documentViewer/documentViewer.py - diff

Return to documentViewer.py CVS log

Up to [Repository] / documentViewer

Diff for /documentViewer/documentViewer.py between versions 1.69.2.13 and 1.94

version 1.69.2.13, 2010/06/28 10:37:12	version 1.94, 2010/08/24 12:34:32
Line 7 from AccessControl import getSecurityMan	Line 7 from AccessControl import getSecurityMan
from Globals import package_home	from Globals import package_home

from Ft.Xml import EMPTY_NAMESPACE, Parse	from Ft.Xml import EMPTY_NAMESPACE, Parse
from Ft.Xml.Domlette import PrettyPrint, Print	import Ft.Xml.Domlette
import os.path	import os.path
import sys	import sys
import urllib	import urllib
Line 43 def getTextFromNode(nodename):	Line 43 def getTextFromNode(nodename):
def serializeNode(node, encoding='utf-8'):	def serializeNode(node, encoding='utf-8'):
"""returns a string containing node as XML"""	"""returns a string containing node as XML"""
buf = cStringIO.StringIO()	buf = cStringIO.StringIO()
Print(node, stream=buf, encoding=encoding)	Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
s = buf.getvalue()	s = buf.getvalue()
buf.close()	buf.close()
return s	return s
Line 68 def getHttpData(url, data=None, num_trie	Line 68 def getHttpData(url, data=None, num_trie
errmsg = None	errmsg = None
for cnt in range(num_tries):	for cnt in range(num_tries):
try:	try:
logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))	#logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
if sys.version_info < (2, 6):	if sys.version_info < (2, 6):
# set timeout on socket -- ugly :-(	# set timeout on socket -- ugly :-(
import socket	import socket
Line 79 def getHttpData(url, data=None, num_trie	Line 79 def getHttpData(url, data=None, num_trie
# check result?	# check result?
break	break
except urllib2.HTTPError, e:	except urllib2.HTTPError, e:
logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))	#logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
errmsg = str(e)	errmsg = str(e)
# stop trying	# stop trying
break	break
except urllib2.URLError, e:	except urllib2.URLError, e:
logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))	#logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
errmsg = str(e)	errmsg = str(e)
# stop trying	# stop trying
#break	#break
Line 119 class documentViewer(Folder):	Line 119 class documentViewer(Folder):
page_main_images = PageTemplateFile('zpt/page_main_images', globals())	page_main_images = PageTemplateFile('zpt/page_main_images', globals())
page_main_text = PageTemplateFile('zpt/page_main_text', globals())	page_main_text = PageTemplateFile('zpt/page_main_text', globals())
page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())	page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
	page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals())
page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())	page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
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())
Line 145 class documentViewer(Folder):	Line 146 class documentViewer(Folder):
self._setObject('template',templateFolder) # old style	self._setObject('template',templateFolder) # old style
try:	try:
import MpdlXmlTextServer	import MpdlXmlTextServer
textServer = MpdlXmlTextServer(id='fulltextclient')	textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
#templateFolder['fulltextclient'] = xmlRpcClient	#templateFolder['fulltextclient'] = xmlRpcClient
templateFolder._setObject('fulltextclient',textServer)	templateFolder._setObject('fulltextclient',textServer)
except Exception, e:	except Exception, e:
Line 172 class documentViewer(Folder):	Line 173 class documentViewer(Folder):
"""get search"""	"""get search"""
return self.template.fulltextclient.getSearch(**args)	return self.template.fulltextclient.getSearch(**args)

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

def getTranslate(self, **args):	def getTranslate(self, **args):
"""get translate"""	"""get translate"""
Line 202 class documentViewer(Folder):	Line 203 class documentViewer(Folder):
@param viewMode: if images display images, if text display text, default is images (text,images or auto)	@param viewMode: if images display images, if text display text, default is images (text,images or auto)

'''	'''
logging.debug("HHHHHHHHHHHHHH:load the rss")	#logging.debug("HHHHHHHHHHHHHH:load the rss")
logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))	#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'):
# create template folder if it doesn't exist	# create template folder if it doesn't exist
Line 232 class documentViewer(Folder):	Line 233 class documentViewer(Folder):
@param url: url which contains display information	@param url: url which contains display information
@param viewMode: if images display images, if text display text, default is auto (text,images or auto)	@param viewMode: if images display images, if text display text, default is auto (text,images or auto)
@param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)	@param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
	@param characterNormalization type of text display (reg, norm, none)
@param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)	@param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
'''	'''

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

if not hasattr(self, 'template'):	if not hasattr(self, 'template'):
# this won't work	# this won't work
Line 243 class documentViewer(Folder):	Line 245 class documentViewer(Folder):
return "ERROR: template folder missing!"	return "ERROR: template folder missing!"

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

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


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

if viewMode=="auto": # automodus gewaehlt	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.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
viewMode="text_dict"	viewMode="text_dict"
else:	else:
viewMode="images"	viewMode="images"
Line 267 class documentViewer(Folder):	Line 268 class documentViewer(Folder):
ret=""	ret=""
if mk is None:	if mk is None:
return ""	return ""
if type(mk) is not ListType:	if not isinstance(mk, list):
mk=[mk]	mk=[mk]
for m in mk:	for m in mk:
ret+="mk=%s"%m	ret+="mk=%s"%m
Line 306 class documentViewer(Folder):	Line 307 class documentViewer(Folder):
params["url"] = getParentDir(params["url"])	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

Line 321 class documentViewer(Folder):	Line 323 class documentViewer(Folder):
params[param] = str(val)	params[param] = str(val)

