documentViewer/documentViewer.py - diff

Return to documentViewer.py CVS log

Up to [Repository] / documentViewer

Diff for /documentViewer/documentViewer.py between versions 1.24 and 1.97

version 1.24, 2007/05/03 17:28:23	version 1.97, 2010/08/24 13:27:07
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
Line 7 from AccessControl import ClassSecurityI	Line 6 from AccessControl import ClassSecurityI
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.Domlette import PrettyPrint, Print
from Ft.Xml import EMPTY_NAMESPACE, Parse	from Ft.Xml import EMPTY_NAMESPACE, Parse
	import Ft.Xml.Domlette
import Ft.Xml.XPath

import os.path	import os.path
import sys	import sys
import cgi
import urllib	import urllib
	import urllib2
import logging	import logging
	import math
import urlparse	import urlparse
	import cStringIO

def logger(txt,method,txt2):	def logger(txt,method,txt2):
"""logging"""	"""logging"""
Line 31 def getInt(number, default=0):	Line 27 def getInt(number, default=0):
try:	try:
return int(number)	return int(number)
except:	except:
return default	return int(default)

def getTextFromNode(nodename):	def getTextFromNode(nodename):
"""get the cdata content of a node"""	"""get the cdata content of a node"""
Line 44 def getTextFromNode(nodename):	Line 40 def getTextFromNode(nodename):
rc = rc + node.data	rc = rc + node.data
return rc	return rc

	def serializeNode(node, encoding='utf-8'):
	"""returns a string containing node as XML"""
	buf = cStringIO.StringIO()
	Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
	s = buf.getvalue()
	buf.close()
	return s


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 getHttpData(url, data=None, num_tries=3, timeout=10):
	"""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	import socket
	socket.setdefaulttimeout(float(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))
	#return None

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


##	##
Line 65 def urlopen(url,timeout=2):	Line 104 def urlopen(url,timeout=2):
##	##
class documentViewer(Folder):	class documentViewer(Folder):
"""document viewer"""	"""document viewer"""
#textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"

meta_type="Document viewer"	meta_type="Document viewer"

security=ClassSecurityInfo()	security=ClassSecurityInfo()
Line 76 class documentViewer(Folder):	Line 113 class documentViewer(Folder):

# templates and forms	# templates and forms
viewer_main = PageTemplateFile('zpt/viewer_main', globals())	viewer_main = PageTemplateFile('zpt/viewer_main', globals())
thumbs_main = PageTemplateFile('zpt/thumbs_main', globals())	toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
image_main = PageTemplateFile('zpt/image_main', globals())	toc_text = PageTemplateFile('zpt/toc_text', globals())
	toc_figures = PageTemplateFile('zpt/toc_figures', globals())
	page_main_images = PageTemplateFile('zpt/page_main_images', globals())
	page_main_text = PageTemplateFile('zpt/page_main_text', 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())
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())


	thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
security.declareProtected('View management screens','changeDocumentViewerForm')	security.declareProtected('View management screens','changeDocumentViewerForm')
changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())	changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())


def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):	def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
"""init document viewer"""	"""init document viewer"""
self.id=id	self.id=id
self.title=title	self.title=title
self.imageViewerUrl=imageViewerUrl
self.textViewerUrl=textViewerUrl

if not digilibBaseUrl:
self.digilibBaseUrl = self.findDigilibUrl()
else:
self.digilibBaseUrl = digilibBaseUrl
self.thumbcols = thumbcols	self.thumbcols = thumbcols
self.thumbrows = thumbrows	self.thumbrows = thumbrows
# authgroups is list of authorized groups (delimited by ,)	# authgroups is list of authorized groups (delimited by ,)
self.authgroups = [s.strip().lower() for s in authgroups.split(',')]	self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
# add template folder so we can always use template.something	# create template folder so we can always use template.something
self.manage_addFolder('template')

	templateFolder = Folder('template')
	#self['template'] = templateFolder # Zope-2.12 style
	self._setObject('template',templateFolder) # old style
	try:
	import MpdlXmlTextServer
	textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
	#templateFolder['fulltextclient'] = xmlRpcClient
	templateFolder._setObject('fulltextclient',textServer)
	except Exception, e:
	logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
	try:
	from Products.zogiLib.zogiLib import zogiLib
	zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
	#templateFolder['zogilib'] = zogilib
	templateFolder._setObject('zogilib',zogilib)
	except Exception, e:
	logging.error("Unable to create zogiLib for zogilib: "+str(e))


