Re: General Purpose Dictionary Generator

On 10/26/06, Alex Fink <a4pq1injbok_0@...> wrote:
> This is a great idea.  I'd actually been recently thinking that I should
> convert my conlangs' lexica to a more structured format (they're currently
> in un-marked-up and inconsistently-formatted human-readable text files) so I
> could process them by computer; this would be perfect for that.
It's also similar to my own conversion from Shoebox to XML. I'm
mid-conversion, but I do have an XML Schema. Perhaps it can be used as
a basis for this program, or at least to spur discussion? In either
capacity, it might prove helpful.

A (very small) example file might look like:

<lexicon lexeme-lang="x-foo" document-lang="en">
   <person role="author">
      <name>Arthaey Angosii</name>
      <email>arthaey@gmail.com</email>
   </person>
   <entry>
      <lexeme>foo</lexeme>
      <cxs>fu</cxs>
      <word-class>pron</word-class>
      <gloss>whatever</gloss>
      <gloss lang="es">cualquier</gloss>
   </entry>
</lexicon>

The schema itself supports much more than shown in the example:
multiple pronuncation schemes, definitions in addition to short
glosses, semantic domains, multiple example sentences,
cross-references (such as synonyms), notes, subentries, and senses.

Below my signature (for easy skipping) is the 193-line schema file. (I
would have attached it and not bothered those not interested, but I
assume the listserv kills attachments.)

Please also note that it's my first schema, and as such I may have
done things in less-than-optimal ways just to get it to validate. :P


--
AA
http://conlang.arthaey.com




<?xml version="1.0" encoding="UTF-8"?>
<xs:schema
   targetNamespace="http://lexicon.arthaey.com/"
   xmlns:lex="http://lexicon.arthaey.com/"
   xmlns:xs="http://www.w3.org/2001/XMLSchema"
   elementFormDefault="qualified"
   attributeFormDefault="unqualified"
>
   <!-- definitions of groups -->

   <xs:group name="entry-info">
      <xs:sequence>
         <xs:element name="lexeme" type="lex:textType" />
         <!-- pronunciation -->
         <xs:sequence maxOccurs="5">
            <xs:element name="ad-hoc" type="xs:token" minOccurs="0" />
            <xs:element name="cxs" type="xs:token" minOccurs="0" />
            <xs:element name="ipa" type="xs:token" minOccurs="0" />
            <xs:element name="sampa" type="xs:token" minOccurs="0" />
            <xs:element name="x-sampa" type="xs:token" minOccurs="0" />
         </xs:sequence>
         <xs:element name="word-class" type="xs:token" />
         <xs:element name="gloss" type="lex:textType" />
         <xs:element name="definition" type="lex:textType"
            minOccurs="0" maxOccurs="unbounded" />
         <xs:element name="domain" type="lex:textType"
            minOccurs="0" maxOccurs="unbounded" />
         <xs:element name="example" minOccurs="0" maxOccurs="unbounded">
            <xs:complexType>
               <xs:sequence>
                  <xs:element name="text" type="lex:textTypeRequired"
                     maxOccurs="unbounded"/>
                  <xs:element name="date" type="xs:date" />
                  <xs:element name="note" type="lex:noteType"
                     minOccurs="0" maxOccurs="unbounded" />
               </xs:sequence>
            </xs:complexType>
         </xs:element>
         <xs:element name="xref" type="lex:xrefType"
            minOccurs="0" maxOccurs="unbounded" />
         <xs:element name="note" type="lex:noteType"
            minOccurs="0" maxOccurs="unbounded" />
         <xs:element name="subentry" minOccurs="0" maxOccurs="unbounded">
            <xs:complexType>
               <xs:sequence>
                  <xs:element name="lexeme" type="lex:textType" />
                  <!-- pronunciation -->
                  <xs:sequence minOccurs="0" maxOccurs="5">
                     <xs:element name="ad-hoc" type="xs:token" minOccurs="0" />
                     <xs:element name="cxs" type="xs:token" minOccurs="0" />
                     <xs:element name="ipa" type="xs:token" minOccurs="0" />
                     <xs:element name="sampa" type="xs:token" minOccurs="0" />
                     <xs:element name="x-sampa" type="xs:token" minOccurs="0" />
                  </xs:sequence>
                  <xs:element name="word-class" type="xs:token" minOccurs="0" />
                  <xs:element name="gloss" type="lex:textType" />
                  <xs:element name="definition" type="lex:textType"
                     minOccurs="0" maxOccurs="unbounded" />
                  <xs:element name="domain" type="lex:textType"
                     minOccurs="0" maxOccurs="unbounded" />
                  <xs:element name="example" minOccurs="0"
maxOccurs="unbounded">
                     <xs:complexType>
                        <xs:sequence>
                           <xs:element name="text" type="lex:textTypeRequired"
                              maxOccurs="unbounded"/>
                           <xs:element name="date" type="xs:date" />
                           <xs:element name="note" type="lex:noteType"
                              minOccurs="0" maxOccurs="unbounded" />
                        </xs:sequence>
                     </xs:complexType>
                  </xs:element>
                  <xs:element name="xref" type="lex:xrefType"
                     minOccurs="0" maxOccurs="unbounded" />
                  <xs:element name="note" type="lex:noteType"
                     minOccurs="0" maxOccurs="unbounded" />
                  <xs:element name="date" type="xs:date" minOccurs="0" />
               </xs:sequence>
            </xs:complexType>
         </xs:element>
         <xs:element name="date" type="xs:date" />
      </xs:sequence>
   </xs:group>

