Annotation of documentViewer/documentViewer.py, revision 1.111
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
1.99 dwinter 19: import re
1.43 casties 20:
1.22 dwinter 21: def logger(txt,method,txt2):
22: """logging"""
23: logging.info(txt+ txt2)
24:
25:
1.4 casties 26: def getInt(number, default=0):
27: """returns always an int (0 in case of problems)"""
28: try:
29: return int(number)
30: except:
1.29 casties 31: return int(default)
1.4 casties 32:
1.1 dwinter 33: def getTextFromNode(nodename):
1.18 dwinter 34: """get the cdata content of a node"""
1.8 casties 35: if nodename is None:
36: return ""
1.1 dwinter 37: nodelist=nodename.childNodes
38: rc = ""
39: for node in nodelist:
40: if node.nodeType == node.TEXT_NODE:
41: rc = rc + node.data
42: return rc
43:
1.43 casties 44: def serializeNode(node, encoding='utf-8'):
45: """returns a string containing node as XML"""
46: buf = cStringIO.StringIO()
1.75 casties 47: Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
1.43 casties 48: s = buf.getvalue()
49: buf.close()
50: return s
51:
1.9 casties 52:
53: def getParentDir(path):
54: """returns pathname shortened by one"""
55: return '/'.join(path.split('/')[0:-1])
56:
57:
1.70 casties 58: def getHttpData(url, data=None, num_tries=3, timeout=10):
59: """returns result from url+data HTTP request"""
60: # we do GET (by appending data to url)
61: if isinstance(data, str) or isinstance(data, unicode):
62: # if data is string then append
63: url = "%s?%s"%(url,data)
64: elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
65: # urlencode
66: url = "%s?%s"%(url,urllib.urlencode(data))
67:
68: response = None
69: errmsg = None
70: for cnt in range(num_tries):
71: try:
1.95 abukhman 72: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
1.70 casties 73: if sys.version_info < (2, 6):
74: # set timeout on socket -- ugly :-(
75: import socket
76: socket.setdefaulttimeout(float(timeout))
77: response = urllib2.urlopen(url)
78: else:
79: response = urllib2.urlopen(url,timeout=float(timeout))
80: # check result?
81: break
82: except urllib2.HTTPError, e:
1.95 abukhman 83: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
1.70 casties 84: errmsg = str(e)
85: # stop trying
86: break
87: except urllib2.URLError, e:
1.95 abukhman 88: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
1.70 casties 89: errmsg = str(e)
90: # stop trying
91: #break
92:
93: if response is not None:
94: data = response.read()
95: response.close()
96: return data
97:
98: raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
99: #return None
1.1 dwinter 100:
101:
102:
1.3 casties 103: ##
104: ## documentViewer class
105: ##
106: class documentViewer(Folder):
1.1 dwinter 107: """document viewer"""
108: meta_type="Document viewer"
109:
110: security=ClassSecurityInfo()
1.3 casties 111: manage_options=Folder.manage_options+(
1.1 dwinter 112: {'label':'main config','action':'changeDocumentViewerForm'},
113: )
114:
1.3 casties 115: # templates and forms
116: viewer_main = PageTemplateFile('zpt/viewer_main', globals())
1.44 casties 117: toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
118: toc_text = PageTemplateFile('zpt/toc_text', globals())
119: toc_figures = PageTemplateFile('zpt/toc_figures', globals())
1.43 casties 120: page_main_images = PageTemplateFile('zpt/page_main_images', globals())
121: page_main_text = PageTemplateFile('zpt/page_main_text', globals())
1.44 casties 122: page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
1.77 abukhman 123: page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
1.48 abukhman 124: page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
1.3 casties 125: head_main = PageTemplateFile('zpt/head_main', globals())
126: docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
1.26 casties 127: info_xml = PageTemplateFile('zpt/info_xml', globals())
1.70 casties 128:
129:
1.32 dwinter 130: thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
1.3 casties 131: security.declareProtected('View management screens','changeDocumentViewerForm')
132: changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
133:
1.1 dwinter 134:
1.45 abukhman 135: def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
1.1 dwinter 136: """init document viewer"""
137: self.id=id
138: self.title=title
1.4 casties 139: self.thumbcols = thumbcols
140: self.thumbrows = thumbrows
1.8 casties 141: # authgroups is list of authorized groups (delimited by ,)
142: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.43 casties 143: # create template folder so we can always use template.something
144:
145: templateFolder = Folder('template')
146: #self['template'] = templateFolder # Zope-2.12 style
147: self._setObject('template',templateFolder) # old style
148: try:
1.70 casties 149: import MpdlXmlTextServer
1.71 casties 150: textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
1.43 casties 151: #templateFolder['fulltextclient'] = xmlRpcClient
1.70 casties 152: templateFolder._setObject('fulltextclient',textServer)
1.43 casties 153: except Exception, e:
1.70 casties 154: logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
1.43 casties 155: try:
156: from Products.zogiLib.zogiLib import zogiLib
157: zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
158: #templateFolder['zogilib'] = zogilib
159: templateFolder._setObject('zogilib',zogilib)
160: except Exception, e:
161: logging.error("Unable to create zogiLib for zogilib: "+str(e))
162:
1.70 casties 163:
164: # proxy text server methods to fulltextclient
165: def getTextPage(self, **args):
166: """get page"""
167: return self.template.fulltextclient.getTextPage(**args)
168:
169: def getQuery(self, **args):
170: """get query"""
171: return self.template.fulltextclient.getQuery(**args)
172:
173: def getSearch(self, **args):
174: """get search"""
175: return self.template.fulltextclient.getSearch(**args)
176:
1.72 casties 177: def getNumPages(self, docinfo):
1.70 casties 178: """get numpages"""
1.72 casties 179: return self.template.fulltextclient.getNumPages(docinfo)
1.100 abukhman 180:
181: def getNumTextPages(self, docinfo):
182: """get numpages text"""
183: return self.template.fulltextclient.getNumTextPages(docinfo)
184:
1.70 casties 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:
1.70 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: '''
1.95 abukhman 211: logging.debug("HHHHHHHHHHHHHH:load the rss")
212: logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.32 dwinter 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
1.70 casties 226: if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.32 dwinter 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')
1.97 abukhman 234: def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""):
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)
1.78 abukhman 241: @param characterNormalization type of text display (reg, norm, none)
1.49 abukhman 242: @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
1.3 casties 243: '''
244:
1.95 abukhman 245: logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
1.1 dwinter 246:
1.3 casties 247: if not hasattr(self, 'template'):
1.43 casties 248: # this won't work
249: logging.error("template folder missing!")
250: return "ERROR: template folder missing!"
1.3 casties 251:
1.43 casties 252: if not getattr(self, 'digilibBaseUrl', None):
1.71 casties 253: self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
1.3 casties 254:
1.4 casties 255: docinfo = self.getDocinfo(mode=mode,url=url)
1.47 abukhman 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
1.71 casties 262: if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
1.68 casties 263: viewMode="text_dict"
1.21 dwinter 264: else:
265: viewMode="images"
1.44 casties 266:
1.97 abukhman 267: pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
1.68 casties 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 ""
1.73 casties 276: if not isinstance(mk, list):
1.71 casties 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
1.74 casties 315: #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
316: ps = urllib.urlencode(params)
1.9 casties 317: url=self.REQUEST['URL1']+"?"+ps
1.4 casties 318: return url
319:
1.32 dwinter 320: def getLinkAmp(self,param=None,val=None):
