1: from OFS.Folder import Folder
2: from OFS.Image import File
3: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
4: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
5: from AccessControl import ClassSecurityInfo
6: from AccessControl import getSecurityManager
7: from Globals import package_home
8:
9: #from Ft.Xml import EMPTY_NAMESPACE, Parse
10: #import Ft.Xml.Domlette
11:
12: import xml.etree.ElementTree as ET
13:
14: import os.path
15: import sys
16: import urllib
17: import logging
18: import math
19: import urlparse
20: import re
21: import string
22:
23: from SrvTxtUtils import getInt, getText, getHttpData
24:
25: def logger(txt,method,txt2):
26: """logging"""
27: logging.info(txt+ txt2)
28:
29:
30: def serializeNode(node, encoding="utf-8"):
31: """returns a string containing node as XML"""
32: s = ET.tostring(node)
33:
34: # 4Suite:
35: # stream = cStringIO.StringIO()
36: # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
37: # s = stream.getvalue()
38: # stream.close()
39: return s
40:
41: def browserCheck(self):
42: """check the browsers request to find out the browser type"""
43: bt = {}
44: ua = self.REQUEST.get_header("HTTP_USER_AGENT")
45: bt['ua'] = ua
46: bt['isIE'] = False
47: bt['isN4'] = False
48: bt['versFirefox']=""
49: bt['versIE']=""
50: bt['versSafariChrome']=""
51: bt['versOpera']=""
52:
53: if string.find(ua, 'MSIE') > -1:
54: bt['isIE'] = True
55: else:
56: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
57: # Safari oder Chrome identification
58: try:
59: nav = ua[string.find(ua, '('):]
60: nav1=ua[string.find(ua,')'):]
61: nav2=nav1[string.find(nav1,'('):]
62: nav3=nav2[string.find(nav2,')'):]
63: ie = string.split(nav, "; ")[1]
64: ie1 =string.split(nav1, " ")[2]
65: ie2 =string.split(nav3, " ")[1]
66: ie3 =string.split(nav3, " ")[2]
67: if string.find(ie3, "Safari") >-1:
68: bt['versSafariChrome']=string.split(ie2, "/")[1]
69: except: pass
70: # IE identification
71: try:
72: nav = ua[string.find(ua, '('):]
73: ie = string.split(nav, "; ")[1]
74: if string.find(ie, "MSIE") > -1:
75: bt['versIE'] = string.split(ie, " ")[1]
76: except:pass
77: # Firefox identification
78: try:
79: nav = ua[string.find(ua, '('):]
80: nav1=ua[string.find(ua,')'):]
81: if string.find(ie1, "Firefox") >-1:
82: nav5= string.split(ie1, "/")[1]
83: logging.debug("FIREFOX: %s"%(nav5))
84: bt['versFirefox']=nav5[0:3]
85: except:pass
86: #Opera identification
87: try:
88: if string.find(ua,"Opera") >-1:
89: nav = ua[string.find(ua, '('):]
90: nav1=nav[string.find(nav,')'):]
91: bt['versOpera']=string.split(nav1,"/")[2]
92: except:pass
93:
94: bt['isMac'] = string.find(ua, 'Macintosh') > -1
95: bt['isWin'] = string.find(ua, 'Windows') > -1
96: bt['isIEWin'] = bt['isIE'] and bt['isWin']
97: bt['isIEMac'] = bt['isIE'] and bt['isMac']
98: bt['staticHTML'] = False
99:
100: return bt
101:
102: def getParentPath(path, cnt=1):
103: """returns pathname shortened by cnt"""
104: # make sure path doesn't end with /
105: path = path.rstrip('/')
106: # split by /, shorten, and reassemble
107: return '/'.join(path.split('/')[0:-cnt])
108:
109:
110: ##
111: ## documentViewer class
112: ##
113: class documentViewer(Folder):
114: """document viewer"""
115: meta_type="Document viewer"
116:
117: security=ClassSecurityInfo()
118: manage_options=Folder.manage_options+(
119: {'label':'main config','action':'changeDocumentViewerForm'},
120: )
121:
122: metadataService = None
123: """MetaDataFolder instance"""
124:
125: # templates and forms
126: viewer_text = PageTemplateFile('zpt/viewer_text', globals())
127: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
128: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
129: toc_text = PageTemplateFile('zpt/toc_text', globals())
130: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
131: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
132: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
133: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
134: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
135: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
136: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
137: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
138: head_main = PageTemplateFile('zpt/head_main', globals())
139: info_xml = PageTemplateFile('zpt/info_xml', globals())
140: # TODO: can this be nicer?
