version 1.163, 2011/01/06 15:44:18
|
version 1.178, 2012/01/04 07:38:17
|
Line 43 def getTextFromNode(nodename):
|
Line 43 def getTextFromNode(nodename):
|
rc = rc + node.data |
rc = rc + node.data |
return rc |
return rc |
|
|
def serializeNode(node, encoding='utf-8'): |
def serializeNode(node, encoding="utf-8"): |
"""returns a string containing node as XML""" |
"""returns a string containing node as XML""" |
buf = cStringIO.StringIO() |
stream = cStringIO.StringIO() |
Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding) |
#logging.debug("BUF: %s"%(stream)) |
s = buf.getvalue() |
Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) |
buf.close() |
s = stream.getvalue() |
|
#logging.debug("BUF: %s"%(s)) |
|
stream.close() |
return s |
return s |
|
|
def browserCheck(self): |
def browserCheck(self): |
Line 58 def browserCheck(self):
|
Line 60 def browserCheck(self):
|
bt['ua'] = ua |
bt['ua'] = ua |
bt['isIE'] = False |
bt['isIE'] = False |
bt['isN4'] = False |
bt['isN4'] = False |
|
bt['versFirefox']="" |
|
bt['versIE']="" |
|
bt['versSafariChrome']="" |
|
bt['versOpera']="" |
|
|
if string.find(ua, 'MSIE') > -1: |
if string.find(ua, 'MSIE') > -1: |
bt['isIE'] = True |
bt['isIE'] = True |
else: |
else: |
bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) |
bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) |
|
# Safari oder Chrome identification |
|
try: |
|
nav = ua[string.find(ua, '('):] |
|
nav1=ua[string.find(ua,')'):] |
|
nav2=nav1[string.find(nav1,'('):] |
|
nav3=nav2[string.find(nav2,')'):] |
|
ie = string.split(nav, "; ")[1] |
|
ie1 =string.split(nav1, " ")[2] |
|
ie2 =string.split(nav3, " ")[1] |
|
ie3 =string.split(nav3, " ")[2] |
|
if string.find(ie3, "Safari") >-1: |
|
bt['versSafariChrome']=string.split(ie2, "/")[1] |
|
except: pass |
|
# IE identification |
try: |
try: |
nav = ua[string.find(ua, '('):] |
nav = ua[string.find(ua, '('):] |
ie = string.split(nav, "; ")[1] |
ie = string.split(nav, "; ")[1] |
if string.find(ie, "MSIE") > -1: |
if string.find(ie, "MSIE") > -1: |
bt['versIE'] = string.split(ie, " ")[1] |
bt['versIE'] = string.split(ie, " ")[1] |
except: pass |
except: pass |
|
# Firefox identification |
|
try: |
|
nav = ua[string.find(ua, '('):] |
|
nav1=ua[string.find(ua,')'):] |
|
if string.find(ie1, "Firefox") >-1: |
|
nav5= string.split(ie1, "/")[1] |
|
logging.debug("FIREFOX: %s"%(nav5)) |
|
bt['versFirefox']=nav5[0:3] |
|
except:pass |
|
#Opera identification |
|
try: |
|
if string.find(ua,"Opera") >-1: |
|
nav = ua[string.find(ua, '('):] |
|
nav1=nav[string.find(nav,')'):] |
|
bt['versOpera']=string.split(nav1,"/")[2] |
|
except:pass |
|
|
bt['isMac'] = string.find(ua, 'Macintosh') > -1 |
bt['isMac'] = string.find(ua, 'Macintosh') > -1 |
bt['isWin'] = string.find(ua, 'Windows') > -1 |
bt['isWin'] = string.find(ua, 'Windows') > -1 |
Line 127 def getHttpData(url, data=None, num_trie
|
Line 163 def getHttpData(url, data=None, num_trie
|
raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) |
raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) |
#return None |
#return None |
|
|
|
|
|
|
## |
## |
## documentViewer class |
## documentViewer class |
## |
## |
Line 197 class documentViewer(Folder):
|
Line 231 class documentViewer(Folder):
|
"""get page""" |
"""get page""" |
return self.template.fulltextclient.getTextPage(**args) |
return self.template.fulltextclient.getTextPage(**args) |
|
|
|
def getOrigPages(self, **args): |
|
"""get page""" |
|
return self.template.fulltextclient.getOrigPages(**args) |
|
|
|
def getOrigPagesNorm(self, **args): |
|
"""get page""" |
|
return self.template.fulltextclient.getOrigPagesNorm(**args) |
|
|
def getQuery(self, **args): |
def getQuery(self, **args): |
"""get query in search""" |
"""get query in search""" |
return self.template.fulltextclient.getQuery(**args) |
return self.template.fulltextclient.getQuery(**args) |
Line 221 class documentViewer(Folder):
|
Line 263 class documentViewer(Folder):
|
"""get lemma""" |
"""get lemma""" |
return self.template.fulltextclient.getLemma(**args) |
return self.template.fulltextclient.getLemma(**args) |
|
|
|
def getLemmaQuery(self, **args): |
|
"""get query""" |
|
return self.template.fulltextclient.getLemmaQuery(**args) |
|
|
|
def getLex(self, **args): |
|
"""get lex""" |
|
return self.template.fulltextclient.getLex(**args) |
|
|
def getToc(self, **args): |
def getToc(self, **args): |
"""get toc""" |
"""get toc""" |
return self.template.fulltextclient.getToc(**args) |
return self.template.fulltextclient.getToc(**args) |
Line 302 class documentViewer(Folder):
