Annotation of documentViewer/documentViewer.py, revision 1.76
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
1.73 casties 10: import Ft.Xml.Domlette
1.1 dwinter 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()
1.75 casties 46: Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
1.43 casties 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:
1.72 casties 175: def getNumPages(self, docinfo):
1.70 casties 176: """get numpages"""
1.72 casties 177: return self.template.fulltextclient.getNumPages(docinfo)
1.70 casties 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 ""
1.73 casties 269: if not isinstance(mk, list):
1.71 casties 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
1.74 casties 308: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
309: ps = urllib.urlencode(params)
1.9 casties 310: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 311: return url
312:
1.32 dwinter 313: def getLinkAmp(self,param=None,val=None):
314: """link to documentviewer with parameter param set to val"""
315: params=self.REQUEST.form.copy()
316: if param is not None:
317: if val is None:
318: if params.has_key(param):
319: del params[param]
320: else:
321: params[param] = str(val)
322:
323: # quote values and assemble into query string
1.70 casties 324: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 325: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
326: url=self.REQUEST['URL1']+"?"+ps
327: return url
1.40 casties 328:
1.26 casties 329: def getInfo_xml(self,url,mode):
330: """returns info about the document as XML"""
331:
332: if not self.digilibBaseUrl:
333: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
334:
335: docinfo = self.getDocinfo(mode=mode,url=url)
336: pt = getattr(self.template, 'info_xml')
337: return pt(docinfo=docinfo)
338:
1.4 casties 339:
1.9 casties 340: def isAccessible(self, docinfo):
1.8 casties 341: """returns if access to the resource is granted"""
342: access = docinfo.get('accessType', None)
1.70 casties 343: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 344: if access is not None and access == 'free':
1.70 casties 345: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 346: return True
1.17 casties 347: elif access is None or access in self.authgroups:
1.9 casties 348: # only local access -- only logged in users
349: user = getSecurityManager().getUser()
1.76 ! casties 350: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 351: if user is not None:
352: #print "user: ", user
353: return (user.getUserName() != "Anonymous User")
354: else:
355: return False
1.8 casties 356:
1.76 ! casties 357: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 358: return False
1.9 casties 359:
1.8 casties 360:
1.35 dwinter 361: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 362: """gibt param von dlInfo aus"""
1.7 casties 363: if docinfo is None:
364: docinfo = {}
1.35 dwinter 365:
366: for x in range(cut):
1.38 dwinter 367:
1.35 dwinter 368: path=getParentDir(path)
1.38 dwinter 369:
1.13 casties 370: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 371:
1.70 casties 372: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 373:
1.70 casties 374: txt = getHttpData(infoUrl)
375: if txt is None:
1.13 casties 376: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 377:
378: dom = Parse(txt)
1.10 casties 379: sizes=dom.xpath("//dir/size")
1.70 casties 380: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 381:
1.10 casties 382: if sizes:
383: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 384: else:
385: docinfo['numPages'] = 0
1.43 casties 386:
387: # TODO: produce and keep list of image names and numbers
1.7 casties 388:
389: return docinfo
1.8 casties 390:
1.6 casties 391:
1.9 casties 392: def getIndexMeta(self, url):
393: """returns dom of index.meta document at url"""
394: dom = None
1.12 casties 395: metaUrl = None
1.9 casties 396: if url.startswith("http://"):
397: # real URL
1.12 casties 398: metaUrl = url
1.9 casties 399: else:
400: # online path
401: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 402: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 403: if not metaUrl.endswith("index.meta"):
404: metaUrl += "/index.meta"
1.12 casties 405:
1.70 casties 406: logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)
407: txt=getHttpData(metaUrl)
