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