Annotation of documentViewer/documentViewer.py, revision 1.152
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())
1.3 casties 154: head_main = PageTemplateFile('zpt/head_main', globals())
155: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 156: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 157:
158:
1.32 dwinter 159: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 160: security.declareProtected('View management screens','changeDocumentViewerForm')
161: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
162:
1.1 dwinter 163:
1.45 abukhman 164: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 165: """init document viewer"""
166: self.id=id
167: self.title=title
1.4 casties 168: self.thumbcols = thumbcols
169: self.thumbrows = thumbrows
1.8 casties 170: # authgroups is list of authorized groups (delimited by ,)
171: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 172: # create template folder so we can always use template.something
173:
174: templateFolder = Folder('template')
175: #self['template'] = templateFolder # Zope-2.12 style
176: self._setObject('template',templateFolder) # old style
177: try:
1.70 casties 178: import MpdlXmlTextServer
1.71 casties 179: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 180: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 181: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 182: except Exception, e:
1.70 casties 183: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 184: try:
185: from Products.zogiLib.zogiLib import zogiLib
186: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
187: #templateFolder['zogilib'] = zogilib
188: templateFolder._setObject('zogilib',zogilib)
189: except Exception, e:
190: logging.error("Unable to create zogiLib for zogilib: "+str(e))
191:
1.70 casties 192:
193: # proxy text server methods to fulltextclient
194: def getTextPage(self, **args):
195: """get page"""
196: return self.template.fulltextclient.getTextPage(**args)
197:
198: def getQuery(self, **args):
199: """get query"""
200: return self.template.fulltextclient.getQuery(**args)
1.147 abukhman 201:
202: def getPDF(self, **args):
203: """get query"""
204: return self.template.fulltextclient.getPDF(**args)
1.70 casties 205:
206: def getSearch(self, **args):
207: """get search"""
208: return self.template.fulltextclient.getSearch(**args)
1.120 abukhman 209:
210: def getGisPlaces(self, **args):
1.121 abukhman 211: """get gis places"""
1.120 abukhman 212: return self.template.fulltextclient.getGisPlaces(**args)
1.121 abukhman 213:
214: def getAllGisPlaces(self, **args):
1.122 abukhman 215: """get all gis places """
216: return self.template.fulltextclient.getAllGisPlaces(**args)
217:
218: def getOrigPages(self, **args):
219: """get original page number """
220: return self.template.fulltextclient.getOrigPages(**args)
221:
1.72 casties 222: def getNumPages(self, docinfo):
1.70 casties 223: """get numpages"""
1.72 casties 224: return self.template.fulltextclient.getNumPages(docinfo)
1.100 abukhman 225:
226: def getNumTextPages(self, docinfo):
227: """get numpages text"""
228: return self.template.fulltextclient.getNumTextPages(docinfo)
229:
1.70 casties 230: def getTranslate(self, **args):
231: """get translate"""
232: return self.template.fulltextclient.getTranslate(**args)
233:
234: def getLemma(self, **args):
235: """get lemma"""
236: return self.template.fulltextclient.getLemma(**args)
237:
238: def getToc(self, **args):
239: """get toc"""
240: return self.template.fulltextclient.getToc(**args)
241:
242: def getTocPage(self, **args):
243: """get tocpage"""
244: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 245:
1.70 casties 246:
1.32 dwinter 247: security.declareProtected('View','thumbs_rss')
248: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
249: '''
250: view it
251: @param mode: defines how to access the document behind url
252: @param url: url which contains display information
253: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
254:
255: '''
1.95 abukhman 256: logging.debug("HHHHHHHHHHHHHH:load the rss")
257: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 258:
259: if not hasattr(self, 'template'):
260: # create template folder if it doesn't exist
261: self.manage_addFolder('template')
262:
263: if not self.digilibBaseUrl:
264: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
265:
266: docinfo = self.getDocinfo(mode=mode,url=url)
1.132 abukhman 267: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.138 abukhman 268: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
1.126 abukhman 269: ''' ZDES '''
1.32 dwinter 270: pt = getattr(self.template, 'thumbs_main_rss')
271:
272: if viewMode=="auto": # automodus gewaehlt
1.70 casties 273: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 274: viewMode="text"
275: else:
276: viewMode="images"
277:
278: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
279:
1.3 casties 280: security.declareProtected('View','index_html')
1.152 ! abukhman 281: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization="", optionsClose=None):
1.3 casties 282: '''
283: view it
1.26 casties 284: @param mode: defines how to access the document behind url
1.3 casties 285: @param url: url which contains display information
1.44 casties 286: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 287: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 288: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 289: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 290: '''
291:
1.138 abukhman 292: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 293:
1.3 casties 294: if not hasattr(self, 'template'):
1.43 casties 295: # this won't work
296: logging.error("template folder missing!")
