Annotation of documentViewer/documentViewer.py, revision 1.118
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
1.117 abukhman 8: from Products.zogiLib import browserCheck
1.1 dwinter 9:
1.70 casties 10: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.73 casties 11: import Ft.Xml.Domlette
1.1 dwinter 12: import os.path
1.7 casties 13: import sys
1.1 dwinter 14: import urllib
1.70 casties 15: import urllib2
1.20 dwinter 16: import logging
1.28 casties 17: import math
1.18 dwinter 18: import urlparse
1.70 casties 19: import cStringIO
1.99 dwinter 20: import re
1.43 casties 21:
1.117 abukhman 22:
1.22 dwinter 23: def logger(txt,method,txt2):
24: """logging"""
25: logging.info(txt+ txt2)
26:
27:
1.4 casties 28: def getInt(number, default=0):
29: """returns always an int (0 in case of problems)"""
30: try:
31: return int(number)
32: except:
1.29 casties 33: return int(default)
1.4 casties 34:
1.1 dwinter 35: def getTextFromNode(nodename):
1.18 dwinter 36: """get the cdata content of a node"""
1.8 casties 37: if nodename is None:
38: return ""
1.1 dwinter 39: nodelist=nodename.childNodes
40: rc = ""
41: for node in nodelist:
42: if node.nodeType == node.TEXT_NODE:
43: rc = rc + node.data
44: return rc
45:
1.43 casties 46: def serializeNode(node, encoding='utf-8'):
47: """returns a string containing node as XML"""
48: buf = cStringIO.StringIO()
1.75 casties 49: Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
1.43 casties 50: s = buf.getvalue()
51: buf.close()
52: return s
53:
1.118 ! abukhman 54: def getBrowserType(self):
! 55: """get browser type object"""
! 56: if self.REQUEST.SESSION.has_key('browserType'):
! 57: return self.REQUEST.SESSION['browserType']
! 58: else:
! 59: bt = browserCheck(self)
! 60: self.REQUEST.SESSION.set('browserType', bt)
! 61: logging.debug("documentViewer (BROWSER TYPE) bt %s"%bt)
! 62: return bt
! 63:
! 64:
1.9 casties 65: def getParentDir(path):
66: """returns pathname shortened by one"""
67: return '/'.join(path.split('/')[0:-1])
68:
69:
1.70 casties 70: def getHttpData(url, data=None, num_tries=3, timeout=10):
71: """returns result from url+data HTTP request"""
72: # we do GET (by appending data to url)
73: if isinstance(data, str) or isinstance(data, unicode):
74: # if data is string then append
75: url = "%s?%s"%(url,data)
76: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
77: # urlencode
78: url = "%s?%s"%(url,urllib.urlencode(data))
79:
80: response = None
81: errmsg = None
82: for cnt in range(num_tries):
83: try:
1.95 abukhman 84: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
1.70 casties 85: if sys.version_info < (2, 6):
86: # set timeout on socket -- ugly :-(
87: import socket
88: socket.setdefaulttimeout(float(timeout))
89: response = urllib2.urlopen(url)
90: else:
91: response = urllib2.urlopen(url,timeout=float(timeout))
92: # check result?