	# proxy text server methods to fulltextclient
	def getTextPage(self, **args):
	"""get page"""
	return self.template.fulltextclient.getTextPage(**args)

	def getQuery(self, **args):
	"""get query"""
	return self.template.fulltextclient.getQuery(**args)

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

	def getNumPages(self, docinfo):
	"""get numpages"""
	return self.template.fulltextclient.getNumPages(docinfo)

	def getTranslate(self, **args):
	"""get translate"""
	return self.template.fulltextclient.getTranslate(**args)

	def getLemma(self, **args):
	"""get lemma"""
	return self.template.fulltextclient.getLemma(**args)

	def getToc(self, **args):
	"""get toc"""
	return self.template.fulltextclient.getToc(**args)

	def getTocPage(self, **args):
	"""get tocpage"""
	return self.template.fulltextclient.getTocPage(**args)

security.declareProtected('View','index_html')
def index_html(self,mode,url,viewMode="auto",start=None,pn=1):	security.declareProtected('View','thumbs_rss')
	def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
'''	'''
view it	view it
@param mode: defines which type of document is behind url (text,images or auto)	@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 images	@param viewMode: if images display images, if text display text, default is images (text,images or auto)

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

if not hasattr(self, 'template'):	if not hasattr(self, 'template'):
Line 125 class documentViewer(Folder):	Line 215 class documentViewer(Folder):

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)
pt = getattr(self.template, 'viewer_main')	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.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
viewMode="text"	viewMode="text"
else:	else:
viewMode="images"	viewMode="images"


return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)	return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)

	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=""):
	'''
	view it
	@param mode: defines how to access the document behind url
	@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 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)
	'''

	logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))

	if not hasattr(self, 'template'):
	# this won't work
	logging.error("template folder missing!")
	return "ERROR: template folder missing!"

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

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

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

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

	pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)

	pt = getattr(self.template, 'viewer_main')
	return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))

	def generateMarks(self,mk):
	ret=""
	if mk is None:
	return ""
	if not isinstance(mk, list):
	mk=[mk]
	for m in mk:
	ret+="mk=%s"%m
	return ret


	def findDigilibUrl(self):
	"""try to get the digilib URL from zogilib"""
	url = self.template.zogilib.getDLBaseUrl()
	return url

	def getDocumentViewerURL(self):
	"""returns the URL of this instance"""
	return self.absolute_url()

	def getStyle(self, idx, selected, style=""):
	"""returns a string with the given style and append 'sel' if path == selected."""
	#logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
	if idx == selected:
	return style + 'sel'
	else:
	return style

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"""
Line 147 class documentViewer(Folder):	Line 302 class documentViewer(Folder):
else:	else:
params[param] = str(val)	params[param] = str(val)

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

# quote values and assemble into query string	# quote values and assemble into query string
ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])	#ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
	ps = urllib.urlencode(params)
url=self.REQUEST['URL1']+"?"+ps	url=self.REQUEST['URL1']+"?"+ps
return url	return url

	def getLinkAmp(self,param=None,val=None):
def getStyle(self, idx, selected, style=""):	"""link to documentviewer with parameter param set to val"""
"""returns a string with the given style and append 'sel' if path == selected."""	params=self.REQUEST.form.copy()
#logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))	if param is not None:
if idx == selected:	if val is None:
return style + 'sel'	if params.has_key(param):
	del params[param]
else:	else:
return style	params[param] = str(val)

