Annotation of documentViewer/documentViewer.py, revision 1.120
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
1.119 abukhman 8: from Products.zogiLib.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)
1.120 ! abukhman 188:
! 189: def getGisPlaces(self, **args):
! 190: """get search"""
! 191: return self.template.fulltextclient.getGisPlaces(**args)
1.70 casties 192:
1.72 casties 193: def getNumPages(self, docinfo):
1.70 casties 194: """get numpages"""
1.72 casties 195: return self.template.fulltextclient.getNumPages(docinfo)
1.100 abukhman 196:
197: def getNumTextPages(self, docinfo):
198: """get numpages text"""
199: return self.template.fulltextclient.getNumTextPages(docinfo)
200:
1.70 casties 201: def getTranslate(self, **args):
202: """get translate"""
203: return self.template.fulltextclient.getTranslate(**args)
204:
205: def getLemma(self, **args):
206: """get lemma"""
207: return self.template.fulltextclient.getLemma(**args)
208:
209: def getToc(self, **args):
210: """get toc"""
211: return self.template.fulltextclient.getToc(**args)
212:
213: def getTocPage(self, **args):
214: """get tocpage"""
215: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 216:
1.70 casties 217:
1.32 dwinter 218: security.declareProtected('View','thumbs_rss')
219: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
220: '''
221: view it
222: @param mode: defines how to access the document behind url
223: @param url: url which contains display information
224: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
225:
226: '''
1.95 abukhman 227: logging.debug("HHHHHHHHHHHHHH:load the rss")
228: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 229:
230: if not hasattr(self, 'template'):
231: # create template folder if it doesn't exist
232: self.manage_addFolder('template')
233:
234: if not self.digilibBaseUrl:
235: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
236:
237: docinfo = self.getDocinfo(mode=mode,url=url)
238: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
239: pt = getattr(self.template, 'thumbs_main_rss')
240:
241: if viewMode=="auto": # automodus gewaehlt
1.70 casties 242: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 243: viewMode="text"
244: else:
245: viewMode="images"
246:
247: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
248:
1.3 casties 249: security.declareProtected('View','index_html')
1.97 abukhman 250: 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 251: '''
252: view it
1.26 casties 253: @param mode: defines how to access the document behind url
1.3 casties 254: @param url: url which contains display information
1.44 casties 255: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 256: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 257: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 258: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 259: '''
260:
1.95 abukhman 261: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 262:
1.3 casties 263: if not hasattr(self, 'template'):
1.43 casties 264: # this won't work
265: logging.error("template folder missing!")
266: return "ERROR: template folder missing!"
1.3 casties 267:
1.43 casties 268: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 269: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 270:
1.4 casties 271: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 272:
1.44 casties 273: if tocMode != "thumbs":
274: # get table of contents
275: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 276:
1.21 dwinter 277: if viewMode=="auto": # automodus gewaehlt
1.71 casties 278: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.68 casties 279: viewMode="text_dict"
1.21 dwinter 280: else:
281: viewMode="images"
1.44 casties 282:
1.97 abukhman 283: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
1.68 casties 284:
1.44 casties 285: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 286: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 287:
1.36 dwinter 288: def generateMarks(self,mk):
289: ret=""
1.44 casties 290: if mk is None:
291: return ""
1.73 casties 292: if not isinstance(mk, list):
1.71 casties 293: mk=[mk]
1.36 dwinter 294: for m in mk:
1.37 dwinter 295: ret+="mk=%s"%m
1.36 dwinter 296: return ret
1.43 casties 297:
1.44 casties 298:
1.43 casties 299: def findDigilibUrl(self):
300: """try to get the digilib URL from zogilib"""
301: url = self.template.zogilib.getDLBaseUrl()
302: return url
1.67 casties 303:
304: def getDocumentViewerURL(self):
305: """returns the URL of this instance"""
306: return self.absolute_url()
1.43 casties 307:
308: def getStyle(self, idx, selected, style=""):
309: """returns a string with the given style and append 'sel' if path == selected."""
