1: from OFS.Folder import Folder
2: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
3: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
4: from App.ImageFile import ImageFile
5: from AccessControl import ClassSecurityInfo
6: from AccessControl import getSecurityManager
7: from Globals import package_home
8:
9: import xml.etree.ElementTree as ET
10:
11: import os
12: import sys
13: import urllib
14: import logging
15: import math
16: import urlparse
17: import re
18: import string
19:
20: from SrvTxtUtils import getInt, getText, getHttpData, refreshingImageFileIndexHtml
21:
22: def serializeNode(node, encoding="utf-8"):
23: """returns a string containing node as XML"""
24: s = ET.tostring(node)
25:
26: # 4Suite:
27: # stream = cStringIO.StringIO()
28: # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
29: # s = stream.getvalue()
30: # stream.close()
31: return s
32:
33: def browserCheck(self):
34: """check the browsers request to find out the browser type"""
35: bt = {}
36: ua = self.REQUEST.get_header("HTTP_USER_AGENT")
37: bt['ua'] = ua
38: bt['isIE'] = False
39: bt['isN4'] = False
40: bt['versFirefox']=""
41: bt['versIE']=""
42: bt['versSafariChrome']=""
43: bt['versOpera']=""
44:
45: if string.find(ua, 'MSIE') > -1:
46: bt['isIE'] = True
47: else:
48: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
49: # Safari oder Chrome identification
50: try:
51: nav = ua[string.find(ua, '('):]
52: nav1=ua[string.find(ua,')'):]
53: nav2=nav1[string.find(nav1,'('):]
54: nav3=nav2[string.find(nav2,')'):]
55: ie = string.split(nav, "; ")[1]
56: ie1 =string.split(nav1, " ")[2]
57: ie2 =string.split(nav3, " ")[1]
58: ie3 =string.split(nav3, " ")[2]
59: if string.find(ie3, "Safari") >-1:
60: bt['versSafariChrome']=string.split(ie2, "/")[1]
61: except: pass
62: # IE identification
63: try:
64: nav = ua[string.find(ua, '('):]
65: ie = string.split(nav, "; ")[1]
66: if string.find(ie, "MSIE") > -1:
67: bt['versIE'] = string.split(ie, " ")[1]
68: except:pass
69: # Firefox identification
70: try:
71: nav = ua[string.find(ua, '('):]
72: nav1=ua[string.find(ua,')'):]
73: if string.find(ie1, "Firefox") >-1:
74: nav5= string.split(ie1, "/")[1]
75: logging.debug("FIREFOX: %s"%(nav5))
76: bt['versFirefox']=nav5[0:3]
77: except:pass
78: #Opera identification
79: try:
80: if string.find(ua,"Opera") >-1:
81: nav = ua[string.find(ua, '('):]
82: nav1=nav[string.find(nav,')'):]
83: bt['versOpera']=string.split(nav1,"/")[2]
84: except:pass
85:
86: bt['isMac'] = string.find(ua, 'Macintosh') > -1
87: bt['isWin'] = string.find(ua, 'Windows') > -1
88: bt['isIEWin'] = bt['isIE'] and bt['isWin']
89: bt['isIEMac'] = bt['isIE'] and bt['isMac']
90: bt['staticHTML'] = False
91:
92: return bt
93:
94: def getParentPath(path, cnt=1):
95: """returns pathname shortened by cnt"""
96: # make sure path doesn't end with /
97: path = path.rstrip('/')
98: # split by /, shorten, and reassemble
99: return '/'.join(path.split('/')[0:-cnt])
100:
101: ##
102: ## documentViewer class
103: ##
104: class documentViewer(Folder):
105: """document viewer"""
106: meta_type="Document viewer"
107:
108: security=ClassSecurityInfo()
109: manage_options=Folder.manage_options+(
110: {'label':'main config','action':'changeDocumentViewerForm'},
111: )
112:
113: metadataService = None
114: """MetaDataFolder instance"""
115:
116: # templates and forms
117: viewer_text = PageTemplateFile('zpt/viewer_text', globals())
118: viewer_images = PageTemplateFile('zpt/viewer_images', globals())
119: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
120: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
121: toc_text = PageTemplateFile('zpt/toc_text', globals())
122: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
123: toc_none = PageTemplateFile('zpt/toc_none', globals())
124: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
125: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
126: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
127: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
128: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
129: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
130: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
131: head_main = PageTemplateFile('zpt/head_main', globals())
132: info_xml = PageTemplateFile('zpt/info_xml', globals())
