Annotation of documentViewer/documentViewer.py, revision 1.175.2.1
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:
1.175.2.1! casties 10: #from Ft.Xml import EMPTY_NAMESPACE, Parse
! 11: #import Ft.Xml.Domlette
! 12:
! 13: import xml.etree.ElementTree as ET
! 14:
1.1 dwinter 15: import os.path
1.7 casties 16: import sys
1.1 dwinter 17: import urllib
1.70 casties 18: import urllib2
1.20 dwinter 19: import logging
1.28 casties 20: import math
1.18 dwinter 21: import urlparse
1.99 dwinter 22: import re
1.149 abukhman 23: import string
1.117 abukhman 24:
1.22 dwinter 25: def logger(txt,method,txt2):
26: """logging"""
27: logging.info(txt+ txt2)
28:
29:
1.4 casties 30: def getInt(number, default=0):
31: """returns always an int (0 in case of problems)"""
32: try:
33: return int(number)
34: except:
1.29 casties 35: return int(default)
1.4 casties 36:
1.175.2.1! casties 37: def getText(node):
1.18 dwinter 38: """get the cdata content of a node"""
1.175.2.1! casties 39: if node is None:
1.8 casties 40: return ""
1.175.2.1! casties 41: # ET:
! 42: text = node.text or ""
! 43: for e in node:
! 44: text += gettext(e)
! 45: if e.tail:
! 46: text += e.tail
! 47:
! 48: # 4Suite:
! 49: #nodelist=node.childNodes
! 50: #text = ""
! 51: #for n in nodelist:
! 52: # if n.nodeType == node.TEXT_NODE:
! 53: # text = text + n.data
! 54:
! 55: return text
! 56:
! 57: getTextFromNode = getText
1.1 dwinter 58:
1.170 abukhman 59: def serializeNode(node, encoding="utf-8"):
1.43 casties 60: """returns a string containing node as XML"""
1.175.2.1! casties 61: s = ET.tostring(node)
! 62:
! 63: # 4Suite:
! 64: # stream = cStringIO.StringIO()
! 65: # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
! 66: # s = stream.getvalue()
! 67: # stream.close()
1.43 casties 68: return s
69:
1.148 abukhman 70: def browserCheck(self):
71: """check the browsers request to find out the browser type"""
72: bt = {}
73: ua = self.REQUEST.get_header("HTTP_USER_AGENT")
74: bt['ua'] = ua
75: bt['isIE'] = False
76: bt['isN4'] = False
1.165 abukhman 77: bt['versFirefox']=""
78: bt['versIE']=""
79: bt['versSafariChrome']=""
80: bt['versOpera']=""
81:
1.148 abukhman 82: if string.find(ua, 'MSIE') > -1:
83: bt['isIE'] = True
84: else:
85: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
1.165 abukhman 86: # Safari oder Chrome identification
87: try:
88: nav = ua[string.find(ua, '('):]
89: nav1=ua[string.find(ua,')'):]
90: nav2=nav1[string.find(nav1,'('):]
91: nav3=nav2[string.find(nav2,')'):]
92: ie = string.split(nav, "; ")[1]
93: ie1 =string.split(nav1, " ")[2]
94: ie2 =string.split(nav3, " ")[1]
95: ie3 =string.split(nav3, " ")[2]
96: if string.find(ie3, "Safari") >-1:
97: bt['versSafariChrome']=string.split(ie2, "/")[1]
98: except: pass
99: # IE identification
1.148 abukhman 100: try:
101: nav = ua[string.find(ua, '('):]
102: ie = string.split(nav, "; ")[1]
103: if string.find(ie, "MSIE") > -1:
104: bt['versIE'] = string.split(ie, " ")[1]
1.165 abukhman 105: except:pass
106: # Firefox identification
107: try:
108: nav = ua[string.find(ua, '('):]
109: nav1=ua[string.find(ua,')'):]
110: if string.find(ie1, "Firefox") >-1:
111: nav5= string.split(ie1, "/")[1]
112: logging.debug("FIREFOX: %s"%(nav5))
1.166 abukhman 113: bt['versFirefox']=nav5[0:3]
1.165 abukhman 114: except:pass
115: #Opera identification
116: try:
117: if string.find(ua,"Opera") >-1:
118: nav = ua[string.find(ua, '('):]
119: nav1=nav[string.find(nav,')'):]
120: bt['versOpera']=string.split(nav1,"/")[2]
121: except:pass
1.148 abukhman 122:
123: bt['isMac'] = string.find(ua, 'Macintosh') > -1
124: bt['isWin'] = string.find(ua, 'Windows') > -1
125: bt['isIEWin'] = bt['isIE'] and bt['isWin']
126: bt['isIEMac'] = bt['isIE'] and bt['isMac']
127: bt['staticHTML'] = False
128:
129: return bt
1.118 abukhman 130:
131:
1.9 casties 132: def getParentDir(path):
133: """returns pathname shortened by one"""
134: return '/'.join(path.split('/')[0:-1])
135:
136:
1.70 casties 137: def getHttpData(url, data=None, num_tries=3, timeout=10):
138: """returns result from url+data HTTP request"""
139: # we do GET (by appending data to url)
140: if isinstance(data, str) or isinstance(data, unicode):
141: # if data is string then append
142: url = "%s?%s"%(url,data)
143: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
144: # urlencode
145: url = "%s?%s"%(url,urllib.urlencode(data))
146:
147: response = None
148: errmsg = None
149: for cnt in range(num_tries):
150: try:
1.95 abukhman 151: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
1.70 casties 152: if sys.version_info < (2, 6):
153: # set timeout on socket -- ugly :-(
154: import socket
155: socket.setdefaulttimeout(float(timeout))
156: response = urllib2.urlopen(url)
157: else:
158: response = urllib2.urlopen(url,timeout=float(timeout))
159: # check result?