321: """link to documentviewer with parameter param set to val"""
322: params=self.REQUEST.form.copy()
323: if param is not None:
324: if val is None:
325: if params.has_key(param):
326: del params[param]
327: else:
328: params[param] = str(val)
329:
330: # quote values and assemble into query string
1.95 abukhman 331: logging.debug("XYXXXXX: %s"%repr(params.items()))
1.32 dwinter 332: ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
333: url=self.REQUEST['URL1']+"?"+ps
334: return url
1.40 casties 335:
1.26 casties 336: def getInfo_xml(self,url,mode):
337: """returns info about the document as XML"""
338:
339: if not self.digilibBaseUrl:
340: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
341:
342: docinfo = self.getDocinfo(mode=mode,url=url)
343: pt = getattr(self.template, 'info_xml')
344: return pt(docinfo=docinfo)
345:
1.4 casties 346:
1.9 casties 347: def isAccessible(self, docinfo):
1.8 casties 348: """returns if access to the resource is granted"""
349: access = docinfo.get('accessType', None)
1.95 abukhman 350: logging.debug("documentViewer (accessOK) access type %s"%access)
1.17 casties 351: if access is not None and access == 'free':
1.95 abukhman 352: logging.debug("documentViewer (accessOK) access is free")
1.8 casties 353: return True
1.17 casties 354: elif access is None or access in self.authgroups:
1.9 casties 355: # only local access -- only logged in users
356: user = getSecurityManager().getUser()
1.95 abukhman 357: logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
1.9 casties 358: if user is not None:
359: #print "user: ", user
360: return (user.getUserName() != "Anonymous User")
361: else:
362: return False
1.8 casties 363:
1.95 abukhman 364: logging.error("documentViewer (accessOK) unknown access type %s"%access)
1.8 casties 365: return False
1.9 casties 366:
1.8 casties 367:
1.35 dwinter 368: def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
1.6 casties 369: """gibt param von dlInfo aus"""
1.7 casties 370: if docinfo is None:
371: docinfo = {}
1.35 dwinter 372:
373: for x in range(cut):
1.38 dwinter 374:
1.35 dwinter 375: path=getParentDir(path)
1.38 dwinter 376:
1.13 casties 377: infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
1.6 casties 378:
1.95 abukhman 379: logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
1.6 casties 380:
1.70 casties 381: txt = getHttpData(infoUrl)
382: if txt is None:
1.13 casties 383: raise IOError("Unable to get dir-info from %s"%(infoUrl))
1.70 casties 384:
385: dom = Parse(txt)
1.10 casties 386: sizes=dom.xpath("//dir/size")
1.95 abukhman 387: logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
1.6 casties 388:
1.10 casties 389: if sizes:
390: docinfo['numPages'] = int(getTextFromNode(sizes[0]))
1.7 casties 391: else:
392: docinfo['numPages'] = 0
1.43 casties 393:
394: # TODO: produce and keep list of image names and numbers
1.7 casties 395:
396: return docinfo
1.8 casties 397:
1.99 dwinter 398: def getIndexMetaPath(self,url):
399: """gib nur den Pfad zurueck"""
400: regexp = re.compile(r".*(experimental|permanent)/(.*)")
401: regpath = regexp.match(url)
402: if (regpath==None):
403: return ""
1.110 abukhman 404: logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
1.99 dwinter 405: return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
406:
1.111 ! abukhman 407: def getIndexMetaName(self,url):
! 408: """gib nur den Pfad zurueck"""
! 409: #regexp = re.compile(r".*(experimental|permanent)/(.*)")
! 410: regpath = regexp.match(url)
! 411: if (regpath==None):
! 412: return ""
! 413: logging.debug("(getIndexMetaName): XAXA: %s"%regpath.group(2))
! 414: return regpath
! 415:
! 416:
1.99 dwinter 417: def getIndexMetaUrl(self,url):
418: """returns utr of index.meta document at url"""
419:
1.12 casties 420: metaUrl = None
1.9 casties 421: if url.startswith("http://"):
422: # real URL
1.12 casties 423: metaUrl = url
1.9 casties 424: else:
425: # online path
426: server=self.digilibBaseUrl+"/servlet/Texter?fn="
1.13 casties 427: metaUrl=server+url.replace("/mpiwg/online","")
1.9 casties 428: if not metaUrl.endswith("index.meta"):
429: metaUrl += "/index.meta"
1.99 dwinter 430:
431: return metaUrl
