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 App.Common import rfc1123_date
6: #from Products.ZSimpleFile.ZSimpleFile import ZSimpleFile
7: from AccessControl import ClassSecurityInfo
8: from AccessControl import getSecurityManager
9: from Globals import package_home
10:
11: import xml.etree.ElementTree as ET
12:
13: import os
14: import stat
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: def devImageFileIndexHtml(self, REQUEST, RESPONSE):
110: """index_html method for App.ImageFile that updates the file info for each request."""
111: stat_info = os.stat(self.path)
112: self.size = stat_info[stat.ST_SIZE]
113: self.lmt = float(stat_info[stat.ST_MTIME]) or time.time()
114: self.lmh = rfc1123_date(self.lmt)
115: # call original method
116: return ImageFile.index_html(self, REQUEST, RESPONSE)
117:
118: ##
119: ## documentViewer class
120: ##
121: class documentViewer(Folder):
122: """document viewer"""
123: meta_type="Document viewer"
124:
125: security=ClassSecurityInfo()
126: manage_options=Folder.manage_options+(
127: {'label':'main config','action':'changeDocumentViewerForm'},
128: )
129:
130: metadataService = None
131: """MetaDataFolder instance"""
132:
133: # templates and forms
134: viewer_text = PageTemplateFile('zpt/viewer_text', globals())
135: viewer_images = PageTemplateFile('zpt/viewer_images', globals())
136: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
137: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
138: toc_text = PageTemplateFile('zpt/toc_text', globals())
139: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
140: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
141: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
142: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
143: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
144: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
145: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
146: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
147: head_main = PageTemplateFile('zpt/head_main', globals())
148: info_xml = PageTemplateFile('zpt/info_xml', globals())
149: docuviewer_css = ImageFile('css/docuviewer.css',globals())
150: # make ImageFile better for development
151: docuviewer_css.index_html = devImageFileIndexHtml
152:
153:
154: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
155:
156:
157: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
158: """init document viewer"""
159: self.id=id
160: self.title=title
161: self.thumbcols = thumbcols
162: self.thumbrows = thumbrows
163: # authgroups is list of authorized groups (delimited by ,)
164: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
165: # create template folder so we can always use template.something
166:
167: templateFolder = Folder('template')
168: #self['template'] = templateFolder # Zope-2.12 style
169: self._setObject('template',templateFolder) # old style
170: try:
171: import MpdlXmlTextServer
172: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
173: #templateFolder['fulltextclient'] = xmlRpcClient
174: templateFolder._setObject('fulltextclient',textServer)
175: except Exception, e:
176: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
177:
178: try:
179: from Products.zogiLib.zogiLib import zogiLib
180: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
181: #templateFolder['zogilib'] = zogilib
182: templateFolder._setObject('zogilib',zogilib)
183: except Exception, e:
184: logging.error("Unable to create zogiLib for zogilib: "+str(e))
185:
186: try:
187: # assume MetaDataFolder instance is called metadata
188: self.metadataService = getattr(self, 'metadata')
189: except Exception, e:
190: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
191:
192: if digilibBaseUrl is not None:
193: self.digilibBaseUrl = digilibBaseUrl
194:
195:
196: # proxy text server methods to fulltextclient
197: def getTextPage(self, **args):
198: """get page"""
199: return self.template.fulltextclient.getTextPage(**args)
200:
201: def getOrigPages(self, **args):
202: """get page"""
203: return self.template.fulltextclient.getOrigPages(**args)
204:
205: def getOrigPagesNorm(self, **args):
206: """get page"""
207: return self.template.fulltextclient.getOrigPagesNorm(**args)
208:
209: def getQuery(self, **args):
210: """get query in search"""
211: return self.template.fulltextclient.getQuery(**args)
212:
213: def getSearch(self, **args):
214: """get search"""
215: return self.template.fulltextclient.getSearch(**args)
216:
217: def getGisPlaces(self, **args):
218: """get gis places"""
219: return self.template.fulltextclient.getGisPlaces(**args)
220:
221: def getAllGisPlaces(self, **args):
222: """get all gis places """
223: return self.template.fulltextclient.getAllGisPlaces(**args)
224:
225: def getWordInfo(self, **args):
226: """get translate"""
227: return self.template.fulltextclient.getWordInfo(**args)
228:
229: def getLemma(self, **args):
230: """get lemma"""
231: return self.template.fulltextclient.getLemma(**args)