160: break
161: except urllib2.HTTPError, e:
1.95 abukhman 162: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
1.70 casties 163: errmsg = str(e)
164: # stop trying
165: break
166: except urllib2.URLError, e:
1.95 abukhman 167: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
1.70 casties 168: errmsg = str(e)
169: # stop trying
170: #break
171:
172: if response is not None:
173: data = response.read()
174: response.close()
175: return data
176:
177: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
178: #return None
1.1 dwinter 179:
1.3 casties 180: ##
181: ## documentViewer class
182: ##
183: class documentViewer(Folder):
1.1 dwinter 184: """document viewer"""
185: meta_type="Document viewer"
186:
187: security=ClassSecurityInfo()
1.3 casties 188: manage_options=Folder.manage_options+(
1.1 dwinter 189: {'label':'main config','action':'changeDocumentViewerForm'},
190: )
191:
1.3 casties 192: # templates and forms
193: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 194: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
195: toc_text = PageTemplateFile('zpt/toc_text', globals())
196: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 197: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
1.161 abukhman 198: page_main_double = PageTemplateFile('zpt/page_main_double', globals())
1.43 casties 199: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 200: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77 abukhman 201: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 202: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.157 abukhman 203: page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
1.3 casties 204: head_main = PageTemplateFile('zpt/head_main', globals())
205: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 206: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 207:
208:
1.32 dwinter 209: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 210: security.declareProtected('View management screens','changeDocumentViewerForm')
211: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
212:
1.1 dwinter 213:
1.45 abukhman 214: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 215: """init document viewer"""
216: self.id=id
217: self.title=title
1.4 casties 218: self.thumbcols = thumbcols
219: self.thumbrows = thumbrows
1.8 casties 220: # authgroups is list of authorized groups (delimited by ,)
221: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 222: # create template folder so we can always use template.something
223:
224: templateFolder = Folder('template')
225: #self['template'] = templateFolder # Zope-2.12 style
226: self._setObject('template',templateFolder) # old style
227: try:
1.70 casties 228: import MpdlXmlTextServer
1.71 casties 229: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 230: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 231: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 232: except Exception, e:
1.70 casties 233: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 234: try:
235: from Products.zogiLib.zogiLib import zogiLib
236: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
237: #templateFolder['zogilib'] = zogilib
238: templateFolder._setObject('zogilib',zogilib)
239: except Exception, e:
240: logging.error("Unable to create zogiLib for zogilib: "+str(e))
241:
1.70 casties 242:
243: # proxy text server methods to fulltextclient
244: def getTextPage(self, **args):
245: """get page"""
246: return self.template.fulltextclient.getTextPage(**args)
1.171 abukhman 247:
248: def getOrigPages(self, **args):
249: """get page"""
250: return self.template.fulltextclient.getOrigPages(**args)
1.167 abukhman 251:
1.171 abukhman 252: def getOrigPagesNorm(self, **args):
253: """get page"""
254: return self.template.fulltextclient.getOrigPagesNorm(**args)
255:
1.70 casties 256: def getQuery(self, **args):
1.163 abukhman 257: """get query in search"""
1.70 casties 258: return self.template.fulltextclient.getQuery(**args)
1.163 abukhman 259:
1.70 casties 260: def getSearch(self, **args):
261: """get search"""
262: return self.template.fulltextclient.getSearch(**args)
1.120 abukhman 263:
264: def getGisPlaces(self, **args):
1.121 abukhman 265: """get gis places"""
1.120 abukhman 266: return self.template.fulltextclient.getGisPlaces(**args)
1.121 abukhman 267:
268: def getAllGisPlaces(self, **args):
1.122 abukhman 269: """get all gis places """
270: return self.template.fulltextclient.getAllGisPlaces(**args)
1.163 abukhman 271:
1.70 casties 272: def getTranslate(self, **args):
273: """get translate"""
274: return self.template.fulltextclient.getTranslate(**args)
275:
276: def getLemma(self, **args):
277: """get lemma"""