432:
433: def getDomFromIndexMeta(self, url):
434: """get dom from index meta"""
435: dom = None
436: metaUrl = self.getIndexMetaUrl(url)
1.12 casties 437:
1.99 dwinter 438: logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
1.70 casties 439: txt=getHttpData(metaUrl)
440: if txt is None:
1.12 casties 441: raise IOError("Unable to read index meta from %s"%(url))
1.70 casties 442:
443: dom = Parse(txt)
1.9 casties 444: return dom
1.20 dwinter 445:
446: def getPresentationInfoXML(self, url):
447: """returns dom of info.xml document at url"""
448: dom = None
449: metaUrl = None
450: if url.startswith("http://"):
451: # real URL
452: metaUrl = url
453: else:
454: # online path
455: server=self.digilibBaseUrl+"/servlet/Texter?fn="
456: metaUrl=server+url.replace("/mpiwg/online","")
457:
1.70 casties 458: txt=getHttpData(metaUrl)
459: if txt is None:
1.20 dwinter 460: raise IOError("Unable to read infoXMLfrom %s"%(url))
1.70 casties 461:
462: dom = Parse(txt)
1.20 dwinter 463: return dom
1.9 casties 464:
465:
1.33 dwinter 466: def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 467: """gets authorization info from the index.meta file at path or given by dom"""
1.95 abukhman 468: logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
1.8 casties 469:
470: access = None
471:
472: if docinfo is None:
473: docinfo = {}
474:
475: if dom is None:
1.38 dwinter 476: for x in range(cut):
1.33 dwinter 477: path=getParentDir(path)
1.99 dwinter 478: dom = self.getDomFromIndexMeta(path)
1.18 dwinter 479:
1.8 casties 480: acctype = dom.xpath("//access-conditions/access/@type")
481: if acctype and (len(acctype)>0):
482: access=acctype[0].value
1.9 casties 483: if access in ['group', 'institution']:
1.8 casties 484: access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
485:
486: docinfo['accessType'] = access
487: return docinfo
1.6 casties 488:
1.8 casties 489:
1.33 dwinter 490: def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
1.9 casties 491: """gets bibliographical info from the index.meta file at path or given by dom"""
1.95 abukhman 492: logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
1.2 dwinter 493:
1.3 casties 494: if docinfo is None:
495: docinfo = {}
1.38 dwinter 496:
1.3 casties 497: if dom is None:
1.38 dwinter 498: for x in range(cut):
1.33 dwinter 499: path=getParentDir(path)
1.99 dwinter 500: dom = self.getDomFromIndexMeta(path)
501:
502: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
1.39 dwinter 503:
1.95 abukhman 504: logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
1.27 casties 505: # put in all raw bib fields as dict "bib"
506: bib = dom.xpath("//bib/*")
507: if bib and len(bib)>0:
508: bibinfo = {}
509: for e in bib:
510: bibinfo[e.localName] = getTextFromNode(e)
511: docinfo['bib'] = bibinfo
512:
513: # extract some fields (author, title, year) according to their mapping
1.4 casties 514: metaData=self.metadata.main.meta.bib
515: bibtype=dom.xpath("//bib/@type")
516: if bibtype and (len(bibtype)>0):
517: bibtype=bibtype[0].value
1.2 dwinter 518: else:
1.4 casties 519: bibtype="generic"
1.27 casties 520:
1.4 casties 521: bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
1.27 casties 522: docinfo['bib_type'] = bibtype
1.4 casties 523: bibmap=metaData.generateMappingForType(bibtype)
1.99 dwinter 524: logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
525: logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
1.8 casties 526: # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
1.7 casties 527: if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
1.30 casties 528: try:
529: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
530: except: pass
531: try:
532: docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
533: except: pass
534: try:
535: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
536: except: pass
1.95 abukhman 537: logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
1.22 dwinter 538: try:
539: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
540: except:
541: docinfo['lang']=''
1.27 casties 542:
1.3 casties 543: return docinfo
1.42 abukhman 544:
1.104 abukhman 545:
546: def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
547: """gets name info from the index.meta file at path or given by dom"""
548: if docinfo is None:
549: docinfo = {}
550:
551: if dom is None:
552: for x in range(cut):
553: path=getParentDir(path)
554: dom = self.getDomFromIndexMeta(path)
555:
556: docinfo['indexMetaPath']=self.getIndexMetaPath(path);
557:
1.105 abukhman 558: #result= dom.xpath("//result/resultPage")
559: #docinfo['numPages']=int(getTextFromNode(result[0]))
1.104 abukhman 560:
1.105 abukhman 561: if len(name) > 0:
1.104 abukhman 562: try:
1.105 abukhman 563: result =dom.xpath("//name")
564: docinfo['name']=getTextFromNode(result[0])
565: logging.debug("documentViewer docinfo[name] %s"%docinfo[name])
1.104 abukhman 566: except: pass
567: #logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
568: return docinfo
1.42 abukhman 569:
1.43 casties 570: def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
571: """parse texttool tag in index meta"""
1.95 abukhman 572: logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
1.43 casties 573: if docinfo is None:
574: docinfo = {}
575: if docinfo.get('lang', None) is None:
576: docinfo['lang'] = '' # default keine Sprache gesetzt
577: if dom is None:
1.99 dwinter 578: dom = self.getDomFromIndexMeta(url)
1.43 casties 579:
580: archivePath = None
581: archiveName = None
582:
583: archiveNames = dom.xpath("//resource/name")
584: if archiveNames and (len(archiveNames) > 0):
585: archiveName = getTextFromNode(archiveNames[0])
586: else:
1.70 casties 587: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
1.43 casties 588:
589: archivePaths = dom.xpath("//resource/archive-path")
590: if archivePaths and (len(archivePaths) > 0):
591: archivePath = getTextFromNode(archivePaths[0])
592: # clean up archive path
593: if archivePath[0] != '/':
594: archivePath = '/' + archivePath
595: if archiveName and (not archivePath.endswith(archiveName)):
596: archivePath += "/" + archiveName
597: else:
598: # try to get archive-path from url
1.95 abukhman 599: logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
1.43 casties 600: if (not url.startswith('http')):
601: archivePath = url.replace('index.meta', '')
602:
603: if archivePath is None:
604: # we balk without archive-path
605: raise IOError("Missing archive-path (for text-tool) in %s" % (url))
606:
607: imageDirs = dom.xpath("//texttool/image")
608: if imageDirs and (len(imageDirs) > 0):
609: imageDir = getTextFromNode(imageDirs[0])
610:
611: else:
612: # we balk with no image tag / not necessary anymore because textmode is now standard
613: #raise IOError("No text-tool info in %s"%(url))
614: imageDir = ""
615: #xquery="//pb"
616: docinfo['imagePath'] = "" # keine Bilder
617: docinfo['imageURL'] = ""
618:
619: if imageDir and archivePath:
620: #print "image: ", imageDir, " archivepath: ", archivePath
621: imageDir = os.path.join(archivePath, imageDir)
622: imageDir = imageDir.replace("/mpiwg/online", '')
623: docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
624: docinfo['imagePath'] = imageDir
625:
626: docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
627:
628: viewerUrls = dom.xpath("//texttool/digiliburlprefix")
629: if viewerUrls and (len(viewerUrls) > 0):
630: viewerUrl = getTextFromNode(viewerUrls[0])
631: docinfo['viewerURL'] = viewerUrl
1.70 casties 632:
633: # old style text URL
1.43 casties 634: textUrls = dom.xpath("//texttool/text")
635: if textUrls and (len(textUrls) > 0):
636: textUrl = getTextFromNode(textUrls[0])
637: if urlparse.urlparse(textUrl)[0] == "": #keine url
638: textUrl = os.path.join(archivePath, textUrl)
639: # fix URLs starting with /mpiwg/online
640: if textUrl.startswith("/mpiwg/online"):
641: textUrl = textUrl.replace("/mpiwg/online", '', 1)
642:
643: docinfo['textURL'] = textUrl
644:
1.70 casties 645: # new style text-url-path
1.43 casties 646: textUrls = dom.xpath("//texttool/text-url-path")
647: if textUrls and (len(textUrls) > 0):
648: textUrl = getTextFromNode(textUrls[0])
1.51 casties 649: docinfo['textURLPath'] = textUrl
650: if not docinfo['imagePath']:
651: # text-only, no page images
1.103 abukhman 652: docinfo = self.getNumTextPages(docinfo)
1.43 casties 653:
654: presentationUrls = dom.xpath("//texttool/presentation")
655: docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag
1.107 abukhman 656: #docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
1.43 casties 657:
658: if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen
659: # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
660: # durch den relativen Pfad auf die presentation infos
661: presentationPath = getTextFromNode(presentationUrls[0])
662: if url.endswith("index.meta"):
663: presentationUrl = url.replace('index.meta', presentationPath)
664: else:
665: presentationUrl = url + "/" + presentationPath
1.51 casties 666:
1.43 casties 667: docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
668:
669: docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info
1.3 casties 670:
1.43 casties 671: return docinfo
1.3 casties 672:
1.20 dwinter 673:
674: def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
675: """gets the bibliographical information from the preseantion entry in texttools
676: """
677: dom=self.getPresentationInfoXML(url)
1.29 casties 678: try:
679: docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
680: except:
681: pass
682: try:
683: docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
684: except:
685: pass
686: try:
687: docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
688: except:
689: pass
1.20 dwinter 690: return docinfo
691:
1.33 dwinter 692: def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
1.3 casties 693: """path ist the path to the images it assumes that the index.meta file is one level higher."""
1.95 abukhman 694: logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
1.3 casties 695: if docinfo is None:
696: docinfo = {}
1.6 casties 697: path=path.replace("/mpiwg/online","")
1.3 casties 698: docinfo['imagePath'] = path
1.35 dwinter 699: docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
1.38 dwinter 700:
1.39 dwinter 701: pathorig=path
1.38 dwinter 702: for x in range(cut):
703: path=getParentDir(path)
1.95 abukhman 704: logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
1.7 casties 705: imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
1.3 casties 706: docinfo['imageURL'] = imageUrl
707:
1.39 dwinter 708: #path ist the path to the images it assumes that the index.meta file is one level higher.
709: docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
710: docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
1.3 casties 711: return docinfo
712:
1.2 dwinter 713:
1.3 casties 714: def getDocinfo(self, mode, url):
715: """returns docinfo depending on mode"""
1.95 abukhman 716: logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
1.3 casties 717: # look for cached docinfo in session
1.21 dwinter 718: if self.REQUEST.SESSION.has_key('docinfo'):
1.3 casties 719: docinfo = self.REQUEST.SESSION['docinfo']
720: # check if its still current
721: if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
1.95 abukhman 722: logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
1.3 casties 723: return docinfo
724: # new docinfo
725: docinfo = {'mode': mode, 'url': url}
726: if mode=="texttool": #index.meta with texttool information
727: docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
728: elif mode=="imagepath":
729: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
1.33 dwinter 730: elif mode=="filepath":
1.37 dwinter 731: docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
1.3 casties 732: else:
1.95 abukhman 733: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
1.44 casties 734: raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
1.10 casties 735:
1.95 abukhman 736: logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
1.3 casties 737: self.REQUEST.SESSION['docinfo'] = docinfo
738: return docinfo
1.69 abukhman 739:
1.97 abukhman 740: def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
1.3 casties 741: """returns pageinfo with the given parameters"""
742: pageinfo = {}
1.4 casties 743: current = getInt(current)
744: pageinfo['current'] = current
