The R Project SVN R-packages

<?xml version="1.0" encoding="UTF-8"?>
<response>
  <lst name="responseHeader">
    <int name="status">0</int>
    <int name="QTime">90</int>
  </lst>
  <lst name="index">  <!-- ANN: Provides info about the state of the index -->
    <int name="numDocs">17</int>
    <int name="maxDoc">17</int>
    <int name="numTerms">1044</int>
    <long name="version">1297337332283</long>
    <bool name="optimized">true</bool>
    <bool name="current">true</bool>
    <bool name="hasDeletions">false</bool>
    <str name="directory"> <!-- ANN: The choice of Directory can sometimes effect performance.  Lucene tries to automatically pick the correct one, but it is sometimes worthwhile to try other options, especially on Windows. -->
      org.apache.lucene.store.NIOFSDirectory:org.apache.lucene.store.NIOFSDirectory@[{PATH}/dev/trunk/solr/example/solr/data/index
      lockFactory=org.apache.lucene.store.NativeFSLockFactory@349319d9
    </str>
    <date name="lastModified">2011-02-10T11:29:03Z</date>
  </lst>
  <lst name="fields"> <!-- ANN: Provide stats and metadata about the fields in the index -->
    <lst name="store_0_coordinate">
      <str name="type">tdouble</str> <!-- ANN: The FieldType, see the schema.xml -->
      <str name="schema">IT-----OF----</str> <!-- ANN: The key/legend at the bottom says what each entry in this list is.  This field is indexed, tokenized, Omits norms and sorts missing first -->
      <str name="dynamicBase">*_coordinate</str> <!-- ANN: This field is a "polyField" and actually corresponds to multiple Lucene fields -->
      <str name="index">(unstored field)</str>
      <int name="docs">14</int> <!-- ANN: 14 documents have a value for this field -->
      <int name="distinct">64</int> <!-- ANN: There are 64 distinct terms -->
      <lst name="topTerms">
        <int name="2.0">14</int> <!-- ANN: The token "2.0" occurs 14 times in the field -->
        <int name="44.0">6</int>
        <int name="37.775177001953125">4</int>
        <int name="37.7734375">4</int>
        <int name="37.77519989013672">4</int>
        <int name="36.0">4</int>
        <int name="37.7752">4</int>
        <int name="37.77519999999822">4</int>
        <int name="37.77519999956712">4</int>
        <int name="40.71429991722107">2</int>
      </lst>
      <lst name="histogram"> <!-- ANN: The histogram measures the distribution of the distinct terms across the documents -->
        <int name="1">46</int> <!-- ANN: 46 of the 64 terms occur in only 1 document -->
        <int name="2">9</int> <!-- ANN: 9 of the 64 terms occur in 2 or 3 (TODO: Check this) -->
        <int name="4">7</int>
        <int name="8">1</int>
        <int name="16">1</int>
      </lst>
    </lst>
    <lst name="text">
      <str name="type">text</str>
      <str name="schema">IT-M---------</str>
      <str name="index">(unstored field)</str>
      <int name="docs">17</int>
      <int name="distinct">389</int>
      <lst name="topTerms">
        <int name="electron">14</int>
        <int name="2">8</int>
        <int name="inc">8</int>
        <int name="x">8</int>
        <int name="1">8</int>
        <int name="gb">7</int>
        <int name="3">7</int>
        <int name="0">6</int>
        <int name="20">5</int>
        <int name="mb">5</int>
      </lst>
      <lst name="histogram">
        <int name="1">278</int>
        <int name="2">67</int>
        <int name="4">31</int>
        <int name="8">12</int>
        <int name="16">1</int>
      </lst>
    </lst>
    <lst name="cat">
      <str name="type">string</str>
      <str name="schema">I-SM---OF---l</str>
      <str name="index">I-S----O----</str>
      <int name="docs">16</int>
      <int name="distinct">14</int>
      <lst name="topTerms">
        <int name="electronics">14</int>
        <int name="memory">3</int>
        <int name="graphics card">2</int>
        <int name="search">2</int>
        <int name="hard drive">2</int>
        <int name="connector">2</int>
        <int name="software">2</int>
        <int name="monitor">2</int>
        <int name="copier">1</int>
        <int name="music">1</int>
      </lst>
      <lst name="histogram">
        <int name="1">6</int>
        <int name="2">6</int>
        <int name="4">1</int>
        <int name="8">0</int>
        <int name="16">1</int>
      </lst>
    </lst>
    <!-- ... -->
  </lst>
  <lst name="info">
    <lst name="key">
      <str name="I">Indexed</str>
      <str name="T">Tokenized</str>
      <str name="S">Stored</str>
      <str name="M">Multivalued</str>
      <str name="V">TermVector Stored</str>
      <str name="o">Store Offset With TermVector</str>
      <str name="p">Store Position With TermVector</str>
      <str name="O">Omit Norms</str>
      <str name="L">Lazy</str>
      <str name="B">Binary</str>
      <str name="f">Sort Missing First</str>
      <str name="l">Sort Missing Last</str>
    </lst>
    <str name="NOTE">Document Frequency (df) is not updated when a document is marked for deletion. df values include
      deleted documents.
    </str>
  </lst>
</response>