Annotation of documentViewer/documentViewer.py, revision 1.77
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())
1.77 ! abukhman 122: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 123: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 124: head_main = PageTemplateFile('zpt/head_main', globals())
125: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 126: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 127:
128:
1.32 dwinter 129: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 130: security.declareProtected('View management screens','changeDocumentViewerForm')
131: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
132:
1.1 dwinter 133:
1.45 abukhman 134: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 135: """init document viewer"""
136: self.id=id
137: self.title=title
1.4 casties 138: self.thumbcols = thumbcols
139: self.thumbrows = thumbrows
1.8 casties 140: # authgroups is list of authorized groups (delimited by ,)
141: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 142: # create template folder so we can always use template.something
143:
144: templateFolder = Folder('template')
145: #self['template'] = templateFolder # Zope-2.12 style
146: self._setObject('template',templateFolder) # old style
147: try:
1.70 casties 148: import MpdlXmlTextServer
1.71 casties 149: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 150: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 151: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 152: except Exception, e:
1.70 casties 153: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 154: try:
155: from Products.zogiLib.zogiLib import zogiLib
156: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
157: #templateFolder['zogilib'] = zogilib
158: templateFolder._setObject('zogilib',zogilib)
159: except Exception, e:
160: logging.error("Unable to create zogiLib for zogilib: "+str(e))
161:
1.70 casties 162:
163: # proxy text server methods to fulltextclient
164: def getTextPage(self, **args):
165: """get page"""
166: return self.template.fulltextclient.getTextPage(**args)
167:
168: def getQuery(self, **args):
169: """get query"""
170: return self.template.fulltextclient.getQuery(**args)
171:
172: def getSearch(self, **args):
173: """get search"""
174: return self.template.fulltextclient.getSearch(**args)
175:
1.72 casties 176: def getNumPages(self, docinfo):
1.70 casties 177: """get numpages"""
1.72 casties 178: return self.template.fulltextclient.getNumPages(docinfo)
1.70 casties 179:
180: def getTranslate(self, **args):
181: """get translate"""
182: return self.template.fulltextclient.getTranslate(**args)
183:
184: def getLemma(self, **args):
185: """get lemma"""
186: return self.template.fulltextclient.getLemma(**args)
187:
188: def getToc(self, **args):
189: """get toc"""
190: return self.template.fulltextclient.getToc(**args)
191:
192: def getTocPage(self, **args):
193: """get tocpage"""
194: return self.template.fulltextclient.getTocPage(**args)
1.3 casties 195:
1.70 casties 196:
1.32 dwinter 197: security.declareProtected('View','thumbs_rss')
198: def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
199: '''
200: view it
201: @param mode: defines how to access the document behind url
202: @param url: url which contains display information
203: @param viewMode: if images display images, if text display text, default is images (text,images or auto)
204:
205: '''
1.43 casties 206: logging.debug("HHHHHHHHHHHHHH:load the rss")
1.32 dwinter 207: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
208:
209: if not hasattr(self, 'template'):
210: # create template folder if it doesn't exist
211: self.manage_addFolder('template')
212:
213: if not self.digilibBaseUrl:
214: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
215:
216: docinfo = self.getDocinfo(mode=mode,url=url)
217: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
218: pt = getattr(self.template, 'thumbs_main_rss')
219:
220: if viewMode=="auto": # automodus gewaehlt
1.70 casties 221: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 222: viewMode="text"
223: else:
224: viewMode="images"
225:
226: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
227:
1.3 casties 228: security.declareProtected('View','index_html')
1.45 abukhman 229: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
1.3 casties 230: '''
231: view it
1.26 casties 232: @param mode: defines how to access the document behind url
1.3 casties 233: @param url: url which contains display information
1.44 casties 234: @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
1.48 abukhman 235: @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
1.49 abukhman 236: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 237: '''
238:
1.43 casties 239: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 240:
1.3 casties 241: if not hasattr(self, 'template'):
1.43 casties 242: # this won't work
243: logging.error("template folder missing!")
244: return "ERROR: template folder missing!"
