documentViewer/documentViewer.py - diff

Return to documentViewer.py CVS log

Up to [Repository] / documentViewer

Diff for /documentViewer/documentViewer.py between versions 1.97 and 1.140

version 1.97, 2010/08/24 13:27:07	version 1.140, 2010/10/18 11:51:42
Line 5 from Products.PageTemplates.PageTemplate	Line 5 from Products.PageTemplates.PageTemplate
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 Products.zogiLib.zogiLib import browserCheck

from Ft.Xml import EMPTY_NAMESPACE, Parse	from Ft.Xml import EMPTY_NAMESPACE, Parse
import Ft.Xml.Domlette	import Ft.Xml.Domlette
import os.path	import os.path
import sys	import sys
import urllib	import urllib

import urllib2	import urllib2
import logging	import logging
import math	import math
import urlparse	import urlparse
import cStringIO	import cStringIO
	import re


def logger(txt,method,txt2):	def logger(txt,method,txt2):
"""logging"""	"""logging"""
Line 48 def serializeNode(node, encoding='utf-8'	Line 52 def serializeNode(node, encoding='utf-8'
buf.close()	buf.close()
return s	return s

	def getBrowserType(self):
	"""get browser type object"""
	if self.REQUEST.SESSION.has_key('browserType'):
	return self.REQUEST.SESSION['browserType']
	else:
	bt = browserCheck(self)
	self.REQUEST.SESSION.set('browserType', bt)
	logging.debug("documentViewer (BROWSER TYPE) bt %s"%bt)
	return bt


def getParentDir(path):	def getParentDir(path):
"""returns pathname shortened by one"""	"""returns pathname shortened by one"""
Line 173 class documentViewer(Folder):	Line 187 class documentViewer(Folder):
"""get search"""	"""get search"""
return self.template.fulltextclient.getSearch(**args)	return self.template.fulltextclient.getSearch(**args)

	def getGisPlaces(self, **args):
	"""get gis places"""
	return self.template.fulltextclient.getGisPlaces(**args)

	def getAllGisPlaces(self, **args):
	"""get all gis places """
	return self.template.fulltextclient.getAllGisPlaces(**args)

	def getOrigPages(self, **args):
	"""get original page number """
	return self.template.fulltextclient.getOrigPages(**args)

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

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

def getTranslate(self, **args):	def getTranslate(self, **args):
"""get translate"""	"""get translate"""
return self.template.fulltextclient.getTranslate(**args)	return self.template.fulltextclient.getTranslate(**args)
Line 214 class documentViewer(Folder):	Line 244 class documentViewer(Folder):
self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.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)
	#pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)	pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
	''' ZDES '''
pt = getattr(self.template, 'thumbs_main_rss')	pt = getattr(self.template, 'thumbs_main_rss')

if viewMode=="auto": # automodus gewaehlt	if viewMode=="auto": # automodus gewaehlt
Line 390 class documentViewer(Folder):	Line 422 class documentViewer(Folder):

return docinfo	return docinfo

	def getIndexMetaPath(self,url):
	"""gib nur den Pfad zurueck"""
	regexp = re.compile(r".(experimental\|permanent)/(.)")
	regpath = regexp.match(url)
	if (regpath==None):
	return ""
	logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))
	return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))



	def getIndexMetaUrl(self,url):
	"""returns utr of index.meta document at url"""

def getIndexMeta(self, url):
"""returns dom of index.meta document at url"""
dom = None
metaUrl = None	metaUrl = None
if url.startswith("http://"):	if url.startswith("http://"):
# real URL	# real URL
Line 405 class documentViewer(Folder):	Line 447 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)	return metaUrl

	def getDomFromIndexMeta(self, url):
	"""get dom from index meta"""
	dom = None
	metaUrl = self.getIndexMetaUrl(url)

	logging.debug("(getDomFromIndexMeta): 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 445 class documentViewer(Folder):	Line 494 class documentViewer(Folder):
if dom is None:	if dom is None:
for x in range(cut):	for x in range(cut):
path=getParentDir(path)	path=getParentDir(path)
dom = self.getIndexMeta(path)	dom = self.getDomFromIndexMeta(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 467 class documentViewer(Folder):	Line 516 class documentViewer(Folder):
if dom is None:	if dom is None:
for x in range(cut):	for x in range(cut):
path=getParentDir(path)	path=getParentDir(path)
dom = self.getIndexMeta(path)	dom = self.getDomFromIndexMeta(path)

	docinfo['indexMetaPath']=self.getIndexMetaPath(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"
Line 489 class documentViewer(Folder):	Line 540 class documentViewer(Folder):
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	docinfo['bib_type'] = bibtype
bibmap=metaData.generateMappingForType(bibtype)	bibmap=metaData.generateMappingForType(bibtype)
	logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
	logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(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:	try:
Line 509 class documentViewer(Folder):	Line 562 class documentViewer(Folder):
return docinfo	return docinfo


	def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
	"""gets name info from the index.meta file at path or given by dom"""
	if docinfo is None:
	docinfo = {}

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

	docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
	logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
	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"""
logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))	logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
Line 517 class documentViewer(Folder):	Line 584 class documentViewer(Folder):
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:
dom = self.getIndexMeta(url)	dom = self.getDomFromIndexMeta(url)

archivePath = None	archivePath = None
archiveName = None	archiveName = None
Line 591 class documentViewer(Folder):	Line 658 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)	docinfo = self.getNumTextPages(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
	docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
	docinfo =self.getOrigPages(docinfo=docinfo)

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 fuer die Metadaten	# presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
Line 675 class documentViewer(Folder):	Line 744 class documentViewer(Folder):
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

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, viewMode=None, tocMode=None,characterNormalization="",originalPage=None):
"""returns pageinfo with the given parameters"""	"""returns pageinfo with the given parameters"""
pageinfo = {}	pageinfo = {}
current = getInt(current)	current = getInt(current)

	pageinfo ['originalPage'] = self.getOrigPages(docinfo=docinfo,pageinfo=pageinfo)
pageinfo['current'] = current	pageinfo['current'] = current
rows = int(rows or self.thumbrows)	rows = int(rows or self.thumbrows)
pageinfo['rows'] = rows	pageinfo['rows'] = rows
Line 701 class documentViewer(Folder):	Line 773 class documentViewer(Folder):
pageinfo['numgroups'] += 1	pageinfo['numgroups'] += 1
pageinfo['viewMode'] = viewMode	pageinfo['viewMode'] = viewMode
pageinfo['tocMode'] = tocMode	pageinfo['tocMode'] = tocMode
pageinfo['characterNormalization'] =characterNormalization	#pageinfo['characterNormalization'] =characterNormalization
#pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')	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 714 class documentViewer(Folder):	Line 786 class documentViewer(Folder):
toc = int (pageinfo['tocPN'])	toc = int (pageinfo['tocPN'])
pageinfo['textPages'] =int (toc)	pageinfo['textPages'] =int (toc)

	logging.debug("originalPage: %s"%originalPage)

if 'tocSize_%s'%tocMode in docinfo:	if 'tocSize_%s'%tocMode in docinfo:
tocSize = int(docinfo['tocSize_%s'%tocMode])	tocSize = int(docinfo['tocSize_%s'%tocMode])
tocPageSize = int(pageinfo['tocPageSize'])	tocPageSize = int(pageinfo['tocPageSize'])

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

Removed from v.1.97
changed lines
	Added in v.1.140