133: docuviewer_css = ImageFile('css/docuviewer.css',globals())
134: # make ImageFile better for development
135: docuviewer_css.index_html = refreshingImageFileIndexHtml
136:
137:
138: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
139:
140:
141: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
142: """init document viewer"""
143: self.id=id
144: self.title=title
145: self.thumbcols = thumbcols
146: self.thumbrows = thumbrows
147: # authgroups is list of authorized groups (delimited by ,)
148: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
149: # create template folder so we can always use template.something
150:
151: templateFolder = Folder('template')
152: #self['template'] = templateFolder # Zope-2.12 style
153: self._setObject('template',templateFolder) # old style
154: try:
155: import MpdlXmlTextServer
156: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
157: #templateFolder['fulltextclient'] = xmlRpcClient
158: templateFolder._setObject('fulltextclient',textServer)
159: except Exception, e:
160: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
161:
162: try:
163: from Products.zogiLib.zogiLib import zogiLib
164: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
165: #templateFolder['zogilib'] = zogilib
166: templateFolder._setObject('zogilib',zogilib)
167: except Exception, e:
168: logging.error("Unable to create zogiLib for zogilib: "+str(e))
169:
170: try:
171: # assume MetaDataFolder instance is called metadata
172: self.metadataService = getattr(self, 'metadata')
173: except Exception, e:
174: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
175:
176: if digilibBaseUrl is not None:
177: self.digilibBaseUrl = digilibBaseUrl
178:
179:
180: # proxy text server methods to fulltextclient
181: def getTextPage(self, **args):
182: """get page"""
183: return self.template.fulltextclient.getTextPage(**args)
184:
185: def getOrigPages(self, **args):
186: """get page"""
187: return self.template.fulltextclient.getOrigPages(**args)
188:
189: def getOrigPagesNorm(self, **args):
190: """get page"""
191: return self.template.fulltextclient.getOrigPagesNorm(**args)
192:
193: def getQuery(self, **args):
194: """get query in search"""
195: return self.template.fulltextclient.getQuery(**args)
196:
197: def getSearch(self, **args):
198: """get search"""
199: return self.template.fulltextclient.getSearch(**args)
200:
201: def getGisPlaces(self, **args):
202: """get gis places"""
203: return self.template.fulltextclient.getGisPlaces(**args)
204:
205: def getAllGisPlaces(self, **args):
206: """get all gis places """
207: return self.template.fulltextclient.getAllGisPlaces(**args)
208:
209: def getWordInfo(self, **args):
210: """get translate"""
211: return self.template.fulltextclient.getWordInfo(**args)
212:
213: def getLemma(self, **args):
214: """get lemma"""
215: return self.template.fulltextclient.getLemma(**args)
216:
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:
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)
232:
233:
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: '''
243: logging.debug("HHHHHHHHHHHHHH:load the rss")
244: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
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)
254: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
255: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
256: ''' ZDES '''
257: pt = getattr(self.template, 'thumbs_main_rss')
258:
259: if viewMode=="auto": # automodus gewaehlt
260: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
261: viewMode="text"
262: else:
263: viewMode="images"
264:
265: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
266:
267:
268: security.declareProtected('View','index_html')
269: def index_html(self,url,mode="texttool",viewMode="auto",viewType=None,tocMode="thumbs",start=1,pn=1):
270: """
271: view page
272: @param url: url which contains display information
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'
276: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
277: """
278:
279: logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewType=%s start=%s pn=%s"%(mode,url,viewMode,viewType,start,pn))
280:
281: if not hasattr(self, 'template'):
282: # this won't work
283: logging.error("template folder missing!")
284: return "ERROR: template folder missing!"
