Annotation of documentViewer/documentViewer.py, revision 1.143
1.18 dwinter 1:
1.1 dwinter 2: from OFS.Folder import Folder
3: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
1.22 dwinter 4: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
1.1 dwinter 5: from AccessControl import ClassSecurityInfo
1.8 casties 6: from AccessControl import getSecurityManager
1.1 dwinter 7: from Globals import package_home
1.119 abukhman 8: from Products.zogiLib.zogiLib import browserCheck
1.1 dwinter 9:
1.70 casties 10: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.73 casties 11: import Ft.Xml.Domlette
1.1 dwinter 12: import os.path
1.7 casties 13: import sys
1.1 dwinter 14: import urllib
1.70 casties 15: import urllib2
1.20 dwinter 16: import logging
1.28 casties 17: import math
1.18 dwinter 18: import urlparse
1.70 casties 19: import cStringIO
1.99 dwinter 20: import re
1.43 casties 21:
1.117 abukhman 22:
1.22 dwinter 23: def logger(txt,method,txt2):
24: """logging"""
25: logging.info(txt+ txt2)
26:
27:
1.4 casties 28: def getInt(number, default=0):
29: """returns always an int (0 in case of problems)"""
30: try:
31: return int(number)
32: except:
1.29 casties 33: return int(default)
1.4 casties 34:
1.1 dwinter 35: def getTextFromNode(nodename):
1.18 dwinter 36: """get the cdata content of a node"""
1.8 casties 37: if nodename is None:
38: return ""
1.1 dwinter 39: nodelist=nodename.childNodes
40: rc = ""
41: for node in nodelist:
42: if node.nodeType == node.TEXT_NODE:
43: rc = rc + node.data
44: return rc
45:
1.43 casties 46: def serializeNode(node, encoding='utf-8'):
47: """returns a string containing node as XML"""
48: buf = cStringIO.StringIO()
1.75 casties 49: Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
1.43 casties 50: s = buf.getvalue()
51: buf.close()
52: return s
53:
1.118 abukhman 54: def getBrowserType(self):
55: """get browser type object"""
56: if self.REQUEST.SESSION.has_key('browserType'):
57: return self.REQUEST.SESSION['browserType']
58: else:
59: bt = browserCheck(self)
60: self.REQUEST.SESSION.set('browserType', bt)
61: logging.debug("documentViewer (BROWSER TYPE) bt %s"%bt)
62: return bt
63:
64:
1.9 casties 65: def getParentDir(path):
66: """returns pathname shortened by one"""
67: return '/'.join(path.split('/')[0:-1])
68:
69:
1.70 casties 70: def getHttpData(url, data=None, num_tries=3, timeout=10):
71: """returns result from url+data HTTP request"""
72: # we do GET (by appending data to url)
73: if isinstance(data, str) or isinstance(data, unicode):
74: # if data is string then append
75: url = "%s?%s"%(url,data)
76: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
77: # urlencode
78: url = "%s?%s"%(url,urllib.urlencode(data))
79:
80: response = None
81: errmsg = None
82: for cnt in range(num_tries):
83: try:
1.95 abukhman 84: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
1.70 casties 85: if sys.version_info < (2, 6):
86: # set timeout on socket -- ugly :-(
87: import socket
88: socket.setdefaulttimeout(float(timeout))
89: response = urllib2.urlopen(url)
90: else:
91: response = urllib2.urlopen(url,timeout=float(timeout))
92: # check result?
