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.Domlette import NonvalidatingReader
10: from Ft.Xml.Domlette import PrettyPrint, Print
11: from Ft.Xml import EMPTY_NAMESPACE, Parse
12:
13: from xml.dom.minidom import parse, parseString
14:
15:
16:
17: import Ft.Xml.XPath
18: import cStringIO
19: import xmlrpclib
20: import os.path
21: import sys
22: import cgi
23: import urllib
24: import logging
25: import math
26:
27: import urlparse
28: from types import *
29:
30: def logger(txt,method,txt2):
31: """logging"""
32: logging.info(txt+ txt2)
33:
34:
35: def getInt(number, default=0):
36: """returns always an int (0 in case of problems)"""
37: try:
38: return int(number)
39: except:
40: return int(default)
41:
42: def getTextFromNode(nodename):
43: """get the cdata content of a node"""
44: if nodename is None:
45: return ""
46: nodelist=nodename.childNodes
47: rc = ""
48: for node in nodelist:
49: if node.nodeType == node.TEXT_NODE:
50: rc = rc + node.data
51: return rc
52:
53: def serializeNode(node, encoding='utf-8'):
54: """returns a string containing node as XML"""
55: buf = cStringIO.StringIO()
56: Print(node, stream=buf, encoding=encoding)
57: s = buf.getvalue()
58: buf.close()
59: return s
60:
61:
62: def getParentDir(path):
63: """returns pathname shortened by one"""
64: return '/'.join(path.split('/')[0:-1])
65:
66:
67: import socket
68:
69: def urlopen(url,timeout=2):
70: """urlopen mit timeout"""
71: socket.setdefaulttimeout(timeout)
72: ret=urllib.urlopen(url)
73: socket.setdefaulttimeout(5)
74: return ret
75:
76:
77: ##
78: ## documentViewer class
79: ##
80: class documentViewer(Folder):
81: """document viewer"""
82: #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"
83:
84: meta_type="Document viewer"
85:
86: security=ClassSecurityInfo()
87: manage_options=Folder.manage_options+(
88: {'label':'main config','action':'changeDocumentViewerForm'},
89: )
90:
91: # templates and forms
92: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
93: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
94: toc_text = PageTemplateFile('zpt/toc_text', globals())
95: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
96: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
97: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
98: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
99: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
100: head_main = PageTemplateFile('zpt/head_main', globals())
101: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
102: info_xml = PageTemplateFile('zpt/info_xml', globals())
103:
104: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
105: security.declareProtected('View management screens','changeDocumentViewerForm')
106: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
107:
108:
109: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
110: """init document viewer"""
111: self.id=id
112: self.title=title
113: self.thumbcols = thumbcols
114: self.thumbrows = thumbrows
115: # authgroups is list of authorized groups (delimited by ,)
116: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
117: # create template folder so we can always use template.something
118:
119: templateFolder = Folder('template')
120: #self['template'] = templateFolder # Zope-2.12 style
121: self._setObject('template',templateFolder) # old style
122: try:
123: from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy
124: xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False)
125: #templateFolder['fulltextclient'] = xmlRpcClient
126: templateFolder._setObject('fulltextclient',xmlRpcClient)
127: except Exception, e:
128: logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e))
129: try:
130: from Products.zogiLib.zogiLib import zogiLib
131: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
132: #templateFolder['zogilib'] = zogilib
133: templateFolder._setObject('zogilib',zogilib)
134: except Exception, e:
135: logging.error("Unable to create zogiLib for zogilib: "+str(e))
136:
137:
138: security.declareProtected('View','thumbs_rss')
139: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
140: '''
141: view it
142: @param mode: defines how to access the document behind url
143: @param url: url which contains display information
144: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
145:
146: '''
147: logging.debug("HHHHHHHHHHHHHH:load the rss")
148: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
149:
150: if not hasattr(self, 'template'):
151: # create template folder if it doesn't exist
152: self.manage_addFolder('template')
153:
154: if not self.digilibBaseUrl:
155: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
156:
157: docinfo = self.getDocinfo(mode=mode,url=url)
158: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
159: pt = getattr(self.template, 'thumbs_main_rss')
160:
161: if viewMode=="auto": # automodus gewaehlt
162: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
163: viewMode="text"
164: else:
165: viewMode="images"
166:
167: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
168:
169: security.declareProtected('View','index_html')
170: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
171: '''
172: view it
173: @param mode: defines how to access the document behind url
174: @param url: url which contains display information
175: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
176: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
177: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
178: '''
179:
180: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
181:
182: if not hasattr(self, 'template'):
183: # this won't work
184: logging.error("template folder missing!")
