Annotation of documentViewer/documentViewer.py, revision 1.175.2.16
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)
1.175.2.16! casties 302:
1.175.2.3 casties 303: # get template /template/viewer_main
304: pt = getattr(self.template, 'viewer_main')
305: # and execute with parameters
306: return pt(docinfo=docinfo, pageinfo=pageinfo, viewMode=viewMode, mk=self.generateMarks(mk))
1.1 dwinter 307:
1.36 dwinter 308: def generateMarks(self,mk):
309: ret=""
1.44 casties 310: if mk is None:
311: return ""
1.73 casties 312: if not isinstance(mk, list):
1.71 casties 313: mk=[mk]
1.36 dwinter 314: for m in mk:
1.37 dwinter 315: ret+="mk=%s"%m
1.36 dwinter 316: return ret
1.149 abukhman 317:
318:
1.148 abukhman 319: def getBrowser(self):
320: """getBrowser the version of browser """
1.162 casties 321: bt = browserCheck(self)
1.164 abukhman 322: logging.debug("BROWSER VERSION: %s"%(bt))
1.162 casties 323: return bt
1.148 abukhman 324:
1.43 casties 325: def findDigilibUrl(self):
326: """try to get the digilib URL from zogilib"""
327: url = self.template.zogilib.getDLBaseUrl()
328: return url
1.67 casties 329:
330: def getDocumentViewerURL(self):
331: """returns the URL of this instance"""
332: return self.absolute_url()
1.43 casties 333:
334: def getStyle(self, idx, selected, style=""):
335: """returns a string with the given style and append 'sel' if path == selected."""
336: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
337: if idx == selected:
338: return style + 'sel'
339: else:
340: return style
1.36 dwinter 341:
1.175.2.16! casties 342: def getParams(self, param=None, val=None, params=None):
! 343: """returns dict with URL parameters.
! 344:
! 345: Takes URL parameters and additionally param=val or dict params.
! 346: Deletes key if value is None."""
1.162 casties 347: # copy existing request params
1.175.2.16! casties 348: newParams=self.REQUEST.form.copy()
1.162 casties 349: # change single param
1.4 casties 350: if param is not None:
1.7 casties 351: if val is None:
1.175.2.16! casties 352: if newParams.has_key(param):
! 353: del newParams[param]
1.4 casties 354: else:
1.175.2.16! casties 355: newParams[param] = str(val)
1.43 casties 356:
1.162 casties 357: # change more params
358: if params is not None:
359: for k in params.keys():
360: v = params[k]
361: if v is None:
362: # val=None removes param
1.175.2.16! casties 363: if newParams.has_key(k):
! 364: del newParams[k]
1.162 casties 365:
366: else:
1.175.2.16! casties 367: newParams[k] = v
! 368:
! 369: return newParams
! 370:
! 371: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
! 372: """returns URL to documentviewer with parameter param set to val or from dict params"""
! 373: urlParams = self.getParams(param=param, val=val, params=params)
1.162 casties 374: # quote values and assemble into query string (not escaping '/')
375: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
376: if baseUrl is None:
1.175.2.16! casties 377: baseUrl = self.getDocumentViewerURL()
1.162 casties 378:
379: url = "%s?%s"%(baseUrl, ps)
1.4 casties 380: return url
381:
1.162 casties 382: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
1.32 dwinter 383: """link to documentviewer with parameter param set to val"""
1.162 casties 384: return self.getLink(param, val, params, baseUrl, '&')
1.40 casties 385:
1.175.2.16! casties 386:
1.26 casties 387: def getInfo_xml(self,url,mode):
388: """returns info about the document as XML"""
389: if not self.digilibBaseUrl:
390: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
391:
392: docinfo = self.getDocinfo(mode=mode,url=url)
393: pt = getattr(self.template, 'info_xml')
394: return pt(docinfo=docinfo)
395:
1.9 casties 396: def isAccessible(self, docinfo):
1.8 casties 397: """returns if access to the resource is granted"""
398: access = docinfo.get('accessType', None)
1.95 abukhman 399: logging.debug("documentViewer (accessOK) access type %s"%access)
1.175.2.12 casties 400: if access == 'free':
1.95 abukhman 401: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 402: return True
1.175.2.12 casties 403:
1.17 casties 404: elif access is None or access in self.authgroups:
1.9 casties 405: # only local access -- only logged in users
406: user = getSecurityManager().getUser()
1.95 abukhman 407: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 408: if user is not None:
409: #print "user: ", user
410: return (user.getUserName() != "Anonymous User")
411: else:
412: return False
1.8 casties 413:
1.95 abukhman 414: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 415: return False
1.9 casties 416:
1.175.2.11 casties 417:
418:
419: def getDocinfo(self, mode, url):
420: """returns docinfo depending on mode"""
421: logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
422: # look for cached docinfo in session
423: if self.REQUEST.SESSION.has_key('docinfo'):
424: docinfo = self.REQUEST.SESSION['docinfo']
425: # check if its still current
426: if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:
427: logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())
428: return docinfo
429:
430: # new docinfo
431: docinfo = {'mode': mode, 'url': url}
432: # add self url
433: docinfo['viewerUrl'] = self.getDocumentViewerURL()
434: # get index.meta DOM
435: docUrl = None
436: metaDom = None
437: if mode=="texttool":
438: # url points to document dir or index.meta
439: metaDom = self.metadataService.getDomFromPathOrUrl(url)
440: docUrl = url.replace('/index.meta', '')
441: if metaDom is None:
442: raise IOError("Unable to find index.meta for mode=texttool!")
