1:
2: from OFS.Folder import Folder
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: import os.path
12: import sys
13: import urllib
14: import urllib2
15: import logging
16: import math
17: import urlparse
18: import cStringIO
19:
20: def logger(txt,method,txt2):
21: """logging"""
22: logging.info(txt+ txt2)
23:
24:
25: def getInt(number, default=0):
26: """returns always an int (0 in case of problems)"""
27: try:
28: return int(number)
29: except:
30: return int(default)
31:
32: def getTextFromNode(nodename):
33: """get the cdata content of a node"""
34: if nodename is None:
35: return ""
36: nodelist=nodename.childNodes
37: rc = ""
38: for node in nodelist:
39: if node.nodeType == node.TEXT_NODE:
40: rc = rc + node.data
41: return rc
42:
43: def serializeNode(node, encoding='utf-8'):
44: """returns a string containing node as XML"""
45: buf = cStringIO.StringIO()
46: Print(node, stream=buf, encoding=encoding)
47: s = buf.getvalue()
48: buf.close()
49: return s
50:
51:
52: def getParentDir(path):
53: """returns pathname shortened by one"""
54: return '/'.join(path.split('/')[0:-1])
55:
56:
57: def getHttpData(url, data=None, num_tries=3, timeout=10):
58: """returns result from url+data HTTP request"""
59: # we do GET (by appending data to url)
60: if isinstance(data, str) or isinstance(data, unicode):
61: # if data is string then append
62: url = "%s?%s"%(url,data)
63: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
64: # urlencode
65: url = "%s?%s"%(url,urllib.urlencode(data))
66:
67: response = None
68: errmsg = None
69: for cnt in range(num_tries):
70: try:
71: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
72: if sys.version_info < (2, 6):
73: # set timeout on socket -- ugly :-(
74: import socket
75: socket.setdefaulttimeout(float(timeout))
76: response = urllib2.urlopen(url)
77: else:
78: response = urllib2.urlopen(url,timeout=float(timeout))
79: # check result?
80: break
81: except urllib2.HTTPError, e:
82: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
83: errmsg = str(e)
84: # stop trying
85: break
86: except urllib2.URLError, e:
87: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
88: errmsg = str(e)
89: # stop trying
90: #break
91:
92: if response is not None:
93: data = response.read()
94: response.close()
95: return data
96:
97: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
98: #return None
99:
100:
101:
102: ##
103: ## documentViewer class
104: ##
105: class documentViewer(Folder):
106: """document viewer"""
107: meta_type="Document viewer"
108:
109: security=ClassSecurityInfo()
110: manage_options=Folder.manage_options+(
111: {'label':'main config','action':'changeDocumentViewerForm'},
112: )
113:
114: # templates and forms
115: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
116: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
117: toc_text = PageTemplateFile('zpt/toc_text', globals())
118: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
119: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
120: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
121: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
122: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
123: head_main = PageTemplateFile('zpt/head_main', globals())
124: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
125: info_xml = PageTemplateFile('zpt/info_xml', globals())
126:
127:
128: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
129: security.declareProtected('View management screens','changeDocumentViewerForm')
130: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
131:
132:
133: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
134: """init document viewer"""
135: self.id=id
136: self.title=title
137: self.thumbcols = thumbcols
138: self.thumbrows = thumbrows
139: # authgroups is list of authorized groups (delimited by ,)
140: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
141: # create template folder so we can always use template.something
142:
143: templateFolder = Folder('template')
144: #self['template'] = templateFolder # Zope-2.12 style
145: self._setObject('template',templateFolder) # old style
146: try:
147: import MpdlXmlTextServer
148: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
149: #templateFolder['fulltextclient'] = xmlRpcClient
150: templateFolder._setObject('fulltextclient',textServer)
151: except Exception, e:
152: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
153: try:
154: from Products.zogiLib.zogiLib import zogiLib
155: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
156: #templateFolder['zogilib'] = zogilib
157: templateFolder._setObject('zogilib',zogilib)
158: except Exception, e:
159: logging.error("Unable to create zogiLib for zogilib: "+str(e))
160:
161:
162: # proxy text server methods to fulltextclient
163: def getTextPage(self, **args):
164: """get page"""
165: return self.template.fulltextclient.getTextPage(**args)
166:
167: def getQuery(self, **args):
168: """get query"""
169: return self.template.fulltextclient.getQuery(**args)
170:
171: def getSearch(self, **args):
172: """get search"""
173: return self.template.fulltextclient.getSearch(**args)
174:
175: def getNumPages(self, docinfo):
176: """get numpages"""
177: return self.template.fulltextclient.getNumPages(docinfo)
178:
179: def getTranslate(self, **args):
180: """get translate"""
181: return self.template.fulltextclient.getTranslate(**args)
182:
183: def getLemma(self, **args):
184: """get lemma"""
185: return self.template.fulltextclient.getLemma(**args)
186:
187: def getToc(self, **args):
188: """get toc"""
189: return self.template.fulltextclient.getToc(**args)
190:
191: def getTocPage(self, **args):
192: """get tocpage"""
193: return self.template.fulltextclient.getTocPage(**args)
194:
195:
196: security.declareProtected('View','thumbs_rss')
197: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
198: '''
199: view it
200: @param mode: defines how to access the document behind url
201: @param url: url which contains display information
202: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
203:
204: '''
205: logging.debug("HHHHHHHHHHHHHH:load the rss")
206: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
207:
208: if not hasattr(self, 'template'):
209: # create template folder if it doesn't exist
210: self.manage_addFolder('template')
211:
212: if not self.digilibBaseUrl:
213: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
214:
215: docinfo = self.getDocinfo(mode=mode,url=url)
216: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
217: pt = getattr(self.template, 'thumbs_main_rss')
218:
219: if viewMode=="auto": # automodus gewaehlt
220: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
221: viewMode="text"
222: else:
223: viewMode="images"
224:
225: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
226:
227: security.declareProtected('View','index_html')
228: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
229: '''
230: view it
231: @param mode: defines how to access the document behind url
232: @param url: url which contains display information
233: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
234: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
235: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
236: '''
237:
238: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
239:
240: if not hasattr(self, 'template'):
241: # this won't work
242: logging.error("template folder missing!")
243: return "ERROR: template folder missing!"
244:
245: if not getattr(self, 'digilibBaseUrl', None):
246: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
247:
248: docinfo = self.getDocinfo(mode=mode,url=url)
249:
250: if tocMode != "thumbs":
251: # get table of contents
252: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
253:
254: if viewMode=="auto": # automodus gewaehlt
255: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
256: viewMode="text_dict"
257: else:
258: viewMode="images"
259:
260: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
261:
262: pt = getattr(self.template, 'viewer_main')
263: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
264:
265: def generateMarks(self,mk):
266: ret=""
267: if mk is None:
268: return ""
269: if not isinstance(mk, list):
270: mk=[mk]
271: for m in mk:
272: ret+="mk=%s"%m
273: return ret
274:
275:
276: def findDigilibUrl(self):
277: """try to get the digilib URL from zogilib"""
278: url = self.template.zogilib.getDLBaseUrl()
279: return url
280:
281: def getDocumentViewerURL(self):
282: """returns the URL of this instance"""
283: return self.absolute_url()
284:
285: def getStyle(self, idx, selected, style=""):
286: """returns a string with the given style and append 'sel' if path == selected."""
287: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
288: if idx == selected:
289: return style + 'sel'
290: else:
291: return style
292:
293: def getLink(self,param=None,val=None):
294: """link to documentviewer with parameter param set to val"""
295: params=self.REQUEST.form.copy()
296: if param is not None:
297: if val is None:
298: if params.has_key(param):
299: del params[param]
300: else:
301: params[param] = str(val)
302:
303: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
304: params["mode"] = "imagepath"
305: params["url"] = getParentDir(params["url"])
306:
307: # quote values and assemble into query string
308: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
309: url=self.REQUEST['URL1']+"?"+ps
310: return url
311:
312: def getLinkAmp(self,param=None,val=None):
313: """link to documentviewer with parameter param set to val"""
314: params=self.REQUEST.form.copy()
315: if param is not None:
316: if val is None:
317: if params.has_key(param):
318: del params[param]
319: else:
320: params[param] = str(val)
321:
322: # quote values and assemble into query string
323: logging.debug("XYXXXXX: %s"%repr(params.items()))
