Annotation of documentViewer/documentViewer.py, revision 1.122
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):
1.121 abukhman 190: """get gis places"""
1.120 abukhman 191: return self.template.fulltextclient.getGisPlaces(**args)
1.121 abukhman 192:
193: def getAllGisPlaces(self, **args):
1.122 ! abukhman 194: """get all gis places """
! 195: return self.template.fulltextclient.getAllGisPlaces(**args)
! 196:
! 197: def getOrigPages(self, **args):
! 198: """get original page number """
! 199: return self.template.fulltextclient.getOrigPages(**args)
! 200:
1.72 casties 201: def getNumPages(self, docinfo):
1.70 casties 202: """get numpages"""
1.72 casties 203: return self.template.fulltextclient.getNumPages(docinfo)
1.100 abukhman 204:
205: def getNumTextPages(self, docinfo):
206: """get numpages text"""
207: return self.template.fulltextclient.getNumTextPages(docinfo)
208:
1.70 casties 209: def getTranslate(self, **args):
210: """get translate"""
211: return self.template.fulltextclient.getTranslate(**args)
212:
213: def getLemma(self, **args):
214: """get lemma"""
215: return self.template.fulltextclient.getLemma(**args)
216:
217: def getToc(self, **args):
218: """get toc"""
219: return self.template.fulltextclient.getToc(**args)
220:
221: def getTocPage(self, **args):
222: """get tocpage"""
223: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 224:
1.70 casties 225:
1.32 dwinter 226: security.declareProtected('View','thumbs_rss')
227: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
228: '''
229: view it
230: @param mode: defines how to access the document behind url
231: @param url: url which contains display information
232: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
233:
234: '''
1.95 abukhman 235: logging.debug("HHHHHHHHHHHHHH:load the rss")
236: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 237:
238: if not hasattr(self, 'template'):
239: # create template folder if it doesn't exist
240: self.manage_addFolder('template')
241:
242: if not self.digilibBaseUrl:
243: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
244:
245: docinfo = self.getDocinfo(mode=mode,url=url)
246: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
247: pt = getattr(self.template, 'thumbs_main_rss')
248:
249: if viewMode=="auto": # automodus gewaehlt
1.70 casties 250: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 251: viewMode="text"
252: else:
253: viewMode="images"
254:
255: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
256:
1.3 casties 257: security.declareProtected('View','index_html')
1.97 abukhman 258: 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 259: '''
260: view it
1.26 casties 261: @param mode: defines how to access the document behind url
1.3 casties 262: @param url: url which contains display information
1.44 casties 263: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 264: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 265: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 266: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 267: '''
268:
1.95 abukhman 269: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 270:
1.3 casties 271: if not hasattr(self, 'template'):
1.43 casties 272: # this won't work
273: logging.error("template folder missing!")
274: return "ERROR: template folder missing!"
1.3 casties 275:
1.43 casties 276: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 277: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 278:
1.4 casties 279: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 280:
1.44 casties 281: if tocMode != "thumbs":
282: # get table of contents
283: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 284:
1.21 dwinter 285: if viewMode=="auto": # automodus gewaehlt
1.71 casties 286: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.68 casties 287: viewMode="text_dict"
1.21 dwinter 288: else:
289: viewMode="images"
1.44 casties 290:
1.97 abukhman 291: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
1.68 casties 292:
1.44 casties 293: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 294: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 295:
1.36 dwinter 296: def generateMarks(self,mk):
297: ret=""
1.44 casties 298: if mk is None:
299: return ""
1.73 casties 300: if not isinstance(mk, list):
1.71 casties 301: mk=[mk]
1.36 dwinter 302: for m in mk:
1.37 dwinter 303: ret+="mk=%s"%m
1.36 dwinter 304: return ret
1.43 casties 305:
1.44 casties 306:
1.43 casties 307: def findDigilibUrl(self):
308: """try to get the digilib URL from zogilib"""
309: url = self.template.zogilib.getDLBaseUrl()
310: return url
1.67 casties 311:
312: def getDocumentViewerURL(self):
313: """returns the URL of this instance"""
314: return self.absolute_url()
1.43 casties 315:
316: def getStyle(self, idx, selected, style=""):
317: """returns a string with the given style and append 'sel' if path == selected."""