310: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
311: if idx == selected:
312: return style + 'sel'
313: else:
314: return style
1.36 dwinter 315:
1.4 casties 316: def getLink(self,param=None,val=None):
317: """link to documentviewer with parameter param set to val"""
1.9 casties 318: params=self.REQUEST.form.copy()
1.4 casties 319: if param is not None:
1.7 casties 320: if val is None:
321: if params.has_key(param):
322: del params[param]
1.4 casties 323: else:
1.9 casties 324: params[param] = str(val)
1.43 casties 325:
326: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 327: params["mode"] = "imagepath"
328: params["url"] = getParentDir(params["url"])
1.7 casties 329:
1.9 casties 330: # quote values and assemble into query string
1.74 casties 331: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
332: ps = urllib.urlencode(params)
1.9 casties 333: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 334: return url
335:
1.32 dwinter 336: def getLinkAmp(self,param=None,val=None):
337: """link to documentviewer with parameter param set to val"""
338: params=self.REQUEST.form.copy()
339: if param is not None:
340: if val is None:
341: if params.has_key(param):
342: del params[param]
343: else:
344: params[param] = str(val)
345:
346: # quote values and assemble into query string
1.95 abukhman 347: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 348: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
349: url=self.REQUEST['URL1']+"?"+ps
350: return url
1.40 casties 351:
1.26 casties 352: def getInfo_xml(self,url,mode):
353: """returns info about the document as XML"""
354:
355: if not self.digilibBaseUrl:
356: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
357:
358: docinfo = self.getDocinfo(mode=mode,url=url)
359: pt = getattr(self.template, 'info_xml')
360: return pt(docinfo=docinfo)
361:
1.4 casties 362:
1.9 casties 363: def isAccessible(self, docinfo):
1.8 casties 364: """returns if access to the resource is granted"""
365: access = docinfo.get('accessType', None)
1.95 abukhman 366: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 367: if access is not None and access == 'free':
1.95 abukhman 368: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 369: return True
1.17 casties 370: elif access is None or access in self.authgroups:
1.9 casties 371: # only local access -- only logged in users
372: user = getSecurityManager().getUser()
1.95 abukhman 373: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 374: if user is not None:
375: #print "user: ", user
376: return (user.getUserName() != "Anonymous User")
377: else:
378: return False
1.8 casties 379:
1.95 abukhman 380: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 381: return False
1.9 casties 382:
1.8 casties 383:
1.35 dwinter 384: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 385: """gibt param von dlInfo aus"""
1.7 casties 386: if docinfo is None:
387: docinfo = {}
1.35 dwinter 388:
389: for x in range(cut):
1.38 dwinter 390:
1.35 dwinter 391: path=getParentDir(path)
1.38 dwinter 392:
1.13 casties 393: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 394:
1.95 abukhman 395: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 396:
1.70 casties 397: txt = getHttpData(infoUrl)
398: if txt is None:
1.13 casties 399: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 400:
401: dom = Parse(txt)
1.10 casties 402: sizes=dom.xpath("//dir/size")
1.95 abukhman 403: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 404:
1.10 casties 405: if sizes:
406: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 407: else:
408: docinfo['numPages'] = 0
1.43 casties 409:
410: # TODO: produce and keep list of image names and numbers
1.7 casties 411:
412: return docinfo
1.8 casties 413:
1.99 dwinter 414: def getIndexMetaPath(self,url):
415: """gib nur den Pfad zurueck"""
416: regexp = re.compile(r".*(experimental|permanent)/(.*)")
417: regpath = regexp.match(url)
418: if (regpath==None):
419: return ""
1.110 abukhman 420: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 421: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
422:
1.111 abukhman 423:
424:
1.99 dwinter 425: def getIndexMetaUrl(self,url):
426: """returns utr of index.meta document at url"""
427:
1.12 casties 428: metaUrl = None
1.9 casties 429: if url.startswith("http://"):
430: # real URL
1.12 casties 431: metaUrl = url
1.9 casties 432: else:
433: # online path
434: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 435: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 436: if not metaUrl.endswith("index.meta"):
437: metaUrl += "/index.meta"
1.99 dwinter 438:
439: return metaUrl
440:
441: def getDomFromIndexMeta(self, url):
442: """get dom from index meta"""
443: dom = None
444: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 445:
1.99 dwinter 446: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 447: txt=getHttpData(metaUrl)
448: if txt is None:
1.12 casties 449: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 450:
451: dom = Parse(txt)
1.9 casties 452: return dom
1.20 dwinter 453:
454: def getPresentationInfoXML(self, url):
455: """returns dom of info.xml document at url"""
456: dom = None
457: metaUrl = None
458: if url.startswith("http://"):
459: # real URL
460: metaUrl = url
461: else:
462: # online path
463: server=self.digilibBaseUrl+"/servlet/Texter?fn="
464: metaUrl=server+url.replace("/mpiwg/online","")
465:
1.70 casties 466: txt=getHttpData(metaUrl)
467: if txt is None:
1.20 dwinter 468: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 469:
470: dom = Parse(txt)
1.20 dwinter 471: return dom
1.9 casties 472:
473:
1.33 dwinter 474: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 475: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 476: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 477:
478: access = None
479:
480: if docinfo is None:
481: docinfo = {}
482:
483: if dom is None:
1.38 dwinter 484: for x in range(cut):
1.33 dwinter 485: path=getParentDir(path)
1.99 dwinter 486: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 487:
1.8 casties 488: acctype = dom.xpath("//access-conditions/access/@type")
489: if acctype and (len(acctype)>0):
490: access=acctype[0].value
1.9 casties 491: if access in ['group', 'institution']:
1.8 casties 492: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
493:
494: docinfo['accessType'] = access
495: return docinfo
1.6 casties 496:
1.8 casties 497:
1.33 dwinter 498: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 499: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 500: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 501:
1.3 casties 502: if docinfo is None:
503: docinfo = {}
1.38 dwinter 504:
1.3 casties 505: if dom is None:
1.38 dwinter 506: for x in range(cut):
1.33 dwinter 507: path=getParentDir(path)
1.99 dwinter 508: dom = self.getDomFromIndexMeta(path)
509:
510: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 511:
1.95 abukhman 512: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 513: # put in all raw bib fields as dict "bib"
514: bib = dom.xpath("//bib/*")
515: if bib and len(bib)>0:
516: bibinfo = {}
517: for e in bib:
518: bibinfo[e.localName] = getTextFromNode(e)
519: docinfo['bib'] = bibinfo
520:
521: # extract some fields (author, title, year) according to their mapping
1.4 casties 522: metaData=self.metadata.main.meta.bib
523: bibtype=dom.xpath("//bib/@type")
524: if bibtype and (len(bibtype)>0):
525: bibtype=bibtype[0].value
1.2 dwinter 526: else:
1.4 casties 527: bibtype="generic"
1.27 casties 528:
1.4 casties 529: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 530: docinfo['bib_type'] = bibtype
1.4 casties 531: bibmap=metaData.generateMappingForType(bibtype)
1.99 dwinter 532: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
533: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
1.8 casties 534: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 535: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 536: try:
537: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
538: except: pass
539: try:
540: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
541: except: pass
542: try:
543: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
544: except: pass
1.95 abukhman 545: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 546: try:
547: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
548: except:
549: docinfo['lang']=''
1.113 abukhman 550:
1.3 casties 551: return docinfo
1.42 abukhman 552:
1.104 abukhman 553:
554: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
555: """gets name info from the index.meta file at path or given by dom"""
556: if docinfo is None:
557: docinfo = {}
558:
559: if dom is None:
560: for x in range(cut):
561: path=getParentDir(path)
562: dom = self.getDomFromIndexMeta(path)
563:
1.112 abukhman 564: #docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.104 abukhman 565:
1.105 abukhman 566: #result= dom.xpath("//result/resultPage")
567: #docinfo['numPages']=int(getTextFromNode(result[0]))
1.104 abukhman 568:
1.113 abukhman 569: #result =dom.xpath("//name")
1.115 abukhman 570: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
1.116 abukhman 571: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.113 abukhman 572:
1.104 abukhman 573: #logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
574: return docinfo
1.42 abukhman 575:
1.43 casties 576: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
577: """parse texttool tag in index meta"""
1.95 abukhman 578: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 579: if docinfo is None:
580: docinfo = {}
581: if docinfo.get('lang', None) is None:
582: docinfo['lang'] = '' # default keine Sprache gesetzt
583: if dom is None:
1.99 dwinter 584: dom = self.getDomFromIndexMeta(url)
1.43 casties 585:
586: archivePath = None
587: archiveName = None
588:
589: archiveNames = dom.xpath("//resource/name")
590: if archiveNames and (len(archiveNames) > 0):
591: archiveName = getTextFromNode(archiveNames[0])
592: else:
1.70 casties 593: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 594:
595: archivePaths = dom.xpath("//resource/archive-path")
596: if archivePaths and (len(archivePaths) > 0):
597: archivePath = getTextFromNode(archivePaths[0])
598: # clean up archive path
599: if archivePath[0] != '/':
600: archivePath = '/' + archivePath
601: if archiveName and (not archivePath.endswith(archiveName)):
602: archivePath += "/" + archiveName
603: else:
604: # try to get archive-path from url
1.95 abukhman 605: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 606: if (not url.startswith('http')):
607: archivePath = url.replace('index.meta', '')
608:
609: if archivePath is None:
610: # we balk without archive-path
611: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
612:
613: imageDirs = dom.xpath("//texttool/image")
614: if imageDirs and (len(imageDirs) > 0):
615: imageDir = getTextFromNode(imageDirs[0])
616:
617: else:
618: # we balk with no image tag / not necessary anymore because textmode is now standard
619: #raise IOError("No text-tool info in %s"%(url))
620: imageDir = ""
621: #xquery="//pb"
622: docinfo['imagePath'] = "" # keine Bilder
623: docinfo['imageURL'] = ""
624:
625: if imageDir and archivePath:
626: #print "image: ", imageDir, " archivepath: ", archivePath
627: imageDir = os.path.join(archivePath, imageDir)
628: imageDir = imageDir.replace("/mpiwg/online", '')
629: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
630: docinfo['imagePath'] = imageDir
631:
632: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
633:
634: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
635: if viewerUrls and (len(viewerUrls) > 0):
636: viewerUrl = getTextFromNode(viewerUrls[0])
637: docinfo['viewerURL'] = viewerUrl
1.70 casties 638:
639: # old style text URL
1.43 casties 640: textUrls = dom.xpath("//texttool/text")
641: if textUrls and (len(textUrls) > 0):
642: textUrl = getTextFromNode(textUrls[0])
643: if urlparse.urlparse(textUrl)[0] == "": #keine url
644: textUrl = os.path.join(archivePath, textUrl)
645: # fix URLs starting with /mpiwg/online
646: if textUrl.startswith("/mpiwg/online"):
647: textUrl = textUrl.replace("/mpiwg/online", '', 1)
648:
649: docinfo['textURL'] = textUrl
650:
1.70 casties 651: # new style text-url-path
1.43 casties 652: textUrls = dom.xpath("//texttool/text-url-path")
653: if textUrls and (len(textUrls) > 0):
654: textUrl = getTextFromNode(textUrls[0])
1.51 casties 655: docinfo['textURLPath'] = textUrl
656: if not docinfo['imagePath']:
657: # text-only, no page images
1.103 abukhman 658: docinfo = self.getNumTextPages(docinfo)
1.43 casties 659:
660: presentationUrls = dom.xpath("//texttool/presentation")
661: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.114 abukhman 662: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.43 casties 663:
664: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
665: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
666: # durch den relativen Pfad auf die presentation infos
667: presentationPath = getTextFromNode(presentationUrls[0])
668: if url.endswith("index.meta"):
669: presentationUrl = url.replace('index.meta', presentationPath)
670: else:
671: presentationUrl = url + "/" + presentationPath
1.51 casties 672:
1.43 casties 673: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
674:
675: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 676:
1.43 casties 677: return docinfo
1.3 casties 678:
1.20 dwinter 679:
680: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
681: """gets the bibliographical information from the preseantion entry in texttools
682: """
683: dom=self.getPresentationInfoXML(url)
1.29 casties 684: try:
685: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
686: except:
687: pass
688: try:
689: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
690: except:
691: pass
692: try:
693: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
694: except:
695: pass
1.20 dwinter 696: return docinfo
697:
1.33 dwinter 698: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 699: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 700: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 701: if docinfo is None:
702: docinfo = {}
1.6 casties 703: path=path.replace("/mpiwg/online","")
1.3 casties 704: docinfo['imagePath'] = path
1.35 dwinter 705: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 706:
1.39 dwinter 707: pathorig=path
1.38 dwinter 708: for x in range(cut):
709: path=getParentDir(path)
1.95 abukhman 710: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 711: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 712: docinfo['imageURL'] = imageUrl
713:
1.39 dwinter 714: #path ist the path to the images it assumes that the index.meta file is one level higher.
