Annotation of documentViewer/documentViewer.py, revision 1.69.2.7
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
8:
1.11 casties 9: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.1 dwinter 10: import os.path
1.7 casties 11: import sys
1.1 dwinter 12: import urllib
1.69.2.5 casties 13: import urllib2
1.20 dwinter 14: import logging
1.69.2.7! casties 15: import math
! 16: import urlparse
1.43 casties 17:
1.22 dwinter 18: def logger(txt,method,txt2):
19: """logging"""
20: logging.info(txt+ txt2)
21:
22:
1.4 casties 23: def getInt(number, default=0):
24: """returns always an int (0 in case of problems)"""
25: try:
26: return int(number)
27: except:
1.29 casties 28: return int(default)
1.4 casties 29:
1.1 dwinter 30: def getTextFromNode(nodename):
1.18 dwinter 31: """get the cdata content of a node"""
1.8 casties 32: if nodename is None:
33: return ""
1.1 dwinter 34: nodelist=nodename.childNodes
35: rc = ""
36: for node in nodelist:
37: if node.nodeType == node.TEXT_NODE:
38: rc = rc + node.data
39: return rc
40:
1.43 casties 41: def serializeNode(node, encoding='utf-8'):
42: """returns a string containing node as XML"""
43: buf = cStringIO.StringIO()
44: Print(node, stream=buf, encoding=encoding)
45: s = buf.getvalue()
46: buf.close()
47: return s
48:
1.9 casties 49:
50: def getParentDir(path):
51: """returns pathname shortened by one"""
52: return '/'.join(path.split('/')[0:-1])
53:
54:
1.69.2.3 casties 55: def getHttpData(url, data=None, num_tries=3, timeout=10):
56: """returns result from url+data HTTP request"""
57: # we do GET (by appending data to url)
58: if isinstance(data, str) or isinstance(data, unicode):
59: # if data is string then append
60: url = "%s?%s"%(url,data)
61: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
62: # urlencode
63: url = "%s?%s"%(url,urllib.urlencode(data))
64:
65: response = None
66: errmsg = None
67: for cnt in range(num_tries):
68: try:
69: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
70: if sys.version_info < (2, 6):
71: # set timeout on socket -- ugly :-(
72: import socket
73: socket.setdefaulttimeout(timeout)
74: response = urllib2.urlopen(url)
75: else:
76: response = urllib2.urlopen(url,timeout=float(timeout))
77: # check result?
78: break
79: except urllib2.HTTPError, e:
80: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
81: errmsg = str(e)
82: # stop trying
83: break
84: except urllib2.URLError, e:
85: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
86: errmsg = str(e)
87: # stop trying
88: #break
89:
90: if response is not None:
91: data = response.read()
92: response.close()
93: return data
94:
95: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
96: #return None
1.1 dwinter 97:
98:
99:
1.3 casties 100: ##
101: ## documentViewer class
102: ##
1.69.2.3 casties 103: class documentViewer(Folder):
1.1 dwinter 104: """document viewer"""
105: meta_type="Document viewer"
106:
107: security=ClassSecurityInfo()
1.3 casties 108: manage_options=Folder.manage_options+(
1.1 dwinter 109: {'label':'main config','action':'changeDocumentViewerForm'},
110: )
111:
1.3 casties 112: # templates and forms
113: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 114: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
115: toc_text = PageTemplateFile('zpt/toc_text', globals())
116: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 117: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
118: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 119: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.48 abukhman 120: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 121: head_main = PageTemplateFile('zpt/head_main', globals())
122: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 123: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.69.2.1 abukhman 124:
125:
1.32 dwinter 126: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 127: security.declareProtected('View management screens','changeDocumentViewerForm')
128: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
129:
1.1 dwinter 130:
1.45 abukhman 131: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 132: """init document viewer"""
133: self.id=id
134: self.title=title
1.4 casties 135: self.thumbcols = thumbcols
136: self.thumbrows = thumbrows
1.8 casties 137: # authgroups is list of authorized groups (delimited by ,)
138: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 139: # create template folder so we can always use template.something
140:
141: templateFolder = Folder('template')
142: #self['template'] = templateFolder # Zope-2.12 style
143: self._setObject('template',templateFolder) # old style
144: try:
1.69.2.3 casties 145: import MpdlXmlTextServer
146: textServer = MpdlXmlTextServer(id='fulltextclient')
1.43 casties 147: #templateFolder['fulltextclient'] = xmlRpcClient
1.69.2.3 casties 148: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 149: except Exception, e:
1.69.2.3 casties 150: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 151: try:
152: from Products.zogiLib.zogiLib import zogiLib
153: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
154: #templateFolder['zogilib'] = zogilib
155: templateFolder._setObject('zogilib',zogilib)
156: except Exception, e:
157: logging.error("Unable to create zogiLib for zogilib: "+str(e))
158:
1.69.2.3 casties 159:
160: # proxy text server methods to fulltextclient
161: def getTextPage(self, **args):
162: """get page"""
163: return self.template.fulltextclient.getTextPage(**args)
164:
165: def getQuery(self, **args):
166: """get query"""
167: return self.template.fulltextclient.getQuery(**args)
168:
169: def getSearch(self, **args):
170: """get search"""
171: return self.template.fulltextclient.getSearch(**args)
172:
173: def getNumPages(self, **args):
174: """get numpages"""
175: return self.template.fulltextclient.getNumPages(**args)
176:
177: def getTranslate(self, **args):
178: """get translate"""
179: return self.template.fulltextclient.getTranslate(**args)
180:
181: def getLemma(self, **args):
182: """get lemma"""
183: return self.template.fulltextclient.getLemma(**args)
184:
185: def getToc(self, **args):
186: """get toc"""
187: return self.template.fulltextclient.getToc(**args)
188:
189: def getTocPage(self, **args):
190: """get tocpage"""
191: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 192:
1.69.2.3 casties 193:
1.32 dwinter 194: security.declareProtected('View','thumbs_rss')
195: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
196: '''
197: view it
198: @param mode: defines how to access the document behind url
199: @param url: url which contains display information
200: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
201:
202: '''
1.43 casties 203: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.32 dwinter 204: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
205:
206: if not hasattr(self, 'template'):
207: # create template folder if it doesn't exist
208: self.manage_addFolder('template')
209:
210: if not self.digilibBaseUrl:
211: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
212:
213: docinfo = self.getDocinfo(mode=mode,url=url)
214: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
215: pt = getattr(self.template, 'thumbs_main_rss')
216:
217: if viewMode=="auto": # automodus gewaehlt
218: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
219: viewMode="text"
220: else:
221: viewMode="images"
222:
223: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
224:
1.3 casties 225: security.declareProtected('View','index_html')
1.45 abukhman 226: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
1.3 casties 227: '''
228: view it
1.26 casties 229: @param mode: defines how to access the document behind url
1.3 casties 230: @param url: url which contains display information
1.44 casties 231: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 232: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.49 abukhman 233: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 234: '''
235:
1.43 casties 236: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 237:
1.3 casties 238: if not hasattr(self, 'template'):
1.43 casties 239: # this won't work
240: logging.error("template folder missing!")
241: return "ERROR: template folder missing!"
1.3 casties 242:
1.43 casties 243: if not getattr(self, 'digilibBaseUrl', None):
1.3 casties 244: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
245:
1.4 casties 246: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 247:
248:
1.44 casties 249: if tocMode != "thumbs":
250: # get table of contents
251: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 252:
1.21 dwinter 253: if viewMode=="auto": # automodus gewaehlt
1.43 casties 254: if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
1.68 casties 255: viewMode="text_dict"
1.21 dwinter 256: else:
257: viewMode="images"
1.44 casties 258:
1.68 casties 259: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
260:
1.44 casties 261: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 262: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 263:
1.36 dwinter 264: def generateMarks(self,mk):
265: ret=""
1.44 casties 266: if mk is None:
267: return ""
268: if type(mk) is not ListType:
269: mk=[mk]
1.36 dwinter 270: for m in mk:
1.37 dwinter 271: ret+="mk=%s"%m
1.36 dwinter 272: return ret
1.43 casties 273:
1.44 casties 274:
1.43 casties 275: def findDigilibUrl(self):
276: """try to get the digilib URL from zogilib"""
277: url = self.template.zogilib.getDLBaseUrl()
278: return url
1.67 casties 279:
280: def getDocumentViewerURL(self):
281: """returns the URL of this instance"""
282: return self.absolute_url()
1.43 casties 283:
284: def getStyle(self, idx, selected, style=""):
285: """returns a string with the given style and append 'sel' if path == selected."""
