Annotation of documentViewer/documentViewer.py, revision 1.175.2.13
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:
1.175.2.11 casties 101: def getParentPath(path, cnt=1):
102: """returns pathname shortened by cnt"""
103: # make sure path doesn't end with /
104: path = path.rstrip('/')
105: # split by /, shorten, and reassemble
106: return '/'.join(path.split('/')[0:-cnt])
107:
1.175.2.8 casties 108:
1.3 casties 109: ##
110: ## documentViewer class
111: ##
112: class documentViewer(Folder):
1.1 dwinter 113: """document viewer"""
114: meta_type="Document viewer"
115:
116: security=ClassSecurityInfo()
1.3 casties 117: manage_options=Folder.manage_options+(
1.1 dwinter 118: {'label':'main config','action':'changeDocumentViewerForm'},
119: )
1.175.2.10 casties 120:
121: metadataService = None
122: """MetaDataFolder instance"""
1.1 dwinter 123:
1.3 casties 124: # templates and forms
125: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 126: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
127: toc_text = PageTemplateFile('zpt/toc_text', globals())
128: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 129: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
1.161 abukhman 130: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
1.43 casties 131: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 132: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77 abukhman 133: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 134: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.157 abukhman 135: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
1.3 casties 136: head_main = PageTemplateFile('zpt/head_main', globals())
137: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 138: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 139:
140:
1.32 dwinter 141: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 142:
1.1 dwinter 143:
1.45 abukhman 144: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 145: """init document viewer"""
146: self.id=id
147: self.title=title
1.4 casties 148: self.thumbcols = thumbcols
149: self.thumbrows = thumbrows
1.8 casties 150: # authgroups is list of authorized groups (delimited by ,)
151: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 152: # create template folder so we can always use template.something
153:
154: templateFolder = Folder('template')
155: #self['template'] = templateFolder # Zope-2.12 style
156: self._setObject('template',templateFolder) # old style
157: try:
1.70 casties 158: import MpdlXmlTextServer
1.71 casties 159: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 160: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 161: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 162: except Exception, e:
1.70 casties 163: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.175.2.10 casties 164:
1.43 casties 165: try:
166: from Products.zogiLib.zogiLib import zogiLib
167: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
168: #templateFolder['zogilib'] = zogilib
169: templateFolder._setObject('zogilib',zogilib)
170: except Exception, e:
171: logging.error("Unable to create zogiLib for zogilib: "+str(e))
1.175.2.10 casties 172:
173: try:
174: # assume MetaDataFolder instance is called metadata
175: self.metadataService = getattr(self, 'metadata')
176: except Exception, e:
177: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
178:
1.70 casties 179:
180: # proxy text server methods to fulltextclient
181: def getTextPage(self, **args):
182: """get page"""
183: return self.template.fulltextclient.getTextPage(**args)
1.171 abukhman 184:
185: def getOrigPages(self, **args):
186: """get page"""
187: return self.template.fulltextclient.getOrigPages(**args)
1.167 abukhman 188:
1.171 abukhman 189: def getOrigPagesNorm(self, **args):
190: """get page"""
191: return self.template.fulltextclient.getOrigPagesNorm(**args)
192:
1.70 casties 193: def getQuery(self, **args):
1.163 abukhman 194: """get query in search"""
1.70 casties 195: return self.template.fulltextclient.getQuery(**args)
1.163 abukhman 196:
1.70 casties 197: def getSearch(self, **args):
198: """get search"""
199: return self.template.fulltextclient.getSearch(**args)
1.120 abukhman 200:
201: def getGisPlaces(self, **args):
1.121 abukhman 202: """get gis places"""
1.120 abukhman 203: return self.template.fulltextclient.getGisPlaces(**args)
1.121 abukhman 204:
205: def getAllGisPlaces(self, **args):
1.122 abukhman 206: """get all gis places """
207: return self.template.fulltextclient.getAllGisPlaces(**args)
1.163 abukhman 208:
1.70 casties 209: def getTranslate(self, **args):
210: """get translate"""
211: return self.template.fulltextclient.getTranslate(**args)
212:
213: def getLemma(self, **args):
214: """get lemma"""
215: return self.template.fulltextclient.getLemma(**args)
