1: from OFS.Folder import Folder
2: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
3: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
4: from AccessControl import ClassSecurityInfo
5: from AccessControl import getSecurityManager
6: from Globals import package_home
7:
8: #from Ft.Xml import EMPTY_NAMESPACE, Parse
9: #import Ft.Xml.Domlette
10:
11: import xml.etree.ElementTree as ET
12:
13: import os.path
14: import sys
15: import urllib
16: import logging
17: import math
18: import urlparse
19: import re
20: import string
21:
22: from SrvTxtUtils import getInt, getText, getHttpData
23:
24: def logger(txt,method,txt2):
25: """logging"""
26: logging.info(txt+ txt2)
27:
28:
29: def serializeNode(node, encoding="utf-8"):
30: """returns a string containing node as XML"""
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()
38: return s
39:
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
47: bt['versFirefox']=""
48: bt['versIE']=""
49: bt['versSafariChrome']=""
50: bt['versOpera']=""
51:
52: if string.find(ua, 'MSIE') > -1:
53: bt['isIE'] = True
54: else:
55: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
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
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]
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))
83: bt['versFirefox']=nav5[0:3]
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
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
100:
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:
108:
109: ##
110: ## documentViewer class
111: ##
112: class documentViewer(Folder):
113: """document viewer"""
114: meta_type="Document viewer"
115:
116: security=ClassSecurityInfo()
117: manage_options=Folder.manage_options+(
118: {'label':'main config','action':'changeDocumentViewerForm'},
119: )
120:
121: metadataService = None
122: """MetaDataFolder instance"""
123:
124: # templates and forms
125: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
126: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
127: toc_text = PageTemplateFile('zpt/toc_text', globals())
128: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
129: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
130: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
131: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
132: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
133: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
134: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
135: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
136: head_main = PageTemplateFile('zpt/head_main', globals())
137: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
138: info_xml = PageTemplateFile('zpt/info_xml', globals())
139:
140:
141: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
142:
143:
144: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
145: """init document viewer"""
146: self.id=id
147: self.title=title
148: self.thumbcols = thumbcols
149: self.thumbrows = thumbrows
150: # authgroups is list of authorized groups (delimited by ,)
151: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
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:
158: import MpdlXmlTextServer
159: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
160: #templateFolder['fulltextclient'] = xmlRpcClient
161: templateFolder._setObject('fulltextclient',textServer)
162: except Exception, e:
163: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
164:
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))
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:
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 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:
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: viewType = ','.join([t for t in viewType if t])
311:
312: pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode)
313:
314: # get template /template/viewer_$viewMode
315: pt = getattr(self.template, 'viewer_%s'%viewMode, None)
316: if pt is None:
317: logging.error("No template for viewMode=%s!"%viewMode)
318: # TODO: error page?
319: return "No template for viewMode=%s!"%viewMode
320:
321: # and execute with parameters
322: return pt(docinfo=docinfo, pageinfo=pageinfo)
323:
324: def generateMarks(self,mk):
325: ret=""
326: if mk is None:
327: return ""
328: if not isinstance(mk, list):
329: mk=[mk]
330: for m in mk:
331: ret+="mk=%s"%m
332: return ret
333:
334:
335: def getBrowser(self):
336: """getBrowser the version of browser """
337: bt = browserCheck(self)
338: logging.debug("BROWSER VERSION: %s"%(bt))
339: return bt
340:
341: def findDigilibUrl(self):
342: """try to get the digilib URL from zogilib"""
343: url = self.template.zogilib.getDLBaseUrl()
344: return url
345:
346: def getDocumentViewerURL(self):
347: """returns the URL of this instance"""
348: return self.absolute_url()
349:
350: def getStyle(self, idx, selected, style=""):
351: """returns a string with the given style and append 'sel' if path == selected."""
352: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
353: if idx == selected:
354: return style + 'sel'
355: else:
356: return style
357:
358: def getParams(self, param=None, val=None, params=None):
359: """returns dict with URL parameters.
360:
361: Takes URL parameters and additionally param=val or dict params.
