Annotation of documentViewer/documentViewer.py, revision 1.69.2.9
1.18 dwinter 1:
1.1 dwinter 2: from OFS.Folder import Folder
3: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
1.22 dwinter 4: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
1.1 dwinter 5: from AccessControl import ClassSecurityInfo
1.8 casties 6: from AccessControl import getSecurityManager
1.1 dwinter 7: from Globals import package_home
8:
1.11 casties 9: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.1 dwinter 10: import os.path
1.7 casties 11: import sys
1.1 dwinter 12: import urllib
1.69.2.5 casties 13: import urllib2
1.20 dwinter 14: import logging
1.69.2.7 casties 15: import math
16: import urlparse
1.69.2.9! casties 17: import cStringIO
1.43 casties 18:
1.22 dwinter 19: def logger(txt,method,txt2):
20: """logging"""
21: logging.info(txt+ txt2)
22:
23:
1.4 casties 24: def getInt(number, default=0):
25: """returns always an int (0 in case of problems)"""
26: try:
27: return int(number)
28: except:
1.29 casties 29: return int(default)
1.4 casties 30:
1.1 dwinter 31: def getTextFromNode(nodename):
1.18 dwinter 32: """get the cdata content of a node"""
1.8 casties 33: if nodename is None:
34: return ""
1.1 dwinter 35: nodelist=nodename.childNodes
36: rc = ""
37: for node in nodelist:
38: if node.nodeType == node.TEXT_NODE:
39: rc = rc + node.data
40: return rc
41:
1.43 casties 42: def serializeNode(node, encoding='utf-8'):
43: """returns a string containing node as XML"""
44: buf = cStringIO.StringIO()
45: Print(node, stream=buf, encoding=encoding)
46: s = buf.getvalue()
47: buf.close()
48: return s
49:
1.9 casties 50:
51: def getParentDir(path):
52: """returns pathname shortened by one"""
53: return '/'.join(path.split('/')[0:-1])
54:
55:
1.69.2.3 casties 56: def getHttpData(url, data=None, num_tries=3, timeout=10):
57: """returns result from url+data HTTP request"""
58: # we do GET (by appending data to url)
59: if isinstance(data, str) or isinstance(data, unicode):
60: # if data is string then append
61: url = "%s?%s"%(url,data)
62: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
63: # urlencode
64: url = "%s?%s"%(url,urllib.urlencode(data))
65:
66: response = None
67: errmsg = None
68: for cnt in range(num_tries):
69: try:
70: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
71: if sys.version_info < (2, 6):
72: # set timeout on socket -- ugly :-(
73: import socket
1.69.2.8 casties 74: socket.setdefaulttimeout(float(timeout))
1.69.2.3 casties 75: response = urllib2.urlopen(url)
76: else:
77: response = urllib2.urlopen(url,timeout=float(timeout))
78: # check result?
79: break
80: except urllib2.HTTPError, e:
81: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
82: errmsg = str(e)
83: # stop trying
84: break
85: except urllib2.URLError, e:
86: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
87: errmsg = str(e)
88: # stop trying
89: #break
90:
91: if response is not None:
92: data = response.read()
93: response.close()
94: return data
95:
96: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
97: #return None
1.1 dwinter 98:
99:
100:
1.3 casties 101: ##
102: ## documentViewer class
103: ##
1.69.2.3 casties 104: class documentViewer(Folder):
1.1 dwinter 105: """document viewer"""
106: meta_type="Document viewer"
107:
108: security=ClassSecurityInfo()
1.3 casties 109: manage_options=Folder.manage_options+(
1.1 dwinter 110: {'label':'main config','action':'changeDocumentViewerForm'},
111: )
112:
1.3 casties 113: # templates and forms
114: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 115: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
116: toc_text = PageTemplateFile('zpt/toc_text', globals())
117: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 118: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
119: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 120: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.48 abukhman 121: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 122: head_main = PageTemplateFile('zpt/head_main', globals())
123: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 124: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.69.2.1 abukhman 125:
126:
1.32 dwinter 127: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 128: security.declareProtected('View management screens','changeDocumentViewerForm')
