Annotation of documentViewer/documentViewer.py, revision 1.69.2.4
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
1.50 abukhman 5: from Products.PythonScripts.standard import url_quote
1.1 dwinter 6: from AccessControl import ClassSecurityInfo
1.8 casties 7: from AccessControl import getSecurityManager
1.1 dwinter 8: from Globals import package_home
9:
10: from Ft.Xml.Domlette import NonvalidatingReader
11: from Ft.Xml.Domlette import PrettyPrint, Print
1.11 casties 12: from Ft.Xml import EMPTY_NAMESPACE, Parse
1.1 dwinter 13: import Ft.Xml.XPath
1.43 casties 14: import cStringIO
1.42 abukhman 15: import xmlrpclib
1.1 dwinter 16: import os.path
1.7 casties 17: import sys
1.1 dwinter 18: import cgi
19: import urllib
1.20 dwinter 20: import logging
1.28 casties 21: import math
1.22 dwinter 22:
1.18 dwinter 23: import urlparse
1.37 dwinter 24: from types import *
1.43 casties 25:
1.22 dwinter 26: def logger(txt,method,txt2):
27: """logging"""
28: logging.info(txt+ txt2)
29:
30:
1.4 casties 31: def getInt(number, default=0):
32: """returns always an int (0 in case of problems)"""
33: try:
34: return int(number)
35: except:
1.29 casties 36: return int(default)
1.4 casties 37:
1.1 dwinter 38: def getTextFromNode(nodename):
1.18 dwinter 39: """get the cdata content of a node"""
1.8 casties 40: if nodename is None:
41: return ""
1.1 dwinter 42: nodelist=nodename.childNodes
43: rc = ""
44: for node in nodelist:
45: if node.nodeType == node.TEXT_NODE:
46: rc = rc + node.data
47: return rc
48:
1.43 casties 49: def serializeNode(node, encoding='utf-8'):
50: """returns a string containing node as XML"""
51: buf = cStringIO.StringIO()
52: Print(node, stream=buf, encoding=encoding)
53: s = buf.getvalue()
54: buf.close()
55: return s
56:
1.9 casties 57:
58: def getParentDir(path):
59: """returns pathname shortened by one"""
60: return '/'.join(path.split('/')[0:-1])
61:
62:
1.69.2.3 casties 63: def getHttpData(url, data=None, num_tries=3, timeout=10):
64: """returns result from url+data HTTP request"""
65: # we do GET (by appending data to url)
66: if isinstance(data, str) or isinstance(data, unicode):
67: # if data is string then append
68: url = "%s?%s"%(url,data)
69: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
70: # urlencode
71: url = "%s?%s"%(url,urllib.urlencode(data))
72:
73: response = None
74: errmsg = None
75: for cnt in range(num_tries):
76: try:
77: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
78: if sys.version_info < (2, 6):
79: # set timeout on socket -- ugly :-(
80: import socket
81: socket.setdefaulttimeout(timeout)
82: response = urllib2.urlopen(url)
83: else:
84: response = urllib2.urlopen(url,timeout=float(timeout))
85: # check result?