232:
233: def getLemmaQuery(self, **args):
234: """get query"""
235: return self.template.fulltextclient.getLemmaQuery(**args)
236:
237: def getLex(self, **args):
238: """get lex"""
239: return self.template.fulltextclient.getLex(**args)
240:
241: def getToc(self, **args):
242: """get toc"""
243: return self.template.fulltextclient.getToc(**args)
244:
245: def getTocPage(self, **args):
246: """get tocpage"""
247: return self.template.fulltextclient.getTocPage(**args)
248:
249:
250: security.declareProtected('View','thumbs_rss')
251: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
252: '''
253: view it
254: @param mode: defines how to access the document behind url
255: @param url: url which contains display information
256: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
257:
258: '''
259: logging.debug("HHHHHHHHHHHHHH:load the rss")
260: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
261:
262: if not hasattr(self, 'template'):
263: # create template folder if it doesn't exist
264: self.manage_addFolder('template')
265:
266: if not self.digilibBaseUrl:
267: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
268:
269: docinfo = self.getDocinfo(mode=mode,url=url)
270: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
271: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
272: ''' ZDES '''
273: pt = getattr(self.template, 'thumbs_main_rss')
274:
275: if viewMode=="auto": # automodus gewaehlt
276: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
277: viewMode="text"
278: else:
279: viewMode="images"
280:
281: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
282:
283:
284: security.declareProtected('View','index_html')
285: def index_html(self,url,mode="texttool",viewMode="auto",viewType=None,tocMode="thumbs",start=1,pn=1):
286: """
287: view page
288: @param url: url which contains display information
289: @param mode: defines how to access the document behind url
290: @param viewMode: 'images': display images, 'text': display text, default is 'auto'
291: @param viewType: sub-type of viewMode, e.g. 'dict' for viewMode='text'
292: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
293: """
294:
295: logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewType=%s start=%s pn=%s"%(mode,url,viewMode,viewType,start,pn))
296:
297: if not hasattr(self, 'template'):
298: # this won't work
299: logging.error("template folder missing!")
300: return "ERROR: template folder missing!"
301:
302: if not getattr(self, 'digilibBaseUrl', None):
303: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
304:
305: docinfo = self.getDocinfo(mode=mode,url=url)
306:
307: if tocMode != "thumbs":
308: # get table of contents
309: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
310:
311: # auto viewMode: text if there is a text else images
312: if viewMode=="auto":
313: if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):
314: viewMode = "text"
315: viewType = "dict"
316: else:
317: viewMode = "images"
318:
319: elif viewMode == "text_dict":
320: # legacy fix
321: viewMode = "text"
322: viewType = "dict"
323:
324: # stringify viewType
325: if isinstance(viewType, list):
326: logging.debug("index_html: viewType is list:%s"%viewType)
327: viewType = ','.join([t for t in viewType if t])
328:
329: pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode)
330:
331: # get template /template/viewer_$viewMode
332: pt = getattr(self.template, 'viewer_%s'%viewMode, None)
333: if pt is None:
334: logging.error("No template for viewMode=%s!"%viewMode)
335: # TODO: error page?
336: return "No template for viewMode=%s!"%viewMode
337:
338: # and execute with parameters
339: return pt(docinfo=docinfo, pageinfo=pageinfo)
340:
341: def generateMarks(self,mk):
342: ret=""
343: if mk is None:
344: return ""
345: if not isinstance(mk, list):
346: mk=[mk]
347: for m in mk:
348: ret+="mk=%s"%m
349: return ret
350:
351:
352: def getBrowser(self):
353: """getBrowser the version of browser """
354: bt = browserCheck(self)
355: logging.debug("BROWSER VERSION: %s"%(bt))
356: return bt
357:
358: def findDigilibUrl(self):
359: """try to get the digilib URL from zogilib"""
360: url = self.template.zogilib.getDLBaseUrl()
361: return url
362:
363: def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None):
364: """returns URL to digilib Scaler with params"""
365: url = None
366: if docinfo is not None:
367: url = docinfo.get('imageURL', None)
368:
369: if url is None:
370: url = "%s/servlet/Scaler?"%self.digilibBaseUrl
371: if fn is None and docinfo is not None:
372: fn = docinfo.get('imagePath','')
373:
374: url += "fn=%s"%fn
375:
376: if pn:
377: url += "&pn=%s"%pn
378:
379: url += "&dw=%s&dh=%s"%(dw,dh)
380: return url
381:
382: def getDocumentViewerURL(self):
383: """returns the URL of this instance"""
384: return self.absolute_url()
385:
386: def getStyle(self, idx, selected, style=""):
387: """returns a string with the given style and append 'sel' if idx == selected."""