129: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
130:
1.1 dwinter 131:
1.45 abukhman 132: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 133: """init document viewer"""
134: self.id=id
135: self.title=title
1.4 casties 136: self.thumbcols = thumbcols
137: self.thumbrows = thumbrows
1.8 casties 138: # authgroups is list of authorized groups (delimited by ,)
139: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 140: # create template folder so we can always use template.something
141:
142: templateFolder = Folder('template')
143: #self['template'] = templateFolder # Zope-2.12 style
144: self._setObject('template',templateFolder) # old style
145: try:
1.69.2.3 casties 146: import MpdlXmlTextServer
147: textServer = MpdlXmlTextServer(id='fulltextclient')
1.43 casties 148: #templateFolder['fulltextclient'] = xmlRpcClient
1.69.2.3 casties 149: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 150: except Exception, e:
1.69.2.3 casties 151: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 152: try:
153: from Products.zogiLib.zogiLib import zogiLib
154: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
155: #templateFolder['zogilib'] = zogilib
156: templateFolder._setObject('zogilib',zogilib)
157: except Exception, e:
158: logging.error("Unable to create zogiLib for zogilib: "+str(e))
159:
1.69.2.3 casties 160:
161: # proxy text server methods to fulltextclient
162: def getTextPage(self, **args):
163: """get page"""
164: return self.template.fulltextclient.getTextPage(**args)
165:
166: def getQuery(self, **args):
167: """get query"""
168: return self.template.fulltextclient.getQuery(**args)
169:
170: def getSearch(self, **args):
171: """get search"""
172: return self.template.fulltextclient.getSearch(**args)
173:
174: def getNumPages(self, **args):
175: """get numpages"""
176: return self.template.fulltextclient.getNumPages(**args)
177:
178: def getTranslate(self, **args):
179: """get translate"""
180: return self.template.fulltextclient.getTranslate(**args)
181:
182: def getLemma(self, **args):
183: """get lemma"""
184: return self.template.fulltextclient.getLemma(**args)
185:
186: def getToc(self, **args):
187: """get toc"""
188: return self.template.fulltextclient.getToc(**args)
189:
190: def getTocPage(self, **args):
191: """get tocpage"""
192: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 193:
1.69.2.3 casties 194:
1.32 dwinter 195: security.declareProtected('View','thumbs_rss')
196: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
197: '''
198: view it
199: @param mode: defines how to access the document behind url
200: @param url: url which contains display information
201: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
202:
203: '''
1.43 casties 204: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.32 dwinter 205: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
206:
207: if not hasattr(self, 'template'):
208: # create template folder if it doesn't exist
209: self.manage_addFolder('template')
210:
211: if not self.digilibBaseUrl:
212: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
213:
214: docinfo = self.getDocinfo(mode=mode,url=url)
215: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
216: pt = getattr(self.template, 'thumbs_main_rss')
217:
218: if viewMode=="auto": # automodus gewaehlt
219: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
220: viewMode="text"
221: else:
222: viewMode="images"
223:
224: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
225:
1.3 casties 226: security.declareProtected('View','index_html')
1.45 abukhman 227: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
1.3 casties 228: '''
229: view it
1.26 casties 230: @param mode: defines how to access the document behind url
1.3 casties 231: @param url: url which contains display information
1.44 casties 232: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 233: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.49 abukhman 234: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 235: '''
236:
1.43 casties 237: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 238:
1.3 casties 239: if not hasattr(self, 'template'):
1.43 casties 240: # this won't work
241: logging.error("template folder missing!")
242: return "ERROR: template folder missing!"
