Annotation of documentViewer/documentViewer.py, revision 1.175.2.8
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: def normalizeBibField(bt, underscore=True):
1.175.2.7 casties 106: """returns normalised bib type for looking up mappings"""
107: bt = bt.strip().replace(' ', '-').lower()
1.175.2.8! casties 108: if underscore:
! 109: bt = bt.replace('_', '-')
! 110:
1.175.2.7 casties 111: return bt
112:
1.175.2.5 casties 113: def getBibdataFromDom(dom):
114: """returns dict with all elements from bib-tag"""
115: bibinfo = {}
116: bib = dom.find(".//meta/bib")
117: if bib is not None:
118: # put type in @type
119: type = bib.get('type')
1.175.2.8! casties 120: bibinfo['@type'] = normalizeBibField(type)
1.175.2.5 casties 121: # put all subelements in dict
122: for e in bib:
1.175.2.8! casties 123: bibinfo[normalizeBibField(e.tag)] = getText(e)
1.175.2.5 casties 124:
125: return bibinfo
1.1 dwinter 126:
1.175.2.8! casties 127:
1.3 casties 128: ##
129: ## documentViewer class
130: ##
131: class documentViewer(Folder):
1.1 dwinter 132: """document viewer"""
133: meta_type="Document viewer"
134:
135: security=ClassSecurityInfo()
1.3 casties 136: manage_options=Folder.manage_options+(
1.1 dwinter 137: {'label':'main config','action':'changeDocumentViewerForm'},
138: )
139:
1.3 casties 140: # templates and forms
141: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 142: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
143: toc_text = PageTemplateFile('zpt/toc_text', globals())
144: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 145: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
1.161 abukhman 146: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
1.43 casties 147: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 148: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77 abukhman 149: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 150: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.157 abukhman 151: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
1.3 casties 152: head_main = PageTemplateFile('zpt/head_main', globals())
153: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 154: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 155:
156:
1.32 dwinter 157: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 158: security.declareProtected('View management screens','changeDocumentViewerForm')
159: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
160:
1.1 dwinter 161:
1.45 abukhman 162: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 163: """init document viewer"""
164: self.id=id
165: self.title=title
1.4 casties 166: self.thumbcols = thumbcols
167: self.thumbrows = thumbrows
1.8 casties 168: # authgroups is list of authorized groups (delimited by ,)
169: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 170: # create template folder so we can always use template.something
171:
172: templateFolder = Folder('template')
173: #self['template'] = templateFolder # Zope-2.12 style
174: self._setObject('template',templateFolder) # old style
175: try:
1.70 casties 176: import MpdlXmlTextServer
1.71 casties 177: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 178: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 179: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 180: except Exception, e:
1.70 casties 181: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 182: try:
183: from Products.zogiLib.zogiLib import zogiLib
184: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
185: #templateFolder['zogilib'] = zogilib
186: templateFolder._setObject('zogilib',zogilib)
187: except Exception, e:
188: logging.error("Unable to create zogiLib for zogilib: "+str(e))
189:
1.70 casties 190:
191: # proxy text server methods to fulltextclient
192: def getTextPage(self, **args):
193: """get page"""
194: return self.template.fulltextclient.getTextPage(**args)
1.171 abukhman 195:
196: def getOrigPages(self, **args):
197: """get page"""
198: return self.template.fulltextclient.getOrigPages(**args)
1.167 abukhman 199:
1.171 abukhman 200: def getOrigPagesNorm(self, **args):
201: """get page"""
202: return self.template.fulltextclient.getOrigPagesNorm(**args)
203:
1.70 casties 204: def getQuery(self, **args):
1.163 abukhman 205: """get query in search"""
1.70 casties 206: return self.template.fulltextclient.getQuery(**args)
1.163 abukhman 207:
1.70 casties 208: def getSearch(self, **args):
209: """get search"""
210: return self.template.fulltextclient.getSearch(**args)
1.120 abukhman 211:
212: def getGisPlaces(self, **args):
1.121 abukhman 213: """get gis places"""
1.120 abukhman 214: return self.template.fulltextclient.getGisPlaces(**args)
1.121 abukhman 215:
216: def getAllGisPlaces(self, **args):
1.122 abukhman 217: """get all gis places """
218: return self.template.fulltextclient.getAllGisPlaces(**args)
1.163 abukhman 219:
1.70 casties 220: def getTranslate(self, **args):
221: """get translate"""
222: return self.template.fulltextclient.getTranslate(**args)