297: return "ERROR: template folder missing!"
1.3 casties 298:
1.43 casties 299: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 300: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 301:
1.4 casties 302: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 303:
1.44 casties 304: if tocMode != "thumbs":
305: # get table of contents
306: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 307:
1.21 dwinter 308: if viewMode=="auto": # automodus gewaehlt
1.71 casties 309: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.68 casties 310: viewMode="text_dict"
1.21 dwinter 311: else:
312: viewMode="images"
1.44 casties 313:
1.138 abukhman 314: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
1.68 casties 315:
1.44 casties 316: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 317: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 318:
1.36 dwinter 319: def generateMarks(self,mk):
320: ret=""
1.44 casties 321: if mk is None:
322: return ""
1.73 casties 323: if not isinstance(mk, list):
1.71 casties 324: mk=[mk]
1.36 dwinter 325: for m in mk:
1.37 dwinter 326: ret+="mk=%s"%m
1.36 dwinter 327: return ret
1.149 abukhman 328:
329:
1.148 abukhman 330: def getBrowser(self):
331: """getBrowser the version of browser """
1.149 abukhman 332: names=""
333: names = browserCheck(self)
334: #logging.debug("XXXXXXXXXXXXXXXX: %s"%names)
335: return names
1.148 abukhman 336:
1.43 casties 337: def findDigilibUrl(self):
338: """try to get the digilib URL from zogilib"""
339: url = self.template.zogilib.getDLBaseUrl()
340: return url
1.67 casties 341:
342: def getDocumentViewerURL(self):
343: """returns the URL of this instance"""
344: return self.absolute_url()
1.43 casties 345:
346: def getStyle(self, idx, selected, style=""):
347: """returns a string with the given style and append 'sel' if path == selected."""
348: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
349: if idx == selected:
350: return style + 'sel'
351: else:
352: return style
1.36 dwinter 353:
1.4 casties 354: def getLink(self,param=None,val=None):
355: """link to documentviewer with parameter param set to val"""
1.9 casties 356: params=self.REQUEST.form.copy()
1.4 casties 357: if param is not None:
1.7 casties 358: if val is None:
359: if params.has_key(param):
360: del params[param]
1.4 casties 361: else:
1.9 casties 362: params[param] = str(val)
1.43 casties 363:
364: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 365: params["mode"] = "imagepath"
366: params["url"] = getParentDir(params["url"])
1.7 casties 367:
1.9 casties 368: # quote values and assemble into query string
1.74 casties 369: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
370: ps = urllib.urlencode(params)
1.9 casties 371: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 372: return url
373:
1.32 dwinter 374: def getLinkAmp(self,param=None,val=None):
375: """link to documentviewer with parameter param set to val"""
376: params=self.REQUEST.form.copy()
377: if param is not None:
378: if val is None:
379: if params.has_key(param):
380: del params[param]
381: else:
382: params[param] = str(val)
383:
384: # quote values and assemble into query string
1.95 abukhman 385: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 386: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
387: url=self.REQUEST['URL1']+"?"+ps
388: return url
1.40 casties 389:
1.26 casties 390: def getInfo_xml(self,url,mode):
391: """returns info about the document as XML"""
392:
393: if not self.digilibBaseUrl:
394: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
395:
396: docinfo = self.getDocinfo(mode=mode,url=url)
397: pt = getattr(self.template, 'info_xml')
398: return pt(docinfo=docinfo)
399:
1.4 casties 400:
1.9 casties 401: def isAccessible(self, docinfo):
1.8 casties 402: """returns if access to the resource is granted"""
403: access = docinfo.get('accessType', None)
1.95 abukhman 404: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 405: if access is not None and access == 'free':
1.95 abukhman 406: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 407: return True