	# quote values and assemble into query string
	logging.debug("XYXXXXX: %s"%repr(params.items()))
	ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
	url=self.REQUEST['URL1']+"?"+ps
	return url

	def getInfo_xml(self,url,mode):
	"""returns info about the document as XML"""

	if not self.digilibBaseUrl:
	self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"

	docinfo = self.getDocinfo(mode=mode,url=url)
	pt = getattr(self.template, 'info_xml')
	return pt(docinfo=docinfo)


def isAccessible(self, docinfo):	def isAccessible(self, docinfo):
"""returns if access to the resource is granted"""	"""returns if access to the resource is granted"""
access = docinfo.get('accessType', None)	access = docinfo.get('accessType', None)
logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)	logging.debug("documentViewer (accessOK) access type %s"%access)
if access is not None and access == 'free':	if access is not None and access == 'free':
logger("documentViewer (accessOK)", logging.INFO, "access is free")	logging.debug("documentViewer (accessOK) access is free")
return True	return True
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

logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)	logging.error("documentViewer (accessOK) unknown access type %s"%access)
return False	return False


def getDirinfoFromDigilib(self,path,docinfo=None):	def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
"""gibt param von dlInfo aus"""	"""gibt param von dlInfo aus"""
num_retries = 3
if docinfo is None:	if docinfo is None:
docinfo = {}	docinfo = {}

	for x in range(cut):

	path=getParentDir(path)

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

logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))	logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))

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

	dom = Parse(txt)
sizes=dom.xpath("//dir/size")	sizes=dom.xpath("//dir/size")
logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)	logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)

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

	# TODO: produce and keep list of image names and numbers

return docinfo	return docinfo


def getIndexMeta(self, url):	def getIndexMeta(self, url):
"""returns dom of index.meta document at url"""	"""returns dom of index.meta document at url"""
num_retries = 3
dom = None	dom = None
metaUrl = None	metaUrl = None
if url.startswith("http://"):	if url.startswith("http://"):
Line 228 class documentViewer(Folder):	Line 404 class documentViewer(Folder):
metaUrl=server+url.replace("/mpiwg/online","")	metaUrl=server+url.replace("/mpiwg/online","")
if not metaUrl.endswith("index.meta"):	if not metaUrl.endswith("index.meta"):
metaUrl += "/index.meta"	metaUrl += "/index.meta"
print metaUrl
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:
logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])

if dom is None:	logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)
	txt=getHttpData(metaUrl)
	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)
return dom	return dom

def getPresentationInfoXML(self, url):	def getPresentationInfoXML(self, url):
"""returns dom of info.xml document at url"""	"""returns dom of info.xml document at url"""
num_retries = 3
dom = None	dom = None
metaUrl = None	metaUrl = None
if url.startswith("http://"):	if url.startswith("http://"):
Line 257 class documentViewer(Folder):	Line 425 class documentViewer(Folder):
server=self.digilibBaseUrl+"/servlet/Texter?fn="	server=self.digilibBaseUrl+"/servlet/Texter?fn="
metaUrl=server+url.replace("/mpiwg/online","")	metaUrl=server+url.replace("/mpiwg/online","")

	txt=getHttpData(metaUrl)
for cnt in range(num_retries):	if txt is None:
try:
# patch dirk encoding fehler treten dann nicht mehr auf
# dom = NonvalidatingReader.parseUri(metaUrl)
txt=urllib.urlopen(metaUrl).read()
dom = Parse(txt)
break
except:
logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])

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

	dom = Parse(txt)
return dom	return dom


def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None):	def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
"""gets authorization info from the index.meta file at path or given by dom"""	"""gets authorization info from the index.meta file at path or given by dom"""
logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))	logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))

access = None	access = None

Line 284 class documentViewer(Folder):	Line 443 class documentViewer(Folder):
docinfo = {}	docinfo = {}

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

acctype = dom.xpath("//access-conditions/access/@type")	acctype = dom.xpath("//access-conditions/access/@type")
if acctype and (len(acctype)>0):	if acctype and (len(acctype)>0):
Line 296 class documentViewer(Folder):	Line 457 class documentViewer(Folder):
return docinfo	return docinfo


def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None):	def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
"""gets bibliographical info from the index.meta file at path or given by dom"""	"""gets bibliographical info from the index.meta file at path or given by dom"""
logger("documentViewer (getbibinfofromindexmeta)", logging.INFO,"path: %s"%(path))	logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))

