documentViewer/documentViewer.py - diff

Return to documentViewer.py CVS log

Up to [Repository] / documentViewer

Diff for /documentViewer/documentViewer.py between versions 1.69.2.3 and 1.175.2.9

version 1.69.2.3, 2010/06/16 18:27:04	version 1.175.2.9, 2011/07/27 19:09:44
Line 1	Line 1

from OFS.Folder import Folder	from OFS.Folder import Folder
from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate	from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
from Products.PageTemplates.PageTemplateFile import PageTemplateFile	from Products.PageTemplates.PageTemplateFile import PageTemplateFile
from Products.PythonScripts.standard import url_quote
from AccessControl import ClassSecurityInfo	from AccessControl import ClassSecurityInfo
from AccessControl import getSecurityManager	from AccessControl import getSecurityManager
from Globals import package_home	from Globals import package_home

from Ft.Xml.Domlette import NonvalidatingReader	#from Ft.Xml import EMPTY_NAMESPACE, Parse
from Ft.Xml.Domlette import PrettyPrint, Print	#import Ft.Xml.Domlette
from Ft.Xml import EMPTY_NAMESPACE, Parse

from xml.dom.minidom import parse, parseString

from extraFunction import *

	import xml.etree.ElementTree as ET

import Ft.Xml.XPath
import cStringIO
import xmlrpclib
import os.path	import os.path
import sys	import sys
import cgi
import urllib	import urllib
import logging	import logging
import math	import math

import urlparse	import urlparse
from types import *	import re
	import string

	from SrvTxtUtils import getInt, getText, getHttpData

def logger(txt,method,txt2):	def logger(txt,method,txt2):
"""logging"""	"""logging"""
logging.info(txt+ txt2)	logging.info(txt+ txt2)


def getInt(number, default=0):	def serializeNode(node, encoding="utf-8"):
"""returns always an int (0 in case of problems)"""
try:
return int(number)
except:
return int(default)

def getTextFromNode(nodename):
"""get the cdata content of a node"""
if nodename is None:
return ""
nodelist=nodename.childNodes
rc = ""
for node in nodelist:
if node.nodeType == node.TEXT_NODE:
rc = rc + node.data
return rc

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)
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):
	"""check the browsers request to find out the browser type"""
	bt = {}
	ua = self.REQUEST.get_header("HTTP_USER_AGENT")
	bt['ua'] = ua
	bt['isIE'] = False
	bt['isN4'] = False
	bt['versFirefox']=""
	bt['versIE']=""
	bt['versSafariChrome']=""
	bt['versOpera']=""

	if string.find(ua, 'MSIE') > -1:
	bt['isIE'] = True
	else:
	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:
	nav = ua[string.find(ua, '('):]
	ie = string.split(nav, "; ")[1]
	if string.find(ie, "MSIE") > -1:
	bt['versIE'] = string.split(ie, " ")[1]
	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['isWin'] = string.find(ua, 'Windows') > -1
	bt['isIEWin'] = bt['isIE'] and bt['isWin']
	bt['isIEMac'] = bt['isIE'] and bt['isMac']
	bt['staticHTML'] = False

	return bt

def getParentDir(path):	def getParentDir(path):
"""returns pathname shortened by one"""	"""returns pathname shortened by one"""
return '/'.join(path.split('/')[0:-1])	return '/'.join(path.split('/')[0:-1])

	def normalizeBibField(bt, underscore=True):
	"""returns normalised bib type for looking up mappings"""
	bt = bt.strip().replace(' ', '-').lower()
	if underscore:
	bt = bt.replace('_', '-')

def getHttpData(url, data=None, num_tries=3, timeout=10):	return bt
"""returns result from url+data HTTP request"""
# we do GET (by appending data to url)
if isinstance(data, str) or isinstance(data, unicode):
# if data is string then append
url = "%s?%s"%(url,data)
elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
# urlencode
url = "%s?%s"%(url,urllib.urlencode(data))

