukhman 431: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 432: return False
1.9 casties 433:
1.8 casties 434:
1.35 dwinter 435: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 436: """gibt param von dlInfo aus"""
1.7 casties 437: if docinfo is None:
438: docinfo = {}
1.35 dwinter 439:
440: for x in range(cut):
1.175.2.2 casties 441: path=getParentDir(path)
1.38 dwinter 442:
1.13 casties 443: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 444:
1.95 abukhman 445: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 446:
1.70 casties 447: txt = getHttpData(infoUrl)
448: if txt is None:
1.13 casties 449: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 450:
1.175.2.1 casties 451: dom = ET.fromstring(txt)
452: #dom = Parse(txt)
453: size=getText(dom.find("size"))
454: #sizes=dom.xpath("//dir/size")
455: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size)
1.6 casties 456:
1.175.2.1 casties 457: if size:
458: docinfo['numPages'] = int(size)
1.7 casties 459: else:
460: docinfo['numPages'] = 0
1.43 casties 461:
462: # TODO: produce and keep list of image names and numbers
1.7 casties 463:
464: return docinfo
1.8 casties 465:
1.99 dwinter 466: def getIndexMetaPath(self,url):
467: """gib nur den Pfad zurueck"""
468: regexp = re.compile(r".*(experimental|permanent)/(.*)")
469: regpath = regexp.match(url)
470: if (regpath==None):
471: return ""
1.110 abukhman 472: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 473: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
474:
1.111 abukhman 475:
476:
1.99 dwinter 477: def getIndexMetaUrl(self,url):
478: """returns utr of index.meta document at url"""
479:
1.12 casties 480: metaUrl = None
1.9 casties 481: if url.startswith("http://"):
482: # real URL
1.12 casties 483: metaUrl = url
1.9 casties 484: else:
485: # online path
486: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 487: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 488: if not metaUrl.endswith("index.meta"):
489: metaUrl += "/index.meta"
1.99 dwinter 490:
491: return metaUrl
492:
493: def getDomFromIndexMeta(self, url):
494: """get dom from index meta"""
495: dom = None
496: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 497:
1.99 dwinter 498: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 499: txt=getHttpData(metaUrl)
500: if txt is None:
1.12 casties 501: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 502:
1.175.2.1 casties 503: dom = ET.fromstring(txt)
504: #dom = Parse(txt)
1.9 casties 505: return dom
1.20 dwinter 506:
507: def getPresentationInfoXML(self, url):
508: """returns dom of info.xml document at url"""
509: dom = None
510: metaUrl = None
511: if url.startswith("http://"):
512: # real URL
513: metaUrl = url
514: else:
515: # online path
516: server=self.digilibBaseUrl+"/servlet/Texter?fn="
517: metaUrl=server+url.replace("/mpiwg/online","")
518:
1.70 casties 519: txt=getHttpData(metaUrl)
520: if txt is None:
1.20 dwinter 521: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 522:
1.175.2.1 casties 523: dom = ET.fromstring(txt)
524: #dom = Parse(txt)
1.20 dwinter 525: return dom
1.9 casties 526:
527:
1.33 dwinter 528: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 529: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 530: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 531:
532: access = None
533:
534: if docinfo is None:
535: docinfo = {}
536:
537: if dom is None:
1.38 dwinter 538: for x in range(cut):
1.33 dwinter 539: path=getParentDir(path)
1.99 dwinter 540: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 541:
1.175.2.1 casties 542: acc = dom.find(".//access-conditions/access")
543: if acc is not None:
544: acctype = acc.get('type')
545: #acctype = dom.xpath("//access-conditions/access/@type")
546: if acctype:
547: access=acctype
548: if access in ['group', 'institution']:
549: access = dom.find(".//access-conditions/access/name").text.lower()
1.8 casties 550:
551: docinfo['accessType'] = access
552: return docinfo
1.6 casties 553:
1.8 casties 554:
1.33 dwinter 555: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 556: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 557: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 558:
1.3 casties 559: if docinfo is None:
560: docinfo = {}
1.38 dwinter 561:
1.3 casties 562: if dom is None:
1.38 dwinter 563: for x in range(cut):
1.33 dwinter 564: path=getParentDir(path)
1.99 dwinter 565: dom = self.getDomFromIndexMeta(path)
566:
567: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 568:
1.95 abukhman 569: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.175.2.10! casties 570: if self.metadataService is not None:
1.175.2.9 casties 571: # put all raw bib fields in dict "bib"
1.175.2.10! casties 572: bib = self.metadataService.getBibData(dom=dom)
1.175.2.9 casties 573: docinfo['bib'] = bib
574: bibtype = bib.get('@type', None)
575: docinfo['bib_type'] = bibtype
576: # also store DC metadata for convenience
1.175.2.10! casties 577: dc = self.metadataService.getDCMappedData(bib)
1.175.2.9 casties 578: docinfo['creator'] = dc.get('creator',None)
579: docinfo['title'] = dc.get('title',None)
580: docinfo['date'] = dc.get('date',None)
581: else:
1.175.2.10! casties 582: logging.error("MetadataService not found!")
