Page History

<dfdl:defineFormat name="foldedLines">
  <dfdl:format layerTransform="foldedLines" dfdl:layerLengthKind="delimitedboundaryMark"/>
</dfdl:defineFormat>

<dfdl:defineFormat name="base64">
  <dfdl:format layerTransform="base64" layerEncoding="us-ascii" layerLengthKind="delimitedboundaryMark" layerBoundaryMark='{ ./marker }'/>
  <!-- note expression above is ./marker, not ../marker -->
</dfdl:defineFormat>

 <xs:sequence dfdl:ref="tns:foldedLines">
   <xs:sequence>
     ...
     ... presumably everything here is textual, and utf-8. FoldedLines only applies sensibly to text.
     ...
     <xs:element name="marker" type="xs:string" .../>
     <xs:sequence dfdl:ref="tns:base64">
        <xs:sequence>
          ...
          ... everything here is parsed against the bytes obtained from base64 decoding
          ... which is itself decoding the output of the foldedLines transform
          ... above. Base64 requires only us-ascii, which is a subset of utf-8.
          ...
        </xs:sequence><!-- end base64 data -->
      </xs:sequence><!-- end base64 sequence e.g., framing, aligning -->
   </xs:sequence><!-- end of foldedLines data-->
 </xs:sequence><!-- end foldedLines sequence e.g., framing, aligning -->

<xs:schema ....>

 <dfdl:format separatorPosition="infix" lengthKind="delimitedboundaryMark" encoding="utf-8"
  occursCountKind="parsed" separator="" sequenceKind="ordered"
  separatorPosition="infix"/>

 <dfdl:defineFormat name="folded">
  <dfdl:format layerTransform="foldedLines" layerLengthKind="delimitedboundaryMark" layerEncoding="us-ascii"/>
  <!-- delimitedboundaryMark here means to enclosing end-of-data, as no boundary mark delimiter is defined. -->
</dfdl:defineFormat>

<dfdl:defineFormat name="qp">
  <dfdl:format layerTransform="quotedPrintable" layerLengthKind="pattern"
     layerLengthPattern="[^\n]*?(?=(?<!=)\n)"/>
 
 <!-- QPs are terminated by a newline that is not preceded by an =. 
      This final newline is not consumed as part of the content. -->
  
 <!-- Alternatively, the QP transform itself can determine the length 
      by searching for this final newline (but leaving it there).
      In which case the lengthKind would be "implicit" -->
</dfdl:defineFormat>

 <xs:element name="VCalendar" dfdl:initiator="BEGIN:VCALENDAR%NL;" dfdl:terminator="END:VCALENDAR%NL; END:VCALENDAR">
  <xs:complexType>
    <xs:sequence dfdl:separator="%NL;" dfdl:sequenceKind="unordered">
      <xs:sequence dfdl:ref="tns:folded">
         <xs:element name="ProdID" type="xs:string" dfdl:initiator="PRODID:" minOccurs="0"/>
      </xs:sequence>
      <xs:element name="Version" type="xs:string" dfdl:initiator="VERSION:" minOccurs="0" />
      <xs:element name="VEvent" maxOccurs="unbounded" minOccurs="0" dfdl:occursCountKind="parsed"
        dfdl:initiator="BEGIN:VEVENT%NL;" dfdl:terminator="END:VEVENT">
        <xs:complexType>
          <xs:sequence dfdl:separator="%NL;" dfdl:sequenceKind="unordered">
            <xs:element name="DTStart" type="xs:string" dfdl:initiator="DTSTART:" />
            <xs:element name="DTEnd" type="xs:string" dfdl:initiator="DTEND:" />
            <!-- 
              content from here could have long lines, so must be folded 
            -->
            <xs:sequence dfdl:ref="tns:folded">
              <xs:element name="Location" type="xs:string" dfdl:initiator="LOCATION:" minOccurs="0"/>
              <xs:element name="UID" type="xs:string" dfdl:initiator="UID:" minOccurs="0"/>
              <xs:element name="Description" dfdl:initiator="DESCRIPTION:" minOccurs="0">
                <xs:complexType>
                  <xs:sequence>              
                   <xs:element name="Encoding" type="xs:string" 
                               dfdl:initiator="ENCODING=" dfdl:terminator=":" minOccurs="0" />
                     <xs:choice dfdl:choiceDispatchKey="{ if (fn:exists(./Encoding)) then ./Encoding else '' }">
                       <!-- 
                         we inspect the value of the Encoding element and decide what branch of the choice
                         based on it 
                        -->
                       <xs:sequence dfdl:choiceBranchKey="QUOTED-PRINTABLE">
                         dfdl:separator="" dfdl:sequenceKind="unordered">
                         <!--
                          Each branch starts with a distinct dummy element to satisfy the UPA rules of XML Schema
                         -->
                         <xs:element name="QP" type="xs:string" dfdl:inputValueCalc="{ '' }" />
                         <!--
                          Here notice tha tthe layerRef for the qp data is scoped to just this inner element.
                         -->
                         <xs:sequence dfdl:ref="tns:qp">
                           <xs:element name="Value" type="xs:string"/>
                         </xs:sequence><!-- end layer quoted printable -->
                       </xs:sequence>
                       <!-- 
                          repeat the above pattern for the choice branches for the various encodings 
                        -->
                    </xs:choice>
                  </xs:sequence>
                </xs:complexType>
              </xs:element>           
              <xs:element name="Summary" type="xs:string"  dfdl:initiator="SUMMARY:" minOccurs="0"/>
              <xs:element name="Priority" type="xs:string" dfdl:initiator="PRIORITY:" minOccurs="0" />
            </xs:sequence>
          </xs:complexType>
        </xs:element>
      </xs:sequence><!-- end folded layer -->
    </xs:sequence>
  </xs:complexType>
</xs:element>
</xs:schema>

<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:fn="http://www.w3.org/2005/xpath-functions"
  xmlns:dfdl="http://www.ogf.org/dfdl/dfdl-1.0/" xmlns:ex="http://example.com"
  targetNamespace="http://example.com" elementFormDefault="unqualified">

  <xs:include schemaLocation="built-in-formats.xsd" />

  <xs:annotation>
    <xs:appinfo source="http://www.ogf.org/dfdl/">
      <dfdl:format ref="ex:daffodilTest1" separator="" initiator=""
        terminator="" leadingSkip='0' textTrimKind="none" initiatedContent="no"
        alignment="implicit" alignmentUnits="bits" trailingSkip="0" ignoreCase="no"
        separatorPosition="infix" occursCountKind="implicit"
        emptyValueDelimiterPolicy="both" representation="text" textNumberRep="standard"
        lengthKind="delimitedboundaryMark" encoding="ASCII" />
    </xs:appinfo>
  </xs:annotation>

    <xs:element name="file" type="ex:fileType"/>

    <!-- broke this up to provide some resuable types and groups here -->

    <xs:complexType name="fileType">
      <xs:group ref="ex:fileTypeGroup"/>
    </xs:complexType>

    <xs:group name="fileTypeGroup">
      <xs:sequence dfdl:separator="%NL;" dfdl:separatorPosition="postfix">
        <xs:element name="header" minOccurs="0" maxOccurs="1"
          dfdl:occursCountKind="implicit">
          <xs:complexType>
            <xs:sequence dfdl:separator=",">
              <xs:element name="title" type="xs:string" maxOccurs="unbounded" />
            </xs:sequence>
          </xs:complexType>
        </xs:element>
        <xs:element name="record" maxOccurs="unbounded">
          <xs:complexType>
            <xs:sequence dfdl:separator=",">
              <xs:element name="item" type="xs:string" maxOccurs="unbounded"
                dfdl:occursCount="{ fn:count(../../header/title) }"
                dfdl:occursCountKind="expression" />
            </xs:sequence>
          </xs:complexType>
        </xs:element>
      </xs:sequence>
    </xs:group>

</xs:schema>