285:
286: if not getattr(self, 'digilibBaseUrl', None):
287: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
288:
289: docinfo = self.getDocinfo(mode=mode,url=url)
290:
291: if tocMode != "thumbs":
292: # get table of contents
293: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
294:
295: # auto viewMode: text if there is a text else images
296: if viewMode=="auto":
297: if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):
298: viewMode = "text"
299: viewType = "dict"
300: else:
301: viewMode = "images"
302:
303: elif viewMode == "text_dict":
304: # legacy fix
305: viewMode = "text"
306: viewType = "dict"
307:
308: # stringify viewType
309: if isinstance(viewType, list):
310: logging.debug("index_html: viewType is list:%s"%viewType)
311: viewType = ','.join([t for t in viewType if t])
312:
313: pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode)
314:
315: # get template /template/viewer_$viewMode
316: pt = getattr(self.template, 'viewer_%s'%viewMode, None)
317: if pt is None:
318: logging.error("No template for viewMode=%s!"%viewMode)
319: # TODO: error page?
320: return "No template for viewMode=%s!"%viewMode
321:
322: # and execute with parameters
323: return pt(docinfo=docinfo, pageinfo=pageinfo)
324:
325: def generateMarks(self,mk):
326: ret=""
327: if mk is None:
328: return ""
329: if not isinstance(mk, list):
330: mk=[mk]
331: for m in mk:
332: ret+="mk=%s"%m
333: return ret
334:
335:
336: def getBrowser(self):
337: """getBrowser the version of browser """
338: bt = browserCheck(self)
339: logging.debug("BROWSER VERSION: %s"%(bt))
340: return bt
341:
342: def findDigilibUrl(self):
343: """try to get the digilib URL from zogilib"""
344: url = self.template.zogilib.getDLBaseUrl()
345: return url
346:
347: def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None):
348: """returns URL to digilib Scaler with params"""
349: url = None
350: if docinfo is not None:
351: url = docinfo.get('imageURL', None)
352:
353: if url is None:
354: url = "%s/servlet/Scaler?"%self.digilibBaseUrl
355: if fn is None and docinfo is not None:
356: fn = docinfo.get('imagePath','')
357:
358: url += "fn=%s"%fn
359:
360: if pn:
361: url += "&pn=%s"%pn
362:
363: url += "&dw=%s&dh=%s"%(dw,dh)
364: return url
365:
366: def getDocumentViewerURL(self):
367: """returns the URL of this instance"""
368: return self.absolute_url()
369:
370: def getStyle(self, idx, selected, style=""):
371: """returns a string with the given style and append 'sel' if idx == selected."""
372: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
373: if idx == selected:
374: return style + 'sel'
375: else:
376: return style
377:
378: def getParams(self, param=None, val=None, params=None, duplicates=None):
379: """returns dict with URL parameters.
380:
381: Takes URL parameters and additionally param=val or dict params.
382: Deletes key if value is None."""
383: # copy existing request params
384: newParams=self.REQUEST.form.copy()
385: # change single param
386: if param is not None:
387: if val is None:
388: if newParams.has_key(param):
389: del newParams[param]
390: else:
391: newParams[param] = str(val)
392:
393: # change more params
394: if params is not None:
395: for (k, v) in params.items():
396: if v is None:
397: # val=None removes param
398: if newParams.has_key(k):
399: del newParams[k]
400:
401: else:
402: newParams[k] = v
403:
404: if duplicates:
405: # eliminate lists (coming from duplicate keys)
406: for (k,v) in newParams.items():
407: if isinstance(v, list):
408: if duplicates == 'comma':
409: # make comma-separated list of non-empty entries
410: newParams[k] = ','.join([t for t in v if t])
411: elif duplicates == 'first':
412: # take first non-empty entry
413: newParams[k] = [t for t in v if t][0]
414:
415: return newParams
416:
417: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'):
418: """returns URL to documentviewer with parameter param set to val or from dict params"""
419: urlParams = self.getParams(param=param, val=val, params=params, duplicates=duplicates)
420: # quote values and assemble into query string (not escaping '/')
421: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(unicode(v),'/')) for (k, v) in urlParams.items()])
422: if baseUrl is None:
423: baseUrl = self.getDocumentViewerURL()
424:
425: url = "%s?%s"%(baseUrl, ps)
426: return url
427:
428: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'):
429: """link to documentviewer with parameter param set to val"""
