# HG changeset patch # User casties # Date 1310665436 -7200 # Node ID beb7ccb9256427ec3bb177aa379d8f4b958cf601 # Parent 4e84c53e49b3cc187c622caa693a10aadb138f23 first version using elementtree instead of 4suite xml diff -r 4e84c53e49b3 -r beb7ccb92564 .cvsignore --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/.cvsignore Thu Jul 14 19:43:56 2011 +0200 @@ -0,0 +1,1 @@ +.pydevproject diff -r 4e84c53e49b3 -r beb7ccb92564 MpdlXmlTextServer.py --- a/MpdlXmlTextServer.py Wed Nov 24 17:01:26 2010 +0100 +++ b/MpdlXmlTextServer.py Thu Jul 14 19:43:56 2011 +0200 @@ -2,12 +2,75 @@ from OFS.SimpleItem import SimpleItem from Products.PageTemplates.PageTemplateFile import PageTemplateFile from Ft.Xml import EMPTY_NAMESPACE, Parse +from Ft.Xml.Domlette import NonvalidatingReader +import Ft.Xml.Domlette +import cStringIO +import xml.etree.ElementTree as ET + +import md5 import sys import logging import urllib import documentViewer -from documentViewer import getTextFromNode, serializeNode +#from documentViewer import getTextFromNode, serializeNode + +def getText(node): + """get the cdata content of a node""" + if node is None: + return "" + # ET: + text = node.text or "" + for e in node: + text += gettext(e) + if e.tail: + text += e.tail + + return text + +def serialize(node): + """returns a string containing an XML snippet of node""" + s = ET.tostring(node, 'UTF-8') + # snip off XML declaration + if s.startswith('') + return s[i+3:] + + return s + + +def getTextFromNode(node): + """get the cdata content of a node""" + if node is None: + return "" + # ET: + #text = node.text or "" + #for e in node: + # text += gettext(e) + # if e.tail: + # text += e.tail + + # 4Suite: + nodelist=node.childNodes + text = "" + for n in nodelist: + if n.nodeType == node.TEXT_NODE: + text = text + n.data + + return text + +def serializeNode(node, encoding="utf-8"): + """returns a string containing node as XML""" + #s = ET.tostring(node) + + # 4Suite: + stream = cStringIO.StringIO() + Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) + s = stream.getvalue() + stream.close() + + return s + class MpdlXmlTextServer(SimpleItem): """TextServer implementation for MPDL-XML eXist server""" @@ -19,7 +82,9 @@ manage_changeMpdlXmlTextServerForm = PageTemplateFile("zpt/manage_changeMpdlXmlTextServer", globals()) - def __init__(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40): + def __init__(self,id,title="",serverUrl="http://mpdl-system.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40): + #def __init__(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/", serverName=None, timeout=40): + """constructor""" self.id=id self.title=title @@ -38,12 +103,12 @@ url = self.serverUrl+method return documentViewer.getHttpData(url,data,timeout=self.timeout) - def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=None, characterNormalization=None, optionToggle=None): + def getSearch(self, pageinfo=None, docinfo=None): """get search list""" docpath = docinfo['textURLPath'] url = docinfo['url'] pagesize = pageinfo['queryPageSize'] - pn = pageinfo['searchPN'] + pn = pageinfo.get('searchPN',1) sn = pageinfo['sn'] highlightQuery = pageinfo['highlightQuery'] query =pageinfo['query'] @@ -51,15 +116,26 @@ viewMode= pageinfo['viewMode'] tocMode = pageinfo['tocMode'] characterNormalization = pageinfo['characterNormalization'] - optionToggle = pageinfo['optionToggle'] + #optionToggle = pageinfo['optionToggle'] tocPN = pageinfo['tocPN'] selfurl = self.absolute_url() - - data = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&characterNormalization=%s&optionToggle=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,characterNormalization,optionToggle ,urllib.quote(highlightQuery))) - #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) - + data = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&characterNormalization=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,characterNormalization, urllib.quote(highlightQuery))) pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url) pagedom = Parse(pagexml) + + """ + pagedivs = pagedom.xpath("//div[@class='queryResultHits']") + if (pagedivs == pagedom.xpath("//div[@class='queryResultHits']")): + if len(pagedivs)>0: + docinfo['queryResultHits'] = int(getTextFromNode(pagedivs[0])) + s = getTextFromNode(pagedivs[0]) + s1 = int(s)/10+1 + try: + docinfo['queryResultHits'] = int(s1) + logging.debug("SEARCH ENTRIES: %s"%(s1)) + except: + docinfo['queryResultHits'] = 0 + """ if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"): pagedivs = pagedom.xpath("//div[@class='queryResultPage']") if len(pagedivs)>0: @@ -71,8 +147,9 @@ 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&optionToggle=%s&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN,optionToggle,characterNormalization)) + pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN, characterNormalization)) hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) + #logging.debug("PUREXML :%s"%(serializeNode(pagenode))) return serializeNode(pagenode) if (queryType=="fulltextMorph"): pagedivs = pagedom.xpath("//div[@class='queryResult']") @@ -85,13 +162,13 @@ 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&optionToggle=%s&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN,optionToggle,characterNormalization)) + pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN,characterNormalization)) 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_New'%(selfurl)) + hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_query'%(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, 'onClick', 'popupWin.focus();') + l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']") return serializeNode(pagenode) if (queryType=="ftIndex")or(queryType=="ftIndexMorph"): @@ -103,47 +180,27 @@ 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&optionToggle=%s&characterNormalization=%s'%(viewMode,tocMode,tocPN,pn,optionToggle,characterNormalization)) + hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s&characterNormalization=%s'%(viewMode,tocMode,tocPN,pn,characterNormalization)) if href.startswith('../lt/lex.xql'): - hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl) + hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_lex'%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, 'onClick', 'popupWin.focus();') + 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) + 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, 'onClick', 'popupWin.focus();') + l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') return serializeNode(pagenode) return "no text here" - - """def getNumPages(self, docinfo): - ""get list of pages from fulltext and put in docinfo"" - if 'numPages' in docinfo: - # already there - return docinfo - xquery = '//pb' - text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) - docinfo['numPages'] = text.count("0: - originalPage= getTextFromNode(pagedivs[0]) - #return docinfo['originalPage'] - return originalPage - - - def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization="regPlusNorm", highlightQuery=None, sn=None, optionToggle=None): + def getTextPage(self, mode="text_dict", pn=1, docinfo=None, pageinfo=None): """returns single page from fulltext""" docpath = docinfo['textURLPath'] path = docinfo['textURLPath'] - url = docinfo['url'] - name = docinfo['name'] - viewMode= pageinfo['viewMode'] + url = docinfo.get('url',None) + name = docinfo.get('name',None) + pn =pageinfo['current'] sn = pageinfo['sn'] + #optionToggle =pageinfo ['optionToggle'] highlightQuery = pageinfo['highlightQuery'] - + #mode = pageinfo ['viewMode'] tocMode = pageinfo['tocMode'] characterNormalization=pageinfo['characterNormalization'] tocPN = pageinfo['tocPN'] @@ -233,110 +258,225 @@ textmode = "textPollux" else: textmode = mode - #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery)) + textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization) if highlightQuery is not None: textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn) - #logging.debug("documentViewer highlightQuery: %s"%(highlightQuery)) + pagexml = self.getServerData("page-fragment.xql",textParam) - logging.debug("documentViewer highlightQuery: %s"%(highlightQuery)) - #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False) + dom = ET.fromstring(pagexml) + #dom = NonvalidatingReader.parseStream(pagexml) + + #original Pages + #pagedivs = dom.xpath("//div[@class='pageNumberOrig']") + + """if pagedivs == dom.xpath("//div[@class='pageNumberOrig']"): + if len(pagedivs)>0: + docinfo['pageNumberOrig']= getTextFromNode(pagedivs[0]) + logging.debug("ORIGINAL PAGE: %s"%(docinfo['pageNumberOrig'])) - pagedom = Parse(pagexml) + #original Pages Norm + pagedivs = dom.xpath("//div[@class='pageNumberOrigNorm']") + if pagedivs == dom.xpath("//div[@class='pageNumberOrigNorm']"): + if len(pagedivs)>0: + docinfo['pageNumberOrigNorm']= getTextFromNode(pagedivs[0]) + logging.debug("ORIGINAL PAGE NORM: %s"%(docinfo['pageNumberOrigNorm'])) + """ + #figureEntries +# pagedivs = dom.xpath("//div[@class='countFigureEntries']") +# if pagedivs == dom.xpath("//div[@class='countFigureEntries']"): +# if len(pagedivs)>0: +# docinfo['countFigureEntries'] = getTextFromNode(pagedivs[0]) +# s = getTextFromNode(pagedivs[0]) +# if s=='0': +# try: +# docinfo['countFigureEntries'] = int(s) +# except: +# docinfo['countFigureEntries'] = 0 +# else: +# s1 = int(s)/30+1 +# try: +# docinfo['countFigureEntries'] = int(s1) +# except: +# docinfo['countFigureEntries'] = 0 +# +# #allPlaces +# pagedivs = dom.xpath("//div[@class='countPlaces']") +# if pagedivs == dom.xpath("//div[@class='countPlaces']"): +# if len(pagedivs)>0: +# docinfo['countPlaces']= getTextFromNode(pagedivs[0]) +# s = getTextFromNode(pagedivs[0]) +# try: +# docinfo['countPlaces'] = int(s) +# except: +# docinfo['countPlaces'] = 0 +# +# #tocEntries +# pagedivs = dom.xpath("//div[@class='countTocEntries']") +# if pagedivs == dom.xpath("//div[@class='countTocEntries']"): +# if len(pagedivs)>0: +# docinfo['countTocEntries'] = int(getTextFromNode(pagedivs[0])) +# s = getTextFromNode(pagedivs[0]) +# if s=='0': +# try: +# docinfo['countTocEntries'] = int(s) +# except: +# docinfo['countTocEntries'] = 0 +# else: +# s1 = int(s)/30+1 +# try: +# docinfo['countTocEntries'] = int(s1) +# except: +# docinfo['countTocEntries'] = 0 + + #numTextPages + #pagedivs = dom.xpath("//div[@class='countPages']") + alldivs = dom.findall(".//div") + pagediv = None + for div in alldivs: + dc = div.get('class') + if dc == 'pageContent': + pagediv = div + + if dc == 'countPages': + try: + np = int(div.text) + docinfo['numPages'] = np + pageinfo['end'] = min(pageinfo['end'], np) + pageinfo['numgroups'] = int(np / pageinfo['groupsize']) + if np % pageinfo['groupsize'] > 0: + pageinfo['numgroups'] += 1 + + except: + docinfo['numPages'] = 0 + + break + +# ROC: why? +# else: +# #no full text -- init to 0 +# docinfo['pageNumberOrig'] = 0 +# docinfo['countFigureEntries'] = 0 +# docinfo['countPlaces'] = 0 +# docinfo['countTocEntries'] = 0 +# docinfo['numPages'] = 0 +# docinfo['pageNumberOrigNorm'] = 0 +# #return docinfo + # plain text mode if mode == "text": - # first div contains text - pagedivs = pagedom.xpath("/div") - if len(pagedivs) > 0: - pagenode = pagedivs[0] - links = pagenode.xpath("//a") + #pagedivs = dom.xpath("/div") + if pagediv: + links = pagediv.findall(".//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) + href = l.get('href') + if href and href.startswith('#note-'): + href = href.replace('#note-',"?url=%s&viewMode=text&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,tocMode,tocPN,pn)) + l.set('href', href) + logging.debug("page=%s"%ET.tostring(pagediv, 'UTF-8')) + return serialize(pagediv) + if mode == "xml": - # first div contains text - pagedivs = pagedom.xpath("/div") - if len(pagedivs) > 0: - pagenode = pagedivs[0] - return serializeNode(pagenode) + if pagediv: + return serialize(pagediv) + + if mode == "pureXml": + if pagediv: + return serialize(pagediv) + if mode == "gis": - # first div contains text - pagedivs = pagedom.xpath("/div") - 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('http://chinagis.mpiwg-berlin.mpg.de'): - hrefNode.nodeValue =href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name) - l.setAttributeNS(None, 'target', '_blank') - return serializeNode(pagenode) + if pagediv: + # check all a-tags + links = pagediv.findall(".//a") + for l in links: + href = l.get('href') + if href: + if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'): + l.set('href', href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name)) + l.set('target', '_blank') + + return serialize(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] + if pagediv: # check all a-tags - links = pagenode.xpath("//a") + links = pagediv.findall(".//a") for l in links: - hrefNode = l.getAttributeNodeNS(None, u"href") - if hrefNode: + href = l.get('href') + + if href: # is link with href - href = hrefNode.nodeValue - if href.startswith('lt/lex.xql'): + if href.startswith('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql'): # is pollux link selfurl = self.absolute_url() # change href - hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl) + l.set('href', href.replace('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/wordInfo.xql','%s/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, 'onClick', 'popupWin.focus();') - if href.startswith('lt/lemma.xql'): + l.set('target', '_blank') + + if href.startswith('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/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, 'onClick', 'popupWin.focus();') + l.set('href', href.replace('http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/lt/lemma.xql','%s/head_main_lemma'%selfurl)) + l.set('target', '_blank') + l.set('onclick',"popupWin = window.open(this.href, 'InfoWindow', 'menubar=no, location,width=500,height=600,top=180, left=700, toolbar=no, scrollbars=1'); return false;") + l.set('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) + l.set('href', href.replace('#note-',"?url=%s&viewMode=text_dict&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,tocMode,tocPN,pn))) + + return serialize(pagediv) + return "no text here" + + def getOrigPages(self, docinfo=None, pageinfo=None): + docpath = docinfo['textURLPath'] + pn =pageinfo['current'] + selfurl = self.absolute_url() + pagexml = self.getServerData("page-fragment.xql","document=%s&pn=%s"%(docpath, pn)) + dom = Parse(pagexml) + pagedivs = dom.xpath("//div[@class='pageNumberOrig']") + if pagedivs == dom.xpath("//div[@class='pageNumberOrig']"): + if len(pagedivs)>0: + docinfo['pageNumberOrig']= getTextFromNode(pagedivs[0]) + return docinfo['pageNumberOrig'] + + def getOrigPagesNorm(self, docinfo=None, pageinfo=None): + docpath = docinfo['textURLPath'] + pn =pageinfo['current'] + selfurl = self.absolute_url() + pagexml = self.getServerData("page-fragment.xql","document=%s&pn=%s"%(docpath, pn)) + dom = Parse(pagexml) + pagedivs = dom.xpath("//div[@class='pageNumberOrigNorm']") + if pagedivs == dom.xpath("//div[@class='pageNumberOrigNorm']"): + if len(pagedivs)>0: + docinfo['pageNumberOrigNorm']= getTextFromNode(pagedivs[0]) + return docinfo['pageNumberOrigNorm'] - def getTranslate(self, query=None, language=None): + + def getTranslate(self, word=None, language=None): """translate into another languages""" - data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query)) + data = self.getServerData("lt/wordInfo.xql","language="+str(language)+"&word="+urllib.quote(word)+"&output=html") #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query))) return data def getLemma(self, lemma=None, language=None): """simular words lemma """ - data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(lemma)) - #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma))) + data = self.getServerData("lt/lemma.xql","language="+str(language)+"&lemma="+urllib.quote(lemma)+"&output=html") + return data + + def getLemmaQuery(self, query=None, language=None): + """simular words lemma """ + data = self.getServerData("lt/lemma.xql","language="+str(language)+"&query="+urllib.quote(query)+"&output=html") return data - def getLemmaNew(self, query=None, language=None): - """simular words lemma """ - data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query)) - #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query))) + def getLex(self, query=None, language=None): + #simular words lemma + data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query)) return data - def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionToggle=None): - """number of""" + def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1): + #number of docpath = docinfo['textURLPath'] pagesize = pageinfo['queryPageSize'] pn = pageinfo['searchPN'] @@ -346,78 +486,14 @@ tocDiv = None pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn)) - #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])) - logging.debug("documentViewer (gettoc) tocSearch: %s"%(tocSearch)) tc=int((tocSearch/10)+1) - logging.debug("documentViewer (gettoc) tc: %s"%(tc)) - return tc - - def getQueryResultHits(self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionsClose=None): - - """number of hits in Search mode""" - docpath = docinfo['textURLPath'] - pagesize = pageinfo['queryPageSize'] - pn = pageinfo['searchPN'] - query =pageinfo['query'] - queryType =pageinfo['queryType'] - tocSearch = 0 - tocDiv = None - - pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn)) - #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) return tc - - def getQueryResultHitsText(self, docinfo=None, pageinfo=None): - """number of hits in Text of Contents mode""" - - docpath = docinfo['textURLPath'] - pagesize = pageinfo['queryPageSize'] - pn = pageinfo['searchPN'] - query =pageinfo['query'] - queryType =pageinfo['queryType'] - tocSearch = 0 - tocDiv = None - tocMode = pageinfo['tocMode'] - tocPN = pageinfo['tocPN'] - pagexml=self.getServerData("doc-query.xql", "document=%s&queryType=%s"%(docpath,'toc')) - pagedom = Parse(pagexml) - logging.debug("documentViewer (pagedom) pagedom: %s"%(pagedom)) - numdivs = pagedom.xpath("//div[@class='queryResultHits']") - tocSearch = int(getTextFromNode(numdivs[0])) - tc=int((tocSearch/30)+1) - return tc - - def getQueryResultHitsFigures(self, docinfo=None, pageinfo=None): - """number of hits in Text of Figures mode""" - - docpath = docinfo['textURLPath'] - pagesize = pageinfo['queryPageSize'] - pn = pageinfo['searchPN'] - query =pageinfo['query'] - queryType =pageinfo['queryType'] - tocSearch = 0 - tocDiv = None - tocMode = pageinfo['tocMode'] - tocPN = pageinfo['tocPN'] - pagexml=self.getServerData("doc-query.xql", "document=%s&queryType=%s"%(docpath,'figures')) - pagedom = Parse(pagexml) - logging.debug("documentViewer (pagedom) pagedom: %s"%(pagedom)) - numdivs = pagedom.xpath("//div[@class='queryResultHits']") - tocSearch = int(getTextFromNode(numdivs[0])) - tc=int((tocSearch/30)+1) - 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 mode == "none": return docinfo if 'tocSize_%s'%mode in docinfo: @@ -437,7 +513,7 @@ tocDiv = None pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn)) - #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 @@ -462,18 +538,17 @@ selfurl = self.absolute_url() viewMode= pageinfo['viewMode'] characterNormalization = pageinfo ['characterNormalization'] - optionToggle =pageinfo ['optionToggle'] + #optionToggle =pageinfo ['optionToggle'] tocMode = pageinfo['tocMode'] tocPN = pageinfo['tocPN'] - data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=regPlusNorm&optionToggle=1"%(docpath,queryType, pagesize, pn)) - page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&optionToggle=1'%(selfurl,url, viewMode, tocMode, tocPN)) + data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=regPlusNorm"%(docpath,queryType, pagesize, pn)) + page = data.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') - logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization)) - #logging.debug("documentViewer (characterNormalization) text: %s"%(text)) return text - def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None): + def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None): + #def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/",timeout=40,RESPONSE=None): """change settings""" self.title=title self.timeout = timeout @@ -487,12 +562,10 @@ pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self) return pt() -def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None): +def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None): +#def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de:30030/mpdl/interface/",timeout=40,RESPONSE=None): """add zogiimage""" newObj = MpdlXmlTextServer(id,title,serverUrl,timeout) self.Destination()._setObject(id, newObj) if RESPONSE is not None: - RESPONSE.redirect('manage_main') - - - + RESPONSE.redirect('manage_main') \ No newline at end of file diff -r 4e84c53e49b3 -r beb7ccb92564 documentViewer.py --- a/documentViewer.py Wed Nov 24 17:01:26 2010 +0100 +++ b/documentViewer.py Thu Jul 14 19:43:56 2011 +0200 @@ -7,8 +7,11 @@ from Globals import package_home from Products.zogiLib.zogiLib import browserCheck -from Ft.Xml import EMPTY_NAMESPACE, Parse -import Ft.Xml.Domlette +#from Ft.Xml import EMPTY_NAMESPACE, Parse +#import Ft.Xml.Domlette + +import xml.etree.ElementTree as ET + import os.path import sys import urllib @@ -16,7 +19,6 @@ import logging import math import urlparse -import cStringIO import re import string @@ -32,23 +34,37 @@ except: return int(default) -def getTextFromNode(nodename): +def getText(node): """get the cdata content of a node""" - if nodename is None: + if node is None: return "" - nodelist=nodename.childNodes - rc = "" - for node in nodelist: - if node.nodeType == node.TEXT_NODE: - rc = rc + node.data - return rc + # ET: + text = node.text or "" + for e in node: + text += gettext(e) + if e.tail: + text += e.tail -def serializeNode(node, encoding='utf-8'): + # 4Suite: + #nodelist=node.childNodes + #text = "" + #for n in nodelist: + # if n.nodeType == node.TEXT_NODE: + # text = text + n.data + + return text + +getTextFromNode = getText + +def serializeNode(node, encoding="utf-8"): """returns a string containing node as XML""" - buf = cStringIO.StringIO() - Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding) - s = buf.getvalue() - buf.close() + s = ET.tostring(node) + + # 4Suite: + # stream = cStringIO.StringIO() + # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) + # s = stream.getvalue() + # stream.close() return s def browserCheck(self): @@ -58,17 +74,51 @@ 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 + except:pass + # Firefox identification + try: + nav = ua[string.find(ua, '('):] + nav1=ua[string.find(ua,')'):] + if string.find(ie1, "Firefox") >-1: + nav5= string.split(ie1, "/")[1] + logging.debug("FIREFOX: %s"%(nav5)) + bt['versFirefox']=nav5[0:3] + except:pass + #Opera identification + try: + if string.find(ua,"Opera") >-1: + nav = ua[string.find(ua, '('):] + nav1=nav[string.find(nav,')'):] + bt['versOpera']=string.split(nav1,"/")[2] + except:pass bt['isMac'] = string.find(ua, 'Macintosh') > -1 bt['isWin'] = string.find(ua, 'Windows') > -1 @@ -127,8 +177,6 @@ raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) #return None - - ## ## documentViewer class ## @@ -147,6 +195,7 @@ 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_double = PageTemplateFile('zpt/page_main_double', globals()) page_main_text = PageTemplateFile('zpt/page_main_text', globals()) page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals()) @@ -196,26 +245,18 @@ """get page""" return self.template.fulltextclient.getTextPage(**args) - def getQuery(self, **args): - """get query""" - return self.template.fulltextclient.getQuery(**args) - - def getQueryResultHits(self, **args): - """get query""" - return self.template.fulltextclient.getQueryResultHits(**args) + def getOrigPages(self, **args): + """get page""" + return self.template.fulltextclient.getOrigPages(**args) - def getQueryResultHitsText(self, **args): - """get query""" - return self.template.fulltextclient.getQueryResultHitsText(**args) - - def getQueryResultHitsFigures(self, **args): - """get query""" - return self.template.fulltextclient.getQueryResultHitsFigures(**args) - - def getPDF(self, **args): - """get query""" - return self.template.fulltextclient.getPDF(**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) @@ -227,19 +268,7 @@ def getAllGisPlaces(self, **args): """get all gis places """ return self.template.fulltextclient.getAllGisPlaces(**args) - - def getOrigPages(self, **args): - """get original page number """ - return self.template.fulltextclient.getOrigPages(**args) - - def getNumPages(self, docinfo): - """get numpages""" - return self.template.fulltextclient.getNumPages(docinfo) - - def getNumTextPages(self, docinfo): - """get numpages text""" - return self.template.fulltextclient.getNumTextPages(docinfo) - + def getTranslate(self, **args): """get translate""" return self.template.fulltextclient.getTranslate(**args) @@ -248,6 +277,14 @@ """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) @@ -283,7 +320,7 @@ pt = getattr(self.template, 'thumbs_main_rss') if viewMode=="auto": # automodus gewaehlt - if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert + if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert viewMode="text" else: viewMode="images" @@ -319,14 +356,18 @@ docinfo = self.getToc(mode=tocMode, docinfo=docinfo) if viewMode=="auto": # automodus gewaehlt - if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert + if docinfo.has_key('textURL') or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert viewMode="text_dict" else: viewMode="images" pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) - pt = getattr(self.template, 'viewer_main') + if (docinfo.get('textURLPath',None)): + page = self.getTextPage(mode=viewMode, docinfo=docinfo, pageinfo=pageinfo) + pageinfo['textPage'] = page + tt = getattr(self, 'template') + pt = getattr(tt, 'viewer_main') return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) def generateMarks(self,mk): @@ -342,10 +383,9 @@ def getBrowser(self): """getBrowser the version of browser """ - names="" - names = browserCheck(self) - #logging.debug("XXXXXXXXXXXXXXXX: %s"%names) - return names + bt = browserCheck(self) + logging.debug("BROWSER VERSION: %s"%(bt)) + return bt def findDigilibUrl(self): """try to get the digilib URL from zogilib""" @@ -364,41 +404,48 @@ else: return style - def getLink(self,param=None,val=None): - """link to documentviewer with parameter param set to val""" - params=self.REQUEST.form.copy() + def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'): + """returns URL to documentviewer with parameter param set to val or from dict params""" + # copy existing request params + urlParams=self.REQUEST.form.copy() + # change single param if param is not None: if val is None: - if params.has_key(param): - del params[param] + if urlParams.has_key(param): + del urlParams[param] else: - params[param] = str(val) + urlParams[param] = str(val) - if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath - params["mode"] = "imagepath" - params["url"] = getParentDir(params["url"]) + # 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"] = getParentDir(urlParams["url"]) - # quote values and assemble into query string - #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) - ps = urllib.urlencode(params) - url=self.REQUEST['URL1']+"?"+ps + # quote values and assemble into query string (not escaping '/') + ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()]) + #ps = urllib.urlencode(urlParams) + if baseUrl is None: + baseUrl = self.REQUEST['URL1'] + + url = "%s?%s"%(baseUrl, ps) return url - def getLinkAmp(self,param=None,val=None): + + def getLinkAmp(self, param=None, val=None, params=None, baseUrl=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 - logging.debug("XYXXXXX: %s"%repr(params.items())) - ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) - url=self.REQUEST['URL1']+"?"+ps - return url + return self.getLink(param, val, params, baseUrl, '&') def getInfo_xml(self,url,mode): """returns info about the document as XML""" @@ -463,12 +510,14 @@ if txt is None: raise IOError("Unable to get dir-info from %s"%(infoUrl)) - dom = Parse(txt) - sizes=dom.xpath("//dir/size") - logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) + dom = ET.fromstring(txt) + #dom = Parse(txt) + size=getText(dom.find("size")) + #sizes=dom.xpath("//dir/size") + logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size) - if sizes: - docinfo['numPages'] = int(getTextFromNode(sizes[0])) + if size: + docinfo['numPages'] = int(size) else: docinfo['numPages'] = 0 @@ -513,7 +562,8 @@ if txt is None: raise IOError("Unable to read index meta from %s"%(url)) - dom = Parse(txt) + dom = ET.fromstring(txt) + #dom = Parse(txt) return dom def getPresentationInfoXML(self, url): @@ -532,7 +582,8 @@ if txt is None: raise IOError("Unable to read infoXMLfrom %s"%(url)) - dom = Parse(txt) + dom = ET.fromstring(txt) + #dom = Parse(txt) return dom @@ -550,11 +601,14 @@ path=getParentDir(path) dom = self.getDomFromIndexMeta(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() + acc = dom.find(".//access-conditions/access") + if acc is not None: + acctype = acc.get('type') + #acctype = dom.xpath("//access-conditions/access/@type") + if acctype: + access=acctype + if access in ['group', 'institution']: + access = dom.find(".//access-conditions/access/name").text.lower() docinfo['accessType'] = access return docinfo @@ -576,7 +630,8 @@ logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) # put in all raw bib fields as dict "bib" - bib = dom.xpath("//bib/*") + bib = dom.find(".//bib/*") + #bib = dom.xpath("//bib/*") if bib and len(bib)>0: bibinfo = {} for e in bib: @@ -585,10 +640,10 @@ # 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: + bib = dom.find(".//bib") + bibtype=bib.get("type") + #bibtype=dom.xpath("//bib/@type") + if not bibtype: bibtype="generic" bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) @@ -597,22 +652,63 @@ logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap)) logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype)) # if there is no mapping bibmap is empty (mapping sometimes has empty fields) - if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: + if len(bibmap) > 0 and len(bibmap['author'][0]) > 0 or len(bibmap['title'][0]) > 0: try: - docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) + docinfo['author']=getText(bib.find(bibmap['author'][0])) except: pass try: - docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) + docinfo['title']=getText(bib.find(bibmap['title'][0])) except: pass try: - docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) + docinfo['year']=getText(bib.find(bibmap['year'][0])) except: pass - logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) - try: - docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) - except: - docinfo['lang']='' - + + # ROC: why is this here? + # logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) + # try: + # docinfo['lang']=getTextFromNode(dom.find(".