|
|
| version 1.162, 2010/12/22 11:54:46 | version 1.175.2.1, 2011/07/14 17:43:56 |
|---|---|
| Line 7 from AccessControl import getSecurityMan | Line 7 from AccessControl import getSecurityMan |
| from Globals import package_home | from Globals import package_home |
| from Products.zogiLib.zogiLib import browserCheck | from Products.zogiLib.zogiLib import browserCheck |
| from Ft.Xml import EMPTY_NAMESPACE, Parse | #from Ft.Xml import EMPTY_NAMESPACE, Parse |
| import Ft.Xml.Domlette | #import Ft.Xml.Domlette |
| import xml.etree.ElementTree as ET | |
| import os.path | import os.path |
| import sys | import sys |
| import urllib | import urllib |
| Line 16 import urllib2 | Line 19 import urllib2 |
| import logging | import logging |
| import math | import math |
| import urlparse | import urlparse |
| import cStringIO | |
| import re | import re |
| import string | import string |
| Line 32 def getInt(number, default=0): | Line 34 def getInt(number, default=0): |
| except: | except: |
| return int(default) | return int(default) |
| def getTextFromNode(nodename): | def getText(node): |
| """get the cdata content of a node""" | """get the cdata content of a node""" |
| if nodename is None: | if node is None: |
| return "" | return "" |
| nodelist=nodename.childNodes | # ET: |
| rc = "" | text = node.text or "" |
| for node in nodelist: | for e in node: |
| if node.nodeType == node.TEXT_NODE: | text += gettext(e) |
| rc = rc + node.data | if e.tail: |
| return rc | text += e.tail |
| # 4Suite: | |
| #nodelist=node.childNodes | |
| #text = "" | |
| #for n in nodelist: | |
| # if n.nodeType == node.TEXT_NODE: | |
| # text = text + n.data | |
| return text | |
| def serializeNode(node, encoding='utf-8'): | getTextFromNode = getText |
| def serializeNode(node, encoding="utf-8"): | |
| """returns a string containing node as XML""" | """returns a string containing node as XML""" |
| buf = cStringIO.StringIO() | s = ET.tostring(node) |
| Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding) | |
| s = buf.getvalue() | # 4Suite: |
| buf.close() | # stream = cStringIO.StringIO() |
| # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) | |
| # s = stream.getvalue() | |
| # stream.close() | |
| return s | return s |
| def browserCheck(self): | def browserCheck(self): |
| Line 58 def browserCheck(self): | Line 74 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 177 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 245 class documentViewer(Folder): |
| """get page""" | """get page""" |
| return self.template.fulltextclient.getTextPage(**args) | return self.template.fulltextclient.getTextPage(**args) |
| def getQuery(self, **args): | def getOrigPages(self, **args): |
| """get query""" | """get page""" |
| return self.template.fulltextclient.getQuery(**args) | return self.template.fulltextclient.getOrigPages(**args) |
| def getQueryResultHits(self, **args): | |
| """get query""" | |
| return self.template.fulltextclient.getQueryResultHits(**args) | |
| def getQueryResultHitsText(self, **args): | def getOrigPagesNorm(self, **args): |
| """get query""" | """get page""" |
| return self.template.fulltextclient.getQueryResultHitsText(**args) | return self.template.fulltextclient.getOrigPagesNorm(**args) |
| def getQueryResultHitsFigures(self, **args): | def getQuery(self, **args): |
| """get query""" | """get query in search""" |
| return self.template.fulltextclient.getQueryResultHitsFigures(**args) | return self.template.fulltextclient.getQuery(**args) |
| def getSearch(self, **args): | def getSearch(self, **args): |
| """get search""" | """get search""" |
| Line 225 class documentViewer(Folder): | Line 269 class documentViewer(Folder): |
| """get all gis places """ | """get all gis places """ |
| return self.template.fulltextclient.getAllGisPlaces(**args) | return self.template.fulltextclient.getAllGisPlaces(**args) |
| def getOrigPages(self, **args): | |
| """get original page number """ | |
| return self.template.fulltextclient.getOrigPages(**args) | |
| def getAllPlaces(self, **args): | |
| """get original page number """ | |
| return self.template.fulltextclient.getAllPlaces(**args) | |
| def getTocEntries(self, **args): | |
| """get original page number """ | |
| return self.template.fulltextclient.getTocEntries(**args) | |
| def getFigureEntries(self, **args): | |
| """get original page number """ | |