408: if txt is None:
1.12 casties 409: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 410:
411: dom = Parse(txt)
1.9 casties 412: return dom
1.20 dwinter 413:
414: def getPresentationInfoXML(self, url):
415: """returns dom of info.xml document at url"""
416: dom = None
417: metaUrl = None
418: if url.startswith("http://"):
419: # real URL
420: metaUrl = url
421: else:
422: # online path
423: server=self.digilibBaseUrl+"/servlet/Texter?fn="
424: metaUrl=server+url.replace("/mpiwg/online","")
425:
1.70 casties 426: txt=getHttpData(metaUrl)
427: if txt is None:
1.20 dwinter 428: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 429:
430: dom = Parse(txt)
1.20 dwinter 431: return dom
1.9 casties 432:
433:
1.33 dwinter 434: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 435: """gets authorization info from the index.meta file at path or given by dom"""
1.70 casties 436: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 437:
438: access = None
439:
440: if docinfo is None:
441: docinfo = {}
442:
443: if dom is None:
1.38 dwinter 444: for x in range(cut):
1.33 dwinter 445: path=getParentDir(path)
446: dom = self.getIndexMeta(path)
1.18 dwinter 447:
1.8 casties 448: acctype = dom.xpath("//access-conditions/access/@type")
449: if acctype and (len(acctype)>0):
450: access=acctype[0].value
1.9 casties 451: if access in ['group', 'institution']:
1.8 casties 452: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
453:
454: docinfo['accessType'] = access
455: return docinfo
1.6 casties 456:
1.8 casties 457:
1.33 dwinter 458: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 459: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 460: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 461:
1.3 casties 462: if docinfo is None:
463: docinfo = {}
1.38 dwinter 464:
1.3 casties 465: if dom is None:
1.38 dwinter 466: for x in range(cut):
1.33 dwinter 467: path=getParentDir(path)
468: dom = self.getIndexMeta(path)
1.39 dwinter 469:
470: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 471: # put in all raw bib fields as dict "bib"
472: bib = dom.xpath("//bib/*")
473: if bib and len(bib)>0:
474: bibinfo = {}
475: for e in bib:
476: bibinfo[e.localName] = getTextFromNode(e)
477: docinfo['bib'] = bibinfo
478:
479: # extract some fields (author, title, year) according to their mapping
1.4 casties 480: metaData=self.metadata.main.meta.bib
481: bibtype=dom.xpath("//bib/@type")
482: if bibtype and (len(bibtype)>0):
483: bibtype=bibtype[0].value
1.2 dwinter 484: else:
1.4 casties 485: bibtype="generic"
1.27 casties 486:
1.4 casties 487: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 488: docinfo['bib_type'] = bibtype
1.4 casties 489: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 490: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 491: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 492: try:
493: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
494: except: pass
495: try:
496: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
497: except: pass
498: try:
499: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
500: except: pass
1.27 casties 501: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 502: try:
503: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
504: except:
505: docinfo['lang']=''
1.27 casties 506:
1.3 casties 507: return docinfo
1.42 abukhman 508:
509:
1.43 casties 510: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
511: """parse texttool tag in index meta"""
1.70 casties 512: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 513: if docinfo is None:
514: docinfo = {}
515: if docinfo.get('lang', None) is None:
516: docinfo['lang'] = '' # default keine Sprache gesetzt
517: if dom is None:
518: dom = self.getIndexMeta(url)
519:
520: archivePath = None
521: archiveName = None
522:
523: archiveNames = dom.xpath("//resource/name")
524: if archiveNames and (len(archiveNames) > 0):
525: archiveName = getTextFromNode(archiveNames[0])
526: else:
1.70 casties 527: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 528:
529: archivePaths = dom.xpath("//resource/archive-path")
530: if archivePaths and (len(archivePaths) > 0):
531: archivePath = getTextFromNode(archivePaths[0])
532: # clean up archive path
533: if archivePath[0] != '/':
534: archivePath = '/' + archivePath
