documentViewer/documentViewer.py - diff

Return to documentViewer.py CVS log

Up to [Repository] / documentViewer

Diff for /documentViewer/documentViewer.py between versions 1.6 and 1.13

version 1.6, 2006/04/10 11:23:18	version 1.13, 2006/06/14 16:24:10
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
from Ft.Xml.Domlette import PrettyPrint, Print	from Ft.Xml.Domlette import PrettyPrint, Print
from Ft.Xml import EMPTY_NAMESPACE	from Ft.Xml import EMPTY_NAMESPACE, Parse

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 25 def getInt(number, default=0):	Line 24 def getInt(number, default=0):
except:	except:
return default	return default


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 34 def getTextFromNode(nodename):	Line 34 def getTextFromNode(nodename):
rc = rc + node.data	rc = rc + node.data
return rc	return rc


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


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




##	##
## documentViewer class	## documentViewer class
##	##
Line 70 class documentViewer(Folder):	Line 74 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 81 class documentViewer(Folder):	Line 85 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 97 class documentViewer(Folder):	Line 103 class documentViewer(Folder):

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 111 class documentViewer(Folder):	Line 116 class documentViewer(Folder):

def getLink(self,param=None,val=None):	def getLink(self,param=None,val=None):
"""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=self.REQUEST.form.copy()
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)	# quote values and assemble into query string
	ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
	url=self.REQUEST['URL1']+"?"+ps
return url	return url


Line 131 class documentViewer(Folder):	Line 139 class documentViewer(Folder):
return style	return style


def getParamFromDigilib(self,path,param):	def isAccessible(self, docinfo):
	"""returns if access to the resource is granted"""
	access = docinfo.get('accessType', None)
	if access is None:
	# no information - no access
	#TODO: check
	return True
	elif access == 'free':
	return True
	elif access in self.authgroups:
	# only local access -- only logged in users
	user = getSecurityManager().getUser()
	if user is not None:
	#print "user: ", user
	return (user.getUserName() != "Anonymous User")
	else:
	return False

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


	def getDirinfoFromDigilib(self,path,docinfo=None):
"""gibt param von dlInfo aus"""	"""gibt param von dlInfo aus"""
imageUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path	num_retries = 3
	if docinfo is None:
	docinfo = {}

zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo (%s) from %s"%(param,imageUrl))	infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path

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

	for cnt in range(num_retries):
try:	try:
dom = NonvalidatingReader.parseUri(imageUrl)	# dom = NonvalidatingReader.parseUri(imageUrl)
	txt=urllib.urlopen(infoUrl).read()
	dom = Parse(txt)
	break
except:	except:
return None	zLOG.LOG("documentViewer (getdirinfofromdigilib)", zLOG.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
	else:
	raise IOError("Unable to get dir-info from %s"%(infoUrl))

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

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

	return docinfo


	def getIndexMeta(self, url):
	"""returns dom of index.meta document at url"""
	num_retries = 3
	dom = None
	metaUrl = None
	if url.startswith("http://"):
	# real URL
	metaUrl = url
	else:
	# online path
	server=self.digilibBaseUrl+"/servlet/Texter?fn="
	metaUrl=server+url.replace("/mpiwg/online","")
	if not metaUrl.endswith("index.meta"):
	metaUrl += "/index.meta"

	for cnt in range(num_retries):
	try:
	# patch dirk encoding fehler treten dann nicht mehr auf
	# dom = NonvalidatingReader.parseUri(metaUrl)
	txt=urllib.urlopen(metaUrl).read()
	dom = Parse(txt)
	break
	except:
	zLOG.LOG("ERROR documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])

	if dom is None:
	raise IOError("Unable to read index meta from %s"%(url))

	return dom


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

	access = None

params=dom.xpath("//dir/%s"%param)	if docinfo is None:
zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:%s"%params)	docinfo = {}

if params:	if dom is None:
return getTextFromNode(params[0])	dom = self.getIndexMeta(getParentDir(path))

	acctype = dom.xpath("//access-conditions/access/@type")
	if acctype and (len(acctype)>0):
	access=acctype[0].value
	if access in ['group', 'institution']:
	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 path or given by dom"""
zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))	zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))

if docinfo is None:	if docinfo is None:
docinfo = {}	docinfo = {}

if dom is None:	if dom is None:
server="http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary/servlet/Texter?fn="	dom = self.getIndexMeta(getParentDir(path))
path="/".join(path.split("/")[0:-1])
metaUrl=server+path+"/index.meta"
try:
dom = NonvalidatingReader.parseUri(metaUrl)
except:
return docinfo

metaData=self.metadata.main.meta.bib	metaData=self.metadata.main.meta.bib
bibtype=dom.xpath("//bib/@type")	bibtype=dom.xpath("//bib/@type")
Line 173 class documentViewer(Folder):	Line 264 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 274 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 = {}

try:	if dom is None:
dom = NonvalidatingReader.parseUri(url)	dom = self.getIndexMeta(url)
except:
zLOG.LOG("documentViewer (parseUrlTexttool)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])
return docinfo

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")	imageDirs=dom.xpath("//texttool/image")
	if imageDirs and (len(imageDirs)>0):
if images and (len(images)>0):	imageDir=getTextFromNode(imageDirs[0])
image=getTextFromNode(images[0])
else:	else:
image=None	# we balk with no image tag
	raise IOError("No text-tool info in %s"%(url))

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

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 237 class documentViewer(Folder):	Line 335 class documentViewer(Folder):
docinfo = {}	docinfo = {}
path=path.replace("/mpiwg/online","")	path=path.replace("/mpiwg/online","")
docinfo['imagePath'] = path	docinfo['imagePath'] = path
pt=self.getParamFromDigilib(path,'size')	docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo)
docinfo['numPages'] = pt	imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn=%s"%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 264 class documentViewer(Folder):	Line 362 class documentViewer(Folder):
docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)	docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
else:	else:
zLOG.LOG("documentViewer (getdocinfo)", zLOG.ERROR,"unknown mode!")	zLOG.LOG("documentViewer (getdocinfo)", zLOG.ERROR,"unknown mode!")
	raise ValueError("Unknown mode %s"%(mode))

zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo: %s"%docinfo)	zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo: %s"%docinfo)
self.REQUEST.SESSION['docinfo'] = docinfo	self.REQUEST.SESSION['docinfo'] = docinfo
return docinfo	return docinfo
Line 281 class documentViewer(Folder):	Line 381 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 298 class documentViewer(Folder):	Line 397 class documentViewer(Folder):
if mode=="texttool": #index.meta with texttool information	if mode=="texttool": #index.meta with texttool information
(viewerUrl,imagepath,textpath)=parseUrlTextTool(url)	(viewerUrl,imagepath,textpath)=parseUrlTextTool(url)

print textpath	#print textpath
try:	try:
dom = NonvalidatingReader.parseUri(textpath)	dom = NonvalidatingReader.parseUri(textpath)
except:	except:
Line 356 class documentViewer(Folder):	Line 455 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.1.6
changed lines
	Added in v.1.13