Annotation of documentViewer/documentViewer.py, revision 1.175.2.20
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')
1.175.2.18 casties 269: def index_html(self,url,mode="texttool",viewMode="auto",viewType=None,tocMode="thumbs",start=1,pn=1):
1.175.2.11 casties 270: """
1.175.2.17 casties 271: view page
1.3 casties 272: @param url: url which contains display information
1.175.2.17 casties 273: @param mode: defines how to access the document behind url
274: @param viewMode: 'images': display images, 'text': display text, default is 'auto'
275: @param viewType: sub-type of viewMode, e.g. 'dict' for viewMode='text'
1.48 abukhman 276: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.175.2.11 casties 277: """
1.3 casties 278:
1.138 abukhman 279: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 280:
1.3 casties 281: if not hasattr(self, 'template'):
1.43 casties 282: # this won't work
283: logging.error("template folder missing!")
284: return "ERROR: template folder missing!"
1.3 casties 285:
1.43 casties 286: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 287: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 288:
1.4 casties 289: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 290:
1.44 casties 291: if tocMode != "thumbs":
292: # get table of contents
293: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.175.2.3 casties 294:
1.175.2.17 casties 295: # auto viewMode: text if there is a text else images
1.175.2.3 casties 296: if viewMode=="auto":
297: if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):
1.175.2.17 casties 298: viewMode = "text"
299: viewType = "dict"
1.21 dwinter 300: else:
1.175.2.17 casties 301: viewMode = "images"
1.44 casties 302:
1.175.2.20! casties 303: elif viewMode == "text_dict":
! 304: # legacy fix
! 305: viewMode = "text"
! 306: viewType = "dict"
! 307:
! 308:
1.175.2.18 casties 309: pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode)
1.175.2.16 casties 310:
1.175.2.3 casties 311: # get template /template/viewer_main
312: pt = getattr(self.template, 'viewer_main')
313: # and execute with parameters
1.175.2.17 casties 314: return pt(docinfo=docinfo, pageinfo=pageinfo)
1.1 dwinter 315:
1.36 dwinter 316: def generateMarks(self,mk):
317: ret=""
1.44 casties 318: if mk is None:
319: return ""
1.73 casties 320: if not isinstance(mk, list):
1.71 casties 321: mk=[mk]
1.36 dwinter 322: for m in mk:
1.37 dwinter 323: ret+="mk=%s"%m
1.36 dwinter 324: return ret
1.149 abukhman 325:
326:
1.148 abukhman 327: def getBrowser(self):
328: """getBrowser the version of browser """
1.162 casties 329: bt = browserCheck(self)
1.164 abukhman 330: logging.debug("BROWSER VERSION: %s"%(bt))
1.162 casties 331: return bt
1.148 abukhman 332:
1.43 casties 333: def findDigilibUrl(self):
334: """try to get the digilib URL from zogilib"""
335: url = self.template.zogilib.getDLBaseUrl()
336: return url
1.67 casties 337:
338: def getDocumentViewerURL(self):
339: """returns the URL of this instance"""
340: return self.absolute_url()
1.43 casties 341:
342: def getStyle(self, idx, selected, style=""):
343: """returns a string with the given style and append 'sel' if path == selected."""
344: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
345: if idx == selected:
346: return style + 'sel'
347: else:
348: return style
1.36 dwinter 349:
1.175.2.16 casties 350: def getParams(self, param=None, val=None, params=None):
351: """returns dict with URL parameters.
352:
353: Takes URL parameters and additionally param=val or dict params.
354: Deletes key if value is None."""