715: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
716: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 717: return docinfo
718:
1.2 dwinter 719:
1.3 casties 720: def getDocinfo(self, mode, url):
721: """returns docinfo depending on mode"""
1.95 abukhman 722: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 723: # look for cached docinfo in session
1.21 dwinter 724: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 725: docinfo = self.REQUEST.SESSION['docinfo']
726: # check if its still current
727: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.95 abukhman 728: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 729: return docinfo
730: # new docinfo
731: docinfo = {'mode': mode, 'url': url}
732: if mode=="texttool": #index.meta with texttool information
733: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
734: elif mode=="imagepath":
735: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 736: elif mode=="filepath":
1.37 dwinter 737: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 738: else:
1.95 abukhman 739: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 740: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 741:
1.95 abukhman 742: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 743: self.REQUEST.SESSION['docinfo'] = docinfo
744: return docinfo
1.69 abukhman 745:
1.97 abukhman 746: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
1.3 casties 747: """returns pageinfo with the given parameters"""
748: pageinfo = {}
1.4 casties 749: current = getInt(current)
750: pageinfo['current'] = current
751: rows = int(rows or self.thumbrows)
752: pageinfo['rows'] = rows
753: cols = int(cols or self.thumbcols)
754: pageinfo['cols'] = cols
755: grpsize = cols * rows
756: pageinfo['groupsize'] = grpsize
1.28 casties 757: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
758: # int(current / grpsize) * grpsize +1))
1.3 casties 759: pageinfo['start'] = start
1.4 casties 760: pageinfo['end'] = start + grpsize
1.44 casties 761: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 762: np = int(docinfo['numPages'])
763: pageinfo['end'] = min(pageinfo['end'], np)
764: pageinfo['numgroups'] = int(np / grpsize)
765: if np % grpsize > 0:
1.69 abukhman 766: pageinfo['numgroups'] += 1
1.44 casties 767: pageinfo['viewMode'] = viewMode
768: pageinfo['tocMode'] = tocMode
1.98 abukhman 769: #pageinfo['characterNormalization'] =characterNormalization
770: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')
1.45 abukhman 771: pageinfo['query'] = self.REQUEST.get('query',' ')
772: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
773: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 774: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 775: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 776: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 777: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 778: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 779: toc = int (pageinfo['tocPN'])
780: pageinfo['textPages'] =int (toc)
1.90 abukhman 781:
1.48 abukhman 782: if 'tocSize_%s'%tocMode in docinfo:
783: tocSize = int(docinfo['tocSize_%s'%tocMode])
784: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 785: # cached toc
1.48 abukhman 786: if tocSize%tocPageSize>0:
787: tocPages=tocSize/tocPageSize+1
788: else:
789: tocPages=tocSize/tocPageSize
1.69 abukhman 790: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 791: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 792: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 793: return pageinfo
794:
1.69 abukhman 795: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 796: """init document viewer"""
797: self.title=title
798: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 799: self.thumbrows = thumbrows
800: self.thumbcols = thumbcols
1.8 casties 801: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 802: if RESPONSE is not None:
803: RESPONSE.redirect('manage_main')
1.1 dwinter 804:
805: def manage_AddDocumentViewerForm(self):
806: """add the viewer form"""
1.3 casties 807: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 808: return pt()
809:
1.43 casties 810: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 811: """add the viewer"""
1.43 casties 812: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 813: self._setObject(id,newObj)
814:
815: if RESPONSE is not None:
816: RESPONSE.redirect('manage_main')
1.3 casties 817:
818: ## DocumentViewerTemplate class
819: class DocumentViewerTemplate(ZopePageTemplate):
820: """Template for document viewer"""
821: meta_type="DocumentViewer Template"
822:
823:
824: def manage_addDocumentViewerTemplateForm(self):
825: """Form for adding"""
826: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
827: return pt()
828:
829: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
830: REQUEST=None, submit=None):
831: "Add a Page Template with optional file content."
832:
833: self._setObject(id, DocumentViewerTemplate(id))
834: ob = getattr(self, id)
1.23 dwinter 835: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 836: logging.info("txt %s:"%txt)
1.23 dwinter 837: ob.pt_edit(txt,"text/html")
1.3 casties 838: if title:
839: ob.pt_setTitle(title)
840: try:
841: u = self.DestinationURL()
842: except AttributeError:
843: u = REQUEST['URL1']
844:
845: u = "%s/%s" % (u, urllib.quote(id))
846: REQUEST.RESPONSE.redirect(u+'/manage_main')
847: return ''
848:
849:
1.14 casties 850:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>