1.3 casties 583: return docinfo
1.42 abukhman 584:
1.175.2.2 casties 585:
586: # TODO: is this needed?
1.104 abukhman 587: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
588: """gets name info from the index.meta file at path or given by dom"""
589: if docinfo is None:
590: docinfo = {}
591:
592: if dom is None:
593: for x in range(cut):
594: path=getParentDir(path)
595: dom = self.getDomFromIndexMeta(path)
1.125 abukhman 596:
1.175.2.1 casties 597: docinfo['name']=getText(dom.find("name"))
1.116 abukhman 598: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.104 abukhman 599: return docinfo
1.175.2.10! casties 600:
1.42 abukhman 601:
1.43 casties 602: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
603: """parse texttool tag in index meta"""
1.95 abukhman 604: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 605: if docinfo is None:
606: docinfo = {}
607: if docinfo.get('lang', None) is None:
608: docinfo['lang'] = '' # default keine Sprache gesetzt
609: if dom is None:
1.99 dwinter 610: dom = self.getDomFromIndexMeta(url)
1.175.2.10! casties 611:
! 612: texttool = self.metadata.getTexttoolData(dom=dom)
1.43 casties 613:
614: archivePath = None
615: archiveName = None
616:
1.175.2.2 casties 617: archiveName = getText(dom.find("name"))
1.175.2.1 casties 618: if not archiveName:
1.70 casties 619: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 620:
1.175.2.2 casties 621: archivePath = getText(dom.find("archive-path"))
1.175.2.1 casties 622: if archivePath:
1.43 casties 623: # clean up archive path
624: if archivePath[0] != '/':
625: archivePath = '/' + archivePath
626: if archiveName and (not archivePath.endswith(archiveName)):
627: archivePath += "/" + archiveName
628: else:
629: # try to get archive-path from url
1.95 abukhman 630: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 631: if (not url.startswith('http')):
632: archivePath = url.replace('index.meta', '')
633:
634: if archivePath is None:
635: # we balk without archive-path
636: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
637:
1.175.2.10! casties 638: imageDir = texttool.get('image', None)
1.43 casties 639:
1.175.2.1 casties 640: if not imageDir:
1.43 casties 641: # we balk with no image tag / not necessary anymore because textmode is now standard
642: #raise IOError("No text-tool info in %s"%(url))
643: imageDir = ""
644: #xquery="//pb"
645: docinfo['imagePath'] = "" # keine Bilder
646: docinfo['imageURL'] = ""
647:
648: if imageDir and archivePath:
649: #print "image: ", imageDir, " archivepath: ", archivePath
650: imageDir = os.path.join(archivePath, imageDir)
651: imageDir = imageDir.replace("/mpiwg/online", '')
652: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
653: docinfo['imagePath'] = imageDir
654:
655: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
656:
1.175.2.10! casties 657: viewerUrl = texttool.get('digiliburlprefix', None)
1.175.2.1 casties 658: if viewerUrl:
1.43 casties 659: docinfo['viewerURL'] = viewerUrl
1.70 casties 660:
661: # old style text URL
1.175.2.10! casties 662: textUrl = texttool.get('text', None)
1.175.2.1 casties 663: if textUrl:
1.43 casties 664: if urlparse.urlparse(textUrl)[0] == "": #keine url
665: textUrl = os.path.join(archivePath, textUrl)
666: # fix URLs starting with /mpiwg/online
667: if textUrl.startswith("/mpiwg/online"):
668: textUrl = textUrl.replace("/mpiwg/online", '', 1)
669:
670: docinfo['textURL'] = textUrl
671:
1.70 casties 672: # new style text-url-path
1.175.2.10! casties 673: textUrl = texttool.get('text-url-path', None)
1.175.2.1 casties 674: if textUrl:
1.51 casties 675: docinfo['textURLPath'] = textUrl
1.169 abukhman 676: textUrlkurz = string.split(textUrl, ".")[0]
677: docinfo['textURLPathkurz'] = textUrlkurz
1.163 abukhman 678: #if not docinfo['imagePath']:
1.51 casties 679: # text-only, no page images
1.163 abukhman 680: #docinfo = self.getNumTextPages(docinfo)
681:
1.175.2.10! casties 682: # get bib info
1.43 casties 683: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.175.2.2 casties 684: # TODO: is this needed here?