141: docuviewer_css = File('docuviewer_css','',open(os.path.join(package_home(globals()),'css/docuviewer.css')), content_type='text/css')
142:
143:
144: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
145:
146:
147: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
148: """init document viewer"""
149: self.id=id
150: self.title=title
151: self.thumbcols = thumbcols
152: self.thumbrows = thumbrows
153: # authgroups is list of authorized groups (delimited by ,)
154: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
155: # create template folder so we can always use template.something
156:
157: templateFolder = Folder('template')
158: #self['template'] = templateFolder # Zope-2.12 style
159: self._setObject('template',templateFolder) # old style
160: try:
161: import MpdlXmlTextServer
162: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
163: #templateFolder['fulltextclient'] = xmlRpcClient
164: templateFolder._setObject('fulltextclient',textServer)
165: except Exception, e:
166: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
167:
168: try:
169: from Products.zogiLib.zogiLib import zogiLib
170: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
171: #templateFolder['zogilib'] = zogilib
172: templateFolder._setObject('zogilib',zogilib)
173: except Exception, e:
174: logging.error("Unable to create zogiLib for zogilib: "+str(e))
175:
176: try:
177: # assume MetaDataFolder instance is called metadata
178: self.metadataService = getattr(self, 'metadata')
179: except Exception, e:
180: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
181:
182: if digilibBaseUrl is not None:
183: self.digilibBaseUrl = digilibBaseUrl
184:
185:
186: # proxy text server methods to fulltextclient
187: def getTextPage(self, **args):
188: """get page"""
189: return self.template.fulltextclient.getTextPage(**args)
190:
191: def getOrigPages(self, **args):
192: """get page"""
193: return self.template.fulltextclient.getOrigPages(**args)
194:
195: def getOrigPagesNorm(self, **args):
196: """get page"""
197: return self.template.fulltextclient.getOrigPagesNorm(**args)
198:
199: def getQuery(self, **args):
200: """get query in search"""
201: return self.template.fulltextclient.getQuery(**args)
202:
203: def getSearch(self, **args):
204: """get search"""
205: return self.template.fulltextclient.getSearch(**args)
206:
207: def getGisPlaces(self, **args):
208: """get gis places"""
209: return self.template.fulltextclient.getGisPlaces(**args)
210:
211: def getAllGisPlaces(self, **args):
212: """get all gis places """
213: return self.template.fulltextclient.getAllGisPlaces(**args)
214:
215: def getWordInfo(self, **args):
216: """get translate"""
217: return self.template.fulltextclient.getWordInfo(**args)
218:
219: def getLemma(self, **args):
220: """get lemma"""
221: return self.template.fulltextclient.getLemma(**args)
222:
223: def getLemmaQuery(self, **args):
224: """get query"""
225: return self.template.fulltextclient.getLemmaQuery(**args)
226:
227: def getLex(self, **args):
228: """get lex"""
229: return self.template.fulltextclient.getLex(**args)
230:
231: def getToc(self, **args):
232: """get toc"""
233: return self.template.fulltextclient.getToc(**args)
234:
235: def getTocPage(self, **args):
236: """get tocpage"""
237: return self.template.fulltextclient.getTocPage(**args)
238:
239:
240: security.declareProtected('View','thumbs_rss')
241: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
242: '''
243: view it
244: @param mode: defines how to access the document behind url
245: @param url: url which contains display information
246: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
247:
248: '''
249: logging.debug("HHHHHHHHHHHHHH:load the rss")
250: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
251:
252: if not hasattr(self, 'template'):
253: # create template folder if it doesn't exist
254: self.manage_addFolder('template')
255:
256: if not self.digilibBaseUrl:
257: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
258:
259: docinfo = self.getDocinfo(mode=mode,url=url)
260: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
261: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
262: ''' ZDES '''
263: pt = getattr(self.template, 'thumbs_main_rss')
264:
265: if viewMode=="auto": # automodus gewaehlt
266: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
267: viewMode="text"
268: else:
269: viewMode="images"
270:
271: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
272:
273:
274: security.declareProtected('View','index_html')
275: def index_html(self,url,mode="texttool",viewMode="auto",viewType=None,tocMode="thumbs",start=1,pn=1):
276: """
277: view page
278: @param url: url which contains display information
279: @param mode: defines how to access the document behind url
280: @param viewMode: 'images': display images, 'text': display text, default is 'auto'
281: @param viewType: sub-type of viewMode, e.g. 'dict' for viewMode='text'
282: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
283: """
284:
285: logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewType=%s start=%s pn=%s"%(mode,url,viewMode,viewType,start,pn))
286:
287: if not hasattr(self, 'template'):
288: # this won't work
289: logging.error("template folder missing!")