216:
1.173 abukhman 217: def getLemmaQuery(self, **args):
218: """get query"""
219: return self.template.fulltextclient.getLemmaQuery(**args)
220:
221: def getLex(self, **args):
222: """get lex"""
223: return self.template.fulltextclient.getLex(**args)
224:
1.70 casties 225: def getToc(self, **args):
226: """get toc"""
227: return self.template.fulltextclient.getToc(**args)
228:
229: def getTocPage(self, **args):
230: """get tocpage"""
231: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 232:
1.70 casties 233:
1.32 dwinter 234: security.declareProtected('View','thumbs_rss')
235: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
236: '''
237: view it
238: @param mode: defines how to access the document behind url
239: @param url: url which contains display information
240: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
241:
242: '''
1.95 abukhman 243: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.175.2.5 casties 244: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 245:
246: if not hasattr(self, 'template'):
247: # create template folder if it doesn't exist
248: self.manage_addFolder('template')
249:
250: if not self.digilibBaseUrl:
251: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
252:
253: docinfo = self.getDocinfo(mode=mode,url=url)
1.132 abukhman 254: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.138 abukhman 255: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
1.126 abukhman 256: ''' ZDES '''
1.32 dwinter 257: pt = getattr(self.template, 'thumbs_main_rss')
258:
259: if viewMode=="auto": # automodus gewaehlt
1.159 casties 260: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 261: viewMode="text"
262: else:
263: viewMode="images"
264:
265: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
1.175.2.12 casties 266:
1.32 dwinter 267:
1.3 casties 268: security.declareProtected('View','index_html')
1.158 casties 269: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
1.175.2.11 casties 270: """
1.3 casties 271: view it
1.26 casties 272: @param mode: defines how to access the document behind url
1.3 casties 273: @param url: url which contains display information
1.44 casties 274: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 275: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.175.2.11 casties 276: """
1.3 casties 277:
1.138 abukhman 278: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 279:
1.3 casties 280: if not hasattr(self, 'template'):
1.43 casties 281: # this won't work
282: logging.error("template folder missing!")
283: return "ERROR: template folder missing!"
1.3 casties 284:
1.43 casties 285: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 286: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 287:
1.4 casties 288: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 289:
1.44 casties 290: if tocMode != "thumbs":
291: # get table of contents
292: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.175.2.3 casties 293:
294: # auto viewMode: text_dict if text else images
295: if viewMode=="auto":
296: if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):
1.68 casties 297: viewMode="text_dict"
1.21 dwinter 298: else:
299: viewMode="images"
1.44 casties 300:
1.175.2.3 casties 301: pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, tocMode=tocMode)
1.68 casties 302:
1.175.2.3 casties 303: if viewMode != 'images' and docinfo.get('textURLPath', None):
304: # get full text page
305: page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo)
1.163 abukhman 306: pageinfo['textPage'] = page
1.175.2.3 casties 307:
308: # get template /template/viewer_main
309: pt = getattr(self.template, 'viewer_main')
310: # and execute with parameters
311: return pt(docinfo=docinfo, pageinfo=pageinfo, viewMode=viewMode, mk=self.generateMarks(mk))
1.1 dwinter 312:
1.36 dwinter 313: def generateMarks(self,mk):
314: ret=""
1.44 casties 315: if mk is None:
316: return ""
1.73 casties 317: if not isinstance(mk, list):
1.71 casties 318: mk=[mk]
1.36 dwinter 319: for m in mk:
1.37 dwinter 320: ret+="mk=%s"%m
1.36 dwinter 321: return ret
1.149 abukhman 322:
323:
1.148 abukhman 324: def getBrowser(self):
325: """getBrowser the version of browser """
1.162 casties 326: bt = browserCheck(self)
1.164 abukhman 327: logging.debug("BROWSER VERSION: %s"%(bt))
1.162 casties 328: return bt
1.148 abukhman 329:
1.43 casties 330: def findDigilibUrl(self):
331: """try to get the digilib URL from zogilib"""
332: url = self.template.zogilib.getDLBaseUrl()
333: return url
1.67 casties 334:
335: def getDocumentViewerURL(self):
336: """returns the URL of this instance"""
337: return self.absolute_url()
1.43 casties 338:
339: def getStyle(self, idx, selected, style=""):
340: """returns a string with the given style and append 'sel' if path == selected."""