//bib/lang")[0]) + # except: + # docinfo['lang']='' + # try: + # docinfo['city']=getTextFromNode(dom.find(".//bib/city")[0]) + # except: + # docinfo['city']='' + # try: + # docinfo['number_of_pages']=getTextFromNode(dom.find(".//bib/number_of_pages")[0]) + # except: + # docinfo['number_of_pages']='' + # try: + # docinfo['series_volume']=getTextFromNode(dom.find(".//bib/series_volume")[0]) + # except: + # docinfo['series_volume']='' + # try: + # docinfo['number_of_volumes']=getTextFromNode(dom.find(".//bib/number_of_volumes")[0]) + # except: + # docinfo['number_of_volumes']='' + # try: + # docinfo['translator']=getTextFromNode(dom.find(".//bib/translator")[0]) + # except: + # docinfo['translator']='' + # try: + # docinfo['edition']=getTextFromNode(dom.find(".//bib/edition")[0]) + # except: + # docinfo['edition']='' + # try: + # docinfo['series_author']=getTextFromNode(dom.find(".//bib/series_author")[0]) + # except: + # docinfo['series_author']='' + # try: + # docinfo['publisher']=getTextFromNode(dom.find(".//bib/publisher")[0]) + # except: + # docinfo['publisher']='' + # try: + # docinfo['series_title']=getTextFromNode(dom.find(".//bib/series_title")[0]) + # except: + # docinfo['series_title']='' + # try: + # docinfo['isbn_issn']=getTextFromNode(dom.find(".//bib/isbn_issn")[0]) + # except: + # docinfo['isbn_issn']='' return docinfo @@ -626,7 +722,7 @@ path=getParentDir(path) dom = self.getDomFromIndexMeta(path) - docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0]) + docinfo['name']=getText(dom.find("name")) logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) return docinfo @@ -643,15 +739,12 @@ archivePath = None archiveName = None - archiveNames = dom.xpath("//resource/name") - if archiveNames and (len(archiveNames) > 0): - archiveName = getTextFromNode(archiveNames[0]) - else: + archiveName = getTextFromNode(dom.find("name")) + if not archiveName: logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) - archivePaths = dom.xpath("//resource/archive-path") - if archivePaths and (len(archivePaths) > 0): - archivePath = getTextFromNode(archivePaths[0]) + archivePath = getTextFromNode(dom.find("archive-path")) + if archivePath: # clean up archive path if archivePath[0] != '/': archivePath = '/' + archivePath @@ -667,11 +760,9 @@ # 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]) + imageDir = getText(dom.find(".//texttool/image")) - else: + if not imageDir: # we balk with no image tag / not necessary anymore because textmode is now standard #raise IOError("No text-tool info in %s"%(url)) imageDir = "" @@ -688,15 +779,13 @@ docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir - viewerUrls = dom.xpath("//texttool/digiliburlprefix") - if viewerUrls and (len(viewerUrls) > 0): - viewerUrl = getTextFromNode(viewerUrls[0]) + viewerUrl = getText(dom.find(".//texttool/digiliburlprefix")) + if viewerUrl: docinfo['viewerURL'] = viewerUrl # old style text URL - textUrls = dom.xpath("//texttool/text") - if textUrls and (len(textUrls) > 0): - textUrl = getTextFromNode(textUrls[0]) + textUrl = getText(dom.find(".//texttool/text")) + if textUrl: if urlparse.urlparse(textUrl)[0] == "": #keine url textUrl = os.path.join(archivePath, textUrl) # fix URLs starting with /mpiwg/online @@ -706,23 +795,25 @@ docinfo['textURL'] = textUrl # new style text-url-path - textUrls = dom.xpath("//texttool/text-url-path") - if textUrls and (len(textUrls) > 0): - textUrl = getTextFromNode(textUrls[0]) + textUrl = getText(dom.find(".//texttool/text-url-path")) + if textUrl: docinfo['textURLPath'] = textUrl - if not docinfo['imagePath']: + textUrlkurz = string.split(textUrl, ".")[0] + docinfo['textURLPathkurz'] = textUrlkurz + #if not docinfo['imagePath']: # text-only, no page images - docinfo = self.getNumTextPages(docinfo) + #docinfo = self.getNumTextPages(docinfo) + - presentationUrls = dom.xpath("//texttool/presentation") + presentationUrl = getText(dom.find(".//texttool/presentation")) docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) - if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen + if presentationUrl: # ueberschreibe diese durch presentation informationen # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten # durch den relativen Pfad auf die presentation infos - presentationPath = getTextFromNode(presentationUrls[0]) + presentationPath = presentationUrl if url.endswith("index.meta"): presentationUrl = url.replace('index.meta', presentationPath) else: @@ -740,15 +831,15 @@ """ dom=self.getPresentationInfoXML(url) try: - docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) + docinfo['author']=getText(dom.find(".//author")) except: pass try: - docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) + docinfo['title']=getText(dom.find(".//title")) except: pass try: - docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) + docinfo['year']=getText(dom.find(".//date")) except: pass return docinfo @@ -796,7 +887,11 @@ else: logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) - + + # FIXME: fake texturlpath + if not docinfo.has_key('textURLPath'): + docinfo['textURLPath'] = None + logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) #logging.debug("documentViewer (getdocinfo) docinfo: %s"%) self.REQUEST.SESSION['docinfo'] = docinfo @@ -826,8 +921,8 @@ pageinfo['numgroups'] += 1 pageinfo['viewMode'] = viewMode pageinfo['tocMode'] = tocMode - pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','regPlusNorm') - pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','') + pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') + #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1') pageinfo['query'] = self.REQUEST.get('query','') pageinfo['queryType'] = self.REQUEST.get('queryType','') pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') @@ -835,12 +930,10 @@ pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10') - pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') + pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') toc = int (pageinfo['tocPN']) pageinfo['textPages'] =int (toc) - - if 'tocSize_%s'%tocMode in docinfo: tocSize = int(docinfo['tocSize_%s'%tocMode]) tocPageSize = int(pageinfo['tocPageSize']) diff -r 4e84c53e49b3 -r beb7ccb92564 documentViewer_old.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/documentViewer_old.py Thu Jul 14 19:43:56 2011 +0200 @@ -0,0 +1,1009 @@ + +from OFS.Folder import Folder +from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate +from Products.PageTemplates.PageTemplateFile import PageTemplateFile +from AccessControl import ClassSecurityInfo +from AccessControl import getSecurityManager +from Globals import package_home +from Products.zogiLib.zogiLib import browserCheck + +from Ft.Xml import EMPTY_NAMESPACE, Parse +import Ft.Xml.Domlette + +import xml.etree.ElementTree as ET + +import os.path +import sys +import urllib +import urllib2 +import logging +import math +import urlparse +import cStringIO +import re +import string + +def logger(txt,method,txt2): + """logging""" + logging.info(txt+ txt2) + + +def getInt(number, default=0): + """returns always an int (0 in case of problems)""" + try: + return int(number) + except: + return int(default) + +def getTextFromNode(node): + """get the cdata content of a node""" + if node is None: + return "" + # ET: + text = node.text or "" + for e in node: + text += gettext(e) + if e.tail: + text += e.tail + + # 4Suite: + #nodelist=node.childNodes + #text = "" + #for n in nodelist: + # if n.nodeType == node.TEXT_NODE: + # text = text + n.data + + return text + +def serializeNode(node, encoding="utf-8"): + """returns a string containing node as XML""" + s = ET.tostring(node) + + # 4Suite: + # stream = cStringIO.StringIO() + # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) + # s = stream.getvalue() + # stream.close() + return s + +def browserCheck(self): + """check the browsers request to find out the browser type""" + bt = {} + ua = self.REQUEST.get_header("HTTP_USER_AGENT") + bt['ua'] = ua + bt['isIE'] = False + bt['isN4'] = False + bt['versFirefox']="" + bt['versIE']="" + bt['versSafariChrome']="" + bt['versOpera']="" + + if string.find(ua, 'MSIE') > -1: + bt['isIE'] = True + else: + bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) + # Safari oder Chrome identification + try: + nav = ua[string.find(ua, '('):] + nav1=ua[string.find(ua,')'):] + nav2=nav1[string.find(nav1,'('):] + nav3=nav2[string.find(nav2,')'):] + ie = string.split(nav, "; ")[1] + ie1 =string.split(nav1, " ")[2] + ie2 =string.split(nav3, " ")[1] + ie3 =string.split(nav3, " ")[2] + if string.find(ie3, "Safari") >-1: + bt['versSafariChrome']=string.split(ie2, "/")[1] + except: pass + # IE identification + try: + nav = ua[string.find(ua, '('):] + ie = string.split(nav, "; ")[1] + if string.find(ie, "MSIE") > -1: + bt['versIE'] = string.split(ie, " ")[1] + except:pass + # Firefox identification + try: + nav = ua[string.find(ua, '('):] + nav1=ua[string.find(ua,')'):] + if string.find(ie1, "Firefox") >-1: + nav5= string.split(ie1, "/")[1] + logging.debug("FIREFOX: %s"%(nav5)) + bt['versFirefox']=nav5[0:3] + except:pass + #Opera identification + try: + if string.find(ua,"Opera") >-1: + nav = ua[string.find(ua, '('):] + nav1=nav[string.find(nav,')'):] + bt['versOpera']=string.split(nav1,"/")[2] + except:pass + + bt['isMac'] = string.find(ua, 'Macintosh') > -1 + bt['isWin'] = string.find(ua, 'Windows') > -1 + bt['isIEWin'] = bt['isIE'] and bt['isWin'] + bt['isIEMac'] = bt['isIE'] and bt['isMac'] + bt['staticHTML'] = False + + return bt + + +def getParentDir(path): + """returns pathname shortened by one""" + return '/'.join(path.split('/')[0:-1]) + + +def getHttpData(url, data=None, num_tries=3, timeout=10): + """returns result from url+data HTTP request""" + # we do GET (by appending data to url) + if isinstance(data, str) or isinstance(data, unicode): + # if data is string then append + url = "%s?%s"%(url,data) + elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple): + # urlencode + url = "%s?%s"%(url,urllib.urlencode(data)) + + response = None + errmsg = None + for cnt in range(num_tries): + try: + logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url)) + if sys.version_info < (2, 6): + # set timeout on socket -- ugly :-( + import socket + socket.setdefaulttimeout(float(timeout)) + response = urllib2.urlopen(url) + else: + response = urllib2.urlopen(url,timeout=float(timeout)) + # check result? + break + except urllib2.HTTPError, e: + logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e)) + errmsg = str(e) + # stop trying + break + except urllib2.URLError, e: + logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e)) + errmsg = str(e) + # stop trying + #break + + if response is not None: + data = response.read() + response.close() + return data + + raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) + #return None + +## +## documentViewer class +## +class documentViewer(Folder): + """document viewer""" + meta_type="Document viewer" + + security=ClassSecurityInfo() + manage_options=Folder.manage_options+( + {'label':'main config','action':'changeDocumentViewerForm'}, + ) + + # templates and forms + viewer_main = PageTemplateFile('zpt/viewer_main', globals()) + toc_thumbs = PageTemplateFile('zpt/toc_thumbs', 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_double = PageTemplateFile('zpt/page_main_double', globals()) + page_main_text = PageTemplateFile('zpt/page_main_text', 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_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals()) + head_main = PageTemplateFile('zpt/head_main', globals()) + docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) + info_xml = PageTemplateFile('zpt/info_xml', 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"): + """init document viewer""" + self.id=id + self.title=title + self.thumbcols = thumbcols + self.thumbrows = thumbrows + # authgroups is list of authorized groups (delimited by ,) + self.authgroups = [s.strip().lower() for s in authgroups.split(',')] + # create template folder so we can always use template.something + + templateFolder = Folder('template') + #self['template'] = templateFolder # Zope-2.12 style + self._setObject('template',templateFolder) # old style + try: + import MpdlXmlTextServer + textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) + #templateFolder['fulltextclient'] = xmlRpcClient + templateFolder._setObject('fulltextclient',textServer) + except Exception, e: + logging.error("Unable to create MpdlXmlTextServer 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)) + + + # 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') + def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): + ''' + view it + @param mode: defines how to access the document behind url + @param url: url which contains display information + @param viewMode: if images display images, if text display text, default is images (text,images or auto) + + ''' + logging.debug("HHHHHHHHHHHHHH:load the rss") + logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) + + if not hasattr(self, 'template'): + # create template folder if it doesn't exist + self.manage_addFolder('template') + + if not self.digilibBaseUrl: + self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" + + 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) + ''' ZDES ''' + pt = getattr(self.template, 'thumbs_main_rss') + + if viewMode=="auto": # automodus gewaehlt + if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert + viewMode="text" + else: + viewMode="images" + + return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) + + security.declareProtected('View','index_html') + def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None): + ''' + view it + @param mode: defines how to access the document behind url + @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 tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) + @param characterNormalization type of text display (reg, norm, 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)) + + if not hasattr(self, 'template'): + # this won't work + logging.error("template folder missing!") + return "ERROR: template folder missing!" + + if not getattr(self, 'digilibBaseUrl', None): + self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" + + docinfo = self.getDocinfo(mode=mode,url=url) + + if tocMode != "thumbs": + # get table of contents + docinfo = self.getToc(mode=tocMode, docinfo=docinfo) + + if viewMode=="auto": # automodus gewaehlt + if docinfo.has_key('textURL') or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert + viewMode="text_dict" + else: + viewMode="images" + + pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) + + if (docinfo.get('textURLPath',None)): + page = self.getTextPage(docinfo=docinfo, pageinfo=pageinfo) + pageinfo['textPage'] = page + tt = getattr(self, 'template') + pt = getattr(tt, 'viewer_main') + return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) + + def generateMarks(self,mk): + ret="" + if mk is None: + return "" + if not isinstance(mk, list): + mk=[mk] + for m in mk: + ret+="mk=%s"%m + return ret + + + def getBrowser(self): + """getBrowser the version of browser """ + bt = browserCheck(self) + logging.debug("BROWSER VERSION: %s"%(bt)) + return bt + + def findDigilibUrl(self): + """try to get the digilib URL from zogilib""" + url = self.template.zogilib.getDLBaseUrl() + return url + + def getDocumentViewerURL(self): + """returns the URL of this instance""" + return self.absolute_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, params=None, baseUrl=None, paramSep='&'): + """returns URL to documentviewer with parameter param set to val or from dict params""" + # copy existing request params + urlParams=self.REQUEST.form.copy() + # change single param + if param is not None: + if val is None: + if urlParams.has_key(param): + del urlParams[param] + else: + 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"] = getParentDir(urlParams["url"]) + + # quote values and assemble into query string (not escaping '/') + ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()]) + #ps = urllib.urlencode(urlParams) + if baseUrl is None: + baseUrl = self.REQUEST['URL1'] + + url = "%s?