1.162 casties 355: # copy existing request params
1.175.2.16 casties 356: newParams=self.REQUEST.form.copy()
1.162 casties 357: # change single param
1.4 casties 358: if param is not None:
1.7 casties 359: if val is None:
1.175.2.16 casties 360: if newParams.has_key(param):
361: del newParams[param]
1.4 casties 362: else:
1.175.2.16 casties 363: newParams[param] = str(val)
1.43 casties 364:
1.162 casties 365: # change more params
366: if params is not None:
367: for k in params.keys():
368: v = params[k]
369: if v is None:
370: # val=None removes param
1.175.2.16 casties 371: if newParams.has_key(k):
372: del newParams[k]
1.162 casties 373:
374: else:
1.175.2.16 casties 375: newParams[k] = v
376:
377: return newParams
378:
379: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
380: """returns URL to documentviewer with parameter param set to val or from dict params"""
381: urlParams = self.getParams(param=param, val=val, params=params)
1.162 casties 382: # quote values and assemble into query string (not escaping '/')
383: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
384: if baseUrl is None:
1.175.2.16 casties 385: baseUrl = self.getDocumentViewerURL()
1.162 casties 386:
387: url = "%s?%s"%(baseUrl, ps)
1.4 casties 388: return url
389:
1.162 casties 390: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
1.32 dwinter 391: """link to documentviewer with parameter param set to val"""
1.162 casties 392: return self.getLink(param, val, params, baseUrl, '&')
1.40 casties 393:
1.175.2.16 casties 394:
1.26 casties 395: def getInfo_xml(self,url,mode):
396: """returns info about the document as XML"""
397: if not self.digilibBaseUrl:
398: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
399:
400: docinfo = self.getDocinfo(mode=mode,url=url)
401: pt = getattr(self.template, 'info_xml')
402: return pt(docinfo=docinfo)
403:
1.9 casties 404: def isAccessible(self, docinfo):
1.8 casties 405: """returns if access to the resource is granted"""
406: access = docinfo.get('accessType', None)
1.95 abukhman 407: logging.debug("documentViewer (accessOK) access type %s"%access)
1.175.2.12 casties 408: if access == 'free':
1.95 abukhman 409: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 410: return True
1.175.2.12 casties 411:
1.17 casties 412: elif access is None or access in self.authgroups:
1.9 casties 413: # only local access -- only logged in users
414: user = getSecurityManager().getUser()
1.95 abukhman 415: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 416: if user is not None:
417: #print "user: ", user
418: return (user.getUserName() != "Anonymous User")
419: else:
420: return False
1.8 casties 421:
1.95 abukhman 422: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 423: return False
1.9 casties 424:
1.175.2.11 casties 425:
426:
427: def getDocinfo(self, mode, url):
428: """returns docinfo depending on mode"""
429: logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
430: # look for cached docinfo in session
431: if self.REQUEST.SESSION.has_key('docinfo'):
432: docinfo = self.REQUEST.SESSION['docinfo']
433: # check if its still current
434: if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:
435: logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())
436: return docinfo
437:
438: # new docinfo
439: docinfo = {'mode': mode, 'url': url}
440: # add self url
441: docinfo['viewerUrl'] = self.getDocumentViewerURL()
442: # get index.meta DOM
443: docUrl = None
444: metaDom = None
445: if mode=="texttool":
446: # url points to document dir or index.meta
447: metaDom = self.metadataService.getDomFromPathOrUrl(url)
448: docUrl = url.replace('/index.meta', '')
449: if metaDom is None:
450: raise IOError("Unable to find index.meta for mode=texttool!")
