tartrazine/lexers/standard_ml.xml

<lexer>
  <config>
    <name>Standard ML</name>
    <alias>sml</alias>
    <filename>*.sml</filename>
    <filename>*.sig</filename>
    <filename>*.fun</filename>
    <mime_type>text/x-standardml</mime_type>
    <mime_type>application/x-standardml</mime_type>
  </config>
  <rules>
    <state name="delimiters">
      <rule pattern="\(|\[|\{">
        <token type="Punctuation"/>
        <push state="main"/>
      </rule>
      <rule pattern="\)|\]|\}">
        <token type="Punctuation"/>
        <pop depth="1"/>
      </rule>
      <rule pattern="\b(let|if|local)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <push state="main" state="main"/>
      </rule>
      <rule pattern="\b(struct|sig|while)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <push state="main"/>
      </rule>
      <rule pattern="\b(do|else|end|in|then)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <pop depth="1"/>
      </rule>
    </state>
    <state name="root">
      <rule>
        <push state="main"/>
      </rule>
    </state>
    <state name="breakout">
      <rule pattern="(?=\b(where|do|handle|if|sig|op|while|case|as|else|signature|andalso|struct|infixr|functor|in|structure|then|local|rec|end|fun|of|orelse|val|include|fn|with|exception|let|and|infix|sharing|datatype|type|abstype|withtype|eqtype|nonfix|raise|open)\b(?!\&#39;))">
        <token type="Text"/>
        <pop depth="1"/>
      </rule>
    </state>
    <state name="tyvarseq">
      <rule pattern="\s">
        <token type="Text"/>
      </rule>
      <rule pattern="\(\*">
        <token type="CommentMultiline"/>
        <push state="comment"/>
      </rule>
      <rule pattern="\&#39;[\w\&#39;]*">
        <token type="NameDecorator"/>
      </rule>
      <rule pattern="[a-zA-Z][\w&#39;]*">
        <token type="Name"/>
      </rule>
      <rule pattern=",">
        <token type="Punctuation"/>
      </rule>
      <rule pattern="\)">
        <token type="Punctuation"/>
        <pop depth="1"/>
      </rule>
      <rule pattern="[!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+">
        <token type="Name"/>
      </rule>
    </state>
    <state name="char">
      <rule pattern="[^&#34;\\]">
        <token type="LiteralStringChar"/>
      </rule>
      <rule pattern="\\[\\&#34;abtnvfr]">
        <token type="LiteralStringEscape"/>
      </rule>
      <rule pattern="\\\^[\x40-\x5e]">
        <token type="LiteralStringEscape"/>
      </rule>
      <rule pattern="\\[0-9]{3}">
        <token type="LiteralStringEscape"/>
      </rule>
      <rule pattern="\\u[0-9a-fA-F]{4}">
        <token type="LiteralStringEscape"/>
      </rule>
      <rule pattern="\\\s+\\">
        <token type="LiteralStringInterpol"/>
      </rule>
      <rule pattern="&#34;">
        <token type="LiteralStringChar"/>
        <pop depth="1"/>
      </rule>
    </state>
    <state name="datbind">
      <rule>
        <include state="whitespace"/>
      </rule>
      <rule pattern="\b(and)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <push state="#pop" state="dname"/>
      </rule>
      <rule pattern="\b(withtype)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <push state="#pop" state="tname"/>
      </rule>
      <rule pattern="\b(of)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
      </rule>
      <rule pattern="(\|)(\s*)([a-zA-Z][\w&#39;]*)">
        <bygroups>
          <token type="Punctuation"/>
          <token type="Text"/>
          <token type="NameClass"/>
        </bygroups>
      </rule>
      <rule pattern="(\|)(\s+)([!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+)">
        <bygroups>
          <token type="Punctuation"/>
          <token type="Text"/>
          <token type="NameClass"/>
        </bygroups>
      </rule>
      <rule>
        <include state="breakout"/>
      </rule>
      <rule>
        <include state="core"/>
      </rule>
      <rule pattern="\S+">
        <token type="Error"/>
      </rule>
    </state>
    <state name="string">
      <rule pattern="[^&#34;\\]">
