Word DOCX – default import config file

Following is the default config used when importing a DOCX. It can be edited to get specific results.

Default import config

Following is the default config file for the Word import. It can be used as a starting point for customizing the import process.

<?xml version="1.0"?>

<!-- This configuration transforms DOCX into PSML -->

<config version="1.5.0">

  <lists>
    <convert-to-list-roles select="false"/>
    <!-- generate numbered attribute to paragraphs for lists -->
    <convert-to-numbered-paragraphs select="false">
      <level value="1" output="prefix"/>
      <!-- prefix or numbering or inline=[label] or text -->
      <level value="2" output="prefix"/>
      <level value="3" output="prefix"/>
      <level value="4" output="prefix"/>
      <level value="5" output="prefix"/>
      <level value="6" output="prefix"/>
    </convert-to-numbered-paragraphs>

    <!-- generate manual prefixes for numbering followed directly by one or more
         pipes then tab where the number of pipes is the level/indent -->
    <convert-manual-numbering select="true">
      <value match="\s*([^\|]+)\|\t\s*">
        <prefix level="1"/>
      </value>
      <value match="\s*([^\|]+)\|\|\t\s*">
        <prefix level="2"/>
      </value>
      <value match="\s*([^\|]+)\|\|\|\t\s*">
        <prefix level="3"/>
      </value>
      <value match="\s*([^\|]+)\|\|\|\|\t\s*">
        <prefix level="4"/>
      </value>
      <value match="\s*([^\|]+)\|\|\|\|\|\t\s*">
        <prefix level="5"/>
      </value>
      <value match="\s*([^\|]+)\|\|\|\|\|\|\t\s*">
        <prefix level="6"/>
      </value>
    </convert-manual-numbering>
  </lists>

  <!-- =======================STYLE PROPERTIES======================= -->

  <!-- Values accepted: name of style available in word file -->
  <styles>
    <ignore>
      <wordstyle value="TOC1" />
      <wordstyle value="TOC2" />
      <wordstyle value="TOC3" />
      <wordstyle value="TOC4" />
      <wordstyle value="TOC5" />
      <wordstyle value="TOC6" />
      <wordstyle value="TOC7" />
      <wordstyle value="TOC8" />
      <wordstyle value="TOC9" />
    </ignore>
    <default>
      <paragraphStyles value="block" />
      <!-- possible values: 'para' or 'block' -->
      <characterStyles value="inline" />
      <!-- possible values: 'none' or 'inline' -->
      <smart-tag keep="true" />
      <references psmlelement="link" /> <!-- required when using PSML split config -->
      <!--  <property name="prefix" value="true" /> possible values: 'false' or 'true' -->
    </default>

    <!-- Values accepted: name of style available in word file -->
    <wordstyle name="Title" psmlelement="heading">
      <level value="1" />
    </wordstyle>

    <wordstyle name="Subtitle" psmlelement="heading">
      <level value="3" />
    </wordstyle>

    <wordstyle name="Heading1" psmlelement="heading">
      <level value="1" />
      <!-- <numbering select="true" value="numbering" /> -->
    </wordstyle>

    <wordstyle name="Heading2" psmlelement="heading">
      <level value="2" />
    </wordstyle>

    <wordstyle name="Heading3" psmlelement="heading">
      <level value="3" />
    </wordstyle>

    <wordstyle name="Heading4" psmlelement="heading">
      <level value="4" />
    </wordstyle>

    <wordstyle name="Heading5" psmlelement="heading">
      <level value="5" />
    </wordstyle>

    <wordstyle name="Heading6" psmlelement="heading">
      <level value="6" />
    </wordstyle>

    <wordstyle name="HeadingUnnum1" psmlelement="heading">
      <level value="1" />
    </wordstyle>

    <wordstyle name="HeadingUnnum2" psmlelement="heading">
      <level value="2" />
    </wordstyle>

    <wordstyle name="HeadingUnnum3" psmlelement="heading">
      <level value="3" />
    </wordstyle>

    <wordstyle name="HeadingUnnum4" psmlelement="heading">
      <level value="4" />
    </wordstyle>

    <wordstyle name="HeadingUnnum5" psmlelement="heading">
      <level value="5" />
    </wordstyle>

    <wordstyle name="HeadingUnnum6" psmlelement="heading">
      <level value="6" />
    </wordstyle>

    <wordstyle name="HTMLCode" psmlelement="monospace"/>

    <wordstyle name="Emphasis" psmlelement="italic"/>

    <wordstyle name="Strong" psmlelement="bold"/>

    <wordstyle name="HTMLPreformatted" psmlelement="preformat"/>

    <wordstyle name="BodyText" psmlelement="para"/>

    <wordstyle name="PSTableHeader" psmlelement="para"/>

    <wordstyle name="PSTableBody" psmlelement="para"/>

    <wordstyle name="FootnoteText" psmlelement="para" />

    <wordstyle name="EndnoteText" psmlelement="para" />
  </styles>


</config>