430: return self.getLink(param=param, val=val, params=params, baseUrl=baseUrl, paramSep='&', duplicates=duplicates)
431:
432:
433: def getInfo_xml(self,url,mode):
434: """returns info about the document as XML"""
435: if not self.digilibBaseUrl:
436: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
437:
438: docinfo = self.getDocinfo(mode=mode,url=url)
439: pt = getattr(self.template, 'info_xml')
440: return pt(docinfo=docinfo)
441:
442: def isAccessible(self, docinfo):
443: """returns if access to the resource is granted"""
444: access = docinfo.get('accessType', None)
445: logging.debug("documentViewer (accessOK) access type %s"%access)
446: if access == 'free':
447: logging.debug("documentViewer (accessOK) access is free")
448: return True
449:
450: elif access is None or access in self.authgroups:
451: # only local access -- only logged in users
452: user = getSecurityManager().getUser()
453: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
454: if user is not None:
455: #print "user: ", user
456: return (user.getUserName() != "Anonymous User")
457: else:
458: return False
459:
460: logging.error("documentViewer (accessOK) unknown access type %s"%access)
461: return False
462:
463:
464:
465: def getDocinfo(self, mode, url):
466: """returns docinfo depending on mode"""
467: logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
468: # look for cached docinfo in session
469: if self.REQUEST.SESSION.has_key('docinfo'):
470: docinfo = self.REQUEST.SESSION['docinfo']
471: # check if its still current
472: if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:
473: logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())
474: return docinfo
475:
476: # new docinfo
477: docinfo = {'mode': mode, 'url': url}
478: # add self url
479: docinfo['viewerUrl'] = self.getDocumentViewerURL()
480: docinfo['digilibBaseUrl'] = self.digilibBaseUrl
481: # get index.meta DOM
482: docUrl = None
483: metaDom = None
484: if mode=="texttool":
485: # url points to document dir or index.meta
486: metaDom = self.metadataService.getDomFromPathOrUrl(url)
487: docUrl = url.replace('/index.meta', '')
488: if metaDom is None:
489: raise IOError("Unable to find index.meta for mode=texttool!")
490:
491: elif mode=="imagepath":
492: # url points to folder with images, index.meta optional
493: # asssume index.meta in parent dir
494: docUrl = getParentPath(url)
495: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
496:
497: elif mode=="filepath":
498: # url points to image file, index.meta optional
499: # asssume index.meta is two path segments up
500: docUrl = getParentPath(url, 2)
501: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
502:
503: else:
504: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
505: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
506:
507: docinfo['documentUrl'] = docUrl
508: # process index.meta contents
509: if metaDom is not None and metaDom.tag == 'resource':
510: # document directory name and path
511: resource = self.metadataService.getResourceData(dom=metaDom)
512: if resource:
513: docinfo = self.getDocinfoFromResource(docinfo, resource)
514:
515: # texttool info
516: texttool = self.metadataService.getTexttoolData(dom=metaDom)
517: if texttool:
518: docinfo = self.getDocinfoFromTexttool(docinfo, texttool)
519:
520: # bib info
521: bib = self.metadataService.getBibData(dom=metaDom)
522: if bib:
523: docinfo = self.getDocinfoFromBib(docinfo, bib)
524: else:
525: # no bib - try info.xml
526: docinfo = self.getDocinfoFromPresentationInfoXml(docinfo)
527:
528: # auth info
529: access = self.metadataService.getAccessData(dom=metaDom)
530: if access:
531: docinfo = self.getDocinfoFromAccess(docinfo, access)
532:
533: # attribution info
534: attribution = self.metadataService.getAttributionData(dom=metaDom)
535: if attribution:
536: logging.debug("getDocinfo: attribution=%s"%repr(attribution))
537: docinfo['attribution'] = attribution
538: #docinfo = self.getDocinfoFromAccess(docinfo, access)
539:
540: # copyright info
541: copyright = self.metadataService.getCopyrightData(dom=metaDom)
542: if copyright:
543: logging.debug("getDocinfo: copyright=%s"%repr(copyright))
544: docinfo['copyright'] = copyright
545: #docinfo = self.getDocinfoFromAccess(docinfo, access)
546:
547: # image path
548: if mode != 'texttool':
549: # override image path from texttool with url
550: docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1)
551:
552: # number of images from digilib
553: if docinfo.get('imagePath', None):
