version 1.39, 2009/03/09 08:37:19
|
version 1.50, 2010/05/07 14:11:49
|
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 |
Line 11 from Ft.Xml.Domlette import Nonvalidatin
|
Line 11 from Ft.Xml.Domlette import Nonvalidatin
|
from Ft.Xml.Domlette import PrettyPrint, Print |
from Ft.Xml.Domlette import PrettyPrint, Print |
from Ft.Xml import EMPTY_NAMESPACE, Parse |
from Ft.Xml import EMPTY_NAMESPACE, Parse |
|
|
import Ft.Xml.XPath |
from xml.dom.minidom import parse, parseString |
|
|
|
|
|
|
|
import Ft.Xml.XPath |
|
import cStringIO |
|
import xmlrpclib |
import os.path |
import os.path |
import sys |
import sys |
import cgi |
import cgi |
Line 22 import math
|
Line 27 import math
|
|
|
import urlparse |
import urlparse |
from types import * |
from types import * |
|
|
def logger(txt,method,txt2): |
def logger(txt,method,txt2): |
"""logging""" |
"""logging""" |
logging.info(txt+ txt2) |
logging.info(txt+ txt2) |
Line 45 def getTextFromNode(nodename):
|
Line 51 def getTextFromNode(nodename):
|
rc = rc + node.data |
rc = rc + node.data |
return rc |
return rc |
|
|
|
def serializeNode(node, encoding='utf-8'): |
|
"""returns a string containing node as XML""" |
|
buf = cStringIO.StringIO() |
|
Print(node, stream=buf, encoding=encoding) |
|
s = buf.getvalue() |
|
buf.close() |
|
return s |
|
|
|
|
def getParentDir(path): |
def getParentDir(path): |
"""returns pathname shortened by one""" |
"""returns pathname shortened by one""" |
Line 77 class documentViewer(Folder):
|
Line 91 class documentViewer(Folder):
|
|
|
# templates and forms |
# templates and forms |
viewer_main = PageTemplateFile('zpt/viewer_main', globals()) |
viewer_main = PageTemplateFile('zpt/viewer_main', globals()) |
thumbs_main = PageTemplateFile('zpt/thumbs_main', globals()) |
toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals()) |
image_main = PageTemplateFile('zpt/image_main', globals()) |
toc_text = PageTemplateFile('zpt/toc_text', globals()) |
|
toc_figures = PageTemplateFile('zpt/toc_figures', globals()) |
|
page_main_images = PageTemplateFile('zpt/page_main_images', globals()) |
|
page_main_text = PageTemplateFile('zpt/page_main_text', globals()) |
|
page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) |
|
page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) |
head_main = PageTemplateFile('zpt/head_main', globals()) |
head_main = PageTemplateFile('zpt/head_main', globals()) |
docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) |
docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) |
info_xml = PageTemplateFile('zpt/info_xml', globals()) |
info_xml = PageTemplateFile('zpt/info_xml', globals()) |
Line 88 class documentViewer(Folder):
|
Line 107 class documentViewer(Folder):
|
changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
|
|
|
|
def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): |
def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): |
"""init document viewer""" |
"""init document viewer""" |
self.id=id |
self.id=id |
self.title=title |
self.title=title |
self.imageViewerUrl=imageViewerUrl |
|
self.textViewerUrl=textViewerUrl |
|
|
|
if not digilibBaseUrl: |
|
self.digilibBaseUrl = self.findDigilibUrl() |
|
else: |
|
self.digilibBaseUrl = digilibBaseUrl |
|
self.thumbcols = thumbcols |
self.thumbcols = thumbcols |
self.thumbrows = thumbrows |
self.thumbrows = thumbrows |
# authgroups is list of authorized groups (delimited by ,) |
# authgroups is list of authorized groups (delimited by ,) |
self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
# add template folder so we can always use template.something |
# create template folder so we can always use template.something |
self.manage_addFolder('template') |
|
|
templateFolder = Folder('template') |
|
#self['template'] = templateFolder # Zope-2.12 style |
|
self._setObject('template',templateFolder) # old style |
|
try: |
|
from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy |
|
xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False) |
|
#templateFolder['fulltextclient'] = xmlRpcClient |
|
templateFolder._setObject('fulltextclient',xmlRpcClient) |
|
except Exception, e: |
|
logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e)) |
|
try: |
|
from Products.zogiLib.zogiLib import zogiLib |
|
zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") |
|
#templateFolder['zogilib'] = zogilib |
|
templateFolder._setObject('zogilib',zogilib) |
|
except Exception, e: |
|
logging.error("Unable to create zogiLib for zogilib: "+str(e)) |
|
|
|
|
security.declareProtected('View','thumbs_rss') |
security.declareProtected('View','thumbs_rss') |
Line 116 class documentViewer(Folder):
|
Line 145 class documentViewer(Folder):
|
@param viewMode: if images display images, if text display text, default is images (text,images or auto) |
@param viewMode: if images display images, if text display text, default is images (text,images or auto) |