185: return "ERROR: template folder missing!"
186:
187: if not getattr(self, 'digilibBaseUrl', None):
188: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
189:
190: docinfo = self.getDocinfo(mode=mode,url=url)
191:
192:
193: if tocMode != "thumbs":
194: # get table of contents
195: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
196:
197: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
198:
199: if viewMode=="auto": # automodus gewaehlt
200: if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
201: viewMode="text"
202: else:
203: viewMode="images"
204:
205: pt = getattr(self.template, 'viewer_main')
206: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
207:
208: def generateMarks(self,mk):
209: ret=""
210: if mk is None:
211: return ""
212: if type(mk) is not ListType:
213: mk=[mk]
214: for m in mk:
215: ret+="mk=%s"%m
216: return ret
217:
218:
219: def findDigilibUrl(self):
220: """try to get the digilib URL from zogilib"""
221: url = self.template.zogilib.getDLBaseUrl()
222: return url
223:
224: def getStyle(self, idx, selected, style=""):
225: """returns a string with the given style and append 'sel' if path == selected."""
226: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
227: if idx == selected:
228: return style + 'sel'
229: else:
230: return style
231:
232: def getLink(self,param=None,val=None):
233: """link to documentviewer with parameter param set to val"""
234: params=self.REQUEST.form.copy()
235: if param is not None:
236: if val is None:
237: if params.has_key(param):
238: del params[param]
239: else:
240: params[param] = str(val)
241:
242: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
243: params["mode"] = "imagepath"
244: params["url"] = getParentDir(params["url"])
245:
246: # quote values and assemble into query string
247: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
248: url=self.REQUEST['URL1']+"?"+ps
249: return url
250:
251: def getLinkAmp(self,param=None,val=None):
252: """link to documentviewer with parameter param set to val"""
253: params=self.REQUEST.form.copy()
254: if param is not None:
255: if val is None:
256: if params.has_key(param):
257: del params[param]
258: else:
259: params[param] = str(val)
260:
261: # quote values and assemble into query string
262: logging.info("XYXXXXX: %s"%repr(params.items()))
263: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
264: url=self.REQUEST['URL1']+"?"+ps
265: return url
266:
267: def getInfo_xml(self,url,mode):
268: """returns info about the document as XML"""
269:
270: if not self.digilibBaseUrl:
271: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
272:
273: docinfo = self.getDocinfo(mode=mode,url=url)
274: pt = getattr(self.template, 'info_xml')
275: return pt(docinfo=docinfo)
276:
277:
278: def isAccessible(self, docinfo):
279: """returns if access to the resource is granted"""
280: access = docinfo.get('accessType', None)
281: logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)
282: if access is not None and access == 'free':
283: logger("documentViewer (accessOK)", logging.INFO, "access is free")
284: return True
285: elif access is None or access in self.authgroups:
286: # only local access -- only logged in users
287: user = getSecurityManager().getUser()
288: if user is not None:
289: #print "user: ", user
290: return (user.getUserName() != "Anonymous User")
291: else:
292: return False
293:
294: logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)
295: return False
296:
297:
298: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
299: """gibt param von dlInfo aus"""
300: num_retries = 3
301: if docinfo is None:
302: docinfo = {}
303:
304: for x in range(cut):
305:
306: path=getParentDir(path)
307:
308: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
309:
310: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))
311:
312: for cnt in range(num_retries):
313: try:
314: # dom = NonvalidatingReader.parseUri(imageUrl)
315: txt=urllib.urlopen(infoUrl).read()
316: dom = Parse(txt)
317: break
318: except:
319: logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
320: else:
321: raise IOError("Unable to get dir-info from %s"%(infoUrl))
322:
323: sizes=dom.xpath("//dir/size")
324: logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)
325:
326: if sizes:
327: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
328: else:
329: docinfo['numPages'] = 0
330:
331: # TODO: produce and keep list of image names and numbers
332:
333: return docinfo
334:
335:
336: def getIndexMeta(self, url):
337: """returns dom of index.meta document at url"""
338: num_retries = 3
339: dom = None
340: metaUrl = None
341: if url.startswith("http://"):
342: # real URL
343: metaUrl = url
344: else:
345: # online path
346: server=self.digilibBaseUrl+"/servlet/Texter?fn="
347: metaUrl=server+url.replace("/mpiwg/online","")
348: if not metaUrl.endswith("index.meta"):
349: metaUrl += "/index.meta"
350: logging.debug("METAURL: %s"%metaUrl)
351: for cnt in range(num_retries):
352: try:
353: # patch dirk encoding fehler treten dann nicht mehr auf
354: # dom = NonvalidatingReader.parseUri(metaUrl)
355: txt=urllib.urlopen(metaUrl).read()
356: dom = Parse(txt)
357: break
358: except:
359: logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
360:
361: if dom is None:
362: raise IOError("Unable to read index meta from %s"%(url))
363:
364: return dom
365:
366: def getPresentationInfoXML(self, url):
367: """returns dom of info.xml document at url"""
368: num_retries = 3
369: dom = None
370: metaUrl = None
371: if url.startswith("http://"):
372: # real URL
373: metaUrl = url
374: else:
375: # online path
376: server=self.digilibBaseUrl+"/servlet/Texter?fn="
377: metaUrl=server+url.replace("/mpiwg/online","")
378:
379: for cnt in range(num_retries):
380: try:
381: # patch dirk encoding fehler treten dann nicht mehr auf
382: # dom = NonvalidatingReader.parseUri(metaUrl)
383: txt=urllib.urlopen(metaUrl).read()
384: dom = Parse(txt)
385: break
386: except:
387: logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
388:
389: if dom is None:
390: raise IOError("Unable to read infoXMLfrom %s"%(url))
391:
392: return dom
393:
394:
395: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
396: """gets authorization info from the index.meta file at path or given by dom"""
397: logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))
398:
399: access = None
400:
401: if docinfo is None:
402: docinfo = {}
403:
404: if dom is None:
405: for x in range(cut):
406: path=getParentDir(path)
407: dom = self.getIndexMeta(path)
408:
409: acctype = dom.xpath("//access-conditions/access/@type")
410: if acctype and (len(acctype)>0):
411: access=acctype[0].value
412: if access in ['group', 'institution']:
413: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
414:
415: docinfo['accessType'] = access
416: return docinfo
417:
418:
419: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
420: """gets bibliographical info from the index.meta file at path or given by dom"""
421: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
422:
423: if docinfo is None:
424: docinfo = {}
425:
426: if dom is None:
427: for x in range(cut):
428: path=getParentDir(path)
429: dom = self.getIndexMeta(path)
430:
431: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
432: # put in all raw bib fields as dict "bib"
433: bib = dom.xpath("//bib/*")
434: if bib and len(bib)>0:
435: bibinfo = {}
436: for e in bib:
437: bibinfo[e.localName] = getTextFromNode(e)
438: docinfo['bib'] = bibinfo
439:
440: # extract some fields (author, title, year) according to their mapping
441: metaData=self.metadata.main.meta.bib
442: bibtype=dom.xpath("//bib/@type")
443: if bibtype and (len(bibtype)>0):
444: bibtype=bibtype[0].value
445: else:
446: bibtype="generic"
447:
448: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
449: docinfo['bib_type'] = bibtype
450: bibmap=metaData.generateMappingForType(bibtype)
451: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
452: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
453: try:
454: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
455: except: pass
456: try:
457: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
458: except: pass
459: try:
460: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
461: except: pass
462: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
463: try:
464: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
465: except:
466: docinfo['lang']=''
467:
468: return docinfo
469:
470:
471: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
472: """parse texttool tag in index meta"""
473: logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url))
474: if docinfo is None:
475: docinfo = {}
476: if docinfo.get('lang', None) is None:
477: docinfo['lang'] = '' # default keine Sprache gesetzt
478: if dom is None:
479: dom = self.getIndexMeta(url)
480:
481: archivePath = None
482: archiveName = None
