tartrazine/lexers/thrift.xml

<lexer>
  <config>
    <name>Thrift</name>
    <alias>thrift</alias>
    <filename>*.thrift</filename>
    <mime_type>application/x-thrift</mime_type>
  </config>
  <rules>
    <state name="class">
      <rule pattern="[a-zA-Z_]\w*">
        <token type="NameClass"/>
        <pop depth="1"/>
      </rule>
      <rule>
        <pop depth="1"/>
      </rule>
    </state>
    <state name="keywords">
      <rule pattern="(async|oneway|extends|throws|required|optional)\b">
        <token type="Keyword"/>
      </rule>
      <rule pattern="(true|false)\b">
        <token type="KeywordConstant"/>
      </rule>
      <rule pattern="(const|typedef)\b">
        <token type="KeywordDeclaration"/>
      </rule>
      <rule pattern="(smalltalk_category|smalltalk_prefix|delphi_namespace|csharp_namespace|ruby_namespace|xsd_namespace|cpp_namespace|php_namespace|xsd_nillable|xsd_optional|java_package|cocoa_prefix|perl_package|cpp_include|py_module|xsd_attrs|cpp_type|xsd_all|include)\b">
        <token type="KeywordNamespace"/>
      </rule>
      <rule pattern="(double|binary|string|slist|senum|bool|void|byte|list|i64|map|set|i32|i16)\b">
        <token type="KeywordType"/>
      </rule>
      <rule pattern="\b(__NAMESPACE__|synchronized|__FUNCTION__|__METHOD__|endforeach|implements|enddeclare|instanceof|transient|endswitch|protected|interface|__CLASS__|continue|__FILE__|abstract|function|endwhile|unsigned|register|volatile|__LINE__|declare|foreach|default|__DIR__|private|finally|dynamic|virtual|lambda|elseif|inline|switch|unless|endfor|delete|import|return|module|ensure|native|rescue|assert|sizeof|static|global|except|public|float|BEGIN|super|endif|yield|elsif|throw|clone|class|catch|until|break|retry|begin|raise|alias|while|print|undef|exec|with|when|case|redo|args|elif|this|then|self|goto|else|pass|next|var|for|xor|END|not|try|del|and|def|new|use|nil|end|if|do|is|or|in|as)\b">
        <token type="KeywordReserved"/>
      </rule>
    </state>
    <state name="numbers">
      <rule pattern="[+-]?(\d+\.\d+([eE][+-]?\d+)?|\.?\d+[eE][+-]?\d+)">
        <token type="LiteralNumberFloat"/>
      </rule>
      <rule pattern="[+-]?0x[0-9A-Fa-f]+">
        <token type="LiteralNumberHex"/>
      </rule>
      <rule pattern="[+-]?[0-9]+">
        <token type="LiteralNumberInteger"/>
      </rule>
    </state>
    <state name="root">
      <rule>
        <include state="whitespace"/>
      </rule>
      <rule>
        <include state="comments"/>
      </rule>
      <rule pattern="&#34;">
        <token type="LiteralStringDouble"/>
        <combined state="stringescape" state="dqs"/>
      </rule>
      <rule pattern="\&#39;">
        <token type="LiteralStringSingle"/>
        <combined state="stringescape" state="sqs"/>
      </rule>
      <rule pattern="(namespace)(\s+)">
        <bygroups>
          <token type="KeywordNamespace"/>
          <token type="TextWhitespace"/>
        </bygroups>
        <push state="namespace"/>
      </rule>
      <rule pattern="(enum|union|struct|service|exception)(\s+)">
        <bygroups>
          <token type="KeywordDeclaration"/>
          <token type="TextWhitespace"/>
        </bygroups>
        <push state="class"/>
      </rule>
      <rule pattern="((?:(?:[^\W\d]|\$)[\w.\[\]$&lt;&gt;]*\s+)+?)((?:[^\W\d]|\$)[\w$]*)(\s*)(\()">
        <bygroups>
          <usingself state="root"/>
          <token type="NameFunction"/>
          <token type="Text"/>
          <token type="Operator"/>
        </bygroups>
      </rule>
      <rule>
        <include state="keywords"/>
      </rule>
      <rule>
        <include state="numbers"/>
      </rule>
      <rule pattern="[&amp;=]">
        <token type="Operator"/>
      </rule>
      <rule pattern="[:;,{}()&lt;&gt;\[\]]">
        <token type="Punctuation"/>
      </rule>
      <rule pattern="[a-zA-Z_](\.\w|\w)*">
        <token type="Name"/>
      </rule>
    </state>
    <state name="dqs">
      <rule pattern="&#34;">
        <token type="LiteralStringDouble"/>
        <pop depth="1"/>
      </rule>
      <rule pattern="[^\\&#34;\n]+">
        <token type="LiteralStringDouble"/>
      </rule>
    </state>
    <state name="namespace">
      <rule pattern="[a-z*](\.\w|\w)*">
        <token type="NameNamespace"/>
        <pop depth="1"/>
      </rule>
      <rule>
        <pop depth="1"/>
      </rule>
    </state>
    <state name="whitespace">
      <rule pattern="\n">
        <token type="TextWhitespace"/>
      </rule>
      <rule pattern="\s+">
        <token type="TextWhitespace"/>
      </rule>
    </state>
    <state name="comments">
      <rule pattern="#.*$">
        <token type="Comment"/>
      </rule>
      <rule pattern="//.*?\n">
        <token type="Comment"/>
      </rule>
      <rule pattern="/\*[\w\W]*?\*/">
        <token type="CommentMultiline"/>
      </rule>
    </state>
    <state name="stringescape">
      <rule pattern="\\([\\nrt&#34;\&#39;])">
        <token type="LiteralStringEscape"/>
      </rule>
    </state>
    <state name="sqs">
      <rule pattern="&#39;">
        <token type="LiteralStringSingle"/>
        <pop depth="1"/>
      </rule>
      <rule pattern="[^\\\&#39;\n]+">
        <token type="LiteralStringSingle"/>
      </rule>
    </state>
  </rules>
</lexer>