86: break
87: except urllib2.HTTPError, e:
88: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
89: errmsg = str(e)
90: # stop trying
91: break
92: except urllib2.URLError, e:
93: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
94: errmsg = str(e)
95: # stop trying
96: #break
97:
98: if response is not None:
99: data = response.read()
100: response.close()
101: return data
102:
103: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
104: #return None
1.1 dwinter 105:
106:
107:
1.3 casties 108: ##
109: ## documentViewer class
110: ##
1.69.2.3 casties 111: class documentViewer(Folder):
1.1 dwinter 112: """document viewer"""
113: meta_type="Document viewer"
114:
115: security=ClassSecurityInfo()
1.3 casties 116: manage_options=Folder.manage_options+(
1.1 dwinter 117: {'label':'main config','action':'changeDocumentViewerForm'},
118: )
119:
1.3 casties 120: # templates and forms
121: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 122: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
123: toc_text = PageTemplateFile('zpt/toc_text', globals())
124: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 125: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
126: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 127: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.48 abukhman 128: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 129: head_main = PageTemplateFile('zpt/head_main', globals())
130: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 131: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.69.2.1 abukhman 132:
133:
1.32 dwinter 134: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 135: security.declareProtected('View management screens','changeDocumentViewerForm')
136: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
137:
1.1 dwinter 138:
1.45 abukhman 139: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 140: """init document viewer"""
141: self.id=id
142: self.title=title
1.4 casties 143: self.thumbcols = thumbcols
144: self.thumbrows = thumbrows
1.8 casties 145: # authgroups is list of authorized groups (delimited by ,)
146: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 147: # create template folder so we can always use template.something
148:
149: templateFolder = Folder('template')
150: #self['template'] = templateFolder # Zope-2.12 style
151: self._setObject('template',templateFolder) # old style
152: try:
1.69.2.3 casties 153: import MpdlXmlTextServer
154: textServer = MpdlXmlTextServer(id='fulltextclient')
1.43 casties 155: #templateFolder['fulltextclient'] = xmlRpcClient
1.69.2.3 casties 156: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 157: except Exception, e:
1.69.2.3 casties 158: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 159: try:
160: from Products.zogiLib.zogiLib import zogiLib
161: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
162: #templateFolder['zogilib'] = zogilib
163: templateFolder._setObject('zogilib',zogilib)
164: except Exception, e:
165: logging.error("Unable to create zogiLib for zogilib: "+str(e))
166:
1.69.2.3 casties 167:
168: # proxy text server methods to fulltextclient
169: def getTextPage(self, **args):
170: """get page"""
171: return self.template.fulltextclient.getTextPage(**args)
172:
173: def getQuery(self, **args):
174: """get query"""
175: return self.template.fulltextclient.getQuery(**args)
176:
177: def getSearch(self, **args):
178: """get search"""
179: return self.template.fulltextclient.getSearch(**args)
180:
181: def getNumPages(self, **args):
182: """get numpages"""
183: return self.template.fulltextclient.getNumPages(**args)
184:
185: def getTranslate(self, **args):
186: """get translate"""
187: return self.template.fulltextclient.getTranslate(**args)
188:
189: def getLemma(self, **args):
190: """get lemma"""
191: return self.template.fulltextclient.getLemma(**args)
192:
193: def getToc(self, **args):
194: """get toc"""
195: return self.template.fulltextclient.getToc(**args)
196:
197: def getTocPage(self, **args):
198: """get tocpage"""
199: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 200:
1.69.2.3 casties 201:
1.32 dwinter 202: security.declareProtected('View','thumbs_rss')
203: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
204: '''
205: view it
206: @param mode: defines how to access the document behind url
207: @param url: url which contains display information
208: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
209:
210: '''
1.43 casties 211: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.32 dwinter 212: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
213:
214: if not hasattr(self, 'template'):
215: # create template folder if it doesn't exist
216: self.manage_addFolder('template')
217:
218: if not self.digilibBaseUrl:
219: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
220:
221: docinfo = self.getDocinfo(mode=mode,url=url)
222: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
223: pt = getattr(self.template, 'thumbs_main_rss')
224:
225: if viewMode=="auto": # automodus gewaehlt
226: if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
227: viewMode="text"
228: else:
229: viewMode="images"
230:
231: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
232:
1.3 casties 233: security.declareProtected('View','index_html')
1.45 abukhman 234: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
1.3 casties 235: '''
236: view it
1.26 casties 237: @param mode: defines how to access the document behind url
1.3 casties 238: @param url: url which contains display information
1.44 casties 239: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 240: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.49 abukhman 241: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 242: '''
243:
1.43 casties 244: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 245:
1.3 casties 246: if not hasattr(self, 'template'):
1.43 casties 247: # this won't work
248: logging.error("template folder missing!")
249: return "ERROR: template folder missing!"