response = None
errmsg = None
for cnt in range(num_tries):
try:
logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
if sys.version_info < (2, 6):
# set timeout on socket -- ugly :-(
import socket
socket.setdefaulttimeout(timeout)
response = urllib2.urlopen(url)
else:
response = urllib2.urlopen(url,timeout=float(timeout))
# check result?
break
except urllib2.HTTPError, e:
logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
errmsg = str(e)
# stop trying
break
except urllib2.URLError, e:
logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
errmsg = str(e)
# stop trying
#break

if response is not None:
data = response.read()
response.close()
return data

raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))	def getBibdataFromDom(dom):
#return None	"""returns dict with all elements from bib-tag"""
	bibinfo = {}
	bib = dom.find(".//meta/bib")
	if bib is not None:
	# put type in @type
	type = bib.get('type')
	bibinfo['@type'] = normalizeBibField(type)
	# put all subelements in dict
	for e in bib:
	bibinfo[normalizeBibField(e.tag)] = getText(e)

	return bibinfo


##	##
Line 129 class documentViewer(Folder):	Line 143 class documentViewer(Folder):
toc_text = PageTemplateFile('zpt/toc_text', globals())	toc_text = PageTemplateFile('zpt/toc_text', globals())
toc_figures = PageTemplateFile('zpt/toc_figures', globals())	toc_figures = PageTemplateFile('zpt/toc_figures', globals())
page_main_images = PageTemplateFile('zpt/page_main_images', globals())	page_main_images = PageTemplateFile('zpt/page_main_images', globals())
	page_main_double = PageTemplateFile('zpt/page_main_double', globals())
page_main_text = PageTemplateFile('zpt/page_main_text', globals())	page_main_text = PageTemplateFile('zpt/page_main_text', globals())
page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())	page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
	page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())	page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
	page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
head_main = PageTemplateFile('zpt/head_main', globals())	head_main = PageTemplateFile('zpt/head_main', globals())
docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())	docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
info_xml = PageTemplateFile('zpt/info_xml', globals())	info_xml = PageTemplateFile('zpt/info_xml', globals())
Line 157 class documentViewer(Folder):	Line 174 class documentViewer(Folder):
self._setObject('template',templateFolder) # old style	self._setObject('template',templateFolder) # old style
try:	try:
import MpdlXmlTextServer	import MpdlXmlTextServer
textServer = MpdlXmlTextServer(id='fulltextclient')	textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
#templateFolder['fulltextclient'] = xmlRpcClient	#templateFolder['fulltextclient'] = xmlRpcClient
templateFolder._setObject('fulltextclient',textServer)	templateFolder._setObject('fulltextclient',textServer)
except Exception, e:	except Exception, e:
Line 176 class documentViewer(Folder):	Line 193 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"""	"""get query in search"""
return self.template.fulltextclient.getQuery(**args)	return self.template.fulltextclient.getQuery(**args)

def getSearch(self, **args):	def getSearch(self, **args):
"""get search"""	"""get search"""
return self.template.fulltextclient.getSearch(**args)	return self.template.fulltextclient.getSearch(**args)

def getNumPages(self, **args):	def getGisPlaces(self, **args):
"""get numpages"""	"""get gis places"""
return self.template.fulltextclient.getNumPages(**args)	return self.template.fulltextclient.getGisPlaces(**args)

	def getAllGisPlaces(self, **args):
	"""get all gis places """
	return self.template.fulltextclient.getAllGisPlaces(**args)

def getTranslate(self, **args):	def getTranslate(self, **args):
"""get translate"""	"""get translate"""
Line 196 class documentViewer(Folder):	Line 225 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 215 class documentViewer(Folder):	Line 252 class documentViewer(Folder):