93: break
94: except urllib2.HTTPError, e:
1.95 abukhman 95: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
1.70 casties 96: errmsg = str(e)
97: # stop trying
98: break
99: except urllib2.URLError, e:
1.95 abukhman 100: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
1.70 casties 101: errmsg = str(e)
102: # stop trying
103: #break
104:
105: if response is not None:
106: data = response.read()
107: response.close()
108: return data
109:
110: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
111: #return None
1.1 dwinter 112:
113:
114:
1.3 casties 115: ##
116: ## documentViewer class
117: ##
118: class documentViewer(Folder):
1.1 dwinter 119: """document viewer"""
120: meta_type="Document viewer"
121:
122: security=ClassSecurityInfo()
1.3 casties 123: manage_options=Folder.manage_options+(
1.1 dwinter 124: {'label':'main config','action':'changeDocumentViewerForm'},
125: )
126:
1.3 casties 127: # templates and forms
128: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 129: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
130: toc_text = PageTemplateFile('zpt/toc_text', globals())
131: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 132: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
133: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 134: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77 abukhman 135: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 136: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 137: head_main = PageTemplateFile('zpt/head_main', globals())
138: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 139: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 140:
141:
1.32 dwinter 142: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 143: security.declareProtected('View management screens','changeDocumentViewerForm')
144: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
145:
1.1 dwinter 146:
1.45 abukhman 147: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 148: """init document viewer"""
149: self.id=id
150: self.title=title
1.4 casties 151: self.thumbcols = thumbcols
152: self.thumbrows = thumbrows
1.8 casties 153: # authgroups is list of authorized groups (delimited by ,)
154: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 155: # create template folder so we can always use template.something
156:
157: templateFolder = Folder('template')
158: #self['template'] = templateFolder # Zope-2.12 style
159: self._setObject('template',templateFolder) # old style
160: try:
1.70 casties 161: import MpdlXmlTextServer
1.71 casties 162: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 163: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 164: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 165: except Exception, e:
1.70 casties 166: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 167: try:
168: from Products.zogiLib.zogiLib import zogiLib
169: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
170: #templateFolder['zogilib'] = zogilib
171: templateFolder._setObject('zogilib',zogilib)
172: except Exception, e:
173: logging.error("Unable to create zogiLib for zogilib: "+str(e))
174:
1.70 casties 175:
176: # proxy text server methods to fulltextclient
177: def getTextPage(self, **args):
178: """get page"""
179: return self.template.fulltextclient.getTextPage(**args)
180:
181: def getQuery(self, **args):
182: """get query"""
183: return self.template.fulltextclient.getQuery(**args)
184:
185: def getSearch(self, **args):
186: """get search"""
187: return self.template.fulltextclient.getSearch(**args)
1.120 abukhman 188:
189: def getGisPlaces(self, **args):
1.121 abukhman 190: """get gis places"""
1.120 abukhman 191: return self.template.fulltextclient.getGisPlaces(**args)
1.121 abukhman 192:
193: def getAllGisPlaces(self, **args):
1.122 abukhman 194: """get all gis places """
195: return self.template.fulltextclient.getAllGisPlaces(**args)
196:
197: def getOrigPages(self, **args):
198: """get original page number """
199: return self.template.fulltextclient.getOrigPages(**args)
200:
1.72 casties 201: def getNumPages(self, docinfo):
1.70 casties 202: """get numpages"""
1.72 casties 203: return self.template.fulltextclient.getNumPages(docinfo)
1.100 abukhman 204:
205: def getNumTextPages(self, docinfo):
206: """get numpages text"""
207: return self.template.fulltextclient.getNumTextPages(docinfo)
208:
1.70 casties 209: def getTranslate(self, **args):
210: """get translate"""
211: return self.template.fulltextclient.getTranslate(**args)
212:
213: def getLemma(self, **args):
214: """get lemma"""
215: return self.template.fulltextclient.getLemma(**args)
216:
217: def getToc(self, **args):
218: """get toc"""
219: return self.template.fulltextclient.getToc(**args)
220:
221: def getTocPage(self, **args):
222: """get tocpage"""
223: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 224:
1.70 casties 225:
1.32 dwinter 226: security.declareProtected('View','thumbs_rss')
227: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
228: '''
229: view it
230: @param mode: defines how to access the document behind url
231: @param url: url which contains display information
232: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
233:
234: '''
1.95 abukhman 235: logging.debug("HHHHHHHHHHHHHH:load the rss")
236: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 237:
238: if not hasattr(self, 'template'):
239: # create template folder if it doesn't exist
240: self.manage_addFolder('template')
241:
242: if not self.digilibBaseUrl:
243: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
244:
245: docinfo = self.getDocinfo(mode=mode,url=url)
1.132 abukhman 246: #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
1.138 abukhman 247: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo)
1.126 abukhman 248: ''' ZDES '''
1.32 dwinter 249: pt = getattr(self.template, 'thumbs_main_rss')
250:
251: if viewMode=="auto": # automodus gewaehlt
1.70 casties 252: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 253: viewMode="text"
254: else:
255: viewMode="images"
256:
257: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
258:
1.3 casties 259: security.declareProtected('View','index_html')
1.138 abukhman 260: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""):
1.3 casties 261: '''
262: view it
1.26 casties 263: @param mode: defines how to access the document behind url
1.3 casties 264: @param url: url which contains display information
1.44 casties 265: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 266: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.78 abukhman 267: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 268: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 269: '''
270:
1.138 abukhman 271: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 272:
1.3 casties 273: if not hasattr(self, 'template'):
1.43 casties 274: # this won't work
275: logging.error("template folder missing!")