554: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath']
555: docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath'])
556:
557: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
558: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
559: # store in session
560: self.REQUEST.SESSION['docinfo'] = docinfo
561: return docinfo
562:
563: def getDocinfoFromResource(self, docinfo, resource):
564: """reads contents of resource element into docinfo"""
565: docName = resource.get('name', None)
566: docinfo['documentName'] = docName
567: docPath = resource.get('archive-path', None)
568: if docPath:
569: # clean up document path
570: if docPath[0] != '/':
571: docPath = '/' + docPath
572:
573: if docName and (not docPath.endswith(docName)):
574: docPath += "/" + docName
575:
576: else:
577: # use docUrl as docPath
578: docUrl = docinfo['documentURL']
579: if not docUrl.startswith('http:'):
580: docPath = docUrl
581: if docPath:
582: # fix URLs starting with /mpiwg/online
583: docPath = docPath.replace('/mpiwg/online', '', 1)
584:
585: docinfo['documentPath'] = docPath
586: return docinfo
587:
588: def getDocinfoFromTexttool(self, docinfo, texttool):
589: """reads contents of texttool element into docinfo"""
590: # image dir
591: imageDir = texttool.get('image', None)
592: docPath = docinfo.get('documentPath', None)
593: if imageDir and docPath:
594: #print "image: ", imageDir, " archivepath: ", archivePath
595: imageDir = os.path.join(docPath, imageDir)
596: imageDir = imageDir.replace('/mpiwg/online', '', 1)
597: docinfo['imagePath'] = imageDir
598:
599: # old style text URL
600: textUrl = texttool.get('text', None)
601: if textUrl and docPath:
602: if urlparse.urlparse(textUrl)[0] == "": #keine url
603: textUrl = os.path.join(docPath, textUrl)
604:
605: docinfo['textURL'] = textUrl
606:
607: # new style text-url-path
608: textUrl = texttool.get('text-url-path', None)
609: if textUrl:
610: docinfo['textURLPath'] = textUrl
611:
612: # page flow
613: docinfo['pageFlow'] = texttool.get('page-flow', 'ltr')
614:
615: # odd pages are left
616: docinfo['oddPage'] = texttool.get('odd-scan-position', 'left')
617:
618: # number of title page (0: not defined)
619: docinfo['titlePage'] = texttool.get('title-scan-no', 0)
620:
621: # old presentation stuff
622: presentation = texttool.get('presentation', None)
623: if presentation and docPath:
624: if presentation.startswith('http:'):
625: docinfo['presentationUrl'] = presentation
626: else:
627: docinfo['presentationUrl'] = os.path.join(docPath, presentation)
628:
629:
630: return docinfo
631:
632: def getDocinfoFromBib(self, docinfo, bib):
633: """reads contents of bib element into docinfo"""
634: logging.debug("getDocinfoFromBib bib=%s"%repr(bib))
635: # put all raw bib fields in dict "bib"
636: docinfo['bib'] = bib
637: bibtype = bib.get('@type', None)
638: docinfo['bibType'] = bibtype
639: # also store DC metadata for convenience
640: dc = self.metadataService.getDCMappedData(bib)
641: docinfo['creator'] = dc.get('creator',None)
642: docinfo['title'] = dc.get('title',None)
643: docinfo['date'] = dc.get('date',None)
644: return docinfo
645:
646: def getDocinfoFromAccess(self, docinfo, acc):
647: """reads contents of access element into docinfo"""
648: #TODO: also read resource type
649: logging.debug("getDocinfoFromAccess acc=%s"%repr(acc))
650: try:
651: acctype = acc['@attr']['type']
652: if acctype:
653: access=acctype
654: if access in ['group', 'institution']:
655: access = acc['name'].lower()
656:
657: docinfo['accessType'] = access
658:
659: except:
660: pass
661:
662: return docinfo
663:
664: def getDocinfoFromDigilib(self, docinfo, path):
665: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
666: # fetch data
667: txt = getHttpData(infoUrl)
668: if not txt:
669: logging.error("Unable to get dir-info from %s"%(infoUrl))
670: return docinfo
671:
672: dom = ET.fromstring(txt)
673: size = getText(dom.find("size"))
674: logging.debug("getDocinfoFromDigilib: size=%s"%size)
675: if size:
676: docinfo['numPages'] = int(size)
677: else:
678: docinfo['numPages'] = 0
679:
680: # TODO: produce and keep list of image names and numbers
681: return docinfo
682:
683:
684: def getDocinfoFromPresentationInfoXml(self,docinfo):
685: """gets DC-like bibliographical information from the presentation entry in texttools"""
686: url = docinfo.get('presentationUrl', None)
687: if not url:
688: logging.error("getDocinfoFromPresentation: no URL!")
