Alvis-NLPPlatform

 view release on metacpan or  search on metacpan

etc/alvis-nlpplatform/dtd/enriched-document.dtd  view on Meta::CPAN

<!ELEMENT meta (#PCDATA)>
<!ATTLIST meta name CDATA #REQUIRED>
<!-- meta.name may take values chosen from the Dublin Core element set -->

<!ELEMENT links (outlinks?, inlinks?, inlinkHosts?)>
<!ELEMENT outlinks (link*)>
<!ELEMENT inlinks (link*)>
<!ELEMENT inlinkHosts (#PCDATA)>
<!ELEMENT link (anchorText?, location)>
<!ATTLIST link type CDATA #REQUIRED>
<!-- link.type may take the following values: "a", "img", "frame" -->
<!ELEMENT anchorText (#PCDATA)>
<!ELEMENT location (#PCDATA)>
<!ATTLIST location documentId CDATA #IMPLIED>

<!ELEMENT analysis (domain?, property*, ranking*, topic*)>
<!ELEMENT domain (#PCDATA)>
<!ELEMENT property (#PCDATA)>
<!ATTLIST property name CDATA #REQUIRED>
<!ELEMENT ranking (#PCDATA)>
<!ATTLIST ranking scheme CDATA #REQUIRED>

etc/alvis-nlpplatform/nlpplatform-test.rc  view on Meta::CPAN

#text/plain ; ; GuessText

text/x-tex = tth -g -w1 -r <  

application/x-tex =  tth -g -w1 -r < 
#text/x-tex ; untex -a -e -giso ; TeXText
#application/x-tex ; untex -a -e -giso ; TeXText
#text/x-tex ;  ; TeX
#application/x-tex ; ; TeX

application/pdf = pdftohtml -i -noframes -nomerge -stdout 
#application/pdf ; pstotext ; Text
application/postscript = pstotext 
application/msword = antiword -t 

application/vnd.ms-excel =  xlhtml -fw 

application/vnd.ms-powerpoint = ppthtml 
application/powerpoint = ppthtml 

application/rtf = unrtf --nopict --html 

etc/alvis-nlpplatform/nlpplatform.rc  view on Meta::CPAN

#text/plain ; ; GuessText

text/x-tex = tth -g -w1 -r <  

application/x-tex =  tth -g -w1 -r < 
#text/x-tex ; untex -a -e -giso ; TeXText
#application/x-tex ; untex -a -e -giso ; TeXText
#text/x-tex ;  ; TeX
#application/x-tex ; ; TeX

application/pdf = pdftohtml -i -noframes -nomerge -stdout 
#application/pdf ; pstotext ; Text
application/postscript = pstotext 
application/msword = antiword -t 

application/vnd.ms-excel =  xlhtml -fw 

application/vnd.ms-powerpoint = ppthtml 
application/powerpoint = ppthtml 

application/rtf = unrtf --nopict --html 

etc/alvis-nlpplatform/xsd/enriched-document.xsd  view on Meta::CPAN

    <xs:complexType>
      <xs:sequence>
        <xs:element minOccurs="0" ref="enriched:anchorText"/>
        <xs:element ref="enriched:location"/>
      </xs:sequence>
      <xs:attribute name="type" use="required">
        <xs:simpleType>
          <xs:restriction base="xs:NCName">
            <xs:enumeration value="a"/>
            <xs:enumeration value="img"/>
            <xs:enumeration value="frame"/>
            <xs:enumeration value="text"/>
            <xs:enumeration value="area"/>
          </xs:restriction>
        </xs:simpleType>
      </xs:attribute>
    </xs:complexType>
  </xs:element>
  <xs:element name="anchorText" type="xs:string"/>
  <xs:element name="location">
    <xs:complexType mixed="true">

examples/nlpplatform-test.rc  view on Meta::CPAN

#text/plain ; ; GuessText

text/x-tex = tth -g -w1 -r <  

application/x-tex =  tth -g -w1 -r < 
#text/x-tex ; untex -a -e -giso ; TeXText
#application/x-tex ; untex -a -e -giso ; TeXText
#text/x-tex ;  ; TeX
#application/x-tex ; ; TeX

application/pdf = pdftohtml -i -noframes -nomerge -stdout 
#application/pdf ; pstotext ; Text
application/postscript = pstotext 
application/msword = antiword -t 

application/vnd.ms-excel =  xlhtml -fw 

application/vnd.ms-powerpoint = ppthtml 
application/powerpoint = ppthtml 

application/rtf = unrtf --nopict --html