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

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

	logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
	# put in all raw bib fields as dict "bib"
	bib = dom.xpath("//bib/*")
	if bib and len(bib)>0:
	bibinfo = {}
	for e in bib:
	bibinfo[e.localName] = getTextFromNode(e)
	docinfo['bib'] = bibinfo

	# 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=dom.xpath("//bib/@type")
if bibtype and (len(bibtype)>0):	if bibtype and (len(bibtype)>0):
bibtype=bibtype[0].value	bibtype=bibtype[0].value
else:	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)
	docinfo['bib_type'] = bibtype
bibmap=metaData.generateMappingForType(bibtype)	bibmap=metaData.generateMappingForType(bibtype)
#print "bibmap: ", bibmap, " for: ", 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:
	try:
docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])	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])	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])	docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
	except: pass
logging.info("bla")	logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
try:	try:
docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])	docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
except:	except:
docinfo['lang']=''	docinfo['lang']=''

return docinfo	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"""
logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url))	logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
if docinfo is None:	if docinfo is None:
docinfo = {}	docinfo = {}

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:
Line 347 class documentViewer(Folder):	Line 526 class documentViewer(Folder):
if archiveNames and (len(archiveNames)>0):	if archiveNames and (len(archiveNames)>0):
archiveName=getTextFromNode(archiveNames[0])	archiveName=getTextFromNode(archiveNames[0])
else:	else:
logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/name missing in: %s"%(url))	logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))

archivePaths=dom.xpath("//resource/archive-path")	archivePaths=dom.xpath("//resource/archive-path")
if archivePaths and (len(archivePaths)>0):	if archivePaths and (len(archivePaths)>0):
Line 359 class documentViewer(Folder):	Line 538 class documentViewer(Folder):
archivePath += "/" + archiveName	archivePath += "/" + archiveName
else:	else:
# try to get archive-path from url	# try to get archive-path from url
logger("documentViewer (getdocinfofromtexttool)", logging.WARNING,"resource/archive-path missing in: %s"%(url))	logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
if (not url.startswith('http')):	if (not url.startswith('http')):
archivePath = url.replace('index.meta', '')	archivePath = url.replace('index.meta', '')

Line 370 class documentViewer(Folder):	Line 549 class documentViewer(Folder):
imageDirs=dom.xpath("//texttool/image")	imageDirs=dom.xpath("//texttool/image")
if imageDirs and (len(imageDirs)>0):	if imageDirs and (len(imageDirs)>0):
imageDir=getTextFromNode(imageDirs[0])	imageDir=getTextFromNode(imageDirs[0])

else:	else:
# 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=""
docinfo['numPages']=1 # im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht	#xquery="//pb"

docinfo['imagePath'] = "" # keine Bilder	docinfo['imagePath'] = "" # keine Bilder
docinfo['imageURL'] = ""	docinfo['imageURL'] = ""

Line 385 class documentViewer(Folder):	Line 564 class documentViewer(Folder):
imageDir=imageDir.replace("/mpiwg/online",'')	imageDir=imageDir.replace("/mpiwg/online",'')
docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo)	docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo)
docinfo['imagePath'] = imageDir	docinfo['imagePath'] = imageDir

docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir	docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir

viewerUrls=dom.xpath("//texttool/digiliburlprefix")	viewerUrls=dom.xpath("//texttool/digiliburlprefix")
Line 392 class documentViewer(Folder):	Line 572 class documentViewer(Folder):
viewerUrl=getTextFromNode(viewerUrls[0])	viewerUrl=getTextFromNode(viewerUrls[0])
docinfo['viewerURL'] = viewerUrl	docinfo['viewerURL'] = viewerUrl

	# old style text URL
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])
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
	if textUrl.startswith("/mpiwg/online"):
	textUrl = textUrl.replace("/mpiwg/online", '', 1)

