version 1.42, 2010/09/27 12:59:40
|
version 1.53, 2010/10/05 12:13:11
|
Line 123 class MpdlXmlTextServer(SimpleItem):
|
Line 123 class MpdlXmlTextServer(SimpleItem):
|
if 'numPages' in docinfo: |
if 'numPages' in docinfo: |
# already there |
# already there |
return docinfo |
return docinfo |
|
|
xquery = '//pb' |
xquery = '//pb' |
text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) |
text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) |
#text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) |
|
docinfo['numPages'] = text.count("<pb ") |
docinfo['numPages'] = text.count("<pb ") |
return docinfo |
return docinfo |
|
|
|
def getNumTextPages (self, docinfo): |
|
"""get list of pages from fulltext (texts without images) and put in docinfo""" |
|
if 'numPages' in docinfo: |
|
# allredy there |
|
return docinfo |
|
xpath ='/count(//pb)' |
|
text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'], xpath)) |
|
logging.debug("documentViewer (text) text: %s"%(text)) |
|
#docinfo['numPages']=text('resultPage') |
|
pagedom = Parse(text) |
|
|
|
result= dom.xpath("//result/resultPage") |
|
docinfo['numPages']=int(getTextFromNode(result[0])) |
|
#logging.debug("documentViewer (characterNormalization) docinfo['numPages']: %s"%(docinfo['numPages'])) |
|
return docinfo |
|
|
def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization=""): |
def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization=""): |
"""returns single page from fulltext""" |
"""returns single page from fulltext""" |
docpath = docinfo['textURLPath'] |
docpath = docinfo['textURLPath'] |