278: return self.template.fulltextclient.getLemma(**args)
279:
1.173 abukhman 280: def getLemmaQuery(self, **args):
281: """get query"""
282: return self.template.fulltextclient.getLemmaQuery(**args)
283:
284: def getLex(self, **args):
285: """get lex"""
286: return self.template.fulltextclient.getLex(**args)
287:
1.70 casties 288: def getToc(self, **args):
289: """get toc"""
290: return self.template.fulltextclient.getToc(**args)
291:
292: def getTocPage(self, **args):
293: """get tocpage"""
294: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 295:
1.70 casties 296:
1.32 dwinter 297: security.declareProtected('View','thumbs_rss')
298: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
299: '''
300: view it
301: @param mode: defines how to access the document behind url
302: @param url: url which contains display information
303: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
304:
305: '''
1.95 abukhman 306: logging.debug("HHHHHHHHHHHHHH:load the rss")
307: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 308:
309: if not hasattr(self, 'template'):
310: # create template folder if it doesn't exist
311: self.manage_addFolder('template')
312:
313: if not self.digilibBaseUrl:
314: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
315:
316: docinfo = self.getDocinfo(mode=mode,url=url)
1.132 abukhman 317: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.138 abukhman 318: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
1.126 abukhman 319: ''' ZDES '''
1.32 dwinter 320: pt = getattr(self.template, 'thumbs_main_rss')
321:
322: if viewMode=="auto": # automodus gewaehlt
1.159 casties 323: if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 324: viewMode="text"
325: else:
326: viewMode="images"
327:
328: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
329:
1.3 casties 330: security.declareProtected('View','index_html')
1.158 casties 331: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
1.3 casties 332: '''
333: view it
1.26 casties 334: @param mode: defines how to access the document behind url
1.3 casties 335: @param url: url which contains display information
1.44 casties 336: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 337: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 338: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 339: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 340: '''
341:
1.138 abukhman 342: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 343:
1.3 casties 344: if not hasattr(self, 'template'):
1.43 casties 345: # this won't work
346: logging.error("template folder missing!")
347: return "ERROR: template folder missing!"
1.3 casties 348:
1.43 casties 349: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 350: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 351:
1.4 casties 352: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 353:
1.44 casties 354: if tocMode != "thumbs":
355: # get table of contents
356: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 357:
1.21 dwinter 358: if viewMode=="auto": # automodus gewaehlt
1.159 casties 359: if docinfo.has_key('textURL') or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
1.68 casties 360: viewMode="text_dict"
1.21 dwinter 361: else:
362: viewMode="images"
1.44 casties 363:
1.138 abukhman 364: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
1.68 casties 365:
1.163 abukhman 366: if (docinfo.get('textURLPath',None)):
1.175.2.1! casties 367: page = self.getTextPage(mode=viewMode, docinfo=docinfo, pageinfo=pageinfo)
1.163 abukhman 368: pageinfo['textPage'] = page
1.167 abukhman 369: tt = getattr(self, 'template')
370: pt = getattr(tt, 'viewer_main')
1.37 dwinter 371: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 372:
1.36 dwinter 373: def generateMarks(self,mk):
374: ret=""
1.44 casties 375: if mk is None:
376: return ""
1.73 casties 377: if not isinstance(mk, list):
1.71 casties 378: mk=[mk]
1.36 dwinter 379: for m in mk:
1.37 dwinter 380: ret+="mk=%s"%m
1.36 dwinter 381: return ret
1.149 abukhman 382:
383:
1.148 abukhman 384: def getBrowser(self):
385: """getBrowser the version of browser """
1.162 casties 386: bt = browserCheck(self)
1.164 abukhman 387: logging.debug("BROWSER VERSION: %s"%(bt))
1.162 casties 388: return bt
1.148 abukhman 389:
1.43 casties 390: def findDigilibUrl(self):
391: """try to get the digilib URL from zogilib"""
392: url = self.template.zogilib.getDLBaseUrl()
393: return url
1.67 casties 394:
395: def getDocumentViewerURL(self):
396: """returns the URL of this instance"""
397: return self.absolute_url()
1.43 casties 398:
399: def getStyle(self, idx, selected, style=""):
400: """returns a string with the given style and append 'sel' if path == selected."""