1.3 casties 243:
1.43 casties 244: if not getattr(self, 'digilibBaseUrl', None):
1.3 casties 245: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
246:
1.4 casties 247: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 248:
249:
1.44 casties 250: if tocMode != "thumbs":
251: # get table of contents
252: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 253:
1.21 dwinter 254: if viewMode=="auto": # automodus gewaehlt
1.43 casties 255: if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
1.68 casties 256: viewMode="text_dict"
1.21 dwinter 257: else:
258: viewMode="images"
1.44 casties 259:
1.68 casties 260: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
261:
1.44 casties 262: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 263: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 264:
1.36 dwinter 265: def generateMarks(self,mk):
266: ret=""
1.44 casties 267: if mk is None:
268: return ""
269: if type(mk) is not ListType:
270: mk=[mk]
1.36 dwinter 271: for m in mk:
1.37 dwinter 272: ret+="mk=%s"%m
1.36 dwinter 273: return ret
1.43 casties 274:
1.44 casties 275:
1.43 casties 276: def findDigilibUrl(self):
277: """try to get the digilib URL from zogilib"""
278: url = self.template.zogilib.getDLBaseUrl()
279: return url
1.67 casties 280:
281: def getDocumentViewerURL(self):
282: """returns the URL of this instance"""
283: return self.absolute_url()
1.43 casties 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
1.36 dwinter 292:
1.4 casties 293: def getLink(self,param=None,val=None):
294: """link to documentviewer with parameter param set to val"""
1.9 casties 295: params=self.REQUEST.form.copy()
1.4 casties 296: if param is not None:
1.7 casties 297: if val is None:
298: if params.has_key(param):
299: del params[param]
1.4 casties 300: else:
1.9 casties 301: params[param] = str(val)
1.43 casties 302:
303: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 304: params["mode"] = "imagepath"
305: params["url"] = getParentDir(params["url"])
1.7 casties 306:
1.9 casties 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
1.4 casties 310: return url
311:
1.32 dwinter 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
1.69.2.2 casties 323: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 324: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
325: url=self.REQUEST['URL1']+"?"+ps
326: return url
1.40 casties 327:
1.26 casties 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:
1.4 casties 338:
1.9 casties 339: def isAccessible(self, docinfo):
1.8 casties 340: """returns if access to the resource is granted"""
341: access = docinfo.get('accessType', None)
1.69.2.2 casties 342: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 343: if access is not None and access == 'free':
1.69.2.2 casties 344: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 345: return True
1.17 casties 346: elif access is None or access in self.authgroups:
1.9 casties 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
1.8 casties 354:
1.69.2.2 casties 355: logging.debug("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 356: return False
1.9 casties 357:
1.8 casties 358:
1.35 dwinter 359: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 360: """gibt param von dlInfo aus"""
1.7 casties 361: if docinfo is None:
362: docinfo = {}
1.35 dwinter 363:
364: for x in range(cut):
1.38 dwinter 365:
1.35 dwinter 366: path=getParentDir(path)
1.38 dwinter 367:
1.13 casties 368: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 369:
1.69.2.2 casties 370: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 371:
1.69.2.3 casties 372: txt = getHttpData(infoUrl)
373: if txt is None:
1.13 casties 374: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.69.2.3 casties 375:
376: dom = Parse(txt)
1.10 casties 377: sizes=dom.xpath("//dir/size")
1.69.2.2 casties 378: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 379:
1.10 casties 380: if sizes:
381: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 382: else:
383: docinfo['numPages'] = 0
1.43 casties 384:
385: # TODO: produce and keep list of image names and numbers
1.7 casties 386:
387: return docinfo
1.8 casties 388:
1.6 casties 389:
1.9 casties 390: def getIndexMeta(self, url):
391: """returns dom of index.meta document at url"""
392: dom = None
1.12 casties 393: metaUrl = None
1.9 casties 394: if url.startswith("http://"):
395: # real URL
1.12 casties 396: metaUrl = url
1.9 casties 397: else:
398: # online path
399: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 400: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 401: if not metaUrl.endswith("index.meta"):
402: metaUrl += "/index.meta"
1.12 casties 403:
1.69.2.3 casties 404: logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)
405: txt=getHttpData(metaUrl)
406: if txt is None:
1.12 casties 407: raise IOError("Unable to read index meta from %s"%(url))
1.69.2.3 casties 408:
409: dom = Parse(txt)
1.9 casties 410: return dom
1.20 dwinter 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:
1.69.2.3 casties 424: txt=getHttpData(metaUrl)
425: if txt is None:
1.20 dwinter 426: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.69.2.3 casties 427:
428: dom = Parse(txt)
1.20 dwinter 429: return dom
1.9 casties 430:
431:
1.33 dwinter 432: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 433: """gets authorization info from the index.meta file at path or given by dom"""