'''	'''
logging.debug("HHHHHHHHHHHHHH:load the rss")	logging.debug("HHHHHHHHHHHHHH:load the rss")
logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))	logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))

if not hasattr(self, 'template'):	if not hasattr(self, 'template'):
# create template folder if it doesn't exist	# create template folder if it doesn't exist
Line 225 class documentViewer(Folder):	Line 262 class documentViewer(Folder):
self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"	self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"

docinfo = self.getDocinfo(mode=mode,url=url)	docinfo = self.getDocinfo(mode=mode,url=url)
	#pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)	pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
	''' ZDES '''
pt = getattr(self.template, 'thumbs_main_rss')	pt = getattr(self.template, 'thumbs_main_rss')

if viewMode=="auto": # automodus gewaehlt	if viewMode=="auto": # automodus gewaehlt
if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert	if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
viewMode="text"	viewMode="text"
else:	else:
viewMode="images"	viewMode="images"
Line 237 class documentViewer(Folder):	Line 276 class documentViewer(Folder):
return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)	return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)

security.declareProtected('View','index_html')	security.declareProtected('View','index_html')
def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):	def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
'''	'''
view it	view it
@param mode: defines how to access the document behind url	@param mode: defines how to access the document behind url
@param url: url which contains display information	@param url: url which contains display information
@param viewMode: if images display images, if text display text, default is auto (text,images or auto)	@param viewMode: if images display images, if text display text, default is auto (text,images or auto)
@param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)	@param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
	@param characterNormalization type of text display (reg, norm, none)
@param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)	@param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
'''	'''

Line 255 class documentViewer(Folder):	Line 295 class documentViewer(Folder):
return "ERROR: template folder missing!"	return "ERROR: template folder missing!"

if not getattr(self, 'digilibBaseUrl', None):	if not getattr(self, 'digilibBaseUrl', None):
self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"	self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"

docinfo = self.getDocinfo(mode=mode,url=url)	docinfo = self.getDocinfo(mode=mode,url=url)


if tocMode != "thumbs":	if tocMode != "thumbs":
# get table of contents	# get table of contents
docinfo = self.getToc(mode=tocMode, docinfo=docinfo)	docinfo = self.getToc(mode=tocMode, docinfo=docinfo)

if viewMode=="auto": # automodus gewaehlt	# auto viewMode: text_dict if text else images
if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert	if viewMode=="auto":
	if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):
	#texturl gesetzt und textViewer konfiguriert
viewMode="text_dict"	viewMode="text_dict"
else:	else:
viewMode="images"	viewMode="images"

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 viewMode != 'images' and docinfo.get('textURLPath', None):
	# get full text page
	page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo)
	pageinfo['textPage'] = page

	# get template /template/viewer_main
pt = getattr(self.template, 'viewer_main')	pt = getattr(self.template, 'viewer_main')
	# and execute with parameters
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):
ret=""	ret=""
if mk is None:	if mk is None:
return ""	return ""
if type(mk) is not ListType:	if not isinstance(mk, list):
mk=[mk]	mk=[mk]
for m in mk:	for m in mk:
ret+="mk=%s"%m	ret+="mk=%s"%m
return ret	return ret


	def getBrowser(self):
	"""getBrowser the version of browser """
	bt = browserCheck(self)
	logging.debug("BROWSER VERSION: %s"%(bt))
	return bt

def findDigilibUrl(self):	def findDigilibUrl(self):
"""try to get the digilib URL from zogilib"""	"""try to get the digilib URL from zogilib"""
url = self.template.zogilib.getDLBaseUrl()	url = self.template.zogilib.getDLBaseUrl()
Line 303 class documentViewer(Folder):	Line 357 class documentViewer(Folder):
else:	else:
return style	return style

def getLink(self,param=None,val=None):	def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
"""link to documentviewer with parameter param set to val"""	"""returns URL to documentviewer with parameter param set to val or from dict params"""
params=self.REQUEST.form.copy()	# copy existing request params
	urlParams=self.REQUEST.form.copy()
	# change single param
if param is not None:	if param is not None:
if val is None:	if val is None:
if params.has_key(param):	if urlParams.has_key(param):
del params[param]	del urlParams[param]
else:	else:
params[param] = str(val)	urlParams[param] = str(val)

if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath	# change more params
params["mode"] = "imagepath"	if params is not None:
params["url"] = getParentDir(params["url"])	for k in params.keys():
	v = params[k]
# quote values and assemble into query string	if v is None:
ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])	# val=None removes param
url=self.REQUEST['URL1']+"?"+ps	if urlParams.has_key(k):
	del urlParams[k]

	else:
	urlParams[k] = v

	# FIXME: does this belong here?
	if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
	urlParams["mode"] = "imagepath"
	urlParams["url"] = getParentDir(urlParams["url"])