1.17 casties 408: elif access is None or access in self.authgroups:
1.9 casties 409: # only local access -- only logged in users
410: user = getSecurityManager().getUser()
1.95 abukhman 411: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 412: if user is not None:
413: #print "user: ", user
414: return (user.getUserName() != "Anonymous User")
415: else:
416: return False
1.8 casties 417:
1.95 abukhman 418: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 419: return False
1.9 casties 420:
1.8 casties 421:
1.35 dwinter 422: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 423: """gibt param von dlInfo aus"""
1.7 casties 424: if docinfo is None:
425: docinfo = {}
1.35 dwinter 426:
427: for x in range(cut):
1.38 dwinter 428:
1.35 dwinter 429: path=getParentDir(path)
1.38 dwinter 430:
1.13 casties 431: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 432:
1.95 abukhman 433: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 434:
1.70 casties 435: txt = getHttpData(infoUrl)
436: if txt is None:
1.13 casties 437: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 438:
439: dom = Parse(txt)
1.10 casties 440: sizes=dom.xpath("//dir/size")
1.95 abukhman 441: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 442:
1.10 casties 443: if sizes:
444: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 445: else:
446: docinfo['numPages'] = 0
1.43 casties 447:
448: # TODO: produce and keep list of image names and numbers
1.7 casties 449:
450: return docinfo
1.8 casties 451:
1.99 dwinter 452: def getIndexMetaPath(self,url):
453: """gib nur den Pfad zurueck"""
454: regexp = re.compile(r".*(experimental|permanent)/(.*)")
455: regpath = regexp.match(url)
456: if (regpath==None):
457: return ""
1.110 abukhman 458: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 459: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
460:
1.111 abukhman 461:
462:
1.99 dwinter 463: def getIndexMetaUrl(self,url):
464: """returns utr of index.meta document at url"""
465:
1.12 casties 466: metaUrl = None
1.9 casties 467: if url.startswith("http://"):
468: # real URL
1.12 casties 469: metaUrl = url
1.9 casties 470: else:
471: # online path
472: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 473: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 474: if not metaUrl.endswith("index.meta"):
475: metaUrl += "/index.meta"
1.99 dwinter 476:
477: return metaUrl
478:
479: def getDomFromIndexMeta(self, url):
480: """get dom from index meta"""
481: dom = None
482: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 483:
1.99 dwinter 484: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 485: txt=getHttpData(metaUrl)
486: if txt is None:
1.12 casties 487: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 488:
489: dom = Parse(txt)
1.9 casties 490: return dom
1.20 dwinter 491:
492: def getPresentationInfoXML(self, url):
493: """returns dom of info.xml document at url"""
494: dom = None
495: metaUrl = None
496: if url.startswith("http://"):
497: # real URL
498: metaUrl = url
499: else:
500: # online path
501: server=self.digilibBaseUrl+"/servlet/Texter?fn="
502: metaUrl=server+url.replace("/mpiwg/online","")
503:
1.70 casties 504: txt=getHttpData(metaUrl)
505: if txt is None:
1.20 dwinter 506: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 507:
508: dom = Parse(txt)
1.20 dwinter 509: return dom
1.9 casties 510:
511:
1.33 dwinter 512: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 513: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 514: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 515:
516: access = None
517:
518: if docinfo is None:
519: docinfo = {}
520:
521: if dom is None:
1.38 dwinter 522: for x in range(cut):
1.33 dwinter 523: path=getParentDir(path)
1.99 dwinter 524: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 525:
1.8 casties 526: acctype = dom.xpath("//access-conditions/access/@type")
527: if acctype and (len(acctype)>0):
528: access=acctype[0].value
1.9 casties 529: if access in ['group', 'institution']:
1.8 casties 530: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