        <token type="LiteralStringDouble"/>
      </rule>
      <rule pattern="\\[\\&#34;abtnvfr]">
        <token type="LiteralStringEscape"/>
      </rule>
      <rule pattern="\\\^[\x40-\x5e]">
        <token type="LiteralStringEscape"/>
      </rule>
      <rule pattern="\\[0-9]{3}">
        <token type="LiteralStringEscape"/>
      </rule>
      <rule pattern="\\u[0-9a-fA-F]{4}">
        <token type="LiteralStringEscape"/>
      </rule>
      <rule pattern="\\\s+\\">
        <token type="LiteralStringInterpol"/>
      </rule>
      <rule pattern="&#34;">
        <token type="LiteralStringDouble"/>
        <pop depth="1"/>
      </rule>
    </state>
    <state name="tname">
      <rule>
        <include state="whitespace"/>
      </rule>
      <rule>
        <include state="breakout"/>
      </rule>
      <rule pattern="\&#39;[\w\&#39;]*">
        <token type="NameDecorator"/>
      </rule>
      <rule pattern="\(">
        <token type="Punctuation"/>
        <push state="tyvarseq"/>
      </rule>
      <rule pattern="=(?![!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+)">
        <token type="Punctuation"/>
        <push state="#pop" state="typbind"/>
      </rule>
      <rule pattern="([a-zA-Z][\w&#39;]*)">
        <token type="KeywordType"/>
      </rule>
      <rule pattern="([!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+)">
        <token type="KeywordType"/>
      </rule>
      <rule pattern="\S+">
        <token type="Error"/>
        <pop depth="1"/>
      </rule>
    </state>
    <state name="dname">
      <rule>
        <include state="whitespace"/>
      </rule>
      <rule>
        <include state="breakout"/>
      </rule>
      <rule pattern="\&#39;[\w\&#39;]*">
        <token type="NameDecorator"/>
      </rule>
      <rule pattern="\(">
        <token type="Punctuation"/>
        <push state="tyvarseq"/>
      </rule>
      <rule pattern="(=)(\s*)(datatype)">
        <bygroups>
          <token type="Punctuation"/>
          <token type="Text"/>
          <token type="KeywordReserved"/>
        </bygroups>
        <pop depth="1"/>
      </rule>
      <rule pattern="=(?![!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+)">
        <token type="Punctuation"/>
        <push state="#pop" state="datbind" state="datcon"/>
      </rule>
      <rule pattern="([a-zA-Z][\w&#39;]*)">
        <token type="KeywordType"/>
      </rule>
      <rule pattern="([!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+)">
        <token type="KeywordType"/>
      </rule>
      <rule pattern="\S+">
        <token type="Error"/>
        <pop depth="1"/>
      </rule>
    </state>
    <state name="typbind">
      <rule>
        <include state="whitespace"/>
      </rule>
      <rule pattern="\b(and)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <push state="#pop" state="tname"/>
      </rule>
      <rule>
        <include state="breakout"/>
      </rule>
      <rule>
        <include state="core"/>
      </rule>
      <rule pattern="\S+">
        <token type="Error"/>
        <pop depth="1"/>
      </rule>
    </state>
    <state name="ename">
      <rule>
        <include state="whitespace"/>
      </rule>
      <rule pattern="(exception|and)\b(\s+)([a-zA-Z][\w&#39;]*)">
        <bygroups>
          <token type="KeywordReserved"/>
          <token type="Text"/>
          <token type="NameClass"/>
        </bygroups>
      </rule>
      <rule pattern="(exception|and)\b(\s*)([!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+)">
        <bygroups>
          <token type="KeywordReserved"/>
          <token type="Text"/>
          <token type="NameClass"/>
        </bygroups>
      </rule>
      <rule pattern="\b(of)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
      </rule>
      <rule>
        <include state="breakout"/>
      </rule>
      <rule>
        <include state="core"/>
      </rule>
      <rule pattern="\S+">
        <token type="Error"/>
      </rule>
    </state>
    <state name="vname">
      <rule>
        <include state="whitespace"/>