362: Deletes key if value is None."""
363: # copy existing request params
364: newParams=self.REQUEST.form.copy()
365: # change single param
366: if param is not None:
367: if val is None:
368: if newParams.has_key(param):
369: del newParams[param]
370: else:
371: newParams[param] = str(val)
372:
373: # change more params
374: if params is not None:
375: for k in params.keys():
376: v = params[k]
377: if v is None:
378: # val=None removes param
379: if newParams.has_key(k):
380: del newParams[k]
381:
382: else:
383: newParams[k] = v
384:
385: return newParams
386:
387: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
388: """returns URL to documentviewer with parameter param set to val or from dict params"""
389: urlParams = self.getParams(param=param, val=val, params=params)
390: # quote values and assemble into query string (not escaping '/')
391: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(unicode(v),'/')) for (k, v) in urlParams.items()])
392: if baseUrl is None:
393: baseUrl = self.getDocumentViewerURL()
394:
395: url = "%s?%s"%(baseUrl, ps)
396: return url
397:
398: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
399: """link to documentviewer with parameter param set to val"""
400: return self.getLink(param, val, params, baseUrl, '&')
401:
402:
403: def getInfo_xml(self,url,mode):
404: """returns info about the document as XML"""
405: if not self.digilibBaseUrl:
406: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
407:
408: docinfo = self.getDocinfo(mode=mode,url=url)
409: pt = getattr(self.template, 'info_xml')
410: return pt(docinfo=docinfo)
411:
412: def isAccessible(self, docinfo):
413: """returns if access to the resource is granted"""
414: access = docinfo.get('accessType', None)
415: logging.debug("documentViewer (accessOK) access type %s"%access)
416: if access == 'free':
417: logging.debug("documentViewer (accessOK) access is free")
418: return True
419:
420: elif access is None or access in self.authgroups:
421: # only local access -- only logged in users
422: user = getSecurityManager().getUser()
423: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
424: if user is not None:
425: #print "user: ", user
426: return (user.getUserName() != "Anonymous User")
427: else:
428: return False
429:
430: logging.error("documentViewer (accessOK) unknown access type %s"%access)
431: return False
432:
433:
434:
435: def getDocinfo(self, mode, url):
436: """returns docinfo depending on mode"""
437: logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
438: # look for cached docinfo in session
439: if self.REQUEST.SESSION.has_key('docinfo'):
440: docinfo = self.REQUEST.SESSION['docinfo']
441: # check if its still current
442: if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:
443: logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())
444: return docinfo
445:
446: # new docinfo
447: docinfo = {'mode': mode, 'url': url}
448: # add self url
449: docinfo['viewerUrl'] = self.getDocumentViewerURL()
450: # get index.meta DOM
451: docUrl = None
452: metaDom = None
453: if mode=="texttool":
454: # url points to document dir or index.meta
455: metaDom = self.metadataService.getDomFromPathOrUrl(url)
456: docUrl = url.replace('/index.meta', '')
457: if metaDom is None:
458: raise IOError("Unable to find index.meta for mode=texttool!")