341: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
342: if idx == selected:
343: return style + 'sel'
344: else:
345: return style
1.36 dwinter 346:
1.162 casties 347: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
348: """returns URL to documentviewer with parameter param set to val or from dict params"""
349: # copy existing request params
350: urlParams=self.REQUEST.form.copy()
351: # change single param
1.4 casties 352: if param is not None:
1.7 casties 353: if val is None:
1.162 casties 354: if urlParams.has_key(param):
355: del urlParams[param]
1.4 casties 356: else:
1.162 casties 357: urlParams[param] = str(val)
1.43 casties 358:
1.162 casties 359: # change more params
360: if params is not None:
361: for k in params.keys():
362: v = params[k]
363: if v is None:
364: # val=None removes param
365: if urlParams.has_key(k):
366: del urlParams[k]
367:
368: else:
369: urlParams[k] = v
370:
371: # FIXME: does this belong here?
372: if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
373: urlParams["mode"] = "imagepath"
1.175.2.11 casties 374: urlParams["url"] = getParentPath(urlParams["url"])
1.7 casties 375:
1.162 casties 376: # quote values and assemble into query string (not escaping '/')
377: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
378: #ps = urllib.urlencode(urlParams)
379: if baseUrl is None:
380: baseUrl = self.REQUEST['URL1']
381:
382: url = "%s?%s"%(baseUrl, ps)
1.4 casties 383: return url
384:
1.162 casties 385:
386: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
1.32 dwinter 387: """link to documentviewer with parameter param set to val"""
1.162 casties 388: return self.getLink(param, val, params, baseUrl, '&')
1.40 casties 389:
1.26 casties 390: def getInfo_xml(self,url,mode):
391: """returns info about the document as XML"""
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:
1.9 casties 399: def isAccessible(self, docinfo):
1.8 casties 400: """returns if access to the resource is granted"""
401: access = docinfo.get('accessType', None)
1.95 abukhman 402: logging.debug("documentViewer (accessOK) access type %s"%access)
1.175.2.12 casties 403: if access == 'free':
1.95 abukhman 404: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 405: return True
1.175.2.12 casties 406:
1.17 casties 407: elif access is None or access in self.authgroups:
1.9 casties 408: # only local access -- only logged in users
409: user = getSecurityManager().getUser()
1.95 abukhman 410: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 411: if user is not None:
412: #print "user: ", user
413: return (user.getUserName() != "Anonymous User")
414: else:
415: return False
1.8 casties 416:
1.95 abukhman 417: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 418: return False
1.9 casties 419:
1.175.2.11 casties 420:
421:
422: def getDocinfo(self, mode, url):
423: """returns docinfo depending on mode"""
424: logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
425: # look for cached docinfo in session
426: if self.REQUEST.SESSION.has_key('docinfo'):
427: docinfo = self.REQUEST.SESSION['docinfo']
428: # check if its still current
429: if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:
430: logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())
431: return docinfo
432:
433: # new docinfo
434: docinfo = {'mode': mode, 'url': url}
435: # add self url
436: docinfo['viewerUrl'] = self.getDocumentViewerURL()
437: # get index.meta DOM
438: docUrl = None
439: metaDom = None
440: if mode=="texttool":
441: # url points to document dir or index.meta
442: metaDom = self.metadataService.getDomFromPathOrUrl(url)
443: docUrl = url.replace('/index.meta', '')
444: if metaDom is None:
445: raise IOError("Unable to find index.meta for mode=texttool!")