	# quote values and assemble into query string (not escaping '/')
	ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
	#ps = urllib.urlencode(urlParams)
	if baseUrl is None:
	baseUrl = self.REQUEST['URL1']

	url = "%s?%s"%(baseUrl, ps)
return url	return url

def getLinkAmp(self,param=None,val=None):
"""link to documentviewer with parameter param set to val"""
params=self.REQUEST.form.copy()
if param is not None:
if val is None:
if params.has_key(param):
del params[param]
else:
params[param] = str(val)

# quote values and assemble into query string	def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
logging.debug("XYXXXXX: %s"%repr(params.items()))	"""link to documentviewer with parameter param set to val"""
ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])	return self.getLink(param, val, params, baseUrl, '&')
url=self.REQUEST['URL1']+"?"+ps
return url

def getInfo_xml(self,url,mode):	def getInfo_xml(self,url,mode):
"""returns info about the document as XML"""	"""returns info about the document as XML"""
Line 348 class documentViewer(Folder):	Line 410 class documentViewer(Folder):
pt = getattr(self.template, 'info_xml')	pt = getattr(self.template, 'info_xml')
return pt(docinfo=docinfo)	return pt(docinfo=docinfo)

	def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
	"""returns new option state"""
	if not self.REQUEST.SESSION.has_key(optionName):
	# not in session -- initial
	opt = {'lastState': newState, 'state': initialState}
	else:
	opt = self.REQUEST.SESSION.get(optionName)
	if opt['lastState'] != newState:
	# state in session has changed -- toggle
	opt['state'] = not opt['state']
	opt['lastState'] = newState

	self.REQUEST.SESSION[optionName] = opt
	return opt['state']

def isAccessible(self, docinfo):	def isAccessible(self, docinfo):
"""returns if access to the resource is granted"""	"""returns if access to the resource is granted"""
Line 359 class documentViewer(Folder):	Line 435 class documentViewer(Folder):
elif access is None or access in self.authgroups:	elif access is None or access in self.authgroups:
# only local access -- only logged in users	# only local access -- only logged in users
user = getSecurityManager().getUser()	user = getSecurityManager().getUser()
	logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
if user is not None:	if user is not None:
#print "user: ", user	#print "user: ", user
return (user.getUserName() != "Anonymous User")	return (user.getUserName() != "Anonymous User")
else:	else:
return False	return False

logging.debug("documentViewer (accessOK) unknown access type %s"%access)	logging.error("documentViewer (accessOK) unknown access type %s"%access)
return False	return False


Line 375 class documentViewer(Folder):	Line 452 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 386 class documentViewer(Folder):	Line 462 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 399 class documentViewer(Folder):	Line 477 class documentViewer(Folder):

return docinfo	return docinfo

	def getIndexMetaPath(self,url):
	"""gib nur den Pfad zurueck"""
	regexp = re.compile(r".(experimental\|permanent)/(.)")
	regpath = regexp.match(url)
	if (regpath==None):
	return ""
	logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
	return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))



	def getIndexMetaUrl(self,url):
	"""returns utr of index.meta document at url"""

def getIndexMeta(self, url):
"""returns dom of index.meta document at url"""
dom = None
metaUrl = None	metaUrl = None
if url.startswith("http://"):	if url.startswith("http://"):
# real URL	# real URL
Line 414 class documentViewer(Folder):	Line 502 class documentViewer(Folder):
if not metaUrl.endswith("index.meta"):	if not metaUrl.endswith("index.meta"):
metaUrl += "/index.meta"	metaUrl += "/index.meta"

logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)	return metaUrl

	def getDomFromIndexMeta(self, url):
	"""get dom from index meta"""
	dom = None
	metaUrl = self.getIndexMetaUrl(url)

	logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
txt=getHttpData(metaUrl)	txt=getHttpData(metaUrl)
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 438 class documentViewer(Folder):	Line 534 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 454 class documentViewer(Folder):	Line 551 class documentViewer(Folder):
if dom is None:	if dom is None:
for x in range(cut):	for x in range(cut):
path=getParentDir(path)	path=getParentDir(path)
dom = self.getIndexMeta(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 476 class documentViewer(Folder):	Line 576 class documentViewer(Folder):
if dom is None:	if dom is None:
for x in range(cut):	for x in range(cut):
path=getParentDir(path)	path=getParentDir(path)
dom = self.getIndexMeta(path)	dom = self.getDomFromIndexMeta(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"	# try to get MetaDataFolder
bib = dom.xpath("//bib/*")	metadata = getattr(self, 'metadata')
if bib and len(bib)>0:	if metadata is not None:
bibinfo = {}	# put all raw bib fields in dict "bib"
for e in bib:	bib = metadata.getBibdataFromDom(dom)
bibinfo[e.localName] = getTextFromNode(e)	docinfo['bib'] = bib
docinfo['bib'] = bibinfo	bibtype = bib.get('@type', None)
	docinfo['bib_type'] = bibtype
	# also store DC metadata for convenience
	dc = metadata.getDCMappedData(bib)
	docinfo['creator'] = dc.get('creator',None)
	docinfo['title'] = dc.get('title',None)
	docinfo['date'] = dc.get('date',None)
	else:
	logging.error("MetaDataFolder 'metadata' not found!")
	#TODO: remove
	bib = getBibdataFromDom(dom)
	return docinfo

# extract some fields (author, title, year) according to their mapping
metaData=self.metadata.main.meta.bib
bibtype=dom.xpath("//bib/@type")
if bibtype and (len(bibtype)>0):
bibtype=bibtype[0].value
else:
bibtype="generic"

bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)	# TODO: is this needed?
docinfo['bib_type'] = bibtype	def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
bibmap=metaData.generateMappingForType(bibtype)	"""gets name info from the index.meta file at path or given by dom"""
# if there is no mapping bibmap is empty (mapping sometimes has empty fields)	if docinfo is None:
if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:	docinfo = {}
try:
docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
except: pass
try:
docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
except: pass
try:
docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
except: pass
logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
try:
docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
except:
docinfo['lang']=''

return docinfo	if dom is None:
	for x in range(cut):
	path=getParentDir(path)
	dom = self.getDomFromIndexMeta(path)

	docinfo['name']=getText(dom.find("name"))
	logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
	return docinfo

def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):	def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
"""parse texttool tag in index meta"""	"""parse texttool tag in index meta"""
Line 526 class documentViewer(Folder):	Line 624 class documentViewer(Folder):
if docinfo.get('lang', None) is None:	if docinfo.get('lang', None) is None:
docinfo['lang'] = '' # default keine Sprache gesetzt	docinfo['lang'] = '' # default keine Sprache gesetzt
if dom is None:	if dom is None:
dom = self.getIndexMeta(url)	dom = self.getDomFromIndexMeta(url)

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 555 class documentViewer(Folder):	Line 650 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 576 class documentViewer(Folder):	Line 669 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

textUrls = dom.xpath("//texttool/text")	# old style text URL
if textUrls and (len(textUrls) > 0):	textUrl = getText(dom.find(".//texttool/text"))
textUrl = getTextFromNode(textUrls[0])	if textUrl:
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 592 class documentViewer(Folder):	Line 684 class documentViewer(Folder):

docinfo['textURL'] = textUrl	docinfo['textURL'] = textUrl

textUrls = dom.xpath("//texttool/text-url-path")	# new style text-url-path
if textUrls and (len(textUrls) > 0):	textUrl = getText(dom.find(".//texttool/text-url-path"))
textUrl = getTextFromNode(textUrls[0])	if textUrl:
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.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht	#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)