459:
460: elif mode=="imagepath":
461: # url points to folder with images, index.meta optional
462: # asssume index.meta in parent dir
463: docUrl = getParentPath(url)
464: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
465:
466: elif mode=="filepath":
467: # url points to image file, index.meta optional
468: # asssume index.meta is two path segments up
469: docUrl = getParentPath(url, 2)
470: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
471:
472: else:
473: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
474: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
475:
476: docinfo['documentUrl'] = docUrl
477: # process index.meta contents
478: if metaDom is not None and metaDom.tag == 'resource':
479: # document directory name and path
480: resource = self.metadataService.getResourceData(dom=metaDom)
481: if resource:
482: docinfo = self.getDocinfoFromResource(docinfo, resource)
483:
484: # texttool info
485: texttool = self.metadataService.getTexttoolData(dom=metaDom)
486: if texttool:
487: docinfo = self.getDocinfoFromTexttool(docinfo, texttool)
488:
489: # bib info
490: bib = self.metadataService.getBibData(dom=metaDom)
491: if bib:
492: docinfo = self.getDocinfoFromBib(docinfo, bib)
493: else:
494: # no bib - try info.xml
495: docinfo = self.getDocinfoFromPresentationInfoXml(docinfo)
496:
497: # auth info
498: access = self.metadataService.getAccessData(dom=metaDom)
499: if access:
500: docinfo = self.getDocinfoFromAccess(docinfo, access)
501:
502: # attribution info
503: attribution = self.metadataService.getAttributionData(dom=metaDom)
504: if attribution:
505: logging.debug("getDocinfo: attribution=%s"%repr(attribution))
506: docinfo['attribution'] = attribution
507: #docinfo = self.getDocinfoFromAccess(docinfo, access)
508:
509: # copyright info
510: copyright = self.metadataService.getCopyrightData(dom=metaDom)
511: if copyright:
512: logging.debug("getDocinfo: copyright=%s"%repr(copyright))
513: docinfo['copyright'] = copyright
514: #docinfo = self.getDocinfoFromAccess(docinfo, access)
515:
516: # image path
517: if mode != 'texttool':
518: # override image path from texttool
519: docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1)
520:
521: # number of images from digilib
522: if docinfo.get('imagePath', None):
523: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath']
524: docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath'])
525:
526: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
527: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
528: # store in session
529: self.REQUEST.SESSION['docinfo'] = docinfo
530: return docinfo
531:
532: def getDocinfoFromResource(self, docinfo, resource):
533: """reads contents of resource element into docinfo"""
534: docName = resource.get('name', None)
535: docinfo['documentName'] = docName
536: docPath = resource.get('archive-path', None)
537: if docPath:
538: # clean up document path
539: if docPath[0] != '/':
540: docPath = '/' + docPath
541:
542: if docName and (not docPath.endswith(docName)):
543: docPath += "/" + docName
544:
545: else:
546: # use docUrl as docPath
547: docUrl = docinfo['documentURL']
548: if not docUrl.startswith('http:'):
549: docPath = docUrl
550: if docPath:
551: # fix URLs starting with /mpiwg/online
552: docPath = docPath.replace('/mpiwg/online', '', 1)
553:
554: docinfo['documentPath'] = docPath
555: return docinfo
556:
557: def getDocinfoFromTexttool(self, docinfo, texttool):
558: """reads contents of texttool element into docinfo"""
559: # image dir
560: imageDir = texttool.get('image', None)
561: docPath = docinfo.get('documentPath', None)
562: if imageDir and docPath:
563: #print "image: ", imageDir, " archivepath: ", archivePath
564: imageDir = os.path.join(docPath, imageDir)
565: imageDir = imageDir.replace('/mpiwg/online', '', 1)
566: docinfo['imagePath'] = imageDir
567:
568: # old style text URL
569: textUrl = texttool.get('text', None)
570: if textUrl and docPath:
571: if urlparse.urlparse(textUrl)[0] == "": #keine url
572: textUrl = os.path.join(docPath, textUrl)
573:
574: docinfo['textURL'] = textUrl
575:
576: # new style text-url-path
577: textUrl = texttool.get('text-url-path', None)
578: if textUrl:
579: docinfo['textURLPath'] = textUrl
580:
581: # page flow
582: docinfo['pageFlow'] = texttool.get('page-flow', 'ltr')
583:
584: # odd pages are left
585: docinfo['oddPage'] = texttool.get('odd-scan-position', 'left')
586:
587: # number of title page (0: not defined)
588: docinfo['titlePage'] = texttool.get('title-scan-no', 0)
589:
590: # old presentation stuff
591: presentation = texttool.get('presentation', None)
592: if presentation and docPath:
593: if presentation.startswith('http:'):
594: docinfo['presentationUrl'] = presentation
595: else:
596: docinfo['presentationUrl'] = os.path.join(docPath, presentation)
597:
598:
599: return docinfo
600:
601: def getDocinfoFromBib(self, docinfo, bib):
602: """reads contents of bib element into docinfo"""
603: logging.debug("getDocinfoFromBib bib=%s"%repr(bib))
604: # put all raw bib fields in dict "bib"
605: docinfo['bib'] = bib
606: bibtype = bib.get('@type', None)
607: docinfo['bibType'] = bibtype
608: # also store DC metadata for convenience
609: dc = self.metadataService.getDCMappedData(bib)
610: docinfo['creator'] = dc.get('creator',None)
611: docinfo['title'] = dc.get('title',None)
612: docinfo['date'] = dc.get('date',None)
613: return docinfo
614:
615: def getDocinfoFromAccess(self, docinfo, acc):
616: """reads contents of access element into docinfo"""
617: #TODO: also read resource type
618: logging.debug("getDocinfoFromAccess acc=%s"%repr(acc))
619: try:
620: acctype = acc['@attr']['type']
621: if acctype:
622: access=acctype
623: if access in ['group', 'institution']:
624: access = acc['name'].lower()
625:
626: docinfo['accessType'] = access
627:
628: except:
629: pass
630:
631: return docinfo
632:
633: def getDocinfoFromDigilib(self, docinfo, path):
634: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
635: # fetch data
636: txt = getHttpData(infoUrl)
637: if not txt:
638: logging.error("Unable to get dir-info from %s"%(infoUrl))
639: return docinfo
640:
641: dom = ET.fromstring(txt)
642: size = getText(dom.find("size"))
643: logging.debug("getDocinfoFromDigilib: size=%s"%size)
644: if size:
645: docinfo['numPages'] = int(size)
646: else:
647: docinfo['numPages'] = 0
648:
649: # TODO: produce and keep list of image names and numbers
650: return docinfo
651:
652:
653: def getDocinfoFromPresentationInfoXml(self,docinfo):
654: """gets DC-like bibliographical information from the presentation entry in texttools"""
655: url = docinfo.get('presentationUrl', None)
656: if not url:
657: logging.error("getDocinfoFromPresentation: no URL!")
658: return docinfo
659:
660: dom = None
661: metaUrl = None
662: if url.startswith("http://"):
663: # real URL
664: metaUrl = url
665: else:
666: # online path
667:
668: server=self.digilibBaseUrl+"/servlet/Texter?fn="
669: metaUrl=server+url
670:
671: txt=getHttpData(metaUrl)
672: if txt is None:
673: logging.error("Unable to read info.xml from %s"%(url))
674: return docinfo
675:
676: dom = ET.fromstring(txt)
677: docinfo['creator']=getText(dom.find(".//author"))
678: docinfo['title']=getText(dom.find(".//title"))
679: docinfo['date']=getText(dom.find(".//date"))
680: return docinfo
681:
682:
683: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None):
684: """returns pageinfo with the given parameters"""
685: pageinfo = {}
686: pageinfo['viewMode'] = viewMode
687: pageinfo['viewType'] = viewType
688: pageinfo['tocMode'] = tocMode
689:
690: current = getInt(current)
691: pageinfo['current'] = current
692: rows = int(rows or self.thumbrows)
693: pageinfo['rows'] = rows
694: cols = int(cols or self.thumbcols)
695: pageinfo['cols'] = cols
696: grpsize = cols * rows
697: pageinfo['groupsize'] = grpsize
698: # is start is empty use one around current
699: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
700: # int(current / grpsize) * grpsize +1))
701: pageinfo['start'] = start
702: pn = self.REQUEST.get('pn','1')
703: pageinfo['pn'] = pn
704: np = int(docinfo.get('numPages', 0))
705: if np == 0:
706: # numPages unknown - maybe we can get it from text page
707: if docinfo.get('textURLPath', None):
708: # cache text page as well
709: pageinfo['textPage'] = self.getTextPage(mode=viewType, pn=pn, docinfo=docinfo, pageinfo=pageinfo)
710: np = int(docinfo.get('numPages', 0))
711:
712: pageinfo['numgroups'] = int(np / grpsize)