531:
532: docinfo['accessType'] = access
533: return docinfo
1.6 casties 534:
1.8 casties 535:
1.33 dwinter 536: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 537: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 538: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 539:
1.3 casties 540: if docinfo is None:
541: docinfo = {}
1.38 dwinter 542:
1.3 casties 543: if dom is None:
1.38 dwinter 544: for x in range(cut):
1.33 dwinter 545: path=getParentDir(path)
1.99 dwinter 546: dom = self.getDomFromIndexMeta(path)
547:
548: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 549:
1.95 abukhman 550: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 551: # put in all raw bib fields as dict "bib"
552: bib = dom.xpath("//bib/*")
553: if bib and len(bib)>0:
554: bibinfo = {}
555: for e in bib:
556: bibinfo[e.localName] = getTextFromNode(e)
557: docinfo['bib'] = bibinfo
558:
559: # extract some fields (author, title, year) according to their mapping
1.4 casties 560: metaData=self.metadata.main.meta.bib
561: bibtype=dom.xpath("//bib/@type")
562: if bibtype and (len(bibtype)>0):
563: bibtype=bibtype[0].value
1.2 dwinter 564: else:
1.4 casties 565: bibtype="generic"
1.27 casties 566:
1.4 casties 567: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 568: docinfo['bib_type'] = bibtype
1.4 casties 569: bibmap=metaData.generateMappingForType(bibtype)
1.99 dwinter 570: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
571: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
1.8 casties 572: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 573: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 574: try:
575: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
576: except: pass
577: try:
578: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
579: except: pass
580: try:
581: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
582: except: pass
1.95 abukhman 583: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 584: try:
585: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
586: except:
587: docinfo['lang']=''
1.113 abukhman 588:
1.3 casties 589: return docinfo
1.42 abukhman 590:
1.104 abukhman 591:
592: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
593: """gets name info from the index.meta file at path or given by dom"""
594: if docinfo is None:
595: docinfo = {}
596:
597: if dom is None:
598: for x in range(cut):
599: path=getParentDir(path)
600: dom = self.getDomFromIndexMeta(path)
1.125 abukhman 601:
1.115 abukhman 602: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
1.116 abukhman 603: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.104 abukhman 604: return docinfo
1.42 abukhman 605:
1.43 casties 606: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
607: """parse texttool tag in index meta"""
1.95 abukhman 608: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 609: if docinfo is None:
610: docinfo = {}
611: if docinfo.get('lang', None) is None:
612: docinfo['lang'] = '' # default keine Sprache gesetzt
613: if dom is None:
1.99 dwinter 614: dom = self.getDomFromIndexMeta(url)
1.43 casties 615:
616: archivePath = None
617: archiveName = None
618:
619: archiveNames = dom.xpath("//resource/name")
620: if archiveNames and (len(archiveNames) > 0):
621: archiveName = getTextFromNode(archiveNames[0])
622: else:
1.70 casties 623: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 624:
625: archivePaths = dom.xpath("//resource/archive-path")
626: if archivePaths and (len(archivePaths) > 0):
627: archivePath = getTextFromNode(archivePaths[0])
628: # clean up archive path
629: if archivePath[0] != '/':
630: archivePath = '/' + archivePath
631: if archiveName and (not archivePath.endswith(archiveName)):
632: archivePath += "/" + archiveName
633: else:
634: # try to get archive-path from url
1.95 abukhman 635: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 636: if (not url.startswith('http')):
637: archivePath = url.replace('index.meta', '')
638:
639: if archivePath is None:
640: # we balk without archive-path