223:
224: def getLemma(self, **args):
225: """get lemma"""
226: return self.template.fulltextclient.getLemma(**args)
227:
1.173 abukhman 228: def getLemmaQuery(self, **args):
229: """get query"""
230: return self.template.fulltextclient.getLemmaQuery(**args)
231:
232: def getLex(self, **args):
233: """get lex"""
234: return self.template.fulltextclient.getLex(**args)
235:
1.70 casties 236: def getToc(self, **args):
237: """get toc"""
238: return self.template.fulltextclient.getToc(**args)
239:
240: def getTocPage(self, **args):
241: """get tocpage"""
242: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 243:
1.70 casties 244:
1.32 dwinter 245: security.declareProtected('View','thumbs_rss')
246: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
247: '''
248: view it
249: @param mode: defines how to access the document behind url
250: @param url: url which contains display information
251: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
252:
253: '''
1.95 abukhman 254: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.175.2.5 casties 255: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 256:
257: if not hasattr(self, 'template'):
258: # create template folder if it doesn't exist
259: self.manage_addFolder('template')
260:
261: if not self.digilibBaseUrl:
262: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
263:
264: docinfo = self.getDocinfo(mode=mode,url=url)
1.132 abukhman 265: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.138 abukhman 266: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
1.126 abukhman 267: ''' ZDES '''
1.32 dwinter 268: pt = getattr(self.template, 'thumbs_main_rss')
269:
270: if viewMode=="auto": # automodus gewaehlt
1.159 casties 271: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 272: viewMode="text"
273: else:
274: viewMode="images"
275:
276: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
277:
1.3 casties 278: security.declareProtected('View','index_html')
1.158 casties 279: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
1.3 casties 280: '''
281: view it
1.26 casties 282: @param mode: defines how to access the document behind url
1.3 casties 283: @param url: url which contains display information
1.44 casties 284: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 285: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 286: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 287: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 288: '''
289:
1.138 abukhman 290: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 291:
1.3 casties 292: if not hasattr(self, 'template'):
1.43 casties 293: # this won't work
294: logging.error("template folder missing!")
295: return "ERROR: template folder missing!"
1.3 casties 296:
1.43 casties 297: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 298: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 299:
1.4 casties 300: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 301:
1.44 casties 302: if tocMode != "thumbs":
303: # get table of contents
304: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.175.2.3 casties 305:
306: # auto viewMode: text_dict if text else images
307: if viewMode=="auto":
308: if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):
309: #texturl gesetzt und textViewer konfiguriert
1.68 casties 310: viewMode="text_dict"
1.21 dwinter 311: else:
312: viewMode="images"
1.44 casties 313:
1.175.2.3 casties 314: pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, tocMode=tocMode)
1.68 casties 315:
1.175.2.3 casties 316: if viewMode != 'images' and docinfo.get('textURLPath', None):
317: # get full text page
318: page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo)
1.163 abukhman 319: pageinfo['textPage'] = page
1.175.2.3 casties 320:
321: # get template /template/viewer_main
322: pt = getattr(self.template, 'viewer_main')
323: # and execute with parameters
324: return pt(docinfo=docinfo, pageinfo=pageinfo, viewMode=viewMode, mk=self.generateMarks(mk))
1.1 dwinter 325:
1.36 dwinter 326: def generateMarks(self,mk):
327: ret=""
1.44 casties 328: if mk is None:
329: return ""
1.73 casties 330: if not isinstance(mk, list):
1.71 casties 331: mk=[mk]
1.36 dwinter 332: for m in mk:
1.37 dwinter 333: ret+="mk=%s"%m
1.36 dwinter 334: return ret
1.149 abukhman 335:
336:
1.148 abukhman 337: def getBrowser(self):
338: """getBrowser the version of browser """
1.162 casties 339: bt = browserCheck(self)
1.164 abukhman 340: logging.debug("BROWSER VERSION: %s"%(bt))
1.162 casties 341: return bt
1.148 abukhman 342:
1.43 casties 343: def findDigilibUrl(self):
344: """try to get the digilib URL from zogilib"""
345: url = self.template.zogilib.getDLBaseUrl()
346: return url
1.67 casties 347:
348: def getDocumentViewerURL(self):
349: """returns the URL of this instance"""
350: return self.absolute_url()
1.43 casties 351:
352: def getStyle(self, idx, selected, style=""):
353: """returns a string with the given style and append 'sel' if path == selected."""