| return self.template.fulltextclient.getFigureEntries(**args) | |
| def getNumPages(self, docinfo): | |
| """get numpages""" | |
| return self.template.fulltextclient.getNumPages(docinfo) | |
| def getNumTextPages(self, docinfo): | |
| """get numpages text""" | |
| return self.template.fulltextclient.getNumTextPages(docinfo) | |
| def getTranslate(self, **args): | def getTranslate(self, **args): |
| """get translate""" | """get translate""" |
| return self.template.fulltextclient.getTranslate(**args) | return self.template.fulltextclient.getTranslate(**args) |
| Line 257 class documentViewer(Folder): | Line 277 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 335 class documentViewer(Folder): | Line 363 class documentViewer(Folder): |
| pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) | pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) |
| pt = getattr(self.template, 'viewer_main') | if (docinfo.get('textURLPath',None)): |
| page = self.getTextPage(mode=viewMode, docinfo=docinfo, pageinfo=pageinfo) | |
| pageinfo['textPage'] = page | |
| 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 352 class documentViewer(Folder): | Line 384 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 477 class documentViewer(Folder): | Line 510 class documentViewer(Folder): |
| if txt is None: | if txt is None: |
| raise IOError("Unable to get dir-info from %s"%(infoUrl)) | raise IOError("Unable to get dir-info from %s"%(infoUrl)) |
| dom = Parse(txt) | dom = ET.fromstring(txt) |
| sizes=dom.xpath("//dir/size") | #dom = Parse(txt) |
| logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) | size=getText(dom.find("size")) |
| #sizes=dom.xpath("//dir/size") | |
| logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size) | |
| if sizes: | if size: |
| docinfo['numPages'] = int(getTextFromNode(sizes[0])) | docinfo['numPages'] = int(size) |
| else: | else: |
| docinfo['numPages'] = 0 | docinfo['numPages'] = 0 |
| Line 527 class documentViewer(Folder): | Line 562 class documentViewer(Folder): |
| if txt is None: | if txt is None: |
| raise IOError("Unable to read index meta from %s"%(url)) | raise IOError("Unable to read index meta from %s"%(url)) |
| dom = Parse(txt) | dom = ET.fromstring(txt) |
| #dom = Parse(txt) | |
| return dom | return dom |
| def getPresentationInfoXML(self, url): | def getPresentationInfoXML(self, url): |
| Line 546 class documentViewer(Folder): | Line 582 class documentViewer(Folder): |
| if txt is None: | if txt is None: |
| raise IOError("Unable to read infoXMLfrom %s"%(url)) | raise IOError("Unable to read infoXMLfrom %s"%(url)) |
| dom = Parse(txt) | dom = ET.fromstring(txt) |
| #dom = Parse(txt) | |
| return dom | return dom |
| Line 564 class documentViewer(Folder): | Line 601 class documentViewer(Folder): |
| path=getParentDir(path) | path=getParentDir(path) |
| dom = self.getDomFromIndexMeta(path) | dom = self.getDomFromIndexMeta(path) |
| acctype = dom.xpath("//access-conditions/access/@type") | acc = dom.find(".//access-conditions/access") |
| if acctype and (len(acctype)>0): | if acc is not None: |
| access=acctype[0].value | acctype = acc.get('type') |
| #acctype = dom.xpath("//access-conditions/access/@type") | |
| if acctype: | |
| access=acctype | |
| if access in ['group', 'institution']: | if access in ['group', 'institution']: |
| access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() | access = dom.find(".//access-conditions/access/name").text.lower() |
| docinfo['accessType'] = access | docinfo['accessType'] = access |
| return docinfo | return docinfo |
| Line 590 class documentViewer(Folder): | Line 630 class documentViewer(Folder): |
| 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.find(".//bib/*") |
| #bib = dom.xpath("//bib/*") | |
| if bib and len(bib)>0: | if bib and len(bib)>0: |
| bibinfo = {} | bibinfo = {} |
| for e in bib: | for e in bib: |
| Line 599 class documentViewer(Folder): | Line 640 class documentViewer(Folder): |
| # extract some fields (author, title, year) according to their mapping | # extract some fields (author, title, year) according to their mapping |
| metaData=self.metadata.main.meta.bib | metaData=self.metadata.main.meta.bib |
| bibtype=dom.xpath("//bib/@type") | bib = dom.find(".//bib") |
| if bibtype and (len(bibtype)>0): | bibtype=bib.get("type") |