641: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
642:
643: imageDirs = dom.xpath("//texttool/image")
644: if imageDirs and (len(imageDirs) > 0):
645: imageDir = getTextFromNode(imageDirs[0])
646:
647: else:
648: # we balk with no image tag / not necessary anymore because textmode is now standard
649: #raise IOError("No text-tool info in %s"%(url))
650: imageDir = ""
651: #xquery="//pb"
652: docinfo['imagePath'] = "" # keine Bilder
653: docinfo['imageURL'] = ""
654:
655: if imageDir and archivePath:
656: #print "image: ", imageDir, " archivepath: ", archivePath
657: imageDir = os.path.join(archivePath, imageDir)
658: imageDir = imageDir.replace("/mpiwg/online", '')
659: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
660: docinfo['imagePath'] = imageDir
661:
662: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
663:
664: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
665: if viewerUrls and (len(viewerUrls) > 0):
666: viewerUrl = getTextFromNode(viewerUrls[0])
667: docinfo['viewerURL'] = viewerUrl
1.70 casties 668:
669: # old style text URL
1.43 casties 670: textUrls = dom.xpath("//texttool/text")
671: if textUrls and (len(textUrls) > 0):
672: textUrl = getTextFromNode(textUrls[0])
673: if urlparse.urlparse(textUrl)[0] == "": #keine url
674: textUrl = os.path.join(archivePath, textUrl)
675: # fix URLs starting with /mpiwg/online
676: if textUrl.startswith("/mpiwg/online"):
677: textUrl = textUrl.replace("/mpiwg/online", '', 1)
678:
679: docinfo['textURL'] = textUrl
680:
1.70 casties 681: # new style text-url-path
1.43 casties 682: textUrls = dom.xpath("//texttool/text-url-path")
683: if textUrls and (len(textUrls) > 0):
684: textUrl = getTextFromNode(textUrls[0])
1.51 casties 685: docinfo['textURLPath'] = textUrl
686: if not docinfo['imagePath']:
687: # text-only, no page images
1.103 abukhman 688: docinfo = self.getNumTextPages(docinfo)
1.43 casties 689:
690: presentationUrls = dom.xpath("//texttool/presentation")
691: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.114 abukhman 692: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.147 abukhman 693:
1.43 casties 694:
695: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
696: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
697: # durch den relativen Pfad auf die presentation infos
698: presentationPath = getTextFromNode(presentationUrls[0])
699: if url.endswith("index.meta"):
700: presentationUrl = url.replace('index.meta', presentationPath)
701: else:
702: presentationUrl = url + "/" + presentationPath
1.51 casties 703:
1.43 casties 704: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
705:
706: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 707:
1.43 casties 708: return docinfo
1.3 casties 709:
1.20 dwinter 710:
711: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
712: """gets the bibliographical information from the preseantion entry in texttools
713: """
714: dom=self.getPresentationInfoXML(url)
1.29 casties 715: try:
716: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
717: except:
718: pass
719: try:
720: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
721: except:
722: pass
723: try:
724: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
725: except:
726: pass
1.20 dwinter 727: return docinfo
728:
1.33 dwinter 729: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 730: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 731: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 732: if docinfo is None:
733: docinfo = {}
1.6 casties 734: path=path.replace("/mpiwg/online","")
1.3 casties 735: docinfo['imagePath'] = path
1.35 dwinter 736: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 737:
1.39 dwinter 738: pathorig=path
1.38 dwinter 739: for x in range(cut):
740: path=getParentDir(path)
1.95 abukhman 741: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 742: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 743: docinfo['imageURL'] = imageUrl
744:
1.39 dwinter 745: #path ist the path to the images it assumes that the index.meta file is one level higher.