401: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
402: if idx == selected:
403: return style + 'sel'
404: else:
405: return style
1.36 dwinter 406:
1.162 casties 407: def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
408: """returns URL to documentviewer with parameter param set to val or from dict params"""
409: # copy existing request params
410: urlParams=self.REQUEST.form.copy()
411: # change single param
1.4 casties 412: if param is not None:
1.7 casties 413: if val is None:
1.162 casties 414: if urlParams.has_key(param):
415: del urlParams[param]
1.4 casties 416: else:
1.162 casties 417: urlParams[param] = str(val)
1.43 casties 418:
1.162 casties 419: # change more params
420: if params is not None:
421: for k in params.keys():
422: v = params[k]
423: if v is None:
424: # val=None removes param
425: if urlParams.has_key(k):
426: del urlParams[k]
427:
428: else:
429: urlParams[k] = v
430:
431: # FIXME: does this belong here?
432: if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
433: urlParams["mode"] = "imagepath"
434: urlParams["url"] = getParentDir(urlParams["url"])
1.7 casties 435:
1.162 casties 436: # quote values and assemble into query string (not escaping '/')
437: ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
438: #ps = urllib.urlencode(urlParams)
439: if baseUrl is None:
440: baseUrl = self.REQUEST['URL1']
441:
442: url = "%s?%s"%(baseUrl, ps)
1.4 casties 443: return url
444:
1.162 casties 445:
446: def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
1.32 dwinter 447: """link to documentviewer with parameter param set to val"""
1.162 casties 448: return self.getLink(param, val, params, baseUrl, '&')
1.40 casties 449:
1.26 casties 450: def getInfo_xml(self,url,mode):
451: """returns info about the document as XML"""
452:
453: if not self.digilibBaseUrl:
454: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
455:
456: docinfo = self.getDocinfo(mode=mode,url=url)
457: pt = getattr(self.template, 'info_xml')
458: return pt(docinfo=docinfo)
459:
1.153 casties 460: def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
461: """returns new option state"""
1.155 casties 462: if not self.REQUEST.SESSION.has_key(optionName):
1.153 casties 463: # not in session -- initial
464: opt = {'lastState': newState, 'state': initialState}
465: else:
1.155 casties 466: opt = self.REQUEST.SESSION.get(optionName)
1.153 casties 467: if opt['lastState'] != newState:
468: # state in session has changed -- toggle
469: opt['state'] = not opt['state']
470: opt['lastState'] = newState
471:
472: self.REQUEST.SESSION[optionName] = opt
473: return opt['state']
1.4 casties 474:
1.9 casties 475: def isAccessible(self, docinfo):
1.8 casties 476: """returns if access to the resource is granted"""
477: access = docinfo.get('accessType', None)
1.95 abukhman 478: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 479: if access is not None and access == 'free':
1.95 abukhman 480: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 481: return True
1.17 casties 482: elif access is None or access in self.authgroups:
1.9 casties 483: # only local access -- only logged in users
484: user = getSecurityManager().getUser()
1.95 abukhman 485: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 486: if user is not None:
487: #print "user: ", user
488: return (user.getUserName() != "Anonymous User")
489: else:
490: return False
1.8 casties 491:
1.95 abukhman 492: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 493: return False
1.9 casties 494:
1.8 casties 495:
1.35 dwinter 496: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 497: """gibt param von dlInfo aus"""
1.7 casties 498: if docinfo is None:
499: docinfo = {}
1.35 dwinter 500:
501: for x in range(cut):
1.38 dwinter 502:
1.35 dwinter 503: path=getParentDir(path)
1.38 dwinter 504:
1.13 casties 505: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 506:
1.95 abukhman 507: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 508:
1.70 casties 509: txt = getHttpData(infoUrl)
510: if txt is None:
1.13 casties 511: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 512:
1.175.2.1! casties 513: dom = ET.fromstring(txt)
! 514: #dom = Parse(txt)
! 515: size=getText(dom.find("size"))
! 516: #sizes=dom.xpath("//dir/size")
! 517: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size)
1.6 casties 518:
1.175.2.1! casties 519: if size:
! 520: docinfo['numPages'] = int(size)
1.7 casties 521: else:
522: docinfo['numPages'] = 0
1.43 casties 523:
524: # TODO: produce and keep list of image names and numbers
1.7 casties 525:
526: return docinfo
1.8 casties 527:
1.99 dwinter 528: def getIndexMetaPath(self,url):
529: """gib nur den Pfad zurueck"""
530: regexp = re.compile(r".*(experimental|permanent)/(.*)")
531: regpath = regexp.match(url)
