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