451:
452: elif mode=="imagepath":
453: # url points to folder with images, index.meta optional
454: # asssume index.meta in parent dir
455: docUrl = getParentPath(url)
456: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
457:
458: elif mode=="filepath":
459: # url points to image file, index.meta optional
460: # asssume index.meta is two path segments up
461: docUrl = getParentPath(url, 2)
462: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
463:
464: else:
465: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
466: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
467:
468: docinfo['documentUrl'] = docUrl
469: # process index.meta contents
1.175.2.19 casties 470: if metaDom is not None and metaDom.tag == 'resource':
1.175.2.11 casties 471: # document directory name and path
472: resource = self.metadataService.getResourceData(dom=metaDom)
473: if resource:
474: docinfo = self.getDocinfoFromResource(docinfo, resource)
475:
476: # texttool info
477: texttool = self.metadataService.getTexttoolData(dom=metaDom)
478: if texttool:
479: docinfo = self.getDocinfoFromTexttool(docinfo, texttool)
480:
481: # bib info
482: bib = self.metadataService.getBibData(dom=metaDom)
483: if bib:
484: docinfo = self.getDocinfoFromBib(docinfo, bib)
1.175.2.12 casties 485: else:
486: # no bib - try info.xml
487: docinfo = self.getDocinfoFromPresentationInfoXml(docinfo)
1.175.2.11 casties 488:
489: # auth info
490: access = self.metadataService.getAccessData(dom=metaDom)
491: if access:
492: docinfo = self.getDocinfoFromAccess(docinfo, access)
493:
1.175.2.13 casties 494: # attribution info
495: attribution = self.metadataService.getAttributionData(dom=metaDom)
496: if attribution:
497: logging.debug("getDocinfo: attribution=%s"%repr(attribution))
498: docinfo['attribution'] = attribution
499: #docinfo = self.getDocinfoFromAccess(docinfo, access)
500:
501: # copyright info
502: copyright = self.metadataService.getCopyrightData(dom=metaDom)
503: if copyright:
504: logging.debug("getDocinfo: copyright=%s"%repr(copyright))
505: docinfo['copyright'] = copyright
506: #docinfo = self.getDocinfoFromAccess(docinfo, access)
507:
1.175.2.11 casties 508: # image path
509: if mode != 'texttool':
510: # override image path from texttool
1.175.2.12 casties 511: docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1)
1.175.2.11 casties 512:
513: # number of images from digilib
514: if docinfo.get('imagePath', None):
515: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath']
516: docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath'])
517:
518: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
519: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
520: # store in session
521: self.REQUEST.SESSION['docinfo'] = docinfo
522: return docinfo
523:
524: def getDocinfoFromResource(self, docinfo, resource):
525: """reads contents of resource element into docinfo"""
526: docName = resource.get('name', None)
527: docinfo['documentName'] = docName
528: docPath = resource.get('archive-path', None)
529: if docPath:
530: # clean up document path
531: if docPath[0] != '/':
532: docPath = '/' + docPath
533:
534: if docName and (not docPath.endswith(docName)):
535: docPath += "/" + docName
536:
537: else:
538: # use docUrl as docPath
539: docUrl = docinfo['documentURL']
540: if not docUrl.startswith('http:'):
541: docPath = docUrl
1.175.2.12 casties 542: if docPath:
543: # fix URLs starting with /mpiwg/online
544: docPath = docPath.replace('/mpiwg/online', '', 1)
545:
1.175.2.11 casties 546: docinfo['documentPath'] = docPath
547: return docinfo
548:
549: def getDocinfoFromTexttool(self, docinfo, texttool):
550: """reads contents of texttool element into docinfo"""
551: # image dir
552: imageDir = texttool.get('image', None)
553: docPath = docinfo.get('documentPath', None)
554: if imageDir and docPath:
555: #print "image: ", imageDir, " archivepath: ", archivePath
556: imageDir = os.path.join(docPath, imageDir)
557: imageDir = imageDir.replace('/mpiwg/online', '', 1)
558: docinfo['imagePath'] = imageDir
559:
560: # old style text URL
561: textUrl = texttool.get('text', None)
562: if textUrl and docPath:
563: if urlparse.urlparse(textUrl)[0] == "": #keine url