532: if (regpath==None):
533: return ""
1.110 abukhman 534: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 535: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
536:
1.111 abukhman 537:
538:
1.99 dwinter 539: def getIndexMetaUrl(self,url):
540: """returns utr of index.meta document at url"""
541:
1.12 casties 542: metaUrl = None
1.9 casties 543: if url.startswith("http://"):
544: # real URL
1.12 casties 545: metaUrl = url
1.9 casties 546: else:
547: # online path
548: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 549: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 550: if not metaUrl.endswith("index.meta"):
551: metaUrl += "/index.meta"
1.99 dwinter 552:
553: return metaUrl
554:
555: def getDomFromIndexMeta(self, url):
556: """get dom from index meta"""
557: dom = None
558: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 559:
1.99 dwinter 560: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 561: txt=getHttpData(metaUrl)
562: if txt is None:
1.12 casties 563: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 564:
1.175.2.1! casties 565: dom = ET.fromstring(txt)
! 566: #dom = Parse(txt)
1.9 casties 567: return dom
1.20 dwinter 568:
569: def getPresentationInfoXML(self, url):
570: """returns dom of info.xml document at url"""
571: dom = None
572: metaUrl = None
573: if url.startswith("http://"):
574: # real URL
575: metaUrl = url
576: else:
577: # online path
578: server=self.digilibBaseUrl+"/servlet/Texter?fn="
579: metaUrl=server+url.replace("/mpiwg/online","")
580:
1.70 casties 581: txt=getHttpData(metaUrl)
582: if txt is None:
1.20 dwinter 583: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 584:
1.175.2.1! casties 585: dom = ET.fromstring(txt)
! 586: #dom = Parse(txt)
1.20 dwinter 587: return dom
1.9 casties 588:
589:
1.33 dwinter 590: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 591: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 592: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 593:
594: access = None
595:
596: if docinfo is None:
597: docinfo = {}
598:
599: if dom is None:
1.38 dwinter 600: for x in range(cut):
1.33 dwinter 601: path=getParentDir(path)
1.99 dwinter 602: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 603:
1.175.2.1! casties 604: acc = dom.find(".//access-conditions/access")
! 605: if acc is not None:
! 606: acctype = acc.get('type')
! 607: #acctype = dom.xpath("//access-conditions/access/@type")
! 608: if acctype:
! 609: access=acctype
! 610: if access in ['group', 'institution']:
! 611: access = dom.find(".//access-conditions/access/name").text.lower()
1.8 casties 612:
613: docinfo['accessType'] = access
614: return docinfo
1.6 casties 615:
1.8 casties 616:
1.33 dwinter 617: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 618: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 619: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 620:
1.3 casties 621: if docinfo is None:
622: docinfo = {}
1.38 dwinter 623:
1.3 casties 624: if dom is None:
1.38 dwinter 625: for x in range(cut):
1.33 dwinter 626: path=getParentDir(path)
1.99 dwinter 627: dom = self.getDomFromIndexMeta(path)
628:
629: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 630:
1.95 abukhman 631: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 632: # put in all raw bib fields as dict "bib"
1.175.2.1! casties 633: bib = dom.find(".//bib/*")
! 634: #bib = dom.xpath("//bib/*")
1.27 casties 635: if bib and len(bib)>0:
636: bibinfo = {}
637: for e in bib:
638: bibinfo[e.localName] = getTextFromNode(e)
639: docinfo['bib'] = bibinfo
640:
641: # extract some fields (author, title, year) according to their mapping
1.4 casties 642: metaData=self.metadata.main.meta.bib
1.175.2.1! casties 643: bib = dom.find(".//bib")
! 644: bibtype=bib.get("type")
! 645: #bibtype=dom.xpath("//bib/@type")
! 646: if not bibtype:
1.4 casties 647: bibtype="generic"
1.27 casties 648:
1.4 casties 649: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 650: docinfo['bib_type'] = bibtype
1.4 casties 651: bibmap=metaData.generateMappingForType(bibtype)
1.99 dwinter 652: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
653: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
1.8 casties 654: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.175.2.1! casties 655: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0 or len(bibmap['title'][0]) > 0:
1.30 casties 656: try:
1.175.2.1! casties 657: docinfo['author']=getText(bib.find(bibmap['author'][0]))
1.30 casties 658: except: pass
659: try:
1.175.2.1! casties 660: docinfo['title']=getText(bib.find(bibmap['title'][0]))
1.30 casties 661: except: pass
662: try:
1.175.2.1! casties 663: docinfo['year']=getText(bib.find(bibmap['year'][0]))
1.30 casties 664: except: pass
1.175.2.1! casties 665:
! 666: # ROC: why is this here?