483:
484: archiveNames = dom.xpath("//resource/name")
485: if archiveNames and (len(archiveNames) > 0):
486: archiveName = getTextFromNode(archiveNames[0])
487: else:
488: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url))
489:
490: archivePaths = dom.xpath("//resource/archive-path")
491: if archivePaths and (len(archivePaths) > 0):
492: archivePath = getTextFromNode(archivePaths[0])
493: # clean up archive path
494: if archivePath[0] != '/':
495: archivePath = '/' + archivePath
496: if archiveName and (not archivePath.endswith(archiveName)):
497: archivePath += "/" + archiveName
498: else:
499: # try to get archive-path from url
500: logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url))
501: if (not url.startswith('http')):
502: archivePath = url.replace('index.meta', '')
503:
504: if archivePath is None:
505: # we balk without archive-path
506: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
507:
508: imageDirs = dom.xpath("//texttool/image")
509: if imageDirs and (len(imageDirs) > 0):
510: imageDir = getTextFromNode(imageDirs[0])
511:
512: else:
513: # we balk with no image tag / not necessary anymore because textmode is now standard
514: #raise IOError("No text-tool info in %s"%(url))
515: imageDir = ""
516: #xquery="//pb"
517: docinfo['imagePath'] = "" # keine Bilder
518: docinfo['imageURL'] = ""
519:
520: if imageDir and archivePath:
521: #print "image: ", imageDir, " archivepath: ", archivePath
522: imageDir = os.path.join(archivePath, imageDir)
523: imageDir = imageDir.replace("/mpiwg/online", '')
524: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
525: docinfo['imagePath'] = imageDir
526:
527: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
528:
529: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
530: if viewerUrls and (len(viewerUrls) > 0):
531: viewerUrl = getTextFromNode(viewerUrls[0])
532: docinfo['viewerURL'] = viewerUrl
533:
534: textUrls = dom.xpath("//texttool/text")
535: if textUrls and (len(textUrls) > 0):
536: textUrl = getTextFromNode(textUrls[0])
537: if urlparse.urlparse(textUrl)[0] == "": #keine url
538: textUrl = os.path.join(archivePath, textUrl)
539: # fix URLs starting with /mpiwg/online
540: if textUrl.startswith("/mpiwg/online"):
541: textUrl = textUrl.replace("/mpiwg/online", '', 1)
542:
543: docinfo['textURL'] = textUrl
544:
545: textUrls = dom.xpath("//texttool/text-url-path")
546: if textUrls and (len(textUrls) > 0):
547: textUrl = getTextFromNode(textUrls[0])
548: docinfo['textURLPath'] = textUrl
549:
550: presentationUrls = dom.xpath("//texttool/presentation")
551: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
552:
553: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
554: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
555: # durch den relativen Pfad auf die presentation infos
556: presentationPath = getTextFromNode(presentationUrls[0])
557: if url.endswith("index.meta"):
558: presentationUrl = url.replace('index.meta', presentationPath)
559: else:
560: presentationUrl = url + "/" + presentationPath
561: docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
562: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
563:
564: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
565:
566: return docinfo
567:
568:
569: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
570: """gets the bibliographical information from the preseantion entry in texttools
571: """
572: dom=self.getPresentationInfoXML(url)
573: try:
574: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
575: except:
576: pass
577: try:
578: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
579: except:
580: pass
581: try:
582: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
583: except:
584: pass
585: return docinfo
586:
587: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
588: """path ist the path to the images it assumes that the index.meta file is one level higher."""
589: logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))
590: if docinfo is None:
591: docinfo = {}
592: path=path.replace("/mpiwg/online","")
593: docinfo['imagePath'] = path
594: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
595:
596: pathorig=path
597: for x in range(cut):
598: path=getParentDir(path)
599: logging.error("PATH:"+path)
600: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
601: docinfo['imageURL'] = imageUrl
602:
603: #path ist the path to the images it assumes that the index.meta file is one level higher.