535: if archiveName and (not archivePath.endswith(archiveName)):
536: archivePath += "/" + archiveName
537: else:
538: # try to get archive-path from url
1.70 casties 539: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 540: if (not url.startswith('http')):
541: archivePath = url.replace('index.meta', '')
542:
543: if archivePath is None:
544: # we balk without archive-path
545: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
546:
547: imageDirs = dom.xpath("//texttool/image")
548: if imageDirs and (len(imageDirs) > 0):
549: imageDir = getTextFromNode(imageDirs[0])
550:
551: else:
552: # we balk with no image tag / not necessary anymore because textmode is now standard
553: #raise IOError("No text-tool info in %s"%(url))
554: imageDir = ""
555: #xquery="//pb"
556: docinfo['imagePath'] = "" # keine Bilder
557: docinfo['imageURL'] = ""
558:
559: if imageDir and archivePath:
560: #print "image: ", imageDir, " archivepath: ", archivePath
561: imageDir = os.path.join(archivePath, imageDir)
562: imageDir = imageDir.replace("/mpiwg/online", '')
563: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
564: docinfo['imagePath'] = imageDir
565:
566: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
567:
568: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
569: if viewerUrls and (len(viewerUrls) > 0):
570: viewerUrl = getTextFromNode(viewerUrls[0])
571: docinfo['viewerURL'] = viewerUrl
1.70 casties 572:
573: # old style text URL
1.43 casties 574: textUrls = dom.xpath("//texttool/text")
575: if textUrls and (len(textUrls) > 0):
576: textUrl = getTextFromNode(textUrls[0])
577: if urlparse.urlparse(textUrl)[0] == "": #keine url
578: textUrl = os.path.join(archivePath, textUrl)
579: # fix URLs starting with /mpiwg/online
580: if textUrl.startswith("/mpiwg/online"):
581: textUrl = textUrl.replace("/mpiwg/online", '', 1)
582:
583: docinfo['textURL'] = textUrl
584:
1.70 casties 585: # new style text-url-path
1.43 casties 586: textUrls = dom.xpath("//texttool/text-url-path")
587: if textUrls and (len(textUrls) > 0):
588: textUrl = getTextFromNode(textUrls[0])
1.51 casties 589: docinfo['textURLPath'] = textUrl
590: if not docinfo['imagePath']:
591: # text-only, no page images
1.72 casties 592: docinfo = self.getNumPages(docinfo)
1.43 casties 593:
594: presentationUrls = dom.xpath("//texttool/presentation")
595: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
596:
597: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
598: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
599: # durch den relativen Pfad auf die presentation infos
600: presentationPath = getTextFromNode(presentationUrls[0])
601: if url.endswith("index.meta"):
602: presentationUrl = url.replace('index.meta', presentationPath)
603: else:
604: presentationUrl = url + "/" + presentationPath
1.51 casties 605:
1.43 casties 606: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
607:
608: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 609:
1.43 casties 610: return docinfo
1.3 casties 611:
1.20 dwinter 612:
613: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
614: """gets the bibliographical information from the preseantion entry in texttools
615: """
616: dom=self.getPresentationInfoXML(url)
1.29 casties 617: try:
618: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
619: except:
620: pass
621: try:
622: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
623: except:
624: pass
625: try:
626: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
627: except:
628: pass
1.20 dwinter 629: return docinfo
630:
1.33 dwinter 631: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 632: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.70 casties 633: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 634: if docinfo is None:
635: docinfo = {}
1.6 casties 636: path=path.replace("/mpiwg/online","")
1.3 casties 637: docinfo['imagePath'] = path
1.35 dwinter 638: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 639:
1.39 dwinter 640: pathorig=path
1.38 dwinter 641: for x in range(cut):
642: path=getParentDir(path)
1.70 casties 643: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 644: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 645: docinfo['imageURL'] = imageUrl
646:
1.39 dwinter 647: #path ist the path to the images it assumes that the index.meta file is one level higher.