354: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
355: if idx == selected:
356: return style + 'sel'
357: else:
358: return style
1.36 dwinter 359:
1.162 casties 360: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
361: """returns URL to documentviewer with parameter param set to val or from dict params"""
362: # copy existing request params
363: urlParams=self.REQUEST.form.copy()
364: # change single param
1.4 casties 365: if param is not None:
1.7 casties 366: if val is None:
1.162 casties 367: if urlParams.has_key(param):
368: del urlParams[param]
1.4 casties 369: else:
1.162 casties 370: urlParams[param] = str(val)
1.43 casties 371:
1.162 casties 372: # change more params
373: if params is not None:
374: for k in params.keys():
375: v = params[k]
376: if v is None:
377: # val=None removes param
378: if urlParams.has_key(k):
379: del urlParams[k]
380:
381: else:
382: urlParams[k] = v
383:
384: # FIXME: does this belong here?
385: if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
386: urlParams["mode"] = "imagepath"
387: urlParams["url"] = getParentDir(urlParams["url"])
1.7 casties 388:
1.162 casties 389: # quote values and assemble into query string (not escaping '/')
390: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
391: #ps = urllib.urlencode(urlParams)
392: if baseUrl is None:
393: baseUrl = self.REQUEST['URL1']
394:
395: url = "%s?%s"%(baseUrl, ps)
1.4 casties 396: return url
397:
1.162 casties 398:
399: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
1.32 dwinter 400: """link to documentviewer with parameter param set to val"""
1.162 casties 401: return self.getLink(param, val, params, baseUrl, '&')
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):
1.175.2.2 casties 455: path=getParentDir(path)
1.38 dwinter 456:
1.13 casties 457: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 458:
1.95 abukhman 459: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 460:
1.70 casties 461: txt = getHttpData(infoUrl)
462: if txt is None:
1.13 casties 463: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 464:
1.175.2.1 casties 465: dom = ET.fromstring(txt)
466: #dom = Parse(txt)
467: size=getText(dom.find("size"))
468: #sizes=dom.xpath("//dir/size")
469: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size)
1.6 casties 470:
1.175.2.1 casties 471: if size:
472: docinfo['numPages'] = int(size)
1.7 casties 473: else:
474: docinfo['numPages'] = 0
1.43 casties 475:
476: # TODO: produce and keep list of image names and numbers
1.7 casties 477:
478: return docinfo
1.8 casties 479:
1.99 dwinter 480: def getIndexMetaPath(self,url):
481: """gib nur den Pfad zurueck"""
482: regexp = re.compile(r".*(experimental|permanent)/(.*)")
483: regpath = regexp.match(url)
484: if (regpath==None):
485: return ""
1.110 abukhman 486: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 487: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
488:
1.111 abukhman 489:
490:
1.99 dwinter 491: def getIndexMetaUrl(self,url):
492: """returns utr of index.meta document at url"""
493:
1.12 casties 494: metaUrl = None
1.9 casties 495: if url.startswith("http://"):
496: # real URL
1.12 casties 497: metaUrl = url
1.9 casties 498: else:
499: # online path
500: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 501: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 502: if not metaUrl.endswith("index.meta"):
503: metaUrl += "/index.meta"
1.99 dwinter 504:
505: return metaUrl
506:
507: def getDomFromIndexMeta(self, url):
508: """get dom from index meta"""
509: dom = None
510: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 511:
1.99 dwinter 512: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 513: txt=getHttpData(metaUrl)
514: if txt is None:
1.12 casties 515: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 516:
1.175.2.1 casties 517: dom = ET.fromstring(txt)
518: #dom = Parse(txt)
1.9 casties 519: return dom
1.20 dwinter 520:
521: def getPresentationInfoXML(self, url):
522: """returns dom of info.xml document at url"""
523: dom = None
524: metaUrl = None
525: if url.startswith("http://"):
526: # real URL
527: metaUrl = url
528: else:
529: # online path
530: server=self.digilibBaseUrl+"/servlet/Texter?fn="
531: metaUrl=server+url.replace("/mpiwg/online","")
532:
1.70 casties 533: txt=getHttpData(metaUrl)
534: if txt is None:
1.20 dwinter 535: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 536:
1.175.2.1 casties 537: dom = ET.fromstring(txt)
538: #dom = Parse(txt)
1.20 dwinter 539: return dom
1.9 casties 540:
541:
1.33 dwinter 542: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 543: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 544: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 545:
546: access = None
547:
548: if docinfo is None:
549: docinfo = {}
550:
551: if dom is None:
1.38 dwinter 552: for x in range(cut):
1.33 dwinter 553: path=getParentDir(path)
1.99 dwinter 554: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 555:
1.175.2.1 casties 556: acc = dom.find(".//access-conditions/access")
557: if acc is not None:
558: acctype = acc.get('type')
559: #acctype = dom.xpath("//access-conditions/access/@type")
560: if acctype:
561: access=acctype
562: if access in ['group', 'institution']:
563: access = dom.find(".//access-conditions/access/name").text.lower()
1.8 casties 564:
565: docinfo['accessType'] = access
566: return docinfo
1.6 casties 567:
1.8 casties 568:
1.33 dwinter 569: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 570: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 571: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 572:
1.3 casties 573: if docinfo is None:
574: docinfo = {}
1.38 dwinter 575:
1.3 casties 576: if dom is None:
1.38 dwinter 577: for x in range(cut):
1.33 dwinter 578: path=getParentDir(path)
1.99 dwinter 579: dom = self.getDomFromIndexMeta(path)
580:
581: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 582:
1.95 abukhman 583: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.175.2.6 casties 584: # put all raw bib fields in dict "bib"
1.175.2.5 casties 585: bib = getBibdataFromDom(dom)
586: docinfo['bib'] = bib
1.175.2.7 casties 587: bibtype = bib.get('@type', None)
1.27 casties 588: docinfo['bib_type'] = bibtype
1.175.2.7 casties 589: if bibtype:
590: # also store standard mapped metadata for convenience
1.30 casties 591: try:
1.175.2.7 casties 592: stdbib = self.metadata.getStdMappedHash(bib)
593: docinfo['std_bib'] = stdbib
594: docinfo['author'] = stdbib['author']
595: docinfo['title'] = stdbib['title']
596: docinfo['year'] = stdbib['year']
597: except:
598: pass
599:
1.3 casties 600: return docinfo
1.42 abukhman 601:
1.175.2.2 casties 602:
603: # TODO: is this needed?
1.104 abukhman 604: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
605: """gets name info from the index.meta file at path or given by dom"""
606: if docinfo is None:
607: docinfo = {}
608:
609: if dom is None:
610: for x in range(cut):
611: path=getParentDir(path)
612: dom = self.getDomFromIndexMeta(path)
1.125 abukhman 613:
1.175.2.1 casties 614: docinfo['name']=getText(dom.find("name"))
1.116 abukhman 615: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.104 abukhman 616: return docinfo
1.42 abukhman 617:
1.43 casties 618: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
619: """parse texttool tag in index meta"""
1.95 abukhman 620: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 621: if docinfo is None:
622: docinfo = {}
623: if docinfo.get('lang', None) is None:
624: docinfo['lang'] = '' # default keine Sprache gesetzt
625: if dom is None:
1.99 dwinter 626: dom = self.getDomFromIndexMeta(url)
1.43 casties 627:
628: archivePath = None
629: archiveName = None
630:
1.175.2.2 casties 631: archiveName = getText(dom.find("name"))
1.175.2.1 casties 632: if not archiveName:
1.70 casties 633: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 634:
1.175.2.2 casties 635: archivePath = getText(dom.find("archive-path"))
1.175.2.1 casties 636: if archivePath:
1.43 casties 637: # clean up archive path
638: if archivePath[0] != '/':
639: archivePath = '/' + archivePath
640: if archiveName and (not archivePath.endswith(archiveName)):
641: archivePath += "/" + archiveName
642: else:
643: # try to get archive-path from url
1.95 abukhman 644: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 645: if (not url.startswith('http')):
646: archivePath = url.replace('index.meta', '')
647:
648: if archivePath is None:
649: # we balk without archive-path
650: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
651:
1.175.2.1 casties 652: imageDir = getText(dom.find(".//texttool/image"))
1.43 casties 653:
1.175.2.1 casties 654: if not imageDir:
1.43 casties 655: # we balk with no image tag / not necessary anymore because textmode is now standard
656: #raise IOError("No text-tool info in %s"%(url))
657: imageDir = ""
658: #xquery="//pb"
659: docinfo['imagePath'] = "" # keine Bilder
660: docinfo['imageURL'] = ""
661:
662: if imageDir and archivePath:
663: #print "image: ", imageDir, " archivepath: ", archivePath
664: imageDir = os.path.join(archivePath, imageDir)
665: imageDir = imageDir.replace("/mpiwg/online", '')
666: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
667: docinfo['imagePath'] = imageDir
668:
669: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
670:
1.175.2.1 casties 671: viewerUrl = getText(dom.find(".//texttool/digiliburlprefix"))
672: if viewerUrl:
1.43 casties 673: docinfo['viewerURL'] = viewerUrl
1.70 casties 674:
675: # old style text URL
1.175.2.1 casties 676: textUrl = getText(dom.find(".//texttool/text"))
677: if textUrl:
1.43 casties 678: if urlparse.urlparse(textUrl)[0] == "": #keine url
679: textUrl = os.path.join(archivePath, textUrl)
680: # fix URLs starting with /mpiwg/online
681: if textUrl.startswith("/mpiwg/online"):
682: textUrl = textUrl.replace("/mpiwg/online", '', 1)
683:
684: docinfo['textURL'] = textUrl
685:
1.70 casties 686: # new style text-url-path