93: break
94: except urllib2.HTTPError, e:
1.95 abukhman 95: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
1.70 casties 96: errmsg = str(e)
97: # stop trying
98: break
99: except urllib2.URLError, e:
1.95 abukhman 100: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
1.70 casties 101: errmsg = str(e)
102: # stop trying
103: #break
104:
105: if response is not None:
106: data = response.read()
107: response.close()
108: return data
109:
110: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
111: #return None
1.1 dwinter 112:
113:
114:
1.3 casties 115: ##
116: ## documentViewer class
117: ##
118: class documentViewer(Folder):
1.1 dwinter 119: """document viewer"""
120: meta_type="Document viewer"
121:
122: security=ClassSecurityInfo()
1.3 casties 123: manage_options=Folder.manage_options+(
1.1 dwinter 124: {'label':'main config','action':'changeDocumentViewerForm'},
125: )
126:
1.3 casties 127: # templates and forms
128: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 129: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
130: toc_text = PageTemplateFile('zpt/toc_text', globals())
131: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 132: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
133: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 134: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77 abukhman 135: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 136: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 137: head_main = PageTemplateFile('zpt/head_main', globals())
138: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 139: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 140:
141:
1.32 dwinter 142: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 143: security.declareProtected('View management screens','changeDocumentViewerForm')
144: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
145:
1.1 dwinter 146:
1.45 abukhman 147: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 148: """init document viewer"""
149: self.id=id
150: self.title=title
1.4 casties 151: self.thumbcols = thumbcols
152: self.thumbrows = thumbrows
1.8 casties 153: # authgroups is list of authorized groups (delimited by ,)
154: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 155: # create template folder so we can always use template.something
156:
157: templateFolder = Folder('template')
158: #self['template'] = templateFolder # Zope-2.12 style
159: self._setObject('template',templateFolder) # old style
160: try:
1.70 casties 161: import MpdlXmlTextServer
1.71 casties 162: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 163: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 164: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 165: except Exception, e:
1.70 casties 166: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 167: try:
168: from Products.zogiLib.zogiLib import zogiLib
169: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
170: #templateFolder['zogilib'] = zogilib
171: templateFolder._setObject('zogilib',zogilib)
172: except Exception, e:
173: logging.error("Unable to create zogiLib for zogilib: "+str(e))
174:
1.70 casties 175:
176: # proxy text server methods to fulltextclient
177: def getTextPage(self, **args):
178: """get page"""
179: return self.template.fulltextclient.getTextPage(**args)
180:
181: def getQuery(self, **args):
182: """get query"""
183: return self.template.fulltextclient.getQuery(**args)
184:
185: def getSearch(self, **args):
186: """get search"""
187: return self.template.fulltextclient.getSearch(**args)
188:
1.72 casties 189: def getNumPages(self, docinfo):
1.70 casties 190: """get numpages"""
1.72 casties 191: return self.template.fulltextclient.getNumPages(docinfo)
1.100 abukhman 192:
193: def getNumTextPages(self, docinfo):
194: """get numpages text"""
195: return self.template.fulltextclient.getNumTextPages(docinfo)
196:
1.70 casties 197: def getTranslate(self, **args):
198: """get translate"""
199: return self.template.fulltextclient.getTranslate(**args)
200:
201: def getLemma(self, **args):
202: """get lemma"""
203: return self.template.fulltextclient.getLemma(**args)
204:
205: def getToc(self, **args):
206: """get toc"""
207: return self.template.fulltextclient.getToc(**args)
208:
209: def getTocPage(self, **args):
210: """get tocpage"""
211: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 212:
1.70 casties 213:
1.32 dwinter 214: security.declareProtected('View','thumbs_rss')
215: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
216: '''
217: view it
218: @param mode: defines how to access the document behind url
219: @param url: url which contains display information
220: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
221:
222: '''
1.95 abukhman 223: logging.debug("HHHHHHHHHHHHHH:load the rss")
224: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 225:
226: if not hasattr(self, 'template'):
227: # create template folder if it doesn't exist
228: self.manage_addFolder('template')
229:
230: if not self.digilibBaseUrl:
231: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
232:
233: docinfo = self.getDocinfo(mode=mode,url=url)
234: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
235: pt = getattr(self.template, 'thumbs_main_rss')
236:
237: if viewMode=="auto": # automodus gewaehlt
1.70 casties 238: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 239: viewMode="text"
240: else:
241: viewMode="images"
242:
243: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
244:
1.3 casties 245: security.declareProtected('View','index_html')
1.97 abukhman 246: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""):
1.3 casties 247: '''
248: view it
1.26 casties 249: @param mode: defines how to access the document behind url
1.3 casties 250: @param url: url which contains display information
1.44 casties 251: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 252: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 253: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 254: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 255: '''
256:
1.95 abukhman 257: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 258:
1.3 casties 259: if not hasattr(self, 'template'):
1.43 casties 260: # this won't work
261: logging.error("template folder missing!")
