Annotation of documentViewer/documentViewer.py, revision 1.162
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
1.149 abukhman 21: import string
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:
1.148 abukhman 54: def browserCheck(self):
55: """check the browsers request to find out the browser type"""
56: bt = {}
57: ua = self.REQUEST.get_header("HTTP_USER_AGENT")
58: bt['ua'] = ua
59: bt['isIE'] = False
60: bt['isN4'] = False
61: if string.find(ua, 'MSIE') > -1:
62: bt['isIE'] = True
63: else:
64: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
65:
66: try:
67: nav = ua[string.find(ua, '('):]
68: ie = string.split(nav, "; ")[1]
69: if string.find(ie, "MSIE") > -1:
70: bt['versIE'] = string.split(ie, " ")[1]
71: except: pass
72:
73: bt['isMac'] = string.find(ua, 'Macintosh') > -1
74: bt['isWin'] = string.find(ua, 'Windows') > -1
75: bt['isIEWin'] = bt['isIE'] and bt['isWin']
76: bt['isIEMac'] = bt['isIE'] and bt['isMac']
77: bt['staticHTML'] = False
78:
79: return bt
1.118 abukhman 80:
81:
1.9 casties 82: def getParentDir(path):
83: """returns pathname shortened by one"""
84: return '/'.join(path.split('/')[0:-1])
85:
86:
1.70 casties 87: def getHttpData(url, data=None, num_tries=3, timeout=10):
88: """returns result from url+data HTTP request"""
89: # we do GET (by appending data to url)
90: if isinstance(data, str) or isinstance(data, unicode):
91: # if data is string then append
92: url = "%s?%s"%(url,data)
93: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
94: # urlencode
95: url = "%s?%s"%(url,urllib.urlencode(data))
96:
97: response = None
98: errmsg = None
99: for cnt in range(num_tries):
100: try:
1.95 abukhman 101: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
1.70 casties 102: if sys.version_info < (2, 6):
103: # set timeout on socket -- ugly :-(
104: import socket
105: socket.setdefaulttimeout(float(timeout))
106: response = urllib2.urlopen(url)
107: else:
108: response = urllib2.urlopen(url,timeout=float(timeout))
109: # check result?
110: break
111: except urllib2.HTTPError, e:
1.95 abukhman 112: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
1.70 casties 113: errmsg = str(e)
114: # stop trying
115: break
116: except urllib2.URLError, e:
1.95 abukhman 117: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
1.70 casties 118: errmsg = str(e)
119: # stop trying
120: #break
121:
122: if response is not None:
123: data = response.read()
124: response.close()
125: return data
126:
127: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
128: #return None
1.1 dwinter 129:
130:
131:
1.3 casties 132: ##
133: ## documentViewer class
134: ##
135: class documentViewer(Folder):
1.1 dwinter 136: """document viewer"""
137: meta_type="Document viewer"
138:
139: security=ClassSecurityInfo()
1.3 casties 140: manage_options=Folder.manage_options+(
1.1 dwinter 141: {'label':'main config','action':'changeDocumentViewerForm'},
142: )
143:
1.3 casties 144: # templates and forms
145: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 146: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
147: toc_text = PageTemplateFile('zpt/toc_text', globals())
148: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 149: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
1.161 abukhman 150: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
1.43 casties 151: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 152: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77 abukhman 153: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 154: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.157 abukhman 155: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
1.3 casties 156: head_main = PageTemplateFile('zpt/head_main', globals())
157: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 158: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 159:
160:
1.32 dwinter 161: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 162: security.declareProtected('View management screens','changeDocumentViewerForm')
163: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
164:
1.1 dwinter 165:
1.45 abukhman 166: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 167: """init document viewer"""
168: self.id=id
169: self.title=title
1.4 casties 170: self.thumbcols = thumbcols
171: self.thumbrows = thumbrows
1.8 casties 172: # authgroups is list of authorized groups (delimited by ,)
173: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 174: # create template folder so we can always use template.something
175:
176: templateFolder = Folder('template')
177: #self['template'] = templateFolder # Zope-2.12 style
178: self._setObject('template',templateFolder) # old style
179: try:
1.70 casties 180: import MpdlXmlTextServer
1.71 casties 181: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 182: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 183: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 184: except Exception, e:
1.70 casties 185: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 186: try:
187: from Products.zogiLib.zogiLib import zogiLib
188: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
189: #templateFolder['zogilib'] = zogilib
190: templateFolder._setObject('zogilib',zogilib)
191: except Exception, e:
192: logging.error("Unable to create zogiLib for zogilib: "+str(e))
193:
1.70 casties 194:
195: # proxy text server methods to fulltextclient
196: def getTextPage(self, **args):
197: """get page"""
198: return self.template.fulltextclient.getTextPage(**args)
199:
200: def getQuery(self, **args):
201: """get query"""
202: return self.template.fulltextclient.getQuery(**args)
1.147 abukhman 203:
1.154 abukhman 204: def getQueryResultHits(self, **args):
205: """get query"""
206: return self.template.fulltextclient.getQueryResultHits(**args)
207:
208: def getQueryResultHitsText(self, **args):
209: """get query"""
210: return self.template.fulltextclient.getQueryResultHitsText(**args)
211:
212: def getQueryResultHitsFigures(self, **args):
213: """get query"""
214: return self.template.fulltextclient.getQueryResultHitsFigures(**args)
215:
1.70 casties 216: def getSearch(self, **args):
217: """get search"""
218: return self.template.fulltextclient.getSearch(**args)
1.120 abukhman 219:
220: def getGisPlaces(self, **args):
1.121 abukhman 221: """get gis places"""
1.120 abukhman 222: return self.template.fulltextclient.getGisPlaces(**args)
1.121 abukhman 223:
224: def getAllGisPlaces(self, **args):
1.122 abukhman 225: """get all gis places """
226: return self.template.fulltextclient.getAllGisPlaces(**args)
227:
228: def getOrigPages(self, **args):
229: """get original page number """
230: return self.template.fulltextclient.getOrigPages(**args)
231:
1.160 abukhman 232: def getAllPlaces(self, **args):
233: """get original page number """
234: return self.template.fulltextclient.getAllPlaces(**args)
235:
1.161 abukhman 236: def getTocEntries(self, **args):
237: """get original page number """
238: return self.template.fulltextclient.getTocEntries(**args)
239:
240: def getFigureEntries(self, **args):
241: """get original page number """
242: return self.template.fulltextclient.getFigureEntries(**args)
243:
1.72 casties 244: def getNumPages(self, docinfo):
1.70 casties 245: """get numpages"""
1.72 casties 246: return self.template.fulltextclient.getNumPages(docinfo)
1.100 abukhman 247:
248: def getNumTextPages(self, docinfo):
249: """get numpages text"""
250: return self.template.fulltextclient.getNumTextPages(docinfo)
251:
1.70 casties 252: def getTranslate(self, **args):
253: """get translate"""
254: return self.template.fulltextclient.getTranslate(**args)
255:
256: def getLemma(self, **args):
257: """get lemma"""
258: return self.template.fulltextclient.getLemma(**args)
259:
260: def getToc(self, **args):
261: """get toc"""
262: return self.template.fulltextclient.getToc(**args)
263:
264: def getTocPage(self, **args):
265: """get tocpage"""
266: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 267:
1.70 casties 268:
1.32 dwinter 269: security.declareProtected('View','thumbs_rss')
270: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
271: '''
272: view it
273: @param mode: defines how to access the document behind url
274: @param url: url which contains display information
275: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
276:
277: '''
1.95 abukhman 278: logging.debug("HHHHHHHHHHHHHH:load the rss")
279: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 280:
281: if not hasattr(self, 'template'):
282: # create template folder if it doesn't exist
283: self.manage_addFolder('template')
284:
285: if not self.digilibBaseUrl:
286: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
287:
288: docinfo = self.getDocinfo(mode=mode,url=url)
1.132 abukhman 289: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.138 abukhman 290: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
1.126 abukhman 291: ''' ZDES '''
1.32 dwinter 292: pt = getattr(self.template, 'thumbs_main_rss')
293:
294: if viewMode=="auto": # automodus gewaehlt
1.159 casties 295: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 296: viewMode="text"
297: else:
298: viewMode="images"
299:
300: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
301:
1.3 casties 302: security.declareProtected('View','index_html')
1.158 casties 303: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
1.3 casties 304: '''
305: view it
1.26 casties 306: @param mode: defines how to access the document behind url
1.3 casties 307: @param url: url which contains display information
1.44 casties 308: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 309: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 310: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 311: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 312: '''
313:
1.138 abukhman 314: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 315:
1.3 casties 316: if not hasattr(self, 'template'):
1.43 casties 317: # this won't work
318: logging.error("template folder missing!")