689: return docinfo
690:
691: dom = None
692: metaUrl = None
693: if url.startswith("http://"):
694: # real URL
695: metaUrl = url
696: else:
697: # online path
698:
699: server=self.digilibBaseUrl+"/servlet/Texter?fn="
700: metaUrl=server+url
701:
702: txt=getHttpData(metaUrl)
703: if txt is None:
704: logging.error("Unable to read info.xml from %s"%(url))
705: return docinfo
706:
707: dom = ET.fromstring(txt)
708: docinfo['creator']=getText(dom.find(".//author"))
709: docinfo['title']=getText(dom.find(".//title"))
710: docinfo['date']=getText(dom.find(".//date"))
711: return docinfo
712:
713:
714: def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None):
715: """returns pageinfo with the given parameters"""
716: logging.debug("getPageInfo(current=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewType=%s, tocMode=%s)"%(current,start,rows,cols,viewMode,viewType,tocMode))
717: pageinfo = {}
718: pageinfo['viewMode'] = viewMode
719: pageinfo['viewType'] = viewType
720: pageinfo['tocMode'] = tocMode
721:
722: current = getInt(current)
723: pageinfo['current'] = current
724: pageinfo['pn'] = current
725: rows = int(rows or self.thumbrows)
726: pageinfo['rows'] = rows
727: cols = int(cols or self.thumbcols)
728: pageinfo['cols'] = cols
729: grpsize = cols * rows
730: pageinfo['groupsize'] = grpsize
731: # is start is empty use one around current
732: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
733: # int(current / grpsize) * grpsize +1))
734: pageinfo['start'] = start
735:
736: np = int(docinfo.get('numPages', 0))
737: if np == 0:
738: # numPages unknown - maybe we can get it from text page
739: if docinfo.get('textURLPath', None):
740: # cache text page as well
741: pageinfo['textPage'] = self.getTextPage(mode=viewType, pn=current, docinfo=docinfo, pageinfo=pageinfo)
742: np = int(docinfo.get('numPages', 0))
743:
744: pageinfo['numgroups'] = int(np / grpsize)
745: if np % grpsize > 0:
746: pageinfo['numgroups'] += 1
747:
748: pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl'
749: oddScanLeft = docinfo.get('oddPage', 'left') != 'right'
750: # add zeroth page for two columns
751: pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft))
752: pageinfo['pageZero'] = pageZero
753: pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np)
754:
755: # TODO: do we need this here?