1.3 casties 250:
1.43 casties 251: if not getattr(self, 'digilibBaseUrl', None):
1.3 casties 252: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
253:
1.4 casties 254: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 255:
256:
1.44 casties 257: if tocMode != "thumbs":
258: # get table of contents
259: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 260:
1.21 dwinter 261: if viewMode=="auto": # automodus gewaehlt
1.43 casties 262: if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
1.68 casties 263: viewMode="text_dict"
1.21 dwinter 264: else:
265: viewMode="images"
1.44 casties 266:
1.68 casties 267: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
268:
1.44 casties 269: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 270: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 271:
1.36 dwinter 272: def generateMarks(self,mk):
273: ret=""
1.44 casties 274: if mk is None:
275: return ""
276: if type(mk) is not ListType:
277: mk=[mk]
1.36 dwinter 278: for m in mk:
1.37 dwinter 279: ret+="mk=%s"%m
1.36 dwinter 280: return ret
1.43 casties 281:
1.44 casties 282:
1.43 casties 283: def findDigilibUrl(self):
284: """try to get the digilib URL from zogilib"""
285: url = self.template.zogilib.getDLBaseUrl()
286: return url
1.67 casties 287:
288: def getDocumentViewerURL(self):
289: """returns the URL of this instance"""
290: return self.absolute_url()
1.43 casties 291:
292: def getStyle(self, idx, selected, style=""):
293: """returns a string with the given style and append 'sel' if path == selected."""
294: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
295: if idx == selected:
296: return style + 'sel'
297: else:
298: return style
1.36 dwinter 299:
1.4 casties 300: def getLink(self,param=None,val=None):
301: """link to documentviewer with parameter param set to val"""
1.9 casties 302: params=self.REQUEST.form.copy()
1.4 casties 303: if param is not None:
1.7 casties 304: if val is None:
305: if params.has_key(param):
306: del params[param]
1.4 casties 307: else:
1.9 casties 308: params[param] = str(val)
1.43 casties 309:
310: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 311: params["mode"] = "imagepath"
312: params["url"] = getParentDir(params["url"])
1.7 casties 313:
1.9 casties 314: # quote values and assemble into query string
315: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
316: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 317: return url
318:
1.32 dwinter 319: def getLinkAmp(self,param=None,val=None):
320: """link to documentviewer with parameter param set to val"""
321: params=self.REQUEST.form.copy()
322: if param is not None:
323: if val is None:
324: if params.has_key(param):
325: del params[param]
326: else:
327: params[param] = str(val)
328:
329: # quote values and assemble into query string
1.69.2.2 casties 330: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 331: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
332: url=self.REQUEST['URL1']+"?"+ps
333: return url
1.40 casties 334:
1.26 casties 335: def getInfo_xml(self,url,mode):
336: """returns info about the document as XML"""
337:
338: if not self.digilibBaseUrl:
339: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
340:
341: docinfo = self.getDocinfo(mode=mode,url=url)
342: pt = getattr(self.template, 'info_xml')
343: return pt(docinfo=docinfo)
344:
1.4 casties 345:
1.9 casties 346: def isAccessible(self, docinfo):
1.8 casties 347: """returns if access to the resource is granted"""
348: access = docinfo.get('accessType', None)
1.69.2.2 casties 349: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 350: if access is not None and access == 'free':
1.69.2.2 casties 351: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 352: return True
1.17 casties 353: elif access is None or access in self.authgroups:
1.9 casties 354: # only local access -- only logged in users
355: user = getSecurityManager().getUser()
356: if user is not None:
357: #print "user: ", user
358: return (user.getUserName() != "Anonymous User")
359: else:
360: return False
1.8 casties 361:
1.69.2.2 casties 362: logging.debug("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 363: return False
1.9 casties 364:
1.8 casties 365:
1.35 dwinter 366: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 367: """gibt param von dlInfo aus"""
1.7 casties 368: if docinfo is None:
369: docinfo = {}
1.35 dwinter 370:
371: for x in range(cut):
1.38 dwinter 372:
1.35 dwinter 373: path=getParentDir(path)
1.38 dwinter 374:
1.13 casties 375: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 376:
1.69.2.2 casties 377: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 378:
1.69.2.3 casties 379: txt = getHttpData(infoUrl)
380: if txt is None:
1.13 casties 381: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.69.2.3 casties 382:
383: dom = Parse(txt)