| bibtype=bibtype[0].value | #bibtype=dom.xpath("//bib/@type") |
| else: | if not bibtype: |
| bibtype="generic" | bibtype="generic" |
| bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) | bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
| Line 611 class documentViewer(Folder): | Line 652 class documentViewer(Folder): |
| 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 or len(bibmap['title'][0]) > 0: |
| try: | try: |
| docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) | docinfo['author']=getText(bib.find(bibmap['author'][0])) |
| except: pass | except: pass |
| try: | try: |
| docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) | docinfo['title']=getText(bib.find(bibmap['title'][0])) |
| except: pass | except: pass |
| try: | try: |
| docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) | docinfo['year']=getText(bib.find(bibmap['year'][0])) |
| except: pass | except: pass |
| logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) | |
| try: | |
| docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
| except: | |
| docinfo['lang']='' | |
| # ROC: why is this here? | |
| # logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) | |
| # try: | |
| # docinfo['lang']=getTextFromNode(dom.find(".//bib/lang")[0]) | |
| # except: | |
| # docinfo['lang']='' | |
| # try: | |
| # docinfo['city']=getTextFromNode(dom.find(".//bib/city")[0]) | |
| # except: | |
| # docinfo['city']='' | |
| # try: | |
| # docinfo['number_of_pages']=getTextFromNode(dom.find(".//bib/number_of_pages")[0]) | |
| # except: | |
| # docinfo['number_of_pages']='' | |
| # try: | |
| # docinfo['series_volume']=getTextFromNode(dom.find(".//bib/series_volume")[0]) | |
| # except: | |
| # docinfo['series_volume']='' | |
| # try: | |
| # docinfo['number_of_volumes']=getTextFromNode(dom.find(".//bib/number_of_volumes")[0]) | |
| # except: | |
| # docinfo['number_of_volumes']='' | |
| # try: | |
| # docinfo['translator']=getTextFromNode(dom.find(".//bib/translator")[0]) | |
| # except: | |
| # docinfo['translator']='' | |
| # try: | |
| # docinfo['edition']=getTextFromNode(dom.find(".//bib/edition")[0]) | |
| # except: | |
| # docinfo['edition']='' | |
| # try: | |
| # docinfo['series_author']=getTextFromNode(dom.find(".//bib/series_author")[0]) | |
| # except: | |
| # docinfo['series_author']='' | |
| # try: | |
| # docinfo['publisher']=getTextFromNode(dom.find(".//bib/publisher")[0]) | |
| # except: | |
| # docinfo['publisher']='' | |
| # try: | |
| # docinfo['series_title']=getTextFromNode(dom.find(".//bib/series_title")[0]) | |
| # except: | |
| # docinfo['series_title']='' | |
| # try: | |
| # docinfo['isbn_issn']=getTextFromNode(dom.find(".//bib/isbn_issn")[0]) | |
| # except: | |
| # docinfo['isbn_issn']='' | |
| return docinfo | return docinfo |
| Line 640 class documentViewer(Folder): | Line 722 class documentViewer(Folder): |
| path=getParentDir(path) | path=getParentDir(path) |
| dom = self.getDomFromIndexMeta(path) | dom = self.getDomFromIndexMeta(path) |
| docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0]) | docinfo['name']=getText(dom.find("name")) |
| logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) | logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) |
| return docinfo | return docinfo |
| Line 657 class documentViewer(Folder): | Line 739 class documentViewer(Folder): |
| archivePath = None | archivePath = None |
| archiveName = None | archiveName = None |
| archiveNames = dom.xpath("//resource/name") | archiveName = getTextFromNode(dom.find("name")) |
| if archiveNames and (len(archiveNames) > 0): | if not archiveName: |
| archiveName = getTextFromNode(archiveNames[0]) | |
| else: | |
| logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) | logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) |
| archivePaths = dom.xpath("//resource/archive-path") | archivePath = getTextFromNode(dom.find("archive-path")) |
| if archivePaths and (len(archivePaths) > 0): | if archivePath: |
| archivePath = getTextFromNode(archivePaths[0]) | |
| # clean up archive path | # clean up archive path |
| if archivePath[0] != '/': | if archivePath[0] != '/': |
| archivePath = '/' + archivePath | archivePath = '/' + archivePath |
| Line 681 class documentViewer(Folder): | Line 760 class documentViewer(Folder): |
| # we balk without archive-path | # we balk without archive-path |