443:
444: elif mode=="imagepath":
445: # url points to folder with images, index.meta optional
446: # asssume index.meta in parent dir
447: docUrl = getParentPath(url)
448: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
449:
450: elif mode=="filepath":
451: # url points to image file, index.meta optional
452: # asssume index.meta is two path segments up
453: docUrl = getParentPath(url, 2)
454: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
455:
456: else:
457: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
458: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
459:
460: docinfo['documentUrl'] = docUrl
461: # process index.meta contents
462: if metaDom is not None:
463: # document directory name and path
464: resource = self.metadataService.getResourceData(dom=metaDom)
465: if resource:
466: docinfo = self.getDocinfoFromResource(docinfo, resource)
467:
468: # texttool info
469: texttool = self.metadataService.getTexttoolData(dom=metaDom)
470: if texttool:
471: docinfo = self.getDocinfoFromTexttool(docinfo, texttool)
472:
473: # bib info
474: bib = self.metadataService.getBibData(dom=metaDom)
475: if bib:
476: docinfo = self.getDocinfoFromBib(docinfo, bib)
1.175.2.12 casties 477: else:
478: # no bib - try info.xml
479: docinfo = self.getDocinfoFromPresentationInfoXml(docinfo)
1.175.2.11 casties 480:
481: # auth info
482: access = self.metadataService.getAccessData(dom=metaDom)
483: if access:
484: docinfo = self.getDocinfoFromAccess(docinfo, access)
485:
1.175.2.13 casties 486: # attribution info
487: attribution = self.metadataService.getAttributionData(dom=metaDom)
488: if attribution:
489: logging.debug("getDocinfo: attribution=%s"%repr(attribution))
490: docinfo['attribution'] = attribution
491: #docinfo = self.getDocinfoFromAccess(docinfo, access)
492:
493: # copyright info
494: copyright = self.metadataService.getCopyrightData(dom=metaDom)
495: if copyright:
496: logging.debug("getDocinfo: copyright=%s"%repr(copyright))
497: docinfo['copyright'] = copyright
498: #docinfo = self.getDocinfoFromAccess(docinfo, access)
499:
1.175.2.11 casties 500: # image path
501: if mode != 'texttool':
502: # override image path from texttool
1.175.2.12 casties 503: docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1)
1.175.2.11 casties 504:
505: # number of images from digilib
506: if docinfo.get('imagePath', None):
507: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath']
508: docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath'])
509:
510: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
511: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
512: # store in session
513: self.REQUEST.SESSION['docinfo'] = docinfo
514: return docinfo
515:
516: def getDocinfoFromResource(self, docinfo, resource):
517: """reads contents of resource element into docinfo"""
518: docName = resource.get('name', None)
519: docinfo['documentName'] = docName
520: docPath = resource.get('archive-path', None)
521: if docPath:
522: # clean up document path
523: if docPath[0] != '/':
524: docPath = '/' + docPath
525:
526: if docName and (not docPath.endswith(docName)):
527: docPath += "/" + docName
528:
529: else:
530: # use docUrl as docPath
531: docUrl = docinfo['documentURL']
532: if not docUrl.startswith('http:'):
533: docPath = docUrl
1.175.2.12 casties 534: if docPath:
535: # fix URLs starting with /mpiwg/online
536: docPath = docPath.replace('/mpiwg/online', '', 1)
537:
1.175.2.11 casties 538: docinfo['documentPath'] = docPath
539: return docinfo
540:
541: def getDocinfoFromTexttool(self, docinfo, texttool):
542: """reads contents of texttool element into docinfo"""
543: # image dir
544: imageDir = texttool.get('image', None)
545: docPath = docinfo.get('documentPath', None)
546: if imageDir and docPath:
547: #print "image: ", imageDir, " archivepath: ", archivePath
548: imageDir = os.path.join(docPath, imageDir)
549: imageDir = imageDir.replace('/mpiwg/online', '', 1)
550: docinfo['imagePath'] = imageDir
551:
552: # old style text URL
553: textUrl = texttool.get('text', None)
554: if textUrl and docPath:
555: if urlparse.urlparse(textUrl)[0] == "": #keine url
556: textUrl = os.path.join(docPath, textUrl)
557:
558: docinfo['textURL'] = textUrl
559:
560: # new style text-url-path
561: textUrl = texttool.get('text-url-path', None)
562: if textUrl:
563: docinfo['textURLPath'] = textUrl
1.175.2.15 casties 564:
565: # page flow
566: docinfo['pageFlow'] = texttool.get('page-flow', 'ltr')
567:
568: # odd pages are left
569: docinfo['oddPage'] = texttool.get('odd-scan-orientation', 'left')
570:
1.175.2.16! casties 571: # number of title page (0: not defined)
1.175.2.15 casties 572: docinfo['titlePage'] = texttool.get('title-scan-no', 0)
1.175.2.11 casties 573:
574: # old presentation stuff
575: presentation = texttool.get('presentation', None)
576: if presentation and docPath:
1.175.2.12 casties 577: if presentation.startswith('http:'):
578: docinfo['presentationUrl'] = presentation
579: else:
580: docinfo['presentationUrl'] = os.path.join(docPath, presentation)
1.175.2.11 casties 581:
1.175.2.15 casties 582:
1.175.2.11 casties 583: return docinfo
584:
585: def getDocinfoFromBib(self, docinfo, bib):
586: """reads contents of bib element into docinfo"""
1.175.2.12 casties 587: logging.debug("getDocinfoFromBib bib=%s"%repr(bib))
1.175.2.11 casties 588: # put all raw bib fields in dict "bib"
589: docinfo['bib'] = bib
590: bibtype = bib.get('@type', None)
591: docinfo['bibType'] = bibtype
592: # also store DC metadata for convenience
593: dc = self.metadataService.getDCMappedData(bib)
594: docinfo['creator'] = dc.get('creator',None)
595: docinfo['title'] = dc.get('title',None)
596: docinfo['date'] = dc.get('date',None)
597: return docinfo
598:
599: def getDocinfoFromAccess(self, docinfo, acc):
600: """reads contents of access element into docinfo"""
601: #TODO: also read resource type
1.175.2.12 casties 602: logging.debug("getDocinfoFromAccess acc=%s"%repr(acc))
1.175.2.11 casties 603: try:
1.175.2.12 casties 604: acctype = acc['@attr']['type']
1.175.2.11 casties 605: if acctype:
606: access=acctype
607: if access in ['group', 'institution']:
608: access = acc['name'].lower()
609:
610: docinfo['accessType'] = access
611:
612: except:
613: pass
614:
615: return docinfo
616:
617: def getDocinfoFromDigilib(self, docinfo, path):
618: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
619: # fetch data
620: txt = getHttpData(infoUrl)
621: if not txt:
622: logging.error("Unable to get dir-info from %s"%(infoUrl))
623: return docinfo
624:
625: dom = ET.fromstring(txt)
626: size = getText(dom.find("size"))
627: logging.debug("getDocinfoFromDigilib: size=%s"%size)
628: if size:
629: docinfo['numPages'] = int(size)
630: else:
631: docinfo['numPages'] = 0
632:
633: # TODO: produce and keep list of image names and numbers
634: return docinfo
635:
636:
1.175.2.12 casties 637: def getDocinfoFromPresentationInfoXml(self,docinfo):
638: """gets DC-like bibliographical information from the presentation entry in texttools"""
639: url = docinfo.get('presentationUrl', None)
640: if not url:
641: logging.error("getDocinfoFromPresentation: no URL!")
642: return docinfo
643:
644: dom = None
645: metaUrl = None
646: if url.startswith("http://"):
647: # real URL
648: metaUrl = url
649: else:
650: # online path
651:
652: server=self.digilibBaseUrl+"/servlet/Texter?fn="
653: metaUrl=server+url
654:
655: txt=getHttpData(metaUrl)
656: if txt is None:
657: logging.error("Unable to read info.xml from %s"%(url))
658: return docinfo
659:
660: dom = ET.fromstring(txt)
661: docinfo['creator']=getText(dom.find(".//author"))
662: docinfo['title']=getText(dom.find(".//title"))
663: docinfo['date']=getText(dom.find(".//date"))
664: return docinfo
665:
666:
1.158 casties 667: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 668: """returns pageinfo with the given parameters"""
669: pageinfo = {}
1.4 casties 670: current = getInt(current)
671: pageinfo['current'] = current
672: rows = int(rows or self.thumbrows)
673: pageinfo['rows'] = rows
674: cols = int(cols or self.thumbcols)
675: pageinfo['cols'] = cols
676: grpsize = cols * rows
677: pageinfo['groupsize'] = grpsize
1.175.2.7 casties 678: # what does this do?