713: if np % grpsize > 0:
714: pageinfo['numgroups'] += 1
715:
716: pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl'
717: oddScanLeft = docinfo.get('oddPage', 'left') != 'right'
718: # add zeroth page for two columns
719: pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft))
720: pageinfo['pageZero'] = pageZero
721: pageinfo['pageList'] = self.getPageList(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np)
722:
723: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
724: pageinfo['query'] = self.REQUEST.get('query','')
725: pageinfo['queryType'] = self.REQUEST.get('queryType','')
726: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
727: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
728: pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30))
729: pageinfo['queryPageSize'] = getInt(self.REQUEST.get('queryPageSize', 10))
730: pageinfo['tocPN'] = getInt(self.REQUEST.get('tocPN', '1'))
731: pageinfo['searchPN'] = getInt(self.REQUEST.get('searchPN','1'))
732:
733: # limit tocPN
734: if 'tocSize_%s'%tocMode in docinfo:
735: tocSize = docinfo['tocSize_%s'%tocMode]
736: tocPageSize = pageinfo['tocPageSize']
737: # cached toc
738: if tocSize%tocPageSize>0:
739: tocPages=tocSize/tocPageSize+1
740: else:
741: tocPages=tocSize/tocPageSize
742:
743: pageinfo['tocPN'] = min(tocPages,pageinfo['tocPN'])
744:
745: return pageinfo
746:
747:
748: def getPageList(self, start=None, rows=None, cols=None, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0):
749: """returns array of page informations for one screenfull of thumbnails"""
750: if maxIdx == 0:
751: maxIdx = start + rows * cols
752:
753: pages = []
754: if pageZero and start == 1:
755: # correct beginning
756: idx = 0
757: else:
758: idx = start
759:
760: for r in range(rows):
761: row = []
762: for c in range(cols):
763: if idx < minIdx or idx > maxIdx:
764: page = {'idx':None}
765: else:
766: page = {'idx':idx}
767:
768: idx += 1
769: if pageFlowLtr:
770: row.append(page)
771: else:
772: row.insert(0, page)
773:
774: pages.append(row)
775:
776: logging.debug("getPageList returns=%s"%(pages))
777: return pages
778:
779:
780: security.declareProtected('View management screens','changeDocumentViewerForm')
781: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
782:
783: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
784: """init document viewer"""
785: self.title=title
786: self.digilibBaseUrl = digilibBaseUrl
787: self.thumbrows = thumbrows
788: self.thumbcols = thumbcols
789: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
790: try:
791: # assume MetaDataFolder instance is called metadata
792: self.metadataService = getattr(self, 'metadata')
793: except Exception, e:
794: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
795:
796: if RESPONSE is not None:
797: RESPONSE.redirect('manage_main')
798:
799: def manage_AddDocumentViewerForm(self):
800: """add the viewer form"""
801: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
802: return pt()
803:
804: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
805: """add the viewer"""
806: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
807: self._setObject(id,newObj)
808:
809: if RESPONSE is not None:
810: RESPONSE.redirect('manage_main')
811:
812: ## DocumentViewerTemplate class
813: class DocumentViewerTemplate(ZopePageTemplate):
814: """Template for document viewer"""
815: meta_type="DocumentViewer Template"
816:
817:
818: def manage_addDocumentViewerTemplateForm(self):
819: """Form for adding"""
820: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
821: return pt()
822:
823: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
824: REQUEST=None, submit=None):
825: "Add a Page Template with optional file content."
826:
827: self._setObject(id, DocumentViewerTemplate(id))
828: ob = getattr(self, id)
829: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
830: logging.info("txt %s:"%txt)
831: ob.pt_edit(txt,"text/html")
832: if title:
833: ob.pt_setTitle(title)
834: try:
835: u = self.DestinationURL()
836: except AttributeError:
837: u = REQUEST['URL1']
838:
839: u = "%s/%s" % (u, urllib.quote(id))
840: REQUEST.RESPONSE.redirect(u+'/manage_main')
841: return ''
842:
843:
844:
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