highlight.js/lib/languages/r.js

/*
Language: R
Description: R is a free software environment for statistical computing and graphics.
Author: Joe Cheng <joe@rstudio.org>
Contributors: Konrad Rudolph <konrad.rudolph@gmail.com>
Website: https://www.r-project.org
Category: common,scientific
*/

/** @type LanguageFn */
function r(hljs) {
  const regex = hljs.regex;
  // Identifiers in R cannot start with `_`, but they can start with `.` if it
  // is not immediately followed by a digit.
  // R also supports quoted identifiers, which are near-arbitrary sequences
  // delimited by backticks (`…`), which may contain escape sequences. These are
  // handled in a separate mode. See `test/markup/r/names.txt` for examples.
  // FIXME: Support Unicode identifiers.
  const IDENT_RE = /(?:(?:[a-zA-Z]|\.[._a-zA-Z])[._a-zA-Z0-9]*)|\.(?!\d)/;
  const NUMBER_TYPES_RE = regex.either(
    // Special case: only hexadecimal binary powers can contain fractions
    /0[xX][0-9a-fA-F]+\.[0-9a-fA-F]*[pP][+-]?\d+i?/,
    // Hexadecimal numbers without fraction and optional binary power
    /0[xX][0-9a-fA-F]+(?:[pP][+-]?\d+)?[Li]?/,
    // Decimal numbers
    /(?:\d+(?:\.\d*)?|\.\d+)(?:[eE][+-]?\d+)?[Li]?/
  );
  const OPERATORS_RE = /[=!<>:]=|\|\||&&|:::?|<-|<<-|->>|->|\|>|[-+*\/?!$&|:<=>@^~]|\*\*/;
  const PUNCTUATION_RE = regex.either(
    /[()]/,
    /[{}]/,
    /\[\[/,
    /[[\]]/,
    /\\/,
    /,/
  );

  return {
    name: 'R',

    keywords: {
      $pattern: IDENT_RE,
      keyword:
        'function if in break next repeat else for while',
      literal:
        'NULL NA TRUE FALSE Inf NaN NA_integer_|10 NA_real_|10 '
        + 'NA_character_|10 NA_complex_|10',
      built_in:
        // Builtin constants
        'LETTERS letters month.abb month.name pi T F '
        // Primitive functions
        // These are all the functions in `base` that are implemented as a
        // `.Primitive`, minus those functions that are also keywords.
        + 'abs acos acosh all any anyNA Arg as.call as.character '
        + 'as.complex as.double as.environment as.integer as.logical '
        + 'as.null.default as.numeric as.raw asin asinh atan atanh attr '
        + 'attributes baseenv browser c call ceiling class Conj cos cosh '
        + 'cospi cummax cummin cumprod cumsum digamma dim dimnames '
        + 'emptyenv exp expression floor forceAndCall gamma gc.time '
        + 'globalenv Im interactive invisible is.array is.atomic is.call '
        + 'is.character is.complex is.double is.environment is.expression '
        + 'is.finite is.function is.infinite is.integer is.language '
        + 'is.list is.logical is.matrix is.na is.name is.nan is.null '
        + 'is.numeric is.object is.pairlist is.raw is.recursive is.single '
        + 'is.symbol lazyLoadDBfetch length lgamma list log max min '
        + 'missing Mod names nargs nzchar oldClass on.exit pos.to.env '
        + 'proc.time prod quote range Re rep retracemem return round '
        + 'seq_along seq_len seq.int sign signif sin sinh sinpi sqrt '
        + 'standardGeneric substitute sum switch tan tanh tanpi tracemem '
        + 'trigamma trunc unclass untracemem UseMethod xtfrm',
    },