318: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
319: if idx == selected:
320: return style + 'sel'
321: else:
322: return style
1.36 dwinter 323:
1.4 casties 324: def getLink(self,param=None,val=None):
325: """link to documentviewer with parameter param set to val"""
1.9 casties 326: params=self.REQUEST.form.copy()
1.4 casties 327: if param is not None:
1.7 casties 328: if val is None:
329: if params.has_key(param):
330: del params[param]
1.4 casties 331: else:
1.9 casties 332: params[param] = str(val)
1.43 casties 333:
334: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 335: params["mode"] = "imagepath"
336: params["url"] = getParentDir(params["url"])
1.7 casties 337:
1.9 casties 338: # quote values and assemble into query string
1.74 casties 339: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
340: ps = urllib.urlencode(params)
1.9 casties 341: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 342: return url
343:
1.32 dwinter 344: def getLinkAmp(self,param=None,val=None):
345: """link to documentviewer with parameter param set to val"""
346: params=self.REQUEST.form.copy()
347: if param is not None:
348: if val is None:
349: if params.has_key(param):
350: del params[param]
351: else:
352: params[param] = str(val)
353:
354: # quote values and assemble into query string
1.95 abukhman 355: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 356: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
357: url=self.REQUEST['URL1']+"?"+ps
358: return url
1.40 casties 359:
1.26 casties 360: def getInfo_xml(self,url,mode):
361: """returns info about the document as XML"""
362:
363: if not self.digilibBaseUrl:
364: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
365:
366: docinfo = self.getDocinfo(mode=mode,url=url)
367: pt = getattr(self.template, 'info_xml')
368: return pt(docinfo=docinfo)
369:
1.4 casties 370:
1.9 casties 371: def isAccessible(self, docinfo):
1.8 casties 372: """returns if access to the resource is granted"""
373: access = docinfo.get('accessType', None)
1.95 abukhman 374: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 375: if access is not None and access == 'free':
1.95 abukhman 376: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 377: return True
1.17 casties 378: elif access is None or access in self.authgroups:
1.9 casties 379: # only local access -- only logged in users
380: user = getSecurityManager().getUser()
1.95 abukhman 381: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 382: if user is not None:
383: #print "user: ", user
384: return (user.getUserName() != "Anonymous User")
385: else:
386: return False
1.8 casties 387:
1.95 abukhman 388: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 389: return False
1.9 casties 390:
1.8 casties 391:
1.35 dwinter 392: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 393: """gibt param von dlInfo aus"""
1.7 casties 394: if docinfo is None:
395: docinfo = {}
1.35 dwinter 396:
397: for x in range(cut):
1.38 dwinter 398:
1.35 dwinter 399: path=getParentDir(path)
1.38 dwinter 400:
1.13 casties 401: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 402:
1.95 abukhman 403: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 404:
1.70 casties 405: txt = getHttpData(infoUrl)
406: if txt is None:
1.13 casties 407: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 408:
409: dom = Parse(txt)
1.10 casties 410: sizes=dom.xpath("//dir/size")
1.95 abukhman 411: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 412:
1.10 casties 413: if sizes:
414: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 415: else:
416: docinfo['numPages'] = 0
1.43 casties 417:
418: # TODO: produce and keep list of image names and numbers
1.7 casties 419:
420: return docinfo
1.8 casties 421:
1.99 dwinter 422: def getIndexMetaPath(self,url):
423: """gib nur den Pfad zurueck"""
424: regexp = re.compile(r".*(experimental|permanent)/(.*)")
425: regpath = regexp.match(url)
426: if (regpath==None):
427: return ""
1.110 abukhman 428: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 429: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
430:
1.111 abukhman 431:
432:
1.99 dwinter 433: def getIndexMetaUrl(self,url):
434: """returns utr of index.meta document at url"""
435:
1.12 casties 436: metaUrl = None
1.9 casties 437: if url.startswith("http://"):
438: # real URL
1.12 casties 439: metaUrl = url
1.9 casties 440: else:
441: # online path
442: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 443: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 444: if not metaUrl.endswith("index.meta"):
445: metaUrl += "/index.meta"
1.99 dwinter 446:
447: return metaUrl
448:
449: def getDomFromIndexMeta(self, url):
450: """get dom from index meta"""
451: dom = None
452: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 453:
1.99 dwinter 454: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 455: txt=getHttpData(metaUrl)
456: if txt is None:
1.12 casties 457: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 458:
459: dom = Parse(txt)
1.9 casties 460: return dom
1.20 dwinter 461:
462: def getPresentationInfoXML(self, url):
463: """returns dom of info.xml document at url"""
464: dom = None
465: metaUrl = None
466: if url.startswith("http://"):
467: # real URL
468: metaUrl = url
469: else:
470: # online path
471: server=self.digilibBaseUrl+"/servlet/Texter?fn="
472: metaUrl=server+url.replace("/mpiwg/online","")
473:
1.70 casties 474: txt=getHttpData(metaUrl)
475: if txt is None:
1.20 dwinter 476: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 477:
478: dom = Parse(txt)
1.20 dwinter 479: return dom
1.9 casties 480:
481:
1.33 dwinter 482: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 483: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 484: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 485:
486: access = None
487:
488: if docinfo is None:
489: docinfo = {}
490:
491: if dom is None:
1.38 dwinter 492: for x in range(cut):
1.33 dwinter 493: path=getParentDir(path)
1.99 dwinter 494: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 495:
1.8 casties 496: acctype = dom.xpath("//access-conditions/access/@type")
497: if acctype and (len(acctype)>0):
498: access=acctype[0].value
1.9 casties 499: if access in ['group', 'institution']:
1.8 casties 500: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
501:
502: docinfo['accessType'] = access
503: return docinfo
1.6 casties 504:
1.8 casties 505:
1.33 dwinter 506: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 507: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 508: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 509:
1.3 casties 510: if docinfo is None:
511: docinfo = {}
1.38 dwinter 512:
1.3 casties 513: if dom is None:
1.38 dwinter 514: for x in range(cut):
1.33 dwinter 515: path=getParentDir(path)
1.99 dwinter 516: dom = self.getDomFromIndexMeta(path)
517:
518: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 519:
1.95 abukhman 520: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 521: # put in all raw bib fields as dict "bib"
522: bib = dom.xpath("//bib/*")
523: if bib and len(bib)>0:
524: bibinfo = {}
525: for e in bib:
526: bibinfo[e.localName] = getTextFromNode(e)
527: docinfo['bib'] = bibinfo
528:
529: # extract some fields (author, title, year) according to their mapping
1.4 casties 530: metaData=self.metadata.main.meta.bib
531: bibtype=dom.xpath("//bib/@type")
532: if bibtype and (len(bibtype)>0):
533: bibtype=bibtype[0].value
1.2 dwinter 534: else:
1.4 casties 535: bibtype="generic"
1.27 casties 536:
1.4 casties 537: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 538: docinfo['bib_type'] = bibtype
1.4 casties 539: bibmap=metaData.generateMappingForType(bibtype)
1.99 dwinter 540: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
541: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
1.8 casties 542: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 543: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 544: try:
545: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
546: except: pass
547: try:
548: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
549: except: pass
550: try:
551: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
552: except: pass
1.95 abukhman 553: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 554: try:
555: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
556: except:
557: docinfo['lang']=''
1.113 abukhman 558:
1.3 casties 559: return docinfo
1.42 abukhman 560:
1.104 abukhman 561:
562: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
563: """gets name info from the index.meta file at path or given by dom"""
564: if docinfo is None:
565: docinfo = {}
566:
567: if dom is None:
568: for x in range(cut):
569: path=getParentDir(path)
570: dom = self.getDomFromIndexMeta(path)
571:
1.112 abukhman 572: #docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.104 abukhman 573:
1.105 abukhman 574: #result= dom.xpath("//result/resultPage")
575: #docinfo['numPages']=int(getTextFromNode(result[0]))
1.104 abukhman 576:
1.113 abukhman 577: #result =dom.xpath("//name")
1.115 abukhman 578: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
1.116 abukhman 579: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.113 abukhman 580:
1.104 abukhman 581: #logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
582: return docinfo
1.42 abukhman 583:
1.43 casties 584: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
585: """parse texttool tag in index meta"""
1.95 abukhman 586: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 587: if docinfo is None:
588: docinfo = {}
589: if docinfo.get('lang', None) is None:
590: docinfo['lang'] = '' # default keine Sprache gesetzt
591: if dom is None:
1.99 dwinter 592: dom = self.getDomFromIndexMeta(url)
1.43 casties 593:
594: archivePath = None
595: archiveName = None
596:
597: archiveNames = dom.xpath("//resource/name")
598: if archiveNames and (len(archiveNames) > 0):
599: archiveName = getTextFromNode(archiveNames[0])
600: else:
1.70 casties 601: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 602:
603: archivePaths = dom.xpath("//resource/archive-path")
604: if archivePaths and (len(archivePaths) > 0):
605: archivePath = getTextFromNode(archivePaths[0])
606: # clean up archive path
607: if archivePath[0] != '/':
608: archivePath = '/' + archivePath
609: if archiveName and (not archivePath.endswith(archiveName)):
610: archivePath += "/" + archiveName
611: else:
612: # try to get archive-path from url
1.95 abukhman 613: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 614: if (not url.startswith('http')):
615: archivePath = url.replace('index.meta', '')
616:
617: if archivePath is None:
618: # we balk without archive-path
619: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
620:
621: imageDirs = dom.xpath("//texttool/image")
622: if imageDirs and (len(imageDirs) > 0):
623: imageDir = getTextFromNode(imageDirs[0])
624:
625: else:
626: # we balk with no image tag / not necessary anymore because textmode is now standard
627: #raise IOError("No text-tool info in %s"%(url))
628: imageDir = ""
629: #xquery="//pb"
630: docinfo['imagePath'] = "" # keine Bilder
631: docinfo['imageURL'] = ""
632:
633: if imageDir and archivePath:
634: #print "image: ", imageDir, " archivepath: ", archivePath
635: imageDir = os.path.join(archivePath, imageDir)
636: imageDir = imageDir.replace("/mpiwg/online", '')
637: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
638: docinfo['imagePath'] = imageDir
639:
640: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
641:
642: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
643: if viewerUrls and (len(viewerUrls) > 0):
644: viewerUrl = getTextFromNode(viewerUrls[0])
645: docinfo['viewerURL'] = viewerUrl
1.70 casties 646:
647: # old style text URL
1.43 casties 648: textUrls = dom.xpath("//texttool/text")
649: if textUrls and (len(textUrls) > 0):
650: textUrl = getTextFromNode(textUrls[0])
651: if urlparse.urlparse(textUrl)[0] == "": #keine url
652: textUrl = os.path.join(archivePath, textUrl)
653: # fix URLs starting with /mpiwg/online
654: if textUrl.startswith("/mpiwg/online"):
655: textUrl = textUrl.replace("/mpiwg/online", '', 1)
656:
657: docinfo['textURL'] = textUrl
658:
1.70 casties 659: # new style text-url-path
1.43 casties 660: textUrls = dom.xpath("//texttool/text-url-path")
661: if textUrls and (len(textUrls) > 0):
662: textUrl = getTextFromNode(textUrls[0])
1.51 casties 663: docinfo['textURLPath'] = textUrl
664: if not docinfo['imagePath']:
665: # text-only, no page images
1.103 abukhman 666: docinfo = self.getNumTextPages(docinfo)
1.43 casties 667:
668: presentationUrls = dom.xpath("//texttool/presentation")
669: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.114 abukhman 670: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.43 casties 671:
672: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
673: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
674: # durch den relativen Pfad auf die presentation infos
675: presentationPath = getTextFromNode(presentationUrls[0])
676: if url.endswith("index.meta"):
677: presentationUrl = url.replace('index.meta', presentationPath)
678: else:
679: presentationUrl = url + "/" + presentationPath
1.51 casties 680:
1.43 casties 681: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
682:
683: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 684:
1.43 casties 685: return docinfo
1.3 casties 686:
1.20 dwinter 687:
688: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
689: """gets the bibliographical information from the preseantion entry in texttools
690: """
691: dom=self.getPresentationInfoXML(url)
1.29 casties 692: try:
693: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
694: except:
695: pass
696: try:
697: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
698: except:
699: pass
700: try:
701: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
702: except:
703: pass
1.20 dwinter 704: return docinfo
705:
1.33 dwinter 706: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 707: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 708: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 709: if docinfo is None:
710: docinfo = {}
1.6 casties 711: path=path.replace("/mpiwg/online","")
1.3 casties 712: docinfo['imagePath'] = path
1.35 dwinter 713: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 714:
1.39 dwinter 715: pathorig=path
1.38 dwinter 716: for x in range(cut):
717: path=getParentDir(path)
1.95 abukhman 718: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 719: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 720: docinfo['imageURL'] = imageUrl
721:
1.39 dwinter 722: #path ist the path to the images it assumes that the index.meta file is one level higher.