276: return "ERROR: template folder missing!"
1.3 casties 277:
1.43 casties 278: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 279: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 280:
1.4 casties 281: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 282:
1.44 casties 283: if tocMode != "thumbs":
284: # get table of contents
285: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 286:
1.21 dwinter 287: if viewMode=="auto": # automodus gewaehlt
1.71 casties 288: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.68 casties 289: viewMode="text_dict"
1.21 dwinter 290: else:
291: viewMode="images"
1.44 casties 292:
1.138 abukhman 293: pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
1.68 casties 294:
1.44 casties 295: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 296: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 297:
1.36 dwinter 298: def generateMarks(self,mk):
299: ret=""
1.44 casties 300: if mk is None:
301: return ""
1.73 casties 302: if not isinstance(mk, list):
1.71 casties 303: mk=[mk]
1.36 dwinter 304: for m in mk:
1.37 dwinter 305: ret+="mk=%s"%m
1.36 dwinter 306: return ret
1.43 casties 307:
1.44 casties 308:
1.43 casties 309: def findDigilibUrl(self):
310: """try to get the digilib URL from zogilib"""
311: url = self.template.zogilib.getDLBaseUrl()
312: return url
1.67 casties 313:
314: def getDocumentViewerURL(self):
315: """returns the URL of this instance"""
316: return self.absolute_url()
1.43 casties 317:
318: def getStyle(self, idx, selected, style=""):
319: """returns a string with the given style and append 'sel' if path == selected."""
320: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
321: if idx == selected:
322: return style + 'sel'
323: else:
324: return style
1.36 dwinter 325:
1.4 casties 326: def getLink(self,param=None,val=None):
327: """link to documentviewer with parameter param set to val"""
1.9 casties 328: params=self.REQUEST.form.copy()
1.4 casties 329: if param is not None:
1.7 casties 330: if val is None:
331: if params.has_key(param):
332: del params[param]
1.4 casties 333: else:
1.9 casties 334: params[param] = str(val)
1.43 casties 335:
336: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 337: params["mode"] = "imagepath"
338: params["url"] = getParentDir(params["url"])
1.7 casties 339:
1.9 casties 340: # quote values and assemble into query string
1.74 casties 341: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
342: ps = urllib.urlencode(params)
1.9 casties 343: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 344: return url
345:
1.32 dwinter 346: def getLinkAmp(self,param=None,val=None):
347: """link to documentviewer with parameter param set to val"""
348: params=self.REQUEST.form.copy()
349: if param is not None:
350: if val is None:
351: if params.has_key(param):
352: del params[param]
353: else:
354: params[param] = str(val)
355:
356: # quote values and assemble into query string
1.95 abukhman 357: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 358: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
359: url=self.REQUEST['URL1']+"?"+ps
360: return url
1.40 casties 361:
1.26 casties 362: def getInfo_xml(self,url,mode):
363: """returns info about the document as XML"""
364:
365: if not self.digilibBaseUrl:
366: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
367:
368: docinfo = self.getDocinfo(mode=mode,url=url)
369: pt = getattr(self.template, 'info_xml')
370: return pt(docinfo=docinfo)
371:
1.4 casties 372:
1.9 casties 373: def isAccessible(self, docinfo):
1.8 casties 374: """returns if access to the resource is granted"""
375: access = docinfo.get('accessType', None)
1.95 abukhman 376: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 377: if access is not None and access == 'free':
1.95 abukhman 378: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 379: return True
1.17 casties 380: elif access is None or access in self.authgroups:
1.9 casties 381: # only local access -- only logged in users
382: user = getSecurityManager().getUser()
