documentViewer/documentViewer.py - diff

Return to documentViewer.py CVS log

Up to [Repository] / documentViewer

Diff for /documentViewer/documentViewer.py between versions 1.5 and 1.8

version 1.5, 2006/04/10 10:13:01	version 1.8, 2006/04/11 17:27:57
Line 1	Line 1

genericDigilib="http://nausikaa2.rz-berlin.mpg.de/digitallibrary/"

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 AccessControl import ClassSecurityInfo	from AccessControl import ClassSecurityInfo
	from AccessControl import getSecurityManager
from Globals import package_home	from Globals import package_home

from Ft.Xml.Domlette import NonvalidatingReader	from Ft.Xml.Domlette import NonvalidatingReader
Line 14 from Ft.Xml import EMPTY_NAMESPACE	Line 12 from Ft.Xml import EMPTY_NAMESPACE
import Ft.Xml.XPath	import Ft.Xml.XPath

import os.path	import os.path
	import sys
import cgi	import cgi
import urllib	import urllib
import zLOG	import zLOG
Line 27 def getInt(number, default=0):	Line 26 def getInt(number, default=0):


def getTextFromNode(nodename):	def getTextFromNode(nodename):
	if nodename is None:
	return ""
nodelist=nodename.childNodes	nodelist=nodename.childNodes
rc = ""	rc = ""
for node in nodelist:	for node in nodelist:
Line 36 def getTextFromNode(nodename):	Line 37 def getTextFromNode(nodename):

import socket	import socket

def urlopen(url):	def urlopen(url,timeout=2):
"""urlopen mit timeout"""	"""urlopen mit timeout"""
socket.setdefaulttimeout(2)	socket.setdefaulttimeout(timeout)
ret=urllib.urlopen(url)	ret=urllib.urlopen(url)
socket.setdefaulttimeout(5)	socket.setdefaulttimeout(5)
return ret	return ret

def getParamFromDigilib(path,param):
"""gibt param von dlInfo aus"""
imageUrl=genericDigilib+"/dirInfo-xml.jsp?mo=dir&fn="+path

zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo (%s) from %s"%(param,imageUrl))

try:
dom = NonvalidatingReader.parseUri(imageUrl)
except:
return None

params=dom.xpath("//dir/%s"%param)
zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:%s"%params)

if params:
return getTextFromNode(params[0])




##	##
## documentViewer class	## documentViewer class
Line 87 class documentViewer(Folder):	Line 69 class documentViewer(Folder):
changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())	changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())


def __init__(self,id,imageViewerUrl,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10):	def __init__(self,id,imageViewerUrl,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):
"""init document viewer"""	"""init document viewer"""
self.id=id	self.id=id
self.title=title	self.title=title
Line 98 class documentViewer(Folder):	Line 80 class documentViewer(Folder):
self.digilibBaseUrl = digilibBaseUrl	self.digilibBaseUrl = digilibBaseUrl
self.thumbcols = thumbcols	self.thumbcols = thumbcols
self.thumbrows = thumbrows	self.thumbrows = thumbrows
	# authgroups is list of authorized groups (delimited by ,)
	self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
# add template folder so we can always use template.something	# add template folder so we can always use template.something
self.manage_addFolder('template')	self.manage_addFolder('template')

Line 111 class documentViewer(Folder):	Line 95 class documentViewer(Folder):
'''	'''

zLOG.LOG("documentViewer (index)", zLOG.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))	zLOG.LOG("documentViewer (index)", zLOG.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
print "dlbaseurl:", self.digilibBaseUrl

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
print "no template folder -- creating"
self.manage_addFolder('template')	self.manage_addFolder('template')

if not self.digilibBaseUrl:	if not self.digilibBaseUrl:
Line 131 class documentViewer(Folder):	Line 113 class documentViewer(Folder):
"""link to documentviewer with parameter param set to val"""	"""link to documentviewer with parameter param set to val"""
params=cgi.parse_qs(self.REQUEST['QUERY_STRING'])	params=cgi.parse_qs(self.REQUEST['QUERY_STRING'])
if param is not None:	if param is not None:
if val is None and params.has_key(param):	if val is None:
	if params.has_key(param):
del params[param]	del params[param]
else:	else:
params[param] = val	params[param] = [str(val)]

url=self.REQUEST['URL']+"?"+urllib.urlencode(params, doseq=True)	ps = "&".join(["%s=%s"%(k,urllib.quote(v[0])) for (k, v) in params.items()])
	url=self.REQUEST['URL']+"?"+ps
	#url=self.REQUEST['URL']+"?"+urllib.urlencode(params, doseq=True)
return url	return url