|
Line 352 class documentViewer(Folder):
|
if (docinfo.get('textURLPath',None)): |
if (docinfo.get('textURLPath',None)): |
page = self.getTextPage(docinfo=docinfo, pageinfo=pageinfo) |
page = self.getTextPage(docinfo=docinfo, pageinfo=pageinfo) |
pageinfo['textPage'] = page |
pageinfo['textPage'] = page |
pt = getattr(self.template, 'viewer_main') |
tt = getattr(self, 'template') |
|
pt = getattr(tt, 'viewer_main') |
return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
|
|
def generateMarks(self,mk): |
def generateMarks(self,mk): |
Line 319 class documentViewer(Folder):
|
Line 370 class documentViewer(Folder):
|
def getBrowser(self): |
def getBrowser(self): |
"""getBrowser the version of browser """ |
"""getBrowser the version of browser """ |
bt = browserCheck(self) |
bt = browserCheck(self) |
|
logging.debug("BROWSER VERSION: %s"%(bt)) |
return bt |
return bt |
|
|
def findDigilibUrl(self): |
def findDigilibUrl(self): |
Line 543 class documentViewer(Folder):
|
Line 595 class documentViewer(Folder):
|
|
|
def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
"""gets bibliographical info from the index.meta file at path or given by dom""" |
"""gets bibliographical info from the index.meta file at path or given by dom""" |
logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
#logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
|
|
if docinfo is None: |
if docinfo is None: |
docinfo = {} |
docinfo = {} |
Line 555 class documentViewer(Folder):
|
Line 607 class documentViewer(Folder):
|
|
|
docinfo['indexMetaPath']=self.getIndexMetaPath(path); |
docinfo['indexMetaPath']=self.getIndexMetaPath(path); |
|
|
logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
#logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) |
# put in all raw bib fields as dict "bib" |
# put in all raw bib fields as dict "bib" |
bib = dom.xpath("//bib/*") |
bib = dom.xpath("//bib/*") |
if bib and len(bib)>0: |
if bib and len(bib)>0: |
Line 575 class documentViewer(Folder):
|
Line 627 class documentViewer(Folder):
|
bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
docinfo['bib_type'] = bibtype |
docinfo['bib_type'] = bibtype |
bibmap=metaData.generateMappingForType(bibtype) |
bibmap=metaData.generateMappingForType(bibtype) |
logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap)) |
#logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap)) |
logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype)) |
#logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype)) |
# if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
# if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
try: |
try: |
Line 588 class documentViewer(Folder):
|
Line 640 class documentViewer(Folder):
|
try: |
try: |
docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) |
docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) |
except: pass |
except: pass |
logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
#logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
try: |
try: |
docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) |
docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) |
except: |
except: |
docinfo['lang']='' |
docinfo['lang']='' |
|
try: |
|
docinfo['city']=getTextFromNode(dom.xpath("//bib/city")[0]) |
|
except: |
|
docinfo['city']='' |
|
try: |
|
docinfo['number_of_pages']=getTextFromNode(dom.xpath("//bib/number_of_pages")[0]) |
|
except: |
|
docinfo['number_of_pages']='' |
|
try: |
|
docinfo['series_volume']=getTextFromNode(dom.xpath("//bib/series_volume")[0]) |
|
except: |
|
docinfo['series_volume']='' |
|
try: |
|
docinfo['number_of_volumes']=getTextFromNode(dom.xpath("//bib/number_of_volumes")[0]) |
|
except: |
|
docinfo['number_of_volumes']='' |
|
try: |
|
docinfo['translator']=getTextFromNode(dom.xpath("//bib/translator")[0]) |
|
except: |
|
docinfo['translator']='' |
|
try: |
|
docinfo['edition']=getTextFromNode(dom.xpath("//bib/edition")[0]) |
|
except: |
|
docinfo['edition']='' |
|
try: |
|
docinfo['series_author']=getTextFromNode(dom.xpath("//bib/series_author")[0]) |
|
except: |
|
docinfo['series_author']='' |
|
try: |
|
docinfo['publisher']=getTextFromNode(dom.xpath("//bib/publisher")[0]) |
|
except: |
|
docinfo['publisher']='' |
|
try: |
|
docinfo['series_title']=getTextFromNode(dom.xpath("//bib/series_title")[0]) |
|
except: |
|
docinfo['series_title']='' |
|
try: |
|
docinfo['isbn_issn']=getTextFromNode(dom.xpath("//bib/isbn_issn")[0]) |
|
except: |
|
docinfo['isbn_issn']='' |
|
#logging.debug("I NEED BIBTEX %s"%docinfo) |