1.28 casties 679: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
680: # int(current / grpsize) * grpsize +1))
1.3 casties 681: pageinfo['start'] = start
1.4 casties 682: pageinfo['end'] = start + grpsize
1.175.2.16! casties 683: pn = self.REQUEST.get('pn','1')
! 684: pageinfo['pn'] = pn
! 685: np = int(docinfo.get('numPages', 0))
! 686: if np == 0:
! 687: # numPages unknown - maybe we can get it from text page
! 688: if docinfo.get('textURLPath', None):
! 689: # cache text page as well
! 690: pageinfo['textPage'] = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo)
! 691: np = int(docinfo.get('numPages', 0))
! 692:
! 693: pageinfo['end'] = min(pageinfo['end'], np)
! 694: pageinfo['numgroups'] = int(np / grpsize)
! 695: if np % grpsize > 0:
! 696: pageinfo['numgroups'] += 1
1.175.2.7 casties 697:
1.44 casties 698: pageinfo['viewMode'] = viewMode
699: pageinfo['tocMode'] = tocMode
1.161 abukhman 700: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
1.174 abukhman 701: #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')
1.156 abukhman 702: pageinfo['query'] = self.REQUEST.get('query','')
1.146 abukhman 703: pageinfo['queryType'] = self.REQUEST.get('queryType','')
1.45 abukhman 704: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.146 abukhman 705: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 706: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 707: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.175.2.7 casties 708: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
709: # WTF?:
710: toc = int(pageinfo['tocPN'])
711: pageinfo['textPages'] =int(toc)
1.90 abukhman 712:
1.175.2.7 casties 713: # What does this do?
1.48 abukhman 714: if 'tocSize_%s'%tocMode in docinfo:
715: tocSize = int(docinfo['tocSize_%s'%tocMode])
716: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 717: # cached toc
1.48 abukhman 718: if tocSize%tocPageSize>0:
719: tocPages=tocSize/tocPageSize+1
720: else:
721: tocPages=tocSize/tocPageSize
1.175.2.7 casties 722:
723: pageinfo['tocPN'] = min(tocPages,toc)
724:
1.45 abukhman 725: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.3 casties 726: return pageinfo
1.175.2.7 casties 727:
1.175.2.10 casties 728:
729: security.declareProtected('View management screens','changeDocumentViewerForm')
730: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
1.3 casties 731:
1.175.2.7 casties 732: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 733: """init document viewer"""
734: self.title=title
735: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 736: self.thumbrows = thumbrows
737: self.thumbcols = thumbcols
1.8 casties 738: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.175.2.10 casties 739: try:
740: # assume MetaDataFolder instance is called metadata
741: self.metadataService = getattr(self, 'metadata')
742: except Exception, e:
743: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
744:
1.3 casties 745: if RESPONSE is not None:
746: RESPONSE.redirect('manage_main')
1.1 dwinter 747:
748: def manage_AddDocumentViewerForm(self):
749: """add the viewer form"""
1.3 casties 750: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 751: return pt()
752:
1.43 casties 753: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 754: """add the viewer"""
1.43 casties 755: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 756: self._setObject(id,newObj)
757:
758: if RESPONSE is not None:
759: RESPONSE.redirect('manage_main')
1.3 casties 760:
761: ## DocumentViewerTemplate class
762: class DocumentViewerTemplate(ZopePageTemplate):
763: """Template for document viewer"""
764: meta_type="DocumentViewer Template"
765:
766:
767: def manage_addDocumentViewerTemplateForm(self):
768: """Form for adding"""
769: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
770: return pt()
771:
772: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
773: REQUEST=None, submit=None):
774: "Add a Page Template with optional file content."
775:
776: self._setObject(id, DocumentViewerTemplate(id))
777: ob = getattr(self, id)
1.23 dwinter 778: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 779: logging.info("txt %s:"%txt)
1.23 dwinter 780: ob.pt_edit(txt,"text/html")
1.3 casties 781: if title:
782: ob.pt_setTitle(title)
783: try:
784: u = self.DestinationURL()
785: except AttributeError:
786: u = REQUEST['URL1']
787:
788: u = "%s/%s" % (u, urllib.quote(id))
789: REQUEST.RESPONSE.redirect(u+'/manage_main')
790: return ''
791:
792:
1.14 casties 793:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>