388: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
389: if idx == selected:
390: return style + 'sel'
391: else:
392: return style
393:
394: def getParams(self, param=None, val=None, params=None, duplicates=None):
395: """returns dict with URL parameters.
396:
397: Takes URL parameters and additionally param=val or dict params.
398: Deletes key if value is None."""
399: # copy existing request params
400: newParams=self.REQUEST.form.copy()
401: # change single param
402: if param is not None:
403: if val is None:
404: if newParams.has_key(param):
405: del newParams[param]
406: else:
407: newParams[param] = str(val)
408:
409: # change more params
410: if params is not None:
411: for (k, v) in params.items():
412: if v is None:
413: # val=None removes param
414: if newParams.has_key(k):
415: del newParams[k]
416:
417: else:
418: newParams[k] = v
419:
420: if duplicates:
421: # eliminate lists (coming from duplicate keys)
422: for (k,v) in newParams.items():
423: if isinstance(v, list):
424: if duplicates == 'comma':
425: # make comma-separated list of non-empty entries
426: newParams[k] = ','.join([t for t in v if t])
427: elif duplicates == 'first':
428: # take first non-empty entry
429: newParams[k] = [t for t in v if t][0]
430:
431: return newParams
432:
433: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'):
434: """returns URL to documentviewer with parameter param set to val or from dict params"""
435: urlParams = self.getParams(param=param, val=val, params=params, duplicates=duplicates)
436: # quote values and assemble into query string (not escaping '/')
437: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(unicode(v),'/')) for (k, v) in urlParams.items()])
438: if baseUrl is None:
439: baseUrl = self.getDocumentViewerURL()
440:
441: url = "%s?%s"%(baseUrl, ps)
442: return url
443:
444: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'):
445: """link to documentviewer with parameter param set to val"""
446: return self.getLink(param=param, val=val, params=params, baseUrl=baseUrl, paramSep='&', duplicates=duplicates)
447:
448:
449: def getInfo_xml(self,url,mode):
450: """returns info about the document as XML"""
451: if not self.digilibBaseUrl:
452: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
453:
454: docinfo = self.getDocinfo(mode=mode,url=url)
455: pt = getattr(self.template, 'info_xml')
456: return pt(docinfo=docinfo)
457:
458: def isAccessible(self, docinfo):
459: """returns if access to the resource is granted"""
460: access = docinfo.get('accessType', None)
461: logging.debug("documentViewer (accessOK) access type %s"%access)
462: if access == 'free':
463: logging.debug("documentViewer (accessOK) access is free")
464: return True
465:
466: elif access is None or access in self.authgroups:
467: # only local access -- only logged in users
468: user = getSecurityManager().getUser()
469: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
470: if user is not None:
471: #print "user: ", user
472: return (user.getUserName() != "Anonymous User")
473: else:
474: return False
475:
476: logging.error("documentViewer (accessOK) unknown access type %s"%access)
477: return False
478:
479:
480:
481: def getDocinfo(self, mode, url):
482: """returns docinfo depending on mode"""
483: logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
484: # look for cached docinfo in session
485: if self.REQUEST.SESSION.has_key('docinfo'):
486: docinfo = self.REQUEST.SESSION['docinfo']
487: # check if its still current
488: if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:
489: logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())
490: return docinfo
491:
492: # new docinfo
493: docinfo = {'mode': mode, 'url': url}
494: # add self url
495: docinfo['viewerUrl'] = self.getDocumentViewerURL()
496: docinfo['digilibBaseUrl'] = self.digilibBaseUrl
497: # get index.meta DOM
498: docUrl = None
499: metaDom = None
500: if mode=="texttool":
501: # url points to document dir or index.meta
502: metaDom = self.metadataService.getDomFromPathOrUrl(url)
503: docUrl = url.replace('/index.meta', '')
504: if metaDom is None:
505: raise IOError("Unable to find index.meta for mode=texttool!")
