pextract.dfdl.xsd

<?xml version="1.0" encoding="UTF-8" ?>
<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:pextract="http://keeleleek.ee/pextract"
  targetNamespace="http://keeleleek.ee/pextract"
  elementFormDefault="qualified"
  attributeFormDefault="unqualified">

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

<xs:annotation>
  <xs:appinfo source="http://www.ogf.org/dfdl/">
    <dfdl:format  ref="pextract: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="delimited" encoding="UTF-8" />
  </xs:appinfo>
</xs:annotation>

<!-- The document element is a 'paradigm-file' -->
<xs:element name="paradigm-file">
    <xs:complexType>
      <!-- A paradigm-file consists of rows that each describe a 'paradigm' -->
      <xs:sequence dfdl:separator="%NL;" dfdl:separatorPosition="postfix">
        <xs:element name="paradigm" maxOccurs="unbounded" dfdl:occursCountKind="parsed">
          <xs:complexType>
            <!-- a 'paradigm' consists of two parts (separated by a tab):
                 1) a 'paradigm-description' and
                 2) a list of attested 'variable-values'
            -->
            <xs:sequence dfdl:separator="%HT;">
              <!-- The first part of a 'paradigm' is the 'paradigm-description' -->
              <xs:element name="paradigm-description">
                <xs:complexType>
                  <!-- A 'paradigm-description' consists of 'paradigm-cells'  -->
                  <xs:sequence dfdl:separator="#">
                    <xs:element name="paradigm-cell" maxOccurs="unbounded">
                      <xs:complexType>
                        <!-- A 'paradigm-cell' consists of two parts:
                             1) a 'pattern' and
                             2) the patterns 'msd-descriptions' -->
                        <xs:sequence>
                          <xs:element name="pattern" dfdl:terminator=":">
                            <xs:complexType>
                              <xs:sequence dfdl:separator="+" dfdl:separatorPosition="infix" dfdl:separatorSuppressionPolicy="trailingEmpty">
                                <!-- A 'pattern' consists of 'pattern-part' that are either:
                                     @todo 1) variables
                                     @todo 2) constants
                                -->
                                <xs:element name="pattern-part" type="xs:string" maxOccurs="unbounded" />
                              </xs:sequence>
                            </xs:complexType>
                          </xs:element>
                          <!-- The 'msd-description' hold a list of morphosyntactic features (key-value pairs) -->
                          <xs:element name="msd-description">
                            <xs:complexType>
                              <xs:sequence dfdl:separator=",">
                                <xs:element name="feature" maxOccurs="unbounded">
                                  <xs:complexType>
                                    <xs:sequence>
                                      <xs:element name="name"  type="xs:string" dfdl:terminator="=" />
                                      <xs:element name="value" type="xs:string"/>
                                    </xs:sequence>
                                  </xs:complexType>
                                </xs:element>
                              </xs:sequence>
                            </xs:complexType>
                          </xs:element>
                        </xs:sequence>
                      </xs:complexType>
                    </xs:element>
                  </xs:sequence>
                </xs:complexType>
              </xs:element>
              <!-- The second part of a paradigm is a list of attested 'variable-values' -->
              <xs:element name="variable-values">
                <xs:complexType>
                  <xs:sequence dfdl:separator="#" dfdl:separatorPosition="infix" dfdl:separatorSuppressionPolicy="trailingEmpty">
                    <xs:element name="variable-set" maxOccurs="unbounded">
                      <xs:complexType>
                        <xs:sequence dfdl:separator="," dfdl:separatorPosition="infix" dfdl:separatorSuppressionPolicy="trailingEmpty">
                          <xs:element name="variable" maxOccurs="unbounded">
                            <xs:complexType>
                              <xs:sequence>
                                <xs:element name="variable-number" type="xs:integer" dfdl:terminator="=" />
                                <xs:element name="variable-value"  type="xs:string"/>
                              </xs:sequence>
                            </xs:complexType>
                          </xs:element>
                        </xs:sequence>
                      </xs:complexType>
                    </xs:element>
                  </xs:sequence>
                </xs:complexType>
              </xs:element>
            </xs:sequence>
          </xs:complexType>
        </xs:element>
      </xs:sequence>
    </xs:complexType>
</xs:element>
</xs:schema>