tartrazine/lexers/sparql.xml

<lexer>
  <config>
    <name>SPARQL</name>
    <alias>sparql</alias>
    <filename>*.rq</filename>
    <filename>*.sparql</filename>
    <mime_type>application/sparql-query</mime_type>
  </config>
  <rules>
    <state name="string-escape">
      <rule pattern="u[0-9A-Fa-f]{4}">
        <token type="LiteralStringEscape"/>
        <pop depth="1"/>
      </rule>
      <rule pattern="U[0-9A-Fa-f]{8}">
        <token type="LiteralStringEscape"/>
        <pop depth="1"/>
      </rule>
      <rule pattern=".">
        <token type="LiteralStringEscape"/>
        <pop depth="1"/>
      </rule>
    </state>
    <state name="end-of-string">
      <rule pattern="(@)([a-zA-Z]+(?:-[a-zA-Z0-9]+)*)">
        <bygroups>
          <token type="Operator"/>
          <token type="NameFunction"/>
        </bygroups>
        <pop depth="2"/>
      </rule>
      <rule pattern="\^\^">
        <token type="Operator"/>
        <pop depth="2"/>
      </rule>
      <rule>
        <pop depth="2"/>
      </rule>
    </state>
    <state name="root">
      <rule pattern="\s+">
        <token type="Text"/>
      </rule>
      <rule pattern="((?i)select|construct|describe|ask|where|filter|group\s+by|minus|distinct|reduced|from\s+named|from|order\s+by|desc|asc|limit|offset|bindings|load|clear|drop|create|add|move|copy|insert\s+data|delete\s+data|delete\s+where|delete|insert|using\s+named|using|graph|default|named|all|optional|service|silent|bind|union|not\s+in|in|as|having|to|prefix|base)\b">
        <token type="Keyword"/>
      </rule>
      <rule pattern="(a)\b">
        <token type="Keyword"/>
      </rule>
      <rule pattern="(&lt;(?:[^&lt;&gt;&#34;{}|^`\\\x00-\x20])*&gt;)">
        <token type="NameLabel"/>
      </rule>
      <rule pattern="(_:[_\p{L}\p{N}](?:[-_.\p{L}\p{N}]*[-_\p{L}\p{N}])?)">
        <token type="NameLabel"/>
      </rule>
      <rule pattern="[?$][_\p{L}\p{N}]+">
        <token type="NameVariable"/>
      </rule>
      <rule pattern="([\p{L}][-_.\p{L}\p{N}]*)?(\:)((?:[_:\p{L}\p{N}]|(?:%[0-9A-Fa-f][0-9A-Fa-f])|(?:\\[ _~.\-!$&amp;&#34;()*+,;=/?#@%]))(?:(?:[-_:.\p{L}\p{N}]|(?:%[0-9A-Fa-f][0-9A-Fa-f])|(?:\\[ _~.\-!$&amp;&#34;()*+,;=/?#@%]))*(?:[-_:\p{L}\p{N}]|(?:%[0-9A-Fa-f][0-9A-Fa-f])|(?:\\[ _~.\-!$&amp;&#34;()*+,;=/?#@%])))?)?">
        <bygroups>
          <token type="NameNamespace"/>
          <token type="Punctuation"/>
          <token type="NameTag"/>
        </bygroups>
      </rule>
      <rule pattern="((?i)str|lang|langmatches|datatype|bound|iri|uri|bnode|rand|abs|ceil|floor|round|concat|strlen|ucase|lcase|encode_for_uri|contains|strstarts|strends|strbefore|strafter|year|month|day|hours|minutes|seconds|timezone|tz|now|md5|sha1|sha256|sha384|sha512|coalesce|if|strlang|strdt|sameterm|isiri|isuri|isblank|isliteral|isnumeric|regex|substr|replace|exists|not\s+exists|count|sum|min|max|avg|sample|group_concat|separator)\b">
        <token type="NameFunction"/>
      </rule>
      <rule pattern="(true|false)">
        <token type="KeywordConstant"/>
      </rule>
      <rule pattern="[+\-]?(\d+\.\d*[eE][+-]?\d+|\.?\d+[eE][+-]?\d+)">
        <token type="LiteralNumberFloat"/>
      </rule>
      <rule pattern="[+\-]?(\d+\.\d*|\.\d+)">
        <token type="LiteralNumberFloat"/>
      </rule>
      <rule pattern="[+\-]?\d+">
        <token type="LiteralNumberInteger"/>
      </rule>
      <rule pattern="(\|\||&amp;&amp;|=|\*|\-|\+|/|!=|&lt;=|&gt;=|!|&lt;|&gt;)">
        <token type="Operator"/>
      </rule>
      <rule pattern="[(){}.;,:^\[\]]">
        <token type="Punctuation"/>
      </rule>
      <rule pattern="#[^\n]*">
        <token type="Comment"/>
      </rule>
      <rule pattern="&#34;&#34;&#34;">
        <token type="LiteralString"/>
        <push state="triple-double-quoted-string"/>
      </rule>
      <rule pattern="&#34;">
        <token type="LiteralString"/>
        <push state="single-double-quoted-string"/>
      </rule>
      <rule pattern="&#39;&#39;&#39;">
        <token type="LiteralString"/>
        <push state="triple-single-quoted-string"/>
      </rule>
      <rule pattern="&#39;">
        <token type="LiteralString"/>
        <push state="single-single-quoted-string"/>
      </rule>
    </state>
    <state name="triple-double-quoted-string">
      <rule pattern="&#34;&#34;&#34;">
        <token type="LiteralString"/>
        <push state="end-of-string"/>
      </rule>
      <rule pattern="[^\\]+">
        <token type="LiteralString"/>
      </rule>
      <rule pattern="\\">
        <token type="LiteralString"/>
        <push state="string-escape"/>
      </rule>
    </state>
    <state name="single-double-quoted-string">
      <rule pattern="&#34;">
        <token type="LiteralString"/>
        <push state="end-of-string"/>
      </rule>
      <rule pattern="[^&#34;\\\n]+">
        <token type="LiteralString"/>
      </rule>
      <rule pattern="\\">
        <token type="LiteralString"/>
        <push state="string-escape"/>
      </rule>
    </state>
    <state name="triple-single-quoted-string">
      <rule pattern="&#39;&#39;&#39;">
        <token type="LiteralString"/>
        <push state="end-of-string"/>
      </rule>
      <rule pattern="[^\\]+">
        <token type="LiteralString"/>
      </rule>
      <rule pattern="\\">
        <token type="LiteralStringEscape"/>
        <push state="string-escape"/>
      </rule>
    </state>
    <state name="single-single-quoted-string">
      <rule pattern="&#39;">
        <token type="LiteralString"/>
        <push state="end-of-string"/>
      </rule>
      <rule pattern="[^&#39;\\\n]+">
        <token type="LiteralString"/>
      </rule>
      <rule pattern="\\">
        <token type="LiteralString"/>
        <push state="string-escape"/>
      </rule>
    </state>
  </rules>
</lexer>