324: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
325: url=self.REQUEST['URL1']+"?"+ps
326: return url
327:
328: def getInfo_xml(self,url,mode):
329: """returns info about the document as XML"""
330:
331: if not self.digilibBaseUrl:
332: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
333:
334: docinfo = self.getDocinfo(mode=mode,url=url)
335: pt = getattr(self.template, 'info_xml')
336: return pt(docinfo=docinfo)
337:
338:
339: def isAccessible(self, docinfo):
340: """returns if access to the resource is granted"""
341: access = docinfo.get('accessType', None)
342: logging.debug("documentViewer (accessOK) access type %s"%access)
343: if access is not None and access == 'free':
344: logging.debug("documentViewer (accessOK) access is free")
345: return True
346: elif access is None or access in self.authgroups:
347: # only local access -- only logged in users
348: user = getSecurityManager().getUser()
349: if user is not None:
350: #print "user: ", user
351: return (user.getUserName() != "Anonymous User")
352: else:
353: return False
354:
355: logging.debug("documentViewer (accessOK) unknown access type %s"%access)
356: return False
357:
358:
359: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
360: """gibt param von dlInfo aus"""
361: if docinfo is None:
362: docinfo = {}
363:
364: for x in range(cut):
365:
366: path=getParentDir(path)
367:
368: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
369:
370: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
371:
372: txt = getHttpData(infoUrl)
373: if txt is None:
374: raise IOError("Unable to get dir-info from %s"%(infoUrl))
375:
376: dom = Parse(txt)
377: sizes=dom.xpath("//dir/size")
378: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
379:
380: if sizes:
381: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
382: else:
383: docinfo['numPages'] = 0
384:
385: # TODO: produce and keep list of image names and numbers
386:
387: return docinfo
388:
389:
390: def getIndexMeta(self, url):
391: """returns dom of index.meta document at url"""
392: dom = None
393: metaUrl = None
394: if url.startswith("http://"):
395: # real URL
396: metaUrl = url
397: else:
398: # online path
399: server=self.digilibBaseUrl+"/servlet/Texter?fn="
400: metaUrl=server+url.replace("/mpiwg/online","")
401: if not metaUrl.endswith("index.meta"):
402: metaUrl += "/index.meta"
403:
404: logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)
405: txt=getHttpData(metaUrl)
406: if txt is None:
407: raise IOError("Unable to read index meta from %s"%(url))
408:
409: dom = Parse(txt)
410: return dom
411:
412: def getPresentationInfoXML(self, url):
413: """returns dom of info.xml document at url"""
414: dom = None
415: metaUrl = None
416: if url.startswith("http://"):
417: # real URL
418: metaUrl = url
419: else:
420: # online path
421: server=self.digilibBaseUrl+"/servlet/Texter?fn="
422: metaUrl=server+url.replace("/mpiwg/online","")
423:
424: txt=getHttpData(metaUrl)
425: if txt is None:
426: raise IOError("Unable to read infoXMLfrom %s"%(url))
427:
428: dom = Parse(txt)
429: return dom
430:
431:
432: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
433: """gets authorization info from the index.meta file at path or given by dom"""
434: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
435:
436: access = None
437:
438: if docinfo is None:
439: docinfo = {}
440:
441: if dom is None:
442: for x in range(cut):
443: path=getParentDir(path)
444: dom = self.getIndexMeta(path)
445:
446: acctype = dom.xpath("//access-conditions/access/@type")
447: if acctype and (len(acctype)>0):
448: access=acctype[0].value
449: if access in ['group', 'institution']:
450: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
451:
452: docinfo['accessType'] = access
453: return docinfo
454:
455:
456: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
457: """gets bibliographical info from the index.meta file at path or given by dom"""
458: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
459:
460: if docinfo is None:
461: docinfo = {}
462:
463: if dom is None:
464: for x in range(cut):
465: path=getParentDir(path)
466: dom = self.getIndexMeta(path)
467:
468: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
469: # put in all raw bib fields as dict "bib"
470: bib = dom.xpath("//bib/*")
471: if bib and len(bib)>0:
472: bibinfo = {}
473: for e in bib:
474: bibinfo[e.localName] = getTextFromNode(e)
475: docinfo['bib'] = bibinfo
476:
477: # extract some fields (author, title, year) according to their mapping
478: metaData=self.metadata.main.meta.bib
479: bibtype=dom.xpath("//bib/@type")
480: if bibtype and (len(bibtype)>0):
481: bibtype=bibtype[0].value
482: else:
483: bibtype="generic"
484:
485: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
486: docinfo['bib_type'] = bibtype
487: bibmap=metaData.generateMappingForType(bibtype)
488: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