506:
507: elif mode=="imagepath":
508: # url points to folder with images, index.meta optional
509: # asssume index.meta in parent dir
510: docUrl = getParentPath(url)
511: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
512:
513: elif mode=="filepath":
514: # url points to image file, index.meta optional
515: # asssume index.meta is two path segments up
516: docUrl = getParentPath(url, 2)
517: metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
518:
519: else:
520: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
521: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
522:
523: docinfo['documentUrl'] = docUrl
524: # process index.meta contents
525: if metaDom is not None and metaDom.tag == 'resource':
526: # document directory name and path
527: resource = self.metadataService.getResourceData(dom=metaDom)
528: if resource:
529: docinfo = self.getDocinfoFromResource(docinfo, resource)
530:
531: # texttool info
532: texttool = self.metadataService.getTexttoolData(dom=metaDom)
533: if texttool:
534: docinfo = self.getDocinfoFromTexttool(docinfo, texttool)
535:
536: # bib info
537: bib = self.metadataService.getBibData(dom=metaDom)
538: if bib:
539: docinfo = self.getDocinfoFromBib(docinfo, bib)
540: else:
541: # no bib - try info.xml
542: docinfo = self.getDocinfoFromPresentationInfoXml(docinfo)
543:
544: # auth info
545: access = self.metadataService.getAccessData(dom=metaDom)
546: if access:
547: docinfo = self.getDocinfoFromAccess(docinfo, access)
548:
549: # attribution info
550: attribution = self.metadataService.getAttributionData(dom=metaDom)
551: if attribution:
552: logging.debug("getDocinfo: attribution=%s"%repr(attribution))
553: docinfo['attribution'] = attribution
554: #docinfo = self.getDocinfoFromAccess(docinfo, access)
555:
556: # copyright info
557: copyright = self.metadataService.getCopyrightData(dom=metaDom)
558: if copyright:
559: logging.debug("getDocinfo: copyright=%s"%repr(copyright))
560: docinfo['copyright'] = copyright
561: #docinfo = self.getDocinfoFromAccess(docinfo, access)
562:
563: # image path
564: if mode != 'texttool':
565: # override image path from texttool with url
566: docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1)
567:
568: # number of images from digilib
569: if docinfo.get('imagePath', None):
570: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath']
571: docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath'])
572:
573: logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
574: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
575: # store in session
576: self.REQUEST.SESSION['docinfo'] = docinfo
577: return docinfo
578:
579: def getDocinfoFromResource(self, docinfo, resource):
580: """reads contents of resource element into docinfo"""
581: docName = resource.get('name', None)
582: docinfo['documentName'] = docName
583: docPath = resource.get('archive-path', None)
584: if docPath:
585: # clean up document path
586: if docPath[0] != '/':
587: docPath = '/' + docPath
588:
589: if docName and (not docPath.endswith(docName)):
590: docPath += "/" + docName
591:
592: else:
593: # use docUrl as docPath
594: docUrl = docinfo['documentURL']
595: if not docUrl.startswith('http:'):
596: docPath = docUrl
597: if docPath:
598: # fix URLs starting with /mpiwg/online
599: docPath = docPath.replace('/mpiwg/online', '', 1)
600:
601: docinfo['documentPath'] = docPath
602: return docinfo
603:
604: def getDocinfoFromTexttool(self, docinfo, texttool):
605: """reads contents of texttool element into docinfo"""
606: # image dir
607: imageDir = texttool.get('image', None)
608: docPath = docinfo.get('documentPath', None)
609: if imageDir and docPath:
610: #print "image: ", imageDir, " archivepath: ", archivePath
611: imageDir = os.path.join(docPath, imageDir)
612: imageDir = imageDir.replace('/mpiwg/online', '', 1)
613: docinfo['imagePath'] = imageDir
614:
615: # old style text URL
616: textUrl = texttool.get('text', None)
617: if textUrl and docPath:
618: if urlparse.urlparse(textUrl)[0] == "": #keine url
619: textUrl = os.path.join(docPath, textUrl)
620:
621: docinfo['textURL'] = textUrl
622:
623: # new style text-url-path
624: textUrl = texttool.get('text-url-path', None)
625: if textUrl:
626: docinfo['textURLPath'] = textUrl
627:
628: # page flow
629: docinfo['pageFlow'] = texttool.get('page-flow', 'ltr')
630:
631: # odd pages are left
632: docinfo['oddPage'] = texttool.get('odd-scan-position', 'left')
633:
634: # number of title page (0: not defined)
635: docinfo['titlePage'] = texttool.get('title-scan-no', 0)