1.175.2.1 casties 687: textUrl = getText(dom.find(".//texttool/text-url-path"))
688: if textUrl:
1.51 casties 689: docinfo['textURLPath'] = textUrl
1.169 abukhman 690: textUrlkurz = string.split(textUrl, ".")[0]
691: docinfo['textURLPathkurz'] = textUrlkurz
1.163 abukhman 692: #if not docinfo['imagePath']:
1.51 casties 693: # text-only, no page images
1.163 abukhman 694: #docinfo = self.getNumTextPages(docinfo)
695:
1.43 casties 696:
1.175.2.1 casties 697: presentationUrl = getText(dom.find(".//texttool/presentation"))
1.43 casties 698: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.175.2.2 casties 699: # TODO: is this needed here?
1.114 abukhman 700: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.147 abukhman 701:
1.43 casties 702:
1.175.2.1 casties 703: if presentationUrl: # ueberschreibe diese durch presentation informationen
1.43 casties 704: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
705: # durch den relativen Pfad auf die presentation infos
1.175.2.1 casties 706: presentationPath = presentationUrl
1.43 casties 707: if url.endswith("index.meta"):
708: presentationUrl = url.replace('index.meta', presentationPath)
709: else:
710: presentationUrl = url + "/" + presentationPath
1.51 casties 711:
1.43 casties 712: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
713:
714: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 715:
1.43 casties 716: return docinfo
1.3 casties 717:
1.20 dwinter 718:
719: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
720: """gets the bibliographical information from the preseantion entry in texttools
721: """
722: dom=self.getPresentationInfoXML(url)
1.175.2.2 casties 723: docinfo['author']=getText(dom.find(".//author"))
724: docinfo['title']=getText(dom.find(".//title"))
725: docinfo['year']=getText(dom.find(".//date"))
1.20 dwinter 726: return docinfo
727:
1.33 dwinter 728: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 729: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 730: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 731: if docinfo is None:
732: docinfo = {}
1.6 casties 733: path=path.replace("/mpiwg/online","")
1.3 casties 734: docinfo['imagePath'] = path
1.35 dwinter 735: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 736:
1.39 dwinter 737: pathorig=path
1.38 dwinter 738: for x in range(cut):
739: path=getParentDir(path)
1.95 abukhman 740: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 741: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 742: docinfo['imageURL'] = imageUrl
743:
1.175.2.7 casties 744: #TODO: use getDocinfoFromIndexMeta
1.39 dwinter 745: #path ist the path to the images it assumes that the index.meta file is one level higher.
746: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
747: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 748: return docinfo
749:
1.2 dwinter 750:
1.3 casties 751: def getDocinfo(self, mode, url):
752: """returns docinfo depending on mode"""
1.95 abukhman 753: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 754: # look for cached docinfo in session
1.21 dwinter 755: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 756: docinfo = self.REQUEST.SESSION['docinfo']
757: # check if its still current
758: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.175.2.3 casties 759: logging.debug("documentViewer (getdocinfo) docinfo in session. keys=%s"%docinfo.keys())
1.3 casties 760: return docinfo
1.175.2.3 casties 761:
1.3 casties 762: # new docinfo
763: docinfo = {'mode': mode, 'url': url}
1.175.2.3 casties 764: # add self url
765: docinfo['viewerUrl'] = self.getDocumentViewerURL()
766: if mode=="texttool":
767: # index.meta with texttool information
1.3 casties 768: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
769: elif mode=="imagepath":
1.175.2.3 casties 770: # folder with images, index.meta optional
1.3 casties 771: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 772: elif mode=="filepath":
1.175.2.3 casties 773: # filename
1.37 dwinter 774: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 775: else:
1.95 abukhman 776: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 777: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.159 casties 778:
1.175.2.5 casties 779: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
780: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.175.2.7 casties 781: # store in session
1.3 casties 782: self.REQUEST.SESSION['docinfo'] = docinfo
783: return docinfo
1.69 abukhman 784:
1.158 casties 785: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 786: """returns pageinfo with the given parameters"""
787: pageinfo = {}
1.4 casties 788: current = getInt(current)
1.132 abukhman 789:
1.4 casties 790: pageinfo['current'] = current
791: rows = int(rows or self.thumbrows)
792: pageinfo['rows'] = rows
793: cols = int(cols or self.thumbcols)
794: pageinfo['cols'] = cols
795: grpsize = cols * rows
796: pageinfo['groupsize'] = grpsize
1.175.2.7 casties 797: # what does this do?