1.10 casties 384: sizes=dom.xpath("//dir/size")
1.69.2.2 casties 385: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 386:
1.10 casties 387: if sizes:
388: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 389: else:
390: docinfo['numPages'] = 0
1.43 casties 391:
392: # TODO: produce and keep list of image names and numbers
1.7 casties 393:
394: return docinfo
1.8 casties 395:
1.6 casties 396:
1.9 casties 397: def getIndexMeta(self, url):
398: """returns dom of index.meta document at url"""
399: dom = None
1.12 casties 400: metaUrl = None
1.9 casties 401: if url.startswith("http://"):
402: # real URL
1.12 casties 403: metaUrl = url
1.9 casties 404: else:
405: # online path
406: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 407: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 408: if not metaUrl.endswith("index.meta"):
409: metaUrl += "/index.meta"
1.12 casties 410:
1.69.2.3 casties 411: logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)
412: txt=getHttpData(metaUrl)
413: if txt is None:
1.12 casties 414: raise IOError("Unable to read index meta from %s"%(url))
1.69.2.3 casties 415:
416: dom = Parse(txt)
1.9 casties 417: return dom
1.20 dwinter 418:
419: def getPresentationInfoXML(self, url):
420: """returns dom of info.xml document at url"""
421: dom = None
422: metaUrl = None
423: if url.startswith("http://"):
424: # real URL
425: metaUrl = url
426: else:
427: # online path
428: server=self.digilibBaseUrl+"/servlet/Texter?fn="
429: metaUrl=server+url.replace("/mpiwg/online","")
430:
1.69.2.3 casties 431: txt=getHttpData(metaUrl)
432: if txt is None:
1.20 dwinter 433: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.69.2.3 casties 434:
435: dom = Parse(txt)
1.20 dwinter 436: return dom
1.9 casties 437:
438:
1.33 dwinter 439: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 440: """gets authorization info from the index.meta file at path or given by dom"""
1.69.2.2 casties 441: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 442:
443: access = None
444:
445: if docinfo is None:
446: docinfo = {}
447:
448: if dom is None:
1.38 dwinter 449: for x in range(cut):
1.33 dwinter 450: path=getParentDir(path)
451: dom = self.getIndexMeta(path)
1.18 dwinter 452:
1.8 casties 453: acctype = dom.xpath("//access-conditions/access/@type")
454: if acctype and (len(acctype)>0):
455: access=acctype[0].value
1.9 casties 456: if access in ['group', 'institution']:
1.8 casties 457: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
458:
459: docinfo['accessType'] = access
460: return docinfo
1.6 casties 461:
1.8 casties 462:
1.33 dwinter 463: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 464: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 465: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 466:
1.3 casties 467: if docinfo is None:
468: docinfo = {}
1.38 dwinter 469:
1.3 casties 470: if dom is None:
1.38 dwinter 471: for x in range(cut):
1.33 dwinter 472: path=getParentDir(path)
473: dom = self.getIndexMeta(path)
1.39 dwinter 474:
475: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 476: # put in all raw bib fields as dict "bib"
477: bib = dom.xpath("//bib/*")
478: if bib and len(bib)>0:
479: bibinfo = {}
480: for e in bib:
481: bibinfo[e.localName] = getTextFromNode(e)
482: docinfo['bib'] = bibinfo
483:
484: # extract some fields (author, title, year) according to their mapping
1.4 casties 485: metaData=self.metadata.main.meta.bib
486: bibtype=dom.xpath("//bib/@type")
487: if bibtype and (len(bibtype)>0):
488: bibtype=bibtype[0].value
1.2 dwinter 489: else:
1.4 casties 490: bibtype="generic"
1.27 casties 491:
1.4 casties 492: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 493: docinfo['bib_type'] = bibtype
1.4 casties 494: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 495: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 496: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 497: try:
498: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
499: except: pass
500: try:
501: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
502: except: pass
503: try:
504: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
505: except: pass
1.27 casties 506: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 507: try:
508: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
509: except:
510: docinfo['lang']=''
1.27 casties 511:
1.3 casties 512: return docinfo
1.42 abukhman 513:
514:
1.43 casties 515: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
516: """parse texttool tag in index meta"""
1.69.2.2 casties 517: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 518: if docinfo is None:
519: docinfo = {}
520: if docinfo.get('lang', None) is None:
521: docinfo['lang'] = '' # default keine Sprache gesetzt
522: if dom is None:
523: dom = self.getIndexMeta(url)