286: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
287: if idx == selected:
288: return style + 'sel'
289: else:
290: return style
1.36 dwinter 291:
1.4 casties 292: def getLink(self,param=None,val=None):
293: """link to documentviewer with parameter param set to val"""
1.9 casties 294: params=self.REQUEST.form.copy()
1.4 casties 295: if param is not None:
1.7 casties 296: if val is None:
297: if params.has_key(param):
298: del params[param]
1.4 casties 299: else:
1.9 casties 300: params[param] = str(val)
1.43 casties 301:
302: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 303: params["mode"] = "imagepath"
304: params["url"] = getParentDir(params["url"])
1.7 casties 305:
1.9 casties 306: # quote values and assemble into query string
307: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
308: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 309: return url
310:
1.32 dwinter 311: def getLinkAmp(self,param=None,val=None):
312: """link to documentviewer with parameter param set to val"""
313: params=self.REQUEST.form.copy()
314: if param is not None:
315: if val is None:
316: if params.has_key(param):
317: del params[param]
318: else:
319: params[param] = str(val)
320:
321: # quote values and assemble into query string
1.69.2.2 casties 322: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 323: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
324: url=self.REQUEST['URL1']+"?"+ps
325: return url
1.40 casties 326:
1.26 casties 327: def getInfo_xml(self,url,mode):
328: """returns info about the document as XML"""
329:
330: if not self.digilibBaseUrl:
331: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
332:
333: docinfo = self.getDocinfo(mode=mode,url=url)
334: pt = getattr(self.template, 'info_xml')
335: return pt(docinfo=docinfo)
336:
1.4 casties 337:
1.9 casties 338: def isAccessible(self, docinfo):
1.8 casties 339: """returns if access to the resource is granted"""
340: access = docinfo.get('accessType', None)
1.69.2.2 casties 341: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 342: if access is not None and access == 'free':
1.69.2.2 casties 343: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 344: return True
1.17 casties 345: elif access is None or access in self.authgroups:
1.9 casties 346: # only local access -- only logged in users
347: user = getSecurityManager().getUser()
348: if user is not None:
349: #print "user: ", user
350: return (user.getUserName() != "Anonymous User")
351: else:
352: return False
1.8 casties 353:
1.69.2.2 casties 354: logging.debug("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 355: return False
1.9 casties 356:
1.8 casties 357:
1.35 dwinter 358: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 359: """gibt param von dlInfo aus"""
1.7 casties 360: if docinfo is None:
361: docinfo = {}
1.35 dwinter 362:
363: for x in range(cut):
1.38 dwinter 364:
1.35 dwinter 365: path=getParentDir(path)
1.38 dwinter 366:
1.13 casties 367: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 368:
1.69.2.2 casties 369: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 370:
1.69.2.3 casties 371: txt = getHttpData(infoUrl)
372: if txt is None:
1.13 casties 373: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.69.2.3 casties 374:
375: dom = Parse(txt)
1.10 casties 376: sizes=dom.xpath("//dir/size")
1.69.2.2 casties 377: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 378:
1.10 casties 379: if sizes:
380: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 381: else:
382: docinfo['numPages'] = 0
1.43 casties 383:
384: # TODO: produce and keep list of image names and numbers
1.7 casties 385:
386: return docinfo
1.8 casties 387:
1.6 casties 388:
1.9 casties 389: def getIndexMeta(self, url):
390: """returns dom of index.meta document at url"""
391: dom = None
1.12 casties 392: metaUrl = None
1.9 casties 393: if url.startswith("http://"):
394: # real URL
1.12 casties 395: metaUrl = url
1.9 casties 396: else:
397: # online path
398: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 399: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 400: if not metaUrl.endswith("index.meta"):
401: metaUrl += "/index.meta"
1.12 casties 402:
1.69.2.3 casties 403: logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)
404: txt=getHttpData(metaUrl)
405: if txt is None:
1.12 casties 406: raise IOError("Unable to read index meta from %s"%(url))
1.69.2.3 casties 407:
408: dom = Parse(txt)
1.9 casties 409: return dom
1.20 dwinter 410:
411: def getPresentationInfoXML(self, url):
412: """returns dom of info.xml document at url"""
413: dom = None
414: metaUrl = None
415: if url.startswith("http://"):
416: # real URL
417: metaUrl = url
418: else:
419: # online path
420: server=self.digilibBaseUrl+"/servlet/Texter?fn="
421: metaUrl=server+url.replace("/mpiwg/online","")
422:
1.69.2.3 casties 423: txt=getHttpData(metaUrl)
424: if txt is None:
1.20 dwinter 425: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.69.2.3 casties 426:
427: dom = Parse(txt)
1.20 dwinter 428: return dom
1.9 casties 429:
430:
1.33 dwinter 431: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 432: """gets authorization info from the index.meta file at path or given by dom"""
1.69.2.2 casties 433: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 434:
435: access = None
436:
437: if docinfo is None:
438: docinfo = {}
439:
440: if dom is None:
1.38 dwinter 441: for x in range(cut):
1.33 dwinter 442: path=getParentDir(path)
443: dom = self.getIndexMeta(path)
1.18 dwinter 444:
1.8 casties 445: acctype = dom.xpath("//access-conditions/access/@type")
446: if acctype and (len(acctype)>0):
447: access=acctype[0].value
1.9 casties 448: if access in ['group', 'institution']:
1.8 casties 449: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
450:
451: docinfo['accessType'] = access
452: return docinfo
1.6 casties 453:
1.8 casties 454:
1.33 dwinter 455: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 456: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 457: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 458:
1.3 casties 459: if docinfo is None:
460: docinfo = {}
1.38 dwinter 461:
1.3 casties 462: if dom is None:
1.38 dwinter 463: for x in range(cut):
1.33 dwinter 464: path=getParentDir(path)
465: dom = self.getIndexMeta(path)
1.39 dwinter 466:
467: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 468: # put in all raw bib fields as dict "bib"
469: bib = dom.xpath("//bib/*")
470: if bib and len(bib)>0:
471: bibinfo = {}
472: for e in bib:
473: bibinfo[e.localName] = getTextFromNode(e)
474: docinfo['bib'] = bibinfo
475:
476: # extract some fields (author, title, year) according to their mapping
1.4 casties 477: metaData=self.metadata.main.meta.bib
478: bibtype=dom.xpath("//bib/@type")
479: if bibtype and (len(bibtype)>0):
480: bibtype=bibtype[0].value
1.2 dwinter 481: else:
1.4 casties 482: bibtype="generic"
1.27 casties 483:
1.4 casties 484: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 485: docinfo['bib_type'] = bibtype
1.4 casties 486: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 487: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 488: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 489: try:
490: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
491: except: pass
492: try:
493: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
494: except: pass
495: try:
496: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
497: except: pass
1.27 casties 498: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 499: try:
500: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
501: except:
502: docinfo['lang']=''
1.27 casties 503:
1.3 casties 504: return docinfo
1.42 abukhman 505:
506:
1.43 casties 507: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
508: """parse texttool tag in index meta"""
1.69.2.2 casties 509: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 510: if docinfo is None:
511: docinfo = {}
512: if docinfo.get('lang', None) is None:
513: docinfo['lang'] = '' # default keine Sprache gesetzt
514: if dom is None:
515: dom = self.getIndexMeta(url)
516:
517: archivePath = None
518: archiveName = None
519:
520: archiveNames = dom.xpath("//resource/name")
521: if archiveNames and (len(archiveNames) > 0):
522: archiveName = getTextFromNode(archiveNames[0])
523: else:
1.69.2.2 casties 524: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 525:
526: archivePaths = dom.xpath("//resource/archive-path")
527: if archivePaths and (len(archivePaths) > 0):
528: archivePath = getTextFromNode(archivePaths[0])
529: # clean up archive path
530: if archivePath[0] != '/':