604: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
605: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
606: return docinfo
607:
608:
609: def getDocinfo(self, mode, url):
610: """returns docinfo depending on mode"""
611: logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))
612: # look for cached docinfo in session
613: if self.REQUEST.SESSION.has_key('docinfo'):
614: docinfo = self.REQUEST.SESSION['docinfo']
615: # check if its still current
616: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
617: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)
618: return docinfo
619: # new docinfo
620: docinfo = {'mode': mode, 'url': url}
621: if mode=="texttool": #index.meta with texttool information
622: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
623: elif mode=="imagepath":
624: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
625: elif mode=="filepath":
626: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
627: else:
628: logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
629: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
630:
631: logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
632: self.REQUEST.SESSION['docinfo'] = docinfo
633: return docinfo
634:
635:
636: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
637: """returns pageinfo with the given parameters"""
638: pageinfo = {}
639: current = getInt(current)
640: pageinfo['current'] = current
641: rows = int(rows or self.thumbrows)
642: pageinfo['rows'] = rows
643: cols = int(cols or self.thumbcols)
644: pageinfo['cols'] = cols
645: grpsize = cols * rows
646: pageinfo['groupsize'] = grpsize
647: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
648: # int(current / grpsize) * grpsize +1))
649: pageinfo['start'] = start
650: pageinfo['end'] = start + grpsize
651: if (docinfo is not None) and ('numPages' in docinfo):
652: np = int(docinfo['numPages'])
653: pageinfo['end'] = min(pageinfo['end'], np)
654: pageinfo['numgroups'] = int(np / grpsize)
655: if np % grpsize > 0:
656: pageinfo['numgroups'] += 1
657:
658:
659: pageinfo['viewMode'] = viewMode
660: pageinfo['tocMode'] = tocMode
661: pageinfo['query'] = self.REQUEST.get('query',' ')
662: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
663: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
664:
665: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
666:
667: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
668: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '20')
669: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
670: toc = int (pageinfo['tocPN'])
671: pageinfo['textPages'] =int (toc)
672:
673: if 'tocSize_%s'%tocMode in docinfo:
674: tocSize = int(docinfo['tocSize_%s'%tocMode])
675: tocPageSize = int(pageinfo['tocPageSize'])
676: # cached toc
677:
678: if tocSize%tocPageSize>0:
679: tocPages=tocSize/tocPageSize+1
680: else:
681: tocPages=tocSize/tocPageSize
682: pageinfo['tocPN'] = min (tocPages,toc)
683:
684: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
685: pageinfo['sn'] =self.REQUEST.get('sn','1')
686:
687: return pageinfo
688:
689: def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None):
690: """get search list"""
691: docpath = docinfo['textURLPath']
692: pagesize = pageinfo['queryPageSize']
693: pn = pageinfo['searchPN']
694: sn = pageinfo['sn']
695: query =pageinfo['query']
696: queryType =pageinfo['queryType']
697: viewMode= pageinfo['viewMode']
698: tocMode = pageinfo['tocMode']
699: tocPN = pageinfo['tocPN']
700: selfurl = self.absolute_url()
701: page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode) ,outputUnicode=False)
702: pagexml = page.replace('?document=/echo/la/Benedetti_1585.xml','?url=/mpiwg/online/permanent/library/163127KK')
703: #hrefNode.nodeValue =pagexml.replace('mode=text','%s&mode=texttool'%selfurl)
704: pagedom = Parse(pagexml)
705: #logging.debug("documentViewer (gettoc) pagedom: %s"%(pagedom))
706: if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):
707: pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
708: if len(pagedivs)>0:
709: pagenode=pagedivs[0]
710: links=pagenode.xpath("//a")
711: for l in links:
712: hrefNode = l.getAttributeNodeNS(None, u"href")
713: if hrefNode:
714: href = hrefNode.nodeValue
715: if href.startswith('page-fragment.xql'):
716: selfurl = self.absolute_url()
717: #l.setAttributeNS(None, "span class = 'hit highlight'", "background-color: #77DD77;")
718: pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN))
719: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
720: l.setAttributeNS(None, "span class = 'hit'", "background-color: #77DD77;")
721: return serializeNode(pagenode)
722:
723: if (queryType=="fulltextMorph"):