746: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
747: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 748: return docinfo
749:
1.2 dwinter 750:
1.3 casties 751: def getDocinfo(self, mode, url):
752: """returns docinfo depending on mode"""
1.95 abukhman 753: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 754: # look for cached docinfo in session
1.21 dwinter 755: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 756: docinfo = self.REQUEST.SESSION['docinfo']
757: # check if its still current
758: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.95 abukhman 759: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 760: return docinfo
761: # new docinfo
762: docinfo = {'mode': mode, 'url': url}
763: if mode=="texttool": #index.meta with texttool information
764: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
765: elif mode=="imagepath":
766: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 767: elif mode=="filepath":
1.37 dwinter 768: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 769: else:
1.95 abukhman 770: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 771: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 772:
1.95 abukhman 773: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.142 abukhman 774: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
1.3 casties 775: self.REQUEST.SESSION['docinfo'] = docinfo
776: return docinfo
1.69 abukhman 777:
1.141 abukhman 778: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
1.3 casties 779: """returns pageinfo with the given parameters"""
780: pageinfo = {}
1.4 casties 781: current = getInt(current)
1.132 abukhman 782:
1.4 casties 783: pageinfo['current'] = current
784: rows = int(rows or self.thumbrows)
785: pageinfo['rows'] = rows
786: cols = int(cols or self.thumbcols)
787: pageinfo['cols'] = cols
788: grpsize = cols * rows
789: pageinfo['groupsize'] = grpsize
1.28 casties 790: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
791: # int(current / grpsize) * grpsize +1))
1.3 casties 792: pageinfo['start'] = start
1.4 casties 793: pageinfo['end'] = start + grpsize
1.44 casties 794: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 795: np = int(docinfo['numPages'])
796: pageinfo['end'] = min(pageinfo['end'], np)
797: pageinfo['numgroups'] = int(np / grpsize)
798: if np % grpsize > 0:
1.69 abukhman 799: pageinfo['numgroups'] += 1
1.44 casties 800: pageinfo['viewMode'] = viewMode
801: pageinfo['tocMode'] = tocMode
1.146 abukhman 802: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','')
803: pageinfo['query'] = self.REQUEST.get('query','')
1.152 ! abukhman 804: pageinfo['optionsClose']= self.REQUEST.get('optionsClose','')
1.146 abukhman 805: pageinfo['queryType'] = self.REQUEST.get('queryType','')
1.45 abukhman 806: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 807: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.146 abukhman 808: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 809: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 810: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 811: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 812: toc = int (pageinfo['tocPN'])
813: pageinfo['textPages'] =int (toc)
1.90 abukhman 814:
1.142 abukhman 815:
1.123 abukhman 816:
1.48 abukhman 817: if 'tocSize_%s'%tocMode in docinfo:
818: tocSize = int(docinfo['tocSize_%s'%tocMode])
819: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 820: # cached toc
1.48 abukhman 821: if tocSize%tocPageSize>0:
822: tocPages=tocSize/tocPageSize+1
823: else:
824: tocPages=tocSize/tocPageSize
1.69 abukhman 825: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 826: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 827: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 828: return pageinfo
829:
1.69 abukhman 830: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 831: """init document viewer"""
832: self.title=title
833: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 834: self.thumbrows = thumbrows
835: self.thumbcols = thumbcols
1.8 casties 836: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 837: if RESPONSE is not None:
838: RESPONSE.redirect('manage_main')
1.1 dwinter 839:
840: def manage_AddDocumentViewerForm(self):
841: """add the viewer form"""
1.3 casties 842: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 843: return pt()
844:
1.43 casties 845: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 846: """add the viewer"""
1.43 casties 847: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 848: self._setObject(id,newObj)
849:
850: if RESPONSE is not None:
851: RESPONSE.redirect('manage_main')
1.3 casties 852:
853: ## DocumentViewerTemplate class
854: class DocumentViewerTemplate(ZopePageTemplate):
855: """Template for document viewer"""
856: meta_type="DocumentViewer Template"
857:
858:
859: def manage_addDocumentViewerTemplateForm(self):
860: """Form for adding"""
861: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
862: return pt()
863:
864: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
865: REQUEST=None, submit=None):
866: "Add a Page Template with optional file content."
867:
868: self._setObject(id, DocumentViewerTemplate(id))
869: ob = getattr(self, id)
1.23 dwinter 870: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 871: logging.info("txt %s:"%txt)
1.23 dwinter 872: ob.pt_edit(txt,"text/html")
1.3 casties 873: if title:
874: ob.pt_setTitle(title)
875: try:
876: u = self.DestinationURL()
877: except AttributeError:
878: u = REQUEST['URL1']
879:
880: u = "%s/%s" % (u, urllib.quote(id))
881: REQUEST.RESPONSE.redirect(u+'/manage_main')
882: return ''
883:
884:
1.14 casties 885:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>