! 667: # logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
! 668: # try:
! 669: # docinfo['lang']=getTextFromNode(dom.find(".//bib/lang")[0])
! 670: # except:
! 671: # docinfo['lang']=''
! 672: # try:
! 673: # docinfo['city']=getTextFromNode(dom.find(".//bib/city")[0])
! 674: # except:
! 675: # docinfo['city']=''
! 676: # try:
! 677: # docinfo['number_of_pages']=getTextFromNode(dom.find(".//bib/number_of_pages")[0])
! 678: # except:
! 679: # docinfo['number_of_pages']=''
! 680: # try:
! 681: # docinfo['series_volume']=getTextFromNode(dom.find(".//bib/series_volume")[0])
! 682: # except:
! 683: # docinfo['series_volume']=''
! 684: # try:
! 685: # docinfo['number_of_volumes']=getTextFromNode(dom.find(".//bib/number_of_volumes")[0])
! 686: # except:
! 687: # docinfo['number_of_volumes']=''
! 688: # try:
! 689: # docinfo['translator']=getTextFromNode(dom.find(".//bib/translator")[0])
! 690: # except:
! 691: # docinfo['translator']=''
! 692: # try:
! 693: # docinfo['edition']=getTextFromNode(dom.find(".//bib/edition")[0])
! 694: # except:
! 695: # docinfo['edition']=''
! 696: # try:
! 697: # docinfo['series_author']=getTextFromNode(dom.find(".//bib/series_author")[0])
! 698: # except:
! 699: # docinfo['series_author']=''
! 700: # try:
! 701: # docinfo['publisher']=getTextFromNode(dom.find(".//bib/publisher")[0])
! 702: # except:
! 703: # docinfo['publisher']=''
! 704: # try:
! 705: # docinfo['series_title']=getTextFromNode(dom.find(".//bib/series_title")[0])
! 706: # except:
! 707: # docinfo['series_title']=''
! 708: # try:
! 709: # docinfo['isbn_issn']=getTextFromNode(dom.find(".//bib/isbn_issn")[0])
! 710: # except:
! 711: # docinfo['isbn_issn']=''
1.3 casties 712: return docinfo
1.42 abukhman 713:
1.104 abukhman 714:
715: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
716: """gets name info from the index.meta file at path or given by dom"""
717: if docinfo is None:
718: docinfo = {}
719:
720: if dom is None:
721: for x in range(cut):
722: path=getParentDir(path)
723: dom = self.getDomFromIndexMeta(path)
1.125 abukhman 724:
1.175.2.1! casties 725: docinfo['name']=getText(dom.find("name"))
1.116 abukhman 726: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.104 abukhman 727: return docinfo
1.42 abukhman 728:
1.43 casties 729: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
730: """parse texttool tag in index meta"""
1.95 abukhman 731: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 732: if docinfo is None:
733: docinfo = {}
734: if docinfo.get('lang', None) is None:
735: docinfo['lang'] = '' # default keine Sprache gesetzt
736: if dom is None:
1.99 dwinter 737: dom = self.getDomFromIndexMeta(url)
1.43 casties 738:
739: archivePath = None
740: archiveName = None
741:
1.175.2.1! casties 742: archiveName = getTextFromNode(dom.find("name"))
! 743: if not archiveName:
1.70 casties 744: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 745:
1.175.2.1! casties 746: archivePath = getTextFromNode(dom.find("archive-path"))
! 747: if archivePath:
1.43 casties 748: # clean up archive path
749: if archivePath[0] != '/':
750: archivePath = '/' + archivePath
751: if archiveName and (not archivePath.endswith(archiveName)):
752: archivePath += "/" + archiveName
753: else:
754: # try to get archive-path from url
1.95 abukhman 755: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 756: if (not url.startswith('http')):
757: archivePath = url.replace('index.meta', '')
758:
759: if archivePath is None:
760: # we balk without archive-path
761: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
762:
1.175.2.1! casties 763: imageDir = getText(dom.find(".//texttool/image"))
1.43 casties 764:
1.175.2.1! casties 765: if not imageDir:
1.43 casties 766: # we balk with no image tag / not necessary anymore because textmode is now standard
767: #raise IOError("No text-tool info in %s"%(url))
768: imageDir = ""