    contains: [
      // Roxygen comments
      hljs.COMMENT(
        /#'/,
        /$/,
        { contains: [
          {
            // Handle `@examples` separately to cause all subsequent code
            // until the next `@`-tag on its own line to be kept as-is,
            // preventing highlighting. This code is example R code, so nested
            // doctags shouldn’t be treated as such. See
            // `test/markup/r/roxygen.txt` for an example.
            scope: 'doctag',
            match: /@examples/,
            starts: {
              end: regex.lookahead(regex.either(
                // end if another doc comment
                /\n^#'\s*(?=@[a-zA-Z]+)/,
                // or a line with no comment
                /\n^(?!#')/
              )),
              endsParent: true
            }
          },
          {
            // Handle `@param` to highlight the parameter name following
            // after.
            scope: 'doctag',
            begin: '@param',
            end: /$/,
            contains: [
              {
                scope: 'variable',
                variants: [
                  { match: IDENT_RE },
                  { match: /`(?:\\.|[^`\\])+`/ }
                ],
                endsParent: true
              }
            ]
          },
          {
            scope: 'doctag',
            match: /@[a-zA-Z]+/
          },
          {
            scope: 'keyword',
            match: /\\[a-zA-Z]+/
          }
        ] }
      ),

      hljs.HASH_COMMENT_MODE,

      {
        scope: 'string',
        contains: [ hljs.BACKSLASH_ESCAPE ],
        variants: [
          hljs.END_SAME_AS_BEGIN({
            begin: /[rR]"(-*)\(/,
            end: /\)(-*)"/
          }),
          hljs.END_SAME_AS_BEGIN({
            begin: /[rR]"(-*)\{/,
            end: /\}(-*)"/
          }),
          hljs.END_SAME_AS_BEGIN({
            begin: /[rR]"(-*)\[/,
            end: /\](-*)"/
          }),
          hljs.END_SAME_AS_BEGIN({
            begin: /[rR]'(-*)\(/,
            end: /\)(-*)'/
          }),
          hljs.END_SAME_AS_BEGIN({
            begin: /[rR]'(-*)\{/,
            end: /\}(-*)'/
          }),
          hljs.END_SAME_AS_BEGIN({
            begin: /[rR]'(-*)\[/,
            end: /\](-*)'/
          }),
          {
            begin: '"',
            end: '"',
            relevance: 0
          },
          {
            begin: "'",
            end: "'",
            relevance: 0
          }
        ],
      },

      // Matching numbers immediately following punctuation and operators is
      // tricky since we need to look at the character ahead of a number to
      // ensure the number is not part of an identifier, and we cannot use
      // negative look-behind assertions. So instead we explicitly handle all
      // possible combinations of (operator|punctuation), number.
      // TODO: replace with negative look-behind when available
      // { begin: /(?<![a-zA-Z0-9._])0[xX][0-9a-fA-F]+\.[0-9a-fA-F]*[pP][+-]?\d+i?/ },
      // { begin: /(?<![a-zA-Z0-9._])0[xX][0-9a-fA-F]+([pP][+-]?\d+)?[Li]?/ },
      // { begin: /(?<![a-zA-Z0-9._])(\d+(\.\d*)?|\.\d+)([eE][+-]?\d+)?[Li]?/ }
      {
        relevance: 0,
        variants: [
          {
            scope: {
              1: 'operator',
              2: 'number'
            },
            match: [
              OPERATORS_RE,
              NUMBER_TYPES_RE
            ]
          },
          {
            scope: {
              1: 'operator',
              2: 'number'
            },
            match: [
              /%[^%]*%/,
              NUMBER_TYPES_RE
            ]
          },
          {
            scope: {
              1: 'punctuation',
              2: 'number'
            },
            match: [
              PUNCTUATION_RE,
              NUMBER_TYPES_RE
            ]
          },
          {
            scope: { 2: 'number' },
            match: [
              /[^a-zA-Z0-9._]|^/, // not part of an identifier, or start of document
              NUMBER_TYPES_RE
            ]
          }
        ]
      },

      // Operators/punctuation when they're not directly followed by numbers
      {
        // Relevance boost for the most common assignment form.
        scope: { 3: 'operator' },
        match: [
          IDENT_RE,
          /\s+/,
          /<-/,
          /\s+/
        ]
      },

      {
        scope: 'operator',
        relevance: 0,
        variants: [
          { match: OPERATORS_RE },
          { match: /%[^%]*%/ }
        ]
      },

      {
        scope: 'punctuation',
        relevance: 0,
        match: PUNCTUATION_RE
      },

      {
        // Escaped identifier
        begin: '`',
        end: '`',
        contains: [ { begin: /\\./ } ]
      }
    ]
  };
}

module.exports = r;