564: textUrl = os.path.join(docPath, textUrl)
565:
566: docinfo['textURL'] = textUrl
567:
568: # new style text-url-path
569: textUrl = texttool.get('text-url-path', None)
570: if textUrl:
571: docinfo['textURLPath'] = textUrl
1.175.2.15 casties 572:
573: # page flow
574: docinfo['pageFlow'] = texttool.get('page-flow', 'ltr')
575:
576: # odd pages are left
577: docinfo['oddPage'] = texttool.get('odd-scan-orientation', 'left')
578:
1.175.2.16 casties 579: # number of title page (0: not defined)
1.175.2.15 casties 580: docinfo['titlePage'] = texttool.get('title-scan-no', 0)
1.175.2.11 casties 581:
582: # old presentation stuff
583: presentation = texttool.get('presentation', None)
584: if presentation and docPath:
1.175.2.12 casties 585: if presentation.startswith('http:'):
586: docinfo['presentationUrl'] = presentation
587: else:
588: docinfo['presentationUrl'] = os.path.join(docPath, presentation)
1.175.2.11 casties 589:
1.175.2.15 casties 590:
1.175.2.11 casties 591: return docinfo
592:
593: def getDocinfoFromBib(self, docinfo, bib):
594: """reads contents of bib element into docinfo"""
1.175.2.12 casties 595: logging.debug("getDocinfoFromBib bib=%s"%repr(bib))
1.175.2.11 casties 596: # put all raw bib fields in dict "bib"
597: docinfo['bib'] = bib
598: bibtype = bib.get('@type', None)
599: docinfo['bibType'] = bibtype
600: # also store DC metadata for convenience
601: dc = self.metadataService.getDCMappedData(bib)
602: docinfo['creator'] = dc.get('creator',None)
603: docinfo['title'] = dc.get('title',None)
604: docinfo['date'] = dc.get('date',None)
605: return docinfo
606:
607: def getDocinfoFromAccess(self, docinfo, acc):
608: """reads contents of access element into docinfo"""
609: #TODO: also read resource type
1.175.2.12 casties 610: logging.debug("getDocinfoFromAccess acc=%s"%repr(acc))
1.175.2.11 casties 611: try:
1.175.2.12 casties 612: acctype = acc['@attr']['type']
1.175.2.11 casties 613: if acctype:
614: access=acctype
615: if access in ['group', 'institution']:
616: access = acc['name'].lower()
617:
618: docinfo['accessType'] = access
619:
620: except:
621: pass
622:
623: return docinfo
624:
625: def getDocinfoFromDigilib(self, docinfo, path):
626: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
627: # fetch data
628: txt = getHttpData(infoUrl)
629: if not txt:
630: logging.error("Unable to get dir-info from %s"%(infoUrl))
631: return docinfo
632:
633: dom = ET.fromstring(txt)
634: size = getText(dom.find("size"))
635: logging.debug("getDocinfoFromDigilib: size=%s"%size)
636: if size:
637: docinfo['numPages'] = int(size)
638: else:
639: docinfo['numPages'] = 0
640:
641: # TODO: produce and keep list of image names and numbers
642: return docinfo
643:
644:
1.175.2.12 casties 645: def getDocinfoFromPresentationInfoXml(self,docinfo):
646: """gets DC-like bibliographical information from the presentation entry in texttools"""
647: url = docinfo.get('presentationUrl', None)
648: if not url:
649: logging.error("getDocinfoFromPresentation: no URL!")
650: return docinfo
651:
652: dom = None
653: metaUrl = None
654: if url.startswith("http://"):
655: # real URL
656: metaUrl = url
657: else:
658: # online path
659:
660: server=self.digilibBaseUrl+"/servlet/Texter?fn="
661: metaUrl=server+url
662:
663: txt=getHttpData(metaUrl)
664: if txt is None:
665: logging.error("Unable to read info.xml from %s"%(url))
666: return docinfo
667:
668: dom = ET.fromstring(txt)
669: docinfo['creator']=getText(dom.find(".//author"))
670: docinfo['title']=getText(dom.find(".//title"))
671: docinfo['date']=getText(dom.find(".//date"))
672: return docinfo
673:
674:
1.175.2.17 casties 675: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None):
1.3 casties 676: """returns pageinfo with the given parameters"""
677: pageinfo = {}
1.175.2.17 casties 678: pageinfo['viewMode'] = viewMode
679: pageinfo['viewType'] = viewType
680: pageinfo['tocMode'] = tocMode
681:
1.4 casties 682: current = getInt(current)
683: pageinfo['current'] = current
684: rows = int(rows or self.thumbrows)
685: pageinfo['rows'] = rows
686: cols = int(cols or self.thumbcols)
687: pageinfo['cols'] = cols
688: grpsize = cols * rows
689: pageinfo['groupsize'] = grpsize
1.175.2.7 casties 690: # what does this do?