1.28 casties 798: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
799: # int(current / grpsize) * grpsize +1))
1.3 casties 800: pageinfo['start'] = start
1.4 casties 801: pageinfo['end'] = start + grpsize
1.44 casties 802: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 803: np = int(docinfo['numPages'])
804: pageinfo['end'] = min(pageinfo['end'], np)
805: pageinfo['numgroups'] = int(np / grpsize)
806: if np % grpsize > 0:
1.175.2.7 casties 807: pageinfo['numgroups'] += 1
808:
1.44 casties 809: pageinfo['viewMode'] = viewMode
810: pageinfo['tocMode'] = tocMode
1.161 abukhman 811: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
1.174 abukhman 812: #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')
1.156 abukhman 813: pageinfo['query'] = self.REQUEST.get('query','')
1.146 abukhman 814: pageinfo['queryType'] = self.REQUEST.get('queryType','')
1.45 abukhman 815: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 816: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.146 abukhman 817: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 818: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 819: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.175.2.7 casties 820: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
821: # WTF?:
822: toc = int(pageinfo['tocPN'])
823: pageinfo['textPages'] =int(toc)
1.90 abukhman 824:
1.175.2.7 casties 825: # What does this do?
1.48 abukhman 826: if 'tocSize_%s'%tocMode in docinfo:
827: tocSize = int(docinfo['tocSize_%s'%tocMode])
828: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 829: # cached toc
1.48 abukhman 830: if tocSize%tocPageSize>0:
831: tocPages=tocSize/tocPageSize+1
832: else:
833: tocPages=tocSize/tocPageSize
1.175.2.7 casties 834:
835: pageinfo['tocPN'] = min(tocPages,toc)
836:
1.45 abukhman 837: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 838: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 839: return pageinfo
1.175.2.7 casties 840:
1.3 casties 841:
1.175.2.7 casties 842: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 843: """init document viewer"""
844: self.title=title
845: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 846: self.thumbrows = thumbrows
847: self.thumbcols = thumbcols
1.8 casties 848: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 849: if RESPONSE is not None:
850: RESPONSE.redirect('manage_main')
1.1 dwinter 851:
852: def manage_AddDocumentViewerForm(self):
853: """add the viewer form"""
1.3 casties 854: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 855: return pt()
856:
1.43 casties 857: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 858: """add the viewer"""
1.43 casties 859: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 860: self._setObject(id,newObj)
861:
862: if RESPONSE is not None:
863: RESPONSE.redirect('manage_main')
1.3 casties 864:
865: ## DocumentViewerTemplate class
866: class DocumentViewerTemplate(ZopePageTemplate):
867: """Template for document viewer"""
868: meta_type="DocumentViewer Template"
869:
870:
871: def manage_addDocumentViewerTemplateForm(self):
872: """Form for adding"""
873: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
874: return pt()
875:
876: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
877: REQUEST=None, submit=None):
878: "Add a Page Template with optional file content."
879:
880: self._setObject(id, DocumentViewerTemplate(id))
881: ob = getattr(self, id)
1.23 dwinter 882: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 883: logging.info("txt %s:"%txt)
1.23 dwinter 884: ob.pt_edit(txt,"text/html")
1.3 casties 885: if title:
886: ob.pt_setTitle(title)
887: try:
888: u = self.DestinationURL()
889: except AttributeError:
890: u = REQUEST['URL1']
891:
892: u = "%s/%s" % (u, urllib.quote(id))
893: REQUEST.RESPONSE.redirect(u+'/manage_main')
894: return ''
895:
896:
1.14 casties 897:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>