1.95 abukhman 383: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 384: if user is not None:
385: #print "user: ", user
386: return (user.getUserName() != "Anonymous User")
387: else:
388: return False
1.8 casties 389:
1.95 abukhman 390: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 391: return False
1.9 casties 392:
1.8 casties 393:
1.35 dwinter 394: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 395: """gibt param von dlInfo aus"""
1.7 casties 396: if docinfo is None:
397: docinfo = {}
1.35 dwinter 398:
399: for x in range(cut):
1.38 dwinter 400:
1.35 dwinter 401: path=getParentDir(path)
1.38 dwinter 402:
1.13 casties 403: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 404:
1.95 abukhman 405: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 406:
1.70 casties 407: txt = getHttpData(infoUrl)
408: if txt is None:
1.13 casties 409: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 410:
411: dom = Parse(txt)
1.10 casties 412: sizes=dom.xpath("//dir/size")
1.95 abukhman 413: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 414:
1.10 casties 415: if sizes:
416: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 417: else:
418: docinfo['numPages'] = 0
1.43 casties 419:
420: # TODO: produce and keep list of image names and numbers
1.7 casties 421:
422: return docinfo
1.8 casties 423:
1.99 dwinter 424: def getIndexMetaPath(self,url):
425: """gib nur den Pfad zurueck"""
426: regexp = re.compile(r".*(experimental|permanent)/(.*)")
427: regpath = regexp.match(url)
428: if (regpath==None):
429: return ""
1.110 abukhman 430: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 431: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
432:
1.111 abukhman 433:
434:
1.99 dwinter 435: def getIndexMetaUrl(self,url):
436: """returns utr of index.meta document at url"""
437:
1.12 casties 438: metaUrl = None
1.9 casties 439: if url.startswith("http://"):
440: # real URL
1.12 casties 441: metaUrl = url
1.9 casties 442: else:
443: # online path
444: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 445: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 446: if not metaUrl.endswith("index.meta"):
447: metaUrl += "/index.meta"
1.99 dwinter 448:
449: return metaUrl
450:
451: def getDomFromIndexMeta(self, url):
452: """get dom from index meta"""
453: dom = None
454: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 455:
1.99 dwinter 456: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 457: txt=getHttpData(metaUrl)
458: if txt is None:
1.12 casties 459: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 460:
461: dom = Parse(txt)
1.9 casties 462: return dom
1.20 dwinter 463:
464: def getPresentationInfoXML(self, url):
465: """returns dom of info.xml document at url"""
466: dom = None
467: metaUrl = None
468: if url.startswith("http://"):
469: # real URL
470: metaUrl = url
471: else:
472: # online path
473: server=self.digilibBaseUrl+"/servlet/Texter?fn="
474: metaUrl=server+url.replace("/mpiwg/online","")
475:
1.70 casties 476: txt=getHttpData(metaUrl)
477: if txt is None:
1.20 dwinter 478: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 479:
480: dom = Parse(txt)
1.20 dwinter 481: return dom
1.9 casties 482:
483:
1.33 dwinter 484: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 485: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 486: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 487:
488: access = None
489:
490: if docinfo is None:
491: docinfo = {}
492:
493: if dom is None:
1.38 dwinter 494: for x in range(cut):
1.33 dwinter 495: path=getParentDir(path)
1.99 dwinter 496: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 497:
1.8 casties 498: acctype = dom.xpath("//access-conditions/access/@type")
499: if acctype and (len(acctype)>0):
500: access=acctype[0].value
1.9 casties 501: if access in ['group', 'institution']:
1.8 casties 502: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
503:
504: docinfo['accessType'] = access
505: return docinfo
1.6 casties 506:
1.8 casties 507:
1.33 dwinter 508: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 509: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 510: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 511:
1.3 casties 512: if docinfo is None:
513: docinfo = {}
1.38 dwinter 514:
1.3 casties 515: if dom is None:
1.38 dwinter 516: for x in range(cut):
1.33 dwinter 517: path=getParentDir(path)
1.99 dwinter 518: dom = self.getDomFromIndexMeta(path)
519:
520: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 521:
1.95 abukhman 522: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 523: # put in all raw bib fields as dict "bib"
524: bib = dom.xpath("//bib/*")
525: if bib and len(bib)>0:
526: bibinfo = {}
527: for e in bib:
528: bibinfo[e.localName] = getTextFromNode(e)
529: docinfo['bib'] = bibinfo
530:
531: # extract some fields (author, title, year) according to their mapping
1.4 casties 532: metaData=self.metadata.main.meta.bib
533: bibtype=dom.xpath("//bib/@type")
534: if bibtype and (len(bibtype)>0):
535: bibtype=bibtype[0].value
1.2 dwinter 536: else:
1.4 casties 537: bibtype="generic"
1.27 casties 538:
1.4 casties 539: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 540: docinfo['bib_type'] = bibtype
1.4 casties 541: bibmap=metaData.generateMappingForType(bibtype)
1.99 dwinter 542: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
543: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
1.8 casties 544: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 545: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 546: try:
547: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
548: except: pass
549: try:
550: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
551: except: pass
552: try:
553: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
554: except: pass
1.95 abukhman 555: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 556: try:
557: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
558: except:
559: docinfo['lang']=''
1.113 abukhman 560:
1.3 casties 561: return docinfo
1.42 abukhman 562:
1.104 abukhman 563:
564: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
565: """gets name info from the index.meta file at path or given by dom"""
566: if docinfo is None:
567: docinfo = {}
568:
569: if dom is None:
570: for x in range(cut):
571: path=getParentDir(path)
572: dom = self.getDomFromIndexMeta(path)
1.125 abukhman 573:
1.115 abukhman 574: docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
1.116 abukhman 575: logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
1.104 abukhman 576: return docinfo
1.42 abukhman 577:
1.43 casties 578: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
579: """parse texttool tag in index meta"""
1.95 abukhman 580: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 581: if docinfo is None:
582: docinfo = {}
583: if docinfo.get('lang', None) is None:
584: docinfo['lang'] = '' # default keine Sprache gesetzt
585: if dom is None:
1.99 dwinter 586: dom = self.getDomFromIndexMeta(url)
1.43 casties 587:
588: archivePath = None
589: archiveName = None
590:
591: archiveNames = dom.xpath("//resource/name")
592: if archiveNames and (len(archiveNames) > 0):
593: archiveName = getTextFromNode(archiveNames[0])
594: else:
1.70 casties 595: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 596:
597: archivePaths = dom.xpath("//resource/archive-path")
598: if archivePaths and (len(archivePaths) > 0):
599: archivePath = getTextFromNode(archivePaths[0])
600: # clean up archive path
601: if archivePath[0] != '/':
602: archivePath = '/' + archivePath
603: if archiveName and (not archivePath.endswith(archiveName)):
604: archivePath += "/" + archiveName
605: else:
606: # try to get archive-path from url
1.95 abukhman 607: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 608: if (not url.startswith('http')):
609: archivePath = url.replace('index.meta', '')
610:
611: if archivePath is None:
612: # we balk without archive-path
613: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
614:
615: imageDirs = dom.xpath("//texttool/image")