1.28 casties 691: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
692: # int(current / grpsize) * grpsize +1))
1.3 casties 693: pageinfo['start'] = start
1.4 casties 694: pageinfo['end'] = start + grpsize
1.175.2.16 casties 695: pn = self.REQUEST.get('pn','1')
696: pageinfo['pn'] = pn
697: np = int(docinfo.get('numPages', 0))
698: if np == 0:
699: # numPages unknown - maybe we can get it from text page
700: if docinfo.get('textURLPath', None):
701: # cache text page as well
1.175.2.17 casties 702: pageinfo['textPage'] = self.getTextPage(mode=viewType, pn=pn, docinfo=docinfo, pageinfo=pageinfo)
1.175.2.16 casties 703: np = int(docinfo.get('numPages', 0))
704:
705: pageinfo['end'] = min(pageinfo['end'], np)
706: pageinfo['numgroups'] = int(np / grpsize)
707: if np % grpsize > 0:
708: pageinfo['numgroups'] += 1
1.175.2.7 casties 709:
1.161 abukhman 710: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
1.156 abukhman 711: pageinfo['query'] = self.REQUEST.get('query','')
1.146 abukhman 712: pageinfo['queryType'] = self.REQUEST.get('queryType','')
1.45 abukhman 713: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.146 abukhman 714: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 715: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 716: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.175.2.7 casties 717: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
718: # WTF?:
719: toc = int(pageinfo['tocPN'])
1.175.2.17 casties 720: pageinfo['textPages'] = int(toc)
1.90 abukhman 721:
1.175.2.7 casties 722: # What does this do?
1.48 abukhman 723: if 'tocSize_%s'%tocMode in docinfo:
724: tocSize = int(docinfo['tocSize_%s'%tocMode])
725: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 726: # cached toc
1.48 abukhman 727: if tocSize%tocPageSize>0:
728: tocPages=tocSize/tocPageSize+1
729: else:
730: tocPages=tocSize/tocPageSize
1.175.2.7 casties 731:
732: pageinfo['tocPN'] = min(tocPages,toc)
733:
1.45 abukhman 734: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.3 casties 735: return pageinfo
1.175.2.7 casties 736:
1.175.2.10 casties 737:
738: security.declareProtected('View management screens','changeDocumentViewerForm')
739: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
1.3 casties 740:
1.175.2.7 casties 741: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 742: """init document viewer"""
743: self.title=title
744: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 745: self.thumbrows = thumbrows
746: self.thumbcols = thumbcols
1.8 casties 747: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.175.2.10 casties 748: try:
749: # assume MetaDataFolder instance is called metadata
750: self.metadataService = getattr(self, 'metadata')
751: except Exception, e:
752: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
753:
1.3 casties 754: if RESPONSE is not None:
755: RESPONSE.redirect('manage_main')
1.1 dwinter 756:
757: def manage_AddDocumentViewerForm(self):
758: """add the viewer form"""
1.3 casties 759: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 760: return pt()
761:
1.43 casties 762: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 763: """add the viewer"""
1.43 casties 764: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 765: self._setObject(id,newObj)
766:
767: if RESPONSE is not None:
768: RESPONSE.redirect('manage_main')
1.3 casties 769:
770: ## DocumentViewerTemplate class
771: class DocumentViewerTemplate(ZopePageTemplate):
772: """Template for document viewer"""
773: meta_type="DocumentViewer Template"
774:
775:
776: def manage_addDocumentViewerTemplateForm(self):
777: """Form for adding"""
778: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
779: return pt()
780:
781: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
782: REQUEST=None, submit=None):
783: "Add a Page Template with optional file content."
784:
785: self._setObject(id, DocumentViewerTemplate(id))
786: ob = getattr(self, id)
1.23 dwinter 787: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 788: logging.info("txt %s:"%txt)
1.23 dwinter 789: ob.pt_edit(txt,"text/html")
1.3 casties 790: if title:
791: ob.pt_setTitle(title)
792: try:
793: u = self.DestinationURL()
794: except AttributeError:
795: u = REQUEST['URL1']
796:
797: u = "%s/%s" % (u, urllib.quote(id))
798: REQUEST.RESPONSE.redirect(u+'/manage_main')
799: return ''
800:
801:
1.14 casties 802:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>