524:
525: archivePath = None
526: archiveName = None
527:
528: archiveNames = dom.xpath("//resource/name")
529: if archiveNames and (len(archiveNames) > 0):
530: archiveName = getTextFromNode(archiveNames[0])
531: else:
1.69.2.2 casties 532: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 533:
534: archivePaths = dom.xpath("//resource/archive-path")
535: if archivePaths and (len(archivePaths) > 0):
536: archivePath = getTextFromNode(archivePaths[0])
537: # clean up archive path
538: if archivePath[0] != '/':
539: archivePath = '/' + archivePath
540: if archiveName and (not archivePath.endswith(archiveName)):
541: archivePath += "/" + archiveName
542: else:
543: # try to get archive-path from url
1.69.2.2 casties 544: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 545: if (not url.startswith('http')):
546: archivePath = url.replace('index.meta', '')
547:
548: if archivePath is None:
549: # we balk without archive-path
550: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
551:
552: imageDirs = dom.xpath("//texttool/image")
553: if imageDirs and (len(imageDirs) > 0):
554: imageDir = getTextFromNode(imageDirs[0])
555:
556: else:
557: # we balk with no image tag / not necessary anymore because textmode is now standard
558: #raise IOError("No text-tool info in %s"%(url))
559: imageDir = ""
560: #xquery="//pb"
561: docinfo['imagePath'] = "" # keine Bilder
562: docinfo['imageURL'] = ""
563:
564: if imageDir and archivePath:
565: #print "image: ", imageDir, " archivepath: ", archivePath
566: imageDir = os.path.join(archivePath, imageDir)
567: imageDir = imageDir.replace("/mpiwg/online", '')
568: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
569: docinfo['imagePath'] = imageDir
570:
571: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
572:
573: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
574: if viewerUrls and (len(viewerUrls) > 0):
575: viewerUrl = getTextFromNode(viewerUrls[0])
576: docinfo['viewerURL'] = viewerUrl
577:
578: textUrls = dom.xpath("//texttool/text")
579: if textUrls and (len(textUrls) > 0):
580: textUrl = getTextFromNode(textUrls[0])
581: if urlparse.urlparse(textUrl)[0] == "": #keine url
582: textUrl = os.path.join(archivePath, textUrl)
583: # fix URLs starting with /mpiwg/online
584: if textUrl.startswith("/mpiwg/online"):
585: textUrl = textUrl.replace("/mpiwg/online", '', 1)
586:
587: docinfo['textURL'] = textUrl
588:
589: textUrls = dom.xpath("//texttool/text-url-path")
590: if textUrls and (len(textUrls) > 0):
591: textUrl = getTextFromNode(textUrls[0])
1.51 casties 592: docinfo['textURLPath'] = textUrl
593: if not docinfo['imagePath']:
594: # text-only, no page images
595: docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht
1.43 casties 596:
597: presentationUrls = dom.xpath("//texttool/presentation")
598: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
599:
600: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
601: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
602: # durch den relativen Pfad auf die presentation infos
603: presentationPath = getTextFromNode(presentationUrls[0])
604: if url.endswith("index.meta"):
605: presentationUrl = url.replace('index.meta', presentationPath)
606: else:
607: presentationUrl = url + "/" + presentationPath
1.51 casties 608:
1.43 casties 609: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
610:
611: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 612:
1.43 casties 613: return docinfo
1.3 casties 614:
1.20 dwinter 615:
616: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
617: """gets the bibliographical information from the preseantion entry in texttools
618: """
619: dom=self.getPresentationInfoXML(url)
1.29 casties 620: try:
621: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
622: except:
623: pass
624: try:
625: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
626: except:
627: pass
628: try:
629: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
630: except:
631: pass
1.20 dwinter 632: return docinfo
633:
1.33 dwinter 634: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 635: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.69.2.2 casties 636: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 637: if docinfo is None:
638: docinfo = {}
1.6 casties 639: path=path.replace("/mpiwg/online","")
1.3 casties 640: docinfo['imagePath'] = path
1.35 dwinter 641: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 642:
1.39 dwinter 643: pathorig=path
1.38 dwinter 644: for x in range(cut):
645: path=getParentDir(path)
1.69.2.2 casties 646: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 647: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 648: docinfo['imageURL'] = imageUrl
649:
1.39 dwinter 650: #path ist the path to the images it assumes that the index.meta file is one level higher.