290: return "ERROR: template folder missing!"
291:
292: if not getattr(self, 'digilibBaseUrl', None):
293: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
294:
295: docinfo = self.getDocinfo(mode=mode,url=url)
296:
297: if tocMode != "thumbs":
298: # get table of contents
299: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
300:
301: # auto viewMode: text if there is a text else images
302: if viewMode=="auto":
303: if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):
304: viewMode = "text"
305: viewType = "dict"
306: else:
307: viewMode = "images"
308:
309: elif viewMode == "text_dict":
310: # legacy fix
311: viewMode = "text"
312: viewType = "dict"
313:
314: # stringify viewType
315: if isinstance(viewType, list):
316: logging.debug("index_html: viewType is list:%s"%viewType)
317: viewType = ','.join([t for t in viewType if t])
318:
319: pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode)
320:
321: # get template /template/viewer_$viewMode
322: pt = getattr(self.template, 'viewer_%s'%viewMode, None)
323: if pt is None:
324: logging.error("No template for viewMode=%s!"%viewMode)
325: # TODO: error page?
326: return "No template for viewMode=%s!"%viewMode
327:
328: # and execute with parameters
329: return pt(docinfo=docinfo, pageinfo=pageinfo)
330:
331: def generateMarks(self,mk):
332: ret=""
333: if mk is None:
334: return ""
335: if not isinstance(mk, list):
336: mk=[mk]
337: for m in mk:
338: ret+="mk=%s"%m
339: return ret
340:
341:
342: def getBrowser(self):
343: """getBrowser the version of browser """
344: bt = browserCheck(self)
345: logging.debug("BROWSER VERSION: %s"%(bt))
346: return bt
347:
348: def findDigilibUrl(self):
349: """try to get the digilib URL from zogilib"""
350: url = self.template.zogilib.getDLBaseUrl()
351: return url
352:
353: def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None):
354: """returns URL to digilib Scaler with params"""
355: url = None
356: if docinfo is not None:
357: url = docinfo.get('imageURL', None)
358:
359: if url is None:
360: url = "%s/servlet/Scaler?"%self.digilibBaseUrl
361: if fn is None and docinfo is not None:
362: fn = docinfo.get('imagePath','')
363:
364: url += "fn=%s"%fn
365:
366: if pn:
367: url += "&pn=%s"%pn
368:
369: url += "&dw=%s&dh=%s"%(dw,dh)
370: return url
371:
372: def getDocumentViewerURL(self):
373: """returns the URL of this instance"""
374: return self.absolute_url()
375:
376: def getStyle(self, idx, selected, style=""):
377: """returns a string with the given style and append 'sel' if idx == selected."""
378: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
379: if idx == selected:
380: return style + 'sel'
381: else:
382: return style
383:
384: def getParams(self, param=None, val=None, params=None, duplicates=None):
385: """returns dict with URL parameters.
386:
387: Takes URL parameters and additionally param=val or dict params.
388: Deletes key if value is None."""