489: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
490: try:
491: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
492: except: pass
493: try:
494: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
495: except: pass
496: try:
497: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
498: except: pass
499: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
500: try:
501: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
502: except:
503: docinfo['lang']=''
504:
505: return docinfo
506:
507:
508: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
509: """parse texttool tag in index meta"""
510: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
511: if docinfo is None:
512: docinfo = {}
513: if docinfo.get('lang', None) is None:
514: docinfo['lang'] = '' # default keine Sprache gesetzt
515: if dom is None:
516: dom = self.getIndexMeta(url)
517:
518: archivePath = None
519: archiveName = None
520:
521: archiveNames = dom.xpath("//resource/name")
522: if archiveNames and (len(archiveNames) > 0):
523: archiveName = getTextFromNode(archiveNames[0])
524: else:
525: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
526:
527: archivePaths = dom.xpath("//resource/archive-path")
528: if archivePaths and (len(archivePaths) > 0):
529: archivePath = getTextFromNode(archivePaths[0])
530: # clean up archive path
531: if archivePath[0] != '/':
532: archivePath = '/' + archivePath
533: if archiveName and (not archivePath.endswith(archiveName)):
534: archivePath += "/" + archiveName
535: else:
536: # try to get archive-path from url
537: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
538: if (not url.startswith('http')):
539: archivePath = url.replace('index.meta', '')
540:
541: if archivePath is None:
542: # we balk without archive-path
543: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
544:
545: imageDirs = dom.xpath("//texttool/image")
546: if imageDirs and (len(imageDirs) > 0):
547: imageDir = getTextFromNode(imageDirs[0])
548:
549: else:
550: # we balk with no image tag / not necessary anymore because textmode is now standard
551: #raise IOError("No text-tool info in %s"%(url))
552: imageDir = ""
553: #xquery="//pb"
554: docinfo['imagePath'] = "" # keine Bilder
555: docinfo['imageURL'] = ""
556:
557: if imageDir and archivePath:
558: #print "image: ", imageDir, " archivepath: ", archivePath
559: imageDir = os.path.join(archivePath, imageDir)
560: imageDir = imageDir.replace("/mpiwg/online", '')
561: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
562: docinfo['imagePath'] = imageDir
563:
564: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
565:
566: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
567: if viewerUrls and (len(viewerUrls) > 0):
568: viewerUrl = getTextFromNode(viewerUrls[0])
569: docinfo['viewerURL'] = viewerUrl
570:
571: # old style text URL
572: textUrls = dom.xpath("//texttool/text")
573: if textUrls and (len(textUrls) > 0):
574: textUrl = getTextFromNode(textUrls[0])
575: if urlparse.urlparse(textUrl)[0] == "": #keine url
576: textUrl = os.path.join(archivePath, textUrl)
577: # fix URLs starting with /mpiwg/online
578: if textUrl.startswith("/mpiwg/online"):
579: textUrl = textUrl.replace("/mpiwg/online", '', 1)
580:
581: docinfo['textURL'] = textUrl
582:
583: # new style text-url-path
584: textUrls = dom.xpath("//texttool/text-url-path")
585: if textUrls and (len(textUrls) > 0):
586: textUrl = getTextFromNode(textUrls[0])
587: docinfo['textURLPath'] = textUrl
588: if not docinfo['imagePath']:
589: # text-only, no page images
590: docinfo = self.getNumPages(docinfo)
591:
592: presentationUrls = dom.xpath("//texttool/presentation")
593: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
594:
595: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
596: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
597: # durch den relativen Pfad auf die presentation infos
598: presentationPath = getTextFromNode(presentationUrls[0])
599: if url.endswith("index.meta"):
600: presentationUrl = url.replace('index.meta', presentationPath)
601: else:
602: presentationUrl = url + "/" + presentationPath
603:
604: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
605:
606: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
607:
608: return docinfo
609:
610:
611: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
612: """gets the bibliographical information from the preseantion entry in texttools
613: """
614: dom=self.getPresentationInfoXML(url)
615: try:
616: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
617: except:
618: pass
619: try:
620: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
621: except:
622: pass
623: try:
624: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
625: except:
626: pass
627: return docinfo
628:
629: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
630: """path ist the path to the images it assumes that the index.meta file is one level higher."""