446:
447: elif mode=="imagepath":
448: # url points to folder with images, index.meta optional
449: # asssume index.meta in parent dir
450: docUrl = getParentPath(url)
451: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
452:
453: elif mode=="filepath":
454: # url points to image file, index.meta optional
455: # asssume index.meta is two path segments up
456: docUrl = getParentPath(url, 2)
457: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
458:
459: else:
460: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
461: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
462:
463: docinfo['documentUrl'] = docUrl
464: # process index.meta contents
465: if metaDom is not None:
466: # document directory name and path
467: resource = self.metadataService.getResourceData(dom=metaDom)
468: if resource:
469: docinfo = self.getDocinfoFromResource(docinfo, resource)
470:
471: # texttool info
472: texttool = self.metadataService.getTexttoolData(dom=metaDom)
473: if texttool:
474: docinfo = self.getDocinfoFromTexttool(docinfo, texttool)
475:
476: # bib info
477: bib = self.metadataService.getBibData(dom=metaDom)
478: if bib:
479: docinfo = self.getDocinfoFromBib(docinfo, bib)
1.175.2.12 casties 480: else:
481: # no bib - try info.xml
482: docinfo = self.getDocinfoFromPresentationInfoXml(docinfo)
1.175.2.11 casties 483:
484: # auth info
485: access = self.metadataService.getAccessData(dom=metaDom)
486: if access:
487: docinfo = self.getDocinfoFromAccess(docinfo, access)
488:
1.175.2.13! casties 489: # attribution info
! 490: attribution = self.metadataService.getAttributionData(dom=metaDom)
! 491: if attribution:
! 492: logging.debug("getDocinfo: attribution=%s"%repr(attribution))
! 493: docinfo['attribution'] = attribution
! 494: #docinfo = self.getDocinfoFromAccess(docinfo, access)
! 495:
! 496: # copyright info
! 497: copyright = self.metadataService.getCopyrightData(dom=metaDom)
! 498: if copyright:
! 499: logging.debug("getDocinfo: copyright=%s"%repr(copyright))
! 500: docinfo['copyright'] = copyright
! 501: #docinfo = self.getDocinfoFromAccess(docinfo, access)
! 502:
1.175.2.11 casties 503: # image path
504: if mode != 'texttool':
505: # override image path from texttool
1.175.2.12 casties 506: docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1)
1.175.2.11 casties 507:
508: # number of images from digilib
509: if docinfo.get('imagePath', None):
510: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath']
511: docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath'])
512:
513: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
514: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
515: # store in session
516: self.REQUEST.SESSION['docinfo'] = docinfo
517: return docinfo
518:
519: def getDocinfoFromResource(self, docinfo, resource):
520: """reads contents of resource element into docinfo"""
521: docName = resource.get('name', None)
522: docinfo['documentName'] = docName
523: docPath = resource.get('archive-path', None)
524: if docPath:
525: # clean up document path
526: if docPath[0] != '/':
527: docPath = '/' + docPath
528:
529: if docName and (not docPath.endswith(docName)):
530: docPath += "/" + docName
531:
532: else:
533: # use docUrl as docPath
534: docUrl = docinfo['documentURL']
535: if not docUrl.startswith('http:'):
536: docPath = docUrl
1.175.2.12 casties 537: if docPath:
538: # fix URLs starting with /mpiwg/online
539: docPath = docPath.replace('/mpiwg/online', '', 1)
540:
1.175.2.11 casties 541: docinfo['documentPath'] = docPath
542: return docinfo
543:
544: def getDocinfoFromTexttool(self, docinfo, texttool):
545: """reads contents of texttool element into docinfo"""
546: # image dir
547: imageDir = texttool.get('image', None)
548: docPath = docinfo.get('documentPath', None)
549: if imageDir and docPath:
550: #print "image: ", imageDir, " archivepath: ", archivePath
551: imageDir = os.path.join(docPath, imageDir)
552: imageDir = imageDir.replace('/mpiwg/online', '', 1)