1.3 casties 245:
1.43 casties 246: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 247: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 248:
1.4 casties 249: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 250:
1.44 casties 251: if tocMode != "thumbs":
252: # get table of contents
253: docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
1.47 abukhman 254:
1.21 dwinter 255: if viewMode=="auto": # automodus gewaehlt
1.71 casties 256: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.68 casties 257: viewMode="text_dict"
1.21 dwinter 258: else:
259: viewMode="images"
1.44 casties 260:
1.68 casties 261: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
262:
1.44 casties 263: pt = getattr(self.template, 'viewer_main')
1.37 dwinter 264: return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
1.1 dwinter 265:
1.36 dwinter 266: def generateMarks(self,mk):
267: ret=""
1.44 casties 268: if mk is None:
269: return ""
1.73 casties 270: if not isinstance(mk, list):
1.71 casties 271: mk=[mk]
1.36 dwinter 272: for m in mk:
1.37 dwinter 273: ret+="mk=%s"%m
1.36 dwinter 274: return ret
1.43 casties 275:
1.44 casties 276:
1.43 casties 277: def findDigilibUrl(self):
278: """try to get the digilib URL from zogilib"""
279: url = self.template.zogilib.getDLBaseUrl()
280: return url
1.67 casties 281:
282: def getDocumentViewerURL(self):
283: """returns the URL of this instance"""
284: return self.absolute_url()
1.43 casties 285:
286: def getStyle(self, idx, selected, style=""):
287: """returns a string with the given style and append 'sel' if path == selected."""
288: #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
289: if idx == selected:
290: return style + 'sel'
291: else:
292: return style
1.36 dwinter 293:
1.4 casties 294: def getLink(self,param=None,val=None):
295: """link to documentviewer with parameter param set to val"""
1.9 casties 296: params=self.REQUEST.form.copy()
1.4 casties 297: if param is not None:
1.7 casties 298: if val is None:
299: if params.has_key(param):
300: del params[param]
1.4 casties 301: else:
1.9 casties 302: params[param] = str(val)
1.43 casties 303:
304: if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
1.38 dwinter 305: params["mode"] = "imagepath"
306: params["url"] = getParentDir(params["url"])
1.7 casties 307:
1.9 casties 308: # quote values and assemble into query string
1.74 casties 309: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
310: ps = urllib.urlencode(params)
1.9 casties 311: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 312: return url
313:
1.32 dwinter 314: def getLinkAmp(self,param=None,val=None):
315: """link to documentviewer with parameter param set to val"""
316: params=self.REQUEST.form.copy()
317: if param is not None:
318: if val is None:
319: if params.has_key(param):
320: del params[param]
321: else:
322: params[param] = str(val)
323:
324: # quote values and assemble into query string
1.70 casties 325: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 326: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
327: url=self.REQUEST['URL1']+"?"+ps
328: return url
1.40 casties 329:
1.26 casties 330: def getInfo_xml(self,url,mode):
331: """returns info about the document as XML"""
332:
333: if not self.digilibBaseUrl:
334: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
335:
336: docinfo = self.getDocinfo(mode=mode,url=url)
337: pt = getattr(self.template, 'info_xml')
338: return pt(docinfo=docinfo)
339:
1.4 casties 340:
1.9 casties 341: def isAccessible(self, docinfo):
1.8 casties 342: """returns if access to the resource is granted"""
343: access = docinfo.get('accessType', None)
1.70 casties 344: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 345: if access is not None and access == 'free':
1.70 casties 346: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 347: return True
1.17 casties 348: elif access is None or access in self.authgroups:
1.9 casties 349: # only local access -- only logged in users
350: user = getSecurityManager().getUser()
1.76 casties 351: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 352: if user is not None:
353: #print "user: ", user
354: return (user.getUserName() != "Anonymous User")
355: else:
356: return False
1.8 casties 357:
1.76 casties 358: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 359: return False
1.9 casties 360:
1.8 casties 361:
1.35 dwinter 362: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 363: """gibt param von dlInfo aus"""
1.7 casties 364: if docinfo is None:
365: docinfo = {}
1.35 dwinter 366:
367: for x in range(cut):
1.38 dwinter 368:
1.35 dwinter 369: path=getParentDir(path)
1.38 dwinter 370:
1.13 casties 371: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 372:
1.70 casties 373: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 374:
1.70 casties 375: txt = getHttpData(infoUrl)
376: if txt is None:
1.13 casties 377: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 378:
379: dom = Parse(txt)
1.10 casties 380: sizes=dom.xpath("//dir/size")
1.70 casties 381: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 382:
1.10 casties 383: if sizes:
384: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 385: else:
386: docinfo['numPages'] = 0
1.43 casties 387:
388: # TODO: produce and keep list of image names and numbers
1.7 casties 389:
390: return docinfo
1.8 casties 391:
1.6 casties 392:
1.9 casties 393: def getIndexMeta(self, url):
394: """returns dom of index.meta document at url"""
395: dom = None
1.12 casties 396: metaUrl = None
1.9 casties 397: if url.startswith("http://"):
398: # real URL
1.12 casties 399: metaUrl = url
1.9 casties 400: else:
401: # online path
402: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 403: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 404: if not metaUrl.endswith("index.meta"):
405: metaUrl += "/index.meta"
1.12 casties 406:
1.70 casties 407: logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)
408: txt=getHttpData(metaUrl)
409: if txt is None:
1.12 casties 410: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 411:
412: dom = Parse(txt)
1.9 casties 413: return dom
1.20 dwinter 414:
415: def getPresentationInfoXML(self, url):
416: """returns dom of info.xml document at url"""
417: dom = None
418: metaUrl = None
419: if url.startswith("http://"):
420: # real URL
421: metaUrl = url
422: else:
423: # online path
424: server=self.digilibBaseUrl+"/servlet/Texter?fn="
425: metaUrl=server+url.replace("/mpiwg/online","")
426:
1.70 casties 427: txt=getHttpData(metaUrl)
428: if txt is None:
1.20 dwinter 429: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 430:
431: dom = Parse(txt)
1.20 dwinter 432: return dom
1.9 casties 433:
434:
1.33 dwinter 435: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 436: """gets authorization info from the index.meta file at path or given by dom"""
1.70 casties 437: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 438:
439: access = None
440:
441: if docinfo is None:
442: docinfo = {}
443:
444: if dom is None:
1.38 dwinter 445: for x in range(cut):
1.33 dwinter 446: path=getParentDir(path)
447: dom = self.getIndexMeta(path)
1.18 dwinter 448:
1.8 casties 449: acctype = dom.xpath("//access-conditions/access/@type")
450: if acctype and (len(acctype)>0):
451: access=acctype[0].value
1.9 casties 452: if access in ['group', 'institution']:
1.8 casties 453: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
454:
455: docinfo['accessType'] = access
456: return docinfo
1.6 casties 457:
1.8 casties 458:
1.33 dwinter 459: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 460: """gets bibliographical info from the index.meta file at path or given by dom"""
1.27 casties 461: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 462:
1.3 casties 463: if docinfo is None:
464: docinfo = {}
1.38 dwinter 465:
1.3 casties 466: if dom is None:
1.38 dwinter 467: for x in range(cut):
1.33 dwinter 468: path=getParentDir(path)
469: dom = self.getIndexMeta(path)
1.39 dwinter 470:
471: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 472: # put in all raw bib fields as dict "bib"
473: bib = dom.xpath("//bib/*")
474: if bib and len(bib)>0:
475: bibinfo = {}
476: for e in bib:
477: bibinfo[e.localName] = getTextFromNode(e)
478: docinfo['bib'] = bibinfo
479:
480: # extract some fields (author, title, year) according to their mapping
1.4 casties 481: metaData=self.metadata.main.meta.bib
482: bibtype=dom.xpath("//bib/@type")
483: if bibtype and (len(bibtype)>0):
484: bibtype=bibtype[0].value
1.2 dwinter 485: else:
1.4 casties 486: bibtype="generic"
1.27 casties 487:
1.4 casties 488: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 489: docinfo['bib_type'] = bibtype
1.4 casties 490: bibmap=metaData.generateMappingForType(bibtype)
1.8 casties 491: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 492: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 493: try:
494: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
495: except: pass
496: try:
497: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
498: except: pass
499: try:
500: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
501: except: pass
1.27 casties 502: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 503: try:
504: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
505: except:
506: docinfo['lang']=''
1.27 casties 507:
1.3 casties 508: return docinfo
1.42 abukhman 509:
510:
1.43 casties 511: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
512: """parse texttool tag in index meta"""
1.70 casties 513: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 514: if docinfo is None:
515: docinfo = {}
516: if docinfo.get('lang', None) is None:
517: docinfo['lang'] = '' # default keine Sprache gesetzt
518: if dom is None:
519: dom = self.getIndexMeta(url)
520:
521: archivePath = None
522: archiveName = None
523:
524: archiveNames = dom.xpath("//resource/name")
525: if archiveNames and (len(archiveNames) > 0):
526: archiveName = getTextFromNode(archiveNames[0])
527: else:
1.70 casties 528: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 529:
530: archivePaths = dom.xpath("//resource/archive-path")
531: if archivePaths and (len(archivePaths) > 0):
532: archivePath = getTextFromNode(archivePaths[0])
533: # clean up archive path
534: if archivePath[0] != '/':
535: archivePath = '/' + archivePath
536: if archiveName and (not archivePath.endswith(archiveName)):
537: archivePath += "/" + archiveName
538: else:
539: # try to get archive-path from url
1.70 casties 540: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 541: if (not url.startswith('http')):
542: archivePath = url.replace('index.meta', '')
543:
544: if archivePath is None:
545: # we balk without archive-path
546: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
547:
548: imageDirs = dom.xpath("//texttool/image")
549: if imageDirs and (len(imageDirs) > 0):
550: imageDir = getTextFromNode(imageDirs[0])
551:
552: else:
553: # we balk with no image tag / not necessary anymore because textmode is now standard
554: #raise IOError("No text-tool info in %s"%(url))
555: imageDir = ""
556: #xquery="//pb"
557: docinfo['imagePath'] = "" # keine Bilder
558: docinfo['imageURL'] = ""
559:
560: if imageDir and archivePath:
561: #print "image: ", imageDir, " archivepath: ", archivePath
562: imageDir = os.path.join(archivePath, imageDir)
563: imageDir = imageDir.replace("/mpiwg/online", '')
564: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
565: docinfo['imagePath'] = imageDir
566:
567: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
568:
569: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
570: if viewerUrls and (len(viewerUrls) > 0):
571: viewerUrl = getTextFromNode(viewerUrls[0])
572: docinfo['viewerURL'] = viewerUrl
1.70 casties 573:
574: # old style text URL
1.43 casties 575: textUrls = dom.xpath("//texttool/text")
576: if textUrls and (len(textUrls) > 0):
577: textUrl = getTextFromNode(textUrls[0])
578: if urlparse.urlparse(textUrl)[0] == "": #keine url
579: textUrl = os.path.join(archivePath, textUrl)
580: # fix URLs starting with /mpiwg/online
581: if textUrl.startswith("/mpiwg/online"):
582: textUrl = textUrl.replace("/mpiwg/online", '', 1)
583:
584: docinfo['textURL'] = textUrl
585:
1.70 casties 586: # new style text-url-path
1.43 casties 587: textUrls = dom.xpath("//texttool/text-url-path")
588: if textUrls and (len(textUrls) > 0):
589: textUrl = getTextFromNode(textUrls[0])
1.51 casties 590: docinfo['textURLPath'] = textUrl
591: if not docinfo['imagePath']:
592: # text-only, no page images
1.72 casties 593: docinfo = self.getNumPages(docinfo)
1.43 casties 594:
595: presentationUrls = dom.xpath("//texttool/presentation")
596: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
597:
598: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
599: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
600: # durch den relativen Pfad auf die presentation infos
601: presentationPath = getTextFromNode(presentationUrls[0])
602: if url.endswith("index.meta"):
603: presentationUrl = url.replace('index.meta', presentationPath)
604: else:
605: presentationUrl = url + "/" + presentationPath
1.51 casties 606:
1.43 casties 607: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
608:
609: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 610:
1.43 casties 611: return docinfo
1.3 casties 612:
1.20 dwinter 613:
614: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
615: """gets the bibliographical information from the preseantion entry in texttools
616: """
617: dom=self.getPresentationInfoXML(url)
1.29 casties 618: try:
619: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
620: except:
621: pass
622: try:
623: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
624: except:
625: pass
626: try:
627: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
628: except:
629: pass
1.20 dwinter 630: return docinfo
631:
1.33 dwinter 632: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 633: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.70 casties 634: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 635: if docinfo is None:
636: docinfo = {}
1.6 casties 637: path=path.replace("/mpiwg/online","")
1.3 casties 638: docinfo['imagePath'] = path
1.35 dwinter 639: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 640:
1.39 dwinter 641: pathorig=path
1.38 dwinter 642: for x in range(cut):
643: path=getParentDir(path)
1.70 casties 644: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 645: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 646: docinfo['imageURL'] = imageUrl
647:
1.39 dwinter 648: #path ist the path to the images it assumes that the index.meta file is one level higher.
