documentViewer/documentViewer.py - diff

Return to documentViewer.py CVS log

Up to [Repository] / documentViewer

Diff for /documentViewer/documentViewer.py between versions 1.97 and 1.166

version 1.97, 2010/08/24 13:27:07	version 1.166, 2011/01/20 16:04:21
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
Line 16 import logging	Line 17 import logging
import math	import math
import urlparse	import urlparse
import cStringIO	import cStringIO
	import re
	import string

def logger(txt,method,txt2):	def logger(txt,method,txt2):
"""logging"""	"""logging"""
Line 48 def serializeNode(node, encoding='utf-8'	Line 51 def serializeNode(node, encoding='utf-8'
buf.close()	buf.close()
return s	return s

	def browserCheck(self):
	"""check the browsers request to find out the browser type"""
	bt = {}
	ua = self.REQUEST.get_header("HTTP_USER_AGENT")
	bt['ua'] = ua
	bt['isIE'] = False
	bt['isN4'] = False
	bt['versFirefox']=""
	bt['versIE']=""
	bt['versSafariChrome']=""
	bt['versOpera']=""

	if string.find(ua, 'MSIE') > -1:
	bt['isIE'] = True
	else:
	bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
	# Safari oder Chrome identification
	try:
	nav = ua[string.find(ua, '('):]
	nav1=ua[string.find(ua,')'):]
	nav2=nav1[string.find(nav1,'('):]
	nav3=nav2[string.find(nav2,')'):]
	ie = string.split(nav, "; ")[1]
	ie1 =string.split(nav1, " ")[2]
	ie2 =string.split(nav3, " ")[1]
	ie3 =string.split(nav3, " ")[2]
	if string.find(ie3, "Safari") >-1:
	bt['versSafariChrome']=string.split(ie2, "/")[1]
	except: pass
	# IE identification
	try:
	nav = ua[string.find(ua, '('):]
	ie = string.split(nav, "; ")[1]
	if string.find(ie, "MSIE") > -1:
	bt['versIE'] = string.split(ie, " ")[1]
	except:pass
	# Firefox identification
	try:
	nav = ua[string.find(ua, '('):]
	nav1=ua[string.find(ua,')'):]
	if string.find(ie1, "Firefox") >-1:
	nav5= string.split(ie1, "/")[1]
	logging.debug("FIREFOX: %s"%(nav5))
	bt['versFirefox']=nav5[0:3]
	except:pass
	#Opera identification
	try:
	if string.find(ua,"Opera") >-1:
	nav = ua[string.find(ua, '('):]
	nav1=nav[string.find(nav,')'):]
	bt['versOpera']=string.split(nav1,"/")[2]
	except:pass

	bt['isMac'] = string.find(ua, 'Macintosh') > -1
	bt['isWin'] = string.find(ua, 'Windows') > -1
	bt['isIEWin'] = bt['isIE'] and bt['isWin']
	bt['isIEMac'] = bt['isIE'] and bt['isMac']
	bt['staticHTML'] = False

	return bt


def getParentDir(path):	def getParentDir(path):
"""returns pathname shortened by one"""	"""returns pathname shortened by one"""
Line 117 class documentViewer(Folder):	Line 181 class documentViewer(Folder):
toc_text = PageTemplateFile('zpt/toc_text', globals())	toc_text = PageTemplateFile('zpt/toc_text', globals())
toc_figures = PageTemplateFile('zpt/toc_figures', globals())	toc_figures = PageTemplateFile('zpt/toc_figures', globals())
page_main_images = PageTemplateFile('zpt/page_main_images', globals())	page_main_images = PageTemplateFile('zpt/page_main_images', globals())
	page_main_double = PageTemplateFile('zpt/page_main_double', 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_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())
	page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', 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())	info_xml = PageTemplateFile('zpt/info_xml', globals())
Line 166 class documentViewer(Folder):	Line 232 class documentViewer(Folder):
return self.template.fulltextclient.getTextPage(**args)	return self.template.fulltextclient.getTextPage(**args)

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

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

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

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

def getTranslate(self, **args):	def getTranslate(self, **args):
"""get translate"""	"""get translate"""
Line 214 class documentViewer(Folder):	Line 284 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
if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert	if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
viewMode="text"	viewMode="text"
else:	else:
viewMode="images"	viewMode="images"
Line 226 class documentViewer(Folder):	Line 298 class documentViewer(Folder):
return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)	return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)

security.declareProtected('View','index_html')	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=""):	def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
'''	'''
view it	view it
@param mode: defines how to access the document behind url	@param mode: defines how to access the document behind url
Line 254 class documentViewer(Folder):	Line 326 class documentViewer(Folder):
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.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
viewMode="text_dict"	viewMode="text_dict"
else:	else:
viewMode="images"	viewMode="images"