1.114 abukhman 685: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.147 abukhman 686:
1.175.2.10! casties 687: # TODO: what to do with presentation?
! 688: presentationUrl = texttool.get('presentation', None)
1.175.2.1 casties 689: if presentationUrl: # ueberschreibe diese durch presentation informationen
1.43 casties 690: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
691: # durch den relativen Pfad auf die presentation infos
1.175.2.1 casties 692: presentationPath = presentationUrl
1.43 casties 693: if url.endswith("index.meta"):
694: presentationUrl = url.replace('index.meta', presentationPath)
695: else:
696: presentationUrl = url + "/" + presentationPath
1.51 casties 697:
1.43 casties 698: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
699:
1.175.2.10! casties 700: # get authorization
1.43 casties 701: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 702:
1.43 casties 703: return docinfo
1.3 casties 704:
1.20 dwinter 705:
706: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
707: """gets the bibliographical information from the preseantion entry in texttools
708: """
709: dom=self.getPresentationInfoXML(url)
1.175.2.2 casties 710: docinfo['author']=getText(dom.find(".//author"))
711: docinfo['title']=getText(dom.find(".//title"))
712: docinfo['year']=getText(dom.find(".//date"))
1.20 dwinter 713: return docinfo
714:
1.33 dwinter 715: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 716: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 717: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 718: if docinfo is None:
719: docinfo = {}
1.6 casties 720: path=path.replace("/mpiwg/online","")
1.3 casties 721: docinfo['imagePath'] = path
1.35 dwinter 722: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 723:
1.39 dwinter 724: pathorig=path
1.38 dwinter 725: for x in range(cut):
726: path=getParentDir(path)
1.95 abukhman 727: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 728: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 729: docinfo['imageURL'] = imageUrl
730:
1.175.2.7 casties 731: #TODO: use getDocinfoFromIndexMeta
1.39 dwinter 732: #path ist the path to the images it assumes that the index.meta file is one level higher.
733: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
734: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 735: return docinfo
736:
1.2 dwinter 737:
1.3 casties 738: def getDocinfo(self, mode, url):
739: """returns docinfo depending on mode"""
1.95 abukhman 740: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 741: # look for cached docinfo in session
1.21 dwinter 742: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 743: docinfo = self.REQUEST.SESSION['docinfo']
744: # check if its still current
745: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.175.2.3 casties 746: logging.debug("documentViewer (getdocinfo) docinfo in session. keys=%s"%docinfo.keys())
1.3 casties 747: return docinfo
1.175.2.3 casties 748:
1.3 casties 749: # new docinfo
750: docinfo = {'mode': mode, 'url': url}
1.175.2.3 casties 751: # add self url
752: docinfo['viewerUrl'] = self.getDocumentViewerURL()
753: if mode=="texttool":
754: # index.meta with texttool information
1.3 casties 755: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
756: elif mode=="imagepath":
1.175.2.3 casties 757: # folder with images, index.meta optional
1.3 casties 758: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 759: elif mode=="filepath":
1.175.2.3 casties 760: # filename
1.37 dwinter 761: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 762: else:
1.95 abukhman 763: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 764: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.159 casties 765:
1.175.2.5 casties 766: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
767: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.175.2.7 casties 768: # store in session
1.3 casties 769: self.REQUEST.SESSION['docinfo'] = docinfo
770: return docinfo
1.69 abukhman 771:
1.158 casties 772: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 773: """returns pageinfo with the given parameters"""
774: pageinfo = {}
1.4 casties 775: current = getInt(current)
1.132 abukhman 776:
1.4 casties 777: pageinfo['current'] = current
778: rows = int(rows or self.thumbrows)
779: pageinfo['rows'] = rows
780: cols = int(cols or self.thumbcols)
781: pageinfo['cols'] = cols
782: grpsize = cols * rows
783: pageinfo['groupsize'] = grpsize
1.175.2.7 casties 784: # what does this do?