%s"%(baseUrl, ps) + return url + + + def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None): + """link to documentviewer with parameter param set to val""" + return self.getLink(param, val, params, baseUrl, '&') + + def getInfo_xml(self,url,mode): + """returns info about the document as XML""" + + if not self.digilibBaseUrl: + self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" + + docinfo = self.getDocinfo(mode=mode,url=url) + pt = getattr(self.template, 'info_xml') + return pt(docinfo=docinfo) + + def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True): + """returns new option state""" + if not self.REQUEST.SESSION.has_key(optionName): + # not in session -- initial + opt = {'lastState': newState, 'state': initialState} + else: + opt = self.REQUEST.SESSION.get(optionName) + if opt['lastState'] != newState: + # state in session has changed -- toggle + opt['state'] = not opt['state'] + opt['lastState'] = newState + + self.REQUEST.SESSION[optionName] = opt + return opt['state'] + + def isAccessible(self, docinfo): + """returns if access to the resource is granted""" + access = docinfo.get('accessType', None) + logging.debug("documentViewer (accessOK) access type %s"%access) + if access is not None and access == 'free': + logging.debug("documentViewer (accessOK) access is free") + return True + elif access is None or access in self.authgroups: + # only local access -- only logged in users + user = getSecurityManager().getUser() + logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) + if user is not None: + #print "user: ", user + return (user.getUserName() != "Anonymous User") + else: + return False + + logging.error("documentViewer (accessOK) unknown access type %s"%access) + return False + + + def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): + """gibt param von dlInfo aus""" + if docinfo is None: + docinfo = {} + + for x in range(cut): + + path=getParentDir(path) + + infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path + + logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) + + txt = getHttpData(infoUrl) + if txt is None: + raise IOError("Unable to get dir-info from %s"%(infoUrl)) + + dom = ET.fromstring(txt).getroot() + #dom = Parse(txt) + sizes=dom.find("//dir/size") + #sizes=dom.xpath("//dir/size") + logging.debug("documentViewer (getparamfromdigilib) 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 + + return docinfo + + def getIndexMetaPath(self,url): + """gib nur den Pfad zurueck""" + regexp = re.compile(r".*(experimental|permanent)/(.*)") + regpath = regexp.match(url) + if (regpath==None): + return "" + logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2)) + return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2)) + + + + def getIndexMetaUrl(self,url): + """returns utr of index.meta document at url""" + + metaUrl = None + 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" + + return metaUrl + + def getDomFromIndexMeta(self, url): + """get dom from index meta""" + dom = None + metaUrl = self.getIndexMetaUrl(url) + + logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl) + txt=getHttpData(metaUrl) + if txt is None: + raise IOError("Unable to read index meta from %s"%(url)) + + dom = ET.fromstring(txt).getroot() + #dom = Parse(txt) + return dom + + def getPresentationInfoXML(self, url): + """returns dom of info.xml document at url""" + dom = None + metaUrl = None + if url.startswith("http://"): + # real URL + metaUrl = url + else: + # online path + server=self.digilibBaseUrl+"/servlet/Texter?fn=" + metaUrl=server+url.replace("/mpiwg/online","") + + txt=getHttpData(metaUrl) + if txt is None: + raise IOError("Unable to read infoXMLfrom %s"%(url)) + + dom = ET.fromstring(txt).getroot() + #dom = Parse(txt) + 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""" + logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path)) + + access = None + + if docinfo is None: + docinfo = {} + + if dom is None: + for x in range(cut): + path=getParentDir(path) + dom = self.getDomFromIndexMeta(path) + + acctype = dom.find("//access-conditions/access/@type") + #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 + return docinfo + + + def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): + """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.getDomFromIndexMeta(path) + + docinfo['indexMetaPath']=self.getIndexMetaPath(path); + + logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) + # put in all raw bib fields as dict "bib" + bib = dom.find("//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.find("//bib/@type") + #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) + logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap)) + logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype)) + # if there is no mapping bibmap is empty (mapping sometimes has empty fields) + if 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']='' + try: + docinfo['city']=getTextFromNode(dom.xpath("//bib/city")[0]) + except: + docinfo['city']='' + try: + docinfo['number_of_pages']=getTextFromNode(dom.xpath("//bib/number_of_pages")[0]) + except: + docinfo['number_of_pages']='' + try: + docinfo['series_volume']=getTextFromNode(dom.xpath("//bib/series_volume")[0]) + except: + docinfo['series_volume']='' + try: + docinfo['number_of_volumes']=getTextFromNode(dom.xpath("//bib/number_of_volumes")[0]) + except: + docinfo['number_of_volumes']='' + try: + docinfo['translator']=getTextFromNode(dom.xpath("//bib/translator")[0]) + except: + docinfo['translator']='' + try: + docinfo['edition']=getTextFromNode(dom.xpath("//bib/edition")[0]) + except: + docinfo['edition']='' + try: + docinfo['series_author']=getTextFromNode(dom.xpath("//bib/series_author")[0]) + except: + docinfo['series_author']='' + try: + docinfo['publisher']=getTextFromNode(dom.xpath("//bib/publisher")[0]) + except: + docinfo['publisher']='' + try: + docinfo['series_title']=getTextFromNode(dom.xpath("//bib/series_title")[0]) + except: + docinfo['series_title']='' + try: + docinfo['isbn_issn']=getTextFromNode(dom.xpath("//bib/isbn_issn")[0]) + except: + docinfo['isbn_issn']='' + return docinfo + + + def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): + """gets name info from the index.meta file at path or given by dom""" + if docinfo is None: + docinfo = {} + + if dom is None: + for x in range(cut): + path=getParentDir(path) + dom = self.getDomFromIndexMeta(path) + + docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0]) + logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) + return docinfo + + def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): + """parse texttool tag in index meta""" + logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url)) + if docinfo is None: + docinfo = {} + if