1.69.2.2 casties 434: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 435:
436: access = None
437:
438: if docinfo is None:
439: docinfo = {}
440:
441: if dom is None:
1.38 dwinter 442: for x in range(cut):
1.33 dwinter 443: path=getParentDir(path)
444: dom = self.getIndexMeta(path)
1.18 dwinter 445:
1.8 casties 446: acctype = dom.xpath("//access-conditions/access/@type")
447: if acctype and (len(acctype)>0):
448: access=acctype[0].value
1.9 casties 449: if access in ['group', 'institution']:
1.8 casties 450: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
451:
452: docinfo['accessType'] = access
453: return docinfo
1.6 casties 454:
1.8 casties 455:
1.33 dwinter 456: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 457: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 458: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 459:
1.3 casties 460: if docinfo is None:
461: docinfo = {}
1.38 dwinter 462:
1.3 casties 463: if dom is None:
1.38 dwinter 464: for x in range(cut):
1.33 dwinter 465: path=getParentDir(path)
466: dom = self.getIndexMeta(path)
1.39 dwinter 467:
468: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 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
1.4 casties 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
1.2 dwinter 482: else:
1.4 casties 483: bibtype="generic"
1.27 casties 484:
1.4 casties 485: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 486: docinfo['bib_type'] = bibtype
1.4 casties 487: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 488: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 489: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 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
1.27 casties 499: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 500: try:
501: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
502: except:
503: docinfo['lang']=''
1.27 casties 504:
1.3 casties 505: return docinfo
1.42 abukhman 506:
507:
1.43 casties 508: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
509: """parse texttool tag in index meta"""
1.69.2.2 casties 510: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 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:
1.69.2.2 casties 525: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 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
1.69.2.2 casties 537: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 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: textUrls = dom.xpath("//texttool/text")
572: if textUrls and (len(textUrls) > 0):
573: textUrl = getTextFromNode(textUrls[0])
574: if urlparse.urlparse(textUrl)[0] == "": #keine url
575: textUrl = os.path.join(archivePath, textUrl)
576: # fix URLs starting with /mpiwg/online
577: if textUrl.startswith("/mpiwg/online"):
578: textUrl = textUrl.replace("/mpiwg/online", '', 1)
579:
580: docinfo['textURL'] = textUrl
581:
582: textUrls = dom.xpath("//texttool/text-url-path")
583: if textUrls and (len(textUrls) > 0):
584: textUrl = getTextFromNode(textUrls[0])
1.51 casties 585: docinfo['textURLPath'] = textUrl
586: if not docinfo['imagePath']:
587: # text-only, no page images
588: docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
1.43 casties 589:
590: presentationUrls = dom.xpath("//texttool/presentation")
591: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
592:
593: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
594: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
595: # durch den relativen Pfad auf die presentation infos
596: presentationPath = getTextFromNode(presentationUrls[0])
597: if url.endswith("index.meta"):
598: presentationUrl = url.replace('index.meta', presentationPath)
599: else:
600: presentationUrl = url + "/" + presentationPath
1.51 casties 601:
1.43 casties 602: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
603:
604: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 605:
1.43 casties 606: return docinfo
1.3 casties 607:
1.20 dwinter 608:
609: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
610: """gets the bibliographical information from the preseantion entry in texttools
611: """
612: dom=self.getPresentationInfoXML(url)
1.29 casties 613: try:
614: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
615: except:
616: pass
617: try:
618: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
619: except:
620: pass
621: try:
622: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
623: except:
624: pass
1.20 dwinter 625: return docinfo
626:
1.33 dwinter 627: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 628: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.69.2.2 casties 629: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 630: if docinfo is None:
631: docinfo = {}
1.6 casties 632: path=path.replace("/mpiwg/online","")
1.3 casties 633: docinfo['imagePath'] = path
1.35 dwinter 634: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 635:
1.39 dwinter 636: pathorig=path
1.38 dwinter 637: for x in range(cut):
638: path=getParentDir(path)
1.69.2.2 casties 639: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 640: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 641: docinfo['imageURL'] = imageUrl
642:
1.39 dwinter 643: #path ist the path to the images it assumes that the index.meta file is one level higher.