769: #xquery="//pb"
770: docinfo['imagePath'] = "" # keine Bilder
771: docinfo['imageURL'] = ""
772:
773: if imageDir and archivePath:
774: #print "image: ", imageDir, " archivepath: ", archivePath
775: imageDir = os.path.join(archivePath, imageDir)
776: imageDir = imageDir.replace("/mpiwg/online", '')
777: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
778: docinfo['imagePath'] = imageDir
779:
780: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
781:
1.175.2.1! casties 782: viewerUrl = getText(dom.find(".//texttool/digiliburlprefix"))
! 783: if viewerUrl:
1.43 casties 784: docinfo['viewerURL'] = viewerUrl
1.70 casties 785:
786: # old style text URL
1.175.2.1! casties 787: textUrl = getText(dom.find(".//texttool/text"))
! 788: if textUrl:
1.43 casties 789: if urlparse.urlparse(textUrl)[0] == "": #keine url
790: textUrl = os.path.join(archivePath, textUrl)
791: # fix URLs starting with /mpiwg/online
792: if textUrl.startswith("/mpiwg/online"):
793: textUrl = textUrl.replace("/mpiwg/online", '', 1)
794:
795: docinfo['textURL'] = textUrl
796:
1.70 casties 797: # new style text-url-path
1.175.2.1! casties 798: textUrl = getText(dom.find(".//texttool/text-url-path"))
! 799: if textUrl:
1.51 casties 800: docinfo['textURLPath'] = textUrl
1.169 abukhman 801: textUrlkurz = string.split(textUrl, ".")[0]
802: docinfo['textURLPathkurz'] = textUrlkurz
1.163 abukhman 803: #if not docinfo['imagePath']:
1.51 casties 804: # text-only, no page images
1.163 abukhman 805: #docinfo = self.getNumTextPages(docinfo)
806:
1.43 casties 807:
1.175.2.1! casties 808: presentationUrl = getText(dom.find(".//texttool/presentation"))
1.43 casties 809: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.114 abukhman 810: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.147 abukhman 811:
1.43 casties 812:
1.175.2.1! casties 813: if presentationUrl: # ueberschreibe diese durch presentation informationen
1.43 casties 814: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
815: # durch den relativen Pfad auf die presentation infos
1.175.2.1! casties 816: presentationPath = presentationUrl
1.43 casties 817: if url.endswith("index.meta"):
818: presentationUrl = url.replace('index.meta', presentationPath)
819: else:
820: presentationUrl = url + "/" + presentationPath
1.51 casties 821:
1.43 casties 822: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
823:
824: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 825:
1.43 casties 826: return docinfo
1.3 casties 827:
1.20 dwinter 828:
829: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
830: """gets the bibliographical information from the preseantion entry in texttools
831: """
832: dom=self.getPresentationInfoXML(url)
1.29 casties 833: try:
1.175.2.1! casties 834: docinfo['author']=getText(dom.find(".//author"))
1.29 casties 835: except:
836: pass
837: try:
1.175.2.1! casties 838: docinfo['title']=getText(dom.find(".//title"))
1.29 casties 839: except:
840: pass
841: try:
1.175.2.1! casties 842: docinfo['year']=getText(dom.find(".//date"))
1.29 casties 843: except:
844: pass
1.20 dwinter 845: return docinfo
846:
1.33 dwinter 847: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 848: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 849: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 850: if docinfo is None:
851: docinfo = {}
1.6 casties 852: path=path.replace("/mpiwg/online","")
1.3 casties 853: docinfo['imagePath'] = path
1.35 dwinter 854: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 855:
1.39 dwinter 856: pathorig=path
1.38 dwinter 857: for x in range(cut):
858: path=getParentDir(path)
1.95 abukhman 859: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 860: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 861: docinfo['imageURL'] = imageUrl
862:
1.39 dwinter 863: #path ist the path to the images it assumes that the index.meta file is one level higher.