Line 148 class documentViewer(Folder):	Line 133 class documentViewer(Folder):
else:	else:
return style	return style

	def accessOK(self, docinfo):
	"""returns if access to the resource is granted"""
	access = docinfo.get('accessType', None)
	if access is None:
	# no information - no access (not yet)
	return True
	elif access == 'free':
	return True

	print "access: ", access, " authgroups: ", self.authgroups
	if access in self.authgroups:
	# local access OK
	user = getSecurityManager().getUser().getUserName()
	print "user: ", user
	return (user != "Anonymous User")

	zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "unknown access group %s"%access)
	return False


	def getDirinfoFromDigilib(self,path,docinfo=None):
	"""gibt param von dlInfo aus"""
	if docinfo is None:
	docinfo = {}

	imageUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path

	zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(imageUrl))

	try:
	dom = NonvalidatingReader.parseUri(imageUrl)
	except:
	zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.ERROR, "error reading %s"%(imageUrl))
	raise IOError("Unable to get dirinfo from %s"%(imageUrl))

	params=dom.xpath("//dir/size")
	zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:size"%params)

	if params:
	docinfo['numPages'] = int(getTextFromNode(params[0]))
	else:
	docinfo['numPages'] = 0

	return docinfo


	def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None):
	"""gets authorization info from the index.meta file at url or given by dom"""
	zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))

	access = None

	if docinfo is None:
	docinfo = {}

	if dom is None:
	server=self.digilibBaseUrl+"/servlet/Texter?fn="
	path="/".join(path.split("/")[0:-1])
	metaUrl=server+path+"/index.meta"
	try:
	dom = NonvalidatingReader.parseUri(metaUrl)
	except:
	return docinfo

	acctype = dom.xpath("//access-conditions/access/@type")
	if acctype and (len(acctype)>0):
	access=acctype[0].value
	if access == 'group':
	access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()

	docinfo['accessType'] = access
	return docinfo


def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None):	def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None):
"""gets bibliographical info from the index.meta file at url or given by dom"""	"""gets bibliographical info from the index.meta file at url or given by dom"""
Line 157 class documentViewer(Folder):	Line 215 class documentViewer(Folder):
docinfo = {}	docinfo = {}

if dom is None:	if dom is None:
server="http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary/servlet/Texter?fn="	server=self.digilibBaseUrl+"/servlet/Texter?fn="
path="/".join(path.split("/")[0:-1])	path="/".join(path.split("/")[0:-1])
metaUrl=server+path+"/index.meta"	metaUrl=server+path+"/index.meta"
try:	try:
Line 173 class documentViewer(Folder):	Line 231 class documentViewer(Folder):
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)
bibmap=metaData.generateMappingForType(bibtype)	bibmap=metaData.generateMappingForType(bibtype)
if len(bibmap) > 0:	print "bibmap: ", bibmap, " for: ", bibtype
	# if there is no mapping bibmap is empty (mapping sometimes has empty fields)
	if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])	docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])	docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])	docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
Line 181 class documentViewer(Folder):	Line 241 class documentViewer(Folder):
return docinfo	return docinfo


def getDocinfoFromTextTool(self,url,docinfo=None):	def getDocinfoFromTextTool(self,url,dom=None,docinfo=None):
"""parse texttool tag in index meta"""	"""parse texttool tag in index meta"""
zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.INFO,"url: %s"%(url))	zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.INFO,"url: %s"%(url))
if docinfo is None:	if docinfo is None:
docinfo = {}	docinfo = {}

	if dom is None:
try:	try:
dom = NonvalidatingReader.parseUri(url)	dom = NonvalidatingReader.parseUri(url)
except:	except:
zLOG.LOG("documentViewer (parseUrlTexttool)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])	zLOG.LOG("documentViewer (parseUrlTexttool)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])
return docinfo	raise IOError("Unable to get texttool info from %s"%(url))

archivePaths=dom.xpath("//resource/archive-path")	archiveNames=dom.xpath("//resource/name")
	if archiveNames and (len(archiveNames)>0):
	archiveName=getTextFromNode(archiveNames[0])

