source: trunk/gli/classes/xml/import.xml@ 7510

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE Info [
  <!ELEMENT Info      (Name, Desc, Arguments)>
  <!ELEMENT Arguments (Option*)>
  <!ELEMENT Option    (Name, Desc, Type, Required, Range, Default?, List?)>
  <!ELEMENT Name      (#PCDATA)>
  <!ELEMENT Desc      (#PCDATA)>
  <!ELEMENT Type      (#PCDATA)>
  <!ELEMENT Required  (#PCDATA)>
  <!ELEMENT Range     (#PCDATA)>
  <!ELEMENT Default   (#PCDATA)>
  <!ELEMENT List      (Value*)>
  <!ELEMENT Value     (Name, Desc?)>
  <!ELEMENT HiddenGLI (#PCDATA)>
]>

<Info>
  <Name>import.pl</Name>
  <Desc>PERL script used to import files into a GML format ready for building.</Desc>
  <Arguments>
    <Option>
      <Name>archivedir</Name>
      <Desc>{import.achivedir}</Desc>
      <Type>string</Type>
      <Required>no</Required>
      <HiddenGLI>yes</HiddenGLI>
    </Option>
    <Option>
      <Name>collectdir</Name>
      <Desc>Collection directory.</Desc>
      <Type>string</Type>
      <Required>no</Required>
      <Default>/research/jmt12/gsdl/collect</Default>
      <HiddenGLI>yes</HiddenGLI>
    </Option>
    <Option>
      <Name>debug</Name>
      <Desc>Print imported text to STDOUT.</Desc>
      <Type>flag</Type>
      <Required>no</Required>
    </Option>
    <Option>
      <Name>faillog</Name>
      <Desc>Fail log filename. This log receives the filenames of any files which fail to be processed.</Desc>
      <Type>string</Type>
      <Required>no</Required>
      <Default>&lt;collectdir&gt;/colname/etc/fail.log</Default>
    </Option>
    <Option>
      <Name>groupsize</Name>
      <Desc>Number of import documents to group into one XML file.</Desc>
      <Type>int</Type>
      <Required>no</Required>
      <Default>1</Default>
    </Option>
    <Option>
      <Name>gzip</Name>
      <Desc>Use gzip to compress resulting xml documents (don't forget to include ZIPPlug in your plugin list when building from compressed documents).</Desc>
      <Type>flag</Type>
      <Required>no</Required>
    </Option>
    <Option>
      <Name>importdir</Name>
      <Desc>Where the original material lives.</Desc>
      <Type>string</Type>
      <Required>no</Required>
      <HiddenGLI>yes</HiddenGLI>
    </Option>
    <Option>
      <Name>keepold</Name>
      <Desc>Will not destroy the current contents of the archives directory (the default).</Desc>
      <Type>flag</Type>
      <Required>no</Required>
    </Option>
    <Option>
      <Name>language</Name>
      <Desc>Language to display option descriptions in (eg. 'en_US' specifies American English). Requires translations of the option descriptions to exist in the perllib/strings_language-code.rb file.</Desc>
      <Type>string</Type>
      <Required>no</Required>
    </Option>
    <Option>
      <Name>maxdocs</Name>
      <Desc>Maximum number of documents to import.</Desc>
      <Type>int</Type>
      <Required>no</Required>
    </Option>
    <Option>
      <Name>OIDtype</Name>
      <Desc>The method to use when generating unique identifiers for each document.</Desc>
      <Type>enum</Type>
      <Required>no</Required>
      <List>
        <Value>
          <Name>hash</Name>
          <Desc>Hashes the contents of the file. Document identifier will be the same every time the collection is imported.</Desc>
        </Value>
        <Value>
          <Name>incremental</Name>
          <Desc>A simple document count that is significantly faster than "hash". It is not guaranteed to always assign the same identifier to a given document though and does not allow further documents to be added to existing xml archives.</Desc>
        </Value>
      </List>
      <Default>hash</Default>
    </Option>
    <Option>
      <Name>out</Name>
      <Desc>Filename or handle to print output status to.</Desc>
      <Type>string</Type>
      <Required>no</Required>
      <Default>STDERR</Default>
    </Option>
    <Option>
      <Name>removeold</Name>
      <Desc>Will remove the old contents of the archives directory -- use with care.</Desc>
      <Type>flag</Type>
      <Required>no</Required>
    </Option>
    <Option>
      <Name>sortmeta</Name>
      <Desc>Sort documents alphabetically by metadata for building. This will be disabled if groupsize &gt; 1.</Desc>
      <Type>metadata</Type>
      <Required>no</Required>
    </Option>
    <Option>
      <Name>statsfile</Name>
      <Desc>Filename or handle to print import statistics to.</Desc>
      <Type>string</Type>
      <Required>no</Required>
      <Default>STDERR</Default>
    </Option>
    <Option>
      <Name>verbosity</Name>
      <Desc>Controls the quantity of output. 0=none, 3=lots.</Desc>
      <Type>int</Type>
      <Required>no</Required>
      <Range>0,3</Range>
      <Default>2</Default>
    </Option>
  </Arguments>
</Info>