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

	# new style text-url-path
	textUrls = dom.xpath("//texttool/text-url-path")
	if textUrls and (len(textUrls) > 0):
	textUrl = getTextFromNode(textUrls[0])
	docinfo['textURLPath'] = textUrl
	if not docinfo['imagePath']:
	# text-only, no page images
	docinfo = self.getNumPages(docinfo)

presentationUrls=dom.xpath("//texttool/presentation")	presentationUrls=dom.xpath("//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

if presentationUrls and (len(presentationUrls)>0): # ueberschreibe diese durch presentation informationen	if presentationUrls and (len(presentationUrls)>0): # ueberschreibe diese durch presentation informationen
# presentation url ergiebt sich ersetzen von index.meta in der url der f�r 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
presentationUrl=url.replace('index.meta',getTextFromNode(presentationUrls[0]))	presentationPath = getTextFromNode(presentationUrls[0])
	if url.endswith("index.meta"):
	presentationUrl = url.replace('index.meta', presentationPath)
	else:
	presentationUrl = url + "/" + presentationPath

docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom)	docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom)

docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo)	docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info

return docinfo	return docinfo


Line 417 class documentViewer(Folder):	Line 616 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']=getTextFromNode(dom.xpath("//author")[0])	docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
	except:
	pass
	try:
docinfo['title']=getTextFromNode(dom.xpath("//title")[0])	docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
	except:
	pass
	try:
docinfo['year']=getTextFromNode(dom.xpath("//date")[0])	docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
	except:
	pass
return docinfo	return docinfo

def getDocinfoFromImagePath(self,path,docinfo=None):	def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
"""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."""
logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))	logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
if docinfo is None:	if docinfo is None:
docinfo = {}	docinfo = {}
path=path.replace("/mpiwg/online","")	path=path.replace("/mpiwg/online","")
docinfo['imagePath'] = path	docinfo['imagePath'] = path
docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo)	docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)

	pathorig=path
	for x in range(cut):
	path=getParentDir(path)
	logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path	imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
docinfo['imageURL'] = imageUrl	docinfo['imageURL'] = imageUrl

docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo)	#path ist the path to the images it assumes that the index.meta file is one level higher.
docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo)	docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
	docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
return docinfo	return docinfo


def getDocinfo(self, mode, url):	def getDocinfo(self, mode, url):
"""returns docinfo depending on mode"""	"""returns docinfo depending on mode"""
logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))	logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
# look for cached docinfo in session	# look for cached docinfo in session
if self.REQUEST.SESSION.has_key('docinfo'):	if self.REQUEST.SESSION.has_key('docinfo'):
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:
logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)	logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
return docinfo	return docinfo
# new docinfo	# new docinfo
docinfo = {'mode': mode, 'url': url}	docinfo = {'mode': mode, 'url': url}
Line 454 class documentViewer(Folder):	Line 668 class documentViewer(Folder):
docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)	docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
elif mode=="imagepath":	elif mode=="imagepath":
docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)	docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
	elif mode=="filepath":
	docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
else:	else:
logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")	logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
raise ValueError("Unknown mode %s"%(mode))	raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))

logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)	logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
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):
"""returns pageinfo with the given parameters"""	"""returns pageinfo with the given parameters"""
pageinfo = {}	pageinfo = {}
current = getInt(current)	current = getInt(current)
Line 474 class documentViewer(Folder):	Line 689 class documentViewer(Folder):
pageinfo['cols'] = cols	pageinfo['cols'] = cols
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=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
	# int(current / grpsize) * grpsize +1))
pageinfo['start'] = start	pageinfo['start'] = start
pageinfo['end'] = start + grpsize	pageinfo['end'] = start + grpsize
if docinfo is not None:	if (docinfo is not None) and ('numPages' in docinfo):
np = int(docinfo['numPages'])	np = int(docinfo['numPages'])
pageinfo['end'] = min(pageinfo['end'], np)	pageinfo['end'] = min(pageinfo['end'], np)
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['tocMode'] = tocMode
	pageinfo['characterNormalization'] =characterNormalization
	#pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')
	pageinfo['query'] = self.REQUEST.get('query',' ')
	pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
	pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
	pageinfo['textPN'] = self.REQUEST.get('textPN','1')
	pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
	pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
	pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
	pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
	toc = int (pageinfo['tocPN'])
	pageinfo['textPages'] =int (toc)