531: archivePath = '/' + archivePath
532: if archiveName and (not archivePath.endswith(archiveName)):
533: archivePath += "/" + archiveName
534: else:
535: # try to get archive-path from url
1.69.2.2 casties 536: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 537: if (not url.startswith('http')):
538: archivePath = url.replace('index.meta', '')
539:
540: if archivePath is None:
541: # we balk without archive-path
542: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
543:
544: imageDirs = dom.xpath("//texttool/image")
545: if imageDirs and (len(imageDirs) > 0):
546: imageDir = getTextFromNode(imageDirs[0])
547:
548: else:
549: # we balk with no image tag / not necessary anymore because textmode is now standard
550: #raise IOError("No text-tool info in %s"%(url))
551: imageDir = ""
552: #xquery="//pb"
553: docinfo['imagePath'] = "" # keine Bilder
554: docinfo['imageURL'] = ""
555:
556: if imageDir and archivePath:
557: #print "image: ", imageDir, " archivepath: ", archivePath
558: imageDir = os.path.join(archivePath, imageDir)
559: imageDir = imageDir.replace("/mpiwg/online", '')
560: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
561: docinfo['imagePath'] = imageDir
562:
563: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
564:
565: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
566: if viewerUrls and (len(viewerUrls) > 0):
567: viewerUrl = getTextFromNode(viewerUrls[0])
568: docinfo['viewerURL'] = viewerUrl
569:
570: textUrls = dom.xpath("//texttool/text")
571: if textUrls and (len(textUrls) > 0):
572: textUrl = getTextFromNode(textUrls[0])
573: if urlparse.urlparse(textUrl)[0] == "": #keine url
574: textUrl = os.path.join(archivePath, textUrl)
575: # fix URLs starting with /mpiwg/online
576: if textUrl.startswith("/mpiwg/online"):
577: textUrl = textUrl.replace("/mpiwg/online", '', 1)
578:
579: docinfo['textURL'] = textUrl
580:
581: textUrls = dom.xpath("//texttool/text-url-path")
582: if textUrls and (len(textUrls) > 0):
583: textUrl = getTextFromNode(textUrls[0])
1.51 casties 584: docinfo['textURLPath'] = textUrl
585: if not docinfo['imagePath']:
586: # text-only, no page images
587: docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
1.43 casties 588:
589: presentationUrls = dom.xpath("//texttool/presentation")
590: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
591:
592: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
593: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
594: # durch den relativen Pfad auf die presentation infos
595: presentationPath = getTextFromNode(presentationUrls[0])
596: if url.endswith("index.meta"):
597: presentationUrl = url.replace('index.meta', presentationPath)
598: else:
599: presentationUrl = url + "/" + presentationPath
1.51 casties 600:
1.43 casties 601: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
602:
603: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 604:
1.43 casties 605: return docinfo
1.3 casties 606:
1.20 dwinter 607:
608: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
609: """gets the bibliographical information from the preseantion entry in texttools
610: """
611: dom=self.getPresentationInfoXML(url)
1.29 casties 612: try:
613: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
614: except:
615: pass
616: try:
617: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
618: except:
619: pass
620: try:
621: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
622: except:
623: pass
1.20 dwinter 624: return docinfo
625:
1.33 dwinter 626: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 627: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.69.2.2 casties 628: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 629: if docinfo is None:
630: docinfo = {}
1.6 casties 631: path=path.replace("/mpiwg/online","")
1.3 casties 632: docinfo['imagePath'] = path
1.35 dwinter 633: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 634:
1.39 dwinter 635: pathorig=path
1.38 dwinter 636: for x in range(cut):
637: path=getParentDir(path)
1.69.2.2 casties 638: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 639: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 640: docinfo['imageURL'] = imageUrl
641:
1.39 dwinter 642: #path ist the path to the images it assumes that the index.meta file is one level higher.