636:
637: # old presentation stuff
638: presentation = texttool.get('presentation', None)
639: if presentation and docPath:
640: if presentation.startswith('http:'):
641: docinfo['presentationUrl'] = presentation
642: else:
643: docinfo['presentationUrl'] = os.path.join(docPath, presentation)
644:
645:
646: return docinfo
647:
648: def getDocinfoFromBib(self, docinfo, bib):
649: """reads contents of bib element into docinfo"""
650: logging.debug("getDocinfoFromBib bib=%s"%repr(bib))
651: # put all raw bib fields in dict "bib"
652: docinfo['bib'] = bib
653: bibtype = bib.get('@type', None)
654: docinfo['bibType'] = bibtype
655: # also store DC metadata for convenience
656: dc = self.metadataService.getDCMappedData(bib)
657: docinfo['creator'] = dc.get('creator',None)
658: docinfo['title'] = dc.get('title',None)
659: docinfo['date'] = dc.get('date',None)
660: return docinfo
661:
662: def getDocinfoFromAccess(self, docinfo, acc):
663: """reads contents of access element into docinfo"""
664: #TODO: also read resource type
665: logging.debug("getDocinfoFromAccess acc=%s"%repr(acc))
666: try:
667: acctype = acc['@attr']['type']
668: if acctype:
669: access=acctype
670: if access in ['group', 'institution']:
671: access = acc['name'].lower()
672:
673: docinfo['accessType'] = access
674:
675: except:
676: pass
677:
678: return docinfo
679:
680: def getDocinfoFromDigilib(self, docinfo, path):
681: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
682: # fetch data
683: txt = getHttpData(infoUrl)
684: if not txt:
685: logging.error("Unable to get dir-info from %s"%(infoUrl))
686: return docinfo
687:
688: dom = ET.fromstring(txt)
689: size = getText(dom.find("size"))
690: logging.debug("getDocinfoFromDigilib: size=%s"%size)
691: if size:
692: docinfo['numPages'] = int(size)
693: else:
694: docinfo['numPages'] = 0
695:
696: # TODO: produce and keep list of image names and numbers
697: return docinfo
698:
699:
700: def getDocinfoFromPresentationInfoXml(self,docinfo):
701: """gets DC-like bibliographical information from the presentation entry in texttools"""
702: url = docinfo.get('presentationUrl', None)
703: if not url:
704: logging.error("getDocinfoFromPresentation: no URL!")
705: return docinfo
706:
707: dom = None
708: metaUrl = None
709: if url.startswith("http://"):
710: # real URL
711: metaUrl = url
712: else:
713: # online path
714:
715: server=self.digilibBaseUrl+"/servlet/Texter?fn="
716: metaUrl=server+url
717:
718: txt=getHttpData(metaUrl)
719: if txt is None:
720: logging.error("Unable to read info.xml from %s"%(url))
721: return docinfo
722:
723: dom = ET.fromstring(txt)
724: docinfo['creator']=getText(dom.find(".//author"))
725: docinfo['title']=getText(dom.find(".//title"))
726: docinfo['date']=getText(dom.find(".//date"))
727: return docinfo
728:
729:
730: def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None):
731: """returns pageinfo with the given parameters"""
732: logging.debug("getPageInfo(current=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewType=%s, tocMode=%s)"%(current,start,rows,cols,viewMode,viewType,tocMode))
733: pageinfo = {}
734: pageinfo['viewMode'] = viewMode
735: pageinfo['viewType'] = viewType
736: pageinfo['tocMode'] = tocMode
737:
738: current = getInt(current)
739: pageinfo['current'] = current
740: pageinfo['pn'] = current
741: rows = int(rows or self.thumbrows)
742: pageinfo['rows'] = rows
743: cols = int(cols or self.thumbcols)
744: pageinfo['cols'] = cols
745: grpsize = cols * rows
746: pageinfo['groupsize'] = grpsize
747: # is start is empty use one around current
748: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
749: # int(current / grpsize) * grpsize +1))
750: pageinfo['start'] = start
751:
752: np = int(docinfo.get('numPages', 0))
753: if np == 0:
754: # numPages unknown - maybe we can get it from text page
755: if docinfo.get('textURLPath', None):
756: # cache text page as well
757: pageinfo['textPage'] = self.getTextPage(mode=viewType, pn=current, docinfo=docinfo, pageinfo=pageinfo)
758: np = int(docinfo.get('numPages', 0))
759:
760: pageinfo['numgroups'] = int(np / grpsize)
761: if np % grpsize > 0:
762: pageinfo['numgroups'] += 1
763:
764: pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl'
765: oddScanLeft = docinfo.get('oddPage', 'left') != 'right'
766: # add zeroth page for two columns
767: pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft))
768: pageinfo['pageZero'] = pageZero
769: pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np)
770:
771: # TODO: do we need this here?