724: pagedivs = pagedom.xpath("//div[@class='queryResult']")
725:
726: if len(pagedivs)>0:
727: pagenode=pagedivs[0]
728: links=pagenode.xpath("//a")
729: for l in links:
730: hrefNode = l.getAttributeNodeNS(None, u"href")
731: if hrefNode:
732: href = hrefNode.nodeValue
733: if href.startswith('page-fragment.xql'):
734: selfurl = self.absolute_url()
735: pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN))
736: hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)
737: if href.startswith('../lt/lemma.xql'):
738: selfurl = self.absolute_url()
739: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
740: l.setAttributeNS(None, 'target', '_blank')
741: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
742: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
743: return serializeNode(pagenode)
744:
745: if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
746: pagedivs= pagedom.xpath("//div[@class='queryResultPage']")
747: if len(pagedivs)>0:
748: pagenode=pagedivs[0]
749: links=pagenode.xpath("//a")
750: for l in links:
751: hrefNode = l.getAttributeNodeNS(None, u"href")
752: if hrefNode:
753: href = hrefNode.nodeValue
754: hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))
755:
756: if href.startswith('../lt/lex.xql'):
757: selfurl = self.absolute_url()
758: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
759: l.setAttributeNS(None, 'target', '_blank')
760: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
761: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
762: if href.startswith('../lt/lemma.xql'):
763: selfurl = self.absolute_url()
764: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
765: l.setAttributeNS(None, 'target', '_blank')
766: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
767: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
768: return serializeNode(pagenode)
769: return "xexe"
770:
771: def getNumPages(self,docinfo=None):
772: """get list of pages from fulltext and put in docinfo"""
773: xquery = '//pb'
774: text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
775: # TODO: better processing of the page list. do we need the info somewhere else also?
776: docinfo['numPages'] = text.count("<pb ")
777: return docinfo
778:
779: def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None,):
780: """returns single page from fulltext"""
781: docpath = docinfo['textURLPath']
782: if mode == "text_dict":
783: textmode = "textPollux"
784: else:
785: textmode = mode
786:
787: #selfurl = self.absolute_url()
788: #viewMode= pageinfo['viewMode']
789: #tocMode = pageinfo['tocMode']
790: #tocPN = pageinfo['tocPN']
791:
792: pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False)
793: # post-processing downloaded xml
794: pagedom = Parse(pagexml)
795: # plain text mode
796: if mode == "text":
797: # first div contains text
798: pagedivs = pagedom.xpath("/div")
799: #queryResultPage
800: if len(pagedivs) > 0:
801: pagenode = pagedivs[0]
802: return serializeNode(pagenode)
803: if mode == "xml":
804: # first div contains text
805: pagedivs = pagedom.xpath("/div")
806: if len(pagedivs) > 0:
807: pagenode = pagedivs[0]
808: return serializeNode(pagenode)
809: # text-with-links mode
810: if mode == "text_dict":
811: # first div contains text
812: pagedivs = pagedom.xpath("/div")
813: if len(pagedivs) > 0:
814: pagenode = pagedivs[0]
815: # check all a-tags
816: links = pagenode.xpath("//a")
817: for l in links:
818: hrefNode = l.getAttributeNodeNS(None, u"href")
819: if hrefNode:
820: # is link with href
821: href = hrefNode.nodeValue
822: if href.startswith('lt/lex.xql'):
823: # is pollux link
824: selfurl = self.absolute_url()
825: # change href
826: hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
827: # add target
828: l.setAttributeNS(None, 'target', '_blank')
829: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
830: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
831:
832: if href.startswith('lt/lemma.xql'):
833: selfurl = self.absolute_url()
834: hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
835: l.setAttributeNS(None, 'target', '_blank')
836: l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
837: l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
838: return serializeNode(pagenode)
839:
840: return "no text here"
841:
842: def getTranslate(self, query=None, language=None):
843: """translate into another languages"""
844: pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","query=%s&language=%s"%(query,language),outputUnicode=False)
845: return pagexml
846:
847: def getLemma(self, lemma=None, language=None):
848: """simular words lemma """
849: pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","lemma=%s&language=%s"%(lemma,language),outputUnicode=False)