389: # copy existing request params
390: newParams=self.REQUEST.form.copy()
391: # change single param
392: if param is not None:
393: if val is None:
394: if newParams.has_key(param):
395: del newParams[param]
396: else:
397: newParams[param] = str(val)
398:
399: # change more params
400: if params is not None:
401: for (k, v) in params.items():
402: if v is None:
403: # val=None removes param
404: if newParams.has_key(k):
405: del newParams[k]
406:
407: else:
408: newParams[k] = v
409:
410: if duplicates:
411: # eliminate lists (coming from duplicate keys)
412: for (k,v) in newParams.items():
413: if isinstance(v, list):
414: if duplicates == 'comma':
415: # make comma-separated list of non-empty entries
416: newParams[k] = ','.join([t for t in v if t])
417: elif duplicates == 'first':
418: # take first non-empty entry
419: newParams[k] = [t for t in v if t][0]
420:
421: return newParams
422:
423: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'):
424: """returns URL to documentviewer with parameter param set to val or from dict params"""
425: urlParams = self.getParams(param=param, val=val, params=params, duplicates=duplicates)
426: # quote values and assemble into query string (not escaping '/')
427: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(unicode(v),'/')) for (k, v) in urlParams.items()])
428: if baseUrl is None:
429: baseUrl = self.getDocumentViewerURL()
430:
431: url = "%s?%s"%(baseUrl, ps)
432: return url
433:
434: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'):
435: """link to documentviewer with parameter param set to val"""
436: return self.getLink(param=param, val=val, params=params, baseUrl=baseUrl, paramSep='&', duplicates=duplicates)
437:
438:
439: def getInfo_xml(self,url,mode):
440: """returns info about the document as XML"""
441: if not self.digilibBaseUrl:
442: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
443:
444: docinfo = self.getDocinfo(mode=mode,url=url)
445: pt = getattr(self.template, 'info_xml')
446: return pt(docinfo=docinfo)
447:
448: def isAccessible(self, docinfo):
449: """returns if access to the resource is granted"""
450: access = docinfo.get('accessType', None)
451: logging.debug("documentViewer (accessOK) access type %s"%access)
452: if access == 'free':
453: logging.debug("documentViewer (accessOK) access is free")
454: return True
455:
456: elif access is None or access in self.authgroups:
457: # only local access -- only logged in users
458: user = getSecurityManager().getUser()
459: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
460: if user is not None:
461: #print "user: ", user
462: return (user.getUserName() != "Anonymous User")
463: else:
464: return False
465:
466: logging.error("documentViewer (accessOK) unknown access type %s"%access)
467: return False
468:
469:
470:
471: def getDocinfo(self, mode, url):
472: """returns docinfo depending on mode"""
473: logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
474: # look for cached docinfo in session
475: if self.REQUEST.SESSION.has_key('docinfo'):
476: docinfo = self.REQUEST.SESSION['docinfo']
477: # check if its still current
478: if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:
479: logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())
480: return docinfo
481:
482: # new docinfo
483: docinfo = {'mode': mode, 'url': url}
484: # add self url
485: docinfo['viewerUrl'] = self.getDocumentViewerURL()
486: docinfo['digilibBaseUrl'] = self.digilibBaseUrl
487: # get index.meta DOM
488: docUrl = None
489: metaDom = None
490: if mode=="texttool":
491: # url points to document dir or index.meta
492: metaDom = self.metadataService.getDomFromPathOrUrl(url)
493: docUrl = url.replace('/index.meta', '')
494: if metaDom is None:
495: raise IOError("Unable to find index.meta for mode=texttool!")
496:
497: elif mode=="imagepath":
498: # url points to folder with images, index.meta optional
499: # asssume index.meta in parent dir
500: docUrl = getParentPath(url)
501: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
502:
503: elif mode=="filepath":
504: # url points to image file, index.meta optional
505: # asssume index.meta is two path segments up
506: docUrl = getParentPath(url, 2)
507: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
508:
509: else:
510: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
511: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
512:
513: docinfo['documentUrl'] = docUrl
514: # process index.meta contents
515: if metaDom is not None and metaDom.tag == 'resource':
516: # document directory name and path
517: resource = self.metadataService.getResourceData(dom=metaDom)
518: if resource:
519: docinfo = self.getDocinfoFromResource(docinfo, resource)
520:
521: # texttool info
522: texttool = self.metadataService.getTexttoolData(dom=metaDom)
523: if texttool:
524: docinfo = self.getDocinfoFromTexttool(docinfo, texttool)
525:
526: # bib info
527: bib = self.metadataService.getBibData(dom=metaDom)
528: if bib:
529: docinfo = self.getDocinfoFromBib(docinfo, bib)
530: else:
531: # no bib - try info.xml
532: docinfo = self.getDocinfoFromPresentationInfoXml(docinfo)
533:
534: # auth info
535: access = self.metadataService.getAccessData(dom=metaDom)
536: if access:
537: docinfo = self.getDocinfoFromAccess(docinfo, access)