723: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
724: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 725: return docinfo
726:
1.2 dwinter 727:
1.3 casties 728: def getDocinfo(self, mode, url):
729: """returns docinfo depending on mode"""
1.95 abukhman 730: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 731: # look for cached docinfo in session
1.21 dwinter 732: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 733: docinfo = self.REQUEST.SESSION['docinfo']
734: # check if its still current
735: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.95 abukhman 736: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 737: return docinfo
738: # new docinfo
739: docinfo = {'mode': mode, 'url': url}
740: if mode=="texttool": #index.meta with texttool information
741: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
742: elif mode=="imagepath":
743: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 744: elif mode=="filepath":
1.37 dwinter 745: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 746: else:
1.95 abukhman 747: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 748: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 749:
1.95 abukhman 750: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 751: self.REQUEST.SESSION['docinfo'] = docinfo
752: return docinfo
1.69 abukhman 753:
1.97 abukhman 754: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
1.3 casties 755: """returns pageinfo with the given parameters"""
756: pageinfo = {}
1.4 casties 757: current = getInt(current)
758: pageinfo['current'] = current
759: rows = int(rows or self.thumbrows)
760: pageinfo['rows'] = rows
761: cols = int(cols or self.thumbcols)
762: pageinfo['cols'] = cols
763: grpsize = cols * rows
764: pageinfo['groupsize'] = grpsize
1.28 casties 765: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
766: # int(current / grpsize) * grpsize +1))
1.3 casties 767: pageinfo['start'] = start
1.4 casties 768: pageinfo['end'] = start + grpsize
1.44 casties 769: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 770: np = int(docinfo['numPages'])
771: pageinfo['end'] = min(pageinfo['end'], np)
772: pageinfo['numgroups'] = int(np / grpsize)
773: if np % grpsize > 0:
1.69 abukhman 774: pageinfo['numgroups'] += 1
1.44 casties 775: pageinfo['viewMode'] = viewMode
776: pageinfo['tocMode'] = tocMode
1.98 abukhman 777: #pageinfo['characterNormalization'] =characterNormalization
778: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')
1.45 abukhman 779: pageinfo['query'] = self.REQUEST.get('query',' ')
780: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
781: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 782: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 783: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 784: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 785: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 786: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 787: toc = int (pageinfo['tocPN'])
788: pageinfo['textPages'] =int (toc)
1.90 abukhman 789:
1.48 abukhman 790: if 'tocSize_%s'%tocMode in docinfo:
791: tocSize = int(docinfo['tocSize_%s'%tocMode])
792: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 793: # cached toc
1.48 abukhman 794: if tocSize%tocPageSize>0:
795: tocPages=tocSize/tocPageSize+1
796: else:
797: tocPages=tocSize/tocPageSize
1.69 abukhman 798: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 799: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 800: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 801: return pageinfo
802:
1.69 abukhman 803: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 804: """init document viewer"""
805: self.title=title
806: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 807: self.thumbrows = thumbrows
808: self.thumbcols = thumbcols
1.8 casties 809: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 810: if RESPONSE is not None:
811: RESPONSE.redirect('manage_main')
1.1 dwinter 812:
813: def manage_AddDocumentViewerForm(self):
814: """add the viewer form"""
1.3 casties 815: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 816: return pt()
817:
1.43 casties 818: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 819: """add the viewer"""
1.43 casties 820: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 821: self._setObject(id,newObj)
822:
823: if RESPONSE is not None:
824: RESPONSE.redirect('manage_main')
1.3 casties 825:
826: ## DocumentViewerTemplate class
827: class DocumentViewerTemplate(ZopePageTemplate):
828: """Template for document viewer"""
829: meta_type="DocumentViewer Template"
830:
831:
832: def manage_addDocumentViewerTemplateForm(self):
833: """Form for adding"""
834: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
835: return pt()
836:
837: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
838: REQUEST=None, submit=None):
839: "Add a Page Template with optional file content."
840:
841: self._setObject(id, DocumentViewerTemplate(id))
842: ob = getattr(self, id)
1.23 dwinter 843: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 844: logging.info("txt %s:"%txt)
1.23 dwinter 845: ob.pt_edit(txt,"text/html")
1.3 casties 846: if title:
847: ob.pt_setTitle(title)
848: try:
849: u = self.DestinationURL()
850: except AttributeError:
851: u = REQUEST['URL1']
852:
853: u = "%s/%s" % (u, urllib.quote(id))
854: REQUEST.RESPONSE.redirect(u+'/manage_main')
855: return ''
856:
857:
1.14 casties 858:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>