perl.js

module.exports = function(hljs) {
  var PERL_KEYWORDS = 'getpwent getservent quotemeta msgrcv scalar kill dbmclose undef lc ' +
    'ma syswrite tr send umask sysopen shmwrite vec qx utime local oct semctl localtime ' +
    'readpipe do return format read sprintf dbmopen pop getpgrp not getpwnam rewinddir qq' +
    'fileno qw endprotoent wait sethostent bless s|0 opendir continue each sleep endgrent ' +
    'shutdown dump chomp connect getsockname die socketpair close flock exists index shmget' +
    'sub for endpwent redo lstat msgctl setpgrp abs exit select print ref gethostbyaddr ' +
    'unshift fcntl syscall goto getnetbyaddr join gmtime symlink semget splice x|0 ' +
    'getpeername recv log setsockopt cos last reverse gethostbyname getgrnam study formline ' +
    'endhostent times chop length gethostent getnetent pack getprotoent getservbyname rand ' +
    'mkdir pos chmod y|0 substr endnetent printf next open msgsnd readdir use unlink ' +
    'getsockopt getpriority rindex wantarray hex system getservbyport endservent int chr ' +
    'untie rmdir prototype tell listen fork shmread ucfirst setprotoent else sysseek link ' +
    'getgrgid shmctl waitpid unpack getnetbyname reset chdir grep split require caller ' +
    'lcfirst until warn while values shift telldir getpwuid my getprotobynumber delete and ' +
    'sort uc defined srand accept package seekdir getprotobyname semop our rename seek if q|0 ' +
    'chroot sysread setpwent no crypt getc chown sqrt write setnetent setpriority foreach ' +
    'tie sin msgget map stat getlogin unless elsif truncate exec keys glob tied closedir' +
    'ioctl socket readlink eval xor readline binmode setservent eof ord bind alarm pipe ' +
    'atan2 getgrent exp time push setgrent gt lt or ne m|0';
  var SUBST = {
    className: 'subst',
    begin: '[$@]\\{', end: '\\}',
    keywords: PERL_KEYWORDS,
    relevance: 10
  };
  var VAR1 = {
    className: 'variable',
    begin: '\\$\\d'
  };
  var VAR2 = {
    className: 'variable',
    begin: '[\\$\\%\\@\\*](\\^\\w\\b|#\\w+(\\:\\:\\w+)*|[^\\s\\w{]|{\\w+}|\\w+(\\:\\:\\w*)*)'
  };
  var STRING_CONTAINS = [hljs.BACKSLASH_ESCAPE, SUBST, VAR1, VAR2];
  var METHOD = {
    begin: '->',
    contains: [
      {begin: hljs.IDENT_RE},
      {begin: '{', end: '}'}
    ]
  };
  var COMMENT = {
    className: 'comment',
    begin: '^(__END__|__DATA__)', end: '\\n$',
    relevance: 5
  }
  var PERL_DEFAULT_CONTAINS = [
    VAR1, VAR2,
    hljs.HASH_COMMENT_MODE,
    COMMENT,
    {
      className: 'comment',
      begin: '^\\=\\w', end: '\\=cut', endsWithParent: true
    },
    METHOD,
    {
      className: 'string',
      begin: 'q[qwxr]?\\s*\\(', end: '\\)',
      contains: STRING_CONTAINS,
      relevance: 5
    },
    {
      className: 'string',
      begin: 'q[qwxr]?\\s*\\[', end: '\\]',
      contains: STRING_CONTAINS,
      relevance: 5
    },
    {
      className: 'string',
      begin: 'q[qwxr]?\\s*\\{', end: '\\}',
      contains: STRING_CONTAINS,
      relevance: 5
    },
    {
      className: 'string',
      begin: 'q[qwxr]?\\s*\\|', end: '\\|',
      contains: STRING_CONTAINS,
      relevance: 5
    },
    {
      className: 'string',
      begin: 'q[qwxr]?\\s*\\<', end: '\\>',
      contains: STRING_CONTAINS,
      relevance: 5
    },
    {
      className: 'string',
      begin: 'qw\\s+q', end: 'q',
      contains: STRING_CONTAINS,
      relevance: 5
    },
    {
      className: 'string',
      begin: '\'', end: '\'',
      contains: [hljs.BACKSLASH_ESCAPE],
      relevance: 0
    },
    {
      className: 'string',
      begin: '"', end: '"',
      contains: STRING_CONTAINS,
      relevance: 0
    },
    {
      className: 'string',
      begin: '`', end: '`',
      contains: [hljs.BACKSLASH_ESCAPE]
    },
    {
      className: 'string',
      begin: '{\\w+}',
      relevance: 0
    },
    {
      className: 'string',
      begin: '\-?\\w+\\s*\\=\\>',
      relevance: 0
    },
    {
      className: 'number',
      begin: '(\\b0[0-7_]+)|(\\b0x[0-9a-fA-F_]+)|(\\b[1-9][0-9_]*(\\.[0-9_]+)?)|[0_]\\b',
      relevance: 0
    },
    { // regexp container
      begin: '(' + hljs.RE_STARTERS_RE + '|\\b(split|return|print|reverse|grep)\\b)\\s*',
      keywords: 'split return print reverse grep',
      relevance: 0,
      contains: [
        hljs.HASH_COMMENT_MODE,
        COMMENT,
        {
          className: 'regexp',
          begin: '(s|tr|y)/(\\\\.|[^/])*/(\\\\.|[^/])*/[a-z]*',
          relevance: 10
        },
        {
          className: 'regexp',
          begin: '(m|qr)?/', end: '/[a-z]*',
          contains: [hljs.BACKSLASH_ESCAPE],
          relevance: 0 // allows empty "//" which is a common comment delimiter in other languages
        }
      ]
    },
    {
      className: 'sub',
      beginWithKeyword: true, end: '(\\s*\\(.*?\\))?[;{]',
      keywords: 'sub',
      relevance: 5
    },
    {
      className: 'operator',
      begin: '-\\w\\b',
      relevance: 0
    }
  ];
  SUBST.contains = PERL_DEFAULT_CONTAINS;
  METHOD.contains[1].contains = PERL_DEFAULT_CONTAINS;

  return {
    keywords: PERL_KEYWORDS,
    contains: PERL_DEFAULT_CONTAINS
  };
};