319: return "ERROR: template folder missing!"
1.3 casties 320:
1.43 casties 321: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 322: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 323:
1.4 casties 324: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 325:
1.44 casties 326: if tocMode != "thumbs":
327: # get table of contents
328: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 329:
1.21 dwinter 330: if viewMode=="auto": # automodus gewaehlt
1.159 casties 331: if docinfo.has_key('textURL') or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.68 casties 332: viewMode="text_dict"
1.21 dwinter 333: else:
334: viewMode="images"
1.44 casties 335:
1.138 abukhman 336: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
1.68 casties 337:
1.44 casties 338: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 339: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 340:
1.36 dwinter 341: def generateMarks(self,mk):
342: ret=""
1.44 casties 343: if mk is None:
344: return ""
1.73 casties 345: if not isinstance(mk, list):
1.71 casties 346: mk=[mk]
1.36 dwinter 347: for m in mk:
1.37 dwinter 348: ret+="mk=%s"%m
1.36 dwinter 349: return ret
1.149 abukhman 350:
351:
1.148 abukhman 352: def getBrowser(self):
353: """getBrowser the version of browser """
1.162 ! casties 354: bt = browserCheck(self)
! 355: return bt
1.148 abukhman 356:
1.43 casties 357: def findDigilibUrl(self):
358: """try to get the digilib URL from zogilib"""
359: url = self.template.zogilib.getDLBaseUrl()
360: return url
1.67 casties 361:
362: def getDocumentViewerURL(self):
363: """returns the URL of this instance"""
364: return self.absolute_url()
1.43 casties 365:
366: def getStyle(self, idx, selected, style=""):
367: """returns a string with the given style and append 'sel' if path == selected."""
368: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
369: if idx == selected:
370: return style + 'sel'
371: else:
372: return style
1.36 dwinter 373:
1.162 ! casties 374: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
! 375: """returns URL to documentviewer with parameter param set to val or from dict params"""
! 376: # copy existing request params
! 377: urlParams=self.REQUEST.form.copy()
! 378: # change single param
1.4 casties 379: if param is not None:
1.7 casties 380: if val is None:
1.162 ! casties 381: if urlParams.has_key(param):
! 382: del urlParams[param]
1.4 casties 383: else:
1.162 ! casties 384: urlParams[param] = str(val)
1.43 casties 385:
1.162 ! casties 386: # change more params
! 387: if params is not None:
! 388: for k in params.keys():
! 389: v = params[k]
! 390: if v is None:
! 391: # val=None removes param
! 392: if urlParams.has_key(k):
! 393: del urlParams[k]
! 394:
! 395: else:
! 396: urlParams[k] = v
! 397:
! 398: # FIXME: does this belong here?