|
|
''' |
''' |
logging.info("HHHHHHHHHHHHHH:load the rss") |
logging.debug("HHHHHHHHHHHHHH:load the rss") |
logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
|
|
if not hasattr(self, 'template'): |
if not hasattr(self, 'template'): |
Line 139 class documentViewer(Folder):
|
Line 168 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,mode,url,viewMode="auto",start=None,pn=1,mk=None): |
def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=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 images (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 querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma) |
''' |
''' |
|
|
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 |
# this won't work |
self.manage_addFolder('template') |
logging.error("template folder missing!") |
|
return "ERROR: template folder missing!" |
|
|
if not self.digilibBaseUrl: |
if not getattr(self, 'digilibBaseUrl', None): |
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) |
|
pt = getattr(self.template, 'viewer_main') |
|
|
if tocMode != "thumbs": |
|
# get table of contents |
|
docinfo = self.getToc(mode=tocMode, docinfo=docinfo) |
|
|
|
pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) |
|
|
if viewMode=="auto": # automodus gewaehlt |
if viewMode=="auto": # automodus gewaehlt |
if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert |
if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert |
viewMode="text" |
viewMode="text" |
else: |
else: |
viewMode="images" |
viewMode="images" |
|
|
|
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)) |
|
|
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 type(mk) is not ListType: |
mk=[mk] |
mk=[mk] |
for m in mk: |
for m in mk: |
ret+="mk=%s"%m |
ret+="mk=%s"%m |
return ret |
return ret |
|
|
|
|
|
def findDigilibUrl(self): |
|
"""try to get the digilib URL from zogilib""" |
|
url = self.template.zogilib.getDLBaseUrl() |
|
return url |
|
|
|
def getStyle(self, idx, selected, style=""): |
|
"""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)) |
|
if idx == selected: |
|
return style + 'sel' |
|
else: |
|
return style |
|
|
def getLink(self,param=None,val=None): |
def getLink(self,param=None,val=None): |
"""link to documentviewer with parameter param set to val""" |
"""link to documentviewer with parameter param set to val""" |
params=self.REQUEST.form.copy() |
params=self.REQUEST.form.copy() |
Line 189 class documentViewer(Folder):
|
Line 239 class documentViewer(Folder):
|
del params[param] |
del params[param] |
else: |
else: |
params[param] = str(val) |
params[param] = str(val) |
if params["mode"] == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
|
|
if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath |
params["mode"] = "imagepath" |
params["mode"] = "imagepath" |
params["url"] = getParentDir(params["url"]) |
params["url"] = getParentDir(params["url"]) |
|
|
Line 213 class documentViewer(Folder):
|
Line 264 class documentViewer(Folder):
|
ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) |
url=self.REQUEST['URL1']+"?"+ps |
url=self.REQUEST['URL1']+"?"+ps |
return url |
return url |
|
|
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 224 class documentViewer(Folder):
|
Line 276 class documentViewer(Folder):
|
return pt(docinfo=docinfo) |
return pt(docinfo=docinfo) |
|
|
|
|
def getStyle(self, idx, selected, style=""): |
|
"""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)) |
|
if idx == selected: |
|
return style + 'sel' |
|
else: |
|
return style |
|
|
|
|
|
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) |
Line 286 class documentViewer(Folder):
|
Line 329 class documentViewer(Folder):
|
else: |
else: |
docinfo['numPages'] = 0 |
docinfo['numPages'] = 0 |
|
|
|
# TODO: produce and keep list of image names and numbers |
|
|
return docinfo |
return docinfo |
|
|
|
|
Line 312 class documentViewer(Folder):
|
Line 357 class documentViewer(Folder):
|
dom = Parse(txt) |
dom = Parse(txt) |
break |
break |
except: |
except: |
logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) |
logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2]) |
|
|
if dom is None: |
if dom is None: |
raise IOError("Unable to read index meta from %s"%(url)) |
raise IOError("Unable to read index meta from %s"%(url)) |
Line 332 class documentViewer(Folder):
|
Line 377 class documentViewer(Folder):
|
server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
server=self.digilibBaseUrl+"/servlet/Texter?fn=" |
metaUrl=server+url.replace("/mpiwg/online","") |
metaUrl=server+url.replace("/mpiwg/online","") |
|
|
|
|
for cnt in range(num_retries): |
for cnt in range(num_retries): |
try: |
try: |
# patch dirk encoding fehler treten dann nicht mehr auf |
# patch dirk encoding fehler treten dann nicht mehr auf |
Line 430 class documentViewer(Folder):
|
Line 474 class documentViewer(Folder):
|
logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url)) |
logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url)) |
if docinfo is None: |
if docinfo is None: |
docinfo = {} |
docinfo = {} |
|
|
if docinfo.get('lang',None) is None: |
if docinfo.get('lang',None) is None: |
docinfo['lang']='' # default keine Sprache gesetzt |
docinfo['lang']='' # default keine Sprache gesetzt |
if dom is None: |
if dom is None: |
Line 466 class documentViewer(Folder):
|
Line 509 class documentViewer(Folder):
|
imageDirs=dom.xpath("//texttool/image") |
imageDirs=dom.xpath("//texttool/image") |
if imageDirs and (len(imageDirs)>0): |
if imageDirs and (len(imageDirs)>0): |
imageDir=getTextFromNode(imageDirs[0]) |
imageDir=getTextFromNode(imageDirs[0]) |
|
|
else: |
else: |
# we balk with no image tag / not necessary anymore because textmode is now standard |
# we balk with no image tag / not necessary anymore because textmode is now standard |
#raise IOError("No text-tool info in %s"%(url)) |
#raise IOError("No text-tool info in %s"%(url)) |
imageDir="" |
imageDir="" |
docinfo['numPages']=1 # im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht |
#xquery="//pb" |
|
|
docinfo['imagePath'] = "" # keine Bilder |
docinfo['imagePath'] = "" # keine Bilder |
docinfo['imageURL'] = "" |
docinfo['imageURL'] = "" |
|
|
Line 500 class documentViewer(Folder):
|
Line 543 class documentViewer(Folder):
|
|
|
docinfo['textURL'] = textUrl |
docinfo['textURL'] = textUrl |
|
|
|
textUrls = dom.xpath("//texttool/text-url-path") |
|
if textUrls and (len(textUrls) > 0): |
|
textUrl = getTextFromNode(textUrls[0]) |
|
docinfo['textURLPath'] = textUrl |
|
|
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 |
|
|
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 |
# durch den relativen Pfad auf die presentation infos |
# durch den relativen Pfad auf die presentation infos |
presentationUrl=url.replace('index.meta',getTextFromNode(presentationUrls[0])) |
presentationPath = getTextFromNode(presentationUrls[0]) |
|
if url.endswith("index.meta"): |
|
presentationUrl = url.replace('index.meta', presentationPath) |
|
else: |
|
presentationUrl = url + "/" + presentationPath |
|
docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht |
docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom) |
docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom) |
|
|
docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info |
docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info |
|
|
return docinfo |
return docinfo |
|
|
|
|
Line 573 class documentViewer(Folder):
|
Line 627 class documentViewer(Folder):
|
docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) |
else: |
else: |
logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") |
logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!") |
raise ValueError("Unknown mode %s"%(mode)) |
raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) |
|
|
logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo) |
self.REQUEST.SESSION['docinfo'] = docinfo |
self.REQUEST.SESSION['docinfo'] = docinfo |
return docinfo |
return docinfo |
|
|
|
|
def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None): |
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) |
Line 595 class documentViewer(Folder):
|
Line 649 class documentViewer(Folder):
|
# int(current / grpsize) * grpsize +1)) |
# int(current / grpsize) * grpsize +1)) |
pageinfo['start'] = start |
pageinfo['start'] = start |
pageinfo['end'] = start + grpsize |
pageinfo['end'] = start + grpsize |
if docinfo is not None: |
if (docinfo is not None) and ('numPages' in docinfo): |
np = int(docinfo['numPages']) |
np = int(docinfo['numPages']) |
pageinfo['end'] = min(pageinfo['end'], np) |
pageinfo['end'] = min(pageinfo['end'], np) |
pageinfo['numgroups'] = int(np / grpsize) |
pageinfo['numgroups'] = int(np / grpsize) |
if np % grpsize > 0: |
if np % grpsize > 0: |
pageinfo['numgroups'] += 1 |
pageinfo['numgroups'] += 1 |
|
|
return pageinfo |
|
|
|
def text(self,mode,url,pn): |
|
"""give text""" |
|
if mode=="texttool": #index.meta with texttool information |
|
(viewerUrl,imagepath,textpath)=parseUrlTextTool(url) |
|
|
|
#print textpath |
|
try: |
|
dom = NonvalidatingReader.parseUri(textpath) |
|
except: |
|
return None |
|
|
|
list=[] |
|
nodes=dom.xpath("//pb") |
|
|
|
node=nodes[int(pn)-1] |
|
|
|
p=node |
|
|
|
while p.tagName!="p": |
|
p=p.parentNode |
|
|
|
|
pageinfo['viewMode'] = viewMode |
|
pageinfo['tocMode'] = tocMode |
|
pageinfo['query'] = self.REQUEST.get('query',' ') |
|
pageinfo['queryType'] = self.REQUEST.get('queryType',' ') |
|
pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') |
|
|
|
pageinfo['textPN'] = self.REQUEST.get('textPN','1') |
|
|
|
pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') |
|
pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '20') |
|
pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') |
|
toc = int (pageinfo['tocPN']) |
|
pageinfo['textPages'] =int (toc) |
|
|
|
if 'tocSize_%s'%tocMode in docinfo: |
|
tocSize = int(docinfo['tocSize_%s'%tocMode]) |
|
tocPageSize = int(pageinfo['tocPageSize']) |
|
# cached toc |
|
|
endNode=nodes[int(pn)] |
if tocSize%tocPageSize>0: |
|
tocPages=tocSize/tocPageSize+1 |
|
else: |
|
tocPages=tocSize/tocPageSize |
|
pageinfo['tocPN'] = min (tocPages,toc) |
|
|
e=endNode |
pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') |
|
pageinfo['sn'] =self.REQUEST.get('sn','1') |
|
|
while e.tagName!="p": |
return pageinfo |
e=e.parentNode |
|
|
|
|
def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None): |
|
"""get search list""" |
|
docpath = docinfo['textURLPath'] |
|
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'] |
|
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"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode) ,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() |
|
#l.setAttributeNS(None, "span class = 'hit highlight'", "background-color: #77DD77;") |
|
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) |
|
l.setAttributeNS(None, "onClick", "id='highlighting'") |
|
|
|
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'): |
|
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=400, scrollbars=1'); return false;") |
|
l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') |
|
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'): |
|
selfurl = self.absolute_url() |
|
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'): |
|
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=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 |
|
|
next=node.parentNode |
def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None,): |
|
"""returns single page from fulltext""" |
|
docpath = docinfo['textURLPath'] |
|
if mode == "text_dict": |
|
textmode = "textPollux" |
|
else: |
|
textmode = mode |
|
|
|
#selfurl = self.absolute_url() |
|
#viewMode= pageinfo['viewMode'] |
|
#tocMode = pageinfo['tocMode'] |
|
#tocPN = pageinfo['tocPN'] |
|
|
|
pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False) |
|
# post-processing downloaded xml |
|
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] |
|
return serializeNode(pagenode) |
|
if mode == "xml": |
|
# 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();') |
|
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/20)+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] |
|
|
#sammle s |
docinfo['tocSize_%s'%mode] = tocSize |
while next and (next!=endNode.parentNode): |
#docinfo['tocDiv_%s'%mode] = tocDiv |
list.append(next) |
return docinfo |
next=next.nextSibling |
|
list.append(endNode.parentNode) |
|
|
|
if p==e:# beide im selben paragraphen |
def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None): |
pass |
"""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: |
# else: |
# next=p |
# return "No TOC!" |
# while next!=e: |
|
# print next,e |
|
# list.append(next) |
|
# next=next.nextSibling |
|
# |
|
# for x in list: |
|
# PrettyPrint(x) |
|
# |
|
# return list |
|
# |
|
|
|
def findDigilibUrl(self): |
|
"""try to get the digilib URL from zogilib""" |
|
url = self.imageViewerUrl[:-1] + "/getScalerUrl" |
|
#print urlparse.urlparse(url)[0] |
|
#print urlparse.urljoin(self.absolute_url(),url) |
|
logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0]) |
|
logging.info("finddigiliburl: %s"%urlparse.urljoin(self.absolute_url(),url)) |
|
|
|
try: |
|
if urlparse.urlparse(url)[0]=='': #relative path |
|
url=urlparse.urljoin(self.absolute_url()+"/",url) |
|
|
|
scaler = urlopen(url).read() |
|
return scaler.replace("/servlet/Scaler?", "") |
|
except: |
|
return None |
|
|
|
def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): |
def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): |
"""init document viewer""" |
"""init document viewer""" |
self.title=title |
self.title=title |
self.imageViewerUrl=imageViewerUrl |
|
self.textViewerUrl=textViewerUrl |
|
self.digilibBaseUrl = digilibBaseUrl |
self.digilibBaseUrl = digilibBaseUrl |
self.thumbrows = thumbrows |
self.thumbrows = thumbrows |
self.thumbcols = thumbcols |
self.thumbcols = thumbcols |
Line 689 class documentViewer(Folder):
|
Line 950 class documentViewer(Folder):
|
|
|
|
|
|
|
|
|
# security.declareProtected('View management screens','renameImageForm') |
|
|
|
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) |
return pt() |
return pt() |
|
|
def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None): |
def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
"""add the viewer""" |
"""add the viewer""" |
newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl) |
newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
self._setObject(id,newObj) |
self._setObject(id,newObj) |
|
|
if RESPONSE is not None: |
if RESPONSE is not None: |