blob: d7170dfc451fd87a1889ef5e88efb89e3cf1bcaa [file] [log] [blame]
/**
* @fileoverview
* Registers a language handler for OCaml, SML, F# and similar languages.
*
* Based on the lexical grammar at
* http://research.microsoft.com/fsharp/manual/spec2.aspx#_Toc202383715
*
* @author mikesamuel@gmail.com
*/
PR.registerLangHandler(
PR.createSimpleLexer(
[
// Whitespace is made up of spaces, tabs and newline characters.
[PR.PR_PLAIN, /^[\t\n\r \xA0]+/, null, '\t\n\r \xA0'],
// #if ident/#else/#endif directives delimit conditional compilation
// sections
[PR.PR_COMMENT,
/^#(?:if[\t\n\r \xA0]+(?:[a-z_$][\w\']*|``[^\r\n\t`]*(?:``|$))|else|endif|light)/i,
null, '#'],
// A double or single quoted, possibly multi-line, string.
// F# allows escaped newlines in strings.
[PR.PR_STRING, /^(?:\"(?:[^\"\\]|\\[\s\S])*(?:\"|$)|\'(?:[^\'\\]|\\[\s\S])*(?:\'|$))/, null, '"\'']
],
[
// Block comments are delimited by (* and *) and may be
// nested. Single-line comments begin with // and extend to
// the end of a line.
// TODO: (*...*) comments can be nested. This does not handle that.
[PR.PR_COMMENT, /^(?:\/\/[^\r\n]*|\(\*[\s\S]*?\*\))/],
[PR.PR_KEYWORD, /^(?:abstract|and|as|assert|begin|class|default|delegate|do|done|downcast|downto|elif|else|end|exception|extern|false|finally|for|fun|function|if|in|inherit|inline|interface|internal|lazy|let|match|member|module|mutable|namespace|new|null|of|open|or|override|private|public|rec|return|static|struct|then|to|true|try|type|upcast|use|val|void|when|while|with|yield|asr|land|lor|lsl|lsr|lxor|mod|sig|atomic|break|checked|component|const|constraint|constructor|continue|eager|event|external|fixed|functor|global|include|method|mixin|object|parallel|process|protected|pure|sealed|trait|virtual|volatile)\b/],
// A number is a hex integer literal, a decimal real literal, or in
// scientific notation.
[PR.PR_LITERAL,
/^[+\-]?(?:0x[\da-f]+|(?:(?:\.\d+|\d+(?:\.\d*)?)(?:e[+\-]?\d+)?))/i],
[PR.PR_PLAIN, /^(?:[a-z_]\w*[!?#]?|``[^\r\n\t`]*(?:``|$))/i],
// A printable non-space non-special character
[PR.PR_PUNCTUATION, /^[^\t\n\r \xA0\"\'\w]+/]
]),
['fs', 'ml']);