      </rule>
      <rule pattern="\&#39;[\w\&#39;]*">
        <token type="NameDecorator"/>
      </rule>
      <rule pattern="\(">
        <token type="Punctuation"/>
        <push state="tyvarseq"/>
      </rule>
      <rule pattern="([a-zA-Z][\w&#39;]*)(\s*)(=(?![!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+))">
        <bygroups>
          <token type="NameVariable"/>
          <token type="Text"/>
          <token type="Punctuation"/>
        </bygroups>
        <pop depth="1"/>
      </rule>
      <rule pattern="([!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+)(\s*)(=(?![!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+))">
        <bygroups>
          <token type="NameVariable"/>
          <token type="Text"/>
          <token type="Punctuation"/>
        </bygroups>
        <pop depth="1"/>
      </rule>
      <rule pattern="([a-zA-Z][\w&#39;]*)">
        <token type="NameVariable"/>
        <pop depth="1"/>
      </rule>
      <rule pattern="([!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+)">
        <token type="NameVariable"/>
        <pop depth="1"/>
      </rule>
      <rule>
        <pop depth="1"/>
      </rule>
    </state>
    <state name="sname">
      <rule>
        <include state="whitespace"/>
      </rule>
      <rule>
        <include state="breakout"/>
      </rule>
      <rule pattern="([a-zA-Z][\w&#39;]*)">
        <token type="NameNamespace"/>
      </rule>
      <rule>
        <pop depth="1"/>
      </rule>
    </state>
    <state name="main-fun">
      <rule>
        <include state="whitespace"/>
      </rule>
      <rule pattern="\s">
        <token type="Text"/>
      </rule>
      <rule pattern="\(\*">
        <token type="CommentMultiline"/>
        <push state="comment"/>
      </rule>
      <rule pattern="\b(fun|and)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <push state="fname"/>
      </rule>
      <rule pattern="\b(val)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <push state="#pop" state="main" state="vname"/>
      </rule>
      <rule pattern="\|">
        <token type="Punctuation"/>
        <push state="fname"/>
      </rule>
      <rule pattern="\b(case|handle)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <push state="#pop" state="main"/>
      </rule>
      <rule>
        <include state="delimiters"/>
      </rule>
      <rule>
        <include state="core"/>
      </rule>
      <rule pattern="\S+">
        <token type="Error"/>
      </rule>
    </state>
    <state name="datcon">
      <rule>
        <include state="whitespace"/>
      </rule>
      <rule pattern="([a-zA-Z][\w&#39;]*)">
        <token type="NameClass"/>
        <pop depth="1"/>
      </rule>
      <rule pattern="([!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+)">
        <token type="NameClass"/>
        <pop depth="1"/>
      </rule>
      <rule pattern="\S+">
        <token type="Error"/>
        <pop depth="1"/>
      </rule>
    </state>
    <state name="dotted">
      <rule pattern="([a-zA-Z][\w&#39;]*)(\.)">
        <token type="NameNamespace"/>
      </rule>
      <rule pattern="([a-zA-Z][\w&#39;]*)">
        <token type="Name"/>
        <pop depth="1"/>
      </rule>
      <rule pattern="([!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+)">
        <token type="Name"/>
        <pop depth="1"/>
      </rule>
      <rule pattern="\s+">
        <token type="Error"/>
      </rule>
      <rule pattern="\S+">
        <token type="Error"/>
      </rule>
    </state>
    <state name="main">
      <rule>
        <include state="whitespace"/>
      </rule>
      <rule pattern="\b(val|and)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <push state="vname"/>
      </rule>
      <rule pattern="\b(fun)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <push state="#pop" state="main-fun" state="fname"/>
      </rule>
      <rule>
        <include state="delimiters"/>
      </rule>
      <rule>
        <include state="core"/>
      </rule>
      <rule pattern="\S+">
        <token type="Error"/>
      </rule>
    </state>
    <state name="comment">
      <rule pattern="[^(*)]">
        <token type="CommentMultiline"/>
      </rule>
      <rule pattern="\(\*">
        <token type="CommentMultiline"/>
        <push/>
      </rule>
      <rule pattern="\*\)">
        <token type="CommentMultiline"/>
        <pop depth="1"/>
      </rule>
      <rule pattern="[(*)]">
        <token type="CommentMultiline"/>
      </rule>
    </state>
    <state name="whitespace">
      <rule pattern="\s+">
        <token type="Text"/>
      </rule>
      <rule pattern="\(\*">
        <token type="CommentMultiline"/>
        <push state="comment"/>
      </rule>
    </state>
    <state name="core">
      <rule pattern="(_|\}|\{|\)|;|,|\[|\(|\]|\.\.\.)">
        <token type="Punctuation"/>
      </rule>
      <rule pattern="#&#34;">
        <token type="LiteralStringChar"/>
        <push state="char"/>
      </rule>
      <rule pattern="&#34;">
        <token type="LiteralStringDouble"/>
        <push state="string"/>
      </rule>
      <rule pattern="~?0x[0-9a-fA-F]+">
        <token type="LiteralNumberHex"/>
      </rule>
      <rule pattern="0wx[0-9a-fA-F]+">
        <token type="LiteralNumberHex"/>
      </rule>
      <rule pattern="0w\d+">
        <token type="LiteralNumberInteger"/>
      </rule>
      <rule pattern="~?\d+\.\d+[eE]~?\d+">
        <token type="LiteralNumberFloat"/>
      </rule>
      <rule pattern="~?\d+\.\d+">
        <token type="LiteralNumberFloat"/>
      </rule>
      <rule pattern="~?\d+[eE]~?\d+">
        <token type="LiteralNumberFloat"/>
      </rule>
      <rule pattern="~?\d+">
        <token type="LiteralNumberInteger"/>
      </rule>
      <rule pattern="#\s*[1-9][0-9]*">
        <token type="NameLabel"/>
      </rule>
      <rule pattern="#\s*([a-zA-Z][\w&#39;]*)">
        <token type="NameLabel"/>
      </rule>
      <rule pattern="#\s+([!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+)">
        <token type="NameLabel"/>
      </rule>
      <rule pattern="\b(datatype|abstype)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <push state="dname"/>
      </rule>
      <rule pattern="(?=\b(exception)\b(?!\&#39;))">
        <token type="Text"/>
        <push state="ename"/>
      </rule>
      <rule pattern="\b(functor|include|open|signature|structure)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <push state="sname"/>
      </rule>
      <rule pattern="\b(type|eqtype)\b(?!\&#39;)">
        <token type="KeywordReserved"/>
        <push state="tname"/>
      </rule>
      <rule pattern="\&#39;[\w\&#39;]*">
        <token type="NameDecorator"/>
      </rule>
      <rule pattern="([a-zA-Z][\w&#39;]*)(\.)">
        <token type="NameNamespace"/>
        <push state="dotted"/>
      </rule>
      <rule pattern="\b(abstype|and|andalso|as|case|datatype|do|else|end|exception|fn|fun|handle|if|in|infix|infixr|let|local|nonfix|of|op|open|orelse|raise|rec|then|type|val|with|withtype|while|eqtype|functor|include|sharing|sig|signature|struct|structure|where)\b">
        <token type="KeywordReserved"/>
      </rule>
      <rule pattern="([a-zA-Z][\w&#39;]*)">
        <token type="Name"/>
      </rule>
      <rule pattern="\b(:|\|,=|=&gt;|-&gt;|#|:&gt;)\b">
        <token type="KeywordReserved"/>
      </rule>
      <rule pattern="([!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+)">
        <token type="Name"/>
      </rule>
    </state>
    <state name="fname">
      <rule>
        <include state="whitespace"/>
      </rule>
      <rule pattern="\&#39;[\w\&#39;]*">
        <token type="NameDecorator"/>
      </rule>
      <rule pattern="\(">
        <token type="Punctuation"/>
        <push state="tyvarseq"/>
      </rule>
      <rule pattern="([a-zA-Z][\w&#39;]*)">
        <token type="NameFunction"/>
        <pop depth="1"/>
      </rule>
      <rule pattern="([!%&amp;$#+\-/:&lt;=&gt;?@\\~`^|*]+)">
        <token type="NameFunction"/>
        <pop depth="1"/>
      </rule>
      <rule>
        <pop depth="1"/>
      </rule>
    </state>
  </rules>
</lexer>