view release on metacpan or  search on metacpan

t/test-data/to-split/29.xml  view on Meta::CPAN

      <semantic_unit><named_entity><form>Gmail</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>MSN</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Yahoo News</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Yahoo Finance</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google Blog</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>MSN MoneyCentral</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Flash</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>way Google</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google Blog Search</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google News</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
    </semantic_unit_level>
  </linguisticAnalysis>

  </documentRecord>
<documentRecord id="48FFC0A03C2756C583F6D80C9E527393" xmlns="http://alvis.info/enriched/">
    <acquisition>
      <acquisitionData>
        <modifiedDate>1142422246164</modifiedDate>
        <httpServer>Apache/1.3.33 (Unix)</httpServer>
        <urls>
          <url>http://blog.outer-court.com/archive/2006-03-15-n42.html</url>
        </urls>
      </acquisitionData>
      <canonicalDocument>        
        <section>Google releases their desktop search tool in an updated version today. Among some bugfixes, there’s a new Quick Search box. Hit Ctrl twice to make it appear in the middle of your desktop, and then search for anything – your compu...
      <metaData>
        <meta name="title">Google Desktop's Quick Search Box</meta>
        <meta name="dc:date">Wed, 15 Mar 2006 11:20:57 GMT</meta>
        <meta name="dc:type">text/html</meta>
      </metaData>
      <links>
        <outlinks>
          <link type="a">
            <anchorText>Quick Search box</anchorText>
            <location>http://desktop.google.com/features.html#quicksearch</location>
          </link>
        </outlinks>
      </links>
    </acquisition>
  <linguisticAnalysis>
    <semantic_unit_level>
      <semantic_unit><named_entity><form>Brin</form><named_entity_type>person</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google</form><named_entity_type>comp</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google Desktop</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
    </semantic_unit_level>
  </linguisticAnalysis>

  </documentRecord>
<documentRecord id="18C9FD35812DFC4D4CCF0FD6AC1646BC" xmlns="http://alvis.info/enriched/">
    <acquisition>
      <acquisitionData>
        <modifiedDate>1149133052555</modifiedDate>
        <httpServer>Apache/1.3.33 (Unix)</httpServer>
        <urls>
          <url>http://blog.outer-court.com/archive/2006-05-30-n12.html</url>
        </urls>
      </acquisitionData>
      <canonicalDocument>        
        <section>Some bloggers are complaining that Google didn’t have a Memorial day logo yesterday. Memorial Day “commemorates U.S. men and women who have died in military service,”Wikipedia explains. From a comment at Newsbusters by Warner T...
      <metaData>
        <meta name="title">Complaints Due to Lack of Google Memorial Day Logo</meta>
        <meta name="dc:date">Thu, 01 Jun 2006 02:44:56 GMT</meta>
        <meta name="dc:type">text/html</meta>
      </metaData>
      <links>
        <outlinks>
          <link type="a">
            <anchorText>it’s good the way it is</anchorText>
            <location>http://blog.lewrockwell.com/lewrw/archives/010666.html</location>
          </link>
          <link type="a">
            <anchorText>Wikipedia</anchorText>
            <location>http://en.wikipedia.org/wiki/Memorial_Day</location>
          </link>
          <link type="a">
            <anchorText>a comment at Newsbusters</anchorText>
            <location>http://newsbusters.org/node/5580</location>
          </link>
          <link type="a">
            <anchorText>Some bloggers</anchorText>
            <location>http://technorati.com/search/google%20memorial</location>
          </link>
        </outlinks>
      </links>
    </acquisition>
  <linguisticAnalysis>
    <semantic_unit_level>
      <semantic_unit><named_entity><form>Google</form><named_entity_type>comp</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Wikipedia</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
    </semantic_unit_level>
  </linguisticAnalysis>

  </documentRecord>
<documentRecord id="0770964CAC923ACCDC189E0EA4208AE0" xmlns="http://alvis.info/enriched/">
    <acquisition>
      <acquisitionData>
        <modifiedDate>1141993156883</modifiedDate>
        <httpServer>Apache/1.3.34 (Unix) DAV/1.0.3 mod_auth_passthrough/1.8 mod_log_bytes/1.2 mod_bwlimited/1.4 PHP/4.4.1 FrontPage/5.0.2.2635 mod_ssl/2.8.25 OpenSSL/0.9.7a</httpServer>
        <urls>
          <url>http://battellemedia.com/archives/002391.php</url>
        </urls>
      </acquisitionData>
      <canonicalDocument>        
        <section>From a Reuters story: Sen. Ron Wyden on Thursday proposed legislation aimed at preventing high-speed Internet service providers from charging content companies extra so consumers have faster access to their Web sites or receive speci...
      <metaData>
        <meta name="title">Net Neutrality Bill Unveiled</meta>
        <meta name="dc:type">text/html</meta>
      </metaData>
      <links>
        <outlinks>
          <link type="a">
            <anchorText>IPDemocracy</anchorText>
            <location>http://www.ipdemocracy.com/archives/2006/03/02/index.php#001213</location>
          </link>
          <link type="a">
            <anchorText>just joined FM</anchorText>
            <location>http://fmpub.net/archives/2006/03/were_growingmee.php</location>
          </link>