documentViewer/documentViewer.py - diff

Return to documentViewer.py CVS log

Up to [Repository] / documentViewer

Diff for /documentViewer/documentViewer.py between versions 1.146 and 1.175.2.2

version 1.146, 2010/10/26 14:44:55	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

def logger(txt,method,txt2):	def logger(txt,method,txt2):
"""logging"""	"""logging"""
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 getBrowserType(self):	def browserCheck(self):
"""get browser type object"""	"""check the browsers request to find out the browser type"""
if self.REQUEST.SESSION.has_key('browserType'):	bt = {}
return self.REQUEST.SESSION['browserType']	ua = self.REQUEST.get_header("HTTP_USER_AGENT")
else:	bt['ua'] = ua
bt = browserCheck(self)	bt['isIE'] = False
self.REQUEST.SESSION.set('browserType', bt)	bt['isN4'] = False
logging.debug("documentViewer (BROWSER TYPE) bt %s"%bt)	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	return bt


Line 110 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 130 class documentViewer(Folder):	Line 195 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_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 178 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"""	"""get query in search"""
return self.template.fulltextclient.getQuery(**args)	return self.template.fulltextclient.getQuery(**args)

def getSearch(self, **args):	def getSearch(self, **args):
Line 194 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 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 214 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 249 class documentViewer(Folder):	Line 320 class documentViewer(Folder):
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.has_key("textURL") or docinfo.has_key('textURLPath'): #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 257 class documentViewer(Folder):	Line 328 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, characterNormalization=""):	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
Line 285 class documentViewer(Folder):	Line 356 class documentViewer(Folder):
docinfo = self.getToc(mode=tocMode, docinfo=docinfo)	docinfo = self.getToc(mode=tocMode, docinfo=docinfo)

if viewMode=="auto": # automodus gewaehlt	if viewMode=="auto": # automodus gewaehlt
if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert	if docinfo.has_key('textURL') 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)

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 306 class documentViewer(Folder):	Line 381 class documentViewer(Folder):
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 323 class documentViewer(Folder):	Line 404 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)

	# change more params
	if params is not None:
	for k in params.keys():
	v = params[k]
	if v is None:
	# val=None removes param
	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']

if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath	url = "%s?%s"%(baseUrl, ps)
params["mode"] = "imagepath"
params["url"] = getParentDir(params["url"])

# quote values and assemble into query string
#ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
ps = urllib.urlencode(params)
url=self.REQUEST['URL1']+"?"+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 369 class documentViewer(Folder):	Line 457 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 397 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 408 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 458 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 477 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 495 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 521 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 542 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:
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


	# 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 571 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 588 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 612 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 633 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 651 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
	# TODO: is this needed here?
docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)	docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
#docinfo =self.getOrigPages(docinfo=docinfo)

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 684 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 742 class documentViewer(Folder):	Line 880 class documentViewer(Folder):
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))

	# FIXME: fake texturlpath
	if not docinfo.has_key('textURLPath'):
	docinfo['textURLPath'] = None

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

def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):	def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
"""returns pageinfo with the given parameters"""	"""returns pageinfo with the given parameters"""
pageinfo = {}	pageinfo = {}
current = getInt(current)	current = getInt(current)
Line 771 class documentViewer(Folder):	Line 913 class documentViewer(Folder):
pageinfo['numgroups'] += 1	pageinfo['numgroups'] += 1
pageinfo['viewMode'] = viewMode	pageinfo['viewMode'] = viewMode
pageinfo['tocMode'] = tocMode	pageinfo['tocMode'] = tocMode
#pageinfo ['originalPage'] = self.getOrigPages(docinfo=None, pageinfo=None)	pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','')	#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 784 class documentViewer(Folder):	Line 926 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'])

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

Removed from v.1.146
changed lines
	Added in v.1.175.2.2