262: return "ERROR: template folder missing!"
1.3 casties 263:
1.43 casties 264: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 265: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 266:
1.4 casties 267: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 268:
1.44 casties 269: if tocMode != "thumbs":
270: # get table of contents
271: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 272:
1.21 dwinter 273: if viewMode=="auto": # automodus gewaehlt
1.71 casties 274: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.68 casties 275: viewMode="text_dict"
1.21 dwinter 276: else:
277: viewMode="images"
1.44 casties 278:
1.97 abukhman 279: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
1.68 casties 280:
1.44 casties 281: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 282: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 283:
1.36 dwinter 284: def generateMarks(self,mk):
285: ret=""
1.44 casties 286: if mk is None:
287: return ""
1.73 casties 288: if not isinstance(mk, list):
1.71 casties 289: mk=[mk]
1.36 dwinter 290: for m in mk:
1.37 dwinter 291: ret+="mk=%s"%m
1.36 dwinter 292: return ret
1.43 casties 293:
1.44 casties 294:
1.43 casties 295: def findDigilibUrl(self):
296: """try to get the digilib URL from zogilib"""
297: url = self.template.zogilib.getDLBaseUrl()
298: return url
1.67 casties 299:
300: def getDocumentViewerURL(self):
301: """returns the URL of this instance"""
302: return self.absolute_url()
1.43 casties 303:
304: def getStyle(self, idx, selected, style=""):
305: """returns a string with the given style and append 'sel' if path == selected."""
306: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
307: if idx == selected:
308: return style + 'sel'
309: else:
310: return style
1.36 dwinter 311:
1.4 casties 312: def getLink(self,param=None,val=None):
313: """link to documentviewer with parameter param set to val"""
1.9 casties 314: params=self.REQUEST.form.copy()
1.4 casties 315: if param is not None:
1.7 casties 316: if val is None:
317: if params.has_key(param):
318: del params[param]
1.4 casties 319: else:
1.9 casties 320: params[param] = str(val)
1.43 casties 321:
322: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 323: params["mode"] = "imagepath"
324: params["url"] = getParentDir(params["url"])
1.7 casties 325:
1.9 casties 326: # quote values and assemble into query string
1.74 casties 327: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
328: ps = urllib.urlencode(params)
1.9 casties 329: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 330: return url
331:
1.32 dwinter 332: def getLinkAmp(self,param=None,val=None):
333: """link to documentviewer with parameter param set to val"""
334: params=self.REQUEST.form.copy()
335: if param is not None:
336: if val is None:
337: if params.has_key(param):
338: del params[param]
339: else:
340: params[param] = str(val)
341:
342: # quote values and assemble into query string
1.95 abukhman 343: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 344: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
345: url=self.REQUEST['URL1']+"?"+ps
346: return url
1.40 casties 347:
1.26 casties 348: def getInfo_xml(self,url,mode):
349: """returns info about the document as XML"""
350:
351: if not self.digilibBaseUrl:
352: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
353:
354: docinfo = self.getDocinfo(mode=mode,url=url)
355: pt = getattr(self.template, 'info_xml')
356: return pt(docinfo=docinfo)
357:
1.4 casties 358:
1.9 casties 359: def isAccessible(self, docinfo):
1.8 casties 360: """returns if access to the resource is granted"""
361: access = docinfo.get('accessType', None)
1.95 abukhman 362: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 363: if access is not None and access == 'free':
1.95 abukhman 364: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 365: return True
1.17 casties 366: elif access is None or access in self.authgroups:
1.9 casties 367: # only local access -- only logged in users
368: user = getSecurityManager().getUser()
1.95 abukhman 369: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 370: if user is not None:
371: #print "user: ", user
372: return (user.getUserName() != "Anonymous User")
373: else:
374: return False
1.8 casties 375:
1.95 abukhman 376: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 377: return False
1.9 casties 378:
1.8 casties 379:
1.35 dwinter 380: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 381: """gibt param von dlInfo aus"""
1.7 casties 382: if docinfo is None:
383: docinfo = {}
1.35 dwinter 384:
385: for x in range(cut):
1.38 dwinter 386:
1.35 dwinter 387: path=getParentDir(path)
1.38 dwinter 388:
1.13 casties 389: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 390:
1.95 abukhman 391: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 392:
1.70 casties 393: txt = getHttpData(infoUrl)
394: if txt is None:
1.13 casties 395: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 396:
397: dom = Parse(txt)
1.10 casties 398: sizes=dom.xpath("//dir/size")
1.95 abukhman 399: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 400:
1.10 casties 401: if sizes:
402: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 403: else:
404: docinfo['numPages'] = 0
1.43 casties 405:
406: # TODO: produce and keep list of image names and numbers
1.7 casties 407:
408: return docinfo
1.8 casties 409:
1.99 dwinter 410: def getIndexMetaPath(self,url):
411: """gib nur den Pfad zurueck"""
412: regexp = re.compile(r".*(experimental|permanent)/(.*)")
413: regpath = regexp.match(url)
414: if (regpath==None):
415: return ""
1.110 abukhman 416: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 417: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
418:
1.111 abukhman 419:
420:
1.99 dwinter 421: def getIndexMetaUrl(self,url):
422: """returns utr of index.meta document at url"""
423:
1.12 casties 424: metaUrl = None
1.9 casties 425: if url.startswith("http://"):
426: # real URL
1.12 casties 427: metaUrl = url
1.9 casties 428: else:
429: # online path
430: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 431: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 432: if not metaUrl.endswith("index.meta"):
433: metaUrl += "/index.meta"
1.99 dwinter 434:
435: return metaUrl
436:
437: def getDomFromIndexMeta(self, url):
438: """get dom from index meta"""
439: dom = None
440: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 441:
1.99 dwinter 442: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 443: txt=getHttpData(metaUrl)
444: if txt is None:
1.12 casties 445: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 446:
447: dom = Parse(txt)
1.9 casties 448: return dom
1.20 dwinter 449:
450: def getPresentationInfoXML(self, url):
451: """returns dom of info.xml document at url"""
452: dom = None
453: metaUrl = None
454: if url.startswith("http://"):
455: # real URL
456: metaUrl = url
457: else:
458: # online path
459: server=self.digilibBaseUrl+"/servlet/Texter?fn="
460: metaUrl=server+url.replace("/mpiwg/online","")
461:
1.70 casties 462: txt=getHttpData(metaUrl)
463: if txt is None:
1.20 dwinter 464: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 465:
466: dom = Parse(txt)
1.20 dwinter 467: return dom
1.9 casties 468:
469:
1.33 dwinter 470: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 471: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 472: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 473:
474: access = None
475:
476: if docinfo is None:
477: docinfo = {}
478:
479: if dom is None:
1.38 dwinter 480: for x in range(cut):
1.33 dwinter 481: path=getParentDir(path)
1.99 dwinter 482: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 483:
1.8 casties 484: acctype = dom.xpath("//access-conditions/access/@type")
485: if acctype and (len(acctype)>0):
486: access=acctype[0].value
1.9 casties 487: if access in ['group', 'institution']:
1.8 casties 488: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
489:
490: docinfo['accessType'] = access
491: return docinfo
1.6 casties 492:
1.8 casties 493:
1.33 dwinter 494: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 495: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 496: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 497:
1.3 casties 498: if docinfo is None:
499: docinfo = {}
1.38 dwinter 500:
1.3 casties 501: if dom is None:
1.38 dwinter 502: for x in range(cut):
1.33 dwinter 503: path=getParentDir(path)
1.99 dwinter 504: dom = self.getDomFromIndexMeta(path)
505:
506: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 507:
1.95 abukhman 508: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 509: # put in all raw bib fields as dict "bib"
510: bib = dom.xpath("//bib/*")
511: if bib and len(bib)>0:
512: bibinfo = {}
513: for e in bib:
514: bibinfo[e.localName] = getTextFromNode(e)
515: docinfo['bib'] = bibinfo
516:
517: # extract some fields (author, title, year) according to their mapping
1.4 casties 518: metaData=self.metadata.main.meta.bib
519: bibtype=dom.xpath("//bib/@type")
520: if bibtype and (len(bibtype)>0):
521: bibtype=bibtype[0].value
1.2 dwinter 522: else:
1.4 casties 523: bibtype="generic"
1.27 casties 524:
1.4 casties 525: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 526: docinfo['bib_type'] = bibtype
1.4 casties 527: bibmap=metaData.generateMappingForType(bibtype)
1.99 dwinter 528: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
529: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
1.8 casties 530: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 531: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 532: try:
533: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
534: except: pass
535: try:
536: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
537: except: pass
538: try:
539: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
540: except: pass
1.95 abukhman 541: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 542: try:
543: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
544: except:
545: docinfo['lang']=''
1.113 abukhman 546:
1.3 casties 547: return docinfo
1.42 abukhman 548:
1.104 abukhman 549:
550: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
551: """gets name info from the index.meta file at path or given by dom"""
552: if docinfo is None:
553: docinfo = {}
554:
555: if dom is None:
556: for x in range(cut):
557: path=getParentDir(path)
558: dom = self.getDomFromIndexMeta(path)
559:
1.112 abukhman 560: #docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.104 abukhman 561:
1.105 abukhman 562: #result= dom.xpath("//result/resultPage")
563: #docinfo['numPages']=int(getTextFromNode(result[0]))
1.104 abukhman 564:
1.113 abukhman 565: #result =dom.xpath("//name")
1.115 abukhman 566: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
1.116 abukhman 567: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.113 abukhman 568:
1.104 abukhman 569: #logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
570: return docinfo
1.42 abukhman 571:
1.43 casties 572: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
573: """parse texttool tag in index meta"""
1.95 abukhman 574: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 575: if docinfo is None:
576: docinfo = {}
577: if docinfo.get('lang', None) is None:
578: docinfo['lang'] = '' # default keine Sprache gesetzt
579: if dom is None:
1.99 dwinter 580: dom = self.getDomFromIndexMeta(url)
1.43 casties 581:
582: archivePath = None
583: archiveName = None
584:
585: archiveNames = dom.xpath("//resource/name")
586: if archiveNames and (len(archiveNames) > 0):
587: archiveName = getTextFromNode(archiveNames[0])
588: else:
1.70 casties 589: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 590:
591: archivePaths = dom.xpath("//resource/archive-path")
592: if archivePaths and (len(archivePaths) > 0):
593: archivePath = getTextFromNode(archivePaths[0])
594: # clean up archive path
595: if archivePath[0] != '/':
596: archivePath = '/' + archivePath
597: if archiveName and (not archivePath.endswith(archiveName)):
598: archivePath += "/" + archiveName
599: else:
600: # try to get archive-path from url
1.95 abukhman 601: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 602: if (not url.startswith('http')):
603: archivePath = url.replace('index.meta', '')
604:
605: if archivePath is None:
606: # we balk without archive-path
607: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
608:
609: imageDirs = dom.xpath("//texttool/image")
610: if imageDirs and (len(imageDirs) > 0):
611: imageDir = getTextFromNode(imageDirs[0])
612:
613: else:
614: # we balk with no image tag / not necessary anymore because textmode is now standard
615: #raise IOError("No text-tool info in %s"%(url))
616: imageDir = ""
617: #xquery="//pb"
618: docinfo['imagePath'] = "" # keine Bilder
619: docinfo['imageURL'] = ""
620:
621: if imageDir and archivePath:
622: #print "image: ", imageDir, " archivepath: ", archivePath
623: imageDir = os.path.join(archivePath, imageDir)
624: imageDir = imageDir.replace("/mpiwg/online", '')
625: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
626: docinfo['imagePath'] = imageDir
627:
628: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
629:
630: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
631: if viewerUrls and (len(viewerUrls) > 0):
632: viewerUrl = getTextFromNode(viewerUrls[0])
633: docinfo['viewerURL'] = viewerUrl
1.70 casties 634:
635: # old style text URL
1.43 casties 636: textUrls = dom.xpath("//texttool/text")
637: if textUrls and (len(textUrls) > 0):
638: textUrl = getTextFromNode(textUrls[0])
639: if urlparse.urlparse(textUrl)[0] == "": #keine url
640: textUrl = os.path.join(archivePath, textUrl)
641: # fix URLs starting with /mpiwg/online
642: if textUrl.startswith("/mpiwg/online"):
643: textUrl = textUrl.replace("/mpiwg/online", '', 1)
644:
645: docinfo['textURL'] = textUrl
646:
1.70 casties 647: # new style text-url-path
1.43 casties 648: textUrls = dom.xpath("//texttool/text-url-path")
649: if textUrls and (len(textUrls) > 0):
650: textUrl = getTextFromNode(textUrls[0])
1.51 casties 651: docinfo['textURLPath'] = textUrl
652: if not docinfo['imagePath']:
653: # text-only, no page images
1.103 abukhman 654: docinfo = self.getNumTextPages(docinfo)
1.43 casties 655:
656: presentationUrls = dom.xpath("//texttool/presentation")
657: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.114 abukhman 658: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.43 casties 659:
660: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
661: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
662: # durch den relativen Pfad auf die presentation infos
663: presentationPath = getTextFromNode(presentationUrls[0])
664: if url.endswith("index.meta"):
665: presentationUrl = url.replace('index.meta', presentationPath)
666: else:
667: presentationUrl = url + "/" + presentationPath
1.51 casties 668:
1.43 casties 669: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
670:
671: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 672:
1.43 casties 673: return docinfo
1.3 casties 674:
1.20 dwinter 675:
676: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
677: """gets the bibliographical information from the preseantion entry in texttools
678: """
679: dom=self.getPresentationInfoXML(url)
1.29 casties 680: try:
681: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
682: except:
683: pass
684: try:
685: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
686: except:
687: pass
688: try:
689: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
690: except:
691: pass
1.20 dwinter 692: return docinfo
693:
1.33 dwinter 694: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 695: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 696: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 697: if docinfo is None:
698: docinfo = {}
1.6 casties 699: path=path.replace("/mpiwg/online","")
1.3 casties 700: docinfo['imagePath'] = path
1.35 dwinter 701: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 702:
1.39 dwinter 703: pathorig=path
1.38 dwinter 704: for x in range(cut):
705: path=getParentDir(path)
1.95 abukhman 706: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 707: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 708: docinfo['imageURL'] = imageUrl
709:
1.39 dwinter 710: #path ist the path to the images it assumes that the index.meta file is one level higher.
