version 1.170, 2011/03/01 14:53:15
|
version 1.175.2.2, 2011/07/15 09:02:26
|
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 |
|
|
|
getTextFromNode = getText |
|
|
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""" |
stream = cStringIO.StringIO() |
s = ET.tostring(node) |
logging.debug("BUF: %s"%(stream)) |
|
Ft.Xml.Domlette.PrettyPrint(node, stream=stream, encoding=encoding) |
# 4Suite: |
s = stream.getvalue() |
# stream = cStringIO.StringIO() |
logging.debug("BUF: %s"%(s)) |
# Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) |
stream.close() |
# s = stream.getvalue() |
|
# stream.close() |
return s |
return s |
|
|
def browserCheck(self): |
def browserCheck(self): |
Line 231 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 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 255 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 334 class documentViewer(Folder):
|
Line 364 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) |
|
|
if (docinfo.get('textURLPath',None)): |
if (docinfo.get('textURLPath',None)): |
page = self.getTextPage(docinfo=docinfo, pageinfo=pageinfo) |
page = self.getTextPage(mode=viewMode, docinfo=docinfo, pageinfo=pageinfo) |
pageinfo['textPage'] = page |
pageinfo['textPage'] = page |
tt = getattr(self, 'template') |
tt = getattr(self, 'template') |
pt = getattr(tt, 'viewer_main') |
pt = getattr(tt, 'viewer_main') |
Line 469 class documentViewer(Folder):
|
Line 499 class documentViewer(Folder):
|
docinfo = {} |
docinfo = {} |
|
|
for x in range(cut): |
for x in range(cut): |
|
|
path=getParentDir(path) |
path=getParentDir(path) |
|
|
infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
Line 480 class documentViewer(Folder):
|
Line 509 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 530 class documentViewer(Folder):
|
Line 561 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 549 class documentViewer(Folder):
|
Line 581 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 567 class documentViewer(Folder):
|
Line 600 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 593 class documentViewer(Folder):
|
Line 629 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") |
if bib and len(bib)>0: |
#bib = dom.xpath("//bib/*") |
|
if bib is not None: |
bibinfo = {} |
bibinfo = {} |
for e in bib: |
for e in bib: |
bibinfo[e.localName] = getTextFromNode(e) |
bibinfo[e.tag] = getText(e) |
|
|
docinfo['bib'] = bibinfo |
docinfo['bib'] = bibinfo |
|
|
# 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") |
bibtype=bib.get("type") |
if bibtype and (len(bibtype)>0): |
#bibtype=dom.xpath("//bib/@type") |
bibtype=bibtype[0].value |
if not bibtype: |
else: |
|
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 614 class documentViewer(Folder):
|
Line 651 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: |
# ROC: why is this here? |
docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) |
# logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
except: |
# try: |
docinfo['lang']='' |
# docinfo['lang']=getTextFromNode(dom.find(".//bib/lang")[0]) |
try: |
# except: |
docinfo['city']=getTextFromNode(dom.xpath("//bib/city")[0]) |
# docinfo['lang']='' |
except: |
# try: |
docinfo['city']='' |
# docinfo['city']=getTextFromNode(dom.find(".//bib/city")[0]) |
try: |
# except: |
docinfo['number_of_pages']=getTextFromNode(dom.xpath("//bib/number_of_pages")[0]) |
# docinfo['city']='' |
except: |
# try: |
docinfo['number_of_pages']='' |
# docinfo['number_of_pages']=getTextFromNode(dom.find(".//bib/number_of_pages")[0]) |
try: |
# except: |
docinfo['series_volume']=getTextFromNode(dom.xpath("//bib/series_volume")[0]) |
# docinfo['number_of_pages']='' |
except: |
# try: |
docinfo['series_volume']='' |
# docinfo['series_volume']=getTextFromNode(dom.find(".//bib/series_volume")[0]) |
try: |
# except: |
docinfo['number_of_volumes']=getTextFromNode(dom.xpath("//bib/number_of_volumes")[0]) |
