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