	if 'tocSize_%s'%tocMode in docinfo:
	tocSize = int(docinfo['tocSize_%s'%tocMode])
	tocPageSize = int(pageinfo['tocPageSize'])
	# cached toc
	if tocSize%tocPageSize>0:
	tocPages=tocSize/tocPageSize+1
	else:
	tocPages=tocSize/tocPageSize
	pageinfo['tocPN'] = min (tocPages,toc)
	pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
	pageinfo['sn'] =self.REQUEST.get('sn','')
return pageinfo	return pageinfo

def text(self,mode,url,pn):	def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
"""give text"""
if mode=="texttool": #index.meta with texttool information
(viewerUrl,imagepath,textpath)=parseUrlTextTool(url)

#print textpath
try:
dom = NonvalidatingReader.parseUri(textpath)
except:
return None

list=[]
nodes=dom.xpath("//pb")

node=nodes[int(pn)-1]

p=node

while p.tagName!="p":
p=p.parentNode


endNode=nodes[int(pn)]


e=endNode

while e.tagName!="p":
e=e.parentNode


next=node.parentNode

#sammle s
while next and (next!=endNode.parentNode):
list.append(next)
next=next.nextSibling
list.append(endNode.parentNode)

if p==e:# beide im selben paragraphen
pass
# else:
# next=p
# while next!=e:
# print next,e
# list.append(next)
# next=next.nextSibling
#
# for x in list:
# PrettyPrint(x)
#
# return list
#

def findDigilibUrl(self):
"""try to get the digilib URL from zogilib"""
url = self.imageViewerUrl[:-1] + "/getScalerUrl"
#print urlparse.urlparse(url)[0]
#print urlparse.urljoin(self.absolute_url(),url)
logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0])
logging.info("finddigiliburl: %s"%urlparse.urljoin(self.absolute_url(),url))

try:
if urlparse.urlparse(url)[0]=='': #relative path
url=urlparse.urljoin(self.absolute_url()+"/",url)

scaler = urlopen(url).read()
return scaler.replace("/servlet/Scaler?", "")
except:
return None

def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,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.textViewerUrl=textViewerUrl
self.digilibBaseUrl = digilibBaseUrl	self.digilibBaseUrl = digilibBaseUrl
self.thumbrows = thumbrows	self.thumbrows = thumbrows
self.thumbcols = thumbcols	self.thumbcols = thumbcols
Line 569 class documentViewer(Folder):	Line 737 class documentViewer(Folder):
if RESPONSE is not None:	if RESPONSE is not None:
RESPONSE.redirect('manage_main')	RESPONSE.redirect('manage_main')




# security.declareProtected('View management screens','renameImageForm')

def manage_AddDocumentViewerForm(self):	def manage_AddDocumentViewerForm(self):
"""add the viewer form"""	"""add the viewer form"""
pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)	pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
return pt()	return pt()

def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None):	def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
"""add the viewer"""	"""add the viewer"""
newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl)	newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
self._setObject(id,newObj)	self._setObject(id,newObj)

if RESPONSE is not None:	if RESPONSE is not None:
RESPONSE.redirect('manage_main')	RESPONSE.redirect('manage_main')


##
## DocumentViewerTemplate class	## DocumentViewerTemplate class
##
class DocumentViewerTemplate(ZopePageTemplate):	class DocumentViewerTemplate(ZopePageTemplate):
"""Template for document viewer"""	"""Template for document viewer"""
meta_type="DocumentViewer Template"	meta_type="DocumentViewer Template"

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

Removed from v.1.24
changed lines
	Added in v.1.97