return docinfo |
return docinfo |
|
|
|
|
Line 686 class documentViewer(Folder):
|
Line 778 class documentViewer(Folder):
|
|
|
docinfo['textURL'] = textUrl |
docinfo['textURL'] = textUrl |
|
|
|
|
|
#TODO: hack-DW for annalen |
|
if (textUrl is not None) and (textUrl.startswith("/permanent/einstein/annalen")): |
|
textUrl=textUrl.replace("/permanent/einstein/annalen/","/diverse/de/") |
|
splitted=textUrl.split("/fulltext") |
|
textUrl=splitted[0]+".xml" |
|
textUrlkurz = string.split(textUrl, ".")[0] |
|
docinfo['textURLPathkurz'] = textUrlkurz |
|
docinfo['textURLPath'] = textUrl |
|
logging.debug("hack") |
|
logging.debug(textUrl) |
|
|
|
|
# new style text-url-path |
# new style text-url-path |
textUrls = dom.xpath("//texttool/text-url-path") |
textUrls = dom.xpath("//texttool/text-url-path") |
if textUrls and (len(textUrls) > 0): |
if textUrls and (len(textUrls) > 0): |
textUrl = getTextFromNode(textUrls[0]) |
textUrl = getTextFromNode(textUrls[0]) |
docinfo['textURLPath'] = textUrl |
docinfo['textURLPath'] = textUrl |
|
textUrlkurz = string.split(textUrl, ".")[0] |
|
docinfo['textURLPathkurz'] = textUrlkurz |
#if not docinfo['imagePath']: |
#if not docinfo['imagePath']: |
# text-only, no page images |
# text-only, no page images |
#docinfo = self.getNumTextPages(docinfo) |
#docinfo = self.getNumTextPages(docinfo) |
Line 698 class documentViewer(Folder):
|
Line 805 class documentViewer(Folder):
|
|
|
presentationUrls = dom.xpath("//texttool/presentation") |
presentationUrls = dom.xpath("//texttool/presentation") |
docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag |
docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag |
|
#docinfo = self.getDownloadfromDocinfoToBibtex(url, docinfo=docinfo, dom=dom) |
docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) |
docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) |
|
|
|
|
Line 753 class documentViewer(Folder):
|
Line 861 class documentViewer(Folder):
|
|
|
#path ist the path to the images it assumes that the index.meta file is one level higher. |
#path ist the path to the images it assumes that the index.meta file is one level higher. |
docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
|
#docinfo = self.getDownloadfromDocinfoToBibtex(pathorig,docinfo=docinfo,cut=cut+1) |
docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) |
return docinfo |
return docinfo |
|
|
Line 813 class documentViewer(Folder):
|
Line 922 class documentViewer(Folder):
|
pageinfo['viewMode'] = viewMode |
pageinfo['viewMode'] = viewMode |
pageinfo['tocMode'] = tocMode |
pageinfo['tocMode'] = tocMode |
pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','') |
#pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1') |
pageinfo['query'] = self.REQUEST.get('query','') |
pageinfo['query'] = self.REQUEST.get('query','') |
pageinfo['queryType'] = self.REQUEST.get('queryType','') |
pageinfo['queryType'] = self.REQUEST.get('queryType','') |
pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') |
pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') |
pageinfo['textPN'] = self.REQUEST.get('textPN','1') |
pageinfo['textPN'] = self.REQUEST.get('textPN','1') |
pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') |
|
|
|
pageinfo ['highlightElementPos'] = self.REQUEST.get('highlightElementPos','') |
|
pageinfo ['highlightElement'] = self.REQUEST.get('highlightElement','') |
|
|
|
pageinfo ['xpointer'] = self.REQUEST.get('xpointer','') |
|
|
pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10') |
pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10') |
pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
|
|
toc = int (pageinfo['tocPN']) |
toc = int (pageinfo['tocPN']) |
pageinfo['textPages'] =int (toc) |
pageinfo['textPages'] =int (toc) |
|
|
|
|
|
|
if 'tocSize_%s'%tocMode in docinfo: |
if 'tocSize_%s'%tocMode in docinfo: |
tocSize = int(docinfo['tocSize_%s'%tocMode]) |
tocSize = int(docinfo['tocSize_%s'%tocMode]) |
tocPageSize = int(pageinfo['tocPageSize']) |
tocPageSize = int(pageinfo['tocPageSize']) |
Line 838 class documentViewer(Folder):
|
Line 950 class documentViewer(Folder):
|
tocPages=tocSize/tocPageSize |
tocPages=tocSize/tocPageSize |
pageinfo['tocPN'] = min (tocPages,toc) |
pageinfo['tocPN'] = min (tocPages,toc) |
pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
pageinfo['sn'] =self.REQUEST.get('sn','') |
#pageinfo['sn'] =self.REQUEST.get('sn','') |
|
pageinfo['s'] =self.REQUEST.get('s','') |
return pageinfo |
return pageinfo |
|
|
def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |