version 1.66, 2010/06/01 14:31:26
|
version 1.175.2.13, 2011/08/01 17:30:38
|
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 |
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 import EMPTY_NAMESPACE, Parse |
from Ft.Xml.Domlette import PrettyPrint, Print |
#import Ft.Xml.Domlette |
from Ft.Xml import EMPTY_NAMESPACE, Parse |
|
|
|
from xml.dom.minidom import parse, parseString |
|
|
|
|
import xml.etree.ElementTree as ET |
|
|
|
|
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 logging |
import logging |
import math |
import math |
|
|
import urlparse |
import urlparse |
from types import * |
import re |
|
import string |
|
|
|
from SrvTxtUtils import getInt, getText, getHttpData |
|
|
def logger(txt,method,txt2): |
def logger(txt,method,txt2): |
"""logging""" |
"""logging""" |
logging.info(txt+ txt2) |
logging.info(txt+ txt2) |
|
|
|
|
def getInt(number, default=0): |
def serializeNode(node, encoding="utf-8"): |
"""returns always an int (0 in case of problems)""" |
|
try: |
|
return int(number) |
|
except: |
|
return int(default) |
|
|
|
def getTextFromNode(nodename): |
|
"""get the cdata content of a node""" |
|
if nodename is None: |
|
return "" |
|
nodelist=nodename.childNodes |
|
rc = "" |
|
for node in nodelist: |
|
if node.nodeType == node.TEXT_NODE: |
|
rc = rc + node.data |
|
return rc |
|
|
|
def serializeNode(node, encoding='utf-8'): |
|
"""returns a string containing node as XML""" |
"""returns a string containing node as XML""" |
buf = cStringIO.StringIO() |
s = ET.tostring(node) |
Print(node, stream=buf, encoding=encoding) |
|
s = buf.getvalue() |
|
buf.close() |
|
return s |
|
|
|
|
# 4Suite: |
|
# stream = cStringIO.StringIO() |
|
# Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) |
|
# s = stream.getvalue() |
|
# stream.close() |
|
return s |
|
|
def getParentDir(path): |
def browserCheck(self): |
"""returns pathname shortened by one""" |
"""check the browsers request to find out the browser type""" |
return '/'.join(path.split('/')[0:-1]) |
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 |
|
|
import socket |
bt['isMac'] = string.find(ua, 'Macintosh') > -1 |
|
bt['isWin'] = string.find(ua, 'Windows') > -1 |
def urlopen(url,timeout=2): |
bt['isIEWin'] = bt['isIE'] and bt['isWin'] |
"""urlopen mit timeout""" |
bt['isIEMac'] = bt['isIE'] and bt['isMac'] |
socket.setdefaulttimeout(timeout) |
bt['staticHTML'] = False |
ret=urllib.urlopen(url) |
|
socket.setdefaulttimeout(5) |
return bt |
return ret |
|
|
def getParentPath(path, cnt=1): |
|
"""returns pathname shortened by cnt""" |
|
# make sure path doesn't end with / |
|
path = path.rstrip('/') |
|
# split by /, shorten, and reassemble |
|
return '/'.join(path.split('/')[0:-cnt]) |
|
|
|
|
## |
## |
Line 80 def urlopen(url,timeout=2):
|
Line 111 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 89 class documentViewer(Folder):
|
Line 118 class documentViewer(Folder):
|
{'label':'main config','action':'changeDocumentViewerForm'}, |
{'label':'main config','action':'changeDocumentViewerForm'}, |
) |
) |
|
|
|
metadataService = None |
|
"""MetaDataFolder instance""" |
|
|
# templates and forms |
# templates and forms |
viewer_main = PageTemplateFile('zpt/viewer_main', globals()) |
viewer_main = PageTemplateFile('zpt/viewer_main', globals()) |
toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals()) |
toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals()) |
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_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()) |
|
|
|
|
thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
security.declareProtected('View management screens','changeDocumentViewerForm') |
|
changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
|
|
|
|
|
def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
Line 121 class documentViewer(Folder):
|
Line 155 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: |
from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy |
import MpdlXmlTextServer |
xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False) |
textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) |
#templateFolder['fulltextclient'] = xmlRpcClient |
#templateFolder['fulltextclient'] = xmlRpcClient |
templateFolder._setObject('fulltextclient',xmlRpcClient) |
templateFolder._setObject('fulltextclient',textServer) |
except Exception, e: |
except Exception, e: |
logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e)) |
logging.error("Unable to create MpdlXmlTextServer 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 135 class documentViewer(Folder):
|
Line 170 class documentViewer(Folder):
|
except Exception, e: |
except Exception, e: |
logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
|
|
|
try: |
|
# assume MetaDataFolder instance is called metadata |
|
self.metadataService = getattr(self, 'metadata') |
|
except Exception, e: |
|
logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) |
|
|
|
|
|
# proxy text server methods to fulltextclient |
|
def getTextPage(self, **args): |
|
"""get page""" |
|
return self.template.fulltextclient.getTextPage(**args) |
|
|
|
def getOrigPages(self, **args): |
|
"""get page""" |
|
return self.template.fulltextclient.getOrigPages(**args) |
|
|
|
def getOrigPagesNorm(self, **args): |
|
"""get page""" |
|
return self.template.fulltextclient.getOrigPagesNorm(**args) |
|
|
|
def getQuery(self, **args): |
|
"""get query in search""" |
|
return self.template.fulltextclient.getQuery(**args) |
|
|
|
def getSearch(self, **args): |
|
"""get search""" |
|
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 getTranslate(self, **args): |
|
"""get translate""" |
|
return self.template.fulltextclient.getTranslate(**args) |
|
|
|
def getLemma(self, **args): |
|
"""get lemma""" |
|
return self.template.fulltextclient.getLemma(**args) |
|
|
|
def getLemmaQuery(self, **args): |
|
"""get query""" |
|
return self.template.fulltextclient.getLemmaQuery(**args) |
|
|
|
def getLex(self, **args): |
|
"""get lex""" |
|
return self.template.fulltextclient.getLex(**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 146 class documentViewer(Folder):
|
Line 241 class documentViewer(Folder):
|
|
|
''' |
''' |
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)) |
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'): |
# create template folder if it doesn't exist |
# create template folder if it doesn't exist |
Line 156 class documentViewer(Folder):
|
Line 251 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.get("textURL",'') and self.textViewerUrl: #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" |
|
|
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): |
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 |
@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 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)) |
|
|
Line 186 class documentViewer(Folder):
|
Line 283 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) |
|
|
pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) |
# auto viewMode: text_dict if text else images |
|
if viewMode=="auto": |
if viewMode=="auto": # automodus gewaehlt |
if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): |
if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert |
viewMode="text_dict" |
viewMode="text" |
|
else: |
else: |
viewMode="images" |
viewMode="images" |
|
|
|
pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, tocMode=tocMode) |
|
|
|
if viewMode != 'images' and docinfo.get('textURLPath', None): |
|
# get full text page |
|
page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo) |
|
pageinfo['textPage'] = page |
|
|
|
# get template /template/viewer_main |
pt = getattr(self.template, 'viewer_main') |
pt = getattr(self.template, 'viewer_main') |
|
# and execute with parameters |
return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) |
|
|
def generateMarks(self,mk): |
def generateMarks(self,mk): |
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 |
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() |
return url |
return url |
|
|
|
def getDocumentViewerURL(self): |
|
"""returns the URL of this instance""" |
|
return self.absolute_url() |
|
|
def getStyle(self, idx, selected, style=""): |
def getStyle(self, idx, selected, style=""): |
"""returns a string with the given style and append 'sel' if path == selected.""" |
"""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)) |
#logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) |
Line 230 class documentViewer(Folder):
|
Line 344 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) |
|
|
|
# change more params |
|
if params is not None: |
|
for k in params.keys(): |
|
v = params[k] |
|
if v is None: |
|
# val=None removes param |
|
if urlParams.has_key(k): |
|
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"] = getParentPath(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'] |
|
|
if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
url = "%s?%s"%(baseUrl, ps) |
params["mode"] = "imagepath" |
|
params["url"] = getParentDir(params["url"]) |
|
|
|
# quote values and assemble into query string |
|
ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
|
url=self.REQUEST['URL1']+"?"+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.info("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""" |
|
|
if not self.digilibBaseUrl: |
if not self.digilibBaseUrl: |
self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
|
|
Line 275 class documentViewer(Folder):
|
Line 396 class documentViewer(Folder):
|
pt = getattr(self.template, 'info_xml') |
pt = getattr(self.template, 'info_xml') |
return pt(docinfo=docinfo) |
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 == '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,cut=0): |
|
"""gibt param von dlInfo aus""" |
|
num_retries = 3 |
|
if docinfo is None: |
|
docinfo = {} |
|
|
|
for x in range(cut): |
|
|
|
path=getParentDir(path) |
|
|
|
infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
|
|
|
logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl)) |
|
|
|
for cnt in range(num_retries): |
|
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)) |
|
|
|
sizes=dom.xpath("//dir/size") |
|
logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes) |
|
|
|
if sizes: |
|
docinfo['numPages'] = int(getTextFromNode(sizes[0])) |
|
else: |
|
docinfo['numPages'] = 0 |
|
|
|
# TODO: produce and keep list of image names and numbers |
|
|
|
|
def getDocinfo(self, mode, url): |
|
"""returns docinfo depending on mode""" |
|
logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url)) |
|
# look for cached docinfo in session |
|
if self.REQUEST.SESSION.has_key('docinfo'): |
|
docinfo = self.REQUEST.SESSION['docinfo'] |
|
# check if its still current |
|
if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url: |
|
logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys()) |
return docinfo |
return docinfo |
|
|
|
# new docinfo |
|
docinfo = {'mode': mode, 'url': url} |
|
# add self url |
|
docinfo['viewerUrl'] = self.getDocumentViewerURL() |
|
# get index.meta DOM |
|
docUrl = None |
|
metaDom = None |
|
if mode=="texttool": |
|
# url points to document dir or index.meta |
|
metaDom = self.metadataService.getDomFromPathOrUrl(url) |
|
docUrl = url.replace('/index.meta', '') |
|
if metaDom is None: |
|
raise IOError("Unable to find index.meta for mode=texttool!") |
|
|
def getIndexMeta(self, url): |
elif mode=="imagepath": |
"""returns dom of index.meta document at url""" |
# url points to folder with images, index.meta optional |
num_retries = 3 |
# asssume index.meta in parent dir |
dom = None |
docUrl = getParentPath(url) |
metaUrl = None |
metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
if url.startswith("http://"): |
|
# real URL |
|
metaUrl = url |
|
else: |
|
# online path |
|
server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
|
metaUrl=server+url.replace("/mpiwg/online","") |
|
if not metaUrl.endswith("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]) |
|
|
|
if dom is None: |
|
raise IOError("Unable to read index meta from %s"%(url)) |
|
|
|
return dom |
elif mode=="filepath": |
|
# url points to image file, index.meta optional |
|
# asssume index.meta is two path segments up |
|
docUrl = getParentPath(url, 2) |
|
metaDom = self.metadataService.getDomFromPathOrUrl(docUrl) |
|
|
def getPresentationInfoXML(self, url): |
|
"""returns dom of info.xml document at url""" |
|
num_retries = 3 |
|
dom = None |
|
metaUrl = None |
|
if url.startswith("http://"): |
|
# real URL |
|
metaUrl = url |
|
else: |
else: |
# online path |
logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) |
server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
metaUrl=server+url.replace("/mpiwg/online","") |
|
|
|
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 (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) |
|
|
|
if dom is None: |
|
raise IOError("Unable to read infoXMLfrom %s"%(url)) |
|
|
|
return dom |
|
|
|
|
|
def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
|
"""gets authorization info from the index.meta file at path or given by dom""" |
|
logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path)) |
|
|
|
access = None |
|
|
|
if docinfo is None: |
|
docinfo = {} |
|
|
|
if dom is None: |
|
for x in range(cut): |
|
path=getParentDir(path) |
|
dom = self.getIndexMeta(path) |
|
|
|
acctype = dom.xpath("//access-conditions/access/@type") |
|
if acctype and (len(acctype)>0): |
|
access=acctype[0].value |
|
if access in ['group', 'institution']: |
|
access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() |
|
|
|
docinfo['accessType'] = access |
docinfo['documentUrl'] = docUrl |
|
# process index.meta contents |
|
if metaDom is not None: |
|
# document directory name and path |
|
resource = self.metadataService.getResourceData(dom=metaDom) |
|
if resource: |
|
docinfo = self.getDocinfoFromResource(docinfo, resource) |
|
|
|
# texttool info |
|
texttool = self.metadataService.getTexttoolData(dom=metaDom) |
|
if texttool: |
|
docinfo = self.getDocinfoFromTexttool(docinfo, texttool) |
|
|
|
# bib info |
|
bib = self.metadataService.getBibData(dom=metaDom) |
|
if bib: |
|
docinfo = self.getDocinfoFromBib(docinfo, bib) |
|
else: |
|
# no bib - try info.xml |
|
docinfo = self.getDocinfoFromPresentationInfoXml(docinfo) |
|
|
|
# auth info |
|
access = self.metadataService.getAccessData(dom=metaDom) |
|
if access: |
|
docinfo = self.getDocinfoFromAccess(docinfo, access) |
|
|
|
# attribution info |
|
attribution = self.metadataService.getAttributionData(dom=metaDom) |
|
if attribution: |
|
logging.debug("getDocinfo: attribution=%s"%repr(attribution)) |
|
docinfo['attribution'] = attribution |
|
#docinfo = self.getDocinfoFromAccess(docinfo, access) |
|
|
|
# copyright info |
|
copyright = self.metadataService.getCopyrightData(dom=metaDom) |
|
if copyright: |
|
logging.debug("getDocinfo: copyright=%s"%repr(copyright)) |
|
docinfo['copyright'] = copyright |
|
#docinfo = self.getDocinfoFromAccess(docinfo, access) |
|
|
|
# image path |
|
if mode != 'texttool': |
|
# override image path from texttool |
|
docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1) |
|
|
|
# number of images from digilib |
|
if docinfo.get('imagePath', None): |
|
docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath'] |
|
docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath']) |
|
|
|
logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys()) |
|
#logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) |
|
# store in session |
|
self.REQUEST.SESSION['docinfo'] = docinfo |
return docinfo |
return docinfo |
|
|
|
def getDocinfoFromResource(self, docinfo, resource): |
|
"""reads contents of resource element into docinfo""" |
|
docName = resource.get('name', None) |
|
docinfo['documentName'] = docName |
|
docPath = resource.get('archive-path', None) |
|
if docPath: |
|
# clean up document path |
|
if docPath[0] != '/': |
|
docPath = '/' + docPath |
|
|
|
if docName and (not docPath.endswith(docName)): |
|
docPath += "/" + docName |
|
|
|
else: |
|
# use docUrl as docPath |
|
docUrl = docinfo['documentURL'] |
|
if not docUrl.startswith('http:'): |
|
docPath = docUrl |
|
if docPath: |
|
# fix URLs starting with /mpiwg/online |
|
docPath = docPath.replace('/mpiwg/online', '', 1) |
|
|
def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): |
docinfo['documentPath'] = docPath |
"""gets bibliographical info from the index.meta file at path or given by dom""" |
|
logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) |
|
|
|
if docinfo is None: |
|
docinfo = {} |
|
|
|
if dom is None: |
|
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 |
|
bibtype=dom.xpath("//bib/@type") |
|
if bibtype and (len(bibtype)>0): |
|
bibtype=bibtype[0].value |
|
else: |
|
bibtype="generic" |
|
|
|
bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) |
|
docinfo['bib_type'] = bibtype |
|
bibmap=metaData.generateMappingForType(bibtype) |
|
# if there is no mapping bibmap is empty (mapping sometimes has empty fields) |
|
if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: |
|
try: |
|
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]) |
|
except: pass |
|
try: |
|
docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) |
|
except: pass |
|
logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) |
|
try: |
|
docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) |
|
except: |
|
docinfo['lang']='' |
|
|
|
return docinfo |
return docinfo |
|
|
|
def getDocinfoFromTexttool(self, docinfo, texttool): |
def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): |
"""reads contents of texttool element into docinfo""" |
"""parse texttool tag in index meta""" |
# image dir |
logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url)) |
imageDir = texttool.get('image', None) |
if docinfo is None: |
docPath = docinfo.get('documentPath', None) |
docinfo = {} |
if imageDir and docPath: |
if docinfo.get('lang', None) is None: |
|
docinfo['lang'] = '' # default keine Sprache gesetzt |
|
if dom is None: |
|
dom = self.getIndexMeta(url) |
|
|
|
archivePath = None |
|
archiveName = None |
|
|
|
archiveNames = dom.xpath("//resource/name") |
|
if archiveNames and (len(archiveNames) > 0): |
|
archiveName = getTextFromNode(archiveNames[0]) |
|
else: |
|
logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url)) |
|
|
|
archivePaths = dom.xpath("//resource/archive-path") |
|
if archivePaths and (len(archivePaths) > 0): |
|
archivePath = getTextFromNode(archivePaths[0]) |
|
# clean up archive path |
|
if archivePath[0] != '/': |
|
archivePath = '/' + archivePath |
|
if archiveName and (not archivePath.endswith(archiveName)): |
|
archivePath += "/" + archiveName |
|
else: |
|
# try to get archive-path from url |
|
logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url)) |
|
if (not url.startswith('http')): |
|
archivePath = url.replace('index.meta', '') |
|
|
|
if archivePath is None: |
|
# we balk without archive-path |
|
raise IOError("Missing archive-path (for text-tool) in %s" % (url)) |
|
|
|
imageDirs = dom.xpath("//texttool/image") |
|
if imageDirs and (len(imageDirs) > 0): |
|
imageDir = getTextFromNode(imageDirs[0]) |
|
|
|
else: |
|
# we balk with no image tag / not necessary anymore because textmode is now standard |
|
#raise IOError("No text-tool info in %s"%(url)) |
|
imageDir = "" |
|
#xquery="//pb" |
|
docinfo['imagePath'] = "" # keine Bilder |
|
docinfo['imageURL'] = "" |
|
|
|
if imageDir and archivePath: |
|
#print "image: ", imageDir, " archivepath: ", archivePath |
#print "image: ", imageDir, " archivepath: ", archivePath |
imageDir = os.path.join(archivePath, imageDir) |
imageDir = os.path.join(docPath, imageDir) |
imageDir = imageDir.replace("/mpiwg/online", '') |
imageDir = imageDir.replace('/mpiwg/online', '', 1) |
docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) |
|
docinfo['imagePath'] = imageDir |
docinfo['imagePath'] = imageDir |
|
|
docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir |
# old style text URL |
|
textUrl = texttool.get('text', None) |
viewerUrls = dom.xpath("//texttool/digiliburlprefix") |
if textUrl and docPath: |
if viewerUrls and (len(viewerUrls) > 0): |
|
viewerUrl = getTextFromNode(viewerUrls[0]) |
|
docinfo['viewerURL'] = viewerUrl |
|
|
|
textUrls = dom.xpath("//texttool/text") |
|
if textUrls and (len(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(docPath, textUrl) |
# fix URLs starting with /mpiwg/online |
|
if textUrl.startswith("/mpiwg/online"): |
|
textUrl = textUrl.replace("/mpiwg/online", '', 1) |
|
|
|
docinfo['textURL'] = textUrl |
docinfo['textURL'] = textUrl |
|
|
textUrls = dom.xpath("//texttool/text-url-path") |
# new style text-url-path |
if textUrls and (len(textUrls) > 0): |
textUrl = texttool.get('text-url-path', None) |
textUrl = getTextFromNode(textUrls[0]) |
if textUrl: |
docinfo['textURLPath'] = textUrl |
docinfo['textURLPath'] = textUrl |
if not docinfo['imagePath']: |
#TODO: ugly: |
# text-only, no page images |
#textUrlkurz = string.split(textUrl, ".")[0] |
docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht |
#docinfo['textURLPathkurz'] = textUrlkurz |
|
|
|
# old presentation stuff |
|
presentation = texttool.get('presentation', None) |
|
if presentation and docPath: |
|
if presentation.startswith('http:'): |
|
docinfo['presentationUrl'] = presentation |
|
else: |
|
docinfo['presentationUrl'] = os.path.join(docPath, presentation) |
|
|
presentationUrls = dom.xpath("//texttool/presentation") |
return docinfo |
docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag |
|
|
|
if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen |
def getDocinfoFromBib(self, docinfo, bib): |
# presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten |
"""reads contents of bib element into docinfo""" |
# durch den relativen Pfad auf die presentation infos |
logging.debug("getDocinfoFromBib bib=%s"%repr(bib)) |
presentationPath = getTextFromNode(presentationUrls[0]) |
# put all raw bib fields in dict "bib" |
if url.endswith("index.meta"): |
docinfo['bib'] = bib |
presentationUrl = url.replace('index.meta', presentationPath) |
bibtype = bib.get('@type', None) |
else: |
docinfo['bibType'] = bibtype |
presentationUrl = url + "/" + presentationPath |
# also store DC metadata for convenience |
|
dc = self.metadataService.getDCMappedData(bib) |
|
docinfo['creator'] = dc.get('creator',None) |
|
docinfo['title'] = dc.get('title',None) |
|
docinfo['date'] = dc.get('date',None) |
|
return docinfo |
|
|
|
def getDocinfoFromAccess(self, docinfo, acc): |
|
"""reads contents of access element into docinfo""" |
|
#TODO: also read resource type |
|
logging.debug("getDocinfoFromAccess acc=%s"%repr(acc)) |
|
try: |
|
acctype = acc['@attr']['type'] |
|
if acctype: |
|
access=acctype |
|
if access in ['group', 'institution']: |
|
access = acc['name'].lower() |
|
|
docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom) |
docinfo['accessType'] = access |
|
|
docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info |
except: |
|
pass |
|
|
return docinfo |
return docinfo |
|
|
|
def getDocinfoFromDigilib(self, docinfo, path): |
def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
"""gets the bibliographical information from the preseantion entry in texttools |
# fetch data |
""" |
txt = getHttpData(infoUrl) |
dom=self.getPresentationInfoXML(url) |
if not txt: |
try: |
logging.error("Unable to get dir-info from %s"%(infoUrl)) |
docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) |
|
except: |
|
pass |
|
try: |
|
docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) |
|
except: |
|
pass |
|
try: |
|
docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) |
|
except: |
|
pass |
|
return docinfo |
return docinfo |
|
|
def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): |
dom = ET.fromstring(txt) |
"""path ist the path to the images it assumes that the index.meta file is one level higher.""" |
size = getText(dom.find("size")) |
logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path)) |
logging.debug("getDocinfoFromDigilib: size=%s"%size) |
if docinfo is None: |
if size: |
docinfo = {} |
docinfo['numPages'] = int(size) |
path=path.replace("/mpiwg/online","") |
else: |
docinfo['imagePath'] = path |
docinfo['numPages'] = 0 |
docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) |
|
|
# TODO: produce and keep list of image names and numbers |
pathorig=path |
|
for x in range(cut): |
|
path=getParentDir(path) |
|
logging.error("PATH:"+path) |
|
imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path |
|
docinfo['imageURL'] = imageUrl |
|
|
|
#path ist the path to the images it assumes that the index.meta file is one level higher. |
|
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 getDocinfoFromPresentationInfoXml(self,docinfo): |
"""returns docinfo depending on mode""" |
"""gets DC-like bibliographical information from the presentation entry in texttools""" |
logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url)) |
url = docinfo.get('presentationUrl', None) |
# look for cached docinfo in session |
if not url: |
if self.REQUEST.SESSION.has_key('docinfo'): |
logging.error("getDocinfoFromPresentation: no URL!") |
docinfo = self.REQUEST.SESSION['docinfo'] |
|
# check if its still current |
|
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) |
|
return docinfo |
return docinfo |
# new docinfo |
|
docinfo = {'mode': mode, 'url': url} |
dom = None |
if mode=="texttool": #index.meta with texttool information |
metaUrl = None |
docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) |
if url.startswith("http://"): |
elif mode=="imagepath": |
# real URL |
docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) |
metaUrl = url |
elif mode=="filepath": |
|
docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
|
else: |
else: |
logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") |
# online path |
raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
|
|
|
logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
self.REQUEST.SESSION['docinfo'] = docinfo |
metaUrl=server+url |
|
|
|
txt=getHttpData(metaUrl) |
|
if txt is None: |
|
logging.error("Unable to read info.xml from %s"%(url)) |
|
return docinfo |
|
|
|
dom = ET.fromstring(txt) |
|
docinfo['creator']=getText(dom.find(".//author")) |
|
docinfo['title']=getText(dom.find(".//title")) |
|
docinfo['date']=getText(dom.find(".//date")) |
return docinfo |
return docinfo |
|
|
|
|
Line 641 class documentViewer(Folder):
|
Line 664 class documentViewer(Folder):
|
"""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 648 class documentViewer(Folder):
|
Line 672 class documentViewer(Folder):
|
pageinfo['cols'] = cols |
pageinfo['cols'] = cols |
grpsize = cols * rows |
grpsize = cols * rows |
pageinfo['groupsize'] = grpsize |
pageinfo['groupsize'] = grpsize |
|
# what does this do? |
start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) |
# int(current / grpsize) * grpsize +1)) |
# int(current / grpsize) * grpsize +1)) |
pageinfo['start'] = start |
pageinfo['start'] = start |
Line 659 class documentViewer(Folder):
|
Line 684 class documentViewer(Folder):
|
if np % grpsize > 0: |
if np % grpsize > 0: |
pageinfo['numgroups'] += 1 |
pageinfo['numgroups'] += 1 |
|
|
|
|
pageinfo['viewMode'] = viewMode |
pageinfo['viewMode'] = viewMode |
pageinfo['tocMode'] = tocMode |
pageinfo['tocMode'] = tocMode |
|
pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') |
|
#pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1') |
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 670 class documentViewer(Folder):
|
Line 696 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') |
|
# WTF?: |
toc = int (pageinfo['tocPN']) |
toc = int (pageinfo['tocPN']) |
pageinfo['textPages'] =int (toc) |
pageinfo['textPages'] =int (toc) |
|
|
|
# What does this do? |
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']) |
# cached toc |
# cached toc |
|
|
if tocSize%tocPageSize>0: |
if tocSize%tocPageSize>0: |
tocPages=tocSize/tocPageSize+1 |
tocPages=tocSize/tocPageSize+1 |
else: |
else: |
tocPages=tocSize/tocPageSize |
tocPages=tocSize/tocPageSize |
|
|
pageinfo['tocPN'] = min (tocPages,toc) |
pageinfo['tocPN'] = min (tocPages,toc) |
|
|
pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
pageinfo['sn'] =self.REQUEST.get('sn','') |
pageinfo['sn'] =self.REQUEST.get('sn','') |
|
|
return pageinfo |
return pageinfo |
|
|
def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None): |
|
"""get search list""" |
security.declareProtected('View management screens','changeDocumentViewerForm') |
docpath = docinfo['textURLPath'] |
changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
url = docinfo['url'] |
|
logging.debug("documentViewer (gettoc) docpath: %s"%(docpath)) |
|
logging.debug("documentViewer (gettoc) url: %s"%(url)) |
|
pagesize = pageinfo['queryPageSize'] |
|
pn = pageinfo['searchPN'] |
|
sn = pageinfo['sn'] |
|
highlightQuery = pageinfo['highlightQuery'] |
|
query =pageinfo['query'] |
|
queryType =pageinfo['queryType'] |
|
viewMode= pageinfo['viewMode'] |
|
tocMode = pageinfo['tocMode'] |
|
tocPN = pageinfo['tocPN'] |
|
selfurl = self.absolute_url() |
|
page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery) ,outputUnicode=False) |
|
pagexml = page.replace('?document=%s'%str(docpath),'?url=%s'%url) |
|
pagedom = Parse(pagexml) |
|
if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"): |
|
pagedivs = pagedom.xpath("//div[@class='queryResultPage']") |
|
if len(pagedivs)>0: |
|
pagenode=pagedivs[0] |
|
links=pagenode.xpath("//a") |
|
for l in links: |
|
hrefNode = l.getAttributeNodeNS(None, u"href") |
|
if hrefNode: |
|
href = hrefNode.nodeValue |
|
if href.startswith('page-fragment.xql'): |
|
selfurl = self.absolute_url() |
|
pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN)) |
|
hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) |
|
return serializeNode(pagenode) |
|
|
|
if (queryType=="fulltextMorph"): |
|
pagedivs = pagedom.xpath("//div[@class='queryResult']") |
|
if len(pagedivs)>0: |
|
pagenode=pagedivs[0] |
|
links=pagenode.xpath("//a") |
|
for l in links: |
|
hrefNode = l.getAttributeNodeNS(None, u"href") |
|
if hrefNode: |
|
href = hrefNode.nodeValue |
|
if href.startswith('page-fragment.xql'): |
|
selfurl = self.absolute_url() |
|
pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN)) |
|
hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) |
|
if href.startswith('../lt/lemma.xql'): |
|
|
|
hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl) |
|
l.setAttributeNS(None, 'target', '_blank') |
|
l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") |
|
l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
|
pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']") |
|
return serializeNode(pagenode) |
|
|
|
if (queryType=="ftIndex")or(queryType=="ftIndexMorph"): |
|
pagedivs= pagedom.xpath("//div[@class='queryResultPage']") |
|
if len(pagedivs)>0: |
|
pagenode=pagedivs[0] |
|
links=pagenode.xpath("//a") |
|
for l in links: |
|
hrefNode = l.getAttributeNodeNS(None, u"href") |
|
if hrefNode: |
|
href = hrefNode.nodeValue |
|
hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn)) |
|
|
|
if href.startswith('../lt/lex.xql'): |
|
hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl) |
|
l.setAttributeNS(None, 'target', '_blank') |
|
l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") |
|
l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
|
if href.startswith('../lt/lemma.xql'): |
|
hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl) |
|
l.setAttributeNS(None, 'target', '_blank') |
|
l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") |
|
l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
|
return serializeNode(pagenode) |
|
return "no text here" |
|
|
|
def getNumPages(self,docinfo=None): |
|
"""get list of pages from fulltext and put in docinfo""" |
|
xquery = '//pb' |
|
text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) |
|
# TODO: better processing of the page list. do we need the info somewhere else also? |
|
docinfo['numPages'] = text.count("<pb ") |
|
return docinfo |
|
|
|
def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None): |
|
"""returns single page from fulltext""" |
|
docpath = docinfo['textURLPath'] |
|
path = docinfo['textURLPath'] |
|
url = docinfo['url'] |
|
viewMode= pageinfo['viewMode'] |
|
tocMode = pageinfo['tocMode'] |
|
tocPN = pageinfo['tocPN'] |
|
selfurl = self.absolute_url() |
|
|
|
#pn = pageinfo['searchPN'] |
|
|
|
if mode == "text_dict": |
|
textmode = "textPollux" |
|
else: |
|
textmode = mode |
|
|
|
textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn) |
|
if highlightQuery is not None: |
|
textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn) |
|
|
|
pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False) |
|
pagedom = Parse(pagexml) |
|
# plain text mode |
|
if mode == "text": |
|
# first div contains text |
|
pagedivs = pagedom.xpath("/div") |
|
#queryResultPage |
|
if len(pagedivs) > 0: |
|
pagenode = pagedivs[0] |
|
links = pagenode.xpath("//a") |
|
for l in links: |
|
hrefNode = l.getAttributeNodeNS(None, u"href") |
|
|
|
if hrefNode: |
|
href= hrefNode.nodeValue |
|
if href.startswith('#note-'): |
|
hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn)) |
|
|
|
return serializeNode(pagenode) |
|
if mode == "xml": |
|
# first div contains text |
|
pagedivs = pagedom.xpath("/div") |
|
if len(pagedivs) > 0: |
|
pagenode = pagedivs[0] |
|
return serializeNode(pagenode) |
|
if mode == "pureXml": |
|
# first div contains text |
|
pagedivs = pagedom.xpath("/div") |
|
if len(pagedivs) > 0: |
|
pagenode = pagedivs[0] |
|
return serializeNode(pagenode) |
|
# text-with-links mode |
|
if mode == "text_dict": |
|
# first div contains text |
|
pagedivs = pagedom.xpath("/div") |
|
if len(pagedivs) > 0: |
|
pagenode = pagedivs[0] |
|
# check all a-tags |
|
links = pagenode.xpath("//a") |
|
for l in links: |
|
hrefNode = l.getAttributeNodeNS(None, u"href") |
|
if hrefNode: |
|
# is link with href |
|
href = hrefNode.nodeValue |
|
if href.startswith('lt/lex.xql'): |
|
# is pollux link |
|
selfurl = self.absolute_url() |
|
# change href |
|
hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl) |
|
# add target |
|
l.setAttributeNS(None, 'target', '_blank') |
|
l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") |
|
l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
|
|
|
if href.startswith('lt/lemma.xql'): |
|
selfurl = self.absolute_url() |
|
hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl) |
|
l.setAttributeNS(None, 'target', '_blank') |
|
l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") |
|
l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
|
|
|
if href.startswith('#note-'): |
|
hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn)) |
|
|
|
|
|
return serializeNode(pagenode) |
|
|
|
return "no text here" |
|
|
|
def getTranslate(self, query=None, language=None): |
|
"""translate into another languages""" |
|
pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query))) |
|
return pagexml |
|
|
|
def getLemma(self, lemma=None, language=None): |
|
"""simular words lemma """ |
|
pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma))) |
|
#pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","lemma=%s&language=%s"%(lemma,language),outputUnicode=False) |
|
return pagexml |
|
|
|
def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1): |
|
"""number of""" |
|
docpath = docinfo['textURLPath'] |
|
pagesize = pageinfo['queryPageSize'] |
|
pn = pageinfo['searchPN'] |
|
query =pageinfo['query'] |
|
queryType =pageinfo['queryType'] |
|
|
|
tocSearch = 0 |
|
tocDiv = None |
|
pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn) ,outputUnicode=False) |
|
|
|
pagedom = Parse(pagexml) |
|
numdivs = pagedom.xpath("//div[@class='queryResultHits']") |
|
tocSearch = int(getTextFromNode(numdivs[0])) |
|
tc=int((tocSearch/10)+1) |
|
logging.debug("documentViewer (gettoc) tc: %s"%(tc)) |
|
return tc |
|
|
|
def getToc(self, mode="text", docinfo=None): |
|
"""loads table of contents and stores in docinfo""" |
|
logging.debug("documentViewer (gettoc) mode: %s"%(mode)) |
|
if 'tocSize_%s'%mode in docinfo: |
|
# cached toc |
|
return docinfo |
|
docpath = docinfo['textURLPath'] |
|
# we need to set a result set size |
|
pagesize = 1000 |
|
pn = 1 |
|
if mode == "text": |
|
queryType = "toc" |
|
else: |
|
queryType = mode |
|
# number of entries in toc |
|
tocSize = 0 |
|
tocDiv = None |
|
pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False) |
|
# post-processing downloaded xml |
|
pagedom = Parse(pagexml) |
|
# get number of entries |
|
numdivs = pagedom.xpath("//div[@class='queryResultHits']") |
|
if len(numdivs) > 0: |
|
tocSize = int(getTextFromNode(numdivs[0])) |
|
# div contains text |
|
#pagedivs = pagedom.xpath("//div[@class='queryResultPage']") |
|
#if len(pagedivs) > 0: |
|
# tocDiv = pagedivs[0] |
|
|
|
docinfo['tocSize_%s'%mode] = tocSize |
|
#docinfo['tocDiv_%s'%mode] = tocDiv |
|
return docinfo |
|
|
|
def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None): |
|
"""returns single page from the table of contents""" |
|
# TODO: this should use the cached TOC |
|
if mode == "text": |
|
queryType = "toc" |
|
else: |
|
queryType = mode |
|
docpath = docinfo['textURLPath'] |
|
path = docinfo['textURLPath'] |
|
#logging.debug("documentViewer (gettoc) pathNomer: %s"%(pathNomer)) |
|
pagesize = pageinfo['tocPageSize'] |
|
pn = pageinfo['tocPN'] |
|
url = docinfo['url'] |
|
selfurl = self.absolute_url() |
|
viewMode= pageinfo['viewMode'] |
|
tocMode = pageinfo['tocMode'] |
|
tocPN = pageinfo['tocPN'] |
|
|
|
pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn), outputUnicode=False) |
|
page = pagexml.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN)) |
|
text = page.replace('mode=image','mode=texttool') |
|
return text |
|
# post-processing downloaded xml |
|
#pagedom = Parse(text) |
|
# div contains text |
|
#pagedivs = pagedom.xpath("//div[@class='queryResultPage']") |
|
#if len(pagedivs) > 0: |
|
# pagenode = pagedivs[0] |
|
# return serializeNode(pagenode) |
|
#else: |
|
# return "No TOC!" |
|
|
|
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""" |
Line 969 class documentViewer(Folder):
|
Line 727 class documentViewer(Folder):
|
self.thumbrows = thumbrows |
self.thumbrows = thumbrows |
self.thumbcols = thumbcols |
self.thumbcols = thumbcols |
self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
|
try: |
|
# assume MetaDataFolder instance is called metadata |
|
self.metadataService = getattr(self, 'metadata') |
|
except Exception, e: |
|
logging.error("Unable to find MetaDataFolder 'metadata': "+str(e)) |
|
|
if RESPONSE is not None: |
if RESPONSE is not None: |
RESPONSE.redirect('manage_main') |
RESPONSE.redirect('manage_main') |
|
|
|
|
|
|
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) |
Line 987 def manage_AddDocumentViewer(self,id,ima
|
Line 749 def manage_AddDocumentViewer(self,id,ima
|
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" |