	archivePaths=dom.xpath("//resource/archive-path")
if archivePaths and (len(archivePaths)>0):	if archivePaths and (len(archivePaths)>0):
archivePath=getTextFromNode(archivePaths[0])	archivePath=getTextFromNode(archivePaths[0])
	# clean up archive path
	if archivePath[0] != '/':
	archivePath = '/' + archivePath
	if not archivePath.endswith(archiveName):
	archivePath += "/" + archiveName
else:	else:
archivePath=None	archivePath=None

images=dom.xpath("//texttool/image")	images=dom.xpath("//texttool/image")

if images and (len(images)>0):	if images and (len(images)>0):
image=getTextFromNode(images[0])	image=getTextFromNode(images[0])
else:	else:
image=None	image=None

if image and archivePath:	if image and archivePath:
	print "image: ", image, " archivepath: ", archivePath
image=os.path.join(archivePath,image)	image=os.path.join(archivePath,image)
image=image.replace("/mpiwg/online",'')	image=image.replace("/mpiwg/online",'')
pt=getParamFromDigilib(image,'size')	docinfo=self.getDirinfoFromDigilib(image,docinfo=docinfo)
docinfo['imagePath'] = image	docinfo['imagePath'] = image
docinfo['numPages'] = pt	docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+image

viewerUrls=dom.xpath("//texttool/digiliburlprefix")	viewerUrls=dom.xpath("//texttool/digiliburlprefix")

if viewerUrls and (len(viewerUrls)>0):	if viewerUrls and (len(viewerUrls)>0):
viewerUrl=getTextFromNode(viewerUrls[0])	viewerUrl=getTextFromNode(viewerUrls[0])
docinfo['imageURL'] = viewerURL	docinfo['viewerURL'] = viewerUrl

textUrls=dom.xpath("//texttool/text")	textUrls=dom.xpath("//texttool/text")

if textUrls and (len(textUrls)>0):	if textUrls and (len(textUrls)>0):
textUrl=getTextFromNode(textUrls[0])	textUrl=getTextFromNode(textUrls[0])
docinfo['textURL'] = textURL	docinfo['textURL'] = textUrl

docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)	docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)
	docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)
return docinfo	return docinfo


Line 235 class documentViewer(Folder):	Line 303 class documentViewer(Folder):
zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path))	zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path))
if docinfo is None:	if docinfo is None:
docinfo = {}	docinfo = {}
docinfo['imagePath'] = path
path=path.replace("/mpiwg/online","")	path=path.replace("/mpiwg/online","")
pt=getParamFromDigilib(path,'size')	docinfo['imagePath'] = path
docinfo['numPages'] = pt	docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo)
imageUrl=genericDigilib+"/servlet/Scaler?fn=%s"%path	imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
docinfo['imageURL'] = imageUrl	docinfo['imageURL'] = imageUrl

docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo)	docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo)
	docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo)
return docinfo	return docinfo


Line 281 class documentViewer(Folder):	Line 349 class documentViewer(Folder):
grpsize = cols * rows	grpsize = cols * rows
pageinfo['groupsize'] = grpsize	pageinfo['groupsize'] = grpsize
start = getInt(start, default=(int(current / grpsize) * grpsize +1))	start = getInt(start, default=(int(current / grpsize) * grpsize +1))
print "start3:", start
pageinfo['start'] = start	pageinfo['start'] = start
pageinfo['end'] = start + grpsize	pageinfo['end'] = start + grpsize
if docinfo is not None:	if docinfo is not None:
Line 356 class documentViewer(Folder):	Line 423 class documentViewer(Folder):
except:	except:
return None	return None

def changeDocumentViewer(self,imageViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,RESPONSE=None):	def changeDocumentViewer(self,imageViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):
"""init document viewer"""	"""init document viewer"""
self.title=title	self.title=title
self.imageViewerUrl=imageViewerUrl	self.imageViewerUrl=imageViewerUrl
self.digilibBaseUrl = digilibBaseUrl	self.digilibBaseUrl = digilibBaseUrl
self.thumbrows = thumbrows	self.thumbrows = thumbrows
self.thumbcols = thumbcols	self.thumbcols = thumbcols
	self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
if RESPONSE is not None:	if RESPONSE is not None:
RESPONSE.redirect('manage_main')	RESPONSE.redirect('manage_main')

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

Removed from v.1.5
changed lines
	Added in v.1.8