# docinfo['series_volume']='' |
except: |
# try: |
docinfo['number_of_volumes']='' |
# docinfo['number_of_volumes']=getTextFromNode(dom.find(".//bib/number_of_volumes")[0]) |
try: |
# except: |
docinfo['translator']=getTextFromNode(dom.xpath("//bib/translator")[0]) |
# docinfo['number_of_volumes']='' |
except: |
# try: |
docinfo['translator']='' |
# docinfo['translator']=getTextFromNode(dom.find(".//bib/translator")[0]) |
try: |
# except: |
docinfo['edition']=getTextFromNode(dom.xpath("//bib/edition")[0]) |
# docinfo['translator']='' |
except: |
# try: |
docinfo['edition']='' |
# docinfo['edition']=getTextFromNode(dom.find(".//bib/edition")[0]) |
try: |
# except: |
docinfo['series_author']=getTextFromNode(dom.xpath("//bib/series_author")[0]) |
# docinfo['edition']='' |
except: |
# try: |
docinfo['series_author']='' |
# docinfo['series_author']=getTextFromNode(dom.find(".//bib/series_author")[0]) |
try: |
# except: |
docinfo['publisher']=getTextFromNode(dom.xpath("//bib/publisher")[0]) |
# docinfo['series_author']='' |
except: |
# try: |
docinfo['publisher']='' |
# docinfo['publisher']=getTextFromNode(dom.find(".//bib/publisher")[0]) |
try: |
# except: |
docinfo['series_title']=getTextFromNode(dom.xpath("//bib/series_title")[0]) |
# docinfo['publisher']='' |
except: |
# try: |
docinfo['series_title']='' |
# docinfo['series_title']=getTextFromNode(dom.find(".//bib/series_title")[0]) |
try: |
# except: |
docinfo['isbn_issn']=getTextFromNode(dom.xpath("//bib/isbn_issn")[0]) |
# docinfo['series_title']='' |
except: |
# try: |
docinfo['isbn_issn']='' |
# docinfo['isbn_issn']=getTextFromNode(dom.find(".//bib/isbn_issn")[0]) |
|
# except: |
|
# docinfo['isbn_issn']='' |
return docinfo |
return docinfo |
|
|
|
|
|
# TODO: is this needed? |
def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
"""gets name info from the index.meta file at path or given by dom""" |
"""gets name info from the index.meta file at path or given by dom""" |
if docinfo is None: |
if docinfo is None: |
Line 682 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 699 class documentViewer(Folder):
|
Line 739 class documentViewer(Folder):
|
archivePath = None |
archivePath = None |
archiveName = None |
archiveName = None |
|
|
archiveNames = dom.xpath("//resource/name") |
archiveName = getText(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 = getText(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 723 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 744 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 762 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 |
textUrlkurz = string.split(textUrl, ".")[0] |
textUrlkurz = string.split(textUrl, ".")[0] |
docinfo['textURLPathkurz'] = textUrlkurz |
docinfo['textURLPathkurz'] = textUrlkurz |
Line 773 class documentViewer(Folder):
|
Line 805 class documentViewer(Folder):
|
#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 |
|
# TODO: is this needed here? |
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 798 class documentViewer(Folder):
|
Line 831 class documentViewer(Folder):
|
"""gets the bibliographical information from the preseantion entry in texttools |
"""gets the bibliographical information from the preseantion entry in texttools |
""" |
""" |
dom=self.getPresentationInfoXML(url) |
dom=self.getPresentationInfoXML(url) |
try: |
docinfo['author']=getText(dom.find(".//author")) |
docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) |
docinfo['title']=getText(dom.find(".//title")) |
except: |
docinfo['year']=getText(dom.find(".//date")) |
pass |
|
try: |
|
docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) |
|
except: |
|
pass |
|
try: |
|
docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) |
|
except: |
|
pass |
|
return docinfo |
return docinfo |
|
|
def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
Line 890 class documentViewer(Folder):
|
Line 914 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') |