553: docinfo['imagePath'] = imageDir
554:
555: # old style text URL
556: textUrl = texttool.get('text', None)
557: if textUrl and docPath:
558: if urlparse.urlparse(textUrl)[0] == "": #keine url
559: textUrl = os.path.join(docPath, textUrl)
560:
561: docinfo['textURL'] = textUrl
562:
563: # new style text-url-path
564: textUrl = texttool.get('text-url-path', None)
565: if textUrl:
566: docinfo['textURLPath'] = textUrl
567: #TODO: ugly:
568: #textUrlkurz = string.split(textUrl, ".")[0]
569: #docinfo['textURLPathkurz'] = textUrlkurz
570:
571: # old presentation stuff
572: presentation = texttool.get('presentation', None)
573: if presentation and docPath:
1.175.2.12 casties 574: if presentation.startswith('http:'):
575: docinfo['presentationUrl'] = presentation
576: else:
577: docinfo['presentationUrl'] = os.path.join(docPath, presentation)
1.175.2.11 casties 578:
579: return docinfo
580:
581: def getDocinfoFromBib(self, docinfo, bib):
582: """reads contents of bib element into docinfo"""
1.175.2.12 casties 583: logging.debug("getDocinfoFromBib bib=%s"%repr(bib))
1.175.2.11 casties 584: # put all raw bib fields in dict "bib"
585: docinfo['bib'] = bib
586: bibtype = bib.get('@type', None)
587: docinfo['bibType'] = bibtype
588: # also store DC metadata for convenience
589: dc = self.metadataService.getDCMappedData(bib)
590: docinfo['creator'] = dc.get('creator',None)
591: docinfo['title'] = dc.get('title',None)
592: docinfo['date'] = dc.get('date',None)
593: return docinfo
594:
595: def getDocinfoFromAccess(self, docinfo, acc):
596: """reads contents of access element into docinfo"""
597: #TODO: also read resource type
1.175.2.12 casties 598: logging.debug("getDocinfoFromAccess acc=%s"%repr(acc))
1.175.2.11 casties 599: try:
1.175.2.12 casties 600: acctype = acc['@attr']['type']
1.175.2.11 casties 601: if acctype:
602: access=acctype
603: if access in ['group', 'institution']:
604: access = acc['name'].lower()
605:
606: docinfo['accessType'] = access
607:
608: except:
609: pass
610:
611: return docinfo
612:
613: def getDocinfoFromDigilib(self, docinfo, path):
614: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
615: # fetch data
616: txt = getHttpData(infoUrl)
617: if not txt:
618: logging.error("Unable to get dir-info from %s"%(infoUrl))
619: return docinfo
620:
621: dom = ET.fromstring(txt)
622: size = getText(dom.find("size"))
623: logging.debug("getDocinfoFromDigilib: size=%s"%size)
624: if size:
625: docinfo['numPages'] = int(size)
626: else:
627: docinfo['numPages'] = 0
628:
629: # TODO: produce and keep list of image names and numbers
630: return docinfo
631:
632:
1.175.2.12 casties 633: def getDocinfoFromPresentationInfoXml(self,docinfo):
634: """gets DC-like bibliographical information from the presentation entry in texttools"""
635: url = docinfo.get('presentationUrl', None)
636: if not url:
637: logging.error("getDocinfoFromPresentation: no URL!")
638: return docinfo
639:
640: dom = None
641: metaUrl = None
642: if url.startswith("http://"):
643: # real URL
644: metaUrl = url
645: else:
646: # online path
647:
648: server=self.digilibBaseUrl+"/servlet/Texter?fn="
649: metaUrl=server+url
650:
651: txt=getHttpData(metaUrl)
652: if txt is None:
653: logging.error("Unable to read info.xml from %s"%(url))
654: return docinfo
655:
656: dom = ET.fromstring(txt)
657: docinfo['creator']=getText(dom.find(".//author"))
658: docinfo['title']=getText(dom.find(".//title"))
659: docinfo['date']=getText(dom.find(".//date"))
660: return docinfo
661:
662:
1.158 casties 663: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 664: """returns pageinfo with the given parameters"""
665: pageinfo = {}
1.4 casties 666: current = getInt(current)
1.132 abukhman 667:
1.4 casties 668: pageinfo['current'] = current
669: rows = int(rows or self.thumbrows)
670: pageinfo['rows'] = rows
671: cols = int(cols or self.thumbcols)
672: pageinfo['cols'] = cols
673: grpsize = cols * rows
674: pageinfo['groupsize'] = grpsize
1.175.2.7 casties 675: # what does this do?
