zeppelin-web-angular/src/app/languages/scala.ts

/*
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *     http://www.apache.org/licenses/LICENSE-2.0
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

'use strict';

import { languages } from 'monaco-editor';

type IRichLanguageConfiguration = languages.LanguageConfiguration;
type ILanguage = languages.IMonarchLanguage;

export const conf: IRichLanguageConfiguration = {
  // the default separators except `@$`
  wordPattern: /(-?\d*\.\d\w*)|([^\`\~\!\#\%\^\&\*\(\)\-\=\+\[\{\]\}\\\|\;\:\'\"\,\.\<\>\/\?\s]+)/g,
  comments: {
    lineComment: '//',
    blockComment: ['/*', '*/']
  },
  brackets: [
    ['{', '}'],
    ['[', ']'],
    ['(', ')']
  ],
  autoClosingPairs: [
    { open: '{', close: '}' },
    { open: '[', close: ']' },
    { open: '(', close: ')' },
    { open: '"', close: '"' },
    { open: "'", close: "'" }
  ],
  surroundingPairs: [
    { open: '{', close: '}' },
    { open: '[', close: ']' },
    { open: '(', close: ')' },
    { open: '"', close: '"' },
    { open: "'", close: "'" },
    { open: '<', close: '>' }
  ]
};

export const language = {
  defaultToken: '',
  tokenPostfix: '.scala',

  keywords: [
    // From https://www.scala-lang.org/files/archive/spec/2.11/01-lexical-syntax.html
    'abstract',
    'case',
    'catch',
    'class',
    'def',
    'do',
    'else',
    'extends',
    'false',
    'final',
    'finally',
    'for',
    'forSome',
    'if',
    'implicit',
    'import',
    'lazy',
    'macro',
    'match',
    'new',
    'null',
    'object',
    'override',
    'package',
    'private',
    'protected',
    'return',
    'sealed',
    'super',
    'this',
    'throw',
    'trait',
    'try',
    'true',
    'type',
    'val',
    'var',
    'while',
    'with',
    'yield'
  ],

  operators: [
    '_',
    ':',
    '=',
    '=>',
    '<-',
    '<:',
    '<%',
    '>:',
    '#',
    '@',

    // Copied from java.ts, to be validated
    '=',
    '>',
    '<',
    '!',
    '~',
    '?',
    ':',
    '==',
    '<=',
    '>=',
    '!=',
    '&&',
    '||',
    '++',
    '--',
    '+',
    '-',
    '*',
    '/',
    '&',
    '|',
    '^',
    '%',
    '<<',
    '>>',
    '>>>',
    '+=',
    '-=',
    '*=',
    '/=',
    '&=',
    '|=',
    '^=',
    '%=',
    '<<=',
    '>>=',
    '>>>='
  ],

  // we include these common regular expressions
  symbols: /[=><!~?:&|+\-*\/\^%]+/,
  escapes: /\\(?:[abfnrtv\\"']|x[0-9A-Fa-f]{1,4}|u[0-9A-Fa-f]{4}|U[0-9A-Fa-f]{8})/,
  digits: /\d+(_+\d+)*/,
  octaldigits: /[0-7]+(_+[0-7]+)*/,
  binarydigits: /[0-1]+(_+[0-1]+)*/,
  hexdigits: /[[0-9a-fA-F]+(_+[0-9a-fA-F]+)*/,

  // The main tokenizer for our languages
  tokenizer: {
    root: [
      // identifiers and keywords
      [
        /[a-zA-Z_$][\w$]*/,
        {
          cases: {
            '@keywords': { token: 'keyword.$0' },
            '@default': 'identifier'
          }
        }
      ],

      // whitespace
      { include: '@whitespace' },

      // delimiters and operators
      [/[{}()\[\]]/, '@brackets'],
      [/[<>](?!@symbols)/, '@brackets'],
      [
        /@symbols/,
        {
          cases: {
            '@operators': 'delimiter',
            '@default': ''
          }
        }
      ],

      // @ annotations.
      [/@\s*[a-zA-Z_\$][\w\$]*/, 'annotation'],

      // numbers
      [/(@digits)[eE]([\-+]?(@digits))?[fFdD]?/, 'number.float'],
      [/(@digits)\.(@digits)([eE][\-+]?(@digits))?[fFdD]?/, 'number.float'],
      [/0[xX](@hexdigits)[Ll]?/, 'number.hex'],
      [/0(@octaldigits)[Ll]?/, 'number.octal'],
      [/0[bB](@binarydigits)[Ll]?/, 'number.binary'],
      [/(@digits)[fFdD]/, 'number.float'],
      [/(@digits)[lL]?/, 'number'],

      // delimiter: after number because of .\d floats
      [/[;,.]/, 'delimiter'],

      // strings
      [/"([^"\\]|\\.)*$/, 'string.invalid'], // non-teminated string
      [/"/, 'string', '@string'],

      // characters
      [/'[^\\']'/, 'string'],
      [/(')(@escapes)(')/, ['string', 'string.escape', 'string']],
      [/'/, 'string.invalid']
    ],

    whitespace: [
      [/[ \t\r\n]+/, ''],
      [/\/\*\*(?!\/)/, 'comment.doc', '@scaladoc'],
      [/\/\*/, 'comment', '@comment'],
      [/\/\/.*$/, 'comment']
    ],

    comment: [
      [/[^\/*]+/, 'comment'],
      // [/\/\*/, 'comment', '@push' ],    // nested comment not allowed :-(
      // [/\/\*/,    'comment.invalid' ],    // this breaks block comments in the shape of /* //*/
      [/\*\//, 'comment', '@pop'],
      [/[\/*]/, 'comment']
    ],
    // Identical copy of comment above, except for the addition of .doc
    scaladoc: [
      [/[^\/*]+/, 'comment.doc'],
      // [/\/\*/, 'comment.doc', '@push' ],    // nested comment not allowed :-(
      [/\/\*/, 'comment.doc.invalid'],
      [/\*\//, 'comment.doc', '@pop'],
      [/[\/*]/, 'comment.doc']
    ],

    // eslint-disable-next-line id-blacklist
    string: [
      [/[^\\"]+/, 'string'],
      [/@escapes/, 'string.escape'],
      [/\\./, 'string.escape.invalid'],
      [/"/, 'string', '@pop']
    ]
  }
} as ILanguage;