! 399: if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
! 400: urlParams["mode"] = "imagepath"
! 401: urlParams["url"] = getParentDir(urlParams["url"])
1.7 casties 402:
1.162 ! casties 403: # quote values and assemble into query string (not escaping '/')
! 404: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
! 405: #ps = urllib.urlencode(urlParams)
! 406: if baseUrl is None:
! 407: baseUrl = self.REQUEST['URL1']
! 408:
! 409: url = "%s?%s"%(baseUrl, ps)
1.4 casties 410: return url
411:
1.162 ! casties 412:
! 413: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
1.32 dwinter 414: """link to documentviewer with parameter param set to val"""
1.162 ! casties 415: return self.getLink(param, val, params, baseUrl, '&')
1.40 casties 416:
1.26 casties 417: def getInfo_xml(self,url,mode):
418: """returns info about the document as XML"""
419:
420: if not self.digilibBaseUrl:
421: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
422:
423: docinfo = self.getDocinfo(mode=mode,url=url)
424: pt = getattr(self.template, 'info_xml')
425: return pt(docinfo=docinfo)
426:
1.153 casties 427: def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
428: """returns new option state"""
1.155 casties 429: if not self.REQUEST.SESSION.has_key(optionName):
1.153 casties 430: # not in session -- initial
431: opt = {'lastState': newState, 'state': initialState}
432: else:
1.155 casties 433: opt = self.REQUEST.SESSION.get(optionName)
1.153 casties 434: if opt['lastState'] != newState:
435: # state in session has changed -- toggle
436: opt['state'] = not opt['state']
437: opt['lastState'] = newState
438:
439: self.REQUEST.SESSION[optionName] = opt
440: return opt['state']
1.4 casties 441:
1.9 casties 442: def isAccessible(self, docinfo):
1.8 casties 443: """returns if access to the resource is granted"""
444: access = docinfo.get('accessType', None)
1.95 abukhman 445: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 446: if access is not None and access == 'free':
1.95 abukhman 447: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 448: return True
1.17 casties 449: elif access is None or access in self.authgroups:
1.9 casties 450: # only local access -- only logged in users
451: user = getSecurityManager().getUser()
1.95 abukhman 452: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 453: if user is not None:
454: #print "user: ", user
455: return (user.getUserName() != "Anonymous User")
456: else:
457: return False
1.8 casties 458:
1.95 abukhman 459: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 460: return False
1.9 casties 461:
1.8 casties 462:
1.35 dwinter 463: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 464: """gibt param von dlInfo aus"""
1.7 casties 465: if docinfo is None:
466: docinfo = {}
1.35 dwinter 467:
468: for x in range(cut):
1.38 dwinter 469:
1.35 dwinter 470: path=getParentDir(path)
1.38 dwinter 471:
1.13 casties 472: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 473:
1.95 abukhman 474: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 475:
1.70 casties 476: txt = getHttpData(infoUrl)
477: if txt is None:
1.13 casties 478: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 479:
480: dom = Parse(txt)
1.10 casties 481: sizes=dom.xpath("//dir/size")
1.95 abukhman 482: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 483:
1.10 casties 484: if sizes:
485: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 486: else:
487: docinfo['numPages'] = 0
1.43 casties 488:
489: # TODO: produce and keep list of image names and numbers
1.7 casties 490:
491: return docinfo
1.8 casties 492:
1.99 dwinter 493: def getIndexMetaPath(self,url):
494: """gib nur den Pfad zurueck"""
495: regexp = re.compile(r".*(experimental|permanent)/(.*)")
496: regpath = regexp.match(url)
497: if (regpath==None):
498: return ""
1.110 abukhman 499: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 500: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
501:
1.111 abukhman 502:
503:
1.99 dwinter 504: def getIndexMetaUrl(self,url):
505: """returns utr of index.meta document at url"""
506:
1.12 casties 507: metaUrl = None
1.9 casties 508: if url.startswith("http://"):
509: # real URL
1.12 casties 510: metaUrl = url
1.9 casties 511: else:
512: # online path
513: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 514: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 515: if not metaUrl.endswith("index.meta"):
516: metaUrl += "/index.meta"
1.99 dwinter 517:
518: return metaUrl
519:
520: def getDomFromIndexMeta(self, url):
521: """get dom from index meta"""
522: dom = None
523: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 524:
1.99 dwinter 525: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 526: txt=getHttpData(metaUrl)
527: if txt is None:
1.12 casties 528: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 529:
530: dom = Parse(txt)
1.9 casties 531: return dom
1.20 dwinter 532:
533: def getPresentationInfoXML(self, url):
534: """returns dom of info.xml document at url"""
535: dom = None
536: metaUrl = None
537: if url.startswith("http://"):
538: # real URL
539: metaUrl = url
540: else:
541: # online path
542: server=self.digilibBaseUrl+"/servlet/Texter?fn="
543: metaUrl=server+url.replace("/mpiwg/online","")
544:
1.70 casties 545: txt=getHttpData(metaUrl)
546: if txt is None:
1.20 dwinter 547: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 548:
549: dom = Parse(txt)
1.20 dwinter 550: return dom
1.9 casties 551:
552:
1.33 dwinter 553: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 554: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 555: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 556:
557: access = None
558:
559: if docinfo is None:
560: docinfo = {}
561:
562: if dom is None:
1.38 dwinter 563: for x in range(cut):
1.33 dwinter 564: path=getParentDir(path)
1.99 dwinter 565: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 566:
1.8 casties 567: acctype = dom.xpath("//access-conditions/access/@type")
568: if acctype and (len(acctype)>0):
569: access=acctype[0].value
1.9 casties 570: if access in ['group', 'institution']:
1.8 casties 571: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
572:
573: docinfo['accessType'] = access
574: return docinfo
1.6 casties 575:
1.8 casties 576:
1.33 dwinter 577: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 578: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 579: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 580:
1.3 casties 581: if docinfo is None:
582: docinfo = {}
1.38 dwinter 583:
1.3 casties 584: if dom is None:
1.38 dwinter 585: for x in range(cut):
1.33 dwinter 586: path=getParentDir(path)
1.99 dwinter 587: dom = self.getDomFromIndexMeta(path)
588:
589: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 590:
1.95 abukhman 591: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 592: # put in all raw bib fields as dict "bib"
593: bib = dom.xpath("//bib/*")
594: if bib and len(bib)>0:
595: bibinfo = {}
596: for e in bib:
597: bibinfo[e.localName] = getTextFromNode(e)
598: docinfo['bib'] = bibinfo
599:
600: # extract some fields (author, title, year) according to their mapping
1.4 casties 601: metaData=self.metadata.main.meta.bib
602: bibtype=dom.xpath("//bib/@type")
603: if bibtype and (len(bibtype)>0):
604: bibtype=bibtype[0].value
1.2 dwinter 605: else:
1.4 casties 606: bibtype="generic"
1.27 casties 607:
1.4 casties 608: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 609: docinfo['bib_type'] = bibtype
1.4 casties 610: bibmap=metaData.generateMappingForType(bibtype)
1.99 dwinter 611: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
612: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
1.8 casties 613: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 614: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 615: try:
616: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
617: except: pass
618: try:
619: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
620: except: pass
621: try:
622: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
623: except: pass
1.95 abukhman 624: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 625: try:
626: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
627: except:
628: docinfo['lang']=''
1.113 abukhman 629:
1.3 casties 630: return docinfo
1.42 abukhman 631:
1.104 abukhman 632:
633: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
634: """gets name info from the index.meta file at path or given by dom"""
635: if docinfo is None:
636: docinfo = {}
637:
638: if dom is None:
639: for x in range(cut):
640: path=getParentDir(path)
641: dom = self.getDomFromIndexMeta(path)
1.125 abukhman 642:
1.115 abukhman 643: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
1.116 abukhman 644: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.104 abukhman 645: return docinfo
1.42 abukhman 646:
1.43 casties 647: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
648: """parse texttool tag in index meta"""
1.95 abukhman 649: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 650: if docinfo is None:
651: docinfo = {}
652: if docinfo.get('lang', None) is None:
653: docinfo['lang'] = '' # default keine Sprache gesetzt
654: if dom is None:
1.99 dwinter 655: dom = self.getDomFromIndexMeta(url)
1.43 casties 656:
657: archivePath = None
658: archiveName = None
659:
660: archiveNames = dom.xpath("//resource/name")
661: if archiveNames and (len(archiveNames) > 0):
662: archiveName = getTextFromNode(archiveNames[0])
663: else:
1.70 casties 664: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 665:
666: archivePaths = dom.xpath("//resource/archive-path")
667: if archivePaths and (len(archivePaths) > 0):
668: archivePath = getTextFromNode(archivePaths[0])
669: # clean up archive path
670: if archivePath[0] != '/':
671: archivePath = '/' + archivePath
672: if archiveName and (not archivePath.endswith(archiveName)):
673: archivePath += "/" + archiveName
674: else:
675: # try to get archive-path from url
1.95 abukhman 676: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 677: if (not url.startswith('http')):
678: archivePath = url.replace('index.meta', '')
679:
680: if archivePath is None:
681: # we balk without archive-path
682: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
683:
684: imageDirs = dom.xpath("//texttool/image")
685: if imageDirs and (len(imageDirs) > 0):
686: imageDir = getTextFromNode(imageDirs[0])
687:
688: else:
689: # we balk with no image tag / not necessary anymore because textmode is now standard
690: #raise IOError("No text-tool info in %s"%(url))
691: imageDir = ""
692: #xquery="//pb"
693: docinfo['imagePath'] = "" # keine Bilder
694: docinfo['imageURL'] = ""
695:
696: if imageDir and archivePath:
697: #print "image: ", imageDir, " archivepath: ", archivePath
698: imageDir = os.path.join(archivePath, imageDir)
699: imageDir = imageDir.replace("/mpiwg/online", '')
700: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
701: docinfo['imagePath'] = imageDir
702:
703: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
704:
705: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
706: if viewerUrls and (len(viewerUrls) > 0):
707: viewerUrl = getTextFromNode(viewerUrls[0])
708: docinfo['viewerURL'] = viewerUrl
1.70 casties 709:
710: # old style text URL
1.43 casties 711: textUrls = dom.xpath("//texttool/text")
712: if textUrls and (len(textUrls) > 0):
713: textUrl = getTextFromNode(textUrls[0])
714: if urlparse.urlparse(textUrl)[0] == "": #keine url
715: textUrl = os.path.join(archivePath, textUrl)
716: # fix URLs starting with /mpiwg/online
717: if textUrl.startswith("/mpiwg/online"):
718: textUrl = textUrl.replace("/mpiwg/online", '', 1)
719:
720: docinfo['textURL'] = textUrl
721:
1.70 casties 722: # new style text-url-path
1.43 casties 723: textUrls = dom.xpath("//texttool/text-url-path")
724: if textUrls and (len(textUrls) > 0):
725: textUrl = getTextFromNode(textUrls[0])
1.51 casties 726: docinfo['textURLPath'] = textUrl
727: if not docinfo['imagePath']:
728: # text-only, no page images
1.103 abukhman 729: docinfo = self.getNumTextPages(docinfo)
1.43 casties 730:
731: presentationUrls = dom.xpath("//texttool/presentation")
732: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.114 abukhman 733: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.147 abukhman 734:
1.43 casties 735:
736: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
737: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
738: # durch den relativen Pfad auf die presentation infos
739: presentationPath = getTextFromNode(presentationUrls[0])
740: if url.endswith("index.meta"):
741: presentationUrl = url.replace('index.meta', presentationPath)
742: else:
743: presentationUrl = url + "/" + presentationPath
1.51 casties 744:
1.43 casties 745: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
746:
747: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 748:
1.43 casties 749: return docinfo
1.3 casties 750:
1.20 dwinter 751:
752: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
753: """gets the bibliographical information from the preseantion entry in texttools
754: """
755: dom=self.getPresentationInfoXML(url)
1.29 casties 756: try:
757: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
758: except:
759: pass
760: try:
761: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
762: except:
763: pass
764: try:
765: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
766: except:
767: pass
1.20 dwinter 768: return docinfo
769:
1.33 dwinter 770: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 771: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 772: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 773: if docinfo is None:
774: docinfo = {}
1.6 casties 775: path=path.replace("/mpiwg/online","")
1.3 casties 776: docinfo['imagePath'] = path
1.35 dwinter 777: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 778:
1.39 dwinter 779: pathorig=path
1.38 dwinter 780: for x in range(cut):
781: path=getParentDir(path)
1.95 abukhman 782: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 783: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 784: docinfo['imageURL'] = imageUrl
785:
1.39 dwinter 786: #path ist the path to the images it assumes that the index.meta file is one level higher.