| raise IOError("Missing archive-path (for text-tool) in %s" % (url)) | raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
| imageDirs = dom.xpath("//texttool/image") | imageDir = getText(dom.find(".//texttool/image")) |
| if imageDirs and (len(imageDirs) > 0): | |
| imageDir = getTextFromNode(imageDirs[0]) | |
| else: | if not imageDir: |
| # we balk with no image tag / not necessary anymore because textmode is now standard | # we balk with no image tag / not necessary anymore because textmode is now standard |
| #raise IOError("No text-tool info in %s"%(url)) | #raise IOError("No text-tool info in %s"%(url)) |
| imageDir = "" | imageDir = "" |
| Line 702 class documentViewer(Folder): | Line 779 class documentViewer(Folder): |
| docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir | docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir |
| viewerUrls = dom.xpath("//texttool/digiliburlprefix") | viewerUrl = getText(dom.find(".//texttool/digiliburlprefix")) |
| if viewerUrls and (len(viewerUrls) > 0): | if viewerUrl: |
| viewerUrl = getTextFromNode(viewerUrls[0]) | |
| docinfo['viewerURL'] = viewerUrl | docinfo['viewerURL'] = viewerUrl |
| # old style text URL | # old style text URL |
| textUrls = dom.xpath("//texttool/text") | textUrl = getText(dom.find(".//texttool/text")) |
| if textUrls and (len(textUrls) > 0): | if textUrl: |
| textUrl = getTextFromNode(textUrls[0]) | |
| if urlparse.urlparse(textUrl)[0] == "": #keine url | if urlparse.urlparse(textUrl)[0] == "": #keine url |
| textUrl = os.path.join(archivePath, textUrl) | textUrl = os.path.join(archivePath, textUrl) |
| # fix URLs starting with /mpiwg/online | # fix URLs starting with /mpiwg/online |
| Line 720 class documentViewer(Folder): | Line 795 class documentViewer(Folder): |
| docinfo['textURL'] = textUrl | docinfo['textURL'] = textUrl |
| # new style text-url-path | # new style text-url-path |
| textUrls = dom.xpath("//texttool/text-url-path") | textUrl = getText(dom.find(".//texttool/text-url-path")) |
| if textUrls and (len(textUrls) > 0): | if textUrl: |
| textUrl = getTextFromNode(textUrls[0]) | |
| docinfo['textURLPath'] = textUrl | docinfo['textURLPath'] = textUrl |
| if not docinfo['imagePath']: | textUrlkurz = string.split(textUrl, ".")[0] |
| docinfo['textURLPathkurz'] = textUrlkurz | |
| #if not docinfo['imagePath']: | |
| # text-only, no page images | # text-only, no page images |
| docinfo = self.getNumTextPages(docinfo) | #docinfo = self.getNumTextPages(docinfo) |
| presentationUrls = dom.xpath("//texttool/presentation") | presentationUrl = getText(dom.find(".//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.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) | docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) |
| if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen | if presentationUrl: # ueberschreibe diese durch presentation informationen |
| # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten | # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten |
| # durch den relativen Pfad auf die presentation infos | # durch den relativen Pfad auf die presentation infos |
| presentationPath = getTextFromNode(presentationUrls[0]) | presentationPath = presentationUrl |
| if url.endswith("index.meta"): | if url.endswith("index.meta"): |
| presentationUrl = url.replace('index.meta', presentationPath) | presentationUrl = url.replace('index.meta', presentationPath) |
| else: | else: |
| Line 754 class documentViewer(Folder): | Line 831 class documentViewer(Folder): |
| """ | """ |
| dom=self.getPresentationInfoXML(url) | dom=self.getPresentationInfoXML(url) |
| try: | try: |
| docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) | docinfo['author']=getText(dom.find(".//author")) |
| except: | except: |
| pass | pass |
| try: | try: |
| docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) | docinfo['title']=getText(dom.find(".//title")) |
| except: | except: |
| pass | pass |
| try: | try: |
| docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) | docinfo['year']=getText(dom.find(".//date")) |
| except: | except: |
| pass | pass |
| return docinfo | return docinfo |
| Line 845 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') |
| Line 857 class documentViewer(Folder): | Line 934 class documentViewer(Folder): |
| 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']) |