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

	if (docinfo.get('textURLPath',None)):
	page = self.getTextPage(docinfo=docinfo, pageinfo=pageinfo)
	pageinfo['textPage'] = page
pt = getattr(self.template, 'viewer_main')	pt = getattr(self.template, 'viewer_main')
return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))	return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))

Line 275 class documentViewer(Folder):	Line 350 class documentViewer(Folder):
return ret	return ret


	def getBrowser(self):
	"""getBrowser the version of browser """
	bt = browserCheck(self)
	logging.debug("BROWSER VERSION: %s"%(bt))
	return bt

def findDigilibUrl(self):	def findDigilibUrl(self):
"""try to get the digilib URL from zogilib"""	"""try to get the digilib URL from zogilib"""
url = self.template.zogilib.getDLBaseUrl()	url = self.template.zogilib.getDLBaseUrl()
Line 292 class documentViewer(Folder):	Line 373 class documentViewer(Folder):
else:	else:
return style	return style

def getLink(self,param=None,val=None):	def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
"""link to documentviewer with parameter param set to val"""	"""returns URL to documentviewer with parameter param set to val or from dict params"""
params=self.REQUEST.form.copy()	# copy existing request params
	urlParams=self.REQUEST.form.copy()
	# change single param
if param is not None:	if param is not None:
if val is None:	if val is None:
if params.has_key(param):	if urlParams.has_key(param):
del params[param]	del urlParams[param]
else:	else:
params[param] = str(val)	urlParams[param] = str(val)

if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath	# change more params
params["mode"] = "imagepath"	if params is not None:
params["url"] = getParentDir(params["url"])	for k in params.keys():
	v = params[k]
# quote values and assemble into query string	if v is None:
#ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])	# val=None removes param
ps = urllib.urlencode(params)	if urlParams.has_key(k):
url=self.REQUEST['URL1']+"?"+ps	del urlParams[k]

	else:
	urlParams[k] = v

	# FIXME: does this belong here?
	if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
	urlParams["mode"] = "imagepath"
	urlParams["url"] = getParentDir(urlParams["url"])

	# quote values and assemble into query string (not escaping '/')
	ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
	#ps = urllib.urlencode(urlParams)
	if baseUrl is None:
	baseUrl = self.REQUEST['URL1']

	url = "%s?%s"%(baseUrl, ps)
return url	return url

def getLinkAmp(self,param=None,val=None):
"""link to documentviewer with parameter param set to val"""
params=self.REQUEST.form.copy()
if param is not None:
if val is None:
if params.has_key(param):
del params[param]
else:
params[param] = str(val)

# quote values and assemble into query string	def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
logging.debug("XYXXXXX: %s"%repr(params.items()))	"""link to documentviewer with parameter param set to val"""
ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])	return self.getLink(param, val, params, baseUrl, '&')
url=self.REQUEST['URL1']+"?"+ps
return url

def getInfo_xml(self,url,mode):	def getInfo_xml(self,url,mode):
"""returns info about the document as XML"""	"""returns info about the document as XML"""
Line 338 class documentViewer(Folder):	Line 426 class documentViewer(Folder):
pt = getattr(self.template, 'info_xml')	pt = getattr(self.template, 'info_xml')
return pt(docinfo=docinfo)	return pt(docinfo=docinfo)

	def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
	"""returns new option state"""
	if not self.REQUEST.SESSION.has_key(optionName):
	# not in session -- initial
	opt = {'lastState': newState, 'state': initialState}
	else:
	opt = self.REQUEST.SESSION.get(optionName)
	if opt['lastState'] != newState:
	# state in session has changed -- toggle
	opt['state'] = not opt['state']
	opt['lastState'] = newState

	self.REQUEST.SESSION[optionName] = opt
	return opt['state']

def isAccessible(self, docinfo):	def isAccessible(self, docinfo):
"""returns if access to the resource is granted"""	"""returns if access to the resource is granted"""
Line 390 class documentViewer(Folder):	Line 492 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 517 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 564 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 586 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 610 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 632 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 654 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 589 class documentViewer(Folder):	Line 726 class documentViewer(Folder):
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.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)


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 674 class documentViewer(Folder):	Line 814 class documentViewer(Folder):
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))

	# FIXME: fake texturlpath
	if not docinfo.has_key('textURLPath'):
	docinfo['textURLPath'] = None

logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)	logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
	#logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
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):
"""returns pageinfo with the given parameters"""	"""returns pageinfo with the given parameters"""
pageinfo = {}	pageinfo = {}
current = getInt(current)	current = getInt(current)

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 847 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'] = self.REQUEST.get('characterNormalization','reg')
#pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')	pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','')
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 711 class documentViewer(Folder):	Line 857 class documentViewer(Folder):
pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')	pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')	pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')	pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')

toc = int (pageinfo['tocPN'])	toc = int (pageinfo['tocPN'])
pageinfo['textPages'] =int (toc)	pageinfo['textPages'] =int (toc)



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.1.166