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 623 class documentViewer(Folder):	Line 721 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 653 class documentViewer(Folder):	Line 742 class documentViewer(Folder):
imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path	imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
docinfo['imageURL'] = imageUrl	docinfo['imageURL'] = imageUrl

	#TODO: use getDocinfoFromIndexMeta
#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.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)	docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
Line 667 class documentViewer(Folder):	Line 757 class documentViewer(Folder):
docinfo = self.REQUEST.SESSION['docinfo']	docinfo = self.REQUEST.SESSION['docinfo']
# check if its still current	# check if its still current
if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:	if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)	logging.debug("documentViewer (getdocinfo) docinfo in session. keys=%s"%docinfo.keys())
return docinfo	return docinfo

# new docinfo	# new docinfo
docinfo = {'mode': mode, 'url': url}	docinfo = {'mode': mode, 'url': url}
if mode=="texttool": #index.meta with texttool information	# add self url
	docinfo['viewerUrl'] = self.getDocumentViewerURL()
	if mode=="texttool":
	# index.meta with texttool information
docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)	docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
elif mode=="imagepath":	elif mode=="imagepath":
	# folder with images, index.meta optional
docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)	docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
elif mode=="filepath":	elif mode=="filepath":
	# filename
docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)	docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
else:	else:
logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)	logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))	raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))

logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)	logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
	#logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
	# store in session
self.REQUEST.SESSION['docinfo'] = docinfo	self.REQUEST.SESSION['docinfo'] = docinfo
return docinfo	return docinfo

Line 689 class documentViewer(Folder):	Line 787 class documentViewer(Folder):
"""returns pageinfo with the given parameters"""	"""returns pageinfo with the given parameters"""
pageinfo = {}	pageinfo = {}
current = getInt(current)	current = getInt(current)

pageinfo['current'] = current	pageinfo['current'] = current
rows = int(rows or self.thumbrows)	rows = int(rows or self.thumbrows)
pageinfo['rows'] = rows	pageinfo['rows'] = rows
Line 696 class documentViewer(Folder):	Line 795 class documentViewer(Folder):
pageinfo['cols'] = cols	pageinfo['cols'] = cols
grpsize = cols * rows	grpsize = cols * rows
pageinfo['groupsize'] = grpsize	pageinfo['groupsize'] = grpsize
	# what does this do?
start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))	start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
# int(current / grpsize) * grpsize +1))	# int(current / grpsize) * grpsize +1))
pageinfo['start'] = start	pageinfo['start'] = start
Line 706 class documentViewer(Folder):	Line 806 class documentViewer(Folder):
pageinfo['numgroups'] = int(np / grpsize)	pageinfo['numgroups'] = int(np / grpsize)
if np % grpsize > 0:	if np % grpsize > 0:
pageinfo['numgroups'] += 1	pageinfo['numgroups'] += 1

pageinfo['viewMode'] = viewMode	pageinfo['viewMode'] = viewMode
pageinfo['tocMode'] = tocMode	pageinfo['tocMode'] = tocMode
	pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
	#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 716 class documentViewer(Folder):	Line 819 class documentViewer(Folder):
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')
	# WTF?:
toc = int (pageinfo['tocPN'])	toc = int (pageinfo['tocPN'])
pageinfo['textPages'] =int (toc)	pageinfo['textPages'] =int (toc)

	# What does this do?
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 727 class documentViewer(Folder):	Line 832 class documentViewer(Folder):
tocPages=tocSize/tocPageSize+1	tocPages=tocSize/tocPageSize+1
else:	else:
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','')
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):
"""init document viewer"""	"""init document viewer"""
self.title=title	self.title=title

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>

Removed from v.1.69.2.3
changed lines
	Added in v.1.175.2.9