850: return pagexml
851:
852: def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
853: """number of"""
854: docpath = docinfo['textURLPath']
855: pagesize = pageinfo['queryPageSize']
856: pn = pageinfo['searchPN']
857: query =pageinfo['query']
858: queryType =pageinfo['queryType']
859:
860: tocSearch = 0
861: tocDiv = None
862: pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn) ,outputUnicode=False)
863:
864: pagedom = Parse(pagexml)
865: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
866: tocSearch = int(getTextFromNode(numdivs[0]))
867: tc=int((tocSearch/20)+1)
868: logging.debug("documentViewer (gettoc) tc: %s"%(tc))
869: return tc
870:
871: def getToc(self, mode="text", docinfo=None):
872: """loads table of contents and stores in docinfo"""
873: logging.debug("documentViewer (gettoc) mode: %s"%(mode))
874: if 'tocSize_%s'%mode in docinfo:
875: # cached toc
876: return docinfo
877: docpath = docinfo['textURLPath']
878: # we need to set a result set size
879: pagesize = 1000
880: pn = 1
881: if mode == "text":
882: queryType = "toc"
883: else:
884: queryType = mode
885: # number of entries in toc
886: tocSize = 0
887: tocDiv = None
888: pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
889: # post-processing downloaded xml
890: pagedom = Parse(pagexml)
891: # get number of entries
892: numdivs = pagedom.xpath("//div[@class='queryResultHits']")
893: if len(numdivs) > 0:
894: tocSize = int(getTextFromNode(numdivs[0]))
895: # div contains text
896: #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
897: #if len(pagedivs) > 0:
898: # tocDiv = pagedivs[0]
899:
900: docinfo['tocSize_%s'%mode] = tocSize
901: #docinfo['tocDiv_%s'%mode] = tocDiv
902: return docinfo
903:
904: def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
905: """returns single page from the table of contents"""
906: # TODO: this should use the cached TOC
907: if mode == "text":
908: queryType = "toc"
909: else:
910: queryType = mode
911: docpath = docinfo['textURLPath']
912: pagesize = pageinfo['tocPageSize']
913: pn = pageinfo['tocPN']
914:
915: selfurl = self.absolute_url()
916: viewMode= pageinfo['viewMode']
917: tocMode = pageinfo['tocMode']
918: tocPN = pageinfo['tocPN']
919:
920: pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn), outputUnicode=False)
921: page = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','%s?url=/mpiwg/online/permanent/library/163127KK&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl, viewMode, tocMode, tocPN))
922: text = page.replace('mode=image','mode=texttool')
923: return text
924: # post-processing downloaded xml
925: #pagedom = Parse(text)
926: # div contains text
927: #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
928: #if len(pagedivs) > 0:
929: # pagenode = pagedivs[0]
930: # return serializeNode(pagenode)
931: #else:
932: # return "No TOC!"
933:
934:
935: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
936: """init document viewer"""
937: self.title=title
938: self.digilibBaseUrl = digilibBaseUrl
939: self.thumbrows = thumbrows
940: self.thumbcols = thumbcols
941: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
942: if RESPONSE is not None:
943: RESPONSE.redirect('manage_main')
944:
945:
946:
947: def manage_AddDocumentViewerForm(self):
948: """add the viewer form"""
949: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
950: return pt()
951:
952: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
953: """add the viewer"""
954: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
955: self._setObject(id,newObj)
956:
957: if RESPONSE is not None:
958: RESPONSE.redirect('manage_main')
959:
960:
961: ##
962: ## DocumentViewerTemplate class
963: ##
964: class DocumentViewerTemplate(ZopePageTemplate):
965: """Template for document viewer"""
966: meta_type="DocumentViewer Template"
967:
968:
969: def manage_addDocumentViewerTemplateForm(self):
970: """Form for adding"""
971: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
972: return pt()
973:
974: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
975: REQUEST=None, submit=None):
976: "Add a Page Template with optional file content."
977:
978: self._setObject(id, DocumentViewerTemplate(id))
979: ob = getattr(self, id)
980: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
981: logging.info("txt %s:"%txt)
982: ob.pt_edit(txt,"text/html")
983: if title:
984: ob.pt_setTitle(title)
985: try:
986: u = self.DestinationURL()
987: except AttributeError:
988: u = REQUEST['URL1']
989:
990: u = "%s/%s" % (u, urllib.quote(id))
991: REQUEST.RESPONSE.redirect(u+'/manage_main')
992: return ''
993:
994:
995:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>