documentViewer/documentViewer.py - diff

Return to documentViewer.py CVS log

Up to [Repository] / documentViewer

Diff for /documentViewer/documentViewer.py between versions 1.65.2.2 and 1.69.2.1

version 1.65.2.2, 2010/06/18 19:41:28	version 1.69.2.1, 2010/06/14 10:49:48
Line 2	Line 2
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 Products.PythonScripts.standard import url_quote
from AccessControl import ClassSecurityInfo	from AccessControl import ClassSecurityInfo
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
	from xml.dom.minidom import parse, parseString

	from extraFunction import *


	import Ft.Xml.XPath
	import cStringIO
	import xmlrpclib
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 math

import urlparse	import urlparse
import cStringIO	from types import *

def logger(txt,method,txt2):	def logger(txt,method,txt2):
"""logging"""	"""logging"""
Line 43 def getTextFromNode(nodename):	Line 55 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()
Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)	Print(node, stream=buf, encoding=encoding)
s = buf.getvalue()	s = buf.getvalue()
buf.close()	buf.close()
return s	return s
Line 54 def getParentDir(path):	Line 66 def getParentDir(path):
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


##	##
## documentViewer class	## documentViewer class
##	##
class documentViewer(Folder):	class documentViewer(Folder, extraFunction):
"""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 144 class documentViewer(Folder):	Line 123 class documentViewer(Folder):
#self['template'] = templateFolder # Zope-2.12 style	#self['template'] = templateFolder # Zope-2.12 style
self._setObject('template',templateFolder) # old style	self._setObject('template',templateFolder) # old style
try:	try:
import MpdlXmlTextServer	from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy
textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)	xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False)
#templateFolder['fulltextclient'] = xmlRpcClient	#templateFolder['fulltextclient'] = xmlRpcClient
templateFolder._setObject('fulltextclient',textServer)	templateFolder._setObject('fulltextclient',xmlRpcClient)
except Exception, e:	except Exception, e:
logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))	logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e))
try:	try:
from Products.zogiLib.zogiLib import zogiLib	from Products.zogiLib.zogiLib import zogiLib
zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")	zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
Line 159 class documentViewer(Folder):	Line 138 class documentViewer(Folder):
logging.error("Unable to create zogiLib for zogilib: "+str(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','thumbs_rss')	security.declareProtected('View','thumbs_rss')
def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):	def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
'''	'''
Line 217 class documentViewer(Folder):	Line 162 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.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
viewMode="text"	viewMode="text"
else:	else:
viewMode="images"	viewMode="images"
Line 243 class documentViewer(Folder):	Line 188 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://digilib.mpiwg-berlin.mpg.de/digitallibrary"	self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.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.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
viewMode="text_dict"	viewMode="text_dict"
else:	else:
viewMode="images"	viewMode="images"
Line 266 class documentViewer(Folder):	Line 212 class documentViewer(Folder):
ret=""	ret=""
if mk is None:	if mk is None:
return ""	return ""
if not isinstance(mk, list):	if type(mk) is not ListType:
mk=[mk]	mk=[mk]
for m in mk:	for m in mk:
ret+="mk=%s"%m	ret+="mk=%s"%m
Line 305 class documentViewer(Folder):	Line 251 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 266 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.info("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 285 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)	logger("documentViewer (accessOK)", logging.INFO, "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")	logger("documentViewer (accessOK)", logging.INFO, "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
Line 353 class documentViewer(Folder):	Line 298 class documentViewer(Folder):
else:	else:
return False	return False

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


def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):	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 = {}

Line 368 class documentViewer(Folder):	Line 314 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))	logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))

txt = getHttpData(infoUrl)	for cnt in range(num_retries):
if txt is None:	try:
	# 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")
logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)	logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)

if sizes:	if sizes:
docinfo['numPages'] = int(getTextFromNode(sizes[0]))	docinfo['numPages'] = int(getTextFromNode(sizes[0]))
Line 390 class documentViewer(Folder):	Line 342 class documentViewer(Folder):

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 401 class documentViewer(Folder):	Line 354 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"
	logging.debug("METAURL: %s"%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 (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])

logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)	if dom is None:
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 422 class documentViewer(Folder):	Line 383 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,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))	logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))

access = None	access = None

Line 508 class documentViewer(Folder):	Line 477 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))	logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "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 523 class documentViewer(Folder):	Line 492 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:
logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))	logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "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 535 class documentViewer(Folder):	Line 504 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))	logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "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 569 class documentViewer(Folder):	Line 538 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])
Line 581 class documentViewer(Folder):	Line 549 class documentViewer(Folder):

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

# new style text-url-path
textUrls = dom.xpath("//texttool/text-url-path")	textUrls = dom.xpath("//texttool/text-url-path")
if textUrls and (len(textUrls) > 0):	if textUrls and (len(textUrls) > 0):
textUrl = getTextFromNode(textUrls[0])	textUrl = getTextFromNode(textUrls[0])
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)	docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht

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 596 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))	logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"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 606 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.error("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 618 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))	logger("documentViewer (getdocinfo)", logging.INFO,"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)	logger("documentViewer (getdocinfo)", logging.INFO,"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 635 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)	logger("documentViewer (getdocinfo)", logging.ERROR,"unknown 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)	logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
self.REQUEST.SESSION['docinfo'] = docinfo	self.REQUEST.SESSION['docinfo'] = docinfo
return docinfo	return docinfo

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

Removed from v.1.65.2.2
changed lines
	Added in v.1.69.2.1