1.28 casties 785: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
786: # int(current / grpsize) * grpsize +1))
1.3 casties 787: pageinfo['start'] = start
1.4 casties 788: pageinfo['end'] = start + grpsize
1.44 casties 789: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 790: np = int(docinfo['numPages'])
791: pageinfo['end'] = min(pageinfo['end'], np)
792: pageinfo['numgroups'] = int(np / grpsize)
793: if np % grpsize > 0:
1.175.2.7 casties 794: pageinfo['numgroups'] += 1
795:
1.44 casties 796: pageinfo['viewMode'] = viewMode
797: pageinfo['tocMode'] = tocMode
1.161 abukhman 798: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
1.174 abukhman 799: #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')
1.156 abukhman 800: pageinfo['query'] = self.REQUEST.get('query','')
1.146 abukhman 801: pageinfo['queryType'] = self.REQUEST.get('queryType','')
1.45 abukhman 802: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 803: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.146 abukhman 804: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 805: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 806: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.175.2.7 casties 807: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
808: # WTF?:
809: toc = int(pageinfo['tocPN'])
810: pageinfo['textPages'] =int(toc)
1.90 abukhman 811:
1.175.2.7 casties 812: # What does this do?
1.48 abukhman 813: if 'tocSize_%s'%tocMode in docinfo:
814: tocSize = int(docinfo['tocSize_%s'%tocMode])
815: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 816: # cached toc
1.48 abukhman 817: if tocSize%tocPageSize>0:
818: tocPages=tocSize/tocPageSize+1
819: else:
820: tocPages=tocSize/tocPageSize
1.175.2.7 casties 821:
822: pageinfo['tocPN'] = min(tocPages,toc)
823:
1.45 abukhman 824: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 825: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 826: return pageinfo
1.175.2.7 casties 827:
1.175.2.10! casties 828:
! 829: security.declareProtected('View management screens','changeDocumentViewerForm')
! 830: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
1.3 casties 831:
1.175.2.7 casties 832: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 833: """init document viewer"""
834: self.title=title
835: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 836: self.thumbrows = thumbrows
837: self.thumbcols = thumbcols
1.8 casties 838: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.175.2.10! casties 839: try:
! 840: # assume MetaDataFolder instance is called metadata
! 841: self.metadataService = getattr(self, 'metadata')
! 842: except Exception, e:
! 843: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
! 844:
1.3 casties 845: if RESPONSE is not None:
846: RESPONSE.redirect('manage_main')
1.1 dwinter 847:
848: def manage_AddDocumentViewerForm(self):
849: """add the viewer form"""
1.3 casties 850: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 851: return pt()
852:
1.43 casties 853: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 854: """add the viewer"""
1.43 casties 855: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 856: self._setObject(id,newObj)
857:
858: if RESPONSE is not None:
859: RESPONSE.redirect('manage_main')
1.3 casties 860:
861: ## DocumentViewerTemplate class
862: class DocumentViewerTemplate(ZopePageTemplate):
863: """Template for document viewer"""
864: meta_type="DocumentViewer Template"
865:
866:
867: def manage_addDocumentViewerTemplateForm(self):
868: """Form for adding"""
869: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
870: return pt()
871:
872: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
873: REQUEST=None, submit=None):
874: "Add a Page Template with optional file content."
875:
876: self._setObject(id, DocumentViewerTemplate(id))
877: ob = getattr(self, id)
1.23 dwinter 878: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 879: logging.info("txt %s:"%txt)
1.23 dwinter 880: ob.pt_edit(txt,"text/html")
1.3 casties 881: if title:
882: ob.pt_setTitle(title)
883: try:
884: u = self.DestinationURL()
885: except AttributeError:
886: u = REQUEST['URL1']
887:
888: u = "%s/%s" % (u, urllib.quote(id))
889: REQUEST.RESPONSE.redirect(u+'/manage_main')
890: return ''
891:
892:
1.14 casties 893:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>