643: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
644: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 645: return docinfo
646:
1.2 dwinter 647:
1.3 casties 648: def getDocinfo(self, mode, url):
649: """returns docinfo depending on mode"""
1.69.2.2 casties 650: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 651: # look for cached docinfo in session
1.21 dwinter 652: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 653: docinfo = self.REQUEST.SESSION['docinfo']
654: # check if its still current
655: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.69.2.2 casties 656: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 657: return docinfo
658: # new docinfo
659: docinfo = {'mode': mode, 'url': url}
660: if mode=="texttool": #index.meta with texttool information
661: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
662: elif mode=="imagepath":
663: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 664: elif mode=="filepath":
1.37 dwinter 665: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 666: else:
1.69.2.2 casties 667: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 668: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 669:
1.69.2.2 casties 670: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 671: self.REQUEST.SESSION['docinfo'] = docinfo
672: return docinfo
1.69 abukhman 673:
1.44 casties 674: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 675: """returns pageinfo with the given parameters"""
676: pageinfo = {}
1.4 casties 677: current = getInt(current)
678: pageinfo['current'] = current
679: rows = int(rows or self.thumbrows)
680: pageinfo['rows'] = rows
681: cols = int(cols or self.thumbcols)
682: pageinfo['cols'] = cols
683: grpsize = cols * rows
684: pageinfo['groupsize'] = grpsize
1.28 casties 685: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
686: # int(current / grpsize) * grpsize +1))
1.3 casties 687: pageinfo['start'] = start
1.4 casties 688: pageinfo['end'] = start + grpsize
1.44 casties 689: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 690: np = int(docinfo['numPages'])
691: pageinfo['end'] = min(pageinfo['end'], np)
692: pageinfo['numgroups'] = int(np / grpsize)
693: if np % grpsize > 0:
1.69 abukhman 694: pageinfo['numgroups'] += 1
1.44 casties 695: pageinfo['viewMode'] = viewMode
696: pageinfo['tocMode'] = tocMode
1.45 abukhman 697: pageinfo['query'] = self.REQUEST.get('query',' ')
698: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
699: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 700: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 701: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 702: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 703: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 704: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 705: toc = int (pageinfo['tocPN'])
706: pageinfo['textPages'] =int (toc)
707:
708: if 'tocSize_%s'%tocMode in docinfo:
709: tocSize = int(docinfo['tocSize_%s'%tocMode])
710: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 711: # cached toc
1.48 abukhman 712: if tocSize%tocPageSize>0:
713: tocPages=tocSize/tocPageSize+1
714: else:
715: tocPages=tocSize/tocPageSize
1.69 abukhman 716: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 717: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 718: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 719: return pageinfo
720:
1.69 abukhman 721: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 722: """init document viewer"""
723: self.title=title
724: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 725: self.thumbrows = thumbrows
726: self.thumbcols = thumbcols
1.8 casties 727: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 728: if RESPONSE is not None:
729: RESPONSE.redirect('manage_main')
1.1 dwinter 730:
731: def manage_AddDocumentViewerForm(self):
732: """add the viewer form"""
1.3 casties 733: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 734: return pt()
735:
1.43 casties 736: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 737: """add the viewer"""
1.43 casties 738: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 739: self._setObject(id,newObj)
740:
741: if RESPONSE is not None:
742: RESPONSE.redirect('manage_main')
1.3 casties 743:
744: ## DocumentViewerTemplate class
745: class DocumentViewerTemplate(ZopePageTemplate):
746: """Template for document viewer"""
747: meta_type="DocumentViewer Template"
748:
749:
750: def manage_addDocumentViewerTemplateForm(self):
751: """Form for adding"""
752: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
753: return pt()
754:
755: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
756: REQUEST=None, submit=None):
757: "Add a Page Template with optional file content."
758:
759: self._setObject(id, DocumentViewerTemplate(id))
760: ob = getattr(self, id)
1.23 dwinter 761: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
762: logging.info("txt %s:"%txt)
763: ob.pt_edit(txt,"text/html")
1.3 casties 764: if title:
765: ob.pt_setTitle(title)
766: try:
767: u = self.DestinationURL()
768: except AttributeError:
769: u = REQUEST['URL1']
770:
771: u = "%s/%s" % (u, urllib.quote(id))
772: REQUEST.RESPONSE.redirect(u+'/manage_main')
773: return ''
774:
775:
1.14 casties 776:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>