772: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
773: pageinfo['query'] = self.REQUEST.get('query','')
774: pageinfo['queryType'] = self.REQUEST.get('queryType','')
775: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
776: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
777: pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30))
778: pageinfo['queryPageSize'] = getInt(self.REQUEST.get('queryPageSize', 10))
779: pageinfo['tocPN'] = getInt(self.REQUEST.get('tocPN', '1'))
780: pageinfo['searchPN'] = getInt(self.REQUEST.get('searchPN','1'))
781:
782: # limit tocPN
783: if 'tocSize_%s'%tocMode in docinfo:
784: tocSize = docinfo['tocSize_%s'%tocMode]
785: tocPageSize = pageinfo['tocPageSize']
786: # cached toc
787: if tocSize%tocPageSize>0:
788: tocPages=tocSize/tocPageSize+1
789: else:
790: tocPages=tocSize/tocPageSize
791:
792: pageinfo['tocPN'] = min(tocPages,pageinfo['tocPN'])
793:
794: return pageinfo
795:
796:
797: def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0):
798: """returns dict with array of page informations for one screenfull of thumbnails"""
799: batch = {}
800: grpsize = rows * cols
801: if maxIdx == 0:
802: maxIdx = start + grpsize
803:
804: nb = int(math.ceil(maxIdx / float(grpsize)))
805: # list of all batch start and end points
806: batches = []
807: if pageZero:
808: ofs = 0
809: else:
810: ofs = 1
811:
812: for i in range(nb):
813: s = i * grpsize + ofs
814: e = min((i + 1) * grpsize + ofs - 1, maxIdx)
815: batches.append({'start':s, 'end':e})
816:
817: batch['batches'] = batches
818:
819: pages = []
820: if pageZero and start == 1:
821: # correct beginning
822: idx = 0
823: else:
824: idx = start
825:
826: for r in range(rows):
827: row = []
828: for c in range(cols):
829: if idx < minIdx or idx > maxIdx:
830: page = {'idx':None}
831: else:
832: page = {'idx':idx}
833:
834: idx += 1
835: if pageFlowLtr:
836: row.append(page)
837: else:
838: row.insert(0, page)
839:
840: pages.append(row)
841:
842: if start > 1:
843: batch['prevStart'] = max(start - grpsize, 1)
844: else:
845: batch['prevStart'] = None
846:
847: if start + grpsize < maxIdx:
848: batch['nextStart'] = start + grpsize
849: else:
850: batch['nextStart'] = None
851:
852: batch['pages'] = pages
853: return batch
854:
855: def getBatch(self, start=1, size=10, end=0, data=None, fullData=True):
856: """returns dict with information for one screenfull of data."""
857: batch = {}
858: if end == 0:
859: end = start + size
860:
861: nb = int(math.ceil(end / float(size)))
862: # list of all batch start and end points
863: batches = []
864: for i in range(nb):
865: s = i * size + 1
866: e = min((i + 1) * size, end)
867: batches.append({'start':s, 'end':e})
868:
869: batch['batches'] = batches
870: # list of elements in this batch
871: this = []
872: j = 0
873: for i in range(start, min(start+size, end)):
874: if data:
875: if fullData:
876: d = data[i]
877: else:
878: d = data[j]
879: j += 1
880:
881: else:
882: d = i+1
883:
884: this.append(d)
885:
886: batch['this'] = this
887: if start > 1:
888: batch['prevStart'] = max(start - size, 1)
889: else:
890: batch['prevStart'] = None
891:
892: if start + size < end:
893: batch['nextStart'] = start + size
894: else:
895: batch['nextStart'] = None
896:
897: return batch
898:
899:
900: security.declareProtected('View management screens','changeDocumentViewerForm')
901: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
902:
903: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
904: """init document viewer"""
905: self.title=title
906: self.digilibBaseUrl = digilibBaseUrl
907: self.thumbrows = thumbrows
908: self.thumbcols = thumbcols
909: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
910: try:
911: # assume MetaDataFolder instance is called metadata
912: self.metadataService = getattr(self, 'metadata')
913: except Exception, e:
914: logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
915:
916: if RESPONSE is not None:
917: RESPONSE.redirect('manage_main')
918:
919: def manage_AddDocumentViewerForm(self):
920: """add the viewer form"""
921: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
922: return pt()
923:
924: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
925: """add the viewer"""
926: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
927: self._setObject(id,newObj)
928:
929: if RESPONSE is not None:
930: 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