616: if imageDirs and (len(imageDirs) > 0):
617: imageDir = getTextFromNode(imageDirs[0])
618:
619: else:
620: # we balk with no image tag / not necessary anymore because textmode is now standard
621: #raise IOError("No text-tool info in %s"%(url))
622: imageDir = ""
623: #xquery="//pb"
624: docinfo['imagePath'] = "" # keine Bilder
625: docinfo['imageURL'] = ""
626:
627: if imageDir and archivePath:
628: #print "image: ", imageDir, " archivepath: ", archivePath
629: imageDir = os.path.join(archivePath, imageDir)
630: imageDir = imageDir.replace("/mpiwg/online", '')
631: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
632: docinfo['imagePath'] = imageDir
633:
634: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
635:
636: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
637: if viewerUrls and (len(viewerUrls) > 0):
638: viewerUrl = getTextFromNode(viewerUrls[0])
639: docinfo['viewerURL'] = viewerUrl
1.70 casties 640:
641: # old style text URL
1.43 casties 642: textUrls = dom.xpath("//texttool/text")
643: if textUrls and (len(textUrls) > 0):
644: textUrl = getTextFromNode(textUrls[0])
645: if urlparse.urlparse(textUrl)[0] == "": #keine url
646: textUrl = os.path.join(archivePath, textUrl)
647: # fix URLs starting with /mpiwg/online
648: if textUrl.startswith("/mpiwg/online"):
649: textUrl = textUrl.replace("/mpiwg/online", '', 1)
650:
651: docinfo['textURL'] = textUrl
652:
1.70 casties 653: # new style text-url-path
1.43 casties 654: textUrls = dom.xpath("//texttool/text-url-path")
655: if textUrls and (len(textUrls) > 0):
656: textUrl = getTextFromNode(textUrls[0])
1.51 casties 657: docinfo['textURLPath'] = textUrl
658: if not docinfo['imagePath']:
659: # text-only, no page images
1.103 abukhman 660: docinfo = self.getNumTextPages(docinfo)
1.43 casties 661:
662: presentationUrls = dom.xpath("//texttool/presentation")
663: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.114 abukhman 664: docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.142 abukhman 665: #docinfo =self.getOrigPages(docinfo=docinfo)
1.43 casties 666:
667: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
668: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
669: # durch den relativen Pfad auf die presentation infos
670: presentationPath = getTextFromNode(presentationUrls[0])
671: if url.endswith("index.meta"):
672: presentationUrl = url.replace('index.meta', presentationPath)
673: else:
674: presentationUrl = url + "/" + presentationPath
1.51 casties 675:
1.43 casties 676: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
677:
678: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 679:
1.43 casties 680: return docinfo
1.3 casties 681:
1.20 dwinter 682:
683: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
684: """gets the bibliographical information from the preseantion entry in texttools
685: """
686: dom=self.getPresentationInfoXML(url)
1.29 casties 687: try:
688: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
689: except:
690: pass
691: try:
692: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
693: except:
694: pass
695: try:
696: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
697: except:
698: pass
1.20 dwinter 699: return docinfo
700:
1.33 dwinter 701: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 702: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 703: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 704: if docinfo is None:
705: docinfo = {}
1.6 casties 706: path=path.replace("/mpiwg/online","")
1.3 casties 707: docinfo['imagePath'] = path
1.35 dwinter 708: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 709:
1.39 dwinter 710: pathorig=path
1.38 dwinter 711: for x in range(cut):
712: path=getParentDir(path)
1.95 abukhman 713: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 714: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 715: docinfo['imageURL'] = imageUrl
716:
1.39 dwinter 717: #path ist the path to the images it assumes that the index.meta file is one level higher.