649: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
650: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 651: return docinfo
652:
1.2 dwinter 653:
1.3 casties 654: def getDocinfo(self, mode, url):
655: """returns docinfo depending on mode"""
1.70 casties 656: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 657: # look for cached docinfo in session
1.21 dwinter 658: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 659: docinfo = self.REQUEST.SESSION['docinfo']
660: # check if its still current
661: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.70 casties 662: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 663: return docinfo
664: # new docinfo
665: docinfo = {'mode': mode, 'url': url}
666: if mode=="texttool": #index.meta with texttool information
667: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
668: elif mode=="imagepath":
669: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 670: elif mode=="filepath":
1.37 dwinter 671: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 672: else:
1.70 casties 673: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 674: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 675:
1.70 casties 676: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 677: self.REQUEST.SESSION['docinfo'] = docinfo
678: return docinfo
1.69 abukhman 679:
1.44 casties 680: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
1.3 casties 681: """returns pageinfo with the given parameters"""
682: pageinfo = {}
1.4 casties 683: current = getInt(current)
684: pageinfo['current'] = current
685: rows = int(rows or self.thumbrows)
686: pageinfo['rows'] = rows
687: cols = int(cols or self.thumbcols)
688: pageinfo['cols'] = cols
689: grpsize = cols * rows
690: pageinfo['groupsize'] = grpsize
1.28 casties 691: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
692: # int(current / grpsize) * grpsize +1))
1.3 casties 693: pageinfo['start'] = start
1.4 casties 694: pageinfo['end'] = start + grpsize
1.44 casties 695: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 696: np = int(docinfo['numPages'])
697: pageinfo['end'] = min(pageinfo['end'], np)
698: pageinfo['numgroups'] = int(np / grpsize)
699: if np % grpsize > 0:
1.69 abukhman 700: pageinfo['numgroups'] += 1
1.44 casties 701: pageinfo['viewMode'] = viewMode
702: pageinfo['tocMode'] = tocMode
1.45 abukhman 703: pageinfo['query'] = self.REQUEST.get('query',' ')
704: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
705: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 706: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 707: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 708: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 709: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 710: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 711: toc = int (pageinfo['tocPN'])
712: pageinfo['textPages'] =int (toc)
713:
714: if 'tocSize_%s'%tocMode in docinfo:
715: tocSize = int(docinfo['tocSize_%s'%tocMode])
716: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 717: # cached toc
1.48 abukhman 718: if tocSize%tocPageSize>0:
719: tocPages=tocSize/tocPageSize+1
720: else:
721: tocPages=tocSize/tocPageSize
1.69 abukhman 722: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 723: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 724: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 725: return pageinfo
726:
1.69 abukhman 727: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 728: """init document viewer"""
729: self.title=title
730: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 731: self.thumbrows = thumbrows
732: self.thumbcols = thumbcols
1.8 casties 733: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 734: if RESPONSE is not None:
735: RESPONSE.redirect('manage_main')
1.1 dwinter 736:
737: def manage_AddDocumentViewerForm(self):
738: """add the viewer form"""
1.3 casties 739: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 740: return pt()
741:
1.43 casties 742: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 743: """add the viewer"""
1.43 casties 744: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 745: self._setObject(id,newObj)
746:
747: if RESPONSE is not None:
748: RESPONSE.redirect('manage_main')
1.3 casties 749:
750: ## DocumentViewerTemplate class
751: class DocumentViewerTemplate(ZopePageTemplate):
752: """Template for document viewer"""
753: meta_type="DocumentViewer Template"
754:
755:
756: def manage_addDocumentViewerTemplateForm(self):
757: """Form for adding"""
758: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
759: return pt()
760:
761: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
762: REQUEST=None, submit=None):
763: "Add a Page Template with optional file content."
764:
765: self._setObject(id, DocumentViewerTemplate(id))
766: ob = getattr(self, id)
1.23 dwinter 767: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
768: logging.info("txt %s:"%txt)
769: ob.pt_edit(txt,"text/html")
1.3 casties 770: if title:
771: ob.pt_setTitle(title)
772: try:
773: u = self.DestinationURL()
774: except AttributeError:
775: u = REQUEST['URL1']
776:
777: u = "%s/%s" % (u, urllib.quote(id))
778: REQUEST.RESPONSE.redirect(u+'/manage_main')
779: return ''
780:
781:
1.14 casties 782:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>