1.28 casties 676: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
677: # int(current / grpsize) * grpsize +1))
1.3 casties 678: pageinfo['start'] = start
1.4 casties 679: pageinfo['end'] = start + grpsize
1.44 casties 680: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 681: np = int(docinfo['numPages'])
682: pageinfo['end'] = min(pageinfo['end'], np)
683: pageinfo['numgroups'] = int(np / grpsize)
684: if np % grpsize > 0:
1.175.2.7 casties 685: pageinfo['numgroups'] += 1
686:
1.44 casties 687: pageinfo['viewMode'] = viewMode
688: pageinfo['tocMode'] = tocMode
1.161 abukhman 689: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
1.174 abukhman 690: #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')
1.156 abukhman 691: pageinfo['query'] = self.REQUEST.get('query','')
1.146 abukhman 692: pageinfo['queryType'] = self.REQUEST.get('queryType','')
1.45 abukhman 693: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 694: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.146 abukhman 695: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 696: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 697: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.175.2.7 casties 698: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
699: # WTF?:
700: toc = int(pageinfo['tocPN'])
701: pageinfo['textPages'] =int(toc)
1.90 abukhman 702:
1.175.2.7 casties 703: # What does this do?
1.48 abukhman 704: if 'tocSize_%s'%tocMode in docinfo:
705: tocSize = int(docinfo['tocSize_%s'%tocMode])
706: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 707: # cached toc
1.48 abukhman 708: if tocSize%tocPageSize>0:
709: tocPages=tocSize/tocPageSize+1
710: else:
711: tocPages=tocSize/tocPageSize
1.175.2.7 casties 712:
713: pageinfo['tocPN'] = min(tocPages,toc)
714:
1.45 abukhman 715: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 716: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 717: return pageinfo
1.175.2.7 casties 718:
1.175.2.10 casties 719:
720: security.declareProtected('View management screens','changeDocumentViewerForm')
721: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
1.3 casties 722:
1.175.2.7 casties 723: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 724: """init document viewer"""
725: self.title=title
726: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 727: self.thumbrows = thumbrows
728: self.thumbcols = thumbcols
1.8 casties 729: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.175.2.10 casties 730: try:
731: # assume MetaDataFolder instance is called metadata
732: self.metadataService = getattr(self, 'metadata')
733: except Exception, e:
734: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
735:
1.3 casties 736: if RESPONSE is not None:
737: RESPONSE.redirect('manage_main')
1.1 dwinter 738:
739: def manage_AddDocumentViewerForm(self):
740: """add the viewer form"""
1.3 casties 741: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 742: return pt()
743:
1.43 casties 744: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 745: """add the viewer"""
1.43 casties 746: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 747: self._setObject(id,newObj)
748:
749: if RESPONSE is not None:
750: RESPONSE.redirect('manage_main')
1.3 casties 751:
752: ## DocumentViewerTemplate class
753: class DocumentViewerTemplate(ZopePageTemplate):
754: """Template for document viewer"""
755: meta_type="DocumentViewer Template"
756:
757:
758: def manage_addDocumentViewerTemplateForm(self):
759: """Form for adding"""
760: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
761: return pt()
762:
763: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
764: REQUEST=None, submit=None):
765: "Add a Page Template with optional file content."
766:
767: self._setObject(id, DocumentViewerTemplate(id))
768: ob = getattr(self, id)
1.23 dwinter 769: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 770: logging.info("txt %s:"%txt)
1.23 dwinter 771: ob.pt_edit(txt,"text/html")
1.3 casties 772: if title:
773: ob.pt_setTitle(title)
774: try:
775: u = self.DestinationURL()
776: except AttributeError:
777: u = REQUEST['URL1']
778:
779: u = "%s/%s" % (u, urllib.quote(id))
780: REQUEST.RESPONSE.redirect(u+'/manage_main')
781: return ''
782:
783:
1.14 casties 784:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>