864: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
865: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 866: return docinfo
867:
1.2 dwinter 868:
1.3 casties 869: def getDocinfo(self, mode, url):
870: """returns docinfo depending on mode"""
1.95 abukhman 871: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 872: # look for cached docinfo in session
1.21 dwinter 873: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 874: docinfo = self.REQUEST.SESSION['docinfo']
875: # check if its still current
876: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.95 abukhman 877: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 878: return docinfo
879: # new docinfo
880: docinfo = {'mode': mode, 'url': url}
881: if mode=="texttool": #index.meta with texttool information
882: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
883: elif mode=="imagepath":
884: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 885: elif mode=="filepath":
1.37 dwinter 886: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 887: else:
1.95 abukhman 888: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 889: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.159 casties 890:
891: # FIXME: fake texturlpath
892: if not docinfo.has_key('textURLPath'):
893: docinfo['textURLPath'] = None
894:
1.95 abukhman 895: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.142 abukhman 896: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
1.3 casties 897: self.REQUEST.SESSION['docinfo'] = docinfo
898: return docinfo
1.69 abukhman 899:
1.158 casties 900: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 901: """returns pageinfo with the given parameters"""
902: pageinfo = {}
1.4 casties 903: current = getInt(current)
1.132 abukhman 904:
1.4 casties 905: pageinfo['current'] = current
906: rows = int(rows or self.thumbrows)
907: pageinfo['rows'] = rows
908: cols = int(cols or self.thumbcols)
909: pageinfo['cols'] = cols
910: grpsize = cols * rows
911: pageinfo['groupsize'] = grpsize
1.28 casties 912: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
913: # int(current / grpsize) * grpsize +1))
1.3 casties 914: pageinfo['start'] = start
1.4 casties 915: pageinfo['end'] = start + grpsize
1.44 casties 916: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 917: np = int(docinfo['numPages'])
918: pageinfo['end'] = min(pageinfo['end'], np)
919: pageinfo['numgroups'] = int(np / grpsize)
920: if np % grpsize > 0:
1.69 abukhman 921: pageinfo['numgroups'] += 1
1.44 casties 922: pageinfo['viewMode'] = viewMode
923: pageinfo['tocMode'] = tocMode
1.161 abukhman 924: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
1.174 abukhman 925: #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')
1.156 abukhman 926: pageinfo['query'] = self.REQUEST.get('query','')
1.146 abukhman 927: pageinfo['queryType'] = self.REQUEST.get('queryType','')
1.45 abukhman 928: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 929: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.146 abukhman 930: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 931: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 932: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.170 abukhman 933: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 934: toc = int (pageinfo['tocPN'])
935: pageinfo['textPages'] =int (toc)
1.90 abukhman 936:
1.48 abukhman 937: if 'tocSize_%s'%tocMode in docinfo:
938: tocSize = int(docinfo['tocSize_%s'%tocMode])
939: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 940: # cached toc
1.48 abukhman 941: if tocSize%tocPageSize>0:
942: tocPages=tocSize/tocPageSize+1
943: else:
944: tocPages=tocSize/tocPageSize
1.69 abukhman 945: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 946: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 947: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 948: return pageinfo
949:
1.69 abukhman 950: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 951: """init document viewer"""
952: self.title=title
953: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 954: self.thumbrows = thumbrows
955: self.thumbcols = thumbcols
1.8 casties 956: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 957: if RESPONSE is not None:
958: RESPONSE.redirect('manage_main')
1.1 dwinter 959:
960: def manage_AddDocumentViewerForm(self):
961: """add the viewer form"""
1.3 casties 962: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 963: return pt()
964:
1.43 casties 965: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 966: """add the viewer"""
1.43 casties 967: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 968: self._setObject(id,newObj)
969:
970: if RESPONSE is not None:
971: RESPONSE.redirect('manage_main')
1.3 casties 972:
973: ## DocumentViewerTemplate class
974: class DocumentViewerTemplate(ZopePageTemplate):
975: """Template for document viewer"""
976: meta_type="DocumentViewer Template"
977:
978:
979: def manage_addDocumentViewerTemplateForm(self):
980: """Form for adding"""
981: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
982: return pt()
983:
984: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
985: REQUEST=None, submit=None):
986: "Add a Page Template with optional file content."
987:
988: self._setObject(id, DocumentViewerTemplate(id))
989: ob = getattr(self, id)
1.23 dwinter 990: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 991: logging.info("txt %s:"%txt)
1.23 dwinter 992: ob.pt_edit(txt,"text/html")
1.3 casties 993: if title:
994: ob.pt_setTitle(title)
995: try:
996: u = self.DestinationURL()
997: except AttributeError:
998: u = REQUEST['URL1']
999:
1000: u = "%s/%s" % (u, urllib.quote(id))
1001: REQUEST.RESPONSE.redirect(u+'/manage_main')
1002: return ''
1003:
1004:
1.14 casties 1005:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>