# quote values and assemble into query string	# quote values and assemble into query string
logging.debug("XYXXXXX: %s"%repr(params.items()))	#logging.debug("XYXXXXX: %s"%repr(params.items()))
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()])
url=self.REQUEST['URL1']+"?"+ps	url=self.REQUEST['URL1']+"?"+ps
return url	return url
Line 340 class documentViewer(Folder):	Line 342 class documentViewer(Folder):
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)
logging.debug("documentViewer (accessOK) 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':
logging.debug("documentViewer (accessOK) 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

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


Line 368 class documentViewer(Folder):	Line 371 class documentViewer(Folder):

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

logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))	#logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))

txt = getHttpData(infoUrl)	txt = getHttpData(infoUrl)
if txt is None:	if txt is None:
Line 376 class documentViewer(Folder):	Line 379 class documentViewer(Folder):

dom = Parse(txt)	dom = Parse(txt)
sizes=dom.xpath("//dir/size")	sizes=dom.xpath("//dir/size")
logging.debug("documentViewer (getparamfromdigilib) 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]))
Line 402 class documentViewer(Folder):	Line 405 class documentViewer(Folder):
if not metaUrl.endswith("index.meta"):	if not metaUrl.endswith("index.meta"):
metaUrl += "/index.meta"	metaUrl += "/index.meta"

logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)	#logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)
txt=getHttpData(metaUrl)	txt=getHttpData(metaUrl)
if txt is None:	if txt is None:
raise IOError("Unable to read index meta from %s"%(url))	raise IOError("Unable to read index meta from %s"%(url))
Line 432 class documentViewer(Folder):	Line 435 class documentViewer(Folder):

def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):	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"""
logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))	#logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))

access = None	access = None

Line 456 class documentViewer(Folder):	Line 459 class documentViewer(Folder):

def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):	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"""
logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))	#logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))

if docinfo is None:	if docinfo is None:
docinfo = {}	docinfo = {}
Line 466 class documentViewer(Folder):	Line 469 class documentViewer(Folder):
path=getParentDir(path)	path=getParentDir(path)
dom = self.getIndexMeta(path)	dom = self.getIndexMeta(path)

logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))	#logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
# put in all raw bib fields as dict "bib"	# put in all raw bib fields as dict "bib"
bib = dom.xpath("//bib/*")	bib = dom.xpath("//bib/*")
if bib and len(bib)>0:	if bib and len(bib)>0:
Line 497 class documentViewer(Folder):	Line 500 class documentViewer(Folder):
try:	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	except: pass
logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)	#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:
Line 508 class documentViewer(Folder):	Line 511 class documentViewer(Folder):

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"""
logging.debug("documentViewer (getdocinfofromtexttool) 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:
Line 535 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
logging.warning("documentViewer (getdocinfofromtexttool) 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 588 class documentViewer(Folder):	Line 591 class documentViewer(Folder):
docinfo['textURLPath'] = textUrl	docinfo['textURLPath'] = textUrl
if not docinfo['imagePath']:	if not docinfo['imagePath']:
# text-only, no page images	# text-only, no page images
docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht	docinfo = self.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
Line 629 class documentViewer(Folder):	Line 632 class documentViewer(Folder):

def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):	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."""
logging.debug("documentViewer (getdocinfofromimagepath) 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","")
Line 639 class documentViewer(Folder):	Line 642 class documentViewer(Folder):
pathorig=path	pathorig=path
for x in range(cut):	for x in range(cut):
path=getParentDir(path)	path=getParentDir(path)
logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+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

Line 651 class documentViewer(Folder):	Line 654 class documentViewer(Folder):

def getDocinfo(self, mode, url):	def getDocinfo(self, mode, url):
"""returns docinfo depending on mode"""	"""returns docinfo depending on mode"""
logging.debug("documentViewer (getdocinfo) 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:
logging.debug("documentViewer (getdocinfo) 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 668 class documentViewer(Folder):	Line 671 class documentViewer(Folder):
elif mode=="filepath":	elif mode=="filepath":
docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)	docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
else:	else:
logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)	#logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))	raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))

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

Line 698 class documentViewer(Folder):	Line 701 class documentViewer(Folder):
pageinfo['numgroups'] += 1	pageinfo['numgroups'] += 1
pageinfo['viewMode'] = viewMode	pageinfo['viewMode'] = viewMode
pageinfo['tocMode'] = tocMode	pageinfo['tocMode'] = tocMode
	pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','')
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 722 class documentViewer(Folder):	Line 726 class documentViewer(Folder):
pageinfo['sn'] =self.REQUEST.get('sn','')	pageinfo['sn'] =self.REQUEST.get('sn','')
return pageinfo	return pageinfo

def getOverview(self, mode="text" , docinfo=None, pageinfo=None, url=None, viewMode="auto", start=None,pn=1,textURLPath="auto", **args):
"""overview mode all thumbnails in one window"""
docinfo = self.getDocinfo(mode=mode,url=url)
pageinfo = self.getPageinfo(current=pn,docinfo=docinfo)
return (docinfo, pageinfo, viewMode)

def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):	def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
"""init document viewer"""	"""init document viewer"""
self.title=title	self.title=title
Line 769 def manage_addDocumentViewerTemplate(sel	Line 767 def manage_addDocumentViewerTemplate(sel
self._setObject(id, DocumentViewerTemplate(id))	self._setObject(id, DocumentViewerTemplate(id))
ob = getattr(self, id)	ob = getattr(self, id)
txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()	txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
logging.info("txt %s:"%txt)	#logging.info("txt %s:"%txt)
ob.pt_edit(txt,"text/html")	ob.pt_edit(txt,"text/html")
if title:	if title:
ob.pt_setTitle(title)	ob.pt_setTitle(title)

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

Removed from v.1.69.2.13
changed lines
	Added in v.1.94