docinfo.get('lang', None) is None: + docinfo['lang'] = '' # default keine Sprache gesetzt + if dom is None: + dom = self.getDomFromIndexMeta(url) + + archivePath = None + archiveName = None + + archiveNames = dom.xpath("//resource/name") + if archiveNames and (len(archiveNames) > 0): + archiveName = getTextFromNode(archiveNames[0]) + else: + logging.warning("documentViewer (getdocinfofromtexttool) 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 + logging.warning("documentViewer (getdocinfofromtexttool) 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 + imageDir = os.path.join(archivePath, imageDir) + imageDir = imageDir.replace("/mpiwg/online", '') + docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) + docinfo['imagePath'] = imageDir + + docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir + + viewerUrls = dom.xpath("//texttool/digiliburlprefix") + if viewerUrls and (len(viewerUrls) > 0): + viewerUrl = getTextFromNode(viewerUrls[0]) + docinfo['viewerURL'] = viewerUrl + + # old style text URL + textUrls = dom.xpath("//texttool/text") + if textUrls and (len(textUrls) > 0): + textUrl = getTextFromNode(textUrls[0]) + if urlparse.urlparse(textUrl)[0] == "": #keine url + textUrl = os.path.join(archivePath, textUrl) + # fix URLs starting with /mpiwg/online + if textUrl.startswith("/mpiwg/online"): + textUrl = textUrl.replace("/mpiwg/online", '', 1) + + docinfo['textURL'] = textUrl + + # new style text-url-path + textUrls = dom.xpath("//texttool/text-url-path") + if textUrls and (len(textUrls) > 0): + textUrl = getTextFromNode(textUrls[0]) + docinfo['textURLPath'] = textUrl + textUrlkurz = string.split(textUrl, ".")[0] + docinfo['textURLPathkurz'] = textUrlkurz + #if not docinfo['imagePath']: + # text-only, no page images + #docinfo = self.getNumTextPages(docinfo) + + + presentationUrls = dom.xpath("//texttool/presentation") + docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag + docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) + + + if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen + # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten + # durch den relativen Pfad auf die presentation infos + presentationPath = getTextFromNode(presentationUrls[0]) + if url.endswith("index.meta"): + presentationUrl = url.replace('index.meta', presentationPath) + else: + presentationUrl = url + "/" + presentationPath + + docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom) + + docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info + + return docinfo + + + def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): + """gets the bibliographical information from the preseantion entry in texttools + """ + dom=self.getPresentationInfoXML(url) + try: + 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 + + def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): + """path ist the path to the images it assumes that the index.meta file is one level higher.""" + logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path)) + if docinfo is None: + docinfo = {} + path=path.replace("/mpiwg/online","") + docinfo['imagePath'] = path + docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) + + pathorig=path + for x in range(cut): + path=getParentDir(path) + logging.debug("documentViewer (getdocinfofromimagepath) 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 + + + def getDocinfo(self, mode, url): + """returns docinfo depending on mode""" + logging.debug("documentViewer (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') == mode and docinfo.get('url') == url: + logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo) + return docinfo + # new docinfo + docinfo = {'mode': mode, 'url': url} + if mode=="texttool": #index.meta with texttool information + docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) + elif mode=="imagepath": + docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) + elif mode=="filepath": + docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) + else: + logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) + raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) + + # FIXME: fake texturlpath + if not docinfo.has_key('textURLPath'): + docinfo['textURLPath'] = None + + logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) + #logging.debug("documentViewer (getdocinfo) docinfo: %s"%) + self.REQUEST.SESSION['docinfo'] = docinfo + return docinfo + + def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): + """returns pageinfo with the given parameters""" + pageinfo = {} + current = getInt(current) + + pageinfo['current'] = current + rows = int(rows or self.thumbrows) + pageinfo['rows'] = rows + cols = int(cols or self.thumbcols) + pageinfo['cols'] = cols + grpsize = cols * rows + pageinfo['groupsize'] = grpsize + start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) + # int(current / grpsize) * grpsize +1)) + pageinfo['start'] = start + pageinfo['end'] = start + grpsize + if (docinfo is not None) and ('numPages' in docinfo): + np = int(docinfo['numPages']) + pageinfo['end'] = min(pageinfo['end'], np) + pageinfo['numgroups'] = int(np / grpsize) + if np % grpsize > 0: + pageinfo['numgroups'] += 1 + pageinfo['viewMode'] = viewMode + pageinfo['tocMode'] = tocMode + pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') + #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1') + 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['highlightQuery'] = self.REQUEST.get('highlightQuery','') + pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') + pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10') + 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 + if tocSize%tocPageSize>0: + tocPages=tocSize/tocPageSize+1 + else: + tocPages=tocSize/tocPageSize + pageinfo['tocPN'] = min (tocPages,toc) + pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') + pageinfo['sn'] =self.REQUEST.get('sn','') + return pageinfo + +def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): + """init document viewer""" + self.title=title + self.digilibBaseUrl = digilibBaseUrl + self.thumbrows = thumbrows + self.thumbcols = thumbcols + self.authgroups = [s.strip().lower() for s in authgroups.split(',')] + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + +def manage_AddDocumentViewerForm(self): + """add the viewer form""" + pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) + return pt() + +def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): + """add the viewer""" + newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) + self._setObject(id,newObj) + + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + +## DocumentViewerTemplate class +class DocumentViewerTemplate(ZopePageTemplate): + """Template for document viewer""" + meta_type="DocumentViewer Template" + + +def manage_addDocumentViewerTemplateForm(self): + """Form for adding""" + pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) + return pt() + +def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, + REQUEST=None, submit=None): + "Add a Page Template with optional file content." + + self._setObject(id, DocumentViewerTemplate(id)) + ob = getattr(self, id) + txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() + logging.info("txt %s:"%txt) + ob.pt_edit(txt,"text/html") + if title: + ob.pt_setTitle(title) + try: + u = self.DestinationURL() + except AttributeError: + u = REQUEST['URL1'] + + u = "%s/%s" % (u, urllib.quote(id)) + REQUEST.RESPONSE.redirect(u+'/manage_main') + return '' + + + diff -r 4e84c53e49b3 -r beb7ccb92564 version.txt --- a/version.txt Wed Nov 24 17:01:26 2010 +0100 +++ b/version.txt Thu Jul 14 19:43:56 2011 +0200 @@ -1,1 +1,1 @@ -DocumentViewer 0.6.0 \ No newline at end of file +DocumentViewer 0.7.0 \ No newline at end of file