756: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
757: pageinfo['query'] = self.REQUEST.get('query','')
758: pageinfo['queryType'] = self.REQUEST.get('queryType','')
759: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
760: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
761: pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30))
762: pageinfo['queryPageSize'] = getInt(self.REQUEST.get('queryPageSize', 10))
763: pageinfo['tocPN'] = getInt(self.REQUEST.get('tocPN', '1'))
764: pageinfo['searchPN'] = getInt(self.REQUEST.get('searchPN','1'))
765:
766: # limit tocPN
767: if 'tocSize_%s'%tocMode in docinfo:
768: tocSize = docinfo['tocSize_%s'%tocMode]
769: tocPageSize = pageinfo['tocPageSize']
770: # cached toc
771: if tocSize%tocPageSize>0:
772: tocPages=tocSize/tocPageSize+1
773: else:
774: tocPages=tocSize/tocPageSize
775:
776: pageinfo['tocPN'] = min(tocPages,pageinfo['tocPN'])
777:
778: return pageinfo
779:
780:
781: def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0):
782: """returns dict with array of page informations for one screenfull of thumbnails"""
783: batch = {}
784: grpsize = rows * cols
785: if maxIdx == 0:
786: maxIdx = start + grpsize
787:
788: nb = int(math.ceil(maxIdx / float(grpsize)))
789: # list of all batch start and end points
790: batches = []
791: if pageZero:
792: ofs = 0
793: else:
794: ofs = 1
795:
796: for i in range(nb):
797: s = i * grpsize + ofs
798: e = min((i + 1) * grpsize + ofs - 1, maxIdx)
799: batches.append({'start':s, 'end':e})
800:
801: batch['batches'] = batches
802:
803: pages = []
804: if pageZero and start == 1:
805: # correct beginning
806: idx = 0
807: else:
808: idx = start
809:
810: for r in range(rows):
811: row = []
812: for c in range(cols):
813: if idx < minIdx or idx > maxIdx:
814: page = {'idx':None}
815: else:
816: page = {'idx':idx}
817:
818: idx += 1
819: if pageFlowLtr:
820: row.append(page)
821: else:
822: row.insert(0, page)
823:
824: pages.append(row)
825:
826: if start > 1:
827: batch['prevStart'] = max(start - grpsize, 1)
828: else:
829: batch['prevStart'] = None
830:
831: if start + grpsize < maxIdx:
832: batch['nextStart'] = start + grpsize
833: else:
834: batch['nextStart'] = None
835:
836: batch['pages'] = pages
837: return batch
838:
839: def getBatch(self, start=1, size=10, end=0, data=None, fullData=True):
840: """returns dict with information for one screenfull of data."""
841: batch = {}
842: if end == 0:
843: end = start + size
844:
845: nb = int(math.ceil(end / float(size)))
846: # list of all batch start and end points
847: batches = []
848: for i in range(nb):
849: s = i * size + 1
850: e = min((i + 1) * size, end)
851: batches.append({'start':s, 'end':e})
852:
853: batch['batches'] = batches
854: # list of elements in this batch
855: this = []
856: j = 0
857: for i in range(start, min(start+size, end)):
858: if data:
859: if fullData:
860: d = data[i]
861: else:
862: d = data[j]
863: j += 1
864:
865: else:
866: d = i+1
867:
868: this.append(d)
869:
870: batch['this'] = this
871: if start > 1:
872: batch['prevStart'] = max(start - size, 1)
873: else:
874: batch['prevStart'] = None
875:
876: if start + size < end:
877: batch['nextStart'] = start + size
878: else:
879: batch['nextStart'] = None
880:
881: return batch
882:
883:
884: security.declareProtected('View management screens','changeDocumentViewerForm')
885: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
886:
887: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
888: """init document viewer"""
889: self.title=title
890: self.digilibBaseUrl = digilibBaseUrl
891: self.thumbrows = thumbrows
892: self.thumbcols = thumbcols
893: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
894: try:
895: # assume MetaDataFolder instance is called metadata
896: self.metadataService = getattr(self, 'metadata')
897: except Exception, e:
898: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
899:
900: if RESPONSE is not None:
901: RESPONSE.redirect('manage_main')
902:
903: def manage_AddDocumentViewerForm(self):
904: """add the viewer form"""
905: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
906: return pt()
907:
908: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
909: """add the viewer"""
910: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
911: self._setObject(id,newObj)
912:
913: if RESPONSE is not None:
914: RESPONSE.redirect('manage_main')
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/cvs/cvsweb/icons/back.gif){kind=icon}
Return to documentViewer.py CVS log ![[TXT]](/cvs/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvs/cvsweb/icons/dir.gif){kind=icon}
Up to [Repository] / documentViewer