651: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
652: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 653: return docinfo
654:
1.2 dwinter 655:
1.3 casties 656: def getDocinfo(self, mode, url):
657: """returns docinfo depending on mode"""
1.69.2.2 casties 658: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 659: # look for cached docinfo in session
1.21 dwinter 660: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 661: docinfo = self.REQUEST.SESSION['docinfo']
662: # check if its still current
663: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.69.2.2 casties 664: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 665: return docinfo
666: # new docinfo
667: docinfo = {'mode': mode, 'url': url}
668: if mode=="texttool": #index.meta with texttool information
669: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
670: elif mode=="imagepath":
671: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 672: elif mode=="filepath":
1.37 dwinter 673: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 674: else:
1.69.2.2 casties 675: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 676: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 677:
1.69.2.2 casties 678: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 679: self.REQUEST.SESSION['docinfo'] = docinfo
680: return docinfo
1.69 abukhman 681:
1.44 casties 682: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 683: """returns pageinfo with the given parameters"""
684: pageinfo = {}
1.4 casties 685: current = getInt(current)
686: pageinfo['current'] = current
687: rows = int(rows or self.thumbrows)
688: pageinfo['rows'] = rows
689: cols = int(cols or self.thumbcols)
690: pageinfo['cols'] = cols
691: grpsize = cols * rows
692: pageinfo['groupsize'] = grpsize
1.28 casties 693: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
694: # int(current / grpsize) * grpsize +1))
1.3 casties 695: pageinfo['start'] = start
1.4 casties 696: pageinfo['end'] = start + grpsize
1.44 casties 697: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 698: np = int(docinfo['numPages'])
699: pageinfo['end'] = min(pageinfo['end'], np)
700: pageinfo['numgroups'] = int(np / grpsize)
701: if np % grpsize > 0:
1.69 abukhman 702: pageinfo['numgroups'] += 1
1.44 casties 703: pageinfo['viewMode'] = viewMode
704: pageinfo['tocMode'] = tocMode
1.45 abukhman 705: pageinfo['query'] = self.REQUEST.get('query',' ')
706: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
707: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 708: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 709: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 710: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 711: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 712: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 713: toc = int (pageinfo['tocPN'])
714: pageinfo['textPages'] =int (toc)
715:
716: if 'tocSize_%s'%tocMode in docinfo:
717: tocSize = int(docinfo['tocSize_%s'%tocMode])
718: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 719: # cached toc
1.48 abukhman 720: if tocSize%tocPageSize>0:
721: tocPages=tocSize/tocPageSize+1
722: else:
723: tocPages=tocSize/tocPageSize
1.69 abukhman 724: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 725: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 726: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 727: return pageinfo
728:
1.69 abukhman 729: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 730: """init document viewer"""
731: self.title=title
732: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 733: self.thumbrows = thumbrows
734: self.thumbcols = thumbcols
1.8 casties 735: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 736: if RESPONSE is not None:
737: RESPONSE.redirect('manage_main')
1.1 dwinter 738:
739: def manage_AddDocumentViewerForm(self):
740: """add the viewer form"""
1.3 casties 741: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 742: return pt()
743:
1.43 casties 744: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 745: """add the viewer"""
1.43 casties 746: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 747: self._setObject(id,newObj)
748:
749: if RESPONSE is not None:
750: RESPONSE.redirect('manage_main')
1.3 casties 751:
752: ## DocumentViewerTemplate class
753: class DocumentViewerTemplate(ZopePageTemplate):
754: """Template for document viewer"""
755: meta_type="DocumentViewer Template"
756:
757:
758: def manage_addDocumentViewerTemplateForm(self):
759: """Form for adding"""
760: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
761: return pt()
762:
763: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
764: REQUEST=None, submit=None):
765: "Add a Page Template with optional file content."
766:
767: self._setObject(id, DocumentViewerTemplate(id))
768: ob = getattr(self, id)
1.23 dwinter 769: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
770: logging.info("txt %s:"%txt)
771: ob.pt_edit(txt,"text/html")
1.3 casties 772: if title:
773: ob.pt_setTitle(title)
774: try:
775: u = self.DestinationURL()
776: except AttributeError:
777: u = REQUEST['URL1']
778:
779: u = "%s/%s" % (u, urllib.quote(id))
780: REQUEST.RESPONSE.redirect(u+'/manage_main')
781: return ''
782:
783:
1.14 casties 784:
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