718: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
719: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 720: return docinfo
721:
1.2 dwinter 722:
1.3 casties 723: def getDocinfo(self, mode, url):
724: """returns docinfo depending on mode"""
1.95 abukhman 725: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 726: # look for cached docinfo in session
1.21 dwinter 727: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 728: docinfo = self.REQUEST.SESSION['docinfo']
729: # check if its still current
730: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.95 abukhman 731: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 732: return docinfo
733: # new docinfo
734: docinfo = {'mode': mode, 'url': url}
735: if mode=="texttool": #index.meta with texttool information
736: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
737: elif mode=="imagepath":
738: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 739: elif mode=="filepath":
1.37 dwinter 740: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 741: else:
1.95 abukhman 742: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 743: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 744:
1.95 abukhman 745: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.142 abukhman 746: #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
1.3 casties 747: self.REQUEST.SESSION['docinfo'] = docinfo
748: return docinfo
1.69 abukhman 749:
1.141 abukhman 750: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
1.3 casties 751: """returns pageinfo with the given parameters"""
752: pageinfo = {}
1.4 casties 753: current = getInt(current)
1.132 abukhman 754:
1.4 casties 755: pageinfo['current'] = current
756: rows = int(rows or self.thumbrows)
757: pageinfo['rows'] = rows
758: cols = int(cols or self.thumbcols)
759: pageinfo['cols'] = cols
760: grpsize = cols * rows
761: pageinfo['groupsize'] = grpsize
1.28 casties 762: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
763: # int(current / grpsize) * grpsize +1))
1.3 casties 764: pageinfo['start'] = start
1.4 casties 765: pageinfo['end'] = start + grpsize
1.44 casties 766: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 767: np = int(docinfo['numPages'])
768: pageinfo['end'] = min(pageinfo['end'], np)
769: pageinfo['numgroups'] = int(np / grpsize)
770: if np % grpsize > 0:
1.69 abukhman 771: pageinfo['numgroups'] += 1
1.44 casties 772: pageinfo['viewMode'] = viewMode
773: pageinfo['tocMode'] = tocMode
1.143 ! abukhman 774: pageinfo ['originalPage'] = self.getOrigPages(docinfo=None, pageinfo=None)
1.98 abukhman 775: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')
1.45 abukhman 776: pageinfo['query'] = self.REQUEST.get('query',' ')
777: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
778: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 779: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 780: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 781: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 782: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 783: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 784: toc = int (pageinfo['tocPN'])
785: pageinfo['textPages'] =int (toc)
1.90 abukhman 786:
1.142 abukhman 787:
1.123 abukhman 788:
1.48 abukhman 789: if 'tocSize_%s'%tocMode in docinfo:
790: tocSize = int(docinfo['tocSize_%s'%tocMode])
791: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 792: # cached toc
1.48 abukhman 793: if tocSize%tocPageSize>0:
794: tocPages=tocSize/tocPageSize+1
795: else:
796: tocPages=tocSize/tocPageSize
1.69 abukhman 797: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 798: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 799: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 800: return pageinfo
801:
1.69 abukhman 802: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 803: """init document viewer"""
804: self.title=title
805: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 806: self.thumbrows = thumbrows
807: self.thumbcols = thumbcols
1.8 casties 808: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 809: if RESPONSE is not None:
810: RESPONSE.redirect('manage_main')
1.1 dwinter 811:
812: def manage_AddDocumentViewerForm(self):
813: """add the viewer form"""
1.3 casties 814: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 815: return pt()
816:
1.43 casties 817: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 818: """add the viewer"""
1.43 casties 819: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 820: self._setObject(id,newObj)
821:
822: if RESPONSE is not None:
823: RESPONSE.redirect('manage_main')
1.3 casties 824:
825: ## DocumentViewerTemplate class
826: class DocumentViewerTemplate(ZopePageTemplate):
827: """Template for document viewer"""
828: meta_type="DocumentViewer Template"
829:
830:
831: def manage_addDocumentViewerTemplateForm(self):
832: """Form for adding"""
833: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
834: return pt()
835:
836: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
837: REQUEST=None, submit=None):
838: "Add a Page Template with optional file content."
839:
840: self._setObject(id, DocumentViewerTemplate(id))
841: ob = getattr(self, id)
1.23 dwinter 842: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 843: logging.info("txt %s:"%txt)
1.23 dwinter 844: ob.pt_edit(txt,"text/html")
1.3 casties 845: if title:
846: ob.pt_setTitle(title)
847: try:
848: u = self.DestinationURL()
849: except AttributeError:
850: u = REQUEST['URL1']
851:
852: u = "%s/%s" % (u, urllib.quote(id))
853: REQUEST.RESPONSE.redirect(u+'/manage_main')
854: return ''
855:
856:
1.14 casties 857:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/cvs/cvsweb/icons/back.gif){kind=icon}
Return to documentViewer.py CVS log ![[TXT]](/cvs/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvs/cvsweb/icons/dir.gif){kind=icon}
Up to [Repository] / documentViewer