   <xs:group name="nameGroup">
      <xs:choice>
         <xs:element name="name" type="xs:token" />
         <!-- full name -->
         <xs:sequence>
            <xs:element name="personal-name" type="xs:token" maxOccurs="3" />
            <xs:element name="middle-name" type="xs:token" maxOccurs="3" />
            <xs:element name="family-name" type="xs:token" maxOccurs="3" />
         </xs:sequence>
      </xs:choice>
   </xs:group>

   <!-- definitions of simple types -->

   <xs:simpleType name="xrefEnum">
      <xs:restriction base="xs:token">
         <xs:enumeration value="antonym" />
         <xs:enumeration value="etymology" />
         <xs:enumeration value="see" />
         <xs:enumeration value="synonym" />
      </xs:restriction>
   </xs:simpleType>

   <!-- definitions of complex types -->

   <xs:complexType name="textTypeRequired">
      <xs:simpleContent>
         <xs:extension base="xs:token">
            <xs:attribute name="lang" type="xs:language" use="required" />
         </xs:extension>
      </xs:simpleContent>
   </xs:complexType>

   <xs:complexType name="textType">
      <xs:simpleContent>
         <xs:extension base="xs:token">
            <xs:attribute name="lang" type="xs:language" />
         </xs:extension>
      </xs:simpleContent>
   </xs:complexType>

   <xs:complexType name="noteType" mixed="true">
      <xs:complexContent>
         <xs:restriction base="xs:anyType">
            <xs:sequence>
               <xs:any namespace="##any" processContents="lax"
                  minOccurs="0" maxOccurs="unbounded" />
            </xs:sequence>
            <xs:attribute name="type" type="xs:token" />
         </xs:restriction>
      </xs:complexContent>
   </xs:complexType>

   <xs:complexType name="xrefType">
      <xs:simpleContent>
         <xs:extension base="lex:textType">
            <xs:attribute name="type" type="lex:xrefEnum" use="required" />
         </xs:extension>
      </xs:simpleContent>
   </xs:complexType>

   <!-- definitions of complex elements -->

   <xs:element name="lexicon">
      <xs:complexType>
         <xs:sequence>
            <xs:element name="person">
               <xs:complexType>
                  <xs:sequence>
                     <xs:group ref="lex:nameGroup" />
                     <xs:element name="email" type="xs:token"
                        minOccurs="0" maxOccurs="unbounded" />
                     <xs:element name="url" type="xs:anyURI"
                        minOccurs="0" maxOccurs="unbounded" />
                     <xs:element name="note" type="lex:noteType"
                        minOccurs="0" maxOccurs="unbounded" />
                  </xs:sequence>
                  <xs:attribute name="role" type="xs:token" use="required" />
               </xs:complexType>
            </xs:element>
            <xs:element name="entry" minOccurs="0" maxOccurs="unbounded">
               <xs:complexType>
                  <xs:sequence>
                     <xs:choice>
                        <xs:group ref="lex:entry-info" maxOccurs="1" />
                        <xs:element name="sense" minOccurs="2"
maxOccurs="unbounded">
                           <xs:complexType>
                              <xs:sequence>
                                 <xs:group ref="lex:entry-info" />
                              </xs:sequence>
                           </xs:complexType>
                        </xs:element>
                     </xs:choice>
                     <xs:element name="note" type="lex:noteType"
                        minOccurs="0" maxOccurs="unbounded" />
                  </xs:sequence>
                  <xs:attribute name="type" type="xs:token" />
               </xs:complexType>
            </xs:element>
            <xs:element name="note" type="lex:noteType"
               minOccurs="0" maxOccurs="unbounded" />
         </xs:sequence>
         <xs:attribute name="src" type="xs:anyURI" />
         <xs:attribute name="lexeme-lang" type="xs:language" use="required" />
         <xs:attribute name="document-lang" type="xs:language" use="required" />
      </xs:complexType>
   </xs:element>

</xs:schema>