711: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
712: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 713: return docinfo
714:
1.2 dwinter 715:
1.3 casties 716: def getDocinfo(self, mode, url):
717: """returns docinfo depending on mode"""
1.95 abukhman 718: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 719: # look for cached docinfo in session
1.21 dwinter 720: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 721: docinfo = self.REQUEST.SESSION['docinfo']
722: # check if its still current
723: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.95 abukhman 724: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 725: return docinfo
726: # new docinfo
727: docinfo = {'mode': mode, 'url': url}
728: if mode=="texttool": #index.meta with texttool information
729: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
730: elif mode=="imagepath":
731: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 732: elif mode=="filepath":
1.37 dwinter 733: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 734: else:
1.95 abukhman 735: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 736: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 737:
1.95 abukhman 738: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 739: self.REQUEST.SESSION['docinfo'] = docinfo
740: return docinfo
1.69 abukhman 741:
1.97 abukhman 742: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
1.3 casties 743: """returns pageinfo with the given parameters"""
744: pageinfo = {}
1.4 casties 745: current = getInt(current)
746: pageinfo['current'] = current
747: rows = int(rows or self.thumbrows)
748: pageinfo['rows'] = rows
749: cols = int(cols or self.thumbcols)
750: pageinfo['cols'] = cols
751: grpsize = cols * rows
752: pageinfo['groupsize'] = grpsize
1.28 casties 753: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
754: # int(current / grpsize) * grpsize +1))
1.3 casties 755: pageinfo['start'] = start
1.4 casties 756: pageinfo['end'] = start + grpsize
1.44 casties 757: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 758: np = int(docinfo['numPages'])
759: pageinfo['end'] = min(pageinfo['end'], np)
760: pageinfo['numgroups'] = int(np / grpsize)
761: if np % grpsize > 0:
1.69 abukhman 762: pageinfo['numgroups'] += 1
1.44 casties 763: pageinfo['viewMode'] = viewMode
764: pageinfo['tocMode'] = tocMode
1.98 abukhman 765: #pageinfo['characterNormalization'] =characterNormalization
766: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')
1.45 abukhman 767: pageinfo['query'] = self.REQUEST.get('query',' ')
768: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
769: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 770: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 771: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 772: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 773: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 774: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 775: toc = int (pageinfo['tocPN'])
776: pageinfo['textPages'] =int (toc)
1.90 abukhman 777:
1.48 abukhman 778: if 'tocSize_%s'%tocMode in docinfo:
779: tocSize = int(docinfo['tocSize_%s'%tocMode])
780: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 781: # cached toc
1.48 abukhman 782: if tocSize%tocPageSize>0:
783: tocPages=tocSize/tocPageSize+1
784: else:
785: tocPages=tocSize/tocPageSize
1.69 abukhman 786: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 787: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 788: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 789: return pageinfo
790:
1.69 abukhman 791: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 792: """init document viewer"""
793: self.title=title
794: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 795: self.thumbrows = thumbrows
796: self.thumbcols = thumbcols
1.8 casties 797: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 798: if RESPONSE is not None:
799: RESPONSE.redirect('manage_main')
1.1 dwinter 800:
801: def manage_AddDocumentViewerForm(self):
802: """add the viewer form"""
1.3 casties 803: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 804: return pt()
805:
1.43 casties 806: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 807: """add the viewer"""
1.43 casties 808: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 809: self._setObject(id,newObj)
810:
811: if RESPONSE is not None:
812: RESPONSE.redirect('manage_main')
1.3 casties 813:
814: ## DocumentViewerTemplate class
815: class DocumentViewerTemplate(ZopePageTemplate):
816: """Template for document viewer"""
817: meta_type="DocumentViewer Template"
818:
819:
820: def manage_addDocumentViewerTemplateForm(self):
821: """Form for adding"""
822: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
823: return pt()
824:
825: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
826: REQUEST=None, submit=None):
827: "Add a Page Template with optional file content."
828:
829: self._setObject(id, DocumentViewerTemplate(id))
830: ob = getattr(self, id)
1.23 dwinter 831: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 832: logging.info("txt %s:"%txt)
1.23 dwinter 833: ob.pt_edit(txt,"text/html")
1.3 casties 834: if title:
835: ob.pt_setTitle(title)
836: try:
837: u = self.DestinationURL()
838: except AttributeError:
839: u = REQUEST['URL1']
840:
841: u = "%s/%s" % (u, urllib.quote(id))
842: REQUEST.RESPONSE.redirect(u+'/manage_main')
843: return ''
844:
845:
1.14 casties 846:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>