745: rows = int(rows or self.thumbrows)
746: pageinfo['rows'] = rows
747: cols = int(cols or self.thumbcols)
748: pageinfo['cols'] = cols
749: grpsize = cols * rows
750: pageinfo['groupsize'] = grpsize
1.28 casties 751: start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
752: # int(current / grpsize) * grpsize +1))
1.3 casties 753: pageinfo['start'] = start
1.4 casties 754: pageinfo['end'] = start + grpsize
1.44 casties 755: if (docinfo is not None) and ('numPages' in docinfo):
1.4 casties 756: np = int(docinfo['numPages'])
757: pageinfo['end'] = min(pageinfo['end'], np)
758: pageinfo['numgroups'] = int(np / grpsize)
759: if np % grpsize > 0:
1.69 abukhman 760: pageinfo['numgroups'] += 1
1.44 casties 761: pageinfo['viewMode'] = viewMode
762: pageinfo['tocMode'] = tocMode
1.98 abukhman 763: #pageinfo['characterNormalization'] =characterNormalization
764: pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')
1.45 abukhman 765: pageinfo['query'] = self.REQUEST.get('query',' ')
766: pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
767: pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
1.48 abukhman 768: pageinfo['textPN'] = self.REQUEST.get('textPN','1')
1.55 abukhman 769: pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
1.45 abukhman 770: pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
1.54 abukhman 771: pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
1.44 casties 772: pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
1.48 abukhman 773: toc = int (pageinfo['tocPN'])
774: pageinfo['textPages'] =int (toc)
1.90 abukhman 775:
1.48 abukhman 776: if 'tocSize_%s'%tocMode in docinfo:
777: tocSize = int(docinfo['tocSize_%s'%tocMode])
778: tocPageSize = int(pageinfo['tocPageSize'])
1.69 abukhman 779: # cached toc
1.48 abukhman 780: if tocSize%tocPageSize>0:
781: tocPages=tocSize/tocPageSize+1
782: else:
783: tocPages=tocSize/tocPageSize
1.69 abukhman 784: pageinfo['tocPN'] = min (tocPages,toc)
1.45 abukhman 785: pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
1.59 abukhman 786: pageinfo['sn'] =self.REQUEST.get('sn','')
1.3 casties 787: return pageinfo
788:
1.69 abukhman 789: def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
1.3 casties 790: """init document viewer"""
791: self.title=title
792: self.digilibBaseUrl = digilibBaseUrl
1.4 casties 793: self.thumbrows = thumbrows
794: self.thumbcols = thumbcols
1.8 casties 795: self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
1.3 casties 796: if RESPONSE is not None:
797: RESPONSE.redirect('manage_main')
1.1 dwinter 798:
799: def manage_AddDocumentViewerForm(self):
800: """add the viewer form"""
1.3 casties 801: pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
1.1 dwinter 802: return pt()
803:
1.43 casties 804: def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
1.1 dwinter 805: """add the viewer"""
1.43 casties 806: newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
1.1 dwinter 807: self._setObject(id,newObj)
808:
809: if RESPONSE is not None:
810: RESPONSE.redirect('manage_main')
1.3 casties 811:
812: ## DocumentViewerTemplate class
813: class DocumentViewerTemplate(ZopePageTemplate):
814: """Template for document viewer"""
815: meta_type="DocumentViewer Template"
816:
817:
818: def manage_addDocumentViewerTemplateForm(self):
819: """Form for adding"""
820: pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
821: return pt()
822:
823: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
824: REQUEST=None, submit=None):
825: "Add a Page Template with optional file content."
826:
827: self._setObject(id, DocumentViewerTemplate(id))
828: ob = getattr(self, id)
1.23 dwinter 829: txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
1.95 abukhman 830: logging.info("txt %s:"%txt)
1.23 dwinter 831: ob.pt_edit(txt,"text/html")
1.3 casties 832: if title:
833: ob.pt_setTitle(title)
834: try:
835: u = self.DestinationURL()
836: except AttributeError:
837: u = REQUEST['URL1']
838:
839: u = "%s/%s" % (u, urllib.quote(id))
840: REQUEST.RESPONSE.redirect(u+'/manage_main')
841: return ''
842:
843:
1.14 casties 844:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>