644: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
645: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 646: return docinfo
647:
1.2 dwinter 648:
1.3 casties 649: def getDocinfo(self, mode, url):
650: """returns docinfo depending on mode"""
1.69.2.2 casties 651: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 652: # look for cached docinfo in session
1.21 dwinter 653: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 654: docinfo = self.REQUEST.SESSION['docinfo']
655: # check if its still current
656: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.69.2.2 casties 657: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 658: return docinfo
659: # new docinfo
660: docinfo = {'mode': mode, 'url': url}
661: if mode=="texttool": #index.meta with texttool information
662: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
663: elif mode=="imagepath":
664: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 665: elif mode=="filepath":
1.37 dwinter 666: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 667: else:
1.69.2.2 casties 668: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 669: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 670:
1.69.2.2 casties 671: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 672: self.REQUEST.SESSION['docinfo'] = docinfo
673: return docinfo
1.69 abukhman 674:
1.44 casties 675: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 676: """returns pageinfo with the given parameters"""
677: pageinfo = {}
1.4 casties 678: current = getInt(current)
679: pageinfo['current'] = current
680: rows = int(rows or self.thumbrows)
681: pageinfo['rows'] = rows
682: cols = int(cols or self.thumbcols)
683: pageinfo['cols'] = cols
684: grpsize = cols * rows
685: pageinfo['groupsize'] = grpsize
1.28 casties 686: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
687: # int(current / grpsize) * grpsize +1))
1.3 casties 688: pageinfo['start'] = start
1.4 casties 689: pageinfo['end'] = start + grpsize
1.44 casties 690: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 691: np = int(docinfo['numPages'])
692: pageinfo['end'] = min(pageinfo['end'], np)
693: pageinfo['numgroups'] = int(np / grpsize)
694: if np % grpsize > 0:
1.69 abukhman 695: pageinfo['numgroups'] += 1
1.44 casties 696: pageinfo['viewMode'] = viewMode
697: pageinfo['tocMode'] = tocMode
1.45 abukhman 698: pageinfo['query'] = self.REQUEST.get('query',' ')
699: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
700: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 701: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 702: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 703: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 704: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 705: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 706: toc = int (pageinfo['tocPN'])
707: pageinfo['textPages'] =int (toc)
708:
709: if 'tocSize_%s'%tocMode in docinfo:
710: tocSize = int(docinfo['tocSize_%s'%tocMode])
711: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 712: # cached toc
1.48 abukhman 713: if tocSize%tocPageSize>0:
714: tocPages=tocSize/tocPageSize+1
715: else:
716: tocPages=tocSize/tocPageSize
1.69 abukhman 717: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 718: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 719: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 720: return pageinfo
721:
1.69 abukhman 722: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 723: """init document viewer"""
724: self.title=title
725: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 726: self.thumbrows = thumbrows
727: self.thumbcols = thumbcols
1.8 casties 728: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 729: if RESPONSE is not None:
730: RESPONSE.redirect('manage_main')
1.1 dwinter 731:
732: def manage_AddDocumentViewerForm(self):
733: """add the viewer form"""
1.3 casties 734: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 735: return pt()
736:
1.43 casties 737: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 738: """add the viewer"""
1.43 casties 739: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 740: self._setObject(id,newObj)
741:
742: if RESPONSE is not None:
743: RESPONSE.redirect('manage_main')
1.3 casties 744:
745: ## DocumentViewerTemplate class
746: class DocumentViewerTemplate(ZopePageTemplate):
747: """Template for document viewer"""
748: meta_type="DocumentViewer Template"
749:
750:
751: def manage_addDocumentViewerTemplateForm(self):
752: """Form for adding"""
753: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
754: return pt()
755:
756: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
757: REQUEST=None, submit=None):
758: "Add a Page Template with optional file content."
759:
760: self._setObject(id, DocumentViewerTemplate(id))
761: ob = getattr(self, id)
1.23 dwinter 762: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
763: logging.info("txt %s:"%txt)
764: ob.pt_edit(txt,"text/html")
1.3 casties 765: if title:
766: ob.pt_setTitle(title)
767: try:
768: u = self.DestinationURL()
769: except AttributeError:
770: u = REQUEST['URL1']
771:
772: u = "%s/%s" % (u, urllib.quote(id))
773: REQUEST.RESPONSE.redirect(u+'/manage_main')
774: return ''
775:
776:
1.14 casties 777:
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