787: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
788: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 789: return docinfo
790:
1.2 dwinter 791:
1.3 casties 792: def getDocinfo(self, mode, url):
793: """returns docinfo depending on mode"""
1.95 abukhman 794: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 795: # look for cached docinfo in session
1.21 dwinter 796: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 797: docinfo = self.REQUEST.SESSION['docinfo']
798: # check if its still current
799: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.95 abukhman 800: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 801: return docinfo
802: # new docinfo
803: docinfo = {'mode': mode, 'url': url}
804: if mode=="texttool": #index.meta with texttool information
805: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
806: elif mode=="imagepath":
807: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 808: elif mode=="filepath":
1.37 dwinter 809: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 810: else:
1.95 abukhman 811: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 812: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.159 casties 813:
814: # FIXME: fake texturlpath
815: if not docinfo.has_key('textURLPath'):
816: docinfo['textURLPath'] = None
817:
1.95 abukhman 818: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.142 abukhman 819: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
1.3 casties 820: self.REQUEST.SESSION['docinfo'] = docinfo
821: return docinfo
1.69 abukhman 822:
1.158 casties 823: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 824: """returns pageinfo with the given parameters"""
825: pageinfo = {}
1.4 casties 826: current = getInt(current)
1.132 abukhman 827:
1.4 casties 828: pageinfo['current'] = current
829: rows = int(rows or self.thumbrows)
830: pageinfo['rows'] = rows
831: cols = int(cols or self.thumbcols)
832: pageinfo['cols'] = cols
833: grpsize = cols * rows
834: pageinfo['groupsize'] = grpsize
1.28 casties 835: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
836: # int(current / grpsize) * grpsize +1))
1.3 casties 837: pageinfo['start'] = start
1.4 casties 838: pageinfo['end'] = start + grpsize
1.44 casties 839: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 840: np = int(docinfo['numPages'])
841: pageinfo['end'] = min(pageinfo['end'], np)
842: pageinfo['numgroups'] = int(np / grpsize)
843: if np % grpsize > 0:
1.69 abukhman 844: pageinfo['numgroups'] += 1
1.44 casties 845: pageinfo['viewMode'] = viewMode
846: pageinfo['tocMode'] = tocMode
1.161 abukhman 847: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
1.156 abukhman 848: pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','')
849: pageinfo['query'] = self.REQUEST.get('query','')
1.146 abukhman 850: pageinfo['queryType'] = self.REQUEST.get('queryType','')
1.45 abukhman 851: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 852: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.146 abukhman 853: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 854: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 855: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 856: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 857: toc = int (pageinfo['tocPN'])
858: pageinfo['textPages'] =int (toc)
1.90 abukhman 859:
1.142 abukhman 860:
1.123 abukhman 861:
1.48 abukhman 862: if 'tocSize_%s'%tocMode in docinfo:
863: tocSize = int(docinfo['tocSize_%s'%tocMode])
864: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 865: # cached toc
1.48 abukhman 866: if tocSize%tocPageSize>0:
867: tocPages=tocSize/tocPageSize+1
868: else:
869: tocPages=tocSize/tocPageSize
1.69 abukhman 870: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 871: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 872: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 873: return pageinfo
874:
1.69 abukhman 875: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 876: """init document viewer"""
877: self.title=title
878: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 879: self.thumbrows = thumbrows
880: self.thumbcols = thumbcols
1.8 casties 881: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 882: if RESPONSE is not None:
883: RESPONSE.redirect('manage_main')
1.1 dwinter 884:
885: def manage_AddDocumentViewerForm(self):
886: """add the viewer form"""
1.3 casties 887: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 888: return pt()
889:
1.43 casties 890: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 891: """add the viewer"""
1.43 casties 892: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 893: self._setObject(id,newObj)
894:
895: if RESPONSE is not None:
896: RESPONSE.redirect('manage_main')
1.3 casties 897:
898: ## DocumentViewerTemplate class
899: class DocumentViewerTemplate(ZopePageTemplate):
900: """Template for document viewer"""
901: meta_type="DocumentViewer Template"
902:
903:
904: def manage_addDocumentViewerTemplateForm(self):
905: """Form for adding"""
906: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
907: return pt()
908:
909: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
910: REQUEST=None, submit=None):
911: "Add a Page Template with optional file content."
912:
913: self._setObject(id, DocumentViewerTemplate(id))
914: ob = getattr(self, id)
1.23 dwinter 915: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 916: logging.info("txt %s:"%txt)
1.23 dwinter 917: ob.pt_edit(txt,"text/html")
1.3 casties 918: if title:
919: ob.pt_setTitle(title)
920: try:
921: u = self.DestinationURL()
922: except AttributeError:
923: u = REQUEST['URL1']
924:
925: u = "%s/%s" % (u, urllib.quote(id))
926: REQUEST.RESPONSE.redirect(u+'/manage_main')
927: return ''
928:
929:
1.14 casties 930:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>