538:
539: # attribution info
540: attribution = self.metadataService.getAttributionData(dom=metaDom)
541: if attribution:
542: logging.debug("getDocinfo: attribution=%s"%repr(attribution))
543: docinfo['attribution'] = attribution
544: #docinfo = self.getDocinfoFromAccess(docinfo, access)
545:
546: # copyright info
547: copyright = self.metadataService.getCopyrightData(dom=metaDom)
548: if copyright:
549: logging.debug("getDocinfo: copyright=%s"%repr(copyright))
550: docinfo['copyright'] = copyright
551: #docinfo = self.getDocinfoFromAccess(docinfo, access)
552:
553: # image path
554: if mode != 'texttool':
555: # override image path from texttool with url
556: docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1)
557:
558: # number of images from digilib
559: if docinfo.get('imagePath', None):
560: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath']
561: docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath'])
562:
563: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
564: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
565: # store in session
566: self.REQUEST.SESSION['docinfo'] = docinfo
567: return docinfo
568:
569: def getDocinfoFromResource(self, docinfo, resource):
570: """reads contents of resource element into docinfo"""
571: docName = resource.get('name', None)
572: docinfo['documentName'] = docName
573: docPath = resource.get('archive-path', None)
574: if docPath:
575: # clean up document path
576: if docPath[0] != '/':
577: docPath = '/' + docPath
578:
579: if docName and (not docPath.endswith(docName)):
580: docPath += "/" + docName
581:
582: else:
583: # use docUrl as docPath
584: docUrl = docinfo['documentURL']
585: if not docUrl.startswith('http:'):
586: docPath = docUrl
587: if docPath:
588: # fix URLs starting with /mpiwg/online
589: docPath = docPath.replace('/mpiwg/online', '', 1)
590:
591: docinfo['documentPath'] = docPath
592: return docinfo
593:
594: def getDocinfoFromTexttool(self, docinfo, texttool):
595: """reads contents of texttool element into docinfo"""
596: # image dir
597: imageDir = texttool.get('image', None)
598: docPath = docinfo.get('documentPath', None)
599: if imageDir and docPath:
600: #print "image: ", imageDir, " archivepath: ", archivePath
601: imageDir = os.path.join(docPath, imageDir)
602: imageDir = imageDir.replace('/mpiwg/online', '', 1)
603: docinfo['imagePath'] = imageDir
604:
605: # old style text URL
606: textUrl = texttool.get('text', None)
607: if textUrl and docPath:
608: if urlparse.urlparse(textUrl)[0] == "": #keine url
609: textUrl = os.path.join(docPath, textUrl)
610:
611: docinfo['textURL'] = textUrl
612:
613: # new style text-url-path
614: textUrl = texttool.get('text-url-path', None)
615: if textUrl:
616: docinfo['textURLPath'] = textUrl
617:
618: # page flow
619: docinfo['pageFlow'] = texttool.get('page-flow', 'ltr')
620:
621: # odd pages are left
622: docinfo['oddPage'] = texttool.get('odd-scan-position', 'left')
623:
624: # number of title page (0: not defined)
625: docinfo['titlePage'] = texttool.get('title-scan-no', 0)
626:
627: # old presentation stuff
628: presentation = texttool.get('presentation', None)
629: if presentation and docPath:
630: if presentation.startswith('http:'):
631: docinfo['presentationUrl'] = presentation
632: else:
633: docinfo['presentationUrl'] = os.path.join(docPath, presentation)
634:
635:
636: return docinfo
637:
638: def getDocinfoFromBib(self, docinfo, bib):
639: """reads contents of bib element into docinfo"""
640: logging.debug("getDocinfoFromBib bib=%s"%repr(bib))
641: # put all raw bib fields in dict "bib"
642: docinfo['bib'] = bib
643: bibtype = bib.get('@type', None)
644: docinfo['bibType'] = bibtype
645: # also store DC metadata for convenience
646: dc = self.metadataService.getDCMappedData(bib)
647: docinfo['creator'] = dc.get('creator',None)
648: docinfo['title'] = dc.get('title',None)
649: docinfo['date'] = dc.get('date',None)
650: return docinfo
651:
652: def getDocinfoFromAccess(self, docinfo, acc):
653: """reads contents of access element into docinfo"""
654: #TODO: also read resource type
655: logging.debug("getDocinfoFromAccess acc=%s"%repr(acc))
656: try:
657: acctype = acc['@attr']['type']
658: if acctype:
659: access=acctype
660: if access in ['group', 'institution']:
661: access = acc['name'].lower()
662:
663: docinfo['accessType'] = access
664:
665: except:
666: pass
667:
668: return docinfo
669:
670: def getDocinfoFromDigilib(self, docinfo, path):
671: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
672: # fetch data
673: txt = getHttpData(infoUrl)
674: if not txt:
675: logging.error("Unable to get dir-info from %s"%(infoUrl))
676: return docinfo
677:
678: dom = ET.fromstring(txt)
679: size = getText(dom.find("size"))
680: logging.debug("getDocinfoFromDigilib: size=%s"%size)
681: if size:
682: docinfo['numPages'] = int(size)
683: else:
684: docinfo['numPages'] = 0
685:
686: # TODO: produce and keep list of image names and numbers
687: return docinfo
688:
689:
690: def getDocinfoFromPresentationInfoXml(self,docinfo):
691: """gets DC-like bibliographical information from the presentation entry in texttools"""
692: url = docinfo.get('presentationUrl', None)
693: if not url:
694: logging.error("getDocinfoFromPresentation: no URL!")