631: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
632: if docinfo is None:
633: docinfo = {}
634: path=path.replace("/mpiwg/online","")
635: docinfo['imagePath'] = path
636: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
637:
638: pathorig=path
639: for x in range(cut):
640: path=getParentDir(path)
641: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
642: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
643: docinfo['imageURL'] = imageUrl
644:
645: #path ist the path to the images it assumes that the index.meta file is one level higher.
646: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
647: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
648: return docinfo
649:
650:
651: def getDocinfo(self, mode, url):
652: """returns docinfo depending on mode"""
653: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
654: # look for cached docinfo in session
655: if self.REQUEST.SESSION.has_key('docinfo'):
656: docinfo = self.REQUEST.SESSION['docinfo']
657: # check if its still current
658: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
659: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
660: return docinfo
661: # new docinfo
662: docinfo = {'mode': mode, 'url': url}
663: if mode=="texttool": #index.meta with texttool information
664: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
665: elif mode=="imagepath":
666: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
667: elif mode=="filepath":
668: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
669: else:
670: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
671: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
672:
673: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
674: self.REQUEST.SESSION['docinfo'] = docinfo
675: return docinfo
676:
677: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
678: """returns pageinfo with the given parameters"""
679: pageinfo = {}
680: current = getInt(current)
681: pageinfo['current'] = current
682: rows = int(rows or self.thumbrows)
683: pageinfo['rows'] = rows
684: cols = int(cols or self.thumbcols)
685: pageinfo['cols'] = cols
686: grpsize = cols * rows
687: pageinfo['groupsize'] = grpsize
688: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
689: # int(current / grpsize) * grpsize +1))
690: pageinfo['start'] = start
691: pageinfo['end'] = start + grpsize
692: if (docinfo is not None) and ('numPages' in docinfo):
693: np = int(docinfo['numPages'])
694: pageinfo['end'] = min(pageinfo['end'], np)
695: pageinfo['numgroups'] = int(np / grpsize)
696: if np % grpsize > 0:
697: pageinfo['numgroups'] += 1
698: pageinfo['viewMode'] = viewMode
699: pageinfo['tocMode'] = tocMode
700: pageinfo['query'] = self.REQUEST.get('query',' ')
701: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
702: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
703: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
704: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
705: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
706: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
707: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
708: toc = int (pageinfo['tocPN'])
709: pageinfo['textPages'] =int (toc)
710:
711: if 'tocSize_%s'%tocMode in docinfo:
712: tocSize = int(docinfo['tocSize_%s'%tocMode])
713: tocPageSize = int(pageinfo['tocPageSize'])
714: # cached toc
715: if tocSize%tocPageSize>0:
716: tocPages=tocSize/tocPageSize+1
717: else:
718: tocPages=tocSize/tocPageSize
719: pageinfo['tocPN'] = min (tocPages,toc)
720: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
721: pageinfo['sn'] =self.REQUEST.get('sn','')
722: return pageinfo
723:
724: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
725: """init document viewer"""
726: self.title=title
727: self.digilibBaseUrl = digilibBaseUrl
728: self.thumbrows = thumbrows
729: self.thumbcols = thumbcols
730: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
731: if RESPONSE is not None:
732: RESPONSE.redirect('manage_main')
733:
734: def manage_AddDocumentViewerForm(self):
735: """add the viewer form"""
736: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
737: return pt()
738:
739: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
740: """add the viewer"""
741: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
742: self._setObject(id,newObj)
743:
744: if RESPONSE is not None:
745: RESPONSE.redirect('manage_main')
746:
747: ## DocumentViewerTemplate class
748: class DocumentViewerTemplate(ZopePageTemplate):
749: """Template for document viewer"""
750: meta_type="DocumentViewer Template"
751:
752:
753: def manage_addDocumentViewerTemplateForm(self):
754: """Form for adding"""
755: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
756: return pt()
757:
758: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
759: REQUEST=None, submit=None):
760: "Add a Page Template with optional file content."
761:
762: self._setObject(id, DocumentViewerTemplate(id))
763: ob = getattr(self, id)
764: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
765: logging.info("txt %s:"%txt)
766: ob.pt_edit(txt,"text/html")
767: if title:
768: ob.pt_setTitle(title)
769: try:
770: u = self.DestinationURL()
771: except AttributeError:
772: u = REQUEST['URL1']
773:
774: u = "%s/%s" % (u, urllib.quote(id))
775: REQUEST.RESPONSE.redirect(u+'/manage_main')
776: return ''
777:
778:
779:
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