648: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
649: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 650: return docinfo
651:
1.2 dwinter 652:
1.3 casties 653: def getDocinfo(self, mode, url):
654: """returns docinfo depending on mode"""
1.70 casties 655: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 656: # look for cached docinfo in session
1.21 dwinter 657: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 658: docinfo = self.REQUEST.SESSION['docinfo']
659: # check if its still current
660: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.70 casties 661: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 662: return docinfo
663: # new docinfo
664: docinfo = {'mode': mode, 'url': url}
665: if mode=="texttool": #index.meta with texttool information
666: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
667: elif mode=="imagepath":
668: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 669: elif mode=="filepath":
1.37 dwinter 670: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 671: else:
1.70 casties 672: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 673: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 674:
1.70 casties 675: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 676: self.REQUEST.SESSION['docinfo'] = docinfo
677: return docinfo
1.69 abukhman 678:
1.44 casties 679: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 680: """returns pageinfo with the given parameters"""
681: pageinfo = {}
1.4 casties 682: current = getInt(current)
683: pageinfo['current'] = current
684: rows = int(rows or self.thumbrows)
685: pageinfo['rows'] = rows
686: cols = int(cols or self.thumbcols)
687: pageinfo['cols'] = cols
688: grpsize = cols * rows
689: pageinfo['groupsize'] = grpsize
1.28 casties 690: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
691: # int(current / grpsize) * grpsize +1))
1.3 casties 692: pageinfo['start'] = start
1.4 casties 693: pageinfo['end'] = start + grpsize
1.44 casties 694: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 695: np = int(docinfo['numPages'])
696: pageinfo['end'] = min(pageinfo['end'], np)
697: pageinfo['numgroups'] = int(np / grpsize)
698: if np % grpsize > 0:
1.69 abukhman 699: pageinfo['numgroups'] += 1
1.44 casties 700: pageinfo['viewMode'] = viewMode
701: pageinfo['tocMode'] = tocMode
1.45 abukhman 702: pageinfo['query'] = self.REQUEST.get('query',' ')
703: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
704: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 705: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 706: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 707: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 708: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 709: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 710: toc = int (pageinfo['tocPN'])
711: pageinfo['textPages'] =int (toc)
712:
713: if 'tocSize_%s'%tocMode in docinfo:
714: tocSize = int(docinfo['tocSize_%s'%tocMode])
715: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 716: # cached toc
1.48 abukhman 717: if tocSize%tocPageSize>0:
718: tocPages=tocSize/tocPageSize+1
719: else:
720: tocPages=tocSize/tocPageSize
1.69 abukhman 721: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 722: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 723: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 724: return pageinfo
725:
1.69 abukhman 726: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 727: """init document viewer"""
728: self.title=title
729: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 730: self.thumbrows = thumbrows
731: self.thumbcols = thumbcols
1.8 casties 732: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 733: if RESPONSE is not None:
734: RESPONSE.redirect('manage_main')
1.1 dwinter 735:
736: def manage_AddDocumentViewerForm(self):
737: """add the viewer form"""
1.3 casties 738: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 739: return pt()
740:
1.43 casties 741: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 742: """add the viewer"""
1.43 casties 743: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 744: self._setObject(id,newObj)
745:
746: if RESPONSE is not None:
747: RESPONSE.redirect('manage_main')
1.3 casties 748:
749: ## DocumentViewerTemplate class
750: class DocumentViewerTemplate(ZopePageTemplate):
751: """Template for document viewer"""
752: meta_type="DocumentViewer Template"
753:
754:
755: def manage_addDocumentViewerTemplateForm(self):
756: """Form for adding"""
757: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
758: return pt()
759:
760: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
761: REQUEST=None, submit=None):
762: "Add a Page Template with optional file content."
763:
764: self._setObject(id, DocumentViewerTemplate(id))
765: ob = getattr(self, id)
1.23 dwinter 766: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
767: logging.info("txt %s:"%txt)
768: ob.pt_edit(txt,"text/html")
1.3 casties 769: if title:
770: ob.pt_setTitle(title)
771: try:
772: u = self.DestinationURL()
773: except AttributeError:
774: u = REQUEST['URL1']
775:
776: u = "%s/%s" % (u, urllib.quote(id))
777: REQUEST.RESPONSE.redirect(u+'/manage_main')
778: return ''
779:
780:
1.14 casties 781:
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