695: return docinfo
696:
697: dom = None
698: metaUrl = None
699: if url.startswith("http://"):
700: # real URL
701: metaUrl = url
702: else:
703: # online path
704:
705: server=self.digilibBaseUrl+"/servlet/Texter?fn="
706: metaUrl=server+url
707:
708: txt=getHttpData(metaUrl)
709: if txt is None:
710: logging.error("Unable to read info.xml from %s"%(url))
711: return docinfo
712:
713: dom = ET.fromstring(txt)
714: docinfo['creator']=getText(dom.find(".//author"))
715: docinfo['title']=getText(dom.find(".//title"))
716: docinfo['date']=getText(dom.find(".//date"))
717: return docinfo
718:
719:
720: def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None):
721: """returns pageinfo with the given parameters"""
722: logging.debug("getPageInfo(current=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewType=%s, tocMode=%s)"%(current,start,rows,cols,viewMode,viewType,tocMode))
723: pageinfo = {}
724: pageinfo['viewMode'] = viewMode
725: pageinfo['viewType'] = viewType
726: pageinfo['tocMode'] = tocMode
727:
728: current = getInt(current)
729: pageinfo['current'] = current
730: pageinfo['pn'] = current
731: rows = int(rows or self.thumbrows)
732: pageinfo['rows'] = rows
733: cols = int(cols or self.thumbcols)
734: pageinfo['cols'] = cols
735: grpsize = cols * rows
736: pageinfo['groupsize'] = grpsize
737: # is start is empty use one around current
738: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
739: # int(current / grpsize) * grpsize +1))
740: pageinfo['start'] = start
741:
742: np = int(docinfo.get('numPages', 0))
743: if np == 0:
744: # numPages unknown - maybe we can get it from text page
745: if docinfo.get('textURLPath', None):
746: # cache text page as well
747: pageinfo['textPage'] = self.getTextPage(mode=viewType, pn=current, docinfo=docinfo, pageinfo=pageinfo)
748: np = int(docinfo.get('numPages', 0))
749:
750: pageinfo['numgroups'] = int(np / grpsize)
751: if np % grpsize > 0:
752: pageinfo['numgroups'] += 1
753:
754: pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl'
755: oddScanLeft = docinfo.get('oddPage', 'left') != 'right'
756: # add zeroth page for two columns
757: pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft))
758: pageinfo['pageZero'] = pageZero
759: pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np)
760:
761: # TODO: do we need this here?
762: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
763: pageinfo['query'] = self.REQUEST.get('query','')
764: pageinfo['queryType'] = self.REQUEST.get('queryType','')
765: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
766: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
767: pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30))
768: pageinfo['queryPageSize'] = getInt(self.REQUEST.get('queryPageSize', 10))
769: pageinfo['tocPN'] = getInt(self.REQUEST.get('tocPN', '1'))
770: pageinfo['searchPN'] = getInt(self.REQUEST.get('searchPN','1'))
771:
772: # limit tocPN
773: if 'tocSize_%s'%tocMode in docinfo:
774: tocSize = docinfo['tocSize_%s'%tocMode]
775: tocPageSize = pageinfo['tocPageSize']
776: # cached toc
777: if tocSize%tocPageSize>0:
778: tocPages=tocSize/tocPageSize+1
779: else:
780: tocPages=tocSize/tocPageSize
781:
782: pageinfo['tocPN'] = min(tocPages,pageinfo['tocPN'])
783:
784: return pageinfo
785:
786:
787: def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0):
788: """returns dict with array of page informations for one screenfull of thumbnails"""
789: batch = {}
790: grpsize = rows * cols
791: if maxIdx == 0:
792: maxIdx = start + grpsize
793:
794: nb = int(math.ceil(maxIdx / float(grpsize)))
795: # list of all batch start and end points
796: batches = []
797: if pageZero:
798: ofs = 0
799: else:
800: ofs = 1
801:
802: for i in range(nb):
803: s = i * grpsize + ofs
804: e = min((i + 1) * grpsize + ofs - 1, maxIdx)
805: batches.append({'start':s, 'end':e})
806:
807: batch['batches'] = batches
808:
809: pages = []
810: if pageZero and start == 1:
811: # correct beginning
812: idx = 0
813: else:
814: idx = start
815:
816: for r in range(rows):
817: row = []
818: for c in range(cols):
819: if idx < minIdx or idx > maxIdx:
820: page = {'idx':None}
821: else:
822: page = {'idx':idx}
823:
824: idx += 1
825: if pageFlowLtr:
826: row.append(page)
827: else:
828: row.insert(0, page)
829:
830: pages.append(row)
831:
832: if start > 1:
833: batch['prevStart'] = max(start - grpsize, 1)
834: else:
835: batch['prevStart'] = None
836:
837: if start + grpsize < maxIdx:
838: batch['nextStart'] = start + grpsize
839: else:
840: batch['nextStart'] = None
841:
842: batch['pages'] = pages
843: return batch
844:
845: def getBatch(self, start=1, size=10, end=0, data=None, fullData=True):
846: """returns dict with information for one screenfull of data."""
847: batch = {}
848: if end == 0:
849: end = start + size
850:
851: nb = int(math.ceil(end / float(size)))
852: # list of all batch start and end points
853: batches = []
854: for i in range(nb):
855: s = i * size + 1
856: e = min((i + 1) * size, end)
857: batches.append({'start':s, 'end':e})
858:
859: batch['batches'] = batches
860: # list of elements in this batch
861: this = []
862: j = 0
863: for i in range(start, min(start+size, end)):
864: if data:
865: if fullData:
866: d = data[i]
867: else:
868: d = data[j]
869: j += 1
870:
871: else:
872: d = i+1
873:
874: this.append(d)
875:
876: batch['this'] = this
877: if start > 1:
878: batch['prevStart'] = max(start - size, 1)
879: else:
880: batch['prevStart'] = None
881:
882: if start + size < end:
883: batch['nextStart'] = start + size
884: else:
885: batch['nextStart'] = None
886:
887: return batch
888:
889:
890: security.declareProtected('View management screens','changeDocumentViewerForm')
891: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
892:
893: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
894: """init document viewer"""
895: self.title=title
896: self.digilibBaseUrl = digilibBaseUrl
897: self.thumbrows = thumbrows
898: self.thumbcols = thumbcols
899: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
900: try:
901: # assume MetaDataFolder instance is called metadata
902: self.metadataService = getattr(self, 'metadata')
903: except Exception, e:
904: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
905:
906: if RESPONSE is not None:
907: RESPONSE.redirect('manage_main')
908:
909: def manage_AddDocumentViewerForm(self):
910: """add the viewer form"""
911: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
912: return pt()
913:
914: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
915: """add the viewer"""
916: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
917: self._setObject(id,newObj)
918:
919: if RESPONSE is not None:
920: RESPONSE.redirect('manage_main')
921:
922: ## DocumentViewerTemplate class
923: class DocumentViewerTemplate(ZopePageTemplate):
924: """Template for document viewer"""
925: meta_type="DocumentViewer Template"
926:
927:
928: def manage_addDocumentViewerTemplateForm(self):
929: """Form for adding"""
930: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
931: return pt()
932:
933: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
934: REQUEST=None, submit=None):
935: "Add a Page Template with optional file content."
936:
937: self._setObject(id, DocumentViewerTemplate(id))
938: ob = getattr(self, id)
939: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
940: logging.info("txt %s:"%txt)
941: ob.pt_edit(txt,"text/html")
942: if title:
943: ob.pt_setTitle(title)
944: try:
945: u = self.DestinationURL()
946: except AttributeError:
947: u = REQUEST['URL1']
948:
949: u = "%s/%s" % (u, urllib.quote(